## What changes were proposed in this pull request?
"StandaloneSchedulerBackend.dead" is called in a RPC thread, so it should not call "SparkContext.stop" in the same thread. "SparkContext.stop" will block until all RPC threads exit, if it's called inside a RPC thread, it will be dead-lock.
This PR add a thread local flag inside RPC threads. `SparkContext.stop` uses it to decide if launching a new thread to stop the SparkContext.
## How was this patch tested?
Jenkins
Author: Shixiong Zhu <shixiong@databricks.com>
Closes#15775 from zsxwing/SPARK-18280.
## What changes were proposed in this pull request?
This PR port RDD API to use commit protocol, the changes made here:
1. Add new internal helper class that saves an RDD using a Hadoop OutputFormat named `SparkNewHadoopWriter`, it's similar with `SparkHadoopWriter` but uses commit protocol. This class supports the newer `mapreduce` API, instead of the old `mapred` API which is supported by `SparkHadoopWriter`;
2. Rewrite `PairRDDFunctions.saveAsNewAPIHadoopDataset` function, so it uses commit protocol now.
## How was this patch tested?
Exsiting test cases.
Author: jiangxingbo <jiangxb1987@gmail.com>
Closes#15769 from jiangxb1987/rdd-commit.
## What changes were proposed in this pull request?
When profiling heap dumps from the HistoryServer and live Spark web UIs, I found a large amount of memory being wasted on duplicated objects and strings. This patch's changes remove most of this duplication, resulting in over 40% memory savings for some benchmarks.
- **Task metrics** (6441f0624dfcda9c7193a64bfb416a145b5aabdf): previously, every `TaskUIData` object would have its own instances of `InputMetricsUIData`, `OutputMetricsUIData`, `ShuffleReadMetrics`, and `ShuffleWriteMetrics`, but for many tasks these metrics are irrelevant because they're all zero. This patch changes how we construct these metrics in order to re-use a single immutable "empty" value for the cases where these metrics are empty.
- **TaskInfo.accumulables** (ade86db901127bf13c0e0bdc3f09c933a093bb76): Previously, every `TaskInfo` object had its own empty `ListBuffer` for holding updates from named accumulators. Tasks which didn't use named accumulators still paid for the cost of allocating and storing this empty buffer. To avoid this overhead, I changed the `val` with a mutable buffer into a `var` which holds an immutable Scala list, allowing tasks which do not have named accumulator updates to share the same singleton `Nil` object.
- **String.intern() in JSONProtocol** (7e05630e9a78c455db8c8c499f0590c864624e05): in the HistoryServer, executor hostnames and ids are deserialized from JSON, leading to massive duplication of these string objects. By calling `String.intern()` on the deserialized values we can remove all of this duplication. Since Spark now requires Java 7+ we don't have to worry about string interning exhausting the permgen (see http://java-performance.info/string-intern-in-java-6-7-8/).
## How was this patch tested?
I ran
```
sc.parallelize(1 to 100000, 100000).count()
```
in `spark-shell` with event logging enabled, then loaded that event log in the HistoryServer, performed a full GC, and took a heap dump. According to YourKit, the changes in this patch reduced memory consumption by roughly 28 megabytes (or 770k Java objects):
Here's a table illustrating the drop in objects due to deduplication (the drop is <100k for some objects because some events were dropped from the listener bus; this is a separate, existing bug that I'll address separately after CPU-profiling):
Author: Josh Rosen <joshrosen@databricks.com>
Closes#15743 from JoshRosen/spark-ui-memory-usage.
## What changes were proposed in this pull request?
Close `FileStreams`, `ZipFiles` etc to release the resources after using. Not closing the resources will cause IO Exception to be raised while deleting temp files.
## How was this patch tested?
Existing tests
Author: U-FAREAST\tl <tl@microsoft.com>
Author: hyukjinkwon <gurwls223@gmail.com>
Author: Tao LI <tl@microsoft.com>
Closes#15618 from HyukjinKwon/SPARK-14914-1.
## What changes were proposed in this pull request?
[SPARK-18200](https://issues.apache.org/jira/browse/SPARK-18200) reports Apache Spark 2.x raises `java.lang.IllegalArgumentException: requirement failed: Invalid initial capacity` while running `triangleCount`. The root cause is that `VertexSet`, a type alias of `OpenHashSet`, does not allow zero as a initial size. This PR loosens the restriction to allow zero.
## How was this patch tested?
Pass the Jenkins test with a new test case in `OpenHashSetSuite`.
Author: Dongjoon Hyun <dongjoon@apache.org>
Closes#15741 from dongjoon-hyun/SPARK-18200.
## What changes were proposed in this pull request?
Fix `Locale.US` for all usages of `DateFormat`, `NumberFormat`
## How was this patch tested?
Existing tests.
Author: Sean Owen <sowen@cloudera.com>
Closes#15610 from srowen/SPARK-18076.
## What changes were proposed in this pull request?
Removing `appUIAddress` attribute since it is no longer in use.
## How was this patch tested?
Local build
Author: Jacek Laskowski <jacek@japila.pl>
Closes#15603 from jaceklaskowski/sparkui-fixes.
## What changes were proposed in this pull request?
While learning core scheduler code, I found two lines of wrong comments. This PR simply corrects the comments.
## How was this patch tested?
Author: wm624@hotmail.com <wm624@hotmail.com>
Closes#15631 from wangmiao1981/Rbug.
## What changes were proposed in this pull request?
(Please fill in changes proposed in this fix)
`Utils.getIteratorZipWithIndex` was added to deal with number of records > 2147483647 in one partition.
method `getIteratorZipWithIndex` accepts `startIndex` < 0, which leads to negative index.
This PR just adds a defensive check on `startIndex` to make sure it is >= 0.
## How was this patch tested?
Add a new unit test.
Author: Miao Wang <miaowang@Miaos-MacBook-Pro.local>
Closes#15639 from wangmiao1981/zip.
## What changes were proposed in this pull request?
[SPARK-16757](https://issues.apache.org/jira/browse/SPARK-16757) sets the hadoop `CallerContext` when calling hadoop/hdfs apis to make spark applications more diagnosable in hadoop/hdfs logs. However, the `org.apache.hadoop.ipc.CallerContext` class is only added since [hadoop 2.8](https://issues.apache.org/jira/browse/HDFS-9184), which is not officially releaed yet. So each time `utils.CallerContext.setCurrentContext()` is called (e.g [when a task is created](https://github.com/apache/spark/blob/b678e46/core/src/main/scala/org/apache/spark/scheduler/Task.scala#L95-L96)), a "java.lang.ClassNotFoundException: org.apache.hadoop.ipc.CallerContext"
error is logged, which pollutes the spark logs when there are lots of tasks.
This patch improves this behaviour by only logging the `ClassNotFoundException` once.
## How was this patch tested?
Existing tests.
Author: Shuai Lin <linshuai2012@gmail.com>
Closes#15377 from lins05/spark-17802-improve-callercontext-logging.
## What changes were proposed in this pull request?
Currently users can kill stages via the web ui but not jobs directly (jobs are killed if one of their stages is). I've added the ability to kill jobs via the web ui. This code change is based on #4823 by lianhuiwang and updated to work with the latest code matching how stages are currently killed. In general I've copied the kill stage code warning and note comments and all. I also updated applicable tests and documentation.
## How was this patch tested?
Manually tested and dev/run-tests
Author: Alex Bozarth <ajbozart@us.ibm.com>
Author: Lianhui Wang <lianhuiwang09@gmail.com>
Closes#15441 from ajbozarth/spark4411.
spark history server log needs to be fixed to show https url when ssl is enabled
Author: chie8842 <chie@chie-no-Mac-mini.local>
Closes#15611 from hayashidac/SPARK-16988.
The named parameter in an overridden class isn't supported in Scala 2.10 so was breaking the build.
cc zsxwing
Author: Kay Ousterhout <kayousterhout@gmail.com>
Closes#15617 from kayousterhout/hotfix.
`TaskSetManager` should have unique name to avoid adding duplicate ones to parent `Pool` via `SchedulableBuilder`. This problem has been surfaced with following discussion: [[PR: Avoid adding duplicate schedulables]](https://github.com/apache/spark/pull/15326)
**Proposal** :
There is 1x1 relationship between `stageAttemptId` and `TaskSetManager` so `taskSet.Id` covering both `stageId` and `stageAttemptId` looks to be used for uniqueness of `TaskSetManager` name instead of just `stageId`.
**Current TaskSetManager Name** :
`var name = "TaskSet_" + taskSet.stageId.toString`
**Sample**: TaskSet_0
**Proposed TaskSetManager Name** :
`val name = "TaskSet_" + taskSet.Id ` `// taskSet.Id = (stageId + "." + stageAttemptId)`
**Sample** : TaskSet_0.0
Added new Unit Test.
Author: erenavsarogullari <erenavsarogullari@gmail.com>
Closes#15463 from erenavsarogullari/SPARK-17894.
## What changes were proposed in this pull request?
`Array[T]()` -> `Array.empty[T]` to avoid allocating 0-length arrays.
Use regex `find . -name '*.scala' | xargs -i bash -c 'egrep "Array\[[A-Za-z]+\]\(\)" -n {} && echo {}'` to find modification candidates.
cc srowen
## How was this patch tested?
existing tests
Author: Zheng RuiFeng <ruifengz@foxmail.com>
Closes#15564 from zhengruifeng/avoid_0_length_array.
## What changes were proposed in this pull request?
- Fix bug of RDD `zipWithIndex` generating wrong result when one partition contains more than 2147483647 records.
- Fix bug of RDD `zipWithUniqueId` generating wrong result when one partition contains more than 2147483647 records.
## How was this patch tested?
test added.
Author: WeichenXu <WeichenXu123@outlook.com>
Closes#15550 from WeichenXu123/fix_rdd_zipWithIndex_overflow.
## What changes were proposed in this pull request?
This PR adds support for executor log compression.
## How was this patch tested?
Unit tests
cc: yhuai tdas mengxr
Author: Yu Peng <loneknightpy@gmail.com>
Closes#15285 from loneknightpy/compress-executor-log.
## What changes were proposed in this pull request?
Currently we use BufferedInputStream to read the shuffle file which copies the file content from os buffer cache to the user buffer. This adds additional latency in reading the spill files. We made a change to use java nio's direct buffer to read the spill files and for certain pipelines spilling significant amount of data, we see up to 7% speedup for the entire pipeline.
## How was this patch tested?
Tested by running the job in the cluster and observed up to 7% speedup.
Author: Sital Kedia <skedia@fb.com>
Closes#15408 from sitalkedia/skedia/nio_spill_read.
This reverts commit ed14633414.
The patch merged had obvious quality and documentation issue. The idea is useful, and we should work towards improving its quality and merging it in again.
## What changes were proposed in this pull request?
Restructure the code and implement two new task assigner.
PackedAssigner: try to allocate tasks to the executors with least available cores, so that spark can release reserved executors when dynamic allocation is enabled.
BalancedAssigner: try to allocate tasks to the executors with more available cores in order to balance the workload across all executors.
By default, the original round robin assigner is used.
We test a pipeline, and new PackedAssigner save around 45% regarding the reserved cpu and memory with dynamic allocation enabled.
## How was this patch tested?
(Please explain how this patch was tested. E.g. unit tests, integration tests, manual tests)
Both unit test in TaskSchedulerImplSuite and manual tests in production pipeline.
Author: Zhan Zhang <zhanzhang@fb.com>
Closes#15218 from zhzhan/packed-scheduler.
## What changes were proposed in this pull request?
This is a step along the way to SPARK-8425.
To enable incremental review, the first step proposed here is to expand the blacklisting within tasksets. In particular, this will enable blacklisting for
* (task, executor) pairs (this already exists via an undocumented config)
* (task, node)
* (taskset, executor)
* (taskset, node)
Adding (task, node) is critical to making spark fault-tolerant of one-bad disk in a cluster, without requiring careful tuning of "spark.task.maxFailures". The other additions are also important to avoid many misleading task failures and long scheduling delays when there is one bad node on a large cluster.
Note that some of the code changes here aren't really required for just this -- they put pieces in place for SPARK-8425 even though they are not used yet (eg. the `BlacklistTracker` helper is a little out of place, `TaskSetBlacklist` holds onto a little more info than it needs to for just this change, and `ExecutorFailuresInTaskSet` is more complex than it needs to be).
## How was this patch tested?
Added unit tests, run tests via jenkins.
Author: Imran Rashid <irashid@cloudera.com>
Author: mwws <wei.mao@intel.com>
Closes#15249 from squito/taskset_blacklist_only.
## What changes were proposed in this pull request?
Add a flag to ignore corrupt files. For Spark core, the configuration is `spark.files.ignoreCorruptFiles`. For Spark SQL, it's `spark.sql.files.ignoreCorruptFiles`.
## How was this patch tested?
The added unit tests
Author: Shixiong Zhu <shixiong@databricks.com>
Closes#15422 from zsxwing/SPARK-17850.
## What changes were proposed in this pull request?
This PR modified the test case `test("script")` to use resource path for `test_script.sh`. Make the test case portable (even in IntelliJ).
## How was this patch tested?
Passed the test case.
Before:
Run `test("script")` in IntelliJ:
```
Caused by: org.apache.spark.SparkException: Subprocess exited with status 127. Error: bash: src/test/resources/test_script.sh: No such file or directory
```
After:
Test passed.
Author: Weiqing Yang <yangweiqing001@gmail.com>
Closes#15246 from weiqingy/hivetest.
## What changes were proposed in this pull request?
Fix:
- GroupedMeanEvaluator and GroupedSumEvaluator are unused, as is the StudentTCacher support class
- CountEvaluator can return a lower bound < 0, when counts can't be negative
- MeanEvaluator will actually fail on exactly 1 datum (yields t-test with 0 DOF)
- CountEvaluator uses a normal distribution, which may be an inappropriate approximation (leading to above)
- Test for SumEvaluator asserts incorrect expected sums – e.g. after observing 10% of data has sum of 2, expectation should be 20, not 38
- CountEvaluator, MeanEvaluator have no unit tests to catch these
- Duplication of distribution code across CountEvaluator, GroupedCountEvaluator
- The stats in each could use a bit of documentation as I had to guess at them
- (Code could use a few cleanups and optimizations too)
## How was this patch tested?
Existing and new tests
Author: Sean Owen <sowen@cloudera.com>
Closes#15341 from srowen/SPARK-17768.
## What changes were proposed in this pull request?
Mock SparkContext to reduce memory usage of BlockManagerSuite
## How was this patch tested?
Jenkins
Author: Shixiong Zhu <shixiong@databricks.com>
Closes#15350 from zsxwing/SPARK-17778.
## What changes were proposed in this pull request?
Return Iterator of applications internally in history server, for consistency and performance. See https://github.com/apache/spark/pull/15248 for some back-story.
The code called by and calling HistoryServer.getApplicationList wants an Iterator, but this method materializes an Iterable, which potentially causes a performance problem. It's simpler too to make this internal method also pass through an Iterator.
## How was this patch tested?
Existing tests.
Author: Sean Owen <sowen@cloudera.com>
Closes#15321 from srowen/SPARK-17671.
## What changes were proposed in this pull request?
This PR proposes to fix/skip some tests failed on Windows. This PR takes over https://github.com/apache/spark/pull/12696.
**Before**
- **SparkSubmitSuite**
```
[info] - launch simple application with spark-submit *** FAILED *** (202 milliseconds)
[info] java.io.IOException: Cannot run program "./bin/spark-submit" (in directory "C:\projects\spark"): CreateProcess error=2, The system cannot find the file specifie
[info] - includes jars passed in through --jars *** FAILED *** (1 second, 625 milliseconds)
[info] java.io.IOException: Cannot run program "./bin/spark-submit" (in directory "C:\projects\spark"): CreateProcess error=2, The system cannot find the file specified
```
- **DiskStoreSuite**
```
[info] - reads of memory-mapped and non memory-mapped files are equivalent *** FAILED *** (1 second, 78 milliseconds)
[info] diskStoreMapped.remove(blockId) was false (DiskStoreSuite.scala:41)
```
**After**
- **SparkSubmitSuite**
```
[info] - launch simple application with spark-submit (578 milliseconds)
[info] - includes jars passed in through --jars (1 second, 875 milliseconds)
```
- **DiskStoreSuite**
```
[info] DiskStoreSuite:
[info] - reads of memory-mapped and non memory-mapped files are equivalent !!! CANCELED !!! (766 milliseconds
```
For `CreateTableAsSelectSuite` and `FsHistoryProviderSuite`, I could not reproduce as the Java version seems higher than the one that has the bugs about `setReadable(..)` and `setWritable(...)` but as they are bugs reported clearly, it'd be sensible to skip those. We should revert the changes for both back as soon as we drop the support of Java 7.
## How was this patch tested?
Manually tested via AppVeyor.
Closes#12696
Author: Tao LI <tl@microsoft.com>
Author: U-FAREAST\tl <tl@microsoft.com>
Author: hyukjinkwon <gurwls223@gmail.com>
Closes#15320 from HyukjinKwon/SPARK-14914.
## What changes were proposed in this pull request?
As a followup to SPARK-17666, ensure filesystem connections are not leaked at least in unit tests. This is done here by intercepting filesystem calls as suggested by JoshRosen . At the end of each test, we assert no filesystem streams are left open.
This applies to all tests using SharedSQLContext or SharedSparkContext.
## How was this patch tested?
I verified that tests in sql and core are indeed using the filesystem backend, and fixed the detected leaks. I also checked that reverting https://github.com/apache/spark/pull/15245 causes many actual test failures due to connection leaks.
Author: Eric Liang <ekl@databricks.com>
Author: Eric Liang <ekhliang@gmail.com>
Closes#15306 from ericl/sc-4672.
## What changes were proposed in this pull request?
This PR makes block replication strategies pluggable. It provides two trait that can be implemented, one that maps a host to its topology and is used in the master, and the second that helps prioritize a list of peers for block replication and would run in the executors.
This patch contains default implementations of these traits that make sure current Spark behavior is unchanged.
## How was this patch tested?
This patch should not change Spark behavior in any way, and was tested with unit tests for storage.
Author: Shubham Chopra <schopra31@bloomberg.net>
Closes#13152 from shubhamchopra/RackAwareBlockReplication.
## What changes were proposed in this pull request?
FsHistoryProvider was writing a hidden file (to check the fs's clock).
Even though it deleted the file immediately, sometimes another thread
would try to scan the files on the fs in-between, and then there would
be an error msg logged which was very misleading for the end-user.
(The logged error was harmless, though.)
## How was this patch tested?
I added one unit test, but to be clear, that test was passing before. The actual change in behavior in that test is just logging (after the change, there is no more logged error), which I just manually verified.
Author: Imran Rashid <irashid@cloudera.com>
Closes#15250 from squito/SPARK-17676.
## What changes were proposed in this pull request?
The Seq[WorkerOffer] is accessed by index, so it really should be an
IndexedSeq, otherwise an O(n) operation becomes O(n^2). In practice
this hasn't been an issue b/c where these offers are generated, the call
to `.toSeq` just happens to create an IndexedSeq anyway.I got bitten by
this in performance tests I was doing, and its better for the types to be
more precise so eg. a change in Scala doesn't destroy performance.
## How was this patch tested?
Unit tests via jenkins.
Author: Imran Rashid <irashid@cloudera.com>
Closes#15221 from squito/SPARK-17648.
## What changes were proposed in this pull request?
| Time |Thread 1 , Job1 | Thread 2 , Job2 |
|:-------------:|:-------------:|:-----:|
| 1 | abort stage due to FetchFailed | |
| 2 | failedStages += failedStage | |
| 3 | | task failed due to FetchFailed |
| 4 | | can not post ResubmitFailedStages because failedStages is not empty |
Then job2 of thread2 never resubmit the failed stage and hang.
We should not add the failedStages when abortStage for fetch failure
## How was this patch tested?
added unit test
Author: w00228970 <wangfei1@huawei.com>
Author: wangfei <wangfei_hello@126.com>
Closes#15213 from scwf/dag-resubmit.
## What changes were proposed in this pull request?
1. Pass `jobId` to Task.
2. Invoke Hadoop APIs.
* A new function `setCallerContext` is added in `Utils`. `setCallerContext` function invokes APIs of `org.apache.hadoop.ipc.CallerContext` to set up spark caller contexts, which will be written into `hdfs-audit.log` and Yarn RM audit log.
* For HDFS: Spark sets up its caller context by invoking`org.apache.hadoop.ipc.CallerContext` in `Task` and Yarn `Client` and `ApplicationMaster`.
* For Yarn: Spark sets up its caller context by invoking `org.apache.hadoop.ipc.CallerContext` in Yarn `Client`.
## How was this patch tested?
Manual Tests against some Spark applications in Yarn client mode and Yarn cluster mode. Need to check if spark caller contexts are written into HDFS hdfs-audit.log and Yarn RM audit log successfully.
For example, run SparkKmeans in Yarn client mode:
```
./bin/spark-submit --verbose --executor-cores 3 --num-executors 1 --master yarn --deploy-mode client --class org.apache.spark.examples.SparkKMeans examples/target/original-spark-examples_2.11-2.1.0-SNAPSHOT.jar hdfs://localhost:9000/lr_big.txt 2 5
```
**Before**:
There will be no Spark caller context in records of `hdfs-audit.log` and Yarn RM audit log.
**After**:
Spark caller contexts will be written in records of `hdfs-audit.log` and Yarn RM audit log.
These are records in `hdfs-audit.log`:
```
2016-09-20 11:54:24,116 INFO FSNamesystem.audit: allowed=true ugi=wyang (auth:SIMPLE) ip=/127.0.0.1 cmd=open src=/lr_big.txt dst=null perm=null proto=rpc callerContext=SPARK_CLIENT_AppId_application_1474394339641_0005
2016-09-20 11:54:28,164 INFO FSNamesystem.audit: allowed=true ugi=wyang (auth:SIMPLE) ip=/127.0.0.1 cmd=open src=/lr_big.txt dst=null perm=null proto=rpc callerContext=SPARK_TASK_AppId_application_1474394339641_0005_JobId_0_StageId_0_AttemptId_0_TaskId_2_AttemptNum_0
2016-09-20 11:54:28,164 INFO FSNamesystem.audit: allowed=true ugi=wyang (auth:SIMPLE) ip=/127.0.0.1 cmd=open src=/lr_big.txt dst=null perm=null proto=rpc callerContext=SPARK_TASK_AppId_application_1474394339641_0005_JobId_0_StageId_0_AttemptId_0_TaskId_1_AttemptNum_0
2016-09-20 11:54:28,164 INFO FSNamesystem.audit: allowed=true ugi=wyang (auth:SIMPLE) ip=/127.0.0.1 cmd=open src=/lr_big.txt dst=null perm=null proto=rpc callerContext=SPARK_TASK_AppId_application_1474394339641_0005_JobId_0_StageId_0_AttemptId_0_TaskId_0_AttemptNum_0
```
```
2016-09-20 11:59:33,868 INFO FSNamesystem.audit: allowed=true ugi=wyang (auth:SIMPLE) ip=/127.0.0.1 cmd=mkdirs src=/private/tmp/hadoop-wyang/nm-local-dir/usercache/wyang/appcache/application_1474394339641_0006/container_1474394339641_0006_01_000001/spark-warehouse dst=null perm=wyang:supergroup:rwxr-xr-x proto=rpc callerContext=SPARK_APPLICATION_MASTER_AppId_application_1474394339641_0006_AttemptId_1
2016-09-20 11:59:37,214 INFO FSNamesystem.audit: allowed=true ugi=wyang (auth:SIMPLE) ip=/127.0.0.1 cmd=open src=/lr_big.txt dst=null perm=null proto=rpc callerContext=SPARK_TASK_AppId_application_1474394339641_0006_AttemptId_1_JobId_0_StageId_0_AttemptId_0_TaskId_1_AttemptNum_0
2016-09-20 11:59:37,215 INFO FSNamesystem.audit: allowed=true ugi=wyang (auth:SIMPLE) ip=/127.0.0.1 cmd=open src=/lr_big.txt dst=null perm=null proto=rpc callerContext=SPARK_TASK_AppId_application_1474394339641_0006_AttemptId_1_JobId_0_StageId_0_AttemptId_0_TaskId_2_AttemptNum_0
2016-09-20 11:59:37,215 INFO FSNamesystem.audit: allowed=true ugi=wyang (auth:SIMPLE) ip=/127.0.0.1 cmd=open src=/lr_big.txt dst=null perm=null proto=rpc callerContext=SPARK_TASK_AppId_application_1474394339641_0006_AttemptId_1_JobId_0_StageId_0_AttemptId_0_TaskId_0_AttemptNum_0
2016-09-20 11:59:42,391 INFO FSNamesystem.audit: allowed=true ugi=wyang (auth:SIMPLE) ip=/127.0.0.1 cmd=open src=/lr_big.txt dst=null perm=null proto=rpc callerContext=SPARK_TASK_AppId_application_1474394339641_0006_AttemptId_1_JobId_0_StageId_0_AttemptId_0_TaskId_3_AttemptNum_0
```
This is a record in Yarn RM log:
```
2016-09-20 11:59:24,050 INFO org.apache.hadoop.yarn.server.resourcemanager.RMAuditLogger: USER=wyang IP=127.0.0.1 OPERATION=Submit Application Request TARGET=ClientRMService RESULT=SUCCESS APPID=application_1474394339641_0006 CALLERCONTEXT=SPARK_CLIENT_AppId_application_1474394339641_0006
```
Author: Weiqing Yang <yangweiqing001@gmail.com>
Closes#14659 from Sherry302/callercontextSubmit.
## What changes were proposed in this pull request?
Fix two comments since Actor is not used anymore.
Author: Ding Fei <danis@danix>
Closes#15251 from danix800/comment-fixing.
## What changes were proposed in this pull request?
When a malformed URL was sent to Executors through `sc.addJar` and `sc.addFile`, the executors become unusable, because they constantly throw `MalformedURLException`s and can never acknowledge that the file or jar is just bad input.
This PR tries to fix that problem by making sure MalformedURLs can never be submitted through `sc.addJar` and `sc.addFile`. Another solution would be to blacklist bad files and jars on Executors. Maybe fail the first time, and then ignore the second time (but print a warning message).
## How was this patch tested?
Unit tests in SparkContextSuite
Author: Burak Yavuz <brkyvz@gmail.com>
Closes#15224 from brkyvz/SPARK-17650.
Currently task metrics don't support executor CPU time, so there's no way to calculate how much CPU time a stage/task took from History Server metrics. This PR enables reporting CPU time.
Author: jisookim <jisookim0513@gmail.com>
Closes#10212 from jisookim0513/add-cpu-time-metric.
## What changes were proposed in this pull request?
We are killing multiple executors together instead of iterating over expensive RPC calls to kill single executor.
## How was this patch tested?
Executed sample spark job to observe executors being killed/removed with dynamic allocation enabled.
Author: Dhruve Ashar <dashar@yahoo-inc.com>
Author: Dhruve Ashar <dhruveashar@gmail.com>
Closes#15152 from dhruve/impr/SPARK-17365.
## What changes were proposed in this pull request?
Yarn and mesos cluster mode support remote python path (HDFS/S3 scheme) by their own mechanism, it is not necessary to check and format the python when running on these modes. This is a potential regression compared to 1.6, so here propose to fix it.
## How was this patch tested?
Unit test to verify SparkSubmit arguments, also with local cluster verification. Because of lack of `MiniDFSCluster` support in Spark unit test, there's no integration test added.
Author: jerryshao <sshao@hortonworks.com>
Closes#15137 from jerryshao/SPARK-17512.
## What changes were proposed in this pull request?
In TaskResultGetter, enqueueFailedTask currently deserializes the result
as a TaskEndReason. But the type is actually more specific, its a
TaskFailedReason. This just leads to more blind casting later on – it
would be more clear if the msg was cast to the right type immediately,
so method parameter types could be tightened.
## How was this patch tested?
Existing unit tests via jenkins. Note that the code was already performing a blind-cast to a TaskFailedReason before in any case, just in a different spot, so there shouldn't be any behavior change.
Author: Imran Rashid <irashid@cloudera.com>
Closes#15181 from squito/SPARK-17623.
The goal of this feature is to allow the Spark driver to run in an
isolated environment, such as a docker container, and be able to use
the host's port forwarding mechanism to be able to accept connections
from the outside world.
The change is restricted to the driver: there is no support for achieving
the same thing on executors (or the YARN AM for that matter). Those still
need full access to the outside world so that, for example, connections
can be made to an executor's block manager.
The core of the change is simple: add a new configuration that tells what's
the address the driver should bind to, which can be different than the address
it advertises to executors (spark.driver.host). Everything else is plumbing
the new configuration where it's needed.
To use the feature, the host starting the container needs to set up the
driver's port range to fall into a range that is being forwarded; this
required the block manager port to need a special configuration just for
the driver, which falls back to the existing spark.blockManager.port when
not set. This way, users can modify the driver settings without affecting
the executors; it would theoretically be nice to also have different
retry counts for driver and executors, but given that docker (at least)
allows forwarding port ranges, we can probably live without that for now.
Because of the nature of the feature it's kinda hard to add unit tests;
I just added a simple one to make sure the configuration works.
This was tested with a docker image running spark-shell with the following
command:
docker blah blah blah \
-p 38000-38100:38000-38100 \
[image] \
spark-shell \
--num-executors 3 \
--conf spark.shuffle.service.enabled=false \
--conf spark.dynamicAllocation.enabled=false \
--conf spark.driver.host=[host's address] \
--conf spark.driver.port=38000 \
--conf spark.driver.blockManager.port=38020 \
--conf spark.ui.port=38040
Running on YARN; verified the driver works, executors start up and listen
on ephemeral ports (instead of using the driver's config), and that caching
and shuffling (without the shuffle service) works. Clicked through the UI
to make sure all pages (including executor thread dumps) worked. Also tested
apps without docker, and ran unit tests.
Author: Marcelo Vanzin <vanzin@cloudera.com>
Closes#15120 from vanzin/SPARK-4563.
## What changes were proposed in this pull request?
`MemoryStore.putIteratorAsBytes()` may silently lose values when used with `KryoSerializer` because it does not properly close the serialization stream before attempting to deserialize the already-serialized values, which may cause values buffered in Kryo's internal buffers to not be read.
This is the root cause behind a user-reported "wrong answer" bug in PySpark caching reported by bennoleslie on the Spark user mailing list in a thread titled "pyspark persist MEMORY_ONLY vs MEMORY_AND_DISK". Due to Spark 2.0's automatic use of KryoSerializer for "safe" types (such as byte arrays, primitives, etc.) this misuse of serializers manifested itself as silent data corruption rather than a StreamCorrupted error (which you might get from JavaSerializer).
The minimal fix, implemented here, is to close the serialization stream before attempting to deserialize written values. In addition, this patch adds several additional assertions / precondition checks to prevent misuse of `PartiallySerializedBlock` and `ChunkedByteBufferOutputStream`.
## How was this patch tested?
The original bug was masked by an invalid assert in the memory store test cases: the old assert compared two results record-by-record with `zip` but didn't first check that the lengths of the two collections were equal, causing missing records to go unnoticed. The updated test case reproduced this bug.
In addition, I added a new `PartiallySerializedBlockSuite` to unit test that component.
Author: Josh Rosen <joshrosen@databricks.com>
Closes#15043 from JoshRosen/partially-serialized-block-values-iterator-bugfix.
## What changes were proposed in this pull request?
Add a clearUntil() method on BitSet (adapted from the pre-existing setUntil() method).
Use this method to clear the subset of the BitSet which needs to be used during merge joins.
## How was this patch tested?
dev/run-tests, as well as performance tests on skewed data as described in jira.
I expect there to be a small local performance hit using BitSet.clearUntil rather than BitSet.clear for normally shaped (unskewed) joins (additional read on the last long). This is expected to be de-minimis and was not specifically tested.
Author: David Navas <davidn@clearstorydata.com>
Closes#15084 from davidnavas/bitSet.
## What changes were proposed in this pull request?
If a BlockManager `put()` call failed after the BlockManagerMaster was notified of a block's availability then incomplete cleanup logic in a `finally` block would never send a second block status method to inform the master of the block's unavailability. This, in turn, leads to fetch failures and used to be capable of causing complete job failures before #15037 was fixed.
This patch addresses this issue via multiple small changes:
- The `finally` block now calls `removeBlockInternal` when cleaning up from a failed `put()`; in addition to removing the `BlockInfo` entry (which was _all_ that the old cleanup logic did), this code (redundantly) tries to remove the block from the memory and disk stores (as an added layer of defense against bugs lower down in the stack) and optionally notifies the master of block removal (which now happens during exception-triggered cleanup).
- When a BlockManager receives a request for a block that it does not have it will now notify the master to update its block locations. This ensures that bad metadata pointing to non-existent blocks will eventually be fixed. Note that I could have implemented this logic in the block manager client (rather than in the remote server), but that would introduce the problem of distinguishing between transient and permanent failures; on the server, however, we know definitively that the block isn't present.
- Catch `NonFatal` instead of `Exception` to avoid swallowing `InterruptedException`s thrown from synchronous block replication calls.
This patch depends upon the refactorings in #15036, so that other patch will also have to be backported when backporting this fix.
For more background on this issue, including example logs from a real production failure, see [SPARK-17484](https://issues.apache.org/jira/browse/SPARK-17484).
## How was this patch tested?
Two new regression tests in BlockManagerSuite.
Author: Josh Rosen <joshrosen@databricks.com>
Closes#15085 from JoshRosen/SPARK-17484.
## What changes were proposed in this pull request?
Make CollectionAccumulator and SetAccumulator's value can be read thread-safely to fix the ConcurrentModificationException reported in [JIRA](https://issues.apache.org/jira/browse/SPARK-17463).
## How was this patch tested?
Existing tests.
Author: Shixiong Zhu <shixiong@databricks.com>
Closes#15063 from zsxwing/SPARK-17463.
## What changes were proposed in this pull request?
Currently, ORDER BY clause returns nulls value according to sorting order (ASC|DESC), considering null value is always smaller than non-null values.
However, SQL2003 standard support NULLS FIRST or NULLS LAST to allow users to specify whether null values should be returned first or last, regardless of sorting order (ASC|DESC).
This PR is to support this new feature.
## How was this patch tested?
New test cases are added to test NULLS FIRST|LAST for regular select queries and windowing queries.
(If this patch involves UI changes, please attach a screenshot; otherwise, remove this)
Author: Xin Wu <xinwu@us.ibm.com>
Closes#14842 from xwu0226/SPARK-10747.
## What changes were proposed in this pull request?
In Spark's `RDD.getOrCompute` we first try to read a local copy of a cached RDD block, then a remote copy, and only fall back to recomputing the block if no cached copy (local or remote) can be read. This logic works correctly in the case where no remote copies of the block exist, but if there _are_ remote copies and reads of those copies fail (due to network issues or internal Spark bugs) then the BlockManager will throw a `BlockFetchException` that will fail the task (and which could possibly fail the whole job if the read failures keep occurring).
In the cases of TorrentBroadcast and task result fetching we really do want to fail the entire job in case no remote blocks can be fetched, but this logic is inappropriate for reads of cached RDD blocks because those can/should be recomputed in case cached blocks are unavailable.
Therefore, I think that the `BlockManager.getRemoteBytes()` method should never throw on remote fetch errors and, instead, should handle failures by returning `None`.
## How was this patch tested?
Block manager changes should be covered by modified tests in `BlockManagerSuite`: the old tests expected exceptions to be thrown on failed remote reads, while the modified tests now expect `None` to be returned from the `getRemote*` method.
I also manually inspected all usages of `BlockManager.getRemoteValues()`, `getRemoteBytes()`, and `get()` to verify that they correctly pattern-match on the result and handle `None`. Note that these `None` branches are already exercised because the old `getRemoteBytes` returned `None` when no remote locations for the block could be found (which could occur if an executor died and its block manager de-registered with the master).
Author: Josh Rosen <joshrosen@databricks.com>
Closes#15037 from JoshRosen/SPARK-17485.
## What changes were proposed in this pull request?
MemoryStore may throw OutOfMemoryError when trying to cache a super big RDD that cannot fit in memory.
```
scala> sc.parallelize(1 to 1000000000, 100).map(x => new Array[Long](1000)).cache().count()
java.lang.OutOfMemoryError: Java heap space
at $line14.$read$$iw$$iw$$iw$$iw$$iw$$iw$$iw$$iw$$anonfun$1.apply(<console>:24)
at $line14.$read$$iw$$iw$$iw$$iw$$iw$$iw$$iw$$iw$$anonfun$1.apply(<console>:23)
at scala.collection.Iterator$$anon$11.next(Iterator.scala:409)
at scala.collection.Iterator$JoinIterator.next(Iterator.scala:232)
at org.apache.spark.storage.memory.PartiallyUnrolledIterator.next(MemoryStore.scala:683)
at org.apache.spark.InterruptibleIterator.next(InterruptibleIterator.scala:43)
at org.apache.spark.util.Utils$.getIteratorSize(Utils.scala:1684)
at org.apache.spark.rdd.RDD$$anonfun$count$1.apply(RDD.scala:1134)
at org.apache.spark.rdd.RDD$$anonfun$count$1.apply(RDD.scala:1134)
at org.apache.spark.SparkContext$$anonfun$runJob$5.apply(SparkContext.scala:1915)
at org.apache.spark.SparkContext$$anonfun$runJob$5.apply(SparkContext.scala:1915)
at org.apache.spark.scheduler.ResultTask.runTask(ResultTask.scala:70)
at org.apache.spark.scheduler.Task.run(Task.scala:86)
at org.apache.spark.executor.Executor$TaskRunner.run(Executor.scala:274)
at java.util.concurrent.ThreadPoolExecutor.runWorker(ThreadPoolExecutor.java:1142)
at java.util.concurrent.ThreadPoolExecutor$Worker.run(ThreadPoolExecutor.java:617)
at java.lang.Thread.run(Thread.java:745)
```
Spark MemoryStore uses SizeTrackingVector as a temporary unrolling buffer to store all input values that it has read so far before transferring the values to storage memory cache. The problem is that when the input RDD is too big for caching in memory, the temporary unrolling memory SizeTrackingVector is not garbage collected in time. As SizeTrackingVector can occupy all available storage memory, it may cause the executor JVM to run out of memory quickly.
More info can be found at https://issues.apache.org/jira/browse/SPARK-17503
## How was this patch tested?
Unit test and manual test.
### Before change
Heap memory consumption
<img width="702" alt="screen shot 2016-09-12 at 4 16 15 pm" src="https://cloud.githubusercontent.com/assets/2595532/18429524/60d73a26-7906-11e6-9768-6f286f5c58c8.png">
Heap dump
<img width="1402" alt="screen shot 2016-09-12 at 4 34 19 pm" src="https://cloud.githubusercontent.com/assets/2595532/18429577/cbc1ef20-7906-11e6-847b-b5903f450b3b.png">
### After change
Heap memory consumption
<img width="706" alt="screen shot 2016-09-12 at 4 29 10 pm" src="https://cloud.githubusercontent.com/assets/2595532/18429503/4abe9342-7906-11e6-844a-b2f815072624.png">
Author: Sean Zhong <seanzhong@databricks.com>
Closes#15056 from clockfly/memory_store_leak.
## What changes were proposed in this pull request?
This patch adds methods for extracting major and minor versions as Int types in Scala from a Spark version string.
Motivation: There are many hacks within Spark's codebase to identify and compare Spark versions. We should add a simple utility to standardize these code paths, especially since there have been mistakes made in the past. This will let us add unit tests as well. Currently, I want this functionality to check Spark versions to provide backwards compatibility for ML model persistence.
## How was this patch tested?
Unit tests
Author: Joseph K. Bradley <joseph@databricks.com>
Closes#15017 from jkbradley/version-parsing.
## What changes were proposed in this pull request?
This pull request adds the functionality to enable accessing worker and application UI through master UI itself. Thus helps in accessing SparkUI when running spark cluster in closed networks e.g. Kubernetes. Cluster admin needs to expose only spark master UI and rest of the UIs can be in the private network, master UI will reverse proxy the connection request to corresponding resource. It adds the path for workers/application UIs as
WorkerUI: <http/https>://master-publicIP:<port>/target/workerID/
ApplicationUI: <http/https>://master-publicIP:<port>/target/appID/
This makes it easy for users to easily protect the Spark master cluster access by putting some reverse proxy e.g. https://github.com/bitly/oauth2_proxy
## How was this patch tested?
The functionality has been tested manually and there is a unit test too for testing access to worker UI with reverse proxy address.
pwendell bomeng BryanCutler can you please review it, thanks.
Author: Gurvinder Singh <gurvinder.singh@uninett.no>
Closes#13950 from gurvindersingh/rproxy.
## What changes were proposed in this pull request?
DAGScheduler invalidates shuffle files when an executor loss event occurs, but not when the external shuffle service is enabled. This is because when shuffle service is on, the shuffle file lifetime can exceed the executor lifetime.
However, it also doesn't invalidate shuffle files when the shuffle service itself is lost (due to whole slave loss). This can cause long hangs when slaves are lost since the file loss is not detected until a subsequent stage attempts to read the shuffle files.
The proposed fix is to also invalidate shuffle files when an executor is lost due to a `SlaveLost` event.
## How was this patch tested?
Unit tests, also verified on an actual cluster that slave loss invalidates shuffle files immediately as expected.
cc mateiz
Author: Eric Liang <ekl@databricks.com>
Closes#14931 from ericl/sc-4439.
## What changes were proposed in this pull request?
We should generally use `ArrayBuffer.+=(A)` rather than `ArrayBuffer.append(A)`, because `append(A)` would involve extra boxing / unboxing.
## How was this patch tested?
N/A
Author: Liwei Lin <lwlin7@gmail.com>
Closes#14914 from lw-lin/append_to_plus_eq_v2.
## What changes were proposed in this pull request?
This patch fixes a `java.io.StreamCorruptedException` error affecting remote reads of cached values when certain data types are used. The problem stems from #11801 / SPARK-13990, a patch to have Spark automatically pick the "best" serializer when caching RDDs. If PySpark cached a PythonRDD, then this would be cached as an `RDD[Array[Byte]]` and the automatic serializer selection would pick KryoSerializer for replication and block transfer. However, the `getRemoteValues()` / `getRemoteBytes()` code path did not pass proper class tags in order to enable the same serializer to be used during deserialization, causing Java to be inappropriately used instead of Kryo, leading to the StreamCorruptedException.
We already fixed a similar bug in #14311, which dealt with similar issues in block replication. Prior to that patch, it seems that we had no tests to ensure that block replication actually succeeded. Similarly, prior to this bug fix patch it looks like we had no tests to perform remote reads of cached data, which is why this bug was able to remain latent for so long.
This patch addresses the bug by modifying `BlockManager`'s `get()` and `getRemoteValues()` methods to accept ClassTags, allowing the proper class tag to be threaded in the `getOrElseUpdate` code path (which is used by `rdd.iterator`)
## How was this patch tested?
Extended the caching tests in `DistributedSuite` to exercise the `getRemoteValues` path, plus manual testing to verify that the PySpark bug reproduction in SPARK-17110 is fixed.
Author: Josh Rosen <joshrosen@databricks.com>
Closes#14952 from JoshRosen/SPARK-17110.
## What changes were proposed in this pull request?
This pull request reverts the changes made as a part of #14605, which simply side-steps the deadlock issue. Instead, I propose the following approach:
* Use `scheduleWithFixedDelay` when calling `ExecutorAllocationManager.schedule` for scheduling executor requests. The intent of this is that if invocations are delayed beyond the default schedule interval on account of lock contention, then we avoid a situation where calls to `schedule` are made back-to-back, potentially releasing and then immediately reacquiring these locks - further exacerbating contention.
* Replace a number of calls to `askWithRetry` with `ask` inside of message handling code in `CoarseGrainedSchedulerBackend` and its ilk. This allows us queue messages with the relevant endpoints, release whatever locks we might be holding, and then block whilst awaiting the response. This change is made at the cost of being able to retry should sending the message fail, as retrying outside of the lock could easily cause race conditions if other conflicting messages have been sent whilst awaiting a response. I believe this to be the lesser of two evils, as in many cases these RPC calls are to process local components, and so failures are more likely to be deterministic, and timeouts are more likely to be caused by lock contention.
## How was this patch tested?
Existing tests, and manual tests under yarn-client mode.
Author: Angus Gerry <angolon@gmail.com>
Closes#14710 from angolon/SPARK-16533.
## What changes were proposed in this pull request?
With the new History Server the summary page loads the application list via the the REST API, this makes it very slow to impossible to load with large (10K+) application history. This pr fixes this by adding the `spark.history.ui.maxApplications` conf to limit the number of applications the History Server displays. This is accomplished using a new optional `limit` param for the `applications` api. (Note this only applies to what the summary page displays, all the Application UI's are still accessible if the user knows the App ID and goes to the Application UI directly.)
I've also added a new test for the `limit` param in `HistoryServerSuite.scala`
## How was this patch tested?
Manual testing and dev/run-tests
Author: Alex Bozarth <ajbozart@us.ibm.com>
Closes#14835 from ajbozarth/spark17243.
This patch is using Apache Commons Crypto library to enable shuffle encryption support.
Author: Ferdinand Xu <cheng.a.xu@intel.com>
Author: kellyzly <kellyzly@126.com>
Closes#8880 from winningsix/SPARK-10771.
## What changes were proposed in this pull request?
Clean up unused variables and unused import statements, unnecessary `return` and `toArray`, and some more style improvement, when I walk through the code examples.
## How was this patch tested?
Testet manually on local laptop.
Author: Xin Ren <iamshrek@126.com>
Closes#14836 from keypointt/codeWalkThroughML.
## What changes were proposed in this pull request?
Move Mesos code into a mvn module
## How was this patch tested?
unit tests
manually submitting a client mode and cluster mode job
spark/mesos integration test suite
Author: Michael Gummelt <mgummelt@mesosphere.io>
Closes#14637 from mgummelt/mesos-module.
Make the config reader transient, and initialize it lazily so that
serialization works with both java and kryo (and hopefully any other
custom serializer).
Added unit test to make sure SparkConf remains serializable and the
reader works with both built-in serializers.
Author: Marcelo Vanzin <vanzin@cloudera.com>
Closes#14813 from vanzin/SPARK-17240.
## What changes were proposed in this pull request?
Based on #12990 by tankkyo
Since the History Server currently loads all application's data it can OOM if too many applications have a significant task count. `spark.ui.trimTasks` (default: false) can be set to true to trim tasks by `spark.ui.retainedTasks` (default: 10000)
(This is a "quick fix" to help those running into the problem until a update of how the history server loads app data can be done)
## How was this patch tested?
Manual testing and dev/run-tests
Author: Alex Bozarth <ajbozart@us.ibm.com>
Closes#14673 from ajbozarth/spark15083.
## What changes were proposed in this pull request?
This is a straightforward clone of JoshRosen 's original patch. I have follow-up changes to fix block replication for repl-defined classes as well, but those appear to be flaking tests so I'm going to leave that for SPARK-17042
## How was this patch tested?
End-to-end test in ReplSuite (also more tests in DistributedSuite from the original patch).
Author: Eric Liang <ekl@databricks.com>
Closes#14311 from ericl/spark-16550.
JIRA issue link:
https://issues.apache.org/jira/browse/SPARK-16961
Changed one line of Utils.randomizeInPlace to allow elements to stay in place.
Created a unit test that runs a Pearson's chi squared test to determine whether the output diverges significantly from a uniform distribution.
Author: Nick Lavers <nick.lavers@videoamp.com>
Closes#14551 from nicklavers/SPARK-16961-randomizeInPlace.
Both core and sql have slightly different code that does variable substitution
of config values. This change refactors that code and encapsulates the logic
of reading config values and expading variables in a new helper class, which
can be configured so that both core and sql can use it without losing existing
functionality, and allows for easier testing and makes it easier to add more
features in the future.
Tested with existing and new unit tests, and by running spark-shell with
some configs referencing variables and making sure it behaved as expected.
Author: Marcelo Vanzin <vanzin@cloudera.com>
Closes#14468 from vanzin/SPARK-16671.
- Make mesos coarse grained scheduler accept port offers and pre-assign ports
Previous attempt was for fine grained: https://github.com/apache/spark/pull/10808
Author: Stavros Kontopoulos <stavros.kontopoulos@lightbend.com>
Author: Stavros Kontopoulos <stavros.kontopoulos@typesafe.com>
Closes#11157 from skonto/honour_ports_coarse.
## What changes were proposed in this pull request?
Fixed warnings below after scanning through warnings during build:
```
[warn] /home/jenkins/workspace/SparkPullRequestBuilder/core/src/test/scala/org/apache/spark/scheduler/cluster/mesos/MesosClusterSchedulerSuite.scala:34: imported `Utils' is permanently hidden by definition of object Utils in package mesos
[warn] import org.apache.spark.scheduler.cluster.mesos.Utils
[warn] ^
```
and
```
[warn] /home/jenkins/workspace/SparkPullRequestBuilder/core/src/test/scala/org/apache/spark/storage/DiskBlockObjectWriterSuite.scala:113: method shuffleBytesWritten in class ShuffleWriteMetrics is deprecated: use bytesWritten instead
[warn] assert(writeMetrics.shuffleBytesWritten === file.length())
[warn] ^
[warn] /home/jenkins/workspace/SparkPullRequestBuilder/core/src/test/scala/org/apache/spark/storage/DiskBlockObjectWriterSuite.scala:119: method shuffleBytesWritten in class ShuffleWriteMetrics is deprecated: use bytesWritten instead
[warn] assert(writeMetrics.shuffleBytesWritten === file.length())
[warn] ^
[warn] /home/jenkins/workspace/SparkPullRequestBuilder/core/src/test/scala/org/apache/spark/storage/DiskBlockObjectWriterSuite.scala:131: method shuffleBytesWritten in class ShuffleWriteMetrics is deprecated: use bytesWritten instead
[warn] assert(writeMetrics.shuffleBytesWritten === file.length())
[warn] ^
[warn] /home/jenkins/workspace/SparkPullRequestBuilder/core/src/test/scala/org/apache/spark/storage/DiskBlockObjectWriterSuite.scala:135: method shuffleBytesWritten in class ShuffleWriteMetrics is deprecated: use bytesWritten instead
[warn] assert(writeMetrics.shuffleBytesWritten === file.length())
[warn] ^
```
## How was this patch tested?
Tested manually on local laptop.
Author: Xin Ren <iamshrek@126.com>
Closes#14609 from keypointt/suiteWarnings.
Before this PR, user have to export environment variable to specify the python of driver & executor which is not so convenient for users. This PR is trying to allow user to specify python through configuration "--pyspark-driver-python" & "--pyspark-executor-python"
Manually test in local & yarn mode for pyspark-shell and pyspark batch mode.
Author: Jeff Zhang <zjffdu@apache.org>
Closes#13146 from zjffdu/SPARK-13081.
## What changes were proposed in this pull request?
Added shutdown hook to DriverRunner to kill the driver process in case the Worker JVM exits suddenly and the `WorkerWatcher` was unable to properly catch this. Did some cleanup to consolidate driver state management and setting of finalized vars within the running thread.
## How was this patch tested?
Added unit tests to verify that final state and exception variables are set accordingly for successfull, failed, and errors in the driver process. Retrofitted existing test to verify killing of mocked process ends with the correct state and stops properly
Manually tested (with deploy-mode=cluster) that the shutdown hook is called by forcibly exiting the `Worker` and various points in the code with the `WorkerWatcher` both disabled and enabled. Also, manually killed the driver through the ui and verified that the `DriverRunner` interrupted, killed the process and exited properly.
Author: Bryan Cutler <cutlerb@gmail.com>
Closes#11746 from BryanCutler/DriverRunner-shutdown-hook-SPARK-13602.
## What changes were proposed in this pull request?
remove requirement to set spark.mesos.executor.home when spark.executor.uri is used
## How was this patch tested?
unit tests
Author: Michael Gummelt <mgummelt@mesosphere.io>
Closes#14552 from mgummelt/fix-spark-home.
When large number of jobs are run concurrently with Spark thrift server, thrift server starts running at high CPU due to GC pressure. Job UI retention causes memory pressure with large jobs. https://issues.apache.org/jira/secure/attachment/12783302/SPARK-12920.profiler_job_progress_listner.png has the profiler snapshot. This PR honors `spark.ui.retainedStages` strictly to reduce memory pressure.
Manual and unit tests
Author: Rajesh Balamohan <rbalamohan@apache.org>
Closes#10846 from rajeshbalamohan/SPARK-12920.
## What changes were proposed in this pull request?
Spark applications running on Mesos throw exception upon exit. For details, refer to https://issues.apache.org/jira/browse/SPARK-16522.
I am not sure if there is any better fix, so wait for review comments.
## How was this patch tested?
Manual test. Observed that the exception is gone upon application exit.
Author: Sun Rui <sunrui2016@gmail.com>
Closes#14175 from sun-rui/SPARK-16522.
## What changes were proposed in this pull request?
Avoid using postfix operation for command execution in SQLQuerySuite where it wasn't whitelisted and audit existing whitelistings removing postfix operators from most places. Some notable places where postfix operation remains is in the XML parsing & time units (seconds, millis, etc.) where it arguably can improve readability.
## How was this patch tested?
Existing tests.
Author: Holden Karau <holden@us.ibm.com>
Closes#14407 from holdenk/SPARK-16779.
## What changes were proposed in this pull request?
This patch fixes a bug in Spark's standalone Master which could cause applications to hang if tasks cause executors to exit with zero exit codes.
As an example of the bug, run
```
sc.parallelize(1 to 1, 1).foreachPartition { _ => System.exit(0) }
```
on a standalone cluster which has a single Spark application. This will cause all executors to die but those executors won't be replaced unless another Spark application or worker joins or leaves the cluster (or if an executor exits with a non-zero exit code). This behavior is caused by a bug in how the Master handles the `ExecutorStateChanged` event: the current implementation calls `schedule()` only if the executor exited with a non-zero exit code, so a task which causes a JVM to unexpectedly exit "cleanly" will skip the `schedule()` call.
This patch addresses this by modifying the `ExecutorStateChanged` to always unconditionally call `schedule()`. This should be safe because it should always be safe to call `schedule()`; adding extra `schedule()` calls can only affect performance and should not introduce correctness bugs.
## How was this patch tested?
I added a regression test in `DistributedSuite`.
Author: Josh Rosen <joshrosen@databricks.com>
Closes#14510 from JoshRosen/SPARK-16925.
## What changes were proposed in this pull request?
The behavior of `SparkContext.addFile()` changed slightly with the introduction of the Netty-RPC-based file server, which was introduced in Spark 1.6 (where it was disabled by default) and became the default / only file server in Spark 2.0.0.
Prior to 2.0, calling `SparkContext.addFile()` with files that have the same name and identical contents would succeed. This behavior was never explicitly documented but Spark has behaved this way since very early 1.x versions.
In 2.0 (or 1.6 with the Netty file server enabled), the second `addFile()` call will fail with a requirement error because NettyStreamManager tries to guard against duplicate file registration.
This problem also affects `addJar()` in a more subtle way: the `fileServer.addJar()` call will also fail with an exception but that exception is logged and ignored; I believe that the problematic exception-catching path was mistakenly copied from some old code which was only relevant to very old versions of Spark and YARN mode.
I believe that this change of behavior was unintentional, so this patch weakens the `require` check so that adding the same filename at the same path will succeed.
At file download time, Spark tasks will fail with exceptions if an executor already has a local copy of a file and that file's contents do not match the contents of the file being downloaded / added. As a result, it's important that we prevent files with the same name and different contents from being served because allowing that can effectively brick an executor by preventing it from successfully launching any new tasks. Before this patch's change, this was prevented by forbidding `addFile()` from being called twice on files with the same name. Because Spark does not defensively copy local files that are passed to `addFile` it is vulnerable to files' contents changing, so I think it's okay to rely on an implicit assumption that these files are intended to be immutable (since if they _are_ mutable then this can lead to either explicit task failures or implicit incorrectness (in case new executors silently get newer copies of the file while old executors continue to use an older version)). To guard against this, I have decided to only update the file addition timestamps on the first call to `addFile()`; duplicate calls will succeed but will not update the timestamp. This behavior is fine as long as we assume files are immutable, which seems reasonable given the behaviors described above.
As part of this change, I also improved the thread-safety of the `addedJars` and `addedFiles` maps; this is important because these maps may be concurrently read by a task launching thread and written by a driver thread in case the user's driver code is multi-threaded.
## How was this patch tested?
I added regression tests in `SparkContextSuite`.
Author: Josh Rosen <joshrosen@databricks.com>
Closes#14396 from JoshRosen/SPARK-16787.
## What changes were proposed in this pull request?
Use foreach/for instead of map where operation requires execution of body, not actually defining a transformation
## How was this patch tested?
Jenkins
Author: Sean Owen <sowen@cloudera.com>
Closes#14332 from srowen/SPARK-16694.
## What changes were proposed in this pull request?
New config var: spark.mesos.docker.containerizer={"mesos","docker" (default)}
This adds support for running docker containers via the Mesos unified containerizer: http://mesos.apache.org/documentation/latest/container-image/
The benefit is losing the dependency on `dockerd`, and all the costs which it incurs.
I've also updated the supported Mesos version to 0.28.2 for support of the required protobufs.
This is blocked on: https://github.com/apache/spark/pull/14167
## How was this patch tested?
- manually testing jobs submitted with both "mesos" and "docker" settings for the new config var.
- spark/mesos integration test suite
Author: Michael Gummelt <mgummelt@mesosphere.io>
Closes#14275 from mgummelt/unified-containerizer.
## What changes were proposed in this pull request?
Adding a new property to SparkConf called spark.metrics.namespace that allows users to
set a custom namespace for executor and driver metrics in the metrics systems.
By default, the root namespace used for driver or executor metrics is
the value of `spark.app.id`. However, often times, users want to be able to track the metrics
across apps for driver and executor metrics, which is hard to do with application ID
(i.e. `spark.app.id`) since it changes with every invocation of the app. For such use cases,
users can set the `spark.metrics.namespace` property to another spark configuration key like
`spark.app.name` which is then used to populate the root namespace of the metrics system
(with the app name in our example). `spark.metrics.namespace` property can be set to any
arbitrary spark property key, whose value would be used to set the root namespace of the
metrics system. Non driver and executor metrics are never prefixed with `spark.app.id`, nor
does the `spark.metrics.namespace` property have any such affect on such metrics.
## How was this patch tested?
Added new unit tests, modified existing unit tests.
Author: Mark Grover <mark@apache.org>
Closes#14270 from markgrover/spark-5847.
## What changes were proposed in this pull request?
This change adds a new configuration entry to specify the size of the spark listener bus event queue. The value for this config ("spark.scheduler.listenerbus.eventqueue.size") is set to a default to 10000.
Note:
I haven't currently documented the configuration entry. We can decide whether it would be appropriate to make it a public configuration or keep it as an undocumented one. Refer JIRA for more details.
## How was this patch tested?
Ran existing jobs and verified the event queue size with debug logs and from the Spark WebUI Environment tab.
Author: Dhruve Ashar <dhruveashar@gmail.com>
Closes#14269 from dhruve/bug/SPARK-15703.
## What changes were proposed in this pull request?
(Please fill in changes proposed in this fix)
## How was this patch tested?
(Please explain how this patch was tested. E.g. unit tests, integration tests, manual tests)
(If this patch involves UI changes, please attach a screenshot; otherwise, remove this)
Mesos agents by default will not pull docker images which are cached
locally already. In order to run Spark executors from mutable tags like
`:latest` this commit introduces a Spark setting
(`spark.mesos.executor.docker.forcePullImage`). Setting this flag to
true will tell the Mesos agent to force pull the docker image (default is `false` which is consistent with the previous
implementation and Mesos' default
behaviour).
Author: Philipp Hoffmann <mail@philipphoffmann.de>
Closes#14348 from philipphoffmann/force-pull-image.
## What changes were proposed in this pull request?
This patch adds pagination support for the Job Tables in the Jobs tab. Pagination is provided for all of the three Job Tables (active, completed, and failed). Interactions (jumping, sorting, and setting page size) for paged tables are also included.
The diff didn't keep track of some lines based on the original ones. The function `makeRow`of the original `AllJobsPage.scala` is reused. They are separated at the beginning of the function `jobRow` (L427-439) and the function `row`(L594-618) in the new `AllJobsPage.scala`.
## How was this patch tested?
Tested manually by using checking the Web UI after completing and failing hundreds of jobs.
Generate completed jobs by:
```scala
val d = sc.parallelize(Array(1,2,3,4,5))
for(i <- 1 to 255){ var b = d.collect() }
```
Generate failed jobs by calling the following code multiple times:
```scala
var b = d.map(_/0).collect()
```
Interactions like jumping, sorting, and setting page size are all tested.
This shows the pagination for completed jobs:
This shows the sorting works in job tables:
This shows the pagination for failed jobs and the effect of jumping and setting page size:
Author: Tao Lin <nblintao@gmail.com>
Closes#13620 from nblintao/dev.
## What changes were proposed in this pull request?
Currently in the log and UI display, only on-heap storage memory is calculated and displayed,
```
16/06/27 13:41:52 INFO MemoryStore: Block rdd_5_0 stored as values in memory (estimated size 17.8 KB, free 665.9 MB)
```
<img width="1232" alt="untitled" src="https://cloud.githubusercontent.com/assets/850797/16369960/53fb614e-3c6e-11e6-8fa3-7ffe65abcb49.png">
With [SPARK-13992](https://issues.apache.org/jira/browse/SPARK-13992) off-heap memory is supported for data persistence, so here change to also take off-heap storage memory into consideration.
## How was this patch tested?
Unit test and local verification.
Author: jerryshao <sshao@hortonworks.com>
Closes#13920 from jerryshao/SPARK-16166.
## What changes were proposed in this pull request?
Mesos agents by default will not pull docker images which are cached
locally already. In order to run Spark executors from mutable tags like
`:latest` this commit introduces a Spark setting
`spark.mesos.executor.docker.forcePullImage`. Setting this flag to
true will tell the Mesos agent to force pull the docker image (default is `false` which is consistent with the previous
implementation and Mesos' default
behaviour).
## How was this patch tested?
I ran a sample application including this change on a Mesos cluster and verified the correct behaviour for both, with and without, force pulling the executor image. As expected the image is being force pulled if the flag is set.
Author: Philipp Hoffmann <mail@philipphoffmann.de>
Closes#13051 from philipphoffmann/force-pull-image.
…close between each partition
## What changes were proposed in this pull request?
Replace commitAndClose with separate commit and close to avoid opening and closing
the file between partitions.
## How was this patch tested?
Run existing unit tests, add a few unit tests regarding reverts.
Observed a ~20% reduction in total time in tasks on stages with shuffle
writes to many partitions.
JoshRosen
Author: Brian Cho <bcho@fb.com>
Closes#13382 from dafrista/separatecommit-master.
## What changes were proposed in this pull request?
Added new configuration namespace: spark.mesos.env.*
This allows a user submitting a job in cluster mode to set arbitrary environment variables on the driver.
spark.mesos.driverEnv.KEY=VAL will result in the env var "KEY" being set to "VAL"
I've also refactored the tests a bit so we can re-use code in MesosClusterScheduler.
And I've refactored the command building logic in `buildDriverCommand`. Command builder values were very intertwined before, and now it's easier to determine exactly how each variable is set.
## How was this patch tested?
unit tests
Author: Michael Gummelt <mgummelt@mesosphere.io>
Closes#14167 from mgummelt/driver-env-vars.
This allows configuration to be more flexible, for example, when the cluster does
not have a homogeneous configuration (e.g. packages are installed on different
paths in different nodes). By allowing one to reference the environment from
the conf, it becomes possible to work around those in certain cases.
As part of the implementation, ConfigEntry now keeps track of all "known" configs
(i.e. those created through the use of ConfigBuilder), since that list is used
by the resolution code. This duplicates some code in SQLConf, which could potentially
be merged with this now. It will also make it simpler to implement some missing
features such as filtering which configs show up in the UI or in event logs - which
are not part of this change.
Another change is in the way ConfigEntry reads config data; it now takes a string
map and a function that reads env variables, so that it can be called both from
SparkConf and SQLConf. This makes it so both places follow the same read path,
instead of having to replicate certain logic in SQLConf. There are still a
couple of methods in SQLConf that peek into fields of ConfigEntry directly,
though.
Tested via unit tests, and by using the new variable expansion functionality
in a shell session with a custom spark.sql.hive.metastore.jars value.
Author: Marcelo Vanzin <vanzin@cloudera.com>
Closes#14022 from vanzin/SPARK-16272.
## What changes were proposed in this pull request?
Document RDD.pipe semantics; don't execute process for empty input partitions.
Note this includes the fix in https://github.com/apache/spark/pull/14256 because it's necessary to even test this. One or the other will merge the fix.
## How was this patch tested?
Jenkins tests including new test.
Author: Sean Owen <sowen@cloudera.com>
Closes#14260 from srowen/SPARK-16613.
## What changes were proposed in this pull request?
This change moves the include jar test from R to SparkSubmitSuite and uses a dynamically compiled jar. This helps us remove the binary jar from the R package and solves both the CRAN warnings and the lack of source being available for this jar.
## How was this patch tested?
SparkR unit tests, SparkSubmitSuite, check-cran.sh
Author: Shivaram Venkataraman <shivaram@cs.berkeley.edu>
Closes#14243 from shivaram/sparkr-jar-move.
## What changes were proposed in this pull request?
Adds a few public methods to `SparkLauncher` to allow configuring some extra features of the `ProcessBuilder`, including the working directory, output and error stream redirection.
## How was this patch tested?
Unit testing + simple Spark driver programs
Author: Andrew Duffy <root@aduffy.org>
Closes#14201 from andreweduffy/feature/launcher.
## What changes were proposed in this pull request?
Currently `RDD.pipe(command: String)`:
- works only when the command is specified without any options, such as `RDD.pipe("wc")`
- does NOT work when the command is specified with some options, such as `RDD.pipe("wc -l")`
This is a regression from Spark 1.6.
This patch adds back the tokenization process in `RDD.pipe(command: String)` to fix this regression.
## How was this patch tested?
Added a test which:
- would pass in `1.6`
- _[prior to this patch]_ would fail in `master`
- _[after this patch]_ would pass in `master`
Author: Liwei Lin <lwlin7@gmail.com>
Closes#14256 from lw-lin/rdd-pipe.
## What changes were proposed in this pull request?
Currently if `spark.dynamicAllocation.initialExecutors` is less than `spark.dynamicAllocation.minExecutors`, Spark will automatically pick the minExecutors without any warning. While in 1.6 Spark will throw exception if configured like this. So here propose to add warning log if these parameters are configured invalidly.
## How was this patch tested?
Unit test added to verify the scenario.
Author: jerryshao <sshao@hortonworks.com>
Closes#14149 from jerryshao/SPARK-16435.
## What changes were proposed in this pull request?
I fixed a misassigned var, numCompletedTasks was assigned to numSkippedTasks in the convertJobData method
## How was this patch tested?
dev/run-tests
Author: Alex Bozarth <ajbozart@us.ibm.com>
Closes#14141 from ajbozarth/spark16375.
## What changes were proposed in this pull request?
It's possible to also change the callers to not pass in empty chunks, but it seems cleaner to just allow `ChunkedByteBuffer` to handle empty arrays. cc JoshRosen
## How was this patch tested?
Unit tests, also checked that the original reproduction case in https://github.com/apache/spark/pull/11748#issuecomment-230760283 is resolved.
Author: Eric Liang <ekl@databricks.com>
Closes#14099 from ericl/spark-16432.
## What changes were proposed in this pull request?
This moves over old PR https://github.com/apache/spark/pull/13664 to target master rather than branch-1.6.
Added links to logs (or an indication that there are no logs) for entries which list an executor in the stage details page of the UI.
This helps streamline the workflow where a user views a stage details page and determines that they would like to see the associated executor log for further examination. Previously, a user would have to cross reference the executor id listed on the stage details page with the corresponding entry on the executors tab.
Link to the JIRA: https://issues.apache.org/jira/browse/SPARK-15885
## How was this patch tested?
Ran existing unit tests.
Ran test queries on a platform which did not record executor logs and again on a platform which did record executor logs and verified that the new table column was empty and links to the logs (which were verified as linking to the appropriate files), respectively.
Attached is a screenshot of the UI page with no links, with the new columns highlighted. Additional screenshot of these columns with the populated links.
Without links:
With links:
This contribution is my original work and I license the work to the project under the Apache Spark project's open source license.
Author: Tom Magrino <tmagrino@fb.com>
Closes#13861 from tmagrino/uilogstweak.
## What changes were proposed in this pull request?
This patch updates the failure handling logic so Spark executor does not crash when seeing LinkageError.
## How was this patch tested?
Added an end-to-end test in FailureSuite.
Author: petermaxlee <petermaxlee@gmail.com>
Closes#13982 from petermaxlee/SPARK-16304.
## What changes were proposed in this pull request?
Utils.terminateProcess should `destroy()` first and only fall back to `destroyForcibly()` if it fails. It's kind of bad that we're force-killing executors -- and only in Java 8. See JIRA for an example of the impact: no shutdown
While here: `Utils.waitForProcess` should use the Java 8 method if available instead of a custom implementation.
## How was this patch tested?
Existing tests, which cover the force-kill case, and Amplab tests, which will cover both Java 7 and Java 8 eventually. However I tested locally on Java 8 and the PR builder will try Java 7 here.
Author: Sean Owen <sowen@cloudera.com>
Closes#13973 from srowen/SPARK-16182.
## What changes were proposed in this pull request?
Before this change, when you turn on blacklisting with `spark.scheduler.executorTaskBlacklistTime`, but you have fewer than `spark.task.maxFailures` executors, you can end with a job "hung" after some task failures.
Whenever a taskset is unable to schedule anything on resourceOfferSingleTaskSet, we check whether the last pending task can be scheduled on *any* known executor. If not, the taskset (and any corresponding jobs) are failed.
* Worst case, this is O(maxTaskFailures + numTasks). But unless many executors are bad, this should be small
* This does not fail as fast as possible -- when a task becomes unschedulable, we keep scheduling other tasks. This is to avoid an O(numPendingTasks * numExecutors) operation
* Also, it is conceivable this fails too quickly. You may be 1 millisecond away from unblacklisting a place for a task to run, or acquiring a new executor.
## How was this patch tested?
Added unit test which failed before the change, ran new test 5k times manually, ran all scheduler tests manually, and the full suite via jenkins.
Author: Imran Rashid <irashid@cloudera.com>
Closes#13603 from squito/progress_w_few_execs_and_blacklist.
## What changes were proposed in this pull request?
Force the sorter to Spill when number of elements in the pointer array reach a certain size. This is to workaround the issue of timSort failing on large buffer size.
## How was this patch tested?
Tested by running a job which was failing without this change due to TimSort bug.
Author: Sital Kedia <skedia@fb.com>
Closes#13107 from sitalkedia/fix_TimSort.
## What changes were proposed in this pull request?
Previously, the TaskLocation implementation would not allow for executor ids which include underscores. This tweaks the string split used to get the hostname and executor id, allowing for underscores in the executor id.
This addresses the JIRA found here: https://issues.apache.org/jira/browse/SPARK-16148
This is moved over from a previous PR against branch-1.6: https://github.com/apache/spark/pull/13857
## How was this patch tested?
Ran existing unit tests for core and streaming. Manually ran a simple streaming job with an executor whose id contained underscores and confirmed that the job ran successfully.
This is my original work and I license the work to the project under the project's open source license.
Author: Tom Magrino <tmagrino@fb.com>
Closes#13858 from tmagrino/fixtasklocation.
## What changes were proposed in this pull request?
TaskSchedulerImpl used to only set `newExecAvailable` when a new *host* was added, not when a new executor was added to an existing host. It also didn't update some internal state tracking live executors until a task was scheduled on the executor. This patch changes it to properly update as soon as it knows about a new executor.
## How was this patch tested?
added a unit test, ran everything via jenkins.
Author: Imran Rashid <irashid@cloudera.com>
Closes#13826 from squito/SPARK-16106_executorByHosts.
## What changes were proposed in this pull request?
TaskManagerSuite "Kill other task attempts when one attempt belonging to the same task succeeds" was flaky. When checking whether a task is speculatable, at least one millisecond must pass since the task was submitted. Use a manual clock to avoid the problem.
I noticed these tests were leaving lots of threads lying around as well (which prevented me from running the test repeatedly), so I fixed that too.
## How was this patch tested?
Ran the test 1k times on my laptop, passed every time (it failed about 20% of the time before this).
Author: Imran Rashid <irashid@cloudera.com>
Closes#13848 from squito/fix_flaky_taskmanagersuite.
## What changes were proposed in this pull request?
Currently the initial buffer size in the sorter is hard coded inside the code and is too small for large workload. As a result, the sorter spends significant time expanding the buffer size and copying the data. It would be useful to have it configurable.
## How was this patch tested?
Tested by running a job on the cluster.
Author: Sital Kedia <skedia@fb.com>
Closes#13699 from sitalkedia/config_sort_buffer_upstream.
## The problem
Before this change, if either of the following cases happened to a task , the task would be marked as `FAILED` instead of `KILLED`:
- the task was killed before it was deserialized
- `executor.kill()` marked `taskRunner.killed`, but before calling `task.killed()` the worker thread threw the `TaskKilledException`
The reason is, in the `catch` block of the current [Executor.TaskRunner](https://github.com/apache/spark/blob/master/core/src/main/scala/org/apache/spark/executor/Executor.scala#L362)'s implementation, we are mistakenly catching:
```scala
case _: TaskKilledException | _: InterruptedException if task.killed => ...
```
the semantics of which is:
- **(**`TaskKilledException` **OR** `InterruptedException`**)** **AND** `task.killed`
Then when `TaskKilledException` is thrown but `task.killed` is not marked, we would mark the task as `FAILED` (which should really be `KILLED`).
## What changes were proposed in this pull request?
This patch alters the catch condition's semantics from:
- **(**`TaskKilledException` **OR** `InterruptedException`**)** **AND** `task.killed`
to
- `TaskKilledException` **OR** **(**`InterruptedException` **AND** `task.killed`**)**
so that we can catch `TaskKilledException` correctly and mark the task as `KILLED` correctly.
## How was this patch tested?
Added unit test which failed before the change, ran new test 1000 times manually
Author: Liwei Lin <lwlin7@gmail.com>
Closes#13685 from lw-lin/fix-task-killed.
## What changes were proposed in this pull request?
Since SPARK-13220(Deprecate "yarn-client" and "yarn-cluster"), YarnClusterSuite doesn't test "yarn cluster" mode correctly.
This pull request fixes it.
## How was this patch tested?
Unit test
(If this patch involves UI changes, please attach a screenshot; otherwise, remove this)
Author: peng.zhang <peng.zhang@xiaomi.com>
Closes#13836 from renozhang/SPARK-16125-test-yarn-cluster-mode.
## What changes were proposed in this pull request?
This changes the behavior of --num-executors and spark.executor.instances when using dynamic allocation. Instead of turning dynamic allocation off, it uses the value for the initial number of executors.
This changes was discussed on [SPARK-13723](https://issues.apache.org/jira/browse/SPARK-13723). I highly recommend using it while we can change the behavior for 2.0.0. In practice, the 1.x behavior causes unexpected behavior for users (it is not clear that it disables dynamic allocation) and wastes cluster resources because users rarely notice the log message.
## How was this patch tested?
This patch updates tests and adds a test for Utils.getDynamicAllocationInitialExecutors.
Author: Ryan Blue <blue@apache.org>
Closes#13338 from rdblue/SPARK-13723-num-executors-with-dynamic-allocation.
## What changes were proposed in this pull request?
This fixes SerializationDebugger to not recurse forever when `writeReplace` returns an object of the same class, which is the case for at least the `SQLMetrics` class.
See also the OpenJDK unit tests on the behavior of recursive `writeReplace()`:
f4d80957e8/test/java/io/Serializable/nestedReplace/NestedReplace.java
cc davies cloud-fan
## How was this patch tested?
Unit tests for SerializationDebugger.
Author: Eric Liang <ekl@databricks.com>
Closes#13814 from ericl/spark-16003.
## What changes were proposed in this pull request?
Three changes here -- first two were causing failures w/ BlacklistIntegrationSuite
1. The testing framework didn't include the reviveOffers thread, so the test which involved delay scheduling might never submit offers late enough for the delay scheduling to kick in. So added in the periodic revive offers, just like the real scheduler.
2. `assertEmptyDataStructures` would occasionally fail, because it appeared there was still an active job. This is because in DAGScheduler, the jobWaiter is notified of the job completion before the data structures are cleaned up. Most of the time the test code that is waiting on the jobWaiter won't become active until after the data structures are cleared, but occasionally the race goes the other way, and the assertions fail.
3. `DAGSchedulerSuite` was not stopping all the inner parts it was setting up, so each test was leaking a number of threads. So we stop those parts too.
4. Turns out that `assertMapOutputAvailable` is not terribly useful in this framework -- most of the places I was trying to use it suffer from some race.
5. When there is an exception in the backend, try to improve the error msg a little bit. Before the exception was printed to the console, but the test would fail w/ a timeout, and the logs wouldn't show anything.
## How was this patch tested?
I ran all the tests in `BlacklistIntegrationSuite` 5k times and everything in `DAGSchedulerSuite` 1k times on my laptop. Also I ran a full jenkins build with `BlacklistIntegrationSuite` 500 times and `DAGSchedulerSuite` 50 times, see https://github.com/apache/spark/pull/13548. (I tried more times but jenkins timed out.)
To check for more leaked threads, I added some code to dump the list of all threads at the end of each test in DAGSchedulerSuite, which is how I discovered the mapOutputTracker and eventLoop were leaking threads. (I removed that code from the final pr, just part of the testing.)
And I'll run Jenkins on this a couple of times to do one more check.
Author: Imran Rashid <irashid@cloudera.com>
Closes#13565 from squito/blacklist_extra_tests.
## What changes were proposed in this pull request?
[SPARK-15395](https://issues.apache.org/jira/browse/SPARK-15395) changes the behavior that how the driver gets the executor host and the driver will get the executor IP address instead of the host name. This PR just sends the hostname from executors to driver so that driver can pass it to TaskScheduler.
## How was this patch tested?
Existing unit tests.
Author: Shixiong Zhu <shixiong@databricks.com>
Closes#13741 from zsxwing/SPARK-16017.
## What changes were proposed in this pull request?
This pull request refactors parts of the DAGScheduler to improve readability, focusing on the code around stage creation. One goal of this change it to make it clearer which functions may create new stages (as opposed to looking up stages that already exist). There are no functionality changes in this pull request. In more detail:
* shuffleToMapStage was renamed to shuffleIdToMapStage (when reading the existing code I have sometimes struggled to remember what the key is -- is it a stage? A stage id? This change is intended to avoid that confusion)
* Cleaned up the code to create shuffle map stages. Previously, creating a shuffle map stage involved 3 different functions (newOrUsedShuffleStage, newShuffleMapStage, and getShuffleMapStage), and it wasn't clear what the purpose of each function was. With the new code, a single function (getOrCreateShuffleMapStage) is responsible for getting a stage (if it already exists) or creating new shuffle map stages and any missing ancestor stages, and it delegates to createShuffleMapStage when new stages need to be created. There's some remaining confusion here because the getOrCreateParentStages call in createShuffleMapStage may recursively create ancestor stages; this is an issue I plan to fix in a future pull request, because it's trickier to fix and involves a slight functionality change.
* newResultStage was renamed to createResultStage, for consistency with naming around shuffle map stages.
* getParentStages has been renamed to getOrCreateParentStages, to make it clear that this function will sometimes create missing ancestor stages.
* The only *slight* functionality change is that on line 478, updateJobIdStageIdMaps now uses a stage's parents instance variable rather than re-calculating them (I couldn't see any reason why they'd need to be re-calculated, and suspect this is just leftover from older code).
* getAncestorShuffleDependencies was renamed to getMissingAncestorShuffleDependencies, to make it clear that this only returns dependencies that have not yet been run.
cc squito markhamstra JoshRosen (who requested more DAG scheduler commenting long ago -- an issue this pull request tries, in part, to address)
FYI rxin
Author: Kay Ousterhout <kayousterhout@gmail.com>
Closes#13677 from kayousterhout/SPARK-15926.
When `--packages` is specified with spark-shell the classes from those packages cannot be found, which I think is due to some of the changes in SPARK-12343.
Tested manually with both scala 2.10 and 2.11 repls.
vanzin davies can you guys please review?
Author: Marcelo Vanzin <vanzin@cloudera.com>
Author: Nezih Yigitbasi <nyigitbasi@netflix.com>
Closes#13709 from nezihyigitbasi/SPARK-15782.
## What changes were proposed in this pull request?
Reduce `spark.memory.fraction` default to 0.6 in order to make it fit within default JVM old generation size (2/3 heap). See JIRA discussion. This means a full cache doesn't spill into the new gen. CC andrewor14
## How was this patch tested?
Jenkins tests.
Author: Sean Owen <sowen@cloudera.com>
Closes#13618 from srowen/SPARK-15796.
## What changes were proposed in this pull request?
SPARK-15927 exacerbated a race in BasicSchedulerIntegrationTest, so it went from very unlikely to fairly frequent. The issue is that stage numbering is not completely deterministic, but these tests treated it like it was. So turn off the tests.
## How was this patch tested?
on my laptop the test failed abotu 10% of the time before this change, and didn't fail in 500 runs after the change.
Author: Imran Rashid <irashid@cloudera.com>
Closes#13688 from squito/hotfix_basic_scheduler.
## What changes were proposed in this pull request?
When `--packages` is specified with `spark-shell` the classes from those packages cannot be found, which I think is due to some of the changes in `SPARK-12343`. In particular `SPARK-12343` removes a line that sets the `spark.jars` system property in client mode, which is used by the repl main class to set the classpath.
## How was this patch tested?
Tested manually.
This system property is used by the repl to populate its classpath. If
this is not set properly the classes for external packages cannot be
found.
tgravescs vanzin as you may be familiar with this part of the code.
Author: Nezih Yigitbasi <nyigitbasi@netflix.com>
Closes#13527 from nezihyigitbasi/repl-fix.
## What changes were proposed in this pull request?
Link to jira which describes the problem: https://issues.apache.org/jira/browse/SPARK-15826
The fix in this PR is to allow users specify encoding in the pipe() operation. For backward compatibility,
keeping the default value to be system default.
## How was this patch tested?
Ran existing unit tests
Author: Tejas Patil <tejasp@fb.com>
Closes#13563 from tejasapatil/pipedrdd_utf8.
## What changes were proposed in this pull request?
This patch is a follow-up to https://github.com/apache/spark/pull/13288 completing the renaming:
- LocalScheduler -> LocalSchedulerBackend~~Endpoint~~
## How was this patch tested?
Updated test cases to reflect the name change.
Author: Liwei Lin <lwlin7@gmail.com>
Closes#13683 from lw-lin/rename-backend.
To try to eliminate redundant code to traverse the RDD dependency graph,
this PR creates a new function getShuffleDependencies that returns
shuffle dependencies that are immediate parents of a given RDD. This
new function is used by getParentStages and
getAncestorShuffleDependencies.
Author: Kay Ousterhout <kayousterhout@gmail.com>
Closes#13646 from kayousterhout/SPARK-15927.
## What changes were proposed in this pull request?
Another PR to clean up recent build warnings. This particularly cleans up several instances of the old accumulator API usage in tests that are straightforward to update. I think this qualifies as "minor".
## How was this patch tested?
Jenkins
Author: Sean Owen <sowen@cloudera.com>
Closes#13642 from srowen/BuildWarnings.
## What changes were proposed in this pull request?
Remove deprecated support for `zk://` master (`mesos://zk//` remains supported)
## How was this patch tested?
Jenkins
Author: Sean Owen <sowen@cloudera.com>
Closes#13625 from srowen/SPARK-15876.
## What changes were proposed in this pull request?
- Deprecate old Java accumulator API; should use Scala now
- Update Java tests and examples
- Don't bother testing old accumulator API in Java 8 (too)
- (fix a misspelling too)
## How was this patch tested?
Jenkins tests
Author: Sean Owen <sowen@cloudera.com>
Closes#13606 from srowen/SPARK-15086.
## What changes were proposed in this pull request?
These tests weren't properly using `LocalSparkContext` so weren't cleaning up correctly when tests failed.
## How was this patch tested?
Jenkins.
Author: Imran Rashid <irashid@cloudera.com>
Closes#13602 from squito/SPARK-15878_cleanup_replaylistener.
## What changes were proposed in this pull request?
Adds codahale metrics for the codegen source text size and how long it takes to compile. The size is particularly interesting, since the JVM does have hard limits on how large methods can get.
To simplify, I added the metrics under a statically-initialized source that is always registered with SparkEnv.
## How was this patch tested?
Unit tests
Author: Eric Liang <ekl@databricks.com>
Closes#13586 from ericl/spark-15860.
## What changes were proposed in this pull request?
This adds support for radix sort of nullable long fields. When a sort field is null and radix sort is enabled, we keep nulls in a separate region of the sort buffer so that radix sort does not need to deal with them. This also has performance benefits when sorting smaller integer types, since the current representation of nulls in two's complement (Long.MIN_VALUE) otherwise forces a full-width radix sort.
This strategy for nulls does mean the sort is no longer stable. cc davies
## How was this patch tested?
Existing randomized sort tests for correctness. I also tested some TPCDS queries and there does not seem to be any significant regression for non-null sorts.
Some test queries (best of 5 runs each).
Before change:
scala> val start = System.nanoTime; spark.range(5000000).selectExpr("if(id > 5, cast(hash(id) as long), NULL) as h").coalesce(1).orderBy("h").collect(); (System.nanoTime - start) / 1e6
start: Long = 3190437233227987
res3: Double = 4716.471091
After change:
scala> val start = System.nanoTime; spark.range(5000000).selectExpr("if(id > 5, cast(hash(id) as long), NULL) as h").coalesce(1).orderBy("h").collect(); (System.nanoTime - start) / 1e6
start: Long = 3190367870952791
res4: Double = 2981.143045
Author: Eric Liang <ekl@databricks.com>
Closes#13161 from ericl/sc-2998.
## What changes were proposed in this pull request?
SparkContext.listAccumulator, by Spark's convention, makes it sound like "list" is a verb and the method should return a list of accumulators. This patch renames the method and the class collection accumulator.
## How was this patch tested?
Updated test case to reflect the names.
Author: Reynold Xin <rxin@databricks.com>
Closes#13594 from rxin/SPARK-15866.
## What changes were proposed in this pull request?
With very wide tables, e.g. thousands of fields, the plan output is unreadable and often causes OOMs due to inefficient string processing. This truncates all struct and operator field lists to a user configurable threshold to limit performance impact.
It would also be nice to optimize string generation to avoid these sort of O(n^2) slowdowns entirely (i.e. use StringBuilder everywhere including expressions), but this is probably too large of a change for 2.0 at this point, and truncation has other benefits for usability.
## How was this patch tested?
Added a microbenchmark that covers this case particularly well. I also ran the microbenchmark while varying the truncation threshold.
```
numFields = 5
wide shallowly nested struct field r/w: Best/Avg Time(ms) Rate(M/s) Per Row(ns) Relative
------------------------------------------------------------------------------------------------
2000 wide x 50 rows (write in-mem) 2336 / 2558 0.0 23364.4 0.1X
numFields = 25
wide shallowly nested struct field r/w: Best/Avg Time(ms) Rate(M/s) Per Row(ns) Relative
------------------------------------------------------------------------------------------------
2000 wide x 50 rows (write in-mem) 4237 / 4465 0.0 42367.9 0.1X
numFields = 100
wide shallowly nested struct field r/w: Best/Avg Time(ms) Rate(M/s) Per Row(ns) Relative
------------------------------------------------------------------------------------------------
2000 wide x 50 rows (write in-mem) 10458 / 11223 0.0 104582.0 0.0X
numFields = Infinity
wide shallowly nested struct field r/w: Best/Avg Time(ms) Rate(M/s) Per Row(ns) Relative
------------------------------------------------------------------------------------------------
[info] java.lang.OutOfMemoryError: Java heap space
```
Author: Eric Liang <ekl@databricks.com>
Author: Eric Liang <ekhliang@gmail.com>
Closes#13537 from ericl/truncated-string.
## What changes were proposed in this pull request?
There is still some flakiness in BlacklistIntegrationSuite, so turning it off for the moment to avoid breaking more builds -- will turn it back with more fixes.
## How was this patch tested?
jenkins.
Author: Imran Rashid <irashid@cloudera.com>
Closes#13528 from squito/ignore_blacklist.
## What changes were proposed in this pull request?
`an -> a`
Use cmds like `find . -name '*.R' | xargs -i sh -c "grep -in ' an [^aeiou]' {} && echo {}"` to generate candidates, and review them one by one.
## How was this patch tested?
manual tests
Author: Zheng RuiFeng <ruifengz@foxmail.com>
Closes#13515 from zhengruifeng/an_a.
## What changes were proposed in this pull request?
Stop using the abbreviated and ambiguous timezone "EST" in a test, since it is machine-local default timezone dependent, and fails in different timezones. Fixed [SPARK-15723](https://issues.apache.org/jira/browse/SPARK-15723).
## How was this patch tested?
Note that to reproduce this problem in any locale/timezone, you can modify the scalatest-maven-plugin argLine to add a timezone:
<argLine>-ea -Xmx3g -XX:MaxPermSize=${MaxPermGen} -XX:ReservedCodeCacheSize=${CodeCacheSize} -Duser.timezone="Australia/Sydney"</argLine>
and run
$ mvn test -DwildcardSuites=org.apache.spark.status.api.v1.SimpleDateParamSuite -Dtest=none. Equally this will fix it in an effected timezone:
<argLine>-ea -Xmx3g -XX:MaxPermSize=${MaxPermGen} -XX:ReservedCodeCacheSize=${CodeCacheSize} -Duser.timezone="America/New_York"</argLine>
To test the fix, apply the above change to `pom.xml` to set test TZ to `Australia/Sydney`, and confirm the test now passes.
Author: Brett Randall <javabrett@gmail.com>
Closes#13462 from javabrett/SPARK-15723-SimpleDateParamSuite.
## What changes were proposed in this pull request?
Currently, the memory for temporary buffer used by TimSort is always allocated as on-heap without bookkeeping, it could cause OOM both in on-heap and off-heap mode.
This PR will try to manage that by preallocate it together with the pointer array, same with RadixSort. It both works for on-heap and off-heap mode.
This PR also change the loadFactor of BytesToBytesMap to 0.5 (it was 0.70), it enables use to radix sort also makes sure that we have enough memory for timsort.
## How was this patch tested?
Existing tests.
Author: Davies Liu <davies@databricks.com>
Closes#13318 from davies/fix_timsort.
## What changes were proposed in this pull request?
Currently `SparkContext API setLogLevel(level: String) `can not handle lower case or mixed case input string. But `org.apache.log4j.Level.toLevel` can take lowercase or mixed case.
This PR is to allow case-insensitive user input for the log level.
## How was this patch tested?
A unit testcase is added.
Author: Xin Wu <xinwu@us.ibm.com>
Closes#13422 from xwu0226/reset_loglevel.
## What changes were proposed in this pull request?
BlacklistIntegrationSuite (introduced by SPARK-10372) is a bit flaky because of some race conditions:
1. Failed jobs might have non-empty results, because the resultHandler will be invoked for successful tasks (if there are task successes before failures)
2. taskScheduler.taskIdToTaskSetManager must be protected by a lock on taskScheduler
(1) has failed a handful of jenkins builds recently. I don't think I've seen (2) in jenkins, but I've run into with some uncommitted tests I'm working on where there are lots more tasks.
While I was in there, I also made an unrelated fix to `runningTasks`in the test framework -- there was a pointless `O(n)` operation to remove completed tasks, could be `O(1)`.
## How was this patch tested?
I modified the o.a.s.scheduler.BlacklistIntegrationSuite to have it run the tests 1k times on my laptop. It failed 11 times before this change, and none with it. (Pretty sure all the failures were problem (1), though I didn't check all of them).
Also the full suite of tests via jenkins.
Author: Imran Rashid <irashid@cloudera.com>
Closes#13454 from squito/SPARK-15714.
If an RDD partition is cached on disk and the DiskStore file is lost, then reads of that cached partition will fail and the missing partition is supposed to be recomputed by a new task attempt. In the current BlockManager implementation, however, the missing file does not trigger any metadata updates / does not invalidate the cache, so subsequent task attempts will be scheduled on the same executor and the doomed read will be repeatedly retried, leading to repeated task failures and eventually a total job failure.
In order to fix this problem, the executor with the missing file needs to properly mark the corresponding block as missing so that it stops advertising itself as a cache location for that block.
This patch fixes this bug and adds an end-to-end regression test (in `FailureSuite`) and a set of unit tests (`in BlockManagerSuite`).
Author: Josh Rosen <joshrosen@databricks.com>
Closes#13473 from JoshRosen/handle-missing-cache-files.
## What changes were proposed in this pull request?
This PR corrects the remaining cases for using old accumulators.
This does not change some old accumulator usages below:
- `ImplicitSuite.scala` - Tests dedicated to old accumulator, for implicits with `AccumulatorParam`
- `AccumulatorSuite.scala` - Tests dedicated to old accumulator
- `JavaSparkContext.scala` - For supporting old accumulators for Java API.
- `debug.package.scala` - Usage with `HashSet[String]`. Currently, it seems no implementation for this. I might be able to write an anonymous class for this but I didn't because I think it is not worth writing a lot of codes only for this.
- `SQLMetricsSuite.scala` - This uses the old accumulator for checking type boxing. It seems new accumulator does not require type boxing for this case whereas the old one requires (due to the use of generic).
## How was this patch tested?
Existing tests cover this.
Author: hyukjinkwon <gurwls223@gmail.com>
Closes#13434 from HyukjinKwon/accum.
## What changes were proposed in this pull request?
1. The class allocated 4x space than needed as it was using `Int` to store the `Byte` values
2. If CircularBuffer isn't full, currently toString() will print some garbage chars along with the content written as is tries to print the entire array allocated for the buffer. The fix is to keep track of buffer getting full and don't print the tail of the buffer if it isn't full (suggestion by sameeragarwal over https://github.com/apache/spark/pull/12194#discussion_r64495331)
3. Simplified `toString()`
## How was this patch tested?
Added new test case
Author: Tejas Patil <tejasp@fb.com>
Closes#13351 from tejasapatil/circular_buffer.
## What changes were proposed in this pull request?
With this patch, TaskSetManager kills other running attempts when any one of the attempt succeeds for the same task. Also killed tasks will not be considered as failed tasks and they get listed separately in the UI and also shows the task state as KILLED instead of FAILED.
## How was this patch tested?
core\src\test\scala\org\apache\spark\ui\jobs\JobProgressListenerSuite.scala
core\src\test\scala\org\apache\spark\util\JsonProtocolSuite.scala
I have verified this patch manually by enabling spark.speculation as true, when any attempt gets succeeded then other running attempts are getting killed for the same task and other pending tasks are getting assigned in those. And also when any attempt gets killed then they are considered as KILLED tasks and not considered as FAILED tasks. Please find the attached screen shots for the reference.
Ref : https://github.com/apache/spark/pull/11916
Author: Devaraj K <devaraj@apache.org>
Closes#11996 from devaraj-kavali/SPARK-10530.
## What changes were proposed in this pull request?
This is a simple patch that makes package names for Java 8 test suites consistent. I moved everything to test.org.apache.spark to we can test package private APIs properly. Also added "java8" as the package name so we can easily run all the tests related to Java 8.
## How was this patch tested?
This is a test only change.
Author: Reynold Xin <rxin@databricks.com>
Closes#13364 from rxin/SPARK-15633.
## What changes were proposed in this pull request?
Temp directory used to save records is not deleted after program exit in DataFrameExample. Although it called deleteOnExit, it doesn't work as the directory is not empty. Similar things happend in ContextCleanerSuite. Update the code to make sure temp directory is deleted after program exit.
## How was this patch tested?
unit tests and local build.
Author: dding3 <ding.ding@intel.com>
Closes#13328 from dding3/master.
## What changes were proposed in this pull request?
Profiling a Spark job spilling large amount of intermediate data we found that significant portion of time is being spent in DiskObjectWriter.updateBytesWritten function. Looking at the code, we see that the function is being called too frequently to update the number of bytes written to disk. We should reduce the frequency to avoid this.
## How was this patch tested?
Tested by running the job on cluster and saw 20% CPU gain by this change.
Author: Sital Kedia <skedia@fb.com>
Closes#13332 from sitalkedia/DiskObjectWriter.
## What changes were proposed in this pull request?
This patch fixes a few integer overflows in `UnsafeSortDataFormat.copyRange()` and `ShuffleSortDataFormat copyRange()` that seems to be the most likely cause behind a number of `TimSort` contract violation errors seen in Spark 2.0 and Spark 1.6 while sorting large datasets.
## How was this patch tested?
Added a test in `ExternalSorterSuite` that instantiates a large array of the form of [150000000, 150000001, 150000002, ...., 300000000, 0, 1, 2, ..., 149999999] that triggers a `copyRange` in `TimSort.mergeLo` or `TimSort.mergeHi`. Note that the input dataset should contain at least 268.43 million rows with a certain data distribution for an overflow to occur.
Author: Sameer Agarwal <sameer@databricks.com>
Closes#13336 from sameeragarwal/timsort-bug.
This is a basic framework for testing the entire scheduler. The tests this adds aren't very interesting -- the point of this PR is just to setup the framework, to keep the initial change small, but it can be built upon to test more features (eg., speculation, killing tasks, blacklisting, etc.).
Author: Imran Rashid <irashid@cloudera.com>
Closes#8559 from squito/SPARK-10372-scheduler-integs.
## What changes were proposed in this pull request?
Currently a method `submitStage()` for waiting stages is called on every iteration of the event loop in `DAGScheduler` to submit all waiting stages, but most of them are not necessary because they are not related to Stage status.
The case we should try to submit waiting stages is only when their parent stages are successfully completed.
This elimination can improve `DAGScheduler` performance.
## How was this patch tested?
Added some checks and other existing tests, and our projects.
We have a project bottle-necked by `DAGScheduler`, having about 2000 stages.
Before this patch the almost all execution time in `Driver` process was spent to process `submitStage()` of `dag-scheduler-event-loop` thread but after this patch the performance was improved as follows:
| | total execution time | `dag-scheduler-event-loop` thread time | `submitStage()` |
|--------|---------------------:|---------------------------------------:|----------------:|
| Before | 760 sec | 710 sec | 667 sec |
| After | 440 sec | 14 sec | 10 sec |
Author: Takuya UESHIN <ueshin@happy-camper.st>
Closes#12060 from ueshin/issues/SPARK-14269.
## What changes were proposed in this pull request?
1. Making 'name' field of RDDInfo mutable.
2. In StorageListener: catching the fact that RDD's name was changed and updating it in RDDInfo.
## How was this patch tested?
1. Manual verification - the 'Storage' tab now behaves as expected.
2. The commit also contains a new unit test which verifies this.
Author: Lukasz <lgieron@gmail.com>
Closes#13264 from lgieron/SPARK-9044.
## What changes were proposed in this pull request?
This patch renames various scheduler backends to make them consistent:
- LocalScheduler -> LocalSchedulerBackend
- AppClient -> StandaloneAppClient
- AppClientListener -> StandaloneAppClientListener
- SparkDeploySchedulerBackend -> StandaloneSchedulerBackend
- CoarseMesosSchedulerBackend -> MesosCoarseGrainedSchedulerBackend
- MesosSchedulerBackend -> MesosFineGrainedSchedulerBackend
## How was this patch tested?
Updated test cases to reflect the name change.
Author: Reynold Xin <rxin@databricks.com>
Closes#13288 from rxin/SPARK-15518.
## What changes were proposed in this pull request?
Previously, SPARK-8893 added the constraints on positive number of partitions for repartition/coalesce operations in general. This PR adds one missing part for that and adds explicit two testcases.
**Before**
```scala
scala> sc.parallelize(1 to 5).coalesce(0)
java.lang.IllegalArgumentException: requirement failed: Number of partitions (0) must be positive.
...
scala> sc.parallelize(1 to 5).repartition(0).collect()
res1: Array[Int] = Array() // empty
scala> spark.sql("select 1").coalesce(0)
res2: org.apache.spark.sql.Dataset[org.apache.spark.sql.Row] = [1: int]
scala> spark.sql("select 1").coalesce(0).collect()
java.lang.IllegalArgumentException: requirement failed: Number of partitions (0) must be positive.
scala> spark.sql("select 1").repartition(0)
res3: org.apache.spark.sql.Dataset[org.apache.spark.sql.Row] = [1: int]
scala> spark.sql("select 1").repartition(0).collect()
res4: Array[org.apache.spark.sql.Row] = Array() // empty
```
**After**
```scala
scala> sc.parallelize(1 to 5).coalesce(0)
java.lang.IllegalArgumentException: requirement failed: Number of partitions (0) must be positive.
...
scala> sc.parallelize(1 to 5).repartition(0)
java.lang.IllegalArgumentException: requirement failed: Number of partitions (0) must be positive.
...
scala> spark.sql("select 1").coalesce(0)
java.lang.IllegalArgumentException: requirement failed: Number of partitions (0) must be positive.
...
scala> spark.sql("select 1").repartition(0)
java.lang.IllegalArgumentException: requirement failed: Number of partitions (0) must be positive.
...
```
## How was this patch tested?
Pass the Jenkins tests with new testcases.
Author: Dongjoon Hyun <dongjoon@apache.org>
Closes#13282 from dongjoon-hyun/SPARK-15512.
## What changes were proposed in this pull request?
This PR fixes some obsolete comments and assertion in `takeSample` testcase of `RDDSuite.scala`.
## How was this patch tested?
This fixes the testcase only.
Author: Dongjoon Hyun <dongjoon@apache.org>
Closes#13260 from dongjoon-hyun/SPARK-15481.
## What changes were proposed in this pull request?
Currently command `ADD FILE|JAR <filepath | jarpath>` is supported natively in SparkSQL. However, when this command is run, the file/jar is added to the resources that can not be looked up by `LIST FILE(s)|JAR(s)` command because the `LIST` command is passed to Hive command processor in Spark-SQL or simply not supported in Spark-shell. There is no way users can find out what files/jars are added to the spark context.
Refer to [Hive commands](https://cwiki.apache.org/confluence/display/Hive/LanguageManual+Cli)
This PR is to support following commands:
`LIST (FILE[s] [filepath ...] | JAR[s] [jarfile ...])`
### For example:
##### LIST FILE(s)
```
scala> spark.sql("add file hdfs://bdavm009.svl.ibm.com:8020/tmp/test.txt")
res1: org.apache.spark.sql.DataFrame = []
scala> spark.sql("add file hdfs://bdavm009.svl.ibm.com:8020/tmp/test1.txt")
res2: org.apache.spark.sql.DataFrame = []
scala> spark.sql("list file hdfs://bdavm009.svl.ibm.com:8020/tmp/test1.txt").show(false)
+----------------------------------------------+
|result |
+----------------------------------------------+
|hdfs://bdavm009.svl.ibm.com:8020/tmp/test1.txt|
+----------------------------------------------+
scala> spark.sql("list files").show(false)
+----------------------------------------------+
|result |
+----------------------------------------------+
|hdfs://bdavm009.svl.ibm.com:8020/tmp/test1.txt|
|hdfs://bdavm009.svl.ibm.com:8020/tmp/test.txt |
+----------------------------------------------+
```
##### LIST JAR(s)
```
scala> spark.sql("add jar /Users/xinwu/spark/core/src/test/resources/TestUDTF.jar")
res9: org.apache.spark.sql.DataFrame = [result: int]
scala> spark.sql("list jar TestUDTF.jar").show(false)
+---------------------------------------------+
|result |
+---------------------------------------------+
|spark://192.168.1.234:50131/jars/TestUDTF.jar|
+---------------------------------------------+
scala> spark.sql("list jars").show(false)
+---------------------------------------------+
|result |
+---------------------------------------------+
|spark://192.168.1.234:50131/jars/TestUDTF.jar|
+---------------------------------------------+
```
## How was this patch tested?
New test cases are added for Spark-SQL, Spark-Shell and SparkContext API code path.
Author: Xin Wu <xinwu@us.ibm.com>
Author: xin Wu <xinwu@us.ibm.com>
Closes#13212 from xwu0226/list_command.
## What changes were proposed in this pull request?
In general, the Web UI doesn't need to store the Accumulator/AccumulableInfo for every task. It only needs the Accumulator values.
In this PR, it creates new UIData classes to store the necessary fields and make `JobProgressListener` store only these new classes, so that `JobProgressListener` won't store Accumulator/AccumulableInfo and the size of `JobProgressListener` becomes pretty small. I also eliminates `AccumulableInfo` from `SQLListener` so that we don't keep any references for those unused `AccumulableInfo`s.
## How was this patch tested?
I ran two tests reported in JIRA locally:
The first one is:
```
val data = spark.range(0, 10000, 1, 10000)
data.cache().count()
```
The retained size of JobProgressListener decreases from 60.7M to 6.9M.
The second one is:
```
import org.apache.spark.ml.CC
import org.apache.spark.sql.SQLContext
val sqlContext = SQLContext.getOrCreate(sc)
CC.runTest(sqlContext)
```
This test won't cause OOM after applying this patch.
Author: Shixiong Zhu <shixiong@databricks.com>
Closes#13153 from zsxwing/memory.
## What changes were proposed in this pull request?
A writer lock could be acquired when 1) create a new block 2) remove a block 3) evict a block to disk. 1) and 3) could happen in the same time within the same task, all of them could happen in the same time outside a task. It's OK that when someone try to grab the write block for a block, but the block is acquired by another one that has the same task attempt id.
This PR remove the check.
## How was this patch tested?
Updated existing tests.
Author: Davies Liu <davies@databricks.com>
Closes#13082 from davies/write_lock_conflict.
## What changes were proposed in this pull request?
Remove redundant set master in OutputCommitCoordinatorIntegrationSuite, as we are already setting it in SparkContext below on line 43.
## How was this patch tested?
existing tests
Author: Sandeep Singh <sandeep@techaddict.me>
Closes#13168 from techaddict/minor-1.
## What changes were proposed in this pull request?
Since we support forced spilling for Spillable, which only works in OnHeap mode, different from other SQL operators (could be OnHeap or OffHeap), we should considering the mode of consumer before calling trigger forced spilling.
## How was this patch tested?
Add new test.
Author: Davies Liu <davies@databricks.com>
Closes#13151 from davies/fix_mode.
## What changes were proposed in this pull request?
I use Intellj-IDEA to search usage of deprecate SparkContext.accumulator in the whole spark project, and update the code.(except those test code for accumulator method itself)
## How was this patch tested?
Exisiting unit tests
Author: WeichenXu <WeichenXu123@outlook.com>
Closes#13112 from WeichenXu123/update_accuV2_in_mllib.
## What changes were proposed in this pull request?
`DAGScheduler`sometimes generate incorrect stage graph.
Suppose you have the following DAG:
```
[A] <--(s_A)-- [B] <--(s_B)-- [C] <--(s_C)-- [D]
\ /
<-------------
```
Note: [] means an RDD, () means a shuffle dependency.
Here, RDD `B` has a shuffle dependency on RDD `A`, and RDD `C` has shuffle dependency on both `B` and `A`. The shuffle dependency IDs are numbers in the `DAGScheduler`, but to make the example easier to understand, let's call the shuffled data from `A` shuffle dependency ID `s_A` and the shuffled data from `B` shuffle dependency ID `s_B`.
The `getAncestorShuffleDependencies` method in `DAGScheduler` (incorrectly) does not check for duplicates when it's adding ShuffleDependencies to the parents data structure, so for this DAG, when `getAncestorShuffleDependencies` gets called on `C` (previous of the final RDD), `getAncestorShuffleDependencies` will return `s_A`, `s_B`, `s_A` (`s_A` gets added twice: once when the method "visit"s RDD `C`, and once when the method "visit"s RDD `B`). This is problematic because this line of code: https://github.com/apache/spark/blob/8ef3399/core/src/main/scala/org/apache/spark/scheduler/DAGScheduler.scala#L289 then generates a new shuffle stage for each dependency returned by `getAncestorShuffleDependencies`, resulting in duplicate map stages that compute the map output from RDD `A`.
As a result, `DAGScheduler` generates the following stages and their parents for each shuffle:
| | stage | parents |
|----|----|----|
| s_A | ShuffleMapStage 2 | List() |
| s_B | ShuffleMapStage 1 | List(ShuffleMapStage 0) |
| s_C | ShuffleMapStage 3 | List(ShuffleMapStage 1, ShuffleMapStage 2) |
| - | ResultStage 4 | List(ShuffleMapStage 3) |
The stage for s_A should be `ShuffleMapStage 0`, but the stage for `s_A` is generated twice as `ShuffleMapStage 2` and `ShuffleMapStage 0` is overwritten by `ShuffleMapStage 2`, and the stage `ShuffleMap Stage1` keeps referring the old stage `ShuffleMapStage 0`.
This patch is fixing it.
## How was this patch tested?
I added the sample RDD graph to show the illegal stage graph to `DAGSchedulerSuite`.
Author: Takuya UESHIN <ueshin@happy-camper.st>
Closes#12655 from ueshin/issues/SPARK-13902.
## What changes were proposed in this pull request?
Break copyAndReset into two methods copy and reset instead of just one.
## How was this patch tested?
Existing Tests
Author: Sandeep Singh <sandeep@techaddict.me>
Closes#12936 from techaddict/SPARK-15080.
## What changes were proposed in this pull request?
When we acquire execution memory, we do a lot of things between shrinking the storage memory pool and enlarging the execution memory pool. In particular, we call `memoryStore.evictBlocksToFreeSpace`, which may do a lot of I/O and can throw exceptions. If an exception is thrown, the pool sizes on that executor will be in a bad state.
This patch minimizes the things we do between the two calls to make the resizing more atomic.
## How was this patch tested?
Jenkins.
Author: Andrew Or <andrew@databricks.com>
Closes#13039 from andrewor14/safer-pool.
## What changes were proposed in this pull request?
After SPARK-14669 it seems the sort time metric includes both spill and record insertion time. This makes it not very useful since the metric becomes close to the total execution time of the node.
We should track just the time spent for in-memory sort, as before.
## How was this patch tested?
Verified metric in the UI, also unit test on UnsafeExternalRowSorter.
cc davies
Author: Eric Liang <ekl@databricks.com>
Author: Eric Liang <ekhliang@gmail.com>
Closes#13035 from ericl/fix-metrics.
Sending un-updated accumulators back to driver makes no sense, as merging a zero value accumulator is a no-op. We should only send back updated accumulators, to save network IO.
new test in `TaskContextSuite`
Author: Wenchen Fan <wenchen@databricks.com>
Closes#12899 from cloud-fan/acc.
Without this, the code would build an invalid spark-submit command line,
and a more cryptic error would be presented to the user. Also, expose
a constant that allows users to set a dummy resource in cases where
they don't need an actual resource file; for backwards compatibility,
that uses the same "spark-internal" resource that Spark itself uses.
Tested via unit tests, run-example, spark-shell, and running the
thrift server with mixed spark and hive command line arguments.
Author: Marcelo Vanzin <vanzin@cloudera.com>
Closes#12909 from vanzin/SPARK-11249.
## What changes were proposed in this pull request?
Currently PipedRDD internally uses PrintWriter to write data to the stdin of the piped process, which by default uses a BufferedWriter of buffer size 8k. In our experiment, we have seen that 8k buffer size is too small and the job spends significant amount of CPU time in system calls to copy the data. We should have a way to configure the buffer size for the writer.
## How was this patch tested?
Ran PipedRDDSuite tests.
Author: Sital Kedia <skedia@fb.com>
Closes#12309 from sitalkedia/bufferedPipedRDD.
## What changes were proposed in this pull request?
Removed blockTransferService and sparkFilesDir from SparkEnv since they're rarely used and don't need to be in stored in the env. Edited their few usages to accommodate the change.
## How was this patch tested?
ran dev/run-tests locally
Author: Alex Bozarth <ajbozart@us.ibm.com>
Closes#12970 from ajbozarth/spark10653.
The main issue we are trying to solve is the memory bloat of the Driver when tasks request the map output statuses. This means with a large number of tasks you either need a huge amount of memory on Driver or you have to repartition to smaller number. This makes it really difficult to run over say 50000 tasks.
The main issues that cause the memory bloat are:
1) no flow control on sending the map output status responses. We serialize the map status output and then hand off to netty to send. netty is sending asynchronously and it can't send them fast enough to keep up with incoming requests so we end up with lots of copies of the serialized map output statuses sitting there and this causes huge bloat when you have 10's of thousands of tasks and map output status is in the 10's of MB.
2) When initial reduce tasks are started up, they all request the map output statuses from the Driver. These requests are handled by multiple threads in parallel so even though we check to see if we have a cached version, initially when we don't have a cached version yet, many of initial requests can all end up serializing the exact same map output statuses.
This patch does a couple of things:
- When the map output status size is over a threshold (default 512K) then it uses broadcast to send the map statuses. This means we no longer serialize a large map output status and thus we don't have issues with memory bloat. the messages sizes are now in the 300-400 byte range and the map status output are broadcast. If its under the threadshold it sends it as before, the message contains the DIRECT indicator now.
- synchronize the incoming requests to allow one thread to cache the serialized output and broadcast the map output status that can then be used by everyone else. This ensures we don't create multiple broadcast variables when we don't need to. To ensure this happens I added a second thread pool which the Dispatcher hands the requests to so that those threads can block without blocking the main dispatcher threads (which would cause things like heartbeats and such not to come through)
Note that some of design and code was contributed by mridulm
## How was this patch tested?
Unit tests and a lot of manually testing.
Ran with akka and netty rpc. Ran with both dynamic allocation on and off.
one of the large jobs I used to test this was a join of 15TB of data. it had 200,000 map tasks, and 20,000 reduce tasks. Executors ranged from 200 to 2000. This job ran successfully with 5GB of memory on the driver with these changes. Without these changes I was using 20GB and only had 500 reduce tasks. The job has 50mb of serialized map output statuses and took roughly the same amount of time for the executors to get the map output statuses as before.
Ran a variety of other jobs, from large wordcounts to small ones not using broadcasts.
Author: Thomas Graves <tgraves@staydecay.corp.gq1.yahoo.com>
Closes#12113 from tgravescs/SPARK-1239.
This patch has the new logic from #8512 that uses a parallel collection to compute partitions in UnionRDD. The rest of #8512 added an alternative code path for calculating splits in S3, but that isn't necessary to get the same speedup. The underlying problem wasn't that bulk listing wasn't used, it was that an extra FileStatus was retrieved for each file. The fix was just committed as [HADOOP-12810](https://issues.apache.org/jira/browse/HADOOP-12810). (I think the original commit also used a single prefix to enumerate all paths, but that isn't always helpful and it was removed in later versions so there is no need for SparkS3Utils.)
I tested this using the same table that piapiaozhexiu was using. Calculating splits for a 10-day period took 25 seconds with this change and HADOOP-12810, which is on par with the results from #8512.
Author: Ryan Blue <blue@apache.org>
Author: Cheolsoo Park <cheolsoop@netflix.com>
Closes#11242 from rdblue/SPARK-9926-parallelize-union-rdd.
Similar to https://github.com/apache/spark/pull/8639
This change rejects offers for 120s when reached `spark.cores.max` in coarse-grained mode to mitigate offer starvation. This prevents Mesos to send us offers again and again, starving other frameworks. This is especially problematic when running many small frameworks on the same Mesos cluster, e.g. many small Sparks streaming jobs, and cause the bigger spark jobs to stop receiving offers. By rejecting the offers for a long period of time, they become available to those other frameworks.
Author: Sebastien Rainville <sebastien@hopper.com>
Closes#10924 from sebastienrainville/master.
Remove history server functionality from standalone Master. Previously, the Master process rebuilt a SparkUI once the application was completed which sometimes caused problems, such as OOM, when the application event log is large (see SPARK-6270). Keeping this functionality out of the Master will help to simplify the process and increase stability.
Testing for this change included running core unit tests and manually running an application on a standalone cluster to verify that it completed successfully and that the Master UI functioned correctly. Also added 2 unit tests to verify killing an application and driver from MasterWebUI makes the correct request to the Master.
Author: Bryan Cutler <cutlerb@gmail.com>
Closes#10991 from BryanCutler/remove-history-master-SPARK-12299.
## What changes were proposed in this pull request?
We currently have a single suite that is very large, making it difficult to maintain and play with specific primitives. This patch reorganizes the file by creating multiple benchmark suites in a single package.
Most of the changes are straightforward move of code. On top of the code moving, I did:
1. Use SparkSession instead of SQLContext.
2. Turned most benchmark scenarios into a their own test cases, rather than having multiple scenarios in a single test case, which takes forever to run.
## How was this patch tested?
This is a test only change.
Author: Reynold Xin <rxin@databricks.com>
Closes#12891 from rxin/SPARK-15115.
## What changes were proposed in this pull request?
Currently only a list of users can be specified for view and modify acls. This change enables a group of admins/devs/users to be provisioned for viewing and modifying Spark jobs.
**Changes Proposed in the fix**
Three new corresponding config entries have been added where the user can specify the groups to be given access.
```
spark.admin.acls.groups
spark.modify.acls.groups
spark.ui.view.acls.groups
```
New config entries were added because specifying the users and groups explicitly is a better and cleaner way compared to specifying them in the existing config entry using a delimiter.
A generic trait has been introduced to provide the user to group mapping which makes it pluggable to support a variety of mapping protocols - similar to the one used in hadoop. A default unix shell based implementation has been provided.
Custom user to group mapping protocol can be specified and configured by the entry ```spark.user.groups.mapping```
**How the patch was Tested**
We ran different spark jobs setting the config entries in combinations of admin, modify and ui acls. For modify acls we tried killing the job stages from the ui and using yarn commands. For view acls we tried accessing the UI tabs and the logs. Headless accounts were used to launch these jobs and different users tried to modify and view the jobs to ensure that the groups mapping applied correctly.
Additional Unit tests have been added without modifying the existing ones. These test for different ways of setting the acls through configuration and/or API and validate the expected behavior.
Author: Dhruve Ashar <dhruveashar@gmail.com>
Closes#12760 from dhruve/impr/SPARK-4224.
## What changes were proposed in this pull request?
This patch changes our micro-benchmark util to allow setting different iteration numbers for different test cases. For some of our benchmarks, turning off whole-stage codegen can make the runtime 20X slower, making it very difficult to run a large number of times without substantially shortening the input cardinality.
With this change, I set the default num iterations to 2 for whole stage codegen off, and 5 for whole stage codegen on. I also updated some results.
## How was this patch tested?
N/A - this is a test util.
Author: Reynold Xin <rxin@databricks.com>
Closes#12884 from rxin/SPARK-15107.
## What changes were proposed in this pull request?
coalesce doesn't handle UnionRDD with partial locality properly. I had a user who had a UnionRDD that was made up of mapPartitionRDD without preferred locations and a checkpointedRDD with preferred locations (getting from hdfs). It took the driver over 20 minutes to setup the groups and put the partitions into those groups before it even started any tasks. Even perhaps worse is it didn't end up with the number of partitions he was asking for because it didn't put a partition in each of the groups properly.
The changes in this patch get rid of a n^2 while loop that was causing the 20 minutes, it properly distributes the partitions to have at least one per group, and it changes from using the rotation iterator which got the preferred locations many times to get all the preferred locations once up front.
Note that the n^2 while loop that I removed in setupGroups took so long because all of the partitions with preferred locations were already assigned to group, so it basically looped through every single one and wasn't ever able to assign it. At the time I had 960 partitions with preferred locations and 1020 without and did the outer while loop 319 times because that is the # of groups left to create. Note that each of those times through the inner while loop is going off to hdfs to get the block locations, so this is extremely inefficient.
## How was the this patch tested?
Added unit tests for this case and ran existing ones that applied to make sure no regressions.
Also manually tested on the users production job to make sure it fixed their issue. It created the proper number of partitions and now it takes about 6 seconds rather then 20 minutes.
I did also run some basic manual tests with spark-shell doing coalesced to smaller number, same number, and then greater with shuffle.
Author: Thomas Graves <tgraves@prevailsail.corp.gq1.yahoo.com>
Closes#11327 from tgravescs/SPARK-11316.
## What changes were proposed in this pull request?
Added tests for ListAccumulator and LegacyAccumulatorWrapper, test for ListAccumulator is one similar to old Collection Accumulators
## How was this patch tested?
Ran tests locally.
cc rxin
Author: Sandeep Singh <sandeep@techaddict.me>
Closes#12862 from techaddict/SPARK-15082.
## What changes were proposed in this pull request?
Remove AccumulatorV2.localValue and keep only value
## How was this patch tested?
existing tests
Author: Sandeep Singh <sandeep@techaddict.me>
Closes#12865 from techaddict/SPARK-15087.
## What changes were proposed in this pull request?
This patch moves AccumulatorV2 and subclasses into util package.
## How was this patch tested?
Updated relevant tests.
Author: Reynold Xin <rxin@databricks.com>
Closes#12863 from rxin/SPARK-15081.
## What changes were proposed in this pull request?
This patch removes AverageAccumulator and adds the ability to compute average to LongAccumulator and DoubleAccumulator. The patch also improves documentation for the two accumulators.
## How was this patch tested?
Added unit tests for this.
Author: Reynold Xin <rxin@databricks.com>
Closes#12858 from rxin/SPARK-15079.
## What changes were proposed in this pull request?
This updates the java-/scala- doc for setLocalProperty to document heritability of localProperties. This also adds tests for that behaviour.
## How was this patch tested?
Tests pass. New tests were added.
Author: Marcin Tustin <marcin.tustin@gmail.com>
Closes#12455 from marcintustin/SPARK-14685.
## What changes were proposed in this pull request?
NewAccumulator isn't the best name if we ever come up with v3 of the API.
## How was this patch tested?
Updated tests to reflect the change.
Author: Reynold Xin <rxin@databricks.com>
Closes#12827 from rxin/SPARK-15049.
## What changes were proposed in this pull request?
This PR proposes to use ConcurrentHashMap in place of HashMap for NewAccumulator.originals
This should result in better performance.
## How was this patch tested?
Existing unit test suite
cloud-fan
Author: tedyu <yuzhihong@gmail.com>
Closes#12776 from tedyu/master.
## What changes were proposed in this pull request?
`AccumulatorContext` is not thread-safe, that's why all of its methods are synchronized. However, there is one exception: the `AccumulatorContext.originals`. `NewAccumulator` use it to check if it's registered, which is wrong as it's not synchronized.
This PR mark `AccumulatorContext.originals` as `private` and now all access to `AccumulatorContext` is synchronized.
## How was this patch tested?
I verified it locally. To be safe, we can let jenkins test it many times to make sure this problem is gone.
Author: Wenchen Fan <wenchen@databricks.com>
Closes#12773 from cloud-fan/debug.
https://issues.apache.org/jira/browse/SPARK-14935
In DistributedSuite, the "local-cluster format" test actually launches a bunch of clusters, but this doesn't seem necessary for what should just be a unit test of a regex. We should clean up the code so that this is testable without actually launching a cluster, which should buy us about 20 seconds per build.
Passed unit test on my local machine
Author: Xin Ren <iamshrek@126.com>
Closes#12744 from keypointt/SPARK-14935.
## What changes were proposed in this pull request?
This PR introduces a new accumulator API which is much simpler than before:
1. the type hierarchy is simplified, now we only have an `Accumulator` class
2. Combine `initialValue` and `zeroValue` concepts into just one concept: `zeroValue`
3. there in only one `register` method, the accumulator registration and cleanup registration are combined.
4. the `id`,`name` and `countFailedValues` are combined into an `AccumulatorMetadata`, and is provided during registration.
`SQLMetric` is a good example to show the simplicity of this new API.
What we break:
1. no `setValue` anymore. In the new API, the intermedia type can be different from the result type, it's very hard to implement a general `setValue`
2. accumulator can't be serialized before registered.
Problems need to be addressed in follow-ups:
1. with this new API, `AccumulatorInfo` doesn't make a lot of sense, the partial output is not partial updates, we need to expose the intermediate value.
2. `ExceptionFailure` should not carry the accumulator updates. Why do users care about accumulator updates for failed cases? It looks like we only use this feature to update the internal metrics, how about we sending a heartbeat to update internal metrics after the failure event?
3. the public event `SparkListenerTaskEnd` carries a `TaskMetrics`. Ideally this `TaskMetrics` don't need to carry external accumulators, as the only method of `TaskMetrics` that can access external accumulators is `private[spark]`. However, `SQLListener` use it to retrieve sql metrics.
## How was this patch tested?
existing tests
Author: Wenchen Fan <wenchen@databricks.com>
Closes#12612 from cloud-fan/acc.
## What changes were proposed in this pull request?
With the addition of ExternalClusterManager(ECM) interface in PR #11723, any cluster manager can now be integrated with Spark. It was suggested in ExternalClusterManager PR that one of the existing cluster managers should start using the new interface to ensure that the API is correct. Ideally, all the existing cluster managers should eventually use the ECM interface but as a first step yarn will now use the ECM interface. This PR refactors YARN code from SparkContext.createTaskScheduler function into YarnClusterManager that implements ECM interface.
## How was this patch tested?
Since this is refactoring, no new tests has been added. Existing tests have been run. Basic manual testing with YARN was done too.
Author: Hemant Bhanawat <hemant@snappydata.io>
Closes#12641 from hbhanawat/yarnClusterMgr.
## What changes were proposed in this pull request?
Java `sampleByKey` methods should accept `Map` with `java.lang.Double` values
## How was this patch tested?
Existing (updated) Jenkins tests
Author: Sean Owen <sowen@cloudera.com>
Closes#12637 from srowen/SPARK-14873.
## What changes were proposed in this pull request?
Implement some `hashCode` and `equals` together in order to enable the scalastyle.
This is a first batch, I will continue to implement them but I wanted to know your thoughts.
Author: Joan <joan@goyeau.com>
Closes#12157 from joan38/SPARK-6429-HashCode-Equals.
## What changes were proposed in this pull request?
Spark currently uses TimSort for all in-memory sorts, including sorts done for shuffle. One low-hanging fruit is to use radix sort when possible (e.g. sorting by integer keys). This PR adds a radix sort implementation to the unsafe sort package and switches shuffles and sorts to use it when possible.
The current implementation does not have special support for null values, so we cannot radix-sort `LongType`. I will address this in a follow-up PR.
## How was this patch tested?
Unit tests, enabling radix sort on existing tests. Microbenchmark results:
```
Running benchmark: radix sort 25000000
Java HotSpot(TM) 64-Bit Server VM 1.8.0_66-b17 on Linux 3.13.0-44-generic
Intel(R) Core(TM) i7-4600U CPU 2.10GHz
radix sort 25000000: Best/Avg Time(ms) Rate(M/s) Per Row(ns) Relative
-------------------------------------------------------------------------------------------
reference TimSort key prefix array 15546 / 15859 1.6 621.9 1.0X
reference Arrays.sort 2416 / 2446 10.3 96.6 6.4X
radix sort one byte 133 / 137 188.4 5.3 117.2X
radix sort two bytes 255 / 258 98.2 10.2 61.1X
radix sort eight bytes 991 / 997 25.2 39.6 15.7X
radix sort key prefix array 1540 / 1563 16.2 61.6 10.1X
```
I also ran a mix of the supported TPCDS queries and compared TimSort vs RadixSort metrics. The overall benchmark ran ~10% faster with radix sort on. In the breakdown below, the radix-enabled sort phases averaged about 20x faster than TimSort, however sorting is only a small fraction of the overall runtime. About half of the TPCDS queries were able to take advantage of radix sort.
```
TPCDS on master: 2499s real time, 8185s executor
- 1171s in TimSort, avg 267 MB/s
(note the /s accounting is weird here since dataSize counts the record sizes too)
TPCDS with radix enabled: 2294s real time, 7391s executor
- 596s in TimSort, avg 254 MB/s
- 26s in radix sort, avg 4.2 GB/s
```
cc davies rxin
Author: Eric Liang <ekl@databricks.com>
Closes#12490 from ericl/sort-benchmark.
## What changes were proposed in this pull request?
In general, `onDisconnected` is for dealing with unexpected network disconnections. When RpcEnv.shutdown is called, the disconnections are expected so RpcEnv should not fire these events.
This PR moves `dispatcher.stop()` above closing the connections so that when stopping RpcEnv, the endpoints won't receive `onDisconnected` events.
In addition, Outbox should not close the client since it will be reused by others. This PR fixes it as well.
## How was this patch tested?
test("SPARK-14699: RpcEnv.shutdown should not fire onDisconnected events")
Author: Shixiong Zhu <shixiong@databricks.com>
Closes#12481 from zsxwing/SPARK-14699.
## What changes were proposed in this pull request?
In #9241 It implemented a mechanism to call spill() on those SQL operators that support spilling if there is not enough memory for execution.
But ExternalSorter and AppendOnlyMap in Spark core are not worked. So this PR make them benefit from #9241. Now when there is not enough memory for execution, it can get memory by spilling ExternalSorter and AppendOnlyMap in Spark core.
## How was this patch tested?
add two unit tests for it.
Author: Lianhui Wang <lianhuiwang09@gmail.com>
Closes#10024 from lianhuiwang/SPARK-4452-2.
## What changes were proposed in this pull request?
the `Accumulable.internal` flag is only used to avoid registering internal accumulators for 2 certain cases:
1. `TaskMetrics.createTempShuffleReadMetrics`: the accumulators in the temp shuffle read metrics should not be registered.
2. `TaskMetrics.fromAccumulatorUpdates`: the created task metrics is only used to post event, accumulators inside it should not be registered.
For 1, we can create a `TempShuffleReadMetrics` that don't create accumulators, just keep the data and merge it at last.
For 2, we can un-register these accumulators immediately.
TODO: remove `internal` flag in `AccumulableInfo` with followup PR
## How was this patch tested?
existing tests.
Author: Wenchen Fan <wenchen@databricks.com>
Closes#12525 from cloud-fan/acc.
## What changes were proposed in this pull request?
The DAG visualization can cause an OOM when generating the DOT file.
This happens because clusters are not correctly deduped by a contains
check because they use the default equals implementation. This adds a
working equals implementation.
## How was this patch tested?
This adds a test suite that checks the new equals implementation.
Author: Ryan Blue <blue@apache.org>
Closes#12437 from rdblue/SPARK-14679-fix-ui-oom.
## What changes were proposed in this pull request?
Before this PR, we create accumulators at driver side(and register them) and send them to executor side, then we create `TaskMetrics` with these accumulators at executor side.
After this PR, we will create `TaskMetrics` at driver side and send it to executor side, so that we can create accumulators inside `TaskMetrics` directly, which is cleaner.
## How was this patch tested?
existing tests.
Author: Wenchen Fan <wenchen@databricks.com>
Closes#12472 from cloud-fan/acc.
## What changes were proposed in this pull request?
This PR adds support for specifying an optional custom coalescer to the `coalesce()` method. Currently I have only added this feature to the `RDD` interface, and once we sort out the details we can proceed with adding this feature to the other APIs (`Dataset` etc.)
## How was this patch tested?
Added a unit test for this functionality.
/cc rxin (per our discussion on the mailing list)
Author: Nezih Yigitbasi <nyigitbasi@netflix.com>
Closes#11865 from nezihyigitbasi/custom_coalesce_policy.
When `Await.result` throws an exception which originated from a different thread, the resulting stacktrace doesn't include the path leading to the `Await.result` call itself, making it difficult to identify the impact of these exceptions. For example, I've seen cases where broadcast cleaning errors propagate to the main thread and crash it but the resulting stacktrace doesn't include any of the main thread's code, making it difficult to pinpoint which exception crashed that thread.
This patch addresses this issue by explicitly catching, wrapping, and re-throwing exceptions that are thrown by `Await.result`.
I tested this manually using 16b31c8251, a patch which reproduces an issue where an RPC exception which occurs while unpersisting RDDs manages to crash the main thread without any useful stacktrace, and verified that informative, full stacktraces were generated after applying the fix in this PR.
/cc rxin nongli yhuai anabranch
Author: Josh Rosen <joshrosen@databricks.com>
Closes#12433 from JoshRosen/wrap-and-rethrow-await-exceptions.
## What changes were proposed in this pull request?
The sort shuffle manager has been the default since Spark 1.2. It is time to remove the old hash shuffle manager.
## How was this patch tested?
Removed some tests related to the old manager.
Author: Reynold Xin <rxin@databricks.com>
Closes#12423 from rxin/SPARK-14667.
## What changes were proposed in this pull request?
This PR is a follow up for https://github.com/apache/spark/pull/12417, now we always track input/output/shuffle metrics in spark JSON protocol and status API.
Most of the line changes are because of re-generating the gold answer for `HistoryServerSuite`, and we add a lot of 0 values for read/write metrics.
## How was this patch tested?
existing tests.
Author: Wenchen Fan <wenchen@databricks.com>
Closes#12462 from cloud-fan/follow.
## What changes were proposed in this pull request?
When there are multiple tests running, "NettyBlockTransferServiceSuite.can bind to a specific port twice and the second increments" may fail.
E.g., assume there are 2 tests running. Here are the execution order to reproduce the test failure.
| Execution Order | Test 1 | Test 2 |
| ------------- | ------------- | ------------- |
| 1 | service0 binds to 17634 | |
| 2 | | service0 binds to 17635 (17634 is occupied) |
| 3 | service1 binds to 17636 | |
| 4 | pass test | |
| 5 | service0.close (release 17634) | |
| 6 | | service1 binds to 17634 |
| 7 | | `service1.port should be (service0.port + 1)` fails (17634 != 17635 + 1) |
Here is an example in Jenkins: https://amplab.cs.berkeley.edu/jenkins/view/Spark%20QA%20Test/job/spark-master-test-maven-hadoop-2.2/786/testReport/junit/org.apache.spark.network.netty/NettyBlockTransferServiceSuite/can_bind_to_a_specific_port_twice_and_the_second_increments/
This PR makes two changes:
- Use a random port between 17634 and 27634 to reduce the possibility of port conflicts.
- Make `service1` use `service0.port` to bind to avoid the above race condition.
## How was this patch tested?
Jenkins unit tests.
Author: Shixiong Zhu <shixiong@databricks.com>
Closes#12477 from zsxwing/SPARK-14713.
## What changes were proposed in this pull request?
This commit adds support for pluggable cluster manager. And also allows a cluster manager to clean up tasks without taking the parent process down.
To plug a new external cluster manager, ExternalClusterManager trait should be implemented. It returns task scheduler and backend scheduler that will be used by SparkContext to schedule tasks. An external cluster manager is registered using the java.util.ServiceLoader mechanism (This mechanism is also being used to register data sources like parquet, json, jdbc etc.). This allows auto-loading implementations of ExternalClusterManager interface.
Currently, when a driver fails, executors exit using system.exit. This does not bode well for cluster managers that would like to reuse the parent process of an executor. Hence,
1. Moving system.exit to a function that can be overriden in subclasses of CoarseGrainedExecutorBackend.
2. Added functionality of killing all the running tasks in an executor.
## How was this patch tested?
ExternalClusterManagerSuite.scala was added to test this patch.
Author: Hemant Bhanawat <hemant@snappydata.io>
Closes#11723 from hbhanawat/pluggableScheduler.
## What changes were proposed in this pull request?
Part of the reason why TaskMetrics and its callers are complicated are due to the optional metrics we collect, including input, output, shuffle read, and shuffle write. I think we can always track them and just assign 0 as the initial values. It is usually very obvious whether a task is supposed to read any data or not. By always tracking them, we can remove a lot of map, foreach, flatMap, getOrElse(0L) calls throughout Spark.
This patch also changes a few behaviors.
1. Removed the distinction of data read/write methods (e.g. Hadoop, Memory, Network, etc).
2. Accumulate all data reads and writes, rather than only the first method. (Fixes SPARK-5225)
## How was this patch tested?
existing tests.
This is bases on https://github.com/apache/spark/pull/12388, with more test fixes.
Author: Reynold Xin <rxin@databricks.com>
Author: Wenchen Fan <wenchen@databricks.com>
Closes#12417 from cloud-fan/metrics-refactor.
## What changes were proposed in this pull request?
This patch removes some of the deprecated APIs in TaskMetrics. This is part of my bigger effort to simplify accumulators and task metrics.
## How was this patch tested?
N/A - only removals
Author: Reynold Xin <rxin@databricks.com>
Closes#12375 from rxin/SPARK-14617.
## What changes were proposed in this pull request?
When there are multiple attempts for a stage, we currently only reset internal accumulator values if all the tasks are resubmitted. It would make more sense to reset the accumulator values for each stage attempt. This will allow us to eventually get rid of the internal flag in the Accumulator class. This is part of my bigger effort to simplify accumulators and task metrics.
## How was this patch tested?
Covered by existing tests.
Author: Reynold Xin <rxin@databricks.com>
Closes#12378 from rxin/SPARK-14619.
## What changes were proposed in this pull request?
I was trying to understand the accumulator and metrics update source code and these two classes don't really need to be case classes. It would also be more consistent with other UI classes if they are not case classes. This is part of my bigger effort to simplify accumulators and task metrics.
## How was this patch tested?
This is a straightforward refactoring without behavior change.
Author: Reynold Xin <rxin@databricks.com>
Closes#12386 from rxin/SPARK-14625.
## What changes were proposed in this pull request?
According to the [Spark Code Style Guide](https://cwiki.apache.org/confluence/display/SPARK/Spark+Code+Style+Guide) and [Scala Style Guide](http://docs.scala-lang.org/style/control-structures.html#curlybraces), we had better enforce the following rule.
```
case: Always omit braces in case clauses.
```
This PR makes a new ScalaStyle rule, 'OmitBracesInCase', and enforces it to the code.
## How was this patch tested?
Pass the Jenkins tests (including Scala style checking)
Author: Dongjoon Hyun <dongjoon@apache.org>
Closes#12280 from dongjoon-hyun/SPARK-14508.
## What changes were proposed in this pull request?
This adds a new API call `TaskContext.getLocalProperty` for getting properties set in the driver from executors. These local properties are automatically propagated from the driver to executors. For streaming, the context for streaming tasks will be the initial driver context when ssc.start() is called.
## How was this patch tested?
Unit tests.
cc JoshRosen
Author: Eric Liang <ekl@databricks.com>
Closes#12248 from ericl/sc-2813.
## What changes were proposed in this pull request?
When deciding whether a CommitDeniedException caused a task to fail, consider the root cause of the Exception.
## How was this patch tested?
Added a test suite for the component that extracts the root cause of the error.
Made a distribution after cherry-picking this commit to branch-1.6 and used to run our Spark application that would quite often fail due to the CommitDeniedException.
Author: Jason Moore <jasonmoore2k@outlook.com>
Closes#12228 from jasonmoore2k/SPARK-14357.
## What changes were proposed in this pull request?
Here is why SPARK-14437 happens:
BlockManagerId is created using NettyBlockTransferService.hostName which comes from `customHostname`. And `Executor` will set `customHostname` to the hostname which is detected by the driver. However, the driver may not be able to detect the correct address in some complicated network (Netty's Channel.remoteAddress doesn't always return a connectable address). In such case, `BlockManagerId` will be created using a wrong hostname.
To fix this issue, this PR uses `hostname` provided by `SparkEnv.create` to create `NettyBlockTransferService` and set `NettyBlockTransferService.hostname` to this one directly. A bonus of this approach is NettyBlockTransferService won't bound to `0.0.0.0` which is much safer.
## How was this patch tested?
Manually checked the bound address using local-cluster.
Author: Shixiong Zhu <shixiong@databricks.com>
Closes#12240 from zsxwing/SPARK-14437.
Currently all `SparkFirehoseListener` implementations are broken since we expect listeners to extend `SparkListener`, while the fire hose only extends `SparkListenerInterface`. This changes the addListener function and the config based injection to use the interface instead.
The existing tests in SparkListenerSuite are improved such that they would have caught this.
Follow-up to #12142
Author: Michael Armbrust <michael@databricks.com>
Closes#12227 from marmbrus/fixListener.
## What changes were proposed in this pull request?
`OutputCommitCoordinator` was introduced to deal with concurrent task attempts racing to write output, leading to data loss or corruption. For more detail, read the [JIRA description](https://issues.apache.org/jira/browse/SPARK-14468).
Before: `OutputCommitCoordinator` is enabled only if speculation is enabled.
After: `OutputCommitCoordinator` is always enabled.
Users may still disable this through `spark.hadoop.outputCommitCoordination.enabled`, but they really shouldn't...
## How was this patch tested?
`OutputCommitCoordinator*Suite`
Author: Andrew Or <andrew@databricks.com>
Closes#12244 from andrewor14/always-occ.
The current package name uses a dash, which is a little weird but seemed
to work. That is, until a new test tried to mock a class that references
one of those shaded types, and then things started failing.
Most changes are just noise to fix the logging configs.
For reference, SPARK-8815 also raised this issue, although at the time it
did not cause any issues in Spark, so it was not addressed.
Author: Marcelo Vanzin <vanzin@cloudera.com>
Closes#11941 from vanzin/SPARK-14134.
## What changes were proposed in this pull request?
Send `RegisterExecutorResponse` using `executorRef` in order to make sure RegisterExecutorResponse and LaunchTask are both sent using the same channel. Then RegisterExecutorResponse will always arrive before LaunchTask
## How was this patch tested?
Existing unit tests
Closes#12078
Author: Shixiong Zhu <shixiong@databricks.com>
Closes#12211 from zsxwing/SPARK-13112.
## What changes were proposed in this pull request?
As mentioned in the ticket this was because one get path in the refactored `BlockManager` did not check for remote storage.
## How was this patch tested?
Unit test, also verified manually with reproduction in the ticket.
cc JoshRosen
Author: Eric Liang <ekl@databricks.com>
Closes#12193 from ericl/spark-14252.
Because SQL keeps track of all known configs, some customization was
needed in SQLConf to allow that, since the core API does not have that
feature.
Tested via existing (and slightly updated) unit tests.
Author: Marcelo Vanzin <vanzin@cloudera.com>
Closes#11570 from vanzin/SPARK-529-sql.
This change modifies the "assembly/" module to just copy needed
dependencies to its build directory, and modifies the packaging
script to pick those up (and remove duplicate jars packages in the
examples module).
I also made some minor adjustments to dependencies to remove some
test jars from the final packaging, and remove jars that conflict with each
other when packaged separately (e.g. servlet api).
Also note that this change restores guava in applications' classpaths, even
though it's still shaded inside Spark. This is now needed for the Hadoop
libraries that are packaged with Spark, which now are not processed by
the shade plugin.
Author: Marcelo Vanzin <vanzin@cloudera.com>
Closes#11796 from vanzin/SPARK-13579.
## What changes were proposed in this pull request?
This PR contains the following 5 types of maintenance fix over 59 files (+94 lines, -93 lines).
- Fix typos(exception/log strings, testcase name, comments) in 44 lines.
- Fix lint-java errors (MaxLineLength) in 6 lines. (New codes after SPARK-14011)
- Use diamond operators in 40 lines. (New codes after SPARK-13702)
- Fix redundant semicolon in 5 lines.
- Rename class `InferSchemaSuite` to `CSVInferSchemaSuite` in CSVInferSchemaSuite.scala.
## How was this patch tested?
Manual and pass the Jenkins tests.
Author: Dongjoon Hyun <dongjoon@apache.org>
Closes#12139 from dongjoon-hyun/SPARK-14355.
## What changes were proposed in this pull request?
This special cases 0 and 1 counts to avoid passing 0 degrees of freedom.
## How was this patch tested?
Tests run successfully. New test added.
## Note:
This recreates #11982 which was closed to due to non-updated diff. rxin srowen Commented there.
This also adds tests, reworks the code to perform the special casing (based on srowen's comments), and adds equality machinery for BoundedDouble, as well as changing how it is transformed to string.
Author: Marcin Tustin <mtustin@handybook.com>
Author: Marcin Tustin <mtustin@handy.com>
Closes#12016 from mtustin-handy/SPARK-14163.
## What changes were proposed in this pull request?
Straggler references to Tachyon were removed:
- for docs, `tachyon` has been generalized as `off-heap memory`;
- for Mesos test suits, the key-value `tachyon:true`/`tachyon:false` has been changed to `os:centos`/`os:ubuntu`, since `os` is an example constrain used by the [Mesos official docs](http://mesos.apache.org/documentation/attributes-resources/).
## How was this patch tested?
Existing test suites.
Author: Liwei Lin <lwlin7@gmail.com>
Closes#12129 from lw-lin/tachyon-cleanup.
## What changes were proposed in this pull request?
This PR aims to fix all Scala-Style multiline comments into Java-Style multiline comments in Scala codes.
(All comment-only changes over 77 files: +786 lines, −747 lines)
## How was this patch tested?
Manual.
Author: Dongjoon Hyun <dongjoon@apache.org>
Closes#12130 from dongjoon-hyun/use_multiine_javadoc_comments.
## What changes were proposed in this pull request?
Adding long values for each Date in the ApplicationAttemptInfo API for easier use in code
## How was the this patch tested?
Tested with dev/run-tests
Author: Alex Bozarth <ajbozart@us.ibm.com>
Closes#11326 from ajbozarth/spark13241.
This patch adds support for caching blocks in the executor processes using direct / off-heap memory.
## User-facing changes
**Updated semantics of `OFF_HEAP` storage level**: In Spark 1.x, the `OFF_HEAP` storage level indicated that an RDD should be cached in Tachyon. Spark 2.x removed the external block store API that Tachyon caching was based on (see #10752 / SPARK-12667), so `OFF_HEAP` became an alias for `MEMORY_ONLY_SER`. As of this patch, `OFF_HEAP` means "serialized and cached in off-heap memory or on disk". Via the `StorageLevel` constructor, `useOffHeap` can be set if `serialized == true` and can be used to construct custom storage levels which support replication.
**Storage UI reporting**: the storage UI will now report whether in-memory blocks are stored on- or off-heap.
**Only supported by UnifiedMemoryManager**: for simplicity, this feature is only supported when the default UnifiedMemoryManager is used; applications which use the legacy memory manager (`spark.memory.useLegacyMode=true`) are not currently able to allocate off-heap storage memory, so using off-heap caching will fail with an error when legacy memory management is enabled. Given that we plan to eventually remove the legacy memory manager, this is not a significant restriction.
**Memory management policies:** the policies for dividing available memory between execution and storage are the same for both on- and off-heap memory. For off-heap memory, the total amount of memory available for use by Spark is controlled by `spark.memory.offHeap.size`, which is an absolute size. Off-heap storage memory obeys `spark.memory.storageFraction` in order to control the amount of unevictable storage memory. For example, if `spark.memory.offHeap.size` is 1 gigabyte and Spark uses the default `storageFraction` of 0.5, then up to 500 megabytes of off-heap cached blocks will be protected from eviction due to execution memory pressure. If necessary, we can split `spark.memory.storageFraction` into separate on- and off-heap configurations, but this doesn't seem necessary now and can be done later without any breaking changes.
**Use of off-heap memory does not imply use of off-heap execution (or vice-versa)**: for now, the settings controlling the use of off-heap execution memory (`spark.memory.offHeap.enabled`) and off-heap caching are completely independent, so Spark SQL can be configured to use off-heap memory for execution while continuing to cache blocks on-heap. If desired, we can change this in a followup patch so that `spark.memory.offHeap.enabled` affect the default storage level for cached SQL tables.
## Internal changes
- Rename `ByteArrayChunkOutputStream` to `ChunkedByteBufferOutputStream`
- It now returns a `ChunkedByteBuffer` instead of an array of byte arrays.
- Its constructor now accept an `allocator` function which is called to allocate `ByteBuffer`s. This allows us to control whether it allocates regular ByteBuffers or off-heap DirectByteBuffers.
- Because block serialization is now performed during the unroll process, a `ChunkedByteBufferOutputStream` which is configured with a `DirectByteBuffer` allocator will use off-heap memory for both unroll and storage memory.
- The `MemoryStore`'s MemoryEntries now tracks whether blocks are stored on- or off-heap.
- `evictBlocksToFreeSpace()` now accepts a `MemoryMode` parameter so that we don't try to evict off-heap blocks in response to on-heap memory pressure (or vice-versa).
- Make sure that off-heap buffers are properly de-allocated during MemoryStore eviction.
- The JVM limits the total size of allocated direct byte buffers using the `-XX:MaxDirectMemorySize` flag and the default tends to be fairly low (< 512 megabytes in some JVMs). To work around this limitation, this patch adds a custom DirectByteBuffer allocator which ignores this memory limit.
Author: Josh Rosen <joshrosen@databricks.com>
Closes#11805 from JoshRosen/off-heap-caching.
## What changes were proposed in this pull request?
Currently in Spark on YARN, configurations can be passed through SparkConf, env and command arguments, some parts are duplicated, like client argument and SparkConf. So here propose to simplify the command arguments.
## How was this patch tested?
This patch is tested manually with unit test.
CC vanzin tgravescs , please help to suggest this proposal. The original purpose of this JIRA is to remove `ClientArguments`, through refactoring some arguments like `--class`, `--arg` are not so easy to replace, so here I remove the most part of command line arguments, only keep the minimal set.
Author: jerryshao <sshao@hortonworks.com>
Closes#11603 from jerryshao/SPARK-12343.
## What changes were proposed in this pull request?
This PR try to use `incUpdatedBlockStatuses ` to update the `updatedBlockStatuses ` when removing blocks, making sure `BlockManager` correctly updates `updatedBlockStatuses`
## How was this patch tested?
test("updated block statuses") in BlockManagerSuite.scala
Author: jeanlyn <jeanlyn92@gmail.com>
Closes#12091 from jeanlyn/updateBlock.
## What changes were proposed in this pull request?
We have a streaming job using `FlumePollInputStream` always driver OOM after few days, here is some driver heap dump before OOM
```
num #instances #bytes class name
----------------------------------------------
1: 13845916 553836640 org.apache.spark.storage.BlockStatus
2: 14020324 336487776 org.apache.spark.storage.StreamBlockId
3: 13883881 333213144 scala.collection.mutable.DefaultEntry
4: 8907 89043952 [Lscala.collection.mutable.HashEntry;
5: 62360 65107352 [B
6: 163368 24453904 [Ljava.lang.Object;
7: 293651 20342664 [C
...
```
`BlockStatus` and `StreamBlockId` keep on growing, and the driver OOM in the end.
After investigated, i found the `executorIdToStorageStatus` in `StorageStatusListener` seems never remove the blocks from `StorageStatus`.
In order to fix the issue, i try to use `onBlockUpdated` replace `onTaskEnd ` , so we can update the block informations(add blocks, drop the block from memory to disk and delete the blocks) in time.
## How was this patch tested?
Existing unit tests and manual tests
Author: jeanlyn <jeanlyn92@gmail.com>
Closes#11779 from jeanlyn/fix_driver_oom.
## What changes were proposed in this pull request?
Extract the workaround for HADOOP-10622 introduced by #11940 into UninterruptibleThread so that we can test and reuse it.
## How was this patch tested?
Unit tests
Author: Shixiong Zhu <shixiong@databricks.com>
Closes#11971 from zsxwing/uninterrupt.
## What changes were proposed in this pull request?
Currently, for the key that can not fit within a long, we build a hash map for UnsafeHashedRelation, it's converted to BytesToBytesMap after serialization and deserialization. We should build a BytesToBytesMap directly to have better memory efficiency.
In order to do that, BytesToBytesMap should support multiple (K,V) pair with the same K, Location.putNewKey() is renamed to Location.append(), which could append multiple values for the same key (same Location). `Location.newValue()` is added to find the next value for the same key.
## How was this patch tested?
Existing tests. Added benchmark for broadcast hash join with duplicated keys.
Author: Davies Liu <davies@databricks.com>
Closes#11870 from davies/map2.
JIRA: https://issues.apache.org/jira/browse/SPARK-13742
## What changes were proposed in this pull request?
`RandomSampler.sample` currently accepts iterator as input and output another iterator. This makes it inappropriate to use in wholestage codegen of `Sampler` operator #11517. This change is to add non-iterator interface to `RandomSampler`.
This change adds a new method `def sample(): Int` to the trait `RandomSampler`. As we don't need to know the actual values of the sampling items, so this new method takes no arguments.
This method will decide whether to sample the next item or not. It returns how many times the next item will be sampled.
For `BernoulliSampler` and `BernoulliCellSampler`, the returned sampling times can only be 0 or 1. It simply means whether to sample the next item or not.
For `PoissonSampler`, the returned value can be more than 1, meaning the next item will be sampled multiple times.
## How was this patch tested?
Tests are added into `RandomSamplerSuite`.
Author: Liang-Chi Hsieh <simonh@tw.ibm.com>
Author: Liang-Chi Hsieh <viirya@appier.com>
Author: Liang-Chi Hsieh <viirya@gmail.com>
Closes#11578 from viirya/random-sampler-no-iterator.
This patch extends Spark's `UnifiedMemoryManager` to add bookkeeping support for off-heap storage memory, an requirement for enabling off-heap caching (which will be done by #11805). The `MemoryManager`'s `storageMemoryPool` has been split into separate on- and off-heap pools and the storage and unroll memory allocation methods have been updated to accept a `memoryMode` parameter to specify whether allocations should be performed on- or off-heap.
In order to reduce the testing surface, the `StaticMemoryManager` does not support off-heap caching (we plan to eventually remove the `StaticMemoryManager`, so this isn't a significant limitation).
Author: Josh Rosen <joshrosen@databricks.com>
Closes#11942 from JoshRosen/off-heap-storage-memory-bookkeeping.
When a block is persisted in the MemoryStore at a serialized storage level, the current MemoryStore.putIterator() code will unroll the entire iterator as Java objects in memory, then will turn around and serialize an iterator obtained from the unrolled array. This is inefficient and doubles our peak memory requirements.
Instead, I think that we should incrementally serialize blocks while unrolling them.
A downside to incremental serialization is the fact that we will need to deserialize the partially-unrolled data in case there is not enough space to unroll the block and the block cannot be dropped to disk. However, I'm hoping that the memory efficiency improvements will outweigh any performance losses as a result of extra serialization in that hopefully-rare case.
Author: Josh Rosen <joshrosen@databricks.com>
Closes#11791 from JoshRosen/serialize-incrementally.
## What changes were proposed in this pull request?
A fix for local metrics tests that can fail on fast machines.
This is probably what is suggested here #3380 by aarondav?
## How was this patch tested?
CI Tests
Cheers
Author: Joan <joan@goyeau.com>
Closes#11747 from joan38/SPARK-2208-Local-metrics-tests.
## What changes were proposed in this pull request?
In case of failure in subprocess launched in PipedRDD, the failure exception reads “Subprocess exited with status XXX”. Debugging this is not easy for users especially if there are multiple pipe() operations in the Spark application.
Changes done:
- Changed the exception message when non-zero exit code is seen
- If the reader and writer threads see exception, simply logging the command ran. The current model is to propagate the exception "as is" so that upstream Spark logic will take the right action based on what the exception was (eg. for fetch failure, it needs to retry; but for some fatal exception, it will decide to fail the stage / job). So wrapping the exception with a generic exception will not work. Altering the exception message will keep that guarantee but that is ugly (plus not all exceptions might have a constructor for a string message)
## How was this patch tested?
- Added a new test case
- Ran all existing tests for PipedRDD
Author: Tejas Patil <tejasp@fb.com>
Closes#11927 from tejasapatil/SPARK-14110-piperdd-failure.
This patch refactors the `MemoryStore` so that it can be tested without needing to construct / mock an entire `BlockManager`.
- The block manager's serialization- and compression-related methods have been moved from `BlockManager` to `SerializerManager`.
- `BlockInfoManager `is now passed directly to classes that need it, rather than being passed via the `BlockManager`.
- The `MemoryStore` now calls `dropFromMemory` via a new `BlockEvictionHandler` interface rather than directly calling the `BlockManager`. This change helps to enforce a narrow interface between the `MemoryStore` and `BlockManager` functionality and makes this interface easier to mock in tests.
- Several of the block unrolling tests have been moved from `BlockManagerSuite` into a new `MemoryStoreSuite`.
Author: Josh Rosen <joshrosen@databricks.com>
Closes#11899 from JoshRosen/reduce-memorystore-blockmanager-coupling.
Building on the `SerializerManager` introduced in SPARK-13926/ #11755, this patch Spark modifies Spark's BlockManager to use RDD's ClassTags in order to select the best serializer to use when caching RDD blocks.
When storing a local block, the BlockManager `put()` methods use implicits to record ClassTags and stores those tags in the blocks' BlockInfo records. When reading a local block, the stored ClassTag is used to pick the appropriate serializer. When a block is stored with replication, the class tag is written into the block transfer metadata and will also be stored in the remote BlockManager.
There are two or three places where we don't properly pass ClassTags, including TorrentBroadcast and BlockRDD. I think this happens to work because the missing ClassTag always happens to be `ClassTag.Any`, but it might be worth looking more carefully at those places to see whether we should be more explicit.
Author: Josh Rosen <joshrosen@databricks.com>
Closes#11801 from JoshRosen/pick-best-serializer-for-caching.
## What changes were proposed in this pull request?
[Spark Coding Style Guide](https://cwiki.apache.org/confluence/display/SPARK/Spark+Code+Style+Guide) has 100-character limit on lines, but it's disabled for Java since 11/09/15. This PR enables **LineLength** checkstyle again. To help that, this also introduces **RedundantImport** and **RedundantModifier**, too. The following is the diff on `checkstyle.xml`.
```xml
- <!-- TODO: 11/09/15 disabled - the lengths are currently > 100 in many places -->
- <!--
<module name="LineLength">
<property name="max" value="100"/>
<property name="ignorePattern" value="^package.*|^import.*|a href|href|http://|https://|ftp://"/>
</module>
- -->
<module name="NoLineWrap"/>
<module name="EmptyBlock">
<property name="option" value="TEXT"/>
-167,5 +164,7
</module>
<module name="CommentsIndentation"/>
<module name="UnusedImports"/>
+ <module name="RedundantImport"/>
+ <module name="RedundantModifier"/>
```
## How was this patch tested?
Currently, `lint-java` is disabled in Jenkins. It needs a manual test.
After passing the Jenkins tests, `dev/lint-java` should passes locally.
Author: Dongjoon Hyun <dongjoon@apache.org>
Closes#11831 from dongjoon-hyun/SPARK-14011.
This patch modifies the BlockManager, MemoryStore, and several other storage components so that serialized cached blocks are stored as multiple small chunks rather than as a single contiguous ByteBuffer.
This change will help to improve the efficiency of memory allocation and the accuracy of memory accounting when serializing blocks. Our current serialization code uses a ByteBufferOutputStream, which doubles and re-allocates its backing byte array; this increases the peak memory requirements during serialization (since we need to hold extra memory while expanding the array). In addition, we currently don't account for the extra wasted space at the end of the ByteBuffer's backing array, so a 129 megabyte serialized block may actually consume 256 megabytes of memory. After switching to storing blocks in multiple chunks, we'll be able to efficiently trim the backing buffers so that no space is wasted.
This change is also a prerequisite to being able to cache blocks which are larger than 2GB (although full support for that depends on several other changes which have not bee implemented yet).
Author: Josh Rosen <joshrosen@databricks.com>
Closes#11748 from JoshRosen/chunked-block-serialization.
## What changes were proposed in this pull request?
Logging was made private in Spark 2.0. If we move it, then users would be able to create a Logging trait themselves to avoid changing their own code.
## How was this patch tested?
existing tests.
Author: Wenchen Fan <wenchen@databricks.com>
Closes#11764 from cloud-fan/logger.
Because ClassTags are available when constructing ShuffledRDD we can use them to automatically use Kryo for shuffle serialization when the RDD's types are known to be compatible with Kryo.
This patch introduces `SerializerManager`, a component which picks the "best" serializer for a shuffle given the elements' ClassTags. It will automatically pick a Kryo serializer for ShuffledRDDs whose key, value, and/or combiner types are primitives, arrays of primitives, or strings. In the future we can use this class as a narrow extension point to integrate specialized serializers for other types, such as ByteBuffers.
In a planned followup patch, I will extend the BlockManager APIs so that we're able to use similar automatic serializer selection when caching RDDs (this is a little trickier because the ClassTags need to be threaded through many more places).
Author: Josh Rosen <joshrosen@databricks.com>
Closes#11755 from JoshRosen/automatically-pick-best-serializer.
## What changes were proposed in this pull request?
In SparkContext, throw Illegalargumentexception when trying to broadcast rdd directly, instead of logging the warning.
## How was this patch tested?
mvn clean install
Add UT in BroadcastSuite
Author: Wesley Tang <tangmingjun@mininglamp.com>
Closes#11735 from breakdawn/master.
## What changes were proposed in this pull request?
PipedRDD creates a child thread to read output of the parent stage and feed it to the pipe process. Used a variable to save the exception thrown in the child thread and then propagating the exception in the main thread if the variable was set.
## How was this patch tested?
- Added a unit test
- Ran all the existing tests in PipedRDDSuite and they all pass with the change
- Tested the patch with a real pipe() job, bounced the executor node which ran the parent stage to simulate a fetch failure and observed that the parent stage was re-ran.
Author: Tejas Patil <tejasp@fb.com>
Closes#11628 from tejasapatil/pipe_rdd.
## What changes were proposed in this pull request?
Follow up to https://github.com/apache/spark/pull/11657
- Also update `String.getBytes("UTF-8")` to use `StandardCharsets.UTF_8`
- And fix one last new Coverity warning that turned up (use of unguarded `wait()` replaced by simpler/more robust `java.util.concurrent` classes in tests)
- And while we're here cleaning up Coverity warnings, just fix about 15 more build warnings
## How was this patch tested?
Jenkins tests
Author: Sean Owen <sowen@cloudera.com>
Closes#11725 from srowen/SPARK-13823.2.
This patch refactors the MemoryStore to remove the concept of `pendingUnrollMemory`. It also fixes fixes SPARK-6157: "Unrolling with MEMORY_AND_DISK should always release memory".
Key changes:
- Inline `MemoryStore.tryToPut` at its three call sites in the `MemoryStore`.
- Inline `Memory.unrollSafely` at its only call site (in `MemoryStore.putIterator`).
- Inline `MemoryManager.acquireStorageMemory` at its call sites.
- Simplify the code as a result of this inlining (some parameters have fixed values after inlining, so lots of branches can be removed).
- Remove the `pendingUnrollMemory` map by returning the amount of unrollMemory allocated when returning an iterator after a failed `putIterator` call.
- Change `putIterator` to return an instance of `PartiallyUnrolledIterator`, a special iterator subclass which will automatically free the unroll memory of its partially-unrolled elements when the iterator is consumed. To handle cases where the iterator is not consumed (e.g. when a MEMORY_ONLY put fails), `PartiallyUnrolledIterator` exposes a `close()` method which may be called to discard the unrolled values and free their memory.
Author: Josh Rosen <joshrosen@databricks.com>
Closes#11613 from JoshRosen/cleanup-unroll-memory.
I am using dynamic container allocation and speculation and am seeing issues with the active task accounting. The Executor UI still shows active tasks on the an executor but the job/stage is all completed. I think its also affecting the dynamic allocation being able to release containers because it thinks there are still tasks.
There are multiple issues with this:
- If the task end for tasks (in this case probably because of speculation) comes in after the stage is finished, then the DAGScheduler.handleTaskCompletion will skip the task completion event
Author: Thomas Graves <tgraves@prevailsail.corp.gq1.yahoo.com>
Author: Thomas Graves <tgraves@staydecay.corp.gq1.yahoo.com>
Author: Tom Graves <tgraves@yahoo-inc.com>
Closes#10951 from tgravescs/SPARK-11701.
## Problem description:
Mesos shuffle service is completely unusable since Spark 1.6.0 . The problem seems to occur since the move from akka to netty in the networking layer. Until now, a connection from the driver to each shuffle service was used as a signal for the shuffle service to determine, whether the driver is still running. Since 1.6.0, this connection is closed after spark.shuffle.io.connectionTimeout (or spark.network.timeout if the former is not set) due to it being idle. The shuffle service interprets this as a signal that the driver has stopped, despite the driver still being alive. Thus, shuffle files are deleted before the application has stopped.
### Context and analysis:
spark shuffle fails with mesos after 2mins: https://issues.apache.org/jira/browse/SPARK-12583
External shuffle service broken w/ Mesos: https://issues.apache.org/jira/browse/SPARK-13159
This is a follow up on #11207 .
## What changes were proposed in this pull request?
This PR adds a heartbeat signal from the Driver (in MesosExternalShuffleClient) to all registered external mesos shuffle service instances. In MesosExternalShuffleBlockHandler, a thread periodically checks whether a driver has timed out and cleans an application's shuffle files if this is the case.
## How was the this patch tested?
This patch has been tested on a small mesos test cluster using the spark-shell. Log output from mesos shuffle service:
```
16/02/19 15:13:45 INFO mesos.MesosExternalShuffleBlockHandler: Received registration request from app 294def07-3249-4e0f-8d71-bf8c83c58a50-0018 (remote address /xxx.xxx.xxx.xxx:52391, heartbeat timeout 120000 ms).
16/02/19 15:13:47 INFO shuffle.ExternalShuffleBlockResolver: Registered executor AppExecId{appId=294def07-3249-4e0f-8d71-bf8c83c58a50-0018, execId=3} with ExecutorShuffleInfo{localDirs=[/foo/blockmgr-c84c0697-a3f9-4f61-9c64-4d3ee227c047], subDirsPerLocalDir=64, shuffleManager=sort}
16/02/19 15:13:47 INFO shuffle.ExternalShuffleBlockResolver: Registered executor AppExecId{appId=294def07-3249-4e0f-8d71-bf8c83c58a50-0018, execId=7} with ExecutorShuffleInfo{localDirs=[/foo/blockmgr-bf46497a-de80-47b9-88f9-563123b59e03], subDirsPerLocalDir=64, shuffleManager=sort}
16/02/19 15:16:02 INFO mesos.MesosExternalShuffleBlockHandler: Application 294def07-3249-4e0f-8d71-bf8c83c58a50-0018 timed out. Removing shuffle files.
16/02/19 15:16:02 INFO shuffle.ExternalShuffleBlockResolver: Application 294def07-3249-4e0f-8d71-bf8c83c58a50-0018 removed, cleanupLocalDirs = true
16/02/19 15:16:02 INFO shuffle.ExternalShuffleBlockResolver: Cleaning up executor AppExecId{appId=294def07-3249-4e0f-8d71-bf8c83c58a50-0018, execId=3}'s 1 local dirs
16/02/19 15:16:02 INFO shuffle.ExternalShuffleBlockResolver: Cleaning up executor AppExecId{appId=294def07-3249-4e0f-8d71-bf8c83c58a50-0018, execId=7}'s 1 local dirs
```
Note: there are 2 executors running on this slave.
Author: Bertrand Bossy <bertrand.bossy@teralytics.net>
Closes#11272 from bbossy/SPARK-12583-mesos-shuffle-service-heartbeat.
trait SynchronizedSet in package mutable is deprecated
Author: Wilson Wu <wilson888888888@gmail.com>
Closes#11580 from wilson888888888/spark-synchronizedset.
## What changes were proposed in this pull request?
This PR fixes 135 typos over 107 files:
* 121 typos in comments
* 11 typos in testcase name
* 3 typos in log messages
## How was this patch tested?
Manual.
Author: Dongjoon Hyun <dongjoon@apache.org>
Closes#11689 from dongjoon-hyun/fix_more_typos.
## What changes were proposed in this pull request?
- Fixes calls to `new String(byte[])` or `String.getBytes()` that rely on platform default encoding, to use UTF-8
- Same for `InputStreamReader` and `OutputStreamWriter` constructors
- Standardizes on UTF-8 everywhere
- Standardizes specifying the encoding with `StandardCharsets.UTF-8`, not the Guava constant or "UTF-8" (which means handling `UnuspportedEncodingException`)
- (also addresses the other remaining Coverity scan issues, which are pretty trivial; these are separated into commit 1deecd8d9c )
## How was this patch tested?
Jenkins tests
Author: Sean Owen <sowen@cloudera.com>
Closes#11657 from srowen/SPARK-13823.
When dynamic resource allocation is enabled fetching broadcast variables from removed executors were causing job failures and SPARK-9591 fixed this problem by trying all locations of a block before giving up. However, the locations of a block is retrieved only once from the driver in this process and the locations in this list can be stale due to dynamic resource allocation. This situation gets worse when running on a large cluster as the size of this location list can be in the order of several hundreds out of which there may be tens of stale entries. What we have observed is with the default settings of 3 max retries and 5s between retries (that's 15s per location) the time it takes to read a broadcast variable can be as high as ~17m (70 failed attempts * 15s/attempt)
Author: Nezih Yigitbasi <nyigitbasi@netflix.com>
Closes#11241 from nezihyigitbasi/SPARK-13328.
## What changes were proposed in this pull request?
Here lists all cases that Master cannot talk with Worker for a while and then network is back.
1. Master doesn't know the network issue (not yet timeout)
a. Worker doesn't know the network issue (onDisconnected is not called)
- Worker keeps sending Heartbeat. Both Worker and Master don't know the network issue. Nothing to do. (Finally, Master will notice the heartbeat timeout if network is not recovered)
b. Worker knows the network issue (onDisconnected is called)
- Worker stops sending Heartbeat and sends `RegisterWorker` to master. Master will reply `RegisterWorkerFailed("Duplicate worker ID")`. Worker calls "System.exit(1)" (Finally, Master will notice the heartbeat timeout if network is not recovered) (May leak driver processes. See [SPARK-13602](https://issues.apache.org/jira/browse/SPARK-13602))
2. Worker timeout (Master knows the network issue). In such case, master removes Worker and its executors and drivers.
a. Worker doesn't know the network issue (onDisconnected is not called)
- Worker keeps sending Heartbeat.
- If the network is back, say Master receives Heartbeat, Master sends `ReconnectWorker` to Worker
- Worker send `RegisterWorker` to master.
- Master accepts `RegisterWorker` but doesn't know executors and drivers in Worker. (may leak executors)
b. Worker knows the network issue (onDisconnected is called)
- Worker stop sending `Heartbeat`. Worker will send "RegisterWorker" to master.
- Master accepts `RegisterWorker` but doesn't know executors and drivers in Worker. (may leak executors)
This PR fixes executors and drivers leak in 2.a and 2.b when Worker reregisters with Master. The approach is making Worker send `WorkerLatestState` to sync the state after registering with master successfully. Then Master will ask Worker to kill unknown executors and drivers.
Note: Worker cannot just kill executors after registering with master because in the worker, `LaunchExecutor` and `RegisteredWorker` are processed in two threads. If `LaunchExecutor` happens before `RegisteredWorker`, Worker's executor list will contain new executors after Master accepts `RegisterWorker`. We should not kill these executors. So sending the list to Master and let Master tell Worker which executors should be killed.
## How was this patch tested?
test("SPARK-13604: Master should ask Worker kill unknown executors and drivers")
Author: Shixiong Zhu <shixiong@databricks.com>
Closes#11455 from zsxwing/orphan-executors.
## What changes were proposed in this pull request?
Since the opening curly brace, '{', has many usages as discussed in [SPARK-3854](https://issues.apache.org/jira/browse/SPARK-3854), this PR adds a ScalaStyle rule to prevent '){' pattern for the following majority pattern and fixes the code accordingly. If we enforce this in ScalaStyle from now, it will improve the Scala code quality and reduce review time.
```
// Correct:
if (true) {
println("Wow!")
}
// Incorrect:
if (true){
println("Wow!")
}
```
IntelliJ also shows new warnings based on this.
## How was this patch tested?
Pass the Jenkins ScalaStyle test.
Author: Dongjoon Hyun <dongjoon@apache.org>
Closes#11637 from dongjoon-hyun/SPARK-3854.
Today, both the MemoryStore and DiskStore implement a common `BlockStore` API, but I feel that this API is inappropriate because it abstracts away important distinctions between the behavior of these two stores.
For instance, the disk store doesn't have a notion of storing deserialized objects, so it's confusing for it to expose object-based APIs like putIterator() and getValues() instead of only exposing binary APIs and pushing the responsibilities of serialization and deserialization to the client. Similarly, the DiskStore put() methods accepted a `StorageLevel` parameter even though the disk store can only store blocks in one form.
As part of a larger BlockManager interface cleanup, this patch remove the BlockStore interface and refines the MemoryStore and DiskStore interfaces to reflect more narrow sets of responsibilities for those components. Some of the benefits of this interface cleanup are reflected in simplifications to several unit tests to eliminate now-unnecessary mocking, significant simplification of the BlockManager's `getLocal()` and `doPut()` methods, and a narrower API between the MemoryStore and DiskStore.
Author: Josh Rosen <joshrosen@databricks.com>
Closes#11534 from JoshRosen/remove-blockstore-interface.
The contains() method does not return consistently with get() if the key is deprecated. For example,
import org.apache.spark.SparkConf
val conf = new SparkConf()
conf.set("spark.io.compression.lz4.block.size", "12345") # display some deprecated warning message
conf.get("spark.io.compression.lz4.block.size") # return 12345
conf.get("spark.io.compression.lz4.blockSize") # return 12345
conf.contains("spark.io.compression.lz4.block.size") # return true
conf.contains("spark.io.compression.lz4.blockSize") # return false
The fix will make the contains() and get() more consistent.
I've added a test case for this.
(Please explain how this patch was tested. E.g. unit tests, integration tests, manual tests)
Unit tests should be sufficient.
Author: bomeng <bmeng@us.ibm.com>
Closes#11568 from bomeng/SPARK-13727.
## What changes were proposed in this pull request?
Previously the Mesos framework webui URL was being derived only from the Spark UI address leaving no possibility to configure it. This commit makes it configurable. If unset it falls back to the previous behavior.
Motivation:
This change is necessary in order to be able to install Spark on DCOS and to be able to give it a custom service link. The configured `webui_url` is configured to point to a reverse proxy in the DCOS environment.
## How was this patch tested?
Locally, using unit tests and on DCOS testing and stable revision.
Author: Sergiusz Urbaniak <sur@mesosphere.io>
Closes#11369 from s-urbaniak/sur-webui-url.
## What changes were proposed in this pull request?
In order to make `docs/examples` (and other related code) more simple/readable/user-friendly, this PR replaces existing codes like the followings by using `diamond` operator.
```
- final ArrayList<Product2<Object, Object>> dataToWrite =
- new ArrayList<Product2<Object, Object>>();
+ final ArrayList<Product2<Object, Object>> dataToWrite = new ArrayList<>();
```
Java 7 or higher supports **diamond** operator which replaces the type arguments required to invoke the constructor of a generic class with an empty set of type parameters (<>). Currently, Spark Java code use mixed usage of this.
## How was this patch tested?
Manual.
Pass the existing tests.
Author: Dongjoon Hyun <dongjoon@apache.org>
Closes#11541 from dongjoon-hyun/SPARK-13702.
## What changes were proposed in this pull request?
This issue fixes the following potential bugs and Java coding style detected by Coverity and Checkstyle.
- Implement both null and type checking in equals functions.
- Fix wrong type casting logic in SimpleJavaBean2.equals.
- Add `implement Cloneable` to `UTF8String` and `SortedIterator`.
- Remove dereferencing before null check in `AbstractBytesToBytesMapSuite`.
- Fix coding style: Add '{}' to single `for` statement in mllib examples.
- Remove unused imports in `ColumnarBatch` and `JavaKinesisStreamSuite`.
- Remove unused fields in `ChunkFetchIntegrationSuite`.
- Add `stop()` to prevent resource leak.
Please note that the last two checkstyle errors exist on newly added commits after [SPARK-13583](https://issues.apache.org/jira/browse/SPARK-13583).
## How was this patch tested?
manual via `./dev/lint-java` and Coverity site.
Author: Dongjoon Hyun <dongjoon@apache.org>
Closes#11530 from dongjoon-hyun/SPARK-13692.
When a cached block is spilled to disk and read back in serialized form (i.e. as bytes), the current BlockManager implementation will attempt to re-insert the serialized block into the MemoryStore even if the block's storage level requests deserialized caching.
This behavior adds some complexity to the MemoryStore but I don't think it offers many performance benefits and I'd like to remove it in order to simplify a larger refactoring patch. Therefore, this patch changes the behavior so that disk store reads will only cache bytes in the memory store for blocks with serialized storage levels.
There are two places where we request serialized bytes from the BlockStore:
1. getLocalBytes(), which is only called when reading local copies of TorrentBroadcast pieces. Broadcast pieces are always cached using a serialized storage level, so this won't lead to a mismatch in serialization forms if spilled bytes read from disk are cached as bytes in the memory store.
2. the non-shuffle-block branch in getBlockData(), which is only called by the NettyBlockRpcServer when responding to requests to read remote blocks. Caching the serialized bytes in memory will only benefit us if those cached bytes are read before they're evicted and the likelihood of that happening seems low since the frequency of remote reads of non-broadcast cached blocks seems very low. Caching these bytes when they have a low probability of being read is bad if it risks the eviction of blocks which are cached in their expected serialized/deserialized forms, since those blocks seem more likely to be read in local computation.
Given the argument above, I think this change is unlikely to cause performance regressions.
Author: Josh Rosen <joshrosen@databricks.com>
Closes#11533 from JoshRosen/remove-memorystore-level-mismatch.
In preparation for larger refactoring, this patch removes the confusing `returnValues` option from the BlockStore put() APIs: returning the value is only useful in one place (caching) and in other situations, such as block replication, it's simpler to put() and then get().
As part of this change, I needed to refactor `BlockManager.doPut()`'s block replication code. I also changed `doPut()` to access the memory and disk stores directly rather than calling them through the BlockStore interface; this is in anticipation of a followup patch to remove the BlockStore interface so that the disk store can expose a binary-data-oriented API which is not concerned with Java objects or serialization.
These changes should be covered by the existing storage unit tests. The best way to review this patch is probably to look at the individual commits, all of which are small and have useful descriptions to guide the review.
/cc davies for review.
Author: Josh Rosen <joshrosen@databricks.com>
Closes#11502 from JoshRosen/remove-returnvalues.
This is, in a way, the basics to enable SPARK-529 (which was closed as
won't fix but I think is still valuable). In fact, Spark SQL created
something for that, and this change basically factors out that code
and inserts it into SparkConf, with some extra bells and whistles.
To showcase the usage of this pattern, I modified the YARN backend
to use the new config keys (defined in the new `config` package object
under `o.a.s.deploy.yarn`). Most of the changes are mechanic, although
logic had to be slightly modified in a handful of places.
Author: Marcelo Vanzin <vanzin@cloudera.com>
Closes#10205 from vanzin/conf-opts.
## What changes were proposed in this pull request?
This PR fixes typos in comments and testcase name of code.
## How was this patch tested?
manual.
Author: Dongjoon Hyun <dongjoon@apache.org>
Closes#11481 from dongjoon-hyun/minor_fix_typos_in_code.
## What changes were proposed in this pull request?
Fixes (another) compile problem due to inadvertent use of Option.contains, only in Scala 2.11
## How was this patch tested?
Jenkins tests
Author: Sean Owen <sowen@cloudera.com>
Closes#11496 from srowen/SPARK-13423.3.
## What changes were proposed in this pull request?
After SPARK-6990, `dev/lint-java` keeps Java code healthy and helps PR review by saving much time.
This issue aims remove unused imports from Java/Scala code and add `UnusedImports` checkstyle rule to help developers.
## How was this patch tested?
```
./dev/lint-java
./build/sbt compile
```
Author: Dongjoon Hyun <dongjoon@apache.org>
Closes#11438 from dongjoon-hyun/SPARK-13583.
## What changes were proposed in this pull request?
Make some cross-cutting code improvements according to static analysis. These are individually up for discussion since they exist in separate commits that can be reverted. The changes are broadly:
- Inner class should be static
- Mismatched hashCode/equals
- Overflow in compareTo
- Unchecked warnings
- Misuse of assert, vs junit.assert
- get(a) + getOrElse(b) -> getOrElse(a,b)
- Array/String .size -> .length (occasionally, -> .isEmpty / .nonEmpty) to avoid implicit conversions
- Dead code
- tailrec
- exists(_ == ) -> contains find + nonEmpty -> exists filter + size -> count
- reduce(_+_) -> sum map + flatten -> map
The most controversial may be .size -> .length simply because of its size. It is intended to avoid implicits that might be expensive in some places.
## How was the this patch tested?
Existing Jenkins unit tests.
Author: Sean Owen <sowen@cloudera.com>
Closes#11292 from srowen/SPARK-13423.
Moved TestExecutor.scala from src to test package and removed the unused file TestClient.scala.
Author: Devaraj K <devaraj@apache.org>
Closes#11474 from devaraj-kavali/SPARK-13621.
## What changes were proposed in this pull request?
In order to tell OutputStream that the task has failed or not, we should call the failure callbacks BEFORE calling writer.close().
## How was this patch tested?
Added new unit tests.
Author: Davies Liu <davies@databricks.com>
Closes#11450 from davies/callback.
CacheManager directly calls MemoryStore.unrollSafely() and has its own logic for handling graceful fallback to disk when cached data does not fit in memory. However, this logic also exists inside of the MemoryStore itself, so this appears to be unnecessary duplication.
Thanks to the addition of block-level read/write locks in #10705, we can refactor the code to remove the CacheManager and replace it with an atomic `BlockManager.getOrElseUpdate()` method.
This pull request replaces / subsumes #10748.
/cc andrewor14 and nongli for review. Note that this changes the locking semantics of a couple of internal BlockManager methods (`doPut()` and `lockNewBlockForWriting`), so please pay attention to the Scaladoc changes and new test cases for those methods.
Author: Josh Rosen <joshrosen@databricks.com>
Closes#11436 from JoshRosen/remove-cachemanager.
## What changes were proposed in this pull request?
TaskContext supports task completion callback, which gets called regardless of task failures. However, there is no way for the listener to know if there is an error. This patch adds a new listener that gets called when a task fails.
## How was the this patch tested?
New unit test case and integration test case covering the code path
Author: Reynold Xin <rxin@databricks.com>
Closes#11340 from rxin/SPARK-13465.
## Motivation
As a pre-requisite to off-heap caching of blocks, we need a mechanism to prevent pages / blocks from being evicted while they are being read. With on-heap objects, evicting a block while it is being read merely leads to memory-accounting problems (because we assume that an evicted block is a candidate for garbage-collection, which will not be true during a read), but with off-heap memory this will lead to either data corruption or segmentation faults.
## Changes
### BlockInfoManager and reader/writer locks
This patch adds block-level read/write locks to the BlockManager. It introduces a new `BlockInfoManager` component, which is contained within the `BlockManager`, holds the `BlockInfo` objects that the `BlockManager` uses for tracking block metadata, and exposes APIs for locking blocks in either shared read or exclusive write modes.
`BlockManager`'s `get*()` and `put*()` methods now implicitly acquire the necessary locks. After a `get()` call successfully retrieves a block, that block is locked in a shared read mode. A `put()` call will block until it acquires an exclusive write lock. If the write succeeds, the write lock will be downgraded to a shared read lock before returning to the caller. This `put()` locking behavior allows us store a block and then immediately turn around and read it without having to worry about it having been evicted between the write and the read, which will allow us to significantly simplify `CacheManager` in the future (see #10748).
See `BlockInfoManagerSuite`'s test cases for a more detailed specification of the locking semantics.
### Auto-release of locks at the end of tasks
Our locking APIs support explicit release of locks (by calling `unlock()`), but it's not always possible to guarantee that locks will be released prior to the end of the task. One reason for this is our iterator interface: since our iterators don't support an explicit `close()` operator to signal that no more records will be consumed, operations like `take()` or `limit()` don't have a good means to release locks on their input iterators' blocks. Another example is broadcast variables, whose block locks can only be released at the end of the task.
To address this, `BlockInfoManager` uses a pair of maps to track the set of locks acquired by each task. Lock acquisitions automatically record the current task attempt id by obtaining it from `TaskContext`. When a task finishes, code in `Executor` calls `BlockInfoManager.unlockAllLocksForTask(taskAttemptId)` to free locks.
### Locking and the MemoryStore
In order to prevent in-memory blocks from being evicted while they are being read, the `MemoryStore`'s `evictBlocksToFreeSpace()` method acquires write locks on blocks which it is considering as candidates for eviction. These lock acquisitions are non-blocking, so a block which is being read will not be evicted. By holding write locks until the eviction is performed or skipped (in case evicting the blocks would not free enough memory), we avoid a race where a new reader starts to read a block after the block has been marked as an eviction candidate but before it has been removed.
### Locking and remote block transfer
This patch makes small changes to to block transfer and network layer code so that locks acquired by the BlockTransferService are released as soon as block transfer messages are consumed and released by Netty. This builds on top of #11193, a bug fix related to freeing of network layer ManagedBuffers.
## FAQ
- **Why not use Java's built-in [`ReadWriteLock`](https://docs.oracle.com/javase/7/docs/api/java/util/concurrent/locks/ReadWriteLock.html)?**
Our locks operate on a per-task rather than per-thread level. Under certain circumstances a task may consist of multiple threads, so using `ReadWriteLock` would mean that we might call `unlock()` from a thread which didn't hold the lock in question, an operation which has undefined semantics. If we could rely on Java 8 classes, we might be able to use [`StampedLock`](https://docs.oracle.com/javase/8/docs/api/java/util/concurrent/locks/StampedLock.html) to work around this issue.
- **Why not detect "leaked" locks in tests?**:
See above notes about `take()` and `limit`.
Author: Josh Rosen <joshrosen@databricks.com>
Closes#10705 from JoshRosen/pin-pages.
Fixed the HTTP Server Host Name/IP issue i.e. HTTP Server to take the
configured host name/IP and not '0.0.0.0' always.
Author: Devaraj K <devaraj@apache.org>
Closes#11133 from devaraj-kavali/SPARK-13117.
Added an exception to be thrown in UnifiedMemoryManager.scala if the configuration given for executor memory is too low. Also modified the exception message thrown when driver memory is too low.
This patch was tested manually by passing in config options to Spark shell. I also added a test in UnifiedMemoryManagerSuite.scala
Author: Daniel Jalova <djalova@us.ibm.com>
Closes#11255 from djalova/SPARK-12759.
Currently the Mesos cluster dispatcher is not using offers from multiple roles correctly, as it simply aggregates all the offers resource values into one, but doesn't apply them correctly before calling the driver as Mesos needs the resources from the offers to be specified which role it originally belongs to. Multiple roles is already supported with fine/coarse grain scheduler, so porting that logic here to the cluster scheduler.
https://issues.apache.org/jira/browse/SPARK-10749
Author: Timothy Chen <tnachen@gmail.com>
Closes#8872 from tnachen/cluster_multi_roles.
## What changes were proposed in this pull request?
This PR tries to fix all typos in all markdown files under `docs` module,
and fixes similar typos in other comments, too.
## How was the this patch tested?
manual tests.
Author: Dongjoon Hyun <dongjoon@apache.org>
Closes#11300 from dongjoon-hyun/minor_fix_typos.
## What changes were proposed in this pull request?
This PR removes the support of SIMR, since SIMR is not actively used and maintained for a long time, also is not supported from `SparkSubmit`, so here propose to remove it.
## How was the this patch tested?
This patch is tested locally by running unit tests.
Author: jerryshao <sshao@hortonworks.com>
Closes#11296 from jerryshao/SPARK-13426.
## What changes were proposed in this pull request?
`JobWaiter.taskSucceeded` will be called for each task. When `resultHandler` throws an exception, `taskSucceeded` will also throw it for each task. DAGScheduler just catches it and reports it like this:
```Scala
try {
job.listener.taskSucceeded(rt.outputId, event.result)
} catch {
case e: Exception =>
// TODO: Perhaps we want to mark the resultStage as failed?
job.listener.jobFailed(new SparkDriverExecutionException(e))
}
```
Therefore `JobWaiter.jobFailed` may be called multiple times.
So `JobWaiter.jobFailed` should use `Promise.tryFailure` instead of `Promise.failure` because the latter one doesn't support calling multiple times.
## How was the this patch tested?
Jenkins tests.
Author: Shixiong Zhu <shixiong@databricks.com>
Closes#11280 from zsxwing/SPARK-13408.
`TaskMetrics.fromAccumulatorUpdates()` can fail if accumulators have been garbage-collected on the driver. To guard against this, this patch introduces `ListenerTaskMetrics`, a subclass of `TaskMetrics` which is used only in `TaskMetrics.fromAccumulatorUpdates()` and which eliminates the need to access the original accumulators on the driver.
Author: Josh Rosen <joshrosen@databricks.com>
Closes#11276 from JoshRosen/accum-updates-fix.
## What changes were proposed in this pull request?
Fix some comparisons between unequal types that cause IJ warnings and in at least one case a likely bug (TaskSetManager)
## How was the this patch tested?
Running Jenkins tests
Author: Sean Owen <sowen@cloudera.com>
Closes#11253 from srowen/SPARK-13371.
See http://openjdk.java.net/jeps/223 for more information about the JDK 9 version string scheme.
Author: Claes Redestad <claes.redestad@gmail.com>
Closes#11160 from cl4es/master.
Overrode the start() method, which was previously starting a thread causing a race condition. I believe this should fix the flaky test.
Author: Michael Gummelt <mgummelt@mesosphere.io>
Closes#11164 from mgummelt/fix_mesos_tests.
This JIRA is related to
https://github.com/apache/spark/pull/5852
Had to do some minor rework and test to make sure it
works with current version of spark.
Author: Sanket <schintap@untilservice-lm>
Closes#10838 from redsanket/limit-outbound-connections.
When the HistoryServer is showing an incomplete app, it needs to check if there is a newer version of the app available. It does this by checking if a version of the app has been loaded with a larger *filesize*. If so, it detaches the current UI, attaches the new one, and redirects back to the same URL to show the new UI.
https://issues.apache.org/jira/browse/SPARK-7889
Author: Steve Loughran <stevel@hortonworks.com>
Author: Imran Rashid <irashid@cloudera.com>
Closes#11118 from squito/SPARK-7889-alternate.
The "getPersistentRDDs()" is a useful API of SparkContext to get cached RDDs. However, the JavaSparkContext does not have this API.
Add a simple getPersistentRDDs() to get java.util.Map<Integer, JavaRDD> for Java users.
Author: Junyang <fly.shenjy@gmail.com>
Closes#10978 from flyjy/master.
Remove spark.closure.serializer option and use JavaSerializer always
CC andrewor14 rxin I see there's a discussion in the JIRA but just thought I'd offer this for a look at what the change would be.
Author: Sean Owen <sowen@cloudera.com>
Closes#11150 from srowen/SPARK-12414.
This is the next iteration of tnachen's previous PR: https://github.com/apache/spark/pull/4027
In that PR, we resolved with andrewor14 and pwendell to implement the Mesos scheduler's support of `spark.executor.cores` to be consistent with YARN and Standalone. This PR implements that resolution.
This PR implements two high-level features. These two features are co-dependent, so they're implemented both here:
- Mesos support for spark.executor.cores
- Multiple executors per slave
We at Mesosphere have been working with Typesafe on a Spark/Mesos integration test suite: https://github.com/typesafehub/mesos-spark-integration-tests, which passes for this PR.
The contribution is my original work and I license the work to the project under the project's open source license.
Author: Michael Gummelt <mgummelt@mesosphere.io>
Closes#10993 from mgummelt/executor_sizing.
This PR improve the lookup of BytesToBytesMap by:
1. Generate code for calculate the hash code of grouping keys.
2. Do not use MemoryLocation, fetch the baseObject and offset for key and value directly (remove the indirection).
Author: Davies Liu <davies@databricks.com>
Closes#11010 from davies/gen_map.
Additional changes to #10835, mainly related to style and visibility. This patch also adds back a few deprecated methods for backward compatibility.
Author: Andrew Or <andrew@databricks.com>
Closes#10958 from andrewor14/task-metrics-to-accums-followups.
There is a bug when we try to grow the buffer, OOM is ignore wrongly (the assert also skipped by JVM), then we try grow the array again, this one will trigger spilling free the current page, the current record we inserted will be invalid.
The root cause is that JVM has less free memory than MemoryManager thought, it will OOM when allocate a page without trigger spilling. We should catch the OOM, and acquire memory again to trigger spilling.
And also, we could not grow the array in `insertRecord` of `InMemorySorter` (it was there just for easy testing).
Author: Davies Liu <davies@databricks.com>
Closes#11095 from davies/fix_expand.
Trivial search-and-replace to eliminate deprecation warnings in Scala 2.11.
Also works with 2.10
Author: Jakob Odersky <jakob@odersky.com>
Closes#11085 from jodersky/SPARK-13171.
These were ignored because they are incorrectly written; they don't actually trigger stage retries, which is what the tests are testing. These tests are now rewritten to induce stage retries through fetch failures.
Note: there were 2 tests before and now there's only 1. What happened? It turns out that the case where we only resubmit a subset of of the original missing partitions is very difficult to simulate in tests without potentially introducing flakiness. This is because the `DAGScheduler` removes all map outputs associated with a given executor when this happens, and we will need multiple executors to trigger this case, and sometimes the scheduler still removes map outputs from all executors.
Author: Andrew Or <andrew@databricks.com>
Closes#10969 from andrewor14/unignore-accum-test.
Currently the Master would always set an application's initial executor limit to infinity. If the user specified `spark.dynamicAllocation.initialExecutors`, the config would not take effect. This is similar to #11047 but for standalone mode.
Author: Andrew Or <andrew@databricks.com>
Closes#11054 from andrewor14/standalone-da-initial.
Building with scala 2.11 results in the warning trait SynchronizedBuffer in package mutable is deprecated: Synchronization via traits is deprecated as it is inherently unreliable. Consider java.util.concurrent.ConcurrentLinkedQueue as an alternative. Investigation shows we are already using ConcurrentLinkedQueue in other locations so switch our uses of SynchronizedBuffer to ConcurrentLinkedQueue.
Author: Holden Karau <holden@us.ibm.com>
Closes#11059 from holdenk/SPARK-13164-replace-deprecated-synchronized-buffer-in-core.
Add a local property to indicate if checkpointing all RDDs that are marked with the checkpoint flag, and enable it in Streaming
Author: Shixiong Zhu <shixiong@databricks.com>
Closes#10934 from zsxwing/recursive-checkpoint.
This is an existing issue uncovered recently by #10835. The reason for the exception was because the `SQLHistoryListener` gets all sorts of accumulators, not just the ones that represent SQL metrics. For example, the listener gets the `internal.metrics.shuffleRead.remoteBlocksFetched`, which is an Int, then it proceeds to cast the Int to a Long, which fails.
The fix is to mark accumulators representing SQL metrics using some internal metadata. Then we can identify which ones are SQL metrics and only process those in the `SQLHistoryListener`.
Author: Andrew Or <andrew@databricks.com>
Closes#10971 from andrewor14/fix-sql-history.
[SPARK-10873] Support column sort and search for History Server using jQuery DataTable and REST API. Before this commit, the history server was generated hard-coded html and can not support search, also, the sorting was disabled if there is any application that has more than one attempt. Supporting search and sort (over all applications rather than the 20 entries in the current page) in any case will greatly improve user experience.
1. Create the historypage-template.html for displaying application information in datables.
2. historypage.js uses jQuery to access the data from /api/v1/applications REST API, and use DataTable to display each application's information. For application that has more than one attempt, the RowsGroup is used to merge such entries while at the same time supporting sort and search.
3. "duration" and "lastUpdated" rest API are added to application's "attempts".
4. External javascirpt and css files for datatables, RowsGroup and jquery plugins are added with licenses clarified.
Snapshots for how it looks like now:
History page view:
Search:
Sort by started time:
Author: zhuol <zhuol@yahoo-inc.com>
Closes#10648 from zhuoliu/10873.
Spark's `Partition` and `RDD.partitions` APIs have a contract which requires custom implementations of `RDD.partitions` to ensure that for all `x`, `rdd.partitions(x).index == x`; in other words, the `index` reported by a repartition needs to match its position in the partitions array.
If a custom RDD implementation violates this contract, then Spark has the potential to become stuck in an infinite recomputation loop when recomputing a subset of an RDD's partitions, since the tasks that are actually run will not correspond to the missing output partitions that triggered the recomputation. Here's a link to a notebook which demonstrates this problem: 5e8a5aa8d2/Violating%2520RDD.partitions%2520contract.html
In order to guard against this infinite loop behavior, this patch modifies Spark so that it fails fast and refuses to compute RDDs' whose `partitions` violate the API contract.
Author: Josh Rosen <joshrosen@databricks.com>
Closes#10932 from JoshRosen/SPARK-13021.
The high level idea is that instead of having the executors send both accumulator updates and TaskMetrics, we should have them send only accumulator updates. This eliminates the need to maintain both code paths since one can be implemented in terms of the other. This effort is split into two parts:
**SPARK-12895: Implement TaskMetrics using accumulators.** TaskMetrics is basically just a bunch of accumulable fields. This patch makes TaskMetrics a syntactic wrapper around a collection of accumulators so we don't need to send TaskMetrics from the executors to the driver.
**SPARK-12896: Send only accumulator updates to the driver.** Now that TaskMetrics are expressed in terms of accumulators, we can capture all TaskMetrics values if we just send accumulator updates from the executors to the driver. This completes the parent issue SPARK-10620.
While an effort has been made to preserve as much of the public API as possible, there were a few known breaking DeveloperApi changes that would be very awkward to maintain. I will gather the full list shortly and post it here.
Note: This was once part of #10717. This patch is split out into its own patch from there to make it easier for others to review. Other smaller pieces of already been merged into master.
Author: Andrew Or <andrew@databricks.com>
Closes#10835 from andrewor14/task-metrics-use-accums.
Fix Java function API methods for flatMap and mapPartitions to require producing only an Iterator, not Iterable. Also fix DStream.flatMap to require a function producing TraversableOnce only, not Traversable.
CC rxin pwendell for API change; tdas since it also touches streaming.
Author: Sean Owen <sowen@cloudera.com>
Closes#10413 from srowen/SPARK-3369.
Added color coding to the Executors page for Active Tasks, Failed Tasks, Completed Tasks and Task Time.
Active Tasks is shaded blue with it's range based on percentage of total cores used.
Failed Tasks is shaded red ranging over the first 10% of total tasks failed
Completed Tasks is shaded green ranging over 10% of total tasks including failed and active tasks, but only when there are active or failed tasks on that executor.
Task Time is shaded red when GC Time goes over 10% of total time with it's range directly corresponding to the percent of total time.
Author: Alex Bozarth <ajbozart@us.ibm.com>
Closes#10154 from ajbozarth/spark12149.
- Remove Akka dependency from core. Note: the streaming-akka project still uses Akka.
- Remove HttpFileServer
- Remove Akka configs from SparkConf and SSLOptions
- Rename `spark.akka.frameSize` to `spark.rpc.message.maxSize`. I think it's still worth to keep this config because using `DirectTaskResult` or `IndirectTaskResult` depends on it.
- Update comments and docs
Author: Shixiong Zhu <shixiong@databricks.com>
Closes#10854 from zsxwing/remove-akka.
This is a step in implementing SPARK-10620, which migrates TaskMetrics to accumulators.
TaskMetrics has a bunch of var's, some are fully public, some are `private[spark]`. This is bad coding style that makes it easy to accidentally overwrite previously set metrics. This has happened a few times in the past and caused bugs that were difficult to debug.
Instead, we should have get-or-create semantics, which are more readily understandable. This makes sense in the case of TaskMetrics because these are just aggregated metrics that we want to collect throughout the task, so it doesn't matter who's incrementing them.
Parent PR: #10717
Author: Andrew Or <andrew@databricks.com>
Author: Josh Rosen <joshrosen@databricks.com>
Author: andrewor14 <andrew@databricks.com>
Closes#10815 from andrewor14/get-or-create-metrics.
This is a small step in implementing SPARK-10620, which migrates TaskMetrics to accumulators. This patch is strictly a cleanup patch and introduces no change in functionality. It literally just renames 3 fields for consistency. Today we have:
```
inputMetrics.recordsRead
outputMetrics.bytesWritten
shuffleReadMetrics.localBlocksFetched
...
shuffleWriteMetrics.shuffleRecordsWritten
shuffleWriteMetrics.shuffleBytesWritten
shuffleWriteMetrics.shuffleWriteTime
```
The shuffle write ones are kind of redundant. We can drop the `shuffle` part in the method names. I added backward compatible (but deprecated) methods with the old names.
Parent PR: #10717
Author: Andrew Or <andrew@databricks.com>
Closes#10811 from andrewor14/rename-things.
This patch refactors portions of the BlockManager and CacheManager in order to avoid having to pass `evictedBlocks` lists throughout the code. It appears that these lists were only consumed by `TaskContext.taskMetrics`, so the new code now directly updates the metrics from the lower-level BlockManager methods.
Author: Josh Rosen <joshrosen@databricks.com>
Closes#10776 from JoshRosen/SPARK-10985.
This pull request removes the external block store API. This is rarely used, and the file system interface is actually a better, more standard way to interact with external storage systems.
There are some other things to remove also, as pointed out by JoshRosen. We will do those as follow-up pull requests.
Author: Reynold Xin <rxin@databricks.com>
Closes#10752 from rxin/remove-offheap.
This patch significantly speeds up the BlockManagerSuite's "SPARK-9591: getRemoteBytes from another location when Exception throw" test, reducing the test time from 45s to ~250ms. The key change was to set `spark.shuffle.io.maxRetries` to 0 (the code previously set `spark.network.timeout` to `2s`, but this didn't make a difference because the slowdown was not due to this timeout).
Along the way, I also cleaned up the way that we handle SparkConf in BlockManagerSuite: previously, each test would mutate a shared SparkConf instance, while now each test gets a fresh SparkConf.
Author: Josh Rosen <joshrosen@databricks.com>
Closes#10759 from JoshRosen/SPARK-12174.
When an Executor process is destroyed, the FileAppender that is asynchronously reading the stderr stream of the process can throw an IOException during read because the stream is closed. Before the ExecutorRunner destroys the process, the FileAppender thread is flagged to stop. This PR wraps the inputStream.read call of the FileAppender in a try/catch block so that if an IOException is thrown and the thread has been flagged to stop, it will safely ignore the exception. Additionally, the FileAppender thread was changed to use Utils.tryWithSafeFinally to better log any exception that do occur. Added unit tests to verify a IOException is thrown and logged if FileAppender is not flagged to stop, and that no IOException when the flag is set.
Author: Bryan Cutler <cutlerb@gmail.com>
Closes#10714 from BryanCutler/file-appender-read-ioexception-SPARK-9844.
We've already removed local execution but didn't deprecate `TaskContext.isRunningLocally()`; we should deprecate it for 2.0.
Author: Josh Rosen <joshrosen@databricks.com>
Closes#10751 from JoshRosen/remove-local-exec-from-taskcontext.
This problem lies in `BypassMergeSortShuffleWriter`, empty partition will also generate a temp shuffle file with several bytes. So here change to only create file when partition is not empty.
This problem only lies in here, no such issue in `HashShuffleWriter`.
Please help to review, thanks a lot.
Author: jerryshao <sshao@hortonworks.com>
Closes#10376 from jerryshao/SPARK-12400.
Fix the style violation (space before , and :).
This PR is a followup for #10643
Author: Kousuke Saruta <sarutak@oss.nttdata.co.jp>
Closes#10719 from sarutak/SPARK-12692-followup-core.
[SPARK-12582][Test] IndexShuffleBlockResolverSuite fails in windows
* IndexShuffleBlockResolverSuite fails in windows due to file is not closed.
* mv IndexShuffleBlockResolverSuite.scala from "test/java" to "test/scala".
https://issues.apache.org/jira/browse/SPARK-12582
Author: Yucai Yu <yucai.yu@intel.com>
Closes#10526 from yucai/master.
This patch deduplicates some test code in BlockManagerSuite. I'm splitting this change off from a larger PR in order to make things easier to review.
Author: Josh Rosen <joshrosen@databricks.com>
Closes#10667 from JoshRosen/block-mgr-tests-cleanup.
Replace Guava `Optional` with (an API clone of) Java 8 `java.util.Optional` (edit: and a clone of Guava `Optional`)
See also https://github.com/apache/spark/pull/10512
Author: Sean Owen <sowen@cloudera.com>
Closes#10513 from srowen/SPARK-4819.
Fix most build warnings: mostly deprecated API usages. I'll annotate some of the changes below. CC rxin who is leading the charge to remove the deprecated APIs.
Author: Sean Owen <sowen@cloudera.com>
Closes#10570 from srowen/SPARK-12618.
The default serializer in Kryo is FieldSerializer and it ignores transient fields and never calls `writeObject` or `readObject`. So we should register OpenHashMapBasedStateMap using `DefaultSerializer` to make it work with Kryo.
Author: Shixiong Zhu <shixiong@databricks.com>
Closes#10609 from zsxwing/SPARK-12591.
This PR removes `spark.cleaner.ttl` and the associated TTL-based metadata cleaning code.
Now that we have the `ContextCleaner` and a timer to trigger periodic GCs, I don't think that `spark.cleaner.ttl` is necessary anymore. The TTL-based cleaning isn't enabled by default, isn't included in our end-to-end tests, and has been a source of user confusion when it is misconfigured. If the TTL is set too low, data which is still being used may be evicted / deleted, leading to hard to diagnose bugs.
For all of these reasons, I think that we should remove this functionality in Spark 2.0. Additional benefits of doing this include marginally reduced memory usage, since we no longer need to store timetsamps in hashmaps, and a handful fewer threads.
Author: Josh Rosen <joshrosen@databricks.com>
Closes#10534 from JoshRosen/remove-ttl-based-cleaning.
Change Java countByKey, countApproxDistinctByKey return types to use Java Long, not Scala; update similar methods for consistency on java.long.Long.valueOf with no API change
Author: Sean Owen <sowen@cloudera.com>
Closes#10554 from srowen/SPARK-12604.
Whole code of Vector.scala, VectorSuite.scala and GraphKryoRegistrator.scala are no longer used so it's time to remove them in Spark 2.0.
Author: Kousuke Saruta <sarutak@oss.nttdata.co.jp>
Closes#10613 from sarutak/SPARK-12665.
Cartesian product use UnsafeExternalSorter without comparator to do spilling, it will NPE if spilling happens.
This bug also hitted by #10605
cc JoshRosen
Author: Davies Liu <davies@databricks.com>
Closes#10606 from davies/fix_spilling.
I looked at each case individually and it looks like they can all be removed. The only one that I had to think twice was toArray (I even thought about un-deprecating it, until I realized it was a problem in Java to have toArray returning java.util.List).
Author: Reynold Xin <rxin@databricks.com>
Closes#10569 from rxin/SPARK-12615.
This patch updates the ExecutorRunner's terminate path to use the new java 8 API
to terminate processes more forcefully if possible. If the executor is unhealthy,
it would previously ignore the destroy() call. Presumably, the new java API was
added to handle cases like this.
We could update the termination path in the future to use OS specific commands
for older java versions.
Author: Nong Li <nong@databricks.com>
Closes#10438 from nongli/spark-12486-executors.
### Remove AkkaRpcEnv
Keep `SparkEnv.actorSystem` because Streaming still uses it. Will remove it and AkkaUtils after refactoring Streaming actorStream API.
### Remove systemName
There are 2 places using `systemName`:
* `RpcEnvConfig.name`. Actually, although it's used as `systemName` in `AkkaRpcEnv`, `NettyRpcEnv` uses it as the service name to output the log `Successfully started service *** on port ***`. Since the service name in log is useful, I keep `RpcEnvConfig.name`.
* `def setupEndpointRef(systemName: String, address: RpcAddress, endpointName: String)`. Each `ActorSystem` has a `systemName`. Akka requires `systemName` in its URI and will refuse a connection if `systemName` is not matched. However, `NettyRpcEnv` doesn't use it. So we can remove `systemName` from `setupEndpointRef` since we are removing `AkkaRpcEnv`.
### Remove RpcEnv.uriOf
`uriOf` exists because Akka uses different URI formats for with and without authentication, e.g., `akka.ssl.tcp...` and `akka.tcp://...`. But `NettyRpcEnv` uses the same format. So it's not necessary after removing `AkkaRpcEnv`.
Author: Shixiong Zhu <shixiong@databricks.com>
Closes#10459 from zsxwing/remove-akka-rpc-env.
We switched to TorrentBroadcast in Spark 1.1, and HttpBroadcast has been undocumented since then. It's time to remove it in Spark 2.0.
Author: Reynold Xin <rxin@databricks.com>
Closes#10531 from rxin/SPARK-12588.
The web UI's paginated table uses Javascript to implement certain navigation controls, such as table sorting and the "go to page" form. This is unnecessary and should be simplified to use plain HTML form controls and links.
/cc zsxwing, who wrote this original code, and yhuai.
Author: Josh Rosen <joshrosen@databricks.com>
Closes#10441 from JoshRosen/simplify-paginated-table-sorting.
The feature was first added at commit: 7b877b2705 but was later removed (probably by mistake) at commit: fc8b58195a.
This change sets the default path of RDDs created via sc.textFile(...) to the path argument.
Here is the symptom:
* Using spark-1.5.2-bin-hadoop2.6:
scala> sc.textFile("/home/root/.bashrc").name
res5: String = null
scala> sc.binaryFiles("/home/root/.bashrc").name
res6: String = /home/root/.bashrc
* while using Spark 1.3.1:
scala> sc.textFile("/home/root/.bashrc").name
res0: String = /home/root/.bashrc
scala> sc.binaryFiles("/home/root/.bashrc").name
res1: String = /home/root/.bashrc
Author: Yaron Weinsberg <wyaron@gmail.com>
Author: yaron <yaron@il.ibm.com>
Closes#10456 from wyaron/master.
Restore the original value of os.arch property after each test
Since some of tests forced to set the specific value to os.arch property, we need to set the original value.
Author: Kazuaki Ishizaki <ishizaki@jp.ibm.com>
Closes#10289 from kiszk/SPARK-12311.
According the benchmark [1], LZ4-java could be 80% (or 30%) faster than Snappy.
After changing the compressor to LZ4, I saw 20% improvement on end-to-end time for a TPCDS query (Q4).
[1] https://github.com/ning/jvm-compressor-benchmark/wiki
cc rxin
Author: Davies Liu <davies@databricks.com>
Closes#10342 from davies/lz4.
When multiple workers exist in a host, we can bypass unnecessary remote access for broadcasts; block managers fetch broadcast blocks from the same host instead of remote hosts.
Author: Takeshi YAMAMURO <linguin.m.s@gmail.com>
Closes#10346 from maropu/OptimizeBlockLocationOrder.
Added `channelActive` to `RpcHandler` so that `NettyRpcHandler` doesn't need `clients` any more.
Author: Shixiong Zhu <shixiong@databricks.com>
Closes#10301 from zsxwing/network-events.
In discussion (SPARK-9552), we proposed a force kill in `killExecutors`. But if there is nothing to kill, it will return back with true (acknowledgement). And then, it causes the certain executor(s) (which is not eligible to kill) adding to pendingToRemove list for further actions.
In this patch, we'd like to change the return semantics. If there is nothing to kill, we will return "false". and therefore all those non-eligible executors won't be added to the pendingToRemove list.
vanzin andrewor14 As the follow up of PR#7888, please let me know your comments.
Author: Grace <jie.huang@intel.com>
Author: Jie Huang <hjie@fosun.com>
Author: Andrew Or <andrew@databricks.com>
Closes#9796 from GraceH/emptyPendingToRemove.
Not jira is created.
The original test is passed because the class cast is lazy (only when the object's method is invoked).
Author: Jeff Zhang <zjffdu@apache.org>
Closes#10371 from zjffdu/minor_fix.
`DAGSchedulerEventLoop` normally only logs errors (so it can continue to process more events, from other jobs). However, this is not desirable in the tests -- the tests should be able to easily detect any exception, and also shouldn't silently succeed if there is an exception.
This was suggested by mateiz on https://github.com/apache/spark/pull/7699. It may have already turned up an issue in "zero split job".
Author: Imran Rashid <irashid@cloudera.com>
Closes#8466 from squito/SPARK-10248.
These changes rework the implementations of `SimpleFutureAction`, `ComplexFutureAction`, `JobWaiter`, and `AsyncRDDActions` such that asynchronous callbacks on the generated `Futures` NEVER block waiting for a job to complete. A small amount of mutex synchronization is necessary to protect the internal fields that manage cancellation, but these locks are only held very briefly and in practice should almost never cause any blocking to occur. The existing blocking APIs of these classes are retained, but they simply delegate to the underlying non-blocking API and `Await` the results with indefinite timeouts.
Associated JIRA ticket: https://issues.apache.org/jira/browse/SPARK-9026
Also fixes: https://issues.apache.org/jira/browse/SPARK-4514
This pull request contains all my own original work, which I release to the Spark project under its open source license.
Author: Richard W. Eggert II <richard.eggert@gmail.com>
Closes#9264 from reggert/fix-futureaction.
Fix a minor typo (unbalanced bracket) in ResetSystemProperties.
Author: Holden Karau <holden@us.ibm.com>
Closes#10303 from holdenk/SPARK-12332-trivial-typo-in-ResetSystemProperties-comment.
**Problem.** In unified memory management, acquiring execution memory may lead to eviction of storage memory. However, the space freed from evicting cached blocks is distributed among all active tasks. Thus, an incorrect upper bound on the execution memory per task can cause the acquisition to fail, leading to OOM's and premature spills.
**Example.** Suppose total memory is 1000B, cached blocks occupy 900B, `spark.memory.storageFraction` is 0.4, and there are two active tasks. In this case, the cap on task execution memory is 100B / 2 = 50B. If task A tries to acquire 200B, it will evict 100B of storage but can only acquire 50B because of the incorrect cap. For another example, see this [regression test](https://github.com/andrewor14/spark/blob/fix-oom/core/src/test/scala/org/apache/spark/memory/UnifiedMemoryManagerSuite.scala#L233) that I stole from JoshRosen.
**Solution.** Fix the cap on task execution memory. It should take into account the space that could have been freed by storage in addition to the current amount of memory available to execution. In the example above, the correct cap should have been 600B / 2 = 300B.
This patch also guards against the race condition (SPARK-12253):
(1) Existing tasks collectively occupy all execution memory
(2) New task comes in and blocks while existing tasks spill
(3) After tasks finish spilling, another task jumps in and puts in a large block, stealing the freed memory
(4) New task still cannot acquire memory and goes back to sleep
Author: Andrew Or <andrew@databricks.com>
Closes#10240 from andrewor14/fix-oom.
This patch adds documentation for Spark configurations that affect off-heap memory and makes some naming and validation improvements for those configs.
- Change `spark.memory.offHeapSize` to `spark.memory.offHeap.size`. This is fine because this configuration has not shipped in any Spark release yet (it's new in Spark 1.6).
- Deprecated `spark.unsafe.offHeap` in favor of a new `spark.memory.offHeap.enabled` configuration. The motivation behind this change is to gather all memory-related configurations under the same prefix.
- Add a check which prevents users from setting `spark.memory.offHeap.enabled=true` when `spark.memory.offHeap.size == 0`. After SPARK-11389 (#9344), which was committed in Spark 1.6, Spark enforces a hard limit on the amount of off-heap memory that it will allocate to tasks. As a result, enabling off-heap execution memory without setting `spark.memory.offHeap.size` will lead to immediate OOMs. The new configuration validation makes this scenario easier to diagnose, helping to avoid user confusion.
- Document these configurations on the configuration page.
Author: Josh Rosen <joshrosen@databricks.com>
Closes#10237 from JoshRosen/SPARK-12251.
This avoids bringing up yet another HTTP server on the driver, and
instead reuses the file server already managed by the driver's
RpcEnv. As a bonus, the repl now inherits the security features of
the network library.
There's also a small change to create the directory for storing classes
under the root temp dir for the application (instead of directly
under java.io.tmpdir).
Author: Marcelo Vanzin <vanzin@cloudera.com>
Closes#9923 from vanzin/SPARK-11563.
This patch fixes a bug in the eviction of storage memory by execution.
## The bug:
In general, execution should be able to evict storage memory when the total storage memory usage is greater than `maxMemory * spark.memory.storageFraction`. Due to a bug, however, Spark might wind up evicting no storage memory in certain cases where the storage memory usage was between `maxMemory * spark.memory.storageFraction` and `maxMemory`. For example, here is a regression test which illustrates the bug:
```scala
val maxMemory = 1000L
val taskAttemptId = 0L
val (mm, ms) = makeThings(maxMemory)
// Since we used the default storage fraction (0.5), we should be able to allocate 500 bytes
// of storage memory which are immune to eviction by execution memory pressure.
// Acquire enough storage memory to exceed the storage region size
assert(mm.acquireStorageMemory(dummyBlock, 750L, evictedBlocks))
assertEvictBlocksToFreeSpaceNotCalled(ms)
assert(mm.executionMemoryUsed === 0L)
assert(mm.storageMemoryUsed === 750L)
// At this point, storage is using 250 more bytes of memory than it is guaranteed, so execution
// should be able to reclaim up to 250 bytes of storage memory.
// Therefore, execution should now be able to require up to 500 bytes of memory:
assert(mm.acquireExecutionMemory(500L, taskAttemptId, MemoryMode.ON_HEAP) === 500L) // <--- fails by only returning 250L
assert(mm.storageMemoryUsed === 500L)
assert(mm.executionMemoryUsed === 500L)
assertEvictBlocksToFreeSpaceCalled(ms, 250L)
```
The problem relates to the control flow / interaction between `StorageMemoryPool.shrinkPoolToReclaimSpace()` and `MemoryStore.ensureFreeSpace()`. While trying to allocate the 500 bytes of execution memory, the `UnifiedMemoryManager` discovers that it will need to reclaim 250 bytes of memory from storage, so it calls `StorageMemoryPool.shrinkPoolToReclaimSpace(250L)`. This method, in turn, calls `MemoryStore.ensureFreeSpace(250L)`. However, `ensureFreeSpace()` first checks whether the requested space is less than `maxStorageMemory - storageMemoryUsed`, which will be true if there is any free execution memory because it turns out that `MemoryStore.maxStorageMemory = (maxMemory - onHeapExecutionMemoryPool.memoryUsed)` when the `UnifiedMemoryManager` is used.
The control flow here is somewhat confusing (it grew to be messy / confusing over time / as a result of the merging / refactoring of several components). In the pre-Spark 1.6 code, `ensureFreeSpace` was called directly by the `MemoryStore` itself, whereas in 1.6 it's involved in a confusing control flow where `MemoryStore` calls `MemoryManager.acquireStorageMemory`, which then calls back into `MemoryStore.ensureFreeSpace`, which, in turn, calls `MemoryManager.freeStorageMemory`.
## The solution:
The solution implemented in this patch is to remove the confusing circular control flow between `MemoryManager` and `MemoryStore`, making the storage memory acquisition process much more linear / straightforward. The key changes:
- Remove a layer of inheritance which made the memory manager code harder to understand (53841174760a24a0df3eb1562af1f33dbe340eb9).
- Move some bounds checks earlier in the call chain (13ba7ada77f87ef1ec362aec35c89a924e6987cb).
- Refactor `ensureFreeSpace()` so that the part which evicts blocks can be called independently from the part which checks whether there is enough free space to avoid eviction (7c68ca09cb1b12f157400866983f753ac863380e).
- Realize that this lets us remove a layer of overloads from `ensureFreeSpace` (eec4f6c87423d5e482b710e098486b3bbc4daf06).
- Realize that `ensureFreeSpace()` can simply be replaced with an `evictBlocksToFreeSpace()` method which is called [after we've already figured out](2dc842aea8/core/src/main/scala/org/apache/spark/memory/StorageMemoryPool.scala (L88)) how much memory needs to be reclaimed via eviction; (2dc842aea82c8895125d46a00aa43dfb0d121de9).
Along the way, I fixed some problems with the mocks in `MemoryManagerSuite`: the old mocks would [unconditionally](80a824d36e/core/src/test/scala/org/apache/spark/memory/MemoryManagerSuite.scala (L84)) report that a block had been evicted even if there was enough space in the storage pool such that eviction would be avoided.
I also fixed a problem where `StorageMemoryPool._memoryUsed` might become negative due to freed memory being double-counted when excution evicts storage. The problem was that `StorageMemoryPoolshrinkPoolToFreeSpace` would [decrement `_memoryUsed`](7c68ca09cb (diff-935c68a9803be144ed7bafdd2f756a0fL133)) even though `StorageMemoryPool.freeMemory` had already decremented it as each evicted block was freed. See SPARK-12189 for details.
Author: Josh Rosen <joshrosen@databricks.com>
Author: Andrew Or <andrew@databricks.com>
Closes#10170 from JoshRosen/SPARK-12165.
Because of AM failure, the target executor number between driver and AM will be different, which will lead to unexpected behavior in dynamic allocation. So when AM is re-registered with driver, state in `ExecutorAllocationManager` and `CoarseGrainedSchedulerBacked` should be reset.
This issue is originally addressed in #8737 , here re-opened again. Thanks a lot KaiXinXiaoLei for finding this issue.
andrewor14 and vanzin would you please help to review this, thanks a lot.
Author: jerryshao <sshao@hortonworks.com>
Closes#9963 from jerryshao/SPARK-10582.
The json endpoint for stages doesn't include information on the stage duration that is present in the UI. This looks like a simple oversight, they should be included. eg., the metrics should be included at api/v1/applications/<appId>/stages.
Metrics I've added are: submissionTime, firstTaskLaunchedTime and completionTime
Author: Xin Ren <iamshrek@126.com>
Closes#10107 from keypointt/SPARK-11155.
`ByteBuffer` doesn't guarantee all contents in `ByteBuffer.array` are valid. E.g, a ByteBuffer returned by `ByteBuffer.slice`. We should not use the whole content of `ByteBuffer` unless we know that's correct.
This patch fixed all places that use `ByteBuffer.array` incorrectly.
Author: Shixiong Zhu <shixiong@databricks.com>
Closes#10083 from zsxwing/bytebuffer-array.
We should upgrade to SBT 0.13.9, since this is a requirement in order to use SBT's new Maven-style resolution features (which will be done in a separate patch, because it's blocked by some binary compatibility issues in the POM reader plugin).
I also upgraded Scalastyle to version 0.8.0, which was necessary in order to fix a Scala 2.10.5 compatibility issue (see https://github.com/scalastyle/scalastyle/issues/156). The newer Scalastyle is slightly stricter about whitespace surrounding tokens, so I fixed the new style violations.
Author: Josh Rosen <joshrosen@databricks.com>
Closes#10112 from JoshRosen/upgrade-to-sbt-0.13.9.
This replaces https://github.com/apache/spark/pull/9696
Invoke Checkstyle and print any errors to the console, failing the step.
Use Google's style rules modified according to
https://cwiki.apache.org/confluence/display/SPARK/Spark+Code+Style+Guide
Some important checks are disabled (see TODOs in `checkstyle.xml`) due to
multiple violations being present in the codebase.
Suggest fixing those TODOs in a separate PR(s).
More on Checkstyle can be found on the [official website](http://checkstyle.sourceforge.net/).
Sample output (from [build 46345](https://amplab.cs.berkeley.edu/jenkins/job/SparkPullRequestBuilder/46345/consoleFull)) (duplicated because I run the build twice with different profiles):
> Checkstyle checks failed at following occurrences:
[ERROR] src/main/java/org/apache/spark/sql/execution/datasources/parquet/UnsafeRowParquetRecordReader.java:[217,7] (coding) MissingSwitchDefault: switch without "default" clause.
> [ERROR] src/main/java/org/apache/spark/sql/execution/datasources/parquet/SpecificParquetRecordReaderBase.java:[198,10] (modifier) ModifierOrder: 'protected' modifier out of order with the JLS suggestions.
> [ERROR] src/main/java/org/apache/spark/sql/execution/datasources/parquet/UnsafeRowParquetRecordReader.java:[217,7] (coding) MissingSwitchDefault: switch without "default" clause.
> [ERROR] src/main/java/org/apache/spark/sql/execution/datasources/parquet/SpecificParquetRecordReaderBase.java:[198,10] (modifier) ModifierOrder: 'protected' modifier out of order with the JLS suggestions.
> [error] running /home/jenkins/workspace/SparkPullRequestBuilder2/dev/lint-java ; received return code 1
Also fix some of the minor violations that didn't require sweeping changes.
Apologies for the previous botched PRs - I finally figured out the issue.
cr: JoshRosen, pwendell
> I state that the contribution is my original work, and I license the work to the project under the project's open source license.
Author: Dmitry Erastov <derastov@gmail.com>
Closes#9867 from dskrvk/master.
**Problem.** Event logs in 1.6 were much bigger than 1.5. I ran page rank and the event log size in 1.6 was almost 5x that in 1.5. I did a bisect to find that the RDD callsite added in #9398 is largely responsible for this.
**Solution.** This patch removes the long form of the callsite (which is not used!) from the event log. This reduces the size of the event log significantly.
*Note on compatibility*: if this patch is to be merged into 1.6.0, then it won't break any compatibility. Otherwise, if it is merged into 1.6.1, then we might need to add more backward compatibility handling logic (currently does not exist yet).
Author: Andrew Or <andrew@databricks.com>
Closes#10115 from andrewor14/smaller-event-logs.
We should try increasing a timeout in NettyBlockTransferSecuritySuite in order to reduce that suite's flakiness in Jenkins.
Author: Josh Rosen <joshrosen@databricks.com>
Closes#10113 from JoshRosen/SPARK-12082.
I have tried to address all the comments in pull request https://github.com/apache/spark/pull/2447.
Note that the second commit (using the new method in all internal code of all components) is quite intrusive and could be omitted.
Author: Jeroen Schot <jeroen.schot@surfsara.nl>
Closes#9767 from schot/master.
The existing `spark.memory.fraction` (default 0.75) gives the system 25% of the space to work with. For small heaps, this is not enough: e.g. default 1GB leaves only 250MB system memory. This is especially a problem in local mode, where the driver and executor are crammed in the same JVM. Members of the community have reported driver OOM's in such cases.
**New proposal.** We now reserve 300MB before taking the 75%. For 1GB JVMs, this leaves `(1024 - 300) * 0.75 = 543MB` for execution and storage. This is proposal (1) listed in the [JIRA](https://issues.apache.org/jira/browse/SPARK-12081).
Author: Andrew Or <andrew@databricks.com>
Closes#10081 from andrewor14/unified-memory-small-heaps.
The solution is the save the RDD partitioner in a separate file in the RDD checkpoint directory. That is, `<checkpoint dir>/_partitioner`. In most cases, whether the RDD partitioner was recovered or not, does not affect the correctness, only reduces performance. So this solution makes a best-effort attempt to save and recover the partitioner. If either fails, the checkpointing is not affected. This makes this patch safe and backward compatible.
Author: Tathagata Das <tathagata.das1565@gmail.com>
Closes#9983 from tdas/SPARK-12004.
This change seems large, but most of it is just replacing `byte[]`
with `ByteBuffer` and `new byte[]` with `ByteBuffer.allocate()`,
since it changes the network library's API.
The following are parts of the code that actually have meaningful
changes:
- The Message implementations were changed to inherit from a new
AbstractMessage that can optionally hold a reference to a body
(in the form of a ManagedBuffer); this is similar to how
ResponseWithBody worked before, except now it's not restricted
to just responses.
- The TransportFrameDecoder was pretty much rewritten to avoid
copies as much as possible; it doesn't rely on CompositeByteBuf
to accumulate incoming data anymore, since CompositeByteBuf
has issues when slices are retained. The code now is able to
create frames without having to resort to copying bytes except
for a few bytes (containing the frame length) in very rare cases.
- Some minor changes in the SASL layer to convert things back to
`byte[]` since the JDK SASL API operates on those.
Author: Marcelo Vanzin <vanzin@cloudera.com>
Closes#9987 from vanzin/SPARK-12007.
In the previous codes, `newDaemonCachedThreadPool` uses `SynchronousQueue`, which is wrong. `SynchronousQueue` is an empty queue that cannot cache any task. This patch uses `LinkedBlockingQueue` to fix it along with other fixes to make sure `newDaemonCachedThreadPool` can use at most `maxThreadNumber` threads, and after that, cache tasks to `LinkedBlockingQueue`.
Author: Shixiong Zhu <shixiong@databricks.com>
Closes#9978 from zsxwing/cached-threadpool.
This change does a couple of different things to make sure that the RpcEnv-level
code and the network library agree about the status of outstanding RPCs.
For RPCs that do not expect a reply ("RpcEnv.send"), support for one way
messages (hello CORBA!) was added to the network layer. This is a
"fire and forget" message that does not require any state to be kept
by the TransportClient; as a result, the RpcEnv 'Ack' message is not needed
anymore.
For RPCs that do expect a reply ("RpcEnv.ask"), the network library now
returns the internal RPC id; if the RpcEnv layer decides to time out the
RPC before the network layer does, it now asks the TransportClient to
forget about the RPC, so that if the network-level timeout occurs, the
client is not killed.
As part of implementing the above, I cleaned up some of the code in the
netty rpc backend, removing types that were not necessary and factoring
out some common code. Of interest is a slight change in the exceptions
when posting messages to a stopped RpcEnv; that's mostly to avoid nasty
error messages from the local-cluster backend when shutting down, which
pollutes the terminal output.
Author: Marcelo Vanzin <vanzin@cloudera.com>
Closes#9917 from vanzin/SPARK-11866.
- NettyRpcEnv::openStream() now correctly propagates errors to
the read side of the pipe.
- NettyStreamManager now throws if the file being transferred does
not exist.
- The network library now correctly handles zero-sized streams.
Author: Marcelo Vanzin <vanzin@cloudera.com>
Closes#9941 from vanzin/SPARK-11956.
This issue was addressed in https://github.com/apache/spark/pull/5494, but the fix in that PR, while safe in the sense that it will prevent the SparkContext from shutting down, misses the actual bug. The intent of `submitMissingTasks` should be understood as "submit the Tasks that are missing for the Stage, and run them as part of the ActiveJob identified by jobId". Because of a long-standing bug, the `jobId` parameter was never being used. Instead, we were trying to use the jobId with which the Stage was created -- which may no longer exist as an ActiveJob, hence the crash reported in SPARK-6880.
The correct fix is to use the ActiveJob specified by the supplied jobId parameter, which is guaranteed to exist at the call sites of submitMissingTasks.
This fix should be applied to all maintenance branches, since it has existed since 1.0.
kayousterhout pankajarora12
Author: Mark Hamstra <markhamstra@gmail.com>
Author: Imran Rashid <irashid@cloudera.com>
Closes#6291 from markhamstra/SPARK-6880.
This is continuation of SPARK-11761
Andrew suggested adding this protection. See tail of https://github.com/apache/spark/pull/9741
Author: tedyu <yuzhihong@gmail.com>
Closes#9852 from tedyu/master.
This change abstracts the code that serves jars / files to executors so that
each RpcEnv can have its own implementation; the akka version uses the existing
HTTP-based file serving mechanism, while the netty versions uses the new
stream support added to the network lib, which makes file transfers benefit
from the easier security configuration of the network library, and should also
reduce overhead overall.
The change includes a small fix to TransportChannelHandler so that it propagates
user events to downstream handlers.
Author: Marcelo Vanzin <vanzin@cloudera.com>
Closes#9530 from vanzin/SPARK-11140.
In PersistenceEngineSuite, we do not call `close()` on the PersistenceEngine at the end of the test. For the ZooKeeperPersistenceEngine, this causes us to leak a ZooKeeper client, causing the logs of unrelated tests to be periodically spammed with connection error messages from that client:
```
15/11/20 05:13:35.789 pool-1-thread-1-ScalaTest-running-PersistenceEngineSuite-SendThread(localhost:15741) INFO ClientCnxn: Opening socket connection to server localhost/127.0.0.1:15741. Will not attempt to authenticate using SASL (unknown error)
15/11/20 05:13:35.790 pool-1-thread-1-ScalaTest-running-PersistenceEngineSuite-SendThread(localhost:15741) WARN ClientCnxn: Session 0x15124ff48dd0000 for server null, unexpected error, closing socket connection and attempting reconnect
java.net.ConnectException: Connection refused
at sun.nio.ch.SocketChannelImpl.checkConnect(Native Method)
at sun.nio.ch.SocketChannelImpl.finishConnect(SocketChannelImpl.java:739)
at org.apache.zookeeper.ClientCnxnSocketNIO.doTransport(ClientCnxnSocketNIO.java:350)
at org.apache.zookeeper.ClientCnxn$SendThread.run(ClientCnxn.java:1068)
```
This patch fixes this by using a `finally` block.
Author: Josh Rosen <joshrosen@databricks.com>
Closes#9864 from JoshRosen/close-zookeeper-client-in-tests.
This patch reduces some RPC timeouts in order to speed up the slow "AkkaUtilsSuite.remote fetch ssl on - untrusted server", which used to take two minutes to run.
Author: Josh Rosen <joshrosen@databricks.com>
Closes#9869 from JoshRosen/SPARK-11650.
To make sure that all lineage is correctly truncated for TrackStateRDD when checkpointed.
Author: Tathagata Das <tathagata.das1565@gmail.com>
Closes#9831 from tdas/SPARK-11845.
SparkListenerSuite's _"onTaskGettingResult() called when result fetched remotely"_ test was extremely slow (1 to 4 minutes to run) and recently became extremely flaky, frequently failing with OutOfMemoryError.
The root cause was the fact that this was using `System.setProperty` to set the Akka frame size, which was not actually modifying the frame size. As a result, this test would allocate much more data than necessary. The fix here is to simply use SparkConf in order to configure the frame size.
Author: Josh Rosen <joshrosen@databricks.com>
Closes#9822 from JoshRosen/SPARK-11649.
[SPARK-6028](https://issues.apache.org/jira/browse/SPARK-6028) uses network module to implement RPC. However, there are some configurations named with `spark.shuffle` prefix in the network module.
This PR refactors them to make sure the user can control them in shuffle and RPC separately. The user can use `spark.rpc.*` to set the configuration for netty RPC.
Author: Shixiong Zhu <shixiong@databricks.com>
Closes#9481 from zsxwing/SPARK-10745.
https://issues.apache.org/jira/browse/SPARK-11792
The main changes include:
* Renaming `SizeEstimation` to `KnownSizeEstimation`. Hopefully this new name has more information.
* Making `estimatedSize` return `Long` instead of `Option[Long]`.
* In `UnsaveHashedRelation`, `estimatedSize` will delegate the work to `SizeEstimator` if we have not created a `BytesToBytesMap`.
Since we will put `UnsaveHashedRelation` to `BlockManager`, it is generally good to let it provide a more accurate size estimation. Also, if we do not put `BytesToBytesMap` directly into `BlockerManager`, I feel it is not really necessary to make `BytesToBytesMap` extends `KnownSizeEstimation`.
Author: Yin Huai <yhuai@databricks.com>
Closes#9813 from yhuai/SPARK-11792-followup.
Make sure we are using the context classloader when deserializing failed TaskResults instead of the Spark classloader.
The issue is that `enqueueFailedTask` was using the incorrect classloader which results in `ClassNotFoundException`.
Adds a test in TaskResultGetterSuite that compiles a custom exception, throws it on the executor, and asserts that Spark handles the TaskResult deserialization instead of returning `UnknownReason`.
See #9367 for previous comments
See SPARK-11195 for a full repro
Author: Hurshal Patel <hpatel516@gmail.com>
Closes#9779 from choochootrain/spark-11195-master.
This PR upgrade the version of RoaringBitmap to 0.5.10, to optimize the memory layout, will be much smaller when most of blocks are empty.
This PR is based on #9661 (fix conflicts), see all of the comments at https://github.com/apache/spark/pull/9661 .
Author: Kent Yao <yaooqinn@hotmail.com>
Author: Davies Liu <davies@databricks.com>
Author: Charles Allen <charles@allen-net.com>
Closes#9746 from davies/roaring_mapstatus.
By using the dynamic allocation, sometimes it occurs false killing for those busy executors. Some executors with assignments will be killed because of being idle for enough time (say 60 seconds). The root cause is that the Task-Launch listener event is asynchronized.
For example, some executors are under assigning tasks, but not sending out the listener notification yet. Meanwhile, the dynamic allocation's executor idle time is up (e.g., 60 seconds). It will trigger killExecutor event at the same time.
1. the timer expiration starts before the listener event arrives.
2. Then, the task is going to run on top of that killed/killing executor. It will lead to task failure finally.
Here is the proposal to fix it. We can add the force control for killExecutor. If the force control is not set (i.e., false), we'd better to check if the executor under killing is idle or busy. If the current executor has some assignment, we should not kill that executor and return back false (to indicate killing failure). In dynamic allocation, we'd better to turn off force killing (i.e., force = false), we will meet killing failure if tries to kill a busy executor. And then, the executor timer won't be invalid. Later on, the task assignment event arrives, we can remove the idle timer accordingly. So that we can avoid false killing for those busy executors in dynamic allocation.
For the rest of usages, the end users can decide if to use force killing or not by themselves. If to turn on that option, the killExecutor will do the action without any status checking.
Author: Grace <jie.huang@intel.com>
Author: Andrew Or <andrew@databricks.com>
Author: Jie Huang <jie.huang@intel.com>
Closes#7888 from GraceH/forcekill.
The basic idea is that:
The archive of the SparkR package itself, that is sparkr.zip, is created during build process and is contained in the Spark binary distribution. No change to it after the distribution is installed as the directory it resides ($SPARK_HOME/R/lib) may not be writable.
When there is R source code contained in jars or Spark packages specified with "--jars" or "--packages" command line option, a temporary directory is created by calling Utils.createTempDir() where the R packages built from the R source code will be installed. The temporary directory is writable, and won't interfere with each other when there are multiple SparkR sessions, and will be deleted when this SparkR session ends. The R binary packages installed in the temporary directory then are packed into an archive named rpkg.zip.
sparkr.zip and rpkg.zip are distributed to the cluster in YARN modes.
The distribution of rpkg.zip in Standalone modes is not supported in this PR, and will be address in another PR.
Various R files are updated to accept multiple lib paths (one is for SparkR package, the other is for other R packages) so that these package can be accessed in R.
Author: Sun Rui <rui.sun@intel.com>
Closes#9390 from sun-rui/SPARK-10500.
Currently, all the shuffle writer will write to target path directly, the file could be corrupted by other attempt of the same partition on the same executor. They should write to temporary file then rename to target path, as what we do in output committer. In order to make the rename atomic, the temporary file should be created in the same local directory (FileSystem).
This PR is based on #9214 , thanks to squito . Closes#9214
Author: Davies Liu <davies@databricks.com>
Closes#9610 from davies/safe_shuffle.
This patch aims to reduce the test time and flakiness of HiveSparkSubmitSuite, SparkSubmitSuite, and CliSuite.
Key changes:
- Disable IO synchronization calls for Derby writes, since durability doesn't matter for tests. This was done for HiveCompatibilitySuite in #6651 and resulted in huge test speedups.
- Add a few missing `--conf`s to disable various Spark UIs. The CliSuite, in particular, never disabled these UIs, leaving it prone to port-contention-related flakiness.
- Fix two instances where tests defined `beforeAll()` methods which were never called because the appropriate traits were not mixed in. I updated these tests suites to extend `BeforeAndAfterEach` so that they play nicely with our `ResetSystemProperties` trait.
Author: Josh Rosen <joshrosen@databricks.com>
Closes#9623 from JoshRosen/SPARK-11647.
just trying to increase test coverage in the scheduler, this already works. It includes a regression test for SPARK-9809
copied some test utils from https://github.com/apache/spark/pull/5636, we can wait till that is merged first
Author: Imran Rashid <irashid@cloudera.com>
Closes#8402 from squito/test_retry_in_shared_shuffle_dep.
Changed AppClient to be non-blocking in `receiveAndReply` by using a separate thread to wait for response and reply to the context. The threads are managed by a thread pool. Also added unit tests for the AppClient interface.
Author: Bryan Cutler <bjcutler@us.ibm.com>
Closes#9317 from BryanCutler/appClient-receiveAndReply-SPARK-10827.
In order to lay the groundwork for proper off-heap memory support in SQL / Tungsten, we need to extend our MemoryManager to perform bookkeeping for off-heap memory.
## User-facing changes
This PR introduces a new configuration, `spark.memory.offHeapSize` (name subject to change), which specifies the absolute amount of off-heap memory that Spark and Spark SQL can use. If Tungsten is configured to use off-heap execution memory for allocating data pages, then all data page allocations must fit within this size limit.
## Internals changes
This PR contains a lot of internal refactoring of the MemoryManager. The key change at the heart of this patch is the introduction of a `MemoryPool` class (name subject to change) to manage the bookkeeping for a particular category of memory (storage, on-heap execution, and off-heap execution). These MemoryPools are not fixed-size; they can be dynamically grown and shrunk according to the MemoryManager's policies. In StaticMemoryManager, these pools have fixed sizes, proportional to the legacy `[storage|shuffle].memoryFraction`. In the new UnifiedMemoryManager, the sizes of these pools are dynamically adjusted according to its policies.
There are two subclasses of `MemoryPool`: `StorageMemoryPool` manages storage memory and `ExecutionMemoryPool` manages execution memory. The MemoryManager creates two execution pools, one for on-heap memory and one for off-heap. Instances of `ExecutionMemoryPool` manage the logic for fair sharing of their pooled memory across running tasks (in other words, the ShuffleMemoryManager-like logic has been moved out of MemoryManager and pushed into these ExecutionMemoryPool instances).
I think that this design is substantially easier to understand and reason about than the previous design, where most of these responsibilities were handled by MemoryManager and its subclasses. To see this, take at look at how simple the logic in `UnifiedMemoryManager` has become: it's now very easy to see when memory is dynamically shifted between storage and execution.
## TODOs
- [x] Fix handful of test failures in the MemoryManagerSuites.
- [x] Fix remaining TODO comments in code.
- [ ] Document new configuration.
- [x] Fix commented-out tests / asserts:
- [x] UnifiedMemoryManagerSuite.
- [x] Write tests that exercise the new off-heap memory management policies.
Author: Josh Rosen <joshrosen@databricks.com>
Closes#9344 from JoshRosen/offheap-memory-accounting.
https://issues.apache.org/jira/browse/SPARK-10116
This is really trivial, just happened to notice it -- if `XORShiftRandom.hashSeed` is really supposed to have random bits throughout (as the comment implies), it needs to do something for the conversion to `long`.
mengxr mkolod
Author: Imran Rashid <irashid@cloudera.com>
Closes#8314 from squito/SPARK-10116.
This brings the support of off-heap memory for array inside BytesToBytesMap and InMemorySorter, then we could allocate all the memory from off-heap for execution.
Closes#8068
Author: Davies Liu <davies@databricks.com>
Closes#9477 from davies/unsafe_timsort.
OutputCommitCoordinator uses a map in a place where an array would suffice, increasing its memory consumption for result stages with millions of tasks.
This patch replaces that map with an array. The only tricky part of this is reasoning about the range of possible array indexes in order to make sure that we never index out of bounds.
Author: Josh Rosen <joshrosen@databricks.com>
Closes#9274 from JoshRosen/SPARK-11307.
This is an updated version of #8995 by a-roberts. Original description follows:
Snappy now supports concatenation of serialized streams, this patch contains a version number change and the "does not support" test is now a "supports" test.
Snappy 1.1.2 changelog mentions:
> snappy-java-1.1.2 (22 September 2015)
> This is a backward compatible release for 1.1.x.
> Add AIX (32-bit) support.
> There is no upgrade for the native libraries of the other platforms.
> A major change since 1.1.1 is a support for reading concatenated results of SnappyOutputStream(s)
> snappy-java-1.1.2-RC2 (18 May 2015)
> Fix#107: SnappyOutputStream.close() is not idempotent
> snappy-java-1.1.2-RC1 (13 May 2015)
> SnappyInputStream now supports reading concatenated compressed results of SnappyOutputStream
> There has been no compressed format change since 1.0.5.x. So You can read the compressed results > interchangeablly between these versions.
> Fixes a problem when java.io.tmpdir does not exist.
Closes#8995.
Author: Adam Roberts <aroberts@uk.ibm.com>
Author: Josh Rosen <joshrosen@databricks.com>
Closes#9439 from JoshRosen/update-snappy.
In YARN mode, when preemption is enabled, we may leave executors in a
zombie state while we wait to retrieve the reason for which the executor
exited. This is so that we don't account for failed tasks that were
running on a preempted executor.
The issue is that while we wait for this information, the scheduler
might decide to schedule tasks on the executor, which will never be
able to run them. Other side effects include the block manager still
considering the executor available to cache blocks, for example.
So, when we know that an executor went down but we don't know why,
stop everything related to the executor, except its running tasks.
Only when we know the reason for the exit (or give up waiting for
it) we do update the running tasks.
This is achieved by a new `disableExecutor()` method in the
`Schedulable` interface. For managers that do not behave like this
(i.e. every one but YARN), the existing `executorLost()` method
will behave the same way it did before.
On top of that change, a few minor changes that made debugging easier,
and fixed some other minor issues:
- The cluster-mode AM was printing a misleading log message every
time an executor disconnected from the driver (because the akka
actor system was shared between driver and AM).
- Avoid sending unnecessary requests for an executor's exit reason
when we already know it was explicitly disabled / killed. This
avoids both multiple requests, and unnecessary requests that would
just cause warning messages on the AM (in the explicit kill case).
- Tone down a log message about the executor being lost when it
exited normally (e.g. preemption)
- Wake up the AM monitor thread when requests for executor loss
reasons arrive too, so that we can more quickly remove executors
from this zombie state.
Author: Marcelo Vanzin <vanzin@cloudera.com>
Closes#8887 from vanzin/SPARK-10622.
The test functionality should be the same, but without using mockito; logs don't
really say anything useful but I suspect it may be the cause of the flakiness,
since updating mocks when multiple threads may be using it doesn't work very
well. It also allows some other cleanup (= less test code in FsHistoryProvider).
Author: Marcelo Vanzin <vanzin@cloudera.com>
Closes#9425 from vanzin/SPARK-11466.
DriverDescription refactored to case class because it included no mutable fields.
ApplicationDescription had one mutable field, which was appUiUrl. This field was set by the driver to point to the driver web UI. Master was modifying this field when the application was removed to redirect requests to history server. This was wrong because objects which are sent over the wire should be immutable. Now appUiUrl is immutable in ApplicationDescription and always points to the driver UI even if it is already shutdown. The UI url which master exposes to the user and modifies dynamically is now included into ApplicationInfo - a data object which describes the application state internally in master. That URL in ApplicationInfo is initialised with the value from ApplicationDescription.
ApplicationDescription also included value user, which is now a part of case class fields.
Author: Jacek Lewandowski <lewandowski.jacek@gmail.com>
Closes#9299 from jacek-lewandowski/SPARK-11344.
"Client mode" means the RPC env will not listen for incoming connections.
This allows certain processes in the Spark stack (such as Executors or
tha YARN client-mode AM) to act as pure clients when using the netty-based
RPC backend, reducing the number of sockets needed by the app and also the
number of open ports.
Client connections are also preferred when endpoints that actually have
a listening socket are involved; so, for example, if a Worker connects
to a Master and the Master needs to send a message to a Worker endpoint,
that client connection will be used, even though the Worker is also
listening for incoming connections.
With this change, the workaround for SPARK-10987 isn't necessary anymore, and
is removed. The AM connects to the driver in "client mode", and that connection
is used for all driver <-> AM communication, and so the AM is properly notified
when the connection goes down.
Author: Marcelo Vanzin <vanzin@cloudera.com>
Closes#9210 from vanzin/SPARK-10997.
JIRA: https://issues.apache.org/jira/browse/SPARK-11271
As reported in the JIRA ticket, when there are too many tasks, the memory usage of MapStatus will cause problem. Use BitSet instead of RoaringBitMap should be more efficient in memory usage.
Author: Liang-Chi Hsieh <viirya@appier.com>
Closes#9243 from viirya/mapstatus-bitset.
Use standard JDK APIs for that (with a little help from Guava). Most of the
changes here are in test code, since there were no tests specific to that
part of the code.
Author: Marcelo Vanzin <vanzin@cloudera.com>
Closes#9257 from vanzin/SPARK-11073.
Large HDFS clusters may take a while to leave safe mode when starting; this change
makes the HS wait for that before doing checks about its configuraton. This means
the HS won't stop right away if HDFS is in safe mode and the configuration is not
correct, but that should be a very uncommon situation.
Author: Marcelo Vanzin <vanzin@cloudera.com>
Closes#9043 from vanzin/SPARK-11020.
[SPARK-11338: HistoryPage not multi-tenancy enabled ...](https://issues.apache.org/jira/browse/SPARK-11338)
- `HistoryPage.scala` ...prepending all page links with the web proxy (`uiRoot`) path
- `HistoryServerSuite.scala` ...adding a test case to verify all site-relative links are prefixed when the environment variable `APPLICATION_WEB_PROXY_BASE` (or System property `spark.ui.proxyBase`) is set
Author: Christian Kadner <ckadner@us.ibm.com>
Closes#9291 from ckadner/SPARK-11338 and squashes the following commits:
01d2f35 [Christian Kadner] [SPARK-11338][WebUI] nit fixes
d054bd7 [Christian Kadner] [SPARK-11338][WebUI] prependBaseUri in method makePageLink
8bcb3dc [Christian Kadner] [SPARK-11338][WebUI] Prepend application links on HistoryPage with uiRoot path
Since we do not need to preserve a page before calling compute(), MapPartitionsWithPreparationRDD is not needed anymore.
This PR basically revert #8543, #8511, #8038, #8011
Author: Davies Liu <davies@databricks.com>
Closes#9381 from davies/remove_prepare2.
This PR introduce a mechanism to call spill() on those SQL operators that support spilling (for example, BytesToBytesMap, UnsafeExternalSorter and ShuffleExternalSorter) if there is not enough memory for execution. The preserved first page is needed anymore, so removed.
Other Spillable objects in Spark core (ExternalSorter and AppendOnlyMap) are not included in this PR, but those could benefit from this (trigger others' spilling).
The PrepareRDD may be not needed anymore, could be removed in follow up PR.
The following script will fail with OOM before this PR, finished in 150 seconds with 2G heap (also works in 1.5 branch, with similar duration).
```python
sqlContext.setConf("spark.sql.shuffle.partitions", "1")
df = sqlContext.range(1<<25).selectExpr("id", "repeat(id, 2) as s")
df2 = df.select(df.id.alias('id2'), df.s.alias('s2'))
j = df.join(df2, df.id==df2.id2).groupBy(df.id).max("id", "id2")
j.explain()
print j.count()
```
For thread-safety, here what I'm got:
1) Without calling spill(), the operators should only be used by single thread, no safety problems.
2) spill() could be triggered in two cases, triggered by itself, or by other operators. we can check trigger == this in spill(), so it's still in the same thread, so safety problems.
3) if it's triggered by other operators (right now cache will not trigger spill()), we only spill the data into disk when it's in scanning stage (building is finished), so the in-memory sorter or memory pages are read-only, we only need to synchronize the iterator and change it.
4) During scanning, the iterator will only use one record in one page, we can't free this page, because the downstream is currently using it (used by UnsafeRow or other objects). In BytesToBytesMap, we just skip the current page, and dump all others into disk. In UnsafeExternalSorter, we keep the page that is used by current record (having the same baseObject), free it when loading the next record. In ShuffleExternalSorter, the spill() will not trigger during scanning.
5) In order to avoid deadlock, we didn't call acquireMemory during spill (so we reused the pointer array in InMemorySorter).
Author: Davies Liu <davies@databricks.com>
Closes#9241 from davies/force_spill.
Commit af3bc59d1f introduced new
functionality so that if an executor dies for a reason that's not
caused by one of the tasks running on the executor (e.g., due to
pre-emption), Spark doesn't count the failure towards the maximum
number of failures for the task. That commit introduced some vague
naming that this commit attempts to fix; in particular:
(1) The variable "isNormalExit", which was used to refer to cases where
the executor died for a reason unrelated to the tasks running on the
machine, has been renamed (and reversed) to "exitCausedByApp". The problem
with the existing name is that it's not clear (at least to me!) what it
means for an exit to be "normal"; the new name is intended to make the
purpose of this variable more clear.
(2) The variable "shouldEventuallyFailJob" has been renamed to
"countTowardsTaskFailures". This variable is used to determine whether
a task's failure should be counted towards the maximum number of failures
allowed for a task before the associated Stage is aborted. The problem
with the existing name is that it can be confused with implying that
the task's failure should immediately cause the stage to fail because it
is somehow fatal (this is the case for a fetch failure, for example: if
a task fails because of a fetch failure, there's no point in retrying,
and the whole stage should be failed).
Author: Kay Ousterhout <kayousterhout@gmail.com>
Closes#9164 from kayousterhout/SPARK-11178.
… ReceiverTracker and ReceiverSchedulingPolicy to use it
This PR includes the following changes:
1. Add a new preferred location format, `executor_<host>_<executorID>` (e.g., "executor_localhost_2"), to support specifying the executor locations for RDD.
2. Use the new preferred location format in `ReceiverTracker` to optimize the starting time of Receivers when there are multiple executors in a host.
The goal of this PR is to enable the streaming scheduler to place receivers (which run as tasks) in specific executors. Basically, I want to have more control on the placement of the receivers such that they are evenly distributed among the executors. We tried to do this without changing the core scheduling logic. But it does not allow specifying particular executor as preferred location, only at the host level. So if there are two executors in the same host, and I want two receivers to run on them (one on each executor), I cannot specify that. Current code only specifies the host as preference, which may end up launching both receivers on the same executor. We try to work around it but restarting a receiver when it does not launch in the desired executor and hope that next time it will be started in the right one. But that cause lots of restarts, and delays in correctly launching the receiver.
So this change, would allow the streaming scheduler to specify the exact executor as the preferred location. Also this is not exposed to the user, only the streaming scheduler uses this.
Author: zsxwing <zsxwing@gmail.com>
Closes#9181 from zsxwing/executor-location.
This patch refactors the MemoryManager class structure. After #9000, Spark had the following classes:
- MemoryManager
- StaticMemoryManager
- ExecutorMemoryManager
- TaskMemoryManager
- ShuffleMemoryManager
This is fairly confusing. To simplify things, this patch consolidates several of these classes:
- ShuffleMemoryManager and ExecutorMemoryManager were merged into MemoryManager.
- TaskMemoryManager is moved into Spark Core.
**Key changes and tasks**:
- [x] Merge ExecutorMemoryManager into MemoryManager.
- [x] Move pooling logic into Allocator.
- [x] Move TaskMemoryManager from `spark-unsafe` to `spark-core`.
- [x] Refactor the existing Tungsten TaskMemoryManager interactions so Tungsten code use only this and not both this and ShuffleMemoryManager.
- [x] Refactor non-Tungsten code to use the TaskMemoryManager instead of ShuffleMemoryManager.
- [x] Merge ShuffleMemoryManager into MemoryManager.
- [x] Move code
- [x] ~~Simplify 1/n calculation.~~ **Will defer to followup, since this needs more work.**
- [x] Port ShuffleMemoryManagerSuite tests.
- [x] Move classes from `unsafe` package to `memory` package.
- [ ] Figure out how to handle the hacky use of the memory managers in HashedRelation's broadcast variable construction.
- [x] Test porting and cleanup: several tests relied on mock functionality (such as `TestShuffleMemoryManager.markAsOutOfMemory`) which has been changed or broken during the memory manager consolidation
- [x] AbstractBytesToBytesMapSuite
- [x] UnsafeExternalSorterSuite
- [x] UnsafeFixedWidthAggregationMapSuite
- [x] UnsafeKVExternalSorterSuite
**Compatiblity notes**:
- This patch introduces breaking changes in `ExternalAppendOnlyMap`, which is marked as `DevloperAPI` (likely for legacy reasons): this class now cannot be used outside of a task.
Author: Josh Rosen <joshrosen@databricks.com>
Closes#9127 from JoshRosen/SPARK-10984.
This test can take a little while to finish on slow / loaded machines.
Author: Marcelo Vanzin <vanzin@cloudera.com>
Closes#9235 from vanzin/SPARK-11134.
```
// My machine only has 8 cores
$ bin/spark-shell --master local[32]
scala> val df = sc.parallelize(Seq((1, 1), (2, 2))).toDF("a", "b")
scala> df.as("x").join(df.as("y"), $"x.a" === $"y.a").count()
Caused by: java.io.IOException: Unable to acquire 2097152 bytes of memory
at org.apache.spark.util.collection.unsafe.sort.UnsafeExternalSorter.acquireNewPage(UnsafeExternalSorter.java:351)
```
Author: Andrew Or <andrew@databricks.com>
Closes#9209 from andrewor14/fix-local-page-size.
There's a lot of duplication between SortShuffleManager and UnsafeShuffleManager. Given that these now provide the same set of functionality, now that UnsafeShuffleManager supports large records, I think that we should replace SortShuffleManager's serialized shuffle implementation with UnsafeShuffleManager's and should merge the two managers together.
Author: Josh Rosen <joshrosen@databricks.com>
Closes#8829 from JoshRosen/consolidate-sort-shuffle-implementations.
Correct the logic to return `HDFSCacheTaskLocation` instance when the input `str` is a in memory location.
Author: zhichao.li <zhichao.li@intel.com>
Closes#9096 from zhichao-li/uselessBranch.
JIRA: https://issues.apache.org/jira/browse/SPARK-11051
When a `RDD` is materialized and checkpointed, its partitions and dependencies are cleared. If we allow local checkpointing on it and assign `LocalRDDCheckpointData` to its `checkpointData`. Next time when the RDD is materialized again, the error will be thrown.
Author: Liang-Chi Hsieh <viirya@appier.com>
Closes#9072 from viirya/no-localcheckpoint-after-checkpoint.
Because the registration RPC was not really an RPC, but a bunch of
disconnected messages, it was possible for other messages to be
sent before the reply to the registration arrived, and that would
confuse the Worker. Especially in local-cluster mode, the worker was
succeptible to receiving an executor request before it received a
message from the master saying registration succeeded.
On top of the above, the change also fixes a ClassCastException when
the registration fails, which also affects the executor registration
protocol. Because the `ask` is issued with a specific return type,
if the error message (of a different type) was returned instead, the
code would just die with an exception. This is fixed by having a common
base trait for these reply messages.
Author: Marcelo Vanzin <vanzin@cloudera.com>
Closes#9138 from vanzin/SPARK-11131.
#9084 uncovered that many tests that test spilling don't actually spill. This is a follow-up patch to fix that to ensure our unit tests actually catch potential bugs in spilling. The size of this patch is inflated by the refactoring of `ExternalSorterSuite`, which had a lot of duplicate code and logic.
Author: Andrew Or <andrew@databricks.com>
Closes#9124 from andrewor14/spilling-tests.
If the heartbeat receiver kills executors (and new ones are not registered to replace them), the idle timeout for the old executors will be lost (and then change a total number of executors requested by Driver), So new ones will be not to asked to replace them.
For example, executorsPendingToRemove=Set(1), and executor 2 is idle timeout before a new executor is asked to replace executor 1. Then driver kill executor 2, and sending RequestExecutors to AM. But executorsPendingToRemove=Set(1,2), So AM doesn't allocate a executor to replace 1.
see: https://github.com/apache/spark/pull/8668
Author: KaiXinXiaoLei <huleilei1@huawei.com>
Author: huleilei <huleilei1@huawei.com>
Closes#8945 from KaiXinXiaoLei/pendingexecutor.
Internal accumulators don't write the internal flag to event log. So on the history server Web UI, all accumulators are not internal. This causes incorrect peak execution memory and unwanted accumulator table displayed on the stage page.
To fix it, I add the "internal" property of AccumulableInfo when writing the event log.
Author: Carson Wang <carson.wang@intel.com>
Closes#9061 from carsonwang/accumulableBug.
Restrict tasks (of job) to only 1 to ensure that the causing Exception asserted for job failure is the deliberately thrown DAGSchedulerSuiteDummyException intended, not an UnsupportedOperationException from any second/subsequent tasks that can propagate from a race condition during code execution.
Author: shellberg <sah@zepler.org>
Closes#9076 from shellberg/shellberg-DAGSchedulerSuite-misbehavedResultHandlerTest-patch-1.
A few more changes:
1. Renamed IDVerifier -> RpcEndpointVerifier
2. Renamed NettyRpcAddress -> RpcEndpointAddress
3. Simplified NettyRpcHandler a bit by removing the connection count tracking. This is OK because I now force spark.shuffle.io.numConnectionsPerPeer to 1
4. Reduced spark.rpc.connect.threads to 64. It would be great to eventually remove this extra thread pool.
5. Minor cleanup & documentation.
Author: Reynold Xin <rxin@databricks.com>
Closes#9112 from rxin/SPARK-11096.
This patch unifies the memory management of the storage and execution regions such that either side can borrow memory from each other. When memory pressure arises, storage will be evicted in favor of execution. To avoid regressions in cases where storage is crucial, we dynamically allocate a fraction of space for storage that execution cannot evict. Several configurations are introduced:
- **spark.memory.fraction (default 0.75)**: fraction of the heap space used for execution and storage. The lower this is, the more frequently spills and cached data eviction occur. The purpose of this config is to set aside memory for internal metadata, user data structures, and imprecise size estimation in the case of sparse, unusually large records.
- **spark.memory.storageFraction (default 0.5)**: size of the storage region within the space set aside by `spark.memory.fraction`. Cached data may only be evicted if total storage exceeds this region.
- **spark.memory.useLegacyMode (default false)**: whether to use the memory management that existed in Spark 1.5 and before. This is mainly for backward compatibility.
For a detailed description of the design, see [SPARK-10000](https://issues.apache.org/jira/browse/SPARK-10000). This patch builds on top of the `MemoryManager` interface introduced in #9000.
Author: Andrew Or <andrew@databricks.com>
Closes#9084 from andrewor14/unified-memory-manager.
I'm going through the implementation right now for post-doc review. Adding more comments and renaming things as I go through them.
I also want to write higher level documentation about how the whole thing works -- but those will come in other pull requests.
Author: Reynold Xin <rxin@databricks.com>
Closes#9091 from rxin/rpc-review.
https://issues.apache.org/jira/browse/SPARK-10858
The issue here is that in resolveURI we default to calling new File(path).getAbsoluteFile().toURI(). But if the path passed in already has a # in it then File(path) will think that is supposed to be part of the actual file path and not a fragment so it changes # to %23. Then when we try to parse that later in Client as a URI it doesn't recognize there is a fragment.
so to fix we just check if there is a fragment, still create the File like we did before and then add the fragment back on.
Author: Tom Graves <tgraves@yahoo-inc.com>
Closes#9035 from tgravescs/SPARK-10858.
This change adds an API that encapsulates information about an app
launched using the library. It also creates a socket-based communication
layer for apps that are launched as child processes; the launching
application listens for connections from launched apps, and once
communication is established, the channel can be used to send updates
to the launching app, or to send commands to the child app.
The change also includes hooks for local, standalone/client and yarn
masters.
Author: Marcelo Vanzin <vanzin@cloudera.com>
Closes#7052 from vanzin/SPARK-8673.
This patch introduces a `MemoryManager` that is the central arbiter of how much memory to grant to storage and execution. This patch is primarily concerned only with refactoring while preserving the existing behavior as much as possible.
This is the first step away from the existing rigid separation of storage and execution memory, which has several major drawbacks discussed on the [issue](https://issues.apache.org/jira/browse/SPARK-10956). It is the precursor of a series of patches that will attempt to address those drawbacks.
Author: Andrew Or <andrew@databricks.com>
Author: Josh Rosen <joshrosen@databricks.com>
Author: andrewor14 <andrew@databricks.com>
Closes#9000 from andrewor14/memory-manager.
This PR just reverted 02144d6745 to remerge #6457 and also included the commits in #8905.
Author: zsxwing <zsxwing@gmail.com>
Closes#8944 from zsxwing/SPARK-6028.
Compatibility between history server script and functionality
The history server has its argument parsing class in HistoryServerArguments. However, this doesn't get involved in the start-history-server.sh codepath where the $0 arg is assigned to spark.history.fs.logDirectory and all other arguments discarded (e.g --property-file.)
This stops the other options being usable from this script
Author: Joshi <rekhajoshm@gmail.com>
Author: Rekha Joshi <rekhajoshm@gmail.com>
Closes#8758 from rekhajoshm/SPARK-10317.
Fix the following issues in StandaloneDynamicAllocationSuite:
1. It should not assume master and workers start in order
2. It should not assume master and workers get ready at once
3. It should not assume the application is already registered with master after creating SparkContext
4. It should not access Master.app and idToApp which are not thread safe
The changes includes:
* Use `eventually` to wait until master and workers are ready to fix 1 and 2
* Use `eventually` to wait until the application is registered with master to fix 3
* Use `askWithRetry[MasterStateResponse](RequestMasterState)` to get the application info to fix 4
Author: zsxwing <zsxwing@gmail.com>
Closes#8914 from zsxwing/fix-StandaloneDynamicAllocationSuite.
This makes two changes:
- Allow reduce tasks to fetch multiple map output partitions -- this is a pretty small change to HashShuffleFetcher
- Move shuffle locality computation out of DAGScheduler and into ShuffledRDD / MapOutputTracker; this was needed because the code in DAGScheduler wouldn't work for RDDs that fetch multiple map output partitions from each reduce task
I also added an AdaptiveSchedulingSuite that creates RDDs depending on multiple map output partitions.
Author: Matei Zaharia <matei@databricks.com>
Closes#8844 from mateiz/spark-9852.
The DiskBlockObjectWriter constructor took a BlockId parameter but never used it. As part of some general cleanup in these interfaces, this patch refactors its constructor to eliminate this parameter.
Author: Josh Rosen <joshrosen@databricks.com>
Closes#8871 from JoshRosen/disk-block-object-writer-blockid-cleanup.
The current shuffle code has an interface named ShuffleReader with only one implementation, HashShuffleReader. This naming is confusing, since the same read path code is used for both sort- and hash-based shuffle. This patch addresses this by renaming HashShuffleReader to BlockStoreShuffleReader.
Author: Josh Rosen <joshrosen@databricks.com>
Closes#8825 from JoshRosen/shuffle-reader-cleanup.
The job group, and job descriptions information is passed through thread local properties, and get inherited by child threads. In case of spark streaming, the streaming jobs inherit these properties from the thread that called streamingContext.start(). This may not make sense.
1. Job group: This is mainly used for cancelling a group of jobs together. It does not make sense to cancel streaming jobs like this, as the effect will be unpredictable. And its not a valid usecase any way, to cancel a streaming context, call streamingContext.stop()
2. Job description: This is used to pass on nice text descriptions for jobs to show up in the UI. The job description of the thread that calls streamingContext.start() is not useful for all the streaming jobs, as it does not make sense for all of the streaming jobs to have the same description, and the description may or may not be related to streaming.
The solution in this PR is meant for the Spark master branch, where local properties are inherited by cloning the properties. The job group and job description in the thread that starts the streaming scheduler are explicitly removed, so that all the subsequent child threads does not inherit them. Also, the starting is done in a new child thread, so that setting the job group and description for streaming, does not change those properties in the thread that called streamingContext.start().
Author: Tathagata Das <tathagata.das1565@gmail.com>
Closes#8781 from tdas/SPARK-10649.
Track pending tasks by partition ID instead of Task objects.
Before this change, failure & retry could result in a case where a stage got submitted before the map output from its dependencies get registered. This was due to an error in the condition for registering map outputs.
Author: hushan[胡珊] <hushan@xiaomi.com>
Author: Imran Rashid <irashid@cloudera.com>
Closes#7699 from squito/SPARK-5259.
I noticed only one block manager registered with master in an unsuccessful build (https://amplab.cs.berkeley.edu/jenkins/job/Spark-Master-SBT/AMPLAB_JENKINS_BUILD_PROFILE=hadoop2.2,label=spark-test/3534/)
```
15/09/16 13:02:30.981 pool-1-thread-1-ScalaTest-running-BroadcastSuite INFO SparkContext: Running Spark version 1.6.0-SNAPSHOT
...
15/09/16 13:02:38.133 sparkDriver-akka.actor.default-dispatcher-19 INFO BlockManagerMasterEndpoint: Registering block manager localhost:48196 with 530.3 MB RAM, BlockManagerId(0, localhost, 48196)
```
In addition, the first block manager needed 7+ seconds to start. But the test expected 2 block managers so it failed.
However, there was no exception in this log file. So I checked a successful build (https://amplab.cs.berkeley.edu/jenkins/job/Spark-Master-SBT/3536/AMPLAB_JENKINS_BUILD_PROFILE=hadoop2.2,label=spark-test/) and it needed 4-5 seconds to set up the local cluster:
```
15/09/16 18:11:27.738 sparkWorker1-akka.actor.default-dispatcher-5 INFO Worker: Running Spark version 1.6.0-SNAPSHOT
...
15/09/16 18:11:30.838 sparkDriver-akka.actor.default-dispatcher-20 INFO BlockManagerMasterEndpoint: Registering block manager localhost:54202 with 530.3 MB RAM, BlockManagerId(1, localhost, 54202)
15/09/16 18:11:32.112 sparkDriver-akka.actor.default-dispatcher-20 INFO BlockManagerMasterEndpoint: Registering block manager localhost:32955 with 530.3 MB RAM, BlockManagerId(0, localhost, 32955)
```
In this build, the first block manager needed only 3+ seconds to start.
Comparing these two builds, I guess it's possible that the local cluster in `BroadcastSuite` cannot be ready in 10 seconds if the Jenkins worker is busy. So I just increased the timeout to 60 seconds to see if this can fix the issue.
Author: zsxwing <zsxwing@gmail.com>
Closes#8813 from zsxwing/fix-BroadcastSuite.
It does not make much sense to set `spark.shuffle.spill` or `spark.sql.planner.externalSort` to false: I believe that these configurations were initially added as "escape hatches" to guard against bugs in the external operators, but these operators are now mature and well-tested. In addition, these configurations are not handled in a consistent way anymore: SQL's Tungsten codepath ignores these configurations and will continue to use spilling operators. Similarly, Spark Core's `tungsten-sort` shuffle manager does not respect `spark.shuffle.spill=false`.
This pull request removes these configurations, adds warnings at the appropriate places, and deletes a large amount of code which was only used in code paths that did not support spilling.
Author: Josh Rosen <joshrosen@databricks.com>
Closes#8831 from JoshRosen/remove-ability-to-disable-spilling.
When speculative execution is enabled, consider a scenario where the authorized committer of a particular output partition fails during the OutputCommitter.commitTask() call. In this case, the OutputCommitCoordinator is supposed to release that committer's exclusive lock on committing once that task fails. However, due to a unit mismatch (we used task attempt number in one place and task attempt id in another) the lock will not be released, causing Spark to go into an infinite retry loop.
This bug was masked by the fact that the OutputCommitCoordinator does not have enough end-to-end tests (the current tests use many mocks). Other factors contributing to this bug are the fact that we have many similarly-named identifiers that have different semantics but the same data types (e.g. attemptNumber and taskAttemptId, with inconsistent variable naming which makes them difficult to distinguish).
This patch adds a regression test and fixes this bug by always using task attempt numbers throughout this code.
Author: Josh Rosen <joshrosen@databricks.com>
Closes#8544 from JoshRosen/SPARK-10381.
*Note: this is for master branch only.* The fix for branch-1.5 is at #8721.
The query execution ID is currently passed from a thread to its children, which is not the intended behavior. This led to `IllegalArgumentException: spark.sql.execution.id is already set` when running queries in parallel, e.g.:
```
(1 to 100).par.foreach { _ =>
sc.parallelize(1 to 5).map { i => (i, i) }.toDF("a", "b").count()
}
```
The cause is `SparkContext`'s local properties are inherited by default. This patch adds a way to exclude keys we don't want to be inherited, and makes SQL go through that code path.
Author: Andrew Or <andrew@databricks.com>
Closes#8710 from andrewor14/concurrent-sql-executions.
This patch adds support for submitting map stages in a DAG individually so that we can make downstream decisions after seeing statistics about their output, as part of SPARK-9850. I also added more comments to many of the key classes in DAGScheduler. By itself, the patch is not super useful except maybe to switch between a shuffle and broadcast join, but with the other subtasks of SPARK-9850 we'll be able to do more interesting decisions.
The main entry point is SparkContext.submitMapStage, which lets you run a map stage and see stats about the map output sizes. Other stats could also be collected through accumulators. See AdaptiveSchedulingSuite for a short example.
Author: Matei Zaharia <matei@databricks.com>
Closes#8180 from mateiz/spark-9851.
This is a follow-up patch to #8723. I missed one case there.
Author: Andrew Or <andrew@databricks.com>
Closes#8727 from andrewor14/fix-threading-suite.
This is a followup to #8499 which adds a Scalastyle rule to mandate the use of SparkHadoopUtil's JobContext accessor methods and fixes the existing violations.
Author: Josh Rosen <joshrosen@databricks.com>
Closes#8521 from JoshRosen/SPARK-10330-part2.
Fix a few Java API test style issues: unused generic types, exceptions, wrong assert argument order
Author: Sean Owen <sowen@cloudera.com>
Closes#8706 from srowen/SPARK-10547.
This commit ensures if an assertion fails within a thread, it will ultimately fail the test. Otherwise we end up potentially masking real bugs by not propagating assertion failures properly.
Author: Andrew Or <andrew@databricks.com>
Closes#8723 from andrewor14/fix-threading-suite.
ShuffleManager implementations are currently not given type information for
the key, value and combiner classes. Serialization of shuffle objects relies
on objects being JavaSerializable, with methods defined for reading/writing
the object or, alternatively, serialization via Kryo which uses reflection.
Serialization systems like Avro, Thrift and Protobuf generate classes with
zero argument constructors and explicit schema information
(e.g. IndexedRecords in Avro have get, put and getSchema methods).
By serializing the key, value and combiner class names in ShuffleDependency,
shuffle implementations will have access to schema information when
registerShuffle() is called.
Author: Matt Massie <massie@cs.berkeley.edu>
Closes#7403 from massie/shuffle-classtags.
This is a regression introduced in #4960, this commit fixes it and adds a test.
tnachen andrewor14 please review, this should be an easy one.
Author: Iulian Dragos <jaguarul@gmail.com>
Closes#8653 from dragos/issue/mesos/fine-grained-maxExecutorCores.
The architecture is that, in YARN mode, if the driver detects that an executor has disconnected, it asks the ApplicationMaster why the executor died. If the ApplicationMaster is aware that the executor died because of preemption, all tasks associated with that executor are not marked as failed. The executor
is still removed from the driver's list of available executors, however.
There's a few open questions:
1. Should standalone mode have a similar "get executor loss reason" as well? I localized this change as much as possible to affect only YARN, but there could be a valid case to differentiate executor losses in standalone mode as well.
2. I make a pretty strong assumption in YarnAllocator that getExecutorLossReason(executorId) will only be called once per executor id; I do this so that I can remove the metadata from the in-memory map to avoid object accumulation. It's not clear if I'm being overly zealous to save space, however.
cc vanzin specifically for review because it collided with some earlier YARN scheduling work.
cc JoshRosen because it's similar to output commit coordination we did in the past
cc andrewor14 for our discussion on how to get executor exit codes and loss reasons
Author: mcheah <mcheah@palantir.com>
Closes#8007 from mccheah/feature/preemption-handling.
We introduced the Netty network module for shuffle in Spark 1.2, and has turned it on by default for 3 releases. The old ConnectionManager is difficult to maintain. If we merge the patch now, by the time it is released, it would be 1 yr for which ConnectionManager is off by default. It's time to remove it.
Author: Reynold Xin <rxin@databricks.com>
Closes#8161 from rxin/SPARK-9767.
[SPARK-9591](https://issues.apache.org/jira/browse/SPARK-9591)
When we getting the broadcast variable, we can fetch the block form several location,but now when connecting the lost blockmanager(idle for enough time removed by driver when using dynamic resource allocate and so on) will cause task fail,and the worse case will cause the job fail.
Author: jeanlyn <jeanlyn92@gmail.com>
Closes#7927 from jeanlyn/catch_exception.
This contribution is my original work and I license the work to the project under the project's open source license.
Author: Pat Shields <yeoldefortran@gmail.com>
Closes#7979 from pashields/env-loading-on-driver.
This is pretty minor, just trying to improve the readability of `DAGSchedulerSuite`, I figure every bit helps. Before whenever I read this test, I never knew what "should work" and "should be ignored" really meant -- this adds some asserts & updates comments to make it more clear. Also some reformatting per a suggestion from markhamstra on https://github.com/apache/spark/pull/7699
Author: Imran Rashid <irashid@cloudera.com>
Closes#8434 from squito/SPARK-10247.
The ```Stage``` class now tracks whether there were a sufficient number of consecutive failures of that stage to trigger an abort.
To avoid an infinite loop of stage retries, we abort the job completely after 4 consecutive stage failures for one stage. We still allow more than 4 consecutive stage failures if there is an intervening successful attempt for the stage, so that in very long-lived applications, where a stage may get reused many times, we don't abort the job after failures that have been recovered from successfully.
I've added test cases to exercise the most obvious scenarios.
Author: Ilya Ganelin <ilya.ganelin@capitalone.com>
Closes#5636 from ilganeli/SPARK-5945.
SPARK-4223.
Currently we support setting view and modify acls but you have to specify a list of users. It would be nice to support * meaning all users have access.
Manual tests to verify that: "*" works for any user in:
a. Spark ui: view and kill stage. Done.
b. Spark history server. Done.
c. Yarn application killing. Done.
Author: zhuol <zhuol@yahoo-inc.com>
Closes#8398 from zhuoliu/4223.
In SMJ, the first ExternalSorter could consume all the memory before spilling, then the second can not even acquire the first page.
Before we have a better memory allocator, SMJ should call prepare() before call any compute() of it's children.
cc rxin JoshRosen
Author: Davies Liu <davies@databricks.com>
Closes#8511 from davies/smj_memory.
This change aims at speeding up the dev cycle a little bit, by making
sure that all tests behave the same w.r.t. where the code to be tested
is loaded from. Namely, that means that tests don't rely on the assembly
anymore, rather loading all needed classes from the build directories.
The main change is to make sure all build directories (classes and test-classes)
are added to the classpath of child processes when running tests.
YarnClusterSuite required some custom code since the executors are run
differently (i.e. not through the launcher library, like standalone and
Mesos do).
I also found a couple of tests that could leak a SparkContext on failure,
and added code to handle those.
With this patch, it's possible to run the following command from a clean
source directory and have all tests pass:
mvn -Pyarn -Phadoop-2.4 -Phive-thriftserver install
Author: Marcelo Vanzin <vanzin@cloudera.com>
Closes#7629 from vanzin/SPARK-9284.
Replace `JavaConversions` implicits with `JavaConverters`
Most occurrences I've seen so far are necessary conversions; a few have been avoidable. None are in critical code as far as I see, yet.
Author: Sean Owen <sowen@cloudera.com>
Closes#8033 from srowen/SPARK-9613.
The peak execution memory metric was introduced in SPARK-8735. That was before Tungsten was enabled by default, so it assumed that `spark.sql.unsafe.enabled` must be explicitly set to true. The result is that the memory is not displayed by default.
Author: Andrew Or <andrew@databricks.com>
Closes#8345 from andrewor14/show-memory-default.
https://issues.apache.org/jira/browse/SPARK-9439
In general, Yarn apps should be robust to NodeManager restarts. However, if you run spark with the external shuffle service on, after a NM restart all shuffles fail, b/c the shuffle service has lost some state with info on each executor. (Note the shuffle data is perfectly fine on disk across a NM restart, the problem is we've lost the small bit of state that lets us *find* those files.)
The solution proposed here is that the external shuffle service can write out its state to leveldb (backed by a local file) every time an executor is added. When running with yarn, that file is in the NM's local dir. Whenever the service is started, it looks for that file, and if it exists, it reads the file and re-registers all executors there.
Nothing is changed in non-yarn modes with this patch. The service is not given a place to save the state to, so it operates the same as before. This should make it easy to update other cluster managers as well, by just supplying the right file & the equivalent of yarn's `initializeApplication` -- I'm not familiar enough with those modes to know how to do that.
Author: Imran Rashid <irashid@cloudera.com>
Closes#7943 from squito/leveldb_external_shuffle_service_NM_restart and squashes the following commits:
0d285d3 [Imran Rashid] review feedback
70951d6 [Imran Rashid] Merge branch 'master' into leveldb_external_shuffle_service_NM_restart
5c71c8c [Imran Rashid] save executor to db before registering; style
2499c8c [Imran Rashid] explicit dependency on jackson-annotations
795d28f [Imran Rashid] review feedback
81f80e2 [Imran Rashid] Merge branch 'master' into leveldb_external_shuffle_service_NM_restart
594d520 [Imran Rashid] use json to serialize application executor info
1a7980b [Imran Rashid] version
8267d2a [Imran Rashid] style
e9f99e8 [Imran Rashid] cleanup the handling of bad dbs a little
9378ba3 [Imran Rashid] fail gracefully on corrupt leveldb files
acedb62 [Imran Rashid] switch to writing out one record per executor
79922b7 [Imran Rashid] rely on yarn to call stopApplication; assorted cleanup
12b6a35 [Imran Rashid] save registered executors when apps are removed; add tests
c878fbe [Imran Rashid] better explanation of shuffle service port handling
694934c [Imran Rashid] only open leveldb connection once per service
d596410 [Imran Rashid] store executor data in leveldb
59800b7 [Imran Rashid] Files.move in case renaming is unsupported
32fe5ae [Imran Rashid] Merge branch 'master' into external_shuffle_service_NM_restart
d7450f0 [Imran Rashid] style
f729e2b [Imran Rashid] debugging
4492835 [Imran Rashid] lol, dont use a PrintWriter b/c of scalastyle checks
0a39b98 [Imran Rashid] Merge branch 'master' into external_shuffle_service_NM_restart
55f49fc [Imran Rashid] make sure the service doesnt die if the registered executor file is corrupt; add tests
245db19 [Imran Rashid] style
62586a6 [Imran Rashid] just serialize the whole executors map
bdbbf0d [Imran Rashid] comments, remove some unnecessary changes
857331a [Imran Rashid] better tests & comments
bb9d1e6 [Imran Rashid] formatting
bdc4b32 [Imran Rashid] rename
86e0cb9 [Imran Rashid] for tests, shuffle service finds an open port
23994ff [Imran Rashid] style
7504de8 [Imran Rashid] style
a36729c [Imran Rashid] cleanup
efb6195 [Imran Rashid] proper unit test, and no longer leak if apps stop during NM restart
dd93dc0 [Imran Rashid] test for shuffle service w/ NM restarts
d596969 [Imran Rashid] cleanup imports
0e9d69b [Imran Rashid] better names
9eae119 [Imran Rashid] cleanup lots of duplication
1136f44 [Imran Rashid] test needs to have an actual shuffle
0b588bd [Imran Rashid] more fixes ...
ad122ef [Imran Rashid] more fixes
5e5a7c3 [Imran Rashid] fix build
c69f46b [Imran Rashid] maybe working version, needs tests & cleanup ...
bb3ba49 [Imran Rashid] minor cleanup
36127d3 [Imran Rashid] wip
b9d2ced [Imran Rashid] incomplete setup for external shuffle service tests
In Scala, `Seq.fill` always seems to return a List. Accessing a list by index is an O(N) operation. Thus, the following code will be really slow (~10 seconds on my machine):
```scala
val numItems = 100000
val s = Seq.fill(numItems)(1)
for (i <- 0 until numItems) s(i)
```
It turns out that we had a loop like this in DAGScheduler code, although it's a little tricky to spot. In `getPreferredLocsInternal`, there's a call to `getCacheLocs(rdd)(partition)`. The `getCacheLocs` call returns a Seq. If this Seq is a List and the RDD contains many partitions, then indexing into this list will cost O(partitions). Thus, when we loop over our tasks to compute their individual preferred locations we implicitly perform an N^2 loop, reducing scheduling throughput.
This patch fixes this by replacing `Seq` with `Array`.
Author: Josh Rosen <joshrosen@databricks.com>
Closes#8178 from JoshRosen/dagscheduler-perf.
The shuffle locality patch made the DAGScheduler aware of shuffle data,
but for RDDs that have both narrow and shuffle dependencies, it can
cause them to place tasks based on the shuffle dependency instead of the
narrow one. This case is common in iterative join-based algorithms like
PageRank and ALS, where one RDD is hash-partitioned and one isn't.
Author: Matei Zaharia <matei@databricks.com>
Closes#8220 from mateiz/shuffle-loc-fix.
In these tests, we use a custom listener and we assert on fields in the stage / task completion events. However, these events are posted in a separate thread so they're not guaranteed to be posted in time. This commit fixes this flakiness through a job end registration callback.
Author: Andrew Or <andrew@databricks.com>
Closes#8176 from andrewor14/fix-accumulator-suite.
I think that we should pass additional configuration flags to disable the driver UI and Master REST server in SparkSubmitSuite and HiveSparkSubmitSuite. This might cut down on port-contention-related flakiness in Jenkins.
Author: Josh Rosen <joshrosen@databricks.com>
Closes#8124 from JoshRosen/disable-ui-in-sparksubmitsuite.
… allocation are set. Now, dynamic allocation is set to false when num-executors is explicitly specified as an argument. Consequently, executorAllocationManager in not initialized in the SparkContext.
Author: Niranjan Padmanabhan <niranjan.padmanabhan@cloudera.com>
Closes#7657 from neurons/SPARK-9092.
This is the sister patch to #8011, but for aggregation.
In a nutshell: create the `TungstenAggregationIterator` before computing the parent partition. Internally this creates a `BytesToBytesMap` which acquires a page in the constructor as of this patch. This ensures that the aggregation operator is not starved since we reserve at least 1 page in advance.
rxin yhuai
Author: Andrew Or <andrew@databricks.com>
Closes#8038 from andrewor14/unsafe-starve-memory-agg.
This is based on KaiXinXiaoLei's changes in #7716.
The issue is that when someone calls `sc.killExecutor("1")` on the same executor twice quickly, then the executor target will be adjusted downwards by 2 instead of 1 even though we're only actually killing one executor. In certain cases where we don't adjust the target back upwards quickly, we'll end up with jobs hanging.
This is a common danger because there are many places where this is called:
- `HeartbeatReceiver` kills an executor that has not been sending heartbeats
- `ExecutorAllocationManager` kills an executor that has been idle
- The user code might call this, which may interfere with the previous callers
While it's not clear whether this fixes SPARK-9745, fixing this potential race condition seems like a strict improvement. I've added a regression test to illustrate the issue.
Author: Andrew Or <andrew@databricks.com>
Closes#8078 from andrewor14/da-double-kill.
This allows clients to retrieve the original exception from the
cause field of the SparkException that is thrown by the driver.
If the original exception is not in fact Serializable then it will
not be returned, but the message and stacktrace will be. (All Java
Throwables implement the Serializable interface, but this is no
guarantee that a particular implementation can actually be
serialized.)
Author: Tom White <tom@cloudera.com>
Closes#7014 from tomwhite/propagate-user-exceptions.
`InternalAccumulator.create` doesn't call `registerAccumulatorForCleanup` to register itself with ContextCleaner, so `WeakReference`s for these accumulators in `Accumulators.originals` won't be removed.
This PR added `registerAccumulatorForCleanup` for internal accumulators to avoid the memory leak.
Author: zsxwing <zsxwing@gmail.com>
Closes#8108 from zsxwing/internal-accumulators-leak.
PlatformDependent.UNSAFE is way too verbose.
Author: Reynold Xin <rxin@databricks.com>
Closes#8094 from rxin/SPARK-9815 and squashes the following commits:
229b603 [Reynold Xin] [SPARK-9815] Rename PlatformDependent.UNSAFE -> Platform.
The issue only happens if `spark.executor.cores` is not set and executor memory is set to a high value.
For example, if we have a worker with 4G and 10 cores and we set `spark.executor.memory` to 3G, then only 1 core is assigned to the executor. The correct number should be 10 cores.
I've added a unit test to illustrate the issue.
Author: Carson Wang <carson.wang@intel.com>
Closes#8017 from carsonwang/SPARK-9731 and squashes the following commits:
d09ec48 [Carson Wang] Fix code style
86b651f [Carson Wang] Simplify the code
943cc4c [Carson Wang] fix scheduling correct cores to executors
The original code that this test tests is removed in 9270bd06fd. It was ignored shortly before that so we never caught it. This patch re-enables the test and adds the code necessary to make it pass.
JoshRosen yhuai
Author: Andrew Or <andrew@databricks.com>
Closes#8015 from andrewor14/SPARK-9674 and squashes the following commits:
225eac2 [Andrew Or] Merge branch 'master' of github.com:apache/spark into SPARK-9674
8c24209 [Andrew Or] Fix NPE
e541d64 [Andrew Or] Track aggregation memory for both sort and hash
0be3a42 [Andrew Or] Fix test
This patch follows exactly #7891 (except testing)
Author: Davies Liu <davies@databricks.com>
Closes#8005 from davies/larger_record and squashes the following commits:
f9c4aff [Davies Liu] address comments
9de5c72 [Davies Liu] support records larger than page size in UnsafeShuffleExternalSorter
Previously, we use 64MB as the default page size, which was way too big for a lot of Spark applications (especially for single node).
This patch changes it so that the default page size, if unset by the user, is determined by the number of cores available and the total execution memory available.
Author: Reynold Xin <rxin@databricks.com>
Closes#8012 from rxin/pagesize and squashes the following commits:
16f4756 [Reynold Xin] Fixed failing test.
5afd570 [Reynold Xin] private...
0d5fb98 [Reynold Xin] Update default value.
674a6cd [Reynold Xin] Address review feedback.
dc00e05 [Reynold Xin] Merge with master.
73ebdb6 [Reynold Xin] [SPARK-9700] Pick default page size more intelligently.
The issue is that a task may run multiple sorts, and the sorts run by the child operator (i.e. parent RDD) may acquire all available memory such that other sorts in the same task do not have enough to proceed. This manifests itself in an `IOException("Unable to acquire X bytes of memory")` thrown by `UnsafeExternalSorter`.
The solution is to reserve a page in each sorter in the chain before computing the child operator's (parent RDD's) partitions. This requires us to use a new special RDD that does some preparation before computing the parent's partitions.
Author: Andrew Or <andrew@databricks.com>
Closes#8011 from andrewor14/unsafe-starve-memory and squashes the following commits:
35b69a4 [Andrew Or] Simplify test
0b07782 [Andrew Or] Minor: update comments
5d5afdf [Andrew Or] Merge branch 'master' of github.com:apache/spark into unsafe-starve-memory
254032e [Andrew Or] Add tests
234acbd [Andrew Or] Reserve a page in sorter when preparing each partition
b889e08 [Andrew Or] MapPartitionsWithPreparationRDD
This pull request adds a destructive iterator to BytesToBytesMap. When used, the iterator frees pages as it traverses them. This is part of the effort to avoid starving when we have more than one operators that can exhaust memory.
This is based on #7924, but fixes a bug there (Don't use destructive iterator in UnsafeKVExternalSorter).
Closes#7924.
Author: Liang-Chi Hsieh <viirya@appier.com>
Author: Reynold Xin <rxin@databricks.com>
Closes#8003 from rxin/map-destructive-iterator and squashes the following commits:
6b618c3 [Reynold Xin] Don't use destructive iterator in UnsafeKVExternalSorter.
a7bd8ec [Reynold Xin] Merge remote-tracking branch 'viirya/destructive_iter' into map-destructive-iterator
7652083 [Liang-Chi Hsieh] For comments: add destructiveIterator(), modify unit test, remove code block.
4a3e9de [Liang-Chi Hsieh] Merge remote-tracking branch 'upstream/master' into destructive_iter
581e9e3 [Liang-Chi Hsieh] Merge remote-tracking branch 'upstream/master' into destructive_iter
f0ff783 [Liang-Chi Hsieh] No need to free last page.
9e9d2a3 [Liang-Chi Hsieh] Add a destructive iterator for BytesToBytesMap.
First, it's probably a bad idea to call generated Scala methods
from Java. In this case, the method being called wasn't actually
"Utils.createTempDir()", but actually the method that returns the
first default argument to the actual createTempDir method, which
is just the location of java.io.tmpdir; meaning that all tests in
the class were using the same temp dir, and thus affecting each
other.
Second, spillingOccursInResponseToMemoryPressure was not writing
enough records to actually cause a spill.
Author: Marcelo Vanzin <vanzin@cloudera.com>
Closes#7970 from vanzin/SPARK-9651 and squashes the following commits:
74d357f [Marcelo Vanzin] Clean up temp dir on test tear down.
a64f36a [Marcelo Vanzin] [SPARK-9651] Fix UnsafeExternalSorterSuite.
```
Error Message
Failed to bind to: /127.0.0.1:7093: Service 'sparkMaster' failed after 16 retries!
Stacktrace
java.net.BindException: Failed to bind to: /127.0.0.1:7093: Service 'sparkMaster' failed after 16 retries!
at org.jboss.netty.bootstrap.ServerBootstrap.bind(ServerBootstrap.java:272)
at akka.remote.transport.netty.NettyTransport$$anonfun$listen$1.apply(NettyTransport.scala:393)
at akka.remote.transport.netty.NettyTransport$$anonfun$listen$1.apply(NettyTransport.scala:389)
at scala.util.Success$$anonfun$map$1.apply(Try.scala:206)
at scala.util.Try$.apply(Try.scala:161)
```
Author: Andrew Or <andrew@databricks.com>
Closes#7968 from andrewor14/fix-master-flaky-test and squashes the following commits:
fcc42ef [Andrew Or] Randomize port
The current implementation of UnsafeExternalSort uses NoOpPrefixComparator for binary-typed data.
So, we need to add BinaryPrefixComparator in PrefixComparators.
Author: Takeshi YAMAMURO <linguin.m.s@gmail.com>
Closes#7676 from maropu/BinaryTypePrefixComparator and squashes the following commits:
fe6f31b [Takeshi YAMAMURO] Apply comments
d943c04 [Takeshi YAMAMURO] Add a codegen'd entry for BinaryType in SortPrefix
ecf3ac5 [Takeshi YAMAMURO] Support BinaryType in PrefixComparator
shivaram cafreeman Could you please help me in testing this out? Exposing and running `rPackageBuilder` from inside the shell works, but for some reason, I can't get it to work during Spark Submit. It just starts relaunching Spark Submit.
For testing, you may use the R branch with [sbt-spark-package](https://github.com/databricks/sbt-spark-package). You can call spPackage, and then pass the jar using `--jars`.
Author: Burak Yavuz <brkyvz@gmail.com>
Closes#7139 from brkyvz/r-submit and squashes the following commits:
0de384f [Burak Yavuz] remove unused imports 2
d253708 [Burak Yavuz] removed unused imports
6603d0d [Burak Yavuz] addressed comments
4258ffe [Burak Yavuz] merged master
ddfcc06 [Burak Yavuz] added zipping test
3a1be7d [Burak Yavuz] don't zip
77995df [Burak Yavuz] fix URI
ac45527 [Burak Yavuz] added zipping of all libs
e6bf7b0 [Burak Yavuz] add println ignores
1bc5554 [Burak Yavuz] add assumes for tests
9778e03 [Burak Yavuz] addressed comments
b42b300 [Burak Yavuz] merged master
ffd134e [Burak Yavuz] Merge branch 'master' of github.com:apache/spark into r-submit
d867756 [Burak Yavuz] add apache header
eff5ba1 [Burak Yavuz] ready for review
8838edb [Burak Yavuz] Merge branch 'master' of github.com:apache/spark into r-submit
e5b5a06 [Burak Yavuz] added doc
bb751ce [Burak Yavuz] fix null bug
0226768 [Burak Yavuz] fixed issues
8810beb [Burak Yavuz] R packages support
https://issues.apache.org/jira/browse/SPARK-9602
Although we have hidden Akka behind RPC interface, I found that the Akka/Actor-related comments are still spreading everywhere. To make it consistent, we shall remove "actor"/"akka" words from the comments...
Author: CodingCat <zhunansjtu@gmail.com>
Closes#7936 from CodingCat/SPARK-9602 and squashes the following commits:
e8296a3 [CodingCat] remove actor words from comments
This patch extends UnsafeExternalSorter to support records larger than the page size. The basic strategy is the same as in #7762: store large records in their own overflow pages.
Author: Josh Rosen <joshrosen@databricks.com>
Closes#7891 from JoshRosen/large-records-in-sql-sorter and squashes the following commits:
967580b [Josh Rosen] Merge remote-tracking branch 'origin/master' into large-records-in-sql-sorter
948c344 [Josh Rosen] Add large records tests for KV sorter.
3c17288 [Josh Rosen] Combine memory and disk cleanup into general cleanupResources() method
380f217 [Josh Rosen] Merge remote-tracking branch 'origin/master' into large-records-in-sql-sorter
27eafa0 [Josh Rosen] Fix page size in PackedRecordPointerSuite
a49baef [Josh Rosen] Address initial round of review comments
3edb931 [Josh Rosen] Remove accidentally-committed debug statements.
2b164e2 [Josh Rosen] Support large records in UnsafeExternalSorter.
Enable most javac lint warnings; fix a lot of build warnings. In a few cases, touch up surrounding code in the process.
I'll explain several of the changes inline in comments.
Author: Sean Owen <sowen@cloudera.com>
Closes#7862 from srowen/SPARK-9534 and squashes the following commits:
ea51618 [Sean Owen] Enable most javac lint warnings; fix a lot of build warnings. In a few cases, touch up surrounding code in the process.
While the functionality is there to exclude packages, there are no flags that allow users to exclude dependencies, in case of dependency conflicts. We should provide users with a flag to add dependency exclusions in case the packages are not resolved properly (or not available due to licensing).
The flag I added was --packages-exclude, but I'm open on renaming it. I also added property flags in case people would like to use a conf file to provide dependencies, which is possible if there is a long list of dependencies or exclusions.
cc andrewor14 vanzin pwendell
Author: Burak Yavuz <brkyvz@gmail.com>
Closes#7599 from brkyvz/packages-exclusions and squashes the following commits:
636f410 [Burak Yavuz] addressed nits
6e54ede [Burak Yavuz] is this the culprit
b5e508e [Burak Yavuz] Merge branch 'master' of github.com:apache/spark into packages-exclusions
154f5db [Burak Yavuz] addressed initial comments
1536d7a [Burak Yavuz] Added flags to exclude packages using --packages-exclude
Certain use cases of Spark involve RDDs with long lineages that must be truncated periodically (e.g. GraphX). The existing way of doing it is through `rdd.checkpoint()`, which is expensive because it writes to HDFS. This patch provides an alternative to truncate lineages cheaply *without providing the same level of fault tolerance*.
**Local checkpointing** writes checkpointed data to the local file system through the block manager. It is much faster than replicating to a reliable storage and provides the same semantics as long as executors do not fail. It is accessible through a new operator `rdd.localCheckpoint()` and leaves the old one unchanged. Users may even decide to combine the two and call the reliable one less frequently.
The bulk of this patch involves refactoring the checkpointing interface to accept custom implementations of checkpointing. [Design doc](https://issues.apache.org/jira/secure/attachment/12741708/SPARK-7292-design.pdf).
Author: Andrew Or <andrew@databricks.com>
Closes#7279 from andrewor14/local-checkpoint and squashes the following commits:
729600f [Andrew Or] Oops, fix tests
34bc059 [Andrew Or] Avoid computing all partitions in local checkpoint
e43bbb6 [Andrew Or] Merge branch 'master' of github.com:apache/spark into local-checkpoint
3be5aea [Andrew Or] Address comments
bf846a6 [Andrew Or] Merge branch 'master' of github.com:apache/spark into local-checkpoint
ab003a3 [Andrew Or] Fix compile
c2e111b [Andrew Or] Address comments
33f167a [Andrew Or] Merge branch 'master' of github.com:apache/spark into local-checkpoint
e908a42 [Andrew Or] Fix tests
f5be0f3 [Andrew Or] Use MEMORY_AND_DISK as the default local checkpoint level
a92657d [Andrew Or] Update a few comments
e58e3e3 [Andrew Or] Merge branch 'master' of github.com:apache/spark into local-checkpoint
4eb6eb1 [Andrew Or] Merge branch 'master' of github.com:apache/spark into local-checkpoint
1bbe154 [Andrew Or] Simplify LocalCheckpointRDD
48a9996 [Andrew Or] Avoid traversing dependency tree + rewrite tests
62aba3f [Andrew Or] Merge branch 'master' of github.com:apache/spark into local-checkpoint
db70dc2 [Andrew Or] Express local checkpointing through caching the original RDD
87d43c6 [Andrew Or] Merge branch 'master' of github.com:apache/spark into local-checkpoint
c449b38 [Andrew Or] Fix style
4a182f3 [Andrew Or] Add fine-grained tests for local checkpointing
53b363b [Andrew Or] Rename a few more awkwardly named methods (minor)
e4cf071 [Andrew Or] Simplify LocalCheckpointRDD + docs + clean ups
4880deb [Andrew Or] Fix style
d096c67 [Andrew Or] Fix mima
172cb66 [Andrew Or] Fix mima?
e53d964 [Andrew Or] Fix style
56831c5 [Andrew Or] Add a few warnings and clear exception messages
2e59646 [Andrew Or] Add local checkpoint clean up tests
4dbbab1 [Andrew Or] Refactor CheckpointSuite to test local checkpointing
4514dc9 [Andrew Or] Clean local checkpoint files through RDD cleanups
0477eec [Andrew Or] Rename a few methods with awkward names (minor)
2e902e5 [Andrew Or] First implementation of local checkpointing
8447454 [Andrew Or] Fix tests
4ac1896 [Andrew Or] Refactor checkpoint interface for modularity
This patch builds directly on #7820, which is largely written by tnachen. The only addition is one commit for cleaning up the code. There should be no functional differences between this and #7820.
Author: Timothy Chen <tnachen@gmail.com>
Author: Andrew Or <andrew@databricks.com>
Closes#7881 from andrewor14/tim-cleanup-mesos-shuffle and squashes the following commits:
8894f7d [Andrew Or] Clean up code
2a5fa10 [Andrew Or] Merge branch 'mesos_shuffle_clean' of github.com:tnachen/spark into tim-cleanup-mesos-shuffle
fadff89 [Timothy Chen] Address comments.
e4d0f1d [Timothy Chen] Clean up external shuffle data on driver exit with Mesos.
This pull request adds a destructAndCreateExternalSorter method to UnsafeFixedWidthAggregationMap. The new method does the following:
1. Creates a new external sorter UnsafeKVExternalSorter
2. Adds all the data into an in-memory sorter, sorts them
3. Spills the sorted in-memory data to disk
This method can be used to fallback to sort-based aggregation when under memory pressure.
The pull request also includes accounting fixes from JoshRosen.
TODOs (that can be done in follow-up PRs)
- [x] Address Josh's feedbacks from #7849
- [x] More documentation and test cases
- [x] Make sure we are doing memory accounting correctly with test cases (e.g. did we release the memory in BytesToBytesMap twice?)
- [ ] Look harder at possible memory leaks and exception handling
- [ ] Randomized tester for the KV sorter as well as the aggregation map
Author: Reynold Xin <rxin@databricks.com>
Author: Josh Rosen <joshrosen@databricks.com>
Closes#7860 from rxin/kvsorter and squashes the following commits:
986a58c [Reynold Xin] Bug fix.
599317c [Reynold Xin] Style fix and slightly more compact code.
fe7bd4e [Reynold Xin] Bug fixes.
fd71bef [Reynold Xin] Merge remote-tracking branch 'josh/large-records-in-sql-sorter' into kvsorter-with-josh-fix
3efae38 [Reynold Xin] More fixes and documentation.
45f1b09 [Josh Rosen] Ensure that spill files are cleaned up
f6a9bd3 [Reynold Xin] Josh feedback.
9be8139 [Reynold Xin] Remove testSpillFrequency.
7cbe759 [Reynold Xin] [SPARK-9531][SQL] UnsafeFixedWidthAggregationMap.destructAndCreateExternalSorter.
ae4a8af [Josh Rosen] Detect leaked unsafe memory in UnsafeExternalSorterSuite.
52f9b06 [Josh Rosen] Detect ShuffleMemoryManager leaks in UnsafeExternalSorter.
Dynamic allocation is a feature that allows a Spark application to scale the number of executors up and down dynamically based on the workload. Support was first introduced in YARN since 1.2, and then extended to Mesos coarse-grained mode recently. Today, it is finally supported in standalone mode as well!
I tested this locally and it works as expected. This is WIP because unit tests are coming.
Author: Andrew Or <andrew@databricks.com>
Closes#7532 from andrewor14/standalone-da and squashes the following commits:
b3c1736 [Andrew Or] Merge branch 'master' of github.com:apache/spark into standalone-da
879e928 [Andrew Or] Add end-to-end tests for standalone dynamic allocation
accc8f6 [Andrew Or] Address comments
ee686a8 [Andrew Or] Merge branch 'master' of github.com:apache/spark into standalone-da
c0a2c02 [Andrew Or] Fix build after merge conflict
24149eb [Andrew Or] Merge branch 'master' of github.com:apache/spark into standalone-da
2e762d6 [Andrew Or] Merge branch 'master' of github.com:apache/spark into standalone-da
6832bd7 [Andrew Or] Add tests for scheduling with executor limit
a82e907 [Andrew Or] Fix comments
0a8be79 [Andrew Or] Simplify logic by removing the worker blacklist
b7742af [Andrew Or] Merge branch 'master' of github.com:apache/spark into standalone-da
2eb5f3f [Andrew Or] Merge branch 'master' of github.com:apache/spark into standalone-da
1334e9a [Andrew Or] Fix MiMa
32abe44 [Andrew Or] Fix style
58cb06f [Andrew Or] Privatize worker blacklist for cleanliness
42ac215 [Andrew Or] Clean up comments and rewrite code for readability
49702d1 [Andrew Or] Clean up shuffle files after application exits
80047aa [Andrew Or] First working implementation
BytesToBytesMap current encodes key/value data in the following format:
```
8B key length, key data, 8B value length, value data
```
UnsafeExternalSorter, on the other hand, encodes data this way:
```
4B record length, data
```
As a result, we cannot pass records encoded by BytesToBytesMap directly into UnsafeExternalSorter for sorting. However, if we rearrange data slightly, we can then pass the key/value records directly into UnsafeExternalSorter:
```
4B key+value length, 4B key length, key data, value data
```
Author: Reynold Xin <rxin@databricks.com>
Closes#7845 from rxin/kvsort-rebase and squashes the following commits:
5716b59 [Reynold Xin] Fixed test.
2e62ccb [Reynold Xin] Updated BytesToBytesMap's data encoding to put the key first.
a51b641 [Reynold Xin] Added a KV sorter interface.
This patch adds support for entries larger than the default page size in BytesToBytesMap. These large rows are handled by allocating special overflow pages to hold individual entries.
In addition, this patch integrates BytesToBytesMap with the ShuffleMemoryManager:
- Move BytesToBytesMap from `unsafe` to `core` so that it can import `ShuffleMemoryManager`.
- Before allocating new data pages, ask the ShuffleMemoryManager to reserve the memory:
- `putNewKey()` now returns a boolean to indicate whether the insert succeeded or failed due to a lack of memory. The caller can use this value to respond to the memory pressure (e.g. by spilling).
- `UnsafeFixedWidthAggregationMap. getAggregationBuffer()` now returns `null` to signal failure due to a lack of memory.
- Updated all uses of these classes to handle these error conditions.
- Added new tests for allocating large records and for allocations which fail due to memory pressure.
- Extended the `afterAll()` test teardown methods to detect ShuffleMemoryManager leaks.
Author: Josh Rosen <joshrosen@databricks.com>
Closes#7762 from JoshRosen/large-rows and squashes the following commits:
ae7bc56 [Josh Rosen] Fix compilation
82fc657 [Josh Rosen] Merge remote-tracking branch 'origin/master' into large-rows
34ab943 [Josh Rosen] Remove semi
31a525a [Josh Rosen] Integrate BytesToBytesMap with ShuffleMemoryManager.
626b33c [Josh Rosen] Move code to sql/core and spark/core packages so that ShuffleMemoryManager can be integrated
ec4484c [Josh Rosen] Move BytesToBytesMap from unsafe package to core.
642ed69 [Josh Rosen] Rename size to numElements
bea1152 [Josh Rosen] Add basic test.
2cd3570 [Josh Rosen] Remove accidental duplicated code
07ff9ef [Josh Rosen] Basic support for large rows in BytesToBytesMap.
Author: Reynold Xin <rxin@databricks.com>
Closes#7803 from rxin/SPARK-9458 and squashes the following commits:
5b032dc [Reynold Xin] Fix string.
b670dbb [Reynold Xin] [SPARK-9458][SPARK-9469][SQL] Code generate prefix computation in sorting & moves unsafe conversion out of TungstenSort.
As of today, StringPrefixComparator converts the long values back to byte arrays in order to compare them. This patch optimizes this to compare the longs directly, rather than turning the longs into byte arrays and comparing them byte by byte (unsigned).
This only works on little-endian architecture right now.
Author: Reynold Xin <rxin@databricks.com>
Closes#7765 from rxin/SPARK-9460 and squashes the following commits:
e4908cc [Reynold Xin] Stricter randomized tests.
4c8d094 [Reynold Xin] [SPARK-9460] Avoid byte array allocation in StringPrefixComparator.
In our existing sort prefix generation code, we use expression's eval method to generate the prefix, which results in object allocation for every prefix. We can use the specialized getters available on InternalRow directly to avoid the object allocation.
I also removed the FLOAT prefix, opting for converting float directly to double.
Author: Reynold Xin <rxin@databricks.com>
Closes#7763 from rxin/sort-prefix and squashes the following commits:
5dc2f06 [Reynold Xin] [SPARK-9458] Avoid object allocation in prefix generation.
We need to make page sizes configurable so we can reduce them in unit tests and increase them in real production workloads. These sizes are now controlled by a new configuration, `spark.buffer.pageSize`. The new default is 64 megabytes.
Author: Josh Rosen <joshrosen@databricks.com>
Closes#7741 from JoshRosen/SPARK-9411 and squashes the following commits:
a43c4db [Josh Rosen] Fix pow
2c0eefc [Josh Rosen] Fix MAXIMUM_PAGE_SIZE_BYTES comment + value
bccfb51 [Josh Rosen] Lower page size to 4MB in TestHive
ba54d4b [Josh Rosen] Make UnsafeExternalSorter's page size configurable
0045aa2 [Josh Rosen] Make UnsafeShuffle's page size configurable
bc734f0 [Josh Rosen] Rename configuration
e614858 [Josh Rosen] Makes BytesToBytesMap page size configurable
Added a custom Kryo serializer for generic Avro records to reduce the network IO
involved during a shuffle. This compresses the schema and allows for users to
register their schemas ahead of time to further reduce traffic.
Currently Kryo tries to use its default serializer for generic Records, which will include
a lot of unneeded data in each record.
Author: Joseph Batchik <joseph.batchik@cloudera.com>
Author: Joseph Batchik <josephbatchik@gmail.com>
Closes#7004 from JDrit/Avro_serialization and squashes the following commits:
8158d51 [Joseph Batchik] updated per feedback
c0cf329 [Joseph Batchik] implemented @squito suggestion for SparkEnv
dd71efe [Joseph Batchik] fixed bug with serializing
1183a48 [Joseph Batchik] updated codec settings
fa9298b [Joseph Batchik] forgot a couple of fixes
c5fe794 [Joseph Batchik] implemented @squito suggestion
0f5471a [Joseph Batchik] implemented @squito suggestion to use a codec that is already in spark
6d1925c [Joseph Batchik] fixed to changes suggested by @squito
d421bf5 [Joseph Batchik] updated pom to removed versions
ab46d10 [Joseph Batchik] Changed Avro dependency to be similar to parent
f4ae251 [Joseph Batchik] fixed serialization error in that SparkConf cannot be serialized
2b545cc [Joseph Batchik] started working on fixes for pr
97fba62 [Joseph Batchik] Added a custom Kryo serializer for generic Avro records to reduce the network IO involved during a shuffle. This compresses the schema and allows for users to register their schemas ahead of time to further reduce traffic.
Spark's ShuffleMemoryManager and MemoryStore track memory on a per-thread basis, which causes problems in the handful of cases where we have tasks that use multiple threads. In PythonRDD, RRDD, ScriptTransformation, and PipedRDD we consume the input iterator in a separate thread in order to write it to an external process. As a result, these RDD's input iterators are consumed in a different thread than the thread that created them, which can cause problems in our memory allocation tracking. For example, if allocations are performed in one thread but deallocations are performed in a separate thread then memory may be leaked or we may get errors complaining that more memory was allocated than was freed.
I think that the right way to fix this is to change our accounting to be performed on a per-task instead of per-thread basis. Note that the current per-thread tracking has caused problems in the past; SPARK-3731 (#2668) fixes a memory leak in PythonRDD that was caused by this issue (that fix is no longer necessary as of this patch).
Author: Josh Rosen <joshrosen@databricks.com>
Closes#7734 from JoshRosen/memory-tracking-fixes and squashes the following commits:
b4b1702 [Josh Rosen] Propagate TaskContext to writer threads.
57c9b4e [Josh Rosen] Merge remote-tracking branch 'origin/master' into memory-tracking-fixes
ed25d3b [Josh Rosen] Address minor PR review comments
44f6497 [Josh Rosen] Fix long line.
7b0f04b [Josh Rosen] Fix ShuffleMemoryManagerSuite
f57f3f2 [Josh Rosen] More thread -> task changes
fa78ee8 [Josh Rosen] Move Executor's cleanup into Task so that TaskContext is defined when cleanup is performed
5e2f01e [Josh Rosen] Fix capitalization
1b0083b [Josh Rosen] Roll back fix in PySpark, which is no longer necessary
2e1e0f8 [Josh Rosen] Use TaskAttemptIds to track shuffle memory
c9e8e54 [Josh Rosen] Use TaskAttemptIds to track unroll memory
Currently there's no locality preference for container request in YARN mode, this will affect the performance if fetching data remotely, so here proposed to add locality in Yarn dynamic allocation mode.
Ping sryza, please help to review, thanks a lot.
Author: jerryshao <saisai.shao@intel.com>
Closes#6394 from jerryshao/SPARK-4352 and squashes the following commits:
d45fecb [jerryshao] Add documents
6c3fe5c [jerryshao] Fix bug
8db6c0e [jerryshao] Further address the comments
2e2b2cb [jerryshao] Fix rebase compiling problem
ce5f096 [jerryshao] Fix style issue
7f7df95 [jerryshao] Fix rebase issue
9ca9e07 [jerryshao] Code refactor according to comments
d3e4236 [jerryshao] Further address the comments
5e7a593 [jerryshao] Fix bug introduced code rebase
9ca7783 [jerryshao] Style changes
08317f9 [jerryshao] code and comment refines
65b2423 [jerryshao] Further address the comments
a27c587 [jerryshao] address the comment
27faabc [jerryshao] redundant code remove
9ce06a1 [jerryshao] refactor the code
f5ba27b [jerryshao] Style fix
2c6cc8a [jerryshao] Fix bug and add unit tests
0757335 [jerryshao] Consider the distribution of existed containers to recalculate the new container requests
0ad66ff [jerryshao] Fix compile bugs
1c20381 [jerryshao] Minor fix
5ef2dc8 [jerryshao] Add docs and improve the code
3359814 [jerryshao] Fix rebase and test bugs
0398539 [jerryshao] reinitialize the new implementation
67596d6 [jerryshao] Still fix the code
654e1d2 [jerryshao] Fix some bugs
45b1c89 [jerryshao] Further polish the algorithm
dea0152 [jerryshao] Enable node locality information in YarnAllocator
74bbcc6 [jerryshao] Support node locality for dynamic allocation initial commit
This patch fixes two bugs in UnsafeExternalSorter and UnsafeExternalRowSorter:
- UnsafeExternalSorter does not properly update freeSpaceInCurrentPage, which can cause it to write past the end of memory pages and trigger segfaults.
- UnsafeExternalRowSorter has a use-after-free bug when returning the last row from an iterator.
Author: Josh Rosen <joshrosen@databricks.com>
Closes#7680 from JoshRosen/SPARK-9364 and squashes the following commits:
590f311 [Josh Rosen] null out row
f4cf91d [Josh Rosen] Fix use-after-free bug in UnsafeExternalRowSorter.
8abcf82 [Josh Rosen] Properly decrement freeSpaceInCurrentPage in UnsafeExternalSorter
This also fixes a small issue in the standalone Master that was uncovered by the new tests. For more detail, read the description of SPARK-9353.
Author: Andrew Or <andrew@databricks.com>
Closes#7668 from andrewor14/standalone-scheduling-tests and squashes the following commits:
d852faf [Andrew Or] Add tests + fix scheduling with memory limits
It's a thing used in test cases, but named Row. Pretty annoying because everytime I search for Row, it shows up before the Spark SQL Row, which is what a developer wants most of the time.
Author: Reynold Xin <rxin@databricks.com>
Closes#7638 from rxin/remove-row and squashes the following commits:
aeda52d [Reynold Xin] [SPARK-9305] Rename org.apache.spark.Row to Item.
See also comments on https://issues.apache.org/jira/browse/SPARK-9236
Author: François Garillot <francois@garillot.net>
Closes#7616 from huitseeker/issue/SPARK-9236 and squashes the following commits:
217f902 [François Garillot] [SPARK-9236] Make defaultPartitioner not reuse a parent RDD's partitioner if it has 0 partitions
When a task fails with an exception and also fails to properly clean up its managed memory, the `spark.unsafe.exceptionOnMemoryLeak` memory leak detection mechanism's exceptions will mask the original exception that caused the task to fail. We should throw the memory leak exception only if no other exception occurred.
Author: Josh Rosen <joshrosen@databricks.com>
Closes#7603 from JoshRosen/SPARK-9266 and squashes the following commits:
c268cb5 [Josh Rosen] Merge remote-tracking branch 'origin/master' into SPARK-9266
c1f0167 [Josh Rosen] Fix the error masking problem
448eae8 [Josh Rosen] Add regression test
Spark has an option called spark.localExecution.enabled; according to the docs:
> Enables Spark to run certain jobs, such as first() or take() on the driver, without sending tasks to the cluster. This can make certain jobs execute very quickly, but may require shipping a whole partition of data to the driver.
This feature ends up adding quite a bit of complexity to DAGScheduler, especially in the runLocallyWithinThread method, but as far as I know nobody uses this feature (I searched the mailing list and haven't seen any recent mentions of the configuration nor stacktraces including the runLocally method). As a step towards scheduler complexity reduction, I propose that we remove this feature and all code related to it for Spark 1.5.
This pull request simply brings #7484 up to date.
Author: Josh Rosen <joshrosen@databricks.com>
Author: Reynold Xin <rxin@databricks.com>
Closes#7585 from rxin/remove-local-exec and squashes the following commits:
84bd10e [Reynold Xin] Python fix.
1d9739a [Reynold Xin] Merge pull request #7484 from JoshRosen/remove-localexecution
eec39fa [Josh Rosen] Remove allowLocal(); deprecate user-facing uses of it.
b0835dc [Josh Rosen] Remove local execution code in DAGScheduler
8975d96 [Josh Rosen] Remove local execution tests.
ffa8c9b [Josh Rosen] Remove documentation for configuration
There are a few memory limits that people hit often and that we could
make higher, especially now that memory sizes have grown.
- spark.akka.frameSize: This defaults at 10 but is often hit for map
output statuses in large shuffles. This memory is not fully allocated
up-front, so we can just make this larger and still not affect jobs
that never sent a status that large. We increase it to 128.
- spark.executor.memory: Defaults at 512m, which is really small. We
increase it to 1g.
Author: Matei Zaharia <matei@databricks.com>
Closes#7586 from mateiz/configs and squashes the following commits:
ce0038a [Matei Zaharia] [SPARK-9244] Increase some memory defaults
This PR adds pagination for the task table to solve the scalability issue of the stage page. Here is the initial screenshot:
<img width="1347" alt="pagination" src="https://cloud.githubusercontent.com/assets/1000778/8679669/9e63863c-2a8e-11e5-94e4-994febcd6717.png">
The task table only shows 100 tasks. There is a page navigation above the table. Users can click the page navigation or type the page number to jump to another page. The table can be sorted by clicking the headers. However, unlike previous implementation, the sorting work is done in the server now. So clicking a table column to sort needs to refresh the web page.
Author: zsxwing <zsxwing@gmail.com>
Closes#7399 from zsxwing/task-table-pagination and squashes the following commits:
144f513 [zsxwing] Display the page navigation when the page number is out of range
a3eee22 [zsxwing] Add extra space for the error message
54c5b84 [zsxwing] Reset page to 1 if the user changes the page size
c2f7f39 [zsxwing] Add a text field to let users fill the page size
bad52eb [zsxwing] Display user-friendly error messages
410586b [zsxwing] Scroll down to the tasks table if the url contains any sort column
a0746d1 [zsxwing] Use expand-dag-viz-arrow-job and expand-dag-viz-arrow-stage instead of expand-dag-viz-arrow-true and expand-dag-viz-arrow-false
b123f67 [zsxwing] Use localStorage to remember the user's actions and replay them when loading the page
894a342 [zsxwing] Show the link cursor when hovering for headers and page links and other minor fix
4d4fecf [zsxwing] Address Carson's comments
d9285f0 [zsxwing] Add comments and fix the style
74285fa [zsxwing] Merge branch 'master' into task-table-pagination
db6c859 [zsxwing] Task table pagination for the Stage page
Author: Jacek Lewandowski <lewandowski.jacek@gmail.com>
Closes#5805 from jacek-lewandowski/SPARK-7171 and squashes the following commits:
ed20bda [Jacek Lewandowski] SPARK-7171: Added a method to retrieve metrics sources in TaskContext
JIRA: https://issues.apache.org/jira/browse/SPARK-9128
Currently, in `ClosureCleaner`, the outerclasses and objects are retrieved using two different methods. However, the logic of the two methods is the same, and we can get both the outerclasses and objects with only one method calling.
Author: Liang-Chi Hsieh <viirya@appier.com>
Closes#7459 from viirya/remove_extra_closurecleaner and squashes the following commits:
7c9858d [Liang-Chi Hsieh] For comments.
a096941 [Liang-Chi Hsieh] Merge remote-tracking branch 'upstream/master' into remove_extra_closurecleaner
2ec5ce1 [Liang-Chi Hsieh] Remove unnecessary methods.
4df5a51 [Liang-Chi Hsieh] Merge remote-tracking branch 'upstream/master' into remove_extra_closurecleaner
dc110d1 [Liang-Chi Hsieh] Add method to get outerclasses and objects at the same time.
This PR implements a JSON serializer and deserializer in the JSONProtocol to handle the (de)serialization of SparkListenerExecutorMetricsUpdate events. It also includes a unit test in the JSONProtocolSuite file. This was implemented to satisfy the improvement request in the JIRA issue SPARK-9036.
Author: Ben <benjaminpiering@gmail.com>
Closes#7555 from NamelessAnalyst/master and squashes the following commits:
fb4e3cc [Ben] Update JSON Protocol and tests
aa69517 [Ben] Update JSON Protocol and tests --Corrected Stage Attempt to Stage Attempt ID
33e5774 [Ben] Update JSON Protocol Tests
3f237e7 [Ben] Update JSON Protocol Tests
84ca798 [Ben] Update JSON Protocol Tests
cde57a0 [Ben] Update JSON Protocol Tests
8049600 [Ben] Update JSON Protocol Tests
c5bc061 [Ben] Update JSON Protocol Tests
6f25785 [Ben] Merge remote-tracking branch 'origin/master'
df2a609 [Ben] Update JSON Protocol
dcda80b [Ben] Update JSON Protocol
The shuffle code has gotten increasingly difficult to read as it has evolved, and many classes
have evolved significantly since they were originally created. The BlockStoreShuffleFetcher class
now serves little purpose other than to make the code more difficult to read; this commit moves its
functionality into the ShuffleBlockFetcherIterator class.
cc massie JoshRosen (Josh, this PR also removes the Try you pointed out as being confusing / not necessarily useful in a previous comment). Matt, would be helpful to know whether this will interfere in any negative ways with your new shuffle PR (I took a look and it seems like this should still cleanly integrate with your parquet work, but want to double check).
Author: Kay Ousterhout <kayousterhout@gmail.com>
Closes#7268 from kayousterhout/SPARK-8875 and squashes the following commits:
2b24a97 [Kay Ousterhout] Fixed DAGSchedulerSuite compile error
98a1831 [Kay Ousterhout] Merge remote-tracking branch 'upstream/master' into SPARK-8875
90f0e89 [Kay Ousterhout] Fixed broken test
14bfcbb [Kay Ousterhout] Last style fix
bc69d2b [Kay Ousterhout] Style improvements based on Josh's code review
ad3c8d1 [Kay Ousterhout] Better documentation for MapOutputTracker methods
0bc0e59 [Kay Ousterhout] [SPARK-8875] Remove BlockStoreShuffleFetcher class
This patch addresses an issue where queries that sorted float or double columns containing NaN values could fail with "Comparison method violates its general contract!" errors from TimSort. The root of this problem is that `NaN > anything`, `NaN == anything`, and `NaN < anything` all return `false`.
Per the design specified in SPARK-9079, we have decided that `NaN = NaN` should return true and that NaN should appear last when sorting in ascending order (i.e. it is larger than any other numeric value).
In addition to implementing these semantics, this patch also adds canonicalization of NaN values in UnsafeRow, which is necessary in order to be able to do binary equality comparisons on equal NaNs that might have different bit representations (see SPARK-9147).
Author: Josh Rosen <joshrosen@databricks.com>
Closes#7194 from JoshRosen/nan and squashes the following commits:
983d4fc [Josh Rosen] Merge remote-tracking branch 'origin/master' into nan
88bd73c [Josh Rosen] Fix Row.equals()
a702e2e [Josh Rosen] normalization -> canonicalization
a7267cf [Josh Rosen] Normalize NaNs in UnsafeRow
fe629ae [Josh Rosen] Merge remote-tracking branch 'origin/master' into nan
fbb2a29 [Josh Rosen] Fix NaN comparisons in BinaryComparison expressions
c1fd4fe [Josh Rosen] Fold NaN test into existing test framework
b31eb19 [Josh Rosen] Uncomment failing tests
7fe67af [Josh Rosen] Support NaN == NaN (SPARK-9145)
58bad2c [Josh Rosen] Revert "Compare rows' string representations to work around NaN incomparability."
fc6b4d2 [Josh Rosen] Update CodeGenerator
3998ef2 [Josh Rosen] Remove unused code
a2ba2e7 [Josh Rosen] Fix prefix comparision for NaNs
a30d371 [Josh Rosen] Compare rows' string representations to work around NaN incomparability.
6f03f85 [Josh Rosen] Fix bug in Double / Float ordering
42a1ad5 [Josh Rosen] Stop filtering NaNs in UnsafeExternalSortSuite
bfca524 [Josh Rosen] Change ordering so that NaN is maximum value.
8d7be61 [Josh Rosen] Update randomized test to use ScalaTest's assume()
b20837b [Josh Rosen] Add failing test for new NaN comparision ordering
5b88b2b [Josh Rosen] Fix compilation of CodeGenerationSuite
d907b5b [Josh Rosen] Merge remote-tracking branch 'origin/master' into nan
630ebc5 [Josh Rosen] Specify an ordering for NaN values.
9bf195a [Josh Rosen] Re-enable NaNs in CodeGenerationSuite to produce more regression tests
13fc06a [Josh Rosen] Add regression test for NaN sorting issue
f9efbb5 [Josh Rosen] Fix ORDER BY NULL
e7dc4fb [Josh Rosen] Add very generic test for ordering
7d5c13e [Josh Rosen] Add regression test for SPARK-8782 (ORDER BY NULL)
b55875a [Josh Rosen] Generate doubles and floats over entire possible range.
5acdd5c [Josh Rosen] Infinity and NaN are interesting.
ab76cbd [Josh Rosen] Move code to Catalyst package.
d2b4a4a [Josh Rosen] Add random data generator test utilities to Spark SQL.
https://issues.apache.org/jira/browse/SPARK-8103
cc kayousterhout (thanks for the extra test case)
Author: Imran Rashid <irashid@cloudera.com>
Author: Kay Ousterhout <kayousterhout@gmail.com>
Author: Imran Rashid <squito@users.noreply.github.com>
Closes#6750 from squito/SPARK-8103 and squashes the following commits:
fb3acfc [Imran Rashid] fix log msg
e01b7aa [Imran Rashid] fix some comments, style
584acd4 [Imran Rashid] simplify going from taskId to taskSetMgr
e43ac25 [Imran Rashid] Merge branch 'master' into SPARK-8103
6bc23af [Imran Rashid] update log msg
4470fa1 [Imran Rashid] rename
c04707e [Imran Rashid] style
88b61cc [Imran Rashid] add tests to make sure that TaskSchedulerImpl schedules correctly with zombie attempts
d7f1ef2 [Imran Rashid] get rid of activeTaskSets
a21c8b5 [Imran Rashid] Merge branch 'master' into SPARK-8103
906d626 [Imran Rashid] fix merge
109900e [Imran Rashid] Merge branch 'master' into SPARK-8103
c0d4d90 [Imran Rashid] Revert "Index active task sets by stage Id rather than by task set id"
f025154 [Imran Rashid] Merge pull request #2 from kayousterhout/imran_SPARK-8103
baf46e1 [Kay Ousterhout] Index active task sets by stage Id rather than by task set id
19685bb [Imran Rashid] switch to using latestInfo.attemptId, and add comments
a5f7c8c [Imran Rashid] remove comment for reviewers
227b40d [Imran Rashid] style
517b6e5 [Imran Rashid] get rid of SparkIllegalStateException
b2faef5 [Imran Rashid] faster check for conflicting task sets
6542b42 [Imran Rashid] remove extra stageAttemptId
ada7726 [Imran Rashid] reviewer feedback
d8eb202 [Imran Rashid] Merge branch 'master' into SPARK-8103
46bc26a [Imran Rashid] more cleanup of debug garbage
cb245da [Imran Rashid] finally found the issue ... clean up debug stuff
8c29707 [Imran Rashid] Merge branch 'master' into SPARK-8103
89a59b6 [Imran Rashid] more printlns ...
9601b47 [Imran Rashid] more debug printlns
ecb4e7d [Imran Rashid] debugging printlns
b6bc248 [Imran Rashid] style
55f4a94 [Imran Rashid] get rid of more random test case since kays tests are clearer
7021d28 [Imran Rashid] update test since listenerBus.waitUntilEmpty now throws an exception instead of returning a boolean
883fe49 [Kay Ousterhout] Unit tests for concurrent stages issue
6e14683 [Imran Rashid] unit test just to make sure we fail fast on concurrent attempts
06a0af6 [Imran Rashid] ignore for jenkins
c443def [Imran Rashid] better fix and simpler test case
28d70aa [Imran Rashid] wip on getting a better test case ...
a9bf31f [Imran Rashid] wip
This makes sure attempts are listed in the order they were executed, and that the
app's state matches the state of the most current attempt.
Author: Joshi <rekhajoshm@gmail.com>
Author: Rekha Joshi <rekhajoshm@gmail.com>
Closes#7253 from rekhajoshm/SPARK-8593 and squashes the following commits:
874dd80 [Joshi] History Server: updated order for multiple attempts(logcleaner)
716e0b1 [Joshi] History Server: updated order for multiple attempts(descending start time works everytime)
548c753 [Joshi] History Server: updated order for multiple attempts(descending start time works everytime)
83306a8 [Joshi] History Server: updated order for multiple attempts(descending start time)
b0fc922 [Joshi] History Server: updated order for multiple attempts(updated comment)
cc0fda7 [Joshi] History Server: updated order for multiple attempts(updated test)
304cb0b [Joshi] History Server: updated order for multiple attempts(reverted HistoryPage)
85024e8 [Joshi] History Server: updated order for multiple attempts
a41ac4b [Joshi] History Server: updated order for multiple attempts
ab65fa1 [Joshi] History Server: some attempt completed to work with showIncomplete
0be142d [Rekha Joshi] Merge pull request #3 from apache/master
106fd8e [Rekha Joshi] Merge pull request #2 from apache/master
e3677c9 [Rekha Joshi] Merge pull request #1 from apache/master
This PR includes the following changes:
1. Remove the thread local `Accumulators.localAccums`. Instead, all Accumulators in the executors will register with its TaskContext.
2. Add an internal flag to Accumulable. For internal Accumulators, their updates will be sent to the driver via heartbeats.
Author: zsxwing <zsxwing@gmail.com>
Closes#7448 from zsxwing/accumulators and squashes the following commits:
c24bc5b [zsxwing] Add comments
bd7dcf1 [zsxwing] Add an internal flag to Accumulable and send internal accumulator updates to the driver via heartbeats
**Symptom.** If an executor in an application times out, `HeartbeatReceiver` attempts to kill it. After this happens, however, the application never gets an executor back even when there are cluster resources available.
**Cause.** The issue is that `sc.killExecutor` automatically assumes that the application wishes to adjust its resource requirements permanently downwards. This is not the intention in `HeartbeatReceiver`, however, which simply wants a replacement for the expired executor.
**Fix.** Differentiate between the intention to kill and the intention to replace an executor with a fresh one. More details can be found in the commit message.
Author: Andrew Or <andrew@databricks.com>
Closes#7107 from andrewor14/heartbeat-no-kill and squashes the following commits:
1cd2cd7 [Andrew Or] Add regression test for SPARK-8119
25a347d [Andrew Or] Reuse more code in scheduler backend
31ebd40 [Andrew Or] Differentiate between kill and replace
Mesos supports framework authentication and role to be set per framework, which the role is used to identify the framework's role which impacts the sharing weight of resource allocation and optional authentication information to allow the framework to be connected to the master.
Author: Timothy Chen <tnachen@gmail.com>
Closes#4960 from tnachen/mesos_fw_auth and squashes the following commits:
0f9f03e [Timothy Chen] Fix review comments.
8f9488a [Timothy Chen] Fix rebase
f7fc2a9 [Timothy Chen] Add mesos role, auth and secret.
Example exception (new part at bottom, clearly demarcated):
```
org.apache.spark.SparkException: Job aborted due to stage failure: Task 0 in stage 0.0 failed 1 times, most recent failure: Lost task 0.0 in stage 0.0 (TID 0, localhost): java.lang.RuntimeException: uh-oh!
at org.apache.spark.scheduler.DAGSchedulerSuite$$anonfun$37$$anonfun$38$$anonfun$apply$mcJ$sp$2.apply(DAGSchedulerSuite.scala:880)
at org.apache.spark.scheduler.DAGSchedulerSuite$$anonfun$37$$anonfun$38$$anonfun$apply$mcJ$sp$2.apply(DAGSchedulerSuite.scala:880)
at scala.collection.Iterator$$anon$11.next(Iterator.scala:328)
at org.apache.spark.util.Utils$.getIteratorSize(Utils.scala:1640)
at org.apache.spark.rdd.RDD$$anonfun$count$1.apply(RDD.scala:1099)
at org.apache.spark.rdd.RDD$$anonfun$count$1.apply(RDD.scala:1099)
at org.apache.spark.SparkContext$$anonfun$runJob$5.apply(SparkContext.scala:1777)
at org.apache.spark.SparkContext$$anonfun$runJob$5.apply(SparkContext.scala:1777)
at org.apache.spark.scheduler.ResultTask.runTask(ResultTask.scala:63)
at org.apache.spark.scheduler.Task.run(Task.scala:70)
at org.apache.spark.executor.Executor$TaskRunner.run(Executor.scala:213)
at java.util.concurrent.ThreadPoolExecutor.runWorker(ThreadPoolExecutor.java:1145)
at java.util.concurrent.ThreadPoolExecutor$Worker.run(ThreadPoolExecutor.java:615)
at java.lang.Thread.run(Thread.java:744)
Driver stacktrace:
at org.apache.spark.scheduler.DAGScheduler.org$apache$spark$scheduler$DAGScheduler$$failJobAndIndependentStages(DAGScheduler.scala:1298)
at org.apache.spark.scheduler.DAGScheduler$$anonfun$abortStage$1.apply(DAGScheduler.scala:1289)
at org.apache.spark.scheduler.DAGScheduler$$anonfun$abortStage$1.apply(DAGScheduler.scala:1288)
at scala.collection.mutable.ResizableArray$class.foreach(ResizableArray.scala:59)
at scala.collection.mutable.ArrayBuffer.foreach(ArrayBuffer.scala:47)
at org.apache.spark.scheduler.DAGScheduler.abortStage(DAGScheduler.scala:1288)
at org.apache.spark.scheduler.DAGScheduler$$anonfun$handleTaskSetFailed$1.apply(DAGScheduler.scala:755)
at org.apache.spark.scheduler.DAGScheduler$$anonfun$handleTaskSetFailed$1.apply(DAGScheduler.scala:755)
at scala.Option.foreach(Option.scala:236)
at org.apache.spark.scheduler.DAGScheduler.handleTaskSetFailed(DAGScheduler.scala:755)
at org.apache.spark.scheduler.DAGSchedulerEventProcessLoop.doOnReceive(DAGScheduler.scala:1509)
at org.apache.spark.scheduler.DAGSchedulerEventProcessLoop.onReceive(DAGScheduler.scala:1470)
at org.apache.spark.scheduler.DAGSchedulerEventProcessLoop.onReceive(DAGScheduler.scala:1459)
at org.apache.spark.util.EventLoop$$anon$1.run(EventLoop.scala:48)
at org.apache.spark.scheduler.DAGScheduler.runJob(DAGScheduler.scala:560)
at org.apache.spark.SparkContext.runJob(SparkContext.scala:1744)
at org.apache.spark.SparkContext.runJob(SparkContext.scala:1762)
at org.apache.spark.SparkContext.runJob(SparkContext.scala:1777)
at org.apache.spark.SparkContext.runJob(SparkContext.scala:1791)
at org.apache.spark.rdd.RDD.count(RDD.scala:1099)
at org.apache.spark.scheduler.DAGSchedulerSuite$$anonfun$37$$anonfun$38.apply$mcJ$sp(DAGSchedulerSuite.scala:880)
at org.apache.spark.scheduler.DAGSchedulerSuite$$anonfun$37$$anonfun$38.apply(DAGSchedulerSuite.scala:880)
at org.apache.spark.scheduler.DAGSchedulerSuite$$anonfun$37$$anonfun$38.apply(DAGSchedulerSuite.scala:880)
at org.scalatest.Assertions$class.intercept(Assertions.scala:997)
at org.scalatest.FunSuite.intercept(FunSuite.scala:1555)
at org.apache.spark.scheduler.DAGSchedulerSuite$$anonfun$37.apply$mcV$sp(DAGSchedulerSuite.scala:879)
at org.apache.spark.scheduler.DAGSchedulerSuite$$anonfun$37.apply(DAGSchedulerSuite.scala:878)
at org.apache.spark.scheduler.DAGSchedulerSuite$$anonfun$37.apply(DAGSchedulerSuite.scala:878)
at org.scalatest.Transformer$$anonfun$apply$1.apply$mcV$sp(Transformer.scala:22)
at org.scalatest.OutcomeOf$class.outcomeOf(OutcomeOf.scala:85)
at org.scalatest.OutcomeOf$.outcomeOf(OutcomeOf.scala:104)
at org.scalatest.Transformer.apply(Transformer.scala:22)
at org.scalatest.Transformer.apply(Transformer.scala:20)
at org.scalatest.FunSuiteLike$$anon$1.apply(FunSuiteLike.scala:166)
at org.apache.spark.SparkFunSuite.withFixture(SparkFunSuite.scala:42)
at org.scalatest.FunSuiteLike$class.invokeWithFixture$1(FunSuiteLike.scala:163)
at org.scalatest.FunSuiteLike$$anonfun$runTest$1.apply(FunSuiteLike.scala:175)
at org.scalatest.FunSuiteLike$$anonfun$runTest$1.apply(FunSuiteLike.scala:175)
at org.scalatest.SuperEngine.runTestImpl(Engine.scala:306)
at org.scalatest.FunSuiteLike$class.runTest(FunSuiteLike.scala:175)
at org.apache.spark.scheduler.DAGSchedulerSuite.org$scalatest$BeforeAndAfter$$super$runTest(DAGSchedulerSuite.scala:70)
at org.scalatest.BeforeAndAfter$class.runTest(BeforeAndAfter.scala:200)
at org.apache.spark.scheduler.DAGSchedulerSuite.org$scalatest$BeforeAndAfterEach$$super$runTest(DAGSchedulerSuite.scala:70)
at org.scalatest.BeforeAndAfterEach$class.runTest(BeforeAndAfterEach.scala:255)
at org.apache.spark.scheduler.DAGSchedulerSuite.runTest(DAGSchedulerSuite.scala:70)
at org.scalatest.FunSuiteLike$$anonfun$runTests$1.apply(FunSuiteLike.scala:208)
at org.scalatest.FunSuiteLike$$anonfun$runTests$1.apply(FunSuiteLike.scala:208)
at org.scalatest.SuperEngine$$anonfun$traverseSubNodes$1$1.apply(Engine.scala:413)
at org.scalatest.SuperEngine$$anonfun$traverseSubNodes$1$1.apply(Engine.scala:401)
at scala.collection.immutable.List.foreach(List.scala:318)
at org.scalatest.SuperEngine.traverseSubNodes$1(Engine.scala:401)
at org.scalatest.SuperEngine.org$scalatest$SuperEngine$$runTestsInBranch(Engine.scala:396)
at org.scalatest.SuperEngine.runTestsImpl(Engine.scala:483)
at org.scalatest.FunSuiteLike$class.runTests(FunSuiteLike.scala:208)
at org.scalatest.FunSuite.runTests(FunSuite.scala:1555)
at org.scalatest.Suite$class.run(Suite.scala:1424)
at org.scalatest.FunSuite.org$scalatest$FunSuiteLike$$super$run(FunSuite.scala:1555)
at org.scalatest.FunSuiteLike$$anonfun$run$1.apply(FunSuiteLike.scala:212)
at org.scalatest.FunSuiteLike$$anonfun$run$1.apply(FunSuiteLike.scala:212)
at org.scalatest.SuperEngine.runImpl(Engine.scala:545)
at org.scalatest.FunSuiteLike$class.run(FunSuiteLike.scala:212)
at org.apache.spark.scheduler.DAGSchedulerSuite.org$scalatest$BeforeAndAfter$$super$run(DAGSchedulerSuite.scala:70)
at org.scalatest.BeforeAndAfter$class.run(BeforeAndAfter.scala:241)
at org.apache.spark.scheduler.DAGSchedulerSuite.org$scalatest$BeforeAndAfterAll$$super$run(DAGSchedulerSuite.scala:70)
at org.scalatest.BeforeAndAfterAll$class.liftedTree1$1(BeforeAndAfterAll.scala:257)
at org.scalatest.BeforeAndAfterAll$class.run(BeforeAndAfterAll.scala:256)
at org.apache.spark.scheduler.DAGSchedulerSuite.run(DAGSchedulerSuite.scala:70)
at org.scalatest.tools.Framework.org$scalatest$tools$Framework$$runSuite(Framework.scala:462)
at org.scalatest.tools.Framework$ScalaTestTask.execute(Framework.scala:671)
at sbt.ForkMain$Run$2.call(ForkMain.java:294)
at sbt.ForkMain$Run$2.call(ForkMain.java:284)
at java.util.concurrent.FutureTask.run(FutureTask.java:262)
at java.util.concurrent.ThreadPoolExecutor.runWorker(ThreadPoolExecutor.java:1145)
at java.util.concurrent.ThreadPoolExecutor$Worker.run(ThreadPoolExecutor.java:615)
at java.lang.Thread.run(Thread.java:744)
```
Author: Aaron Davidson <aaron@databricks.com>
Closes#7028 from aarondav/stack-trace and squashes the following commits:
4714664 [Aaron Davidson] [SPARK-8644] Include call site in SparkException stack traces thrown by job failures
Replace Akka Serialization with Spark Serializer and add unit tests.
Author: zsxwing <zsxwing@gmail.com>
Closes#7159 from zsxwing/remove-akka-serialization and squashes the following commits:
fc0fca3 [zsxwing] Merge branch 'master' into remove-akka-serialization
cf81a58 [zsxwing] Fix the code style
73251c6 [zsxwing] Add test scope
9ef4af9 [zsxwing] Add AkkaRpcEndpointRef.hashCode
433115c [zsxwing] Remove final
be3edb0 [zsxwing] Support deserializing RpcEndpointRef
ecec410 [zsxwing] Replace Akka Serialization with Spark Serializer
This pull request adds a Scalastyle regex rule which fails the style check if `Class.forName` is used directly. `Class.forName` always loads classes from the default / system classloader, but in a majority of cases, we should be using Spark's own `Utils.classForName` instead, which tries to load classes from the current thread's context classloader and falls back to the classloader which loaded Spark when the context classloader is not defined.
<!-- Reviewable:start -->
[<img src="https://reviewable.io/review_button.png" height=40 alt="Review on Reviewable"/>](https://reviewable.io/reviews/apache/spark/7350)
<!-- Reviewable:end -->
Author: Josh Rosen <joshrosen@databricks.com>
Closes#7350 from JoshRosen/ban-Class.forName and squashes the following commits:
e3e96f7 [Josh Rosen] Merge remote-tracking branch 'origin/master' into ban-Class.forName
c0b7885 [Josh Rosen] Hopefully fix the last two cases
d707ba7 [Josh Rosen] Fix uses of Class.forName that I missed in my first cleanup pass
046470d [Josh Rosen] Merge remote-tracking branch 'origin/master' into ban-Class.forName
62882ee [Josh Rosen] Fix uses of Class.forName or add exclusion.
d9abade [Josh Rosen] Add stylechecker rule to ban uses of Class.forName
Replace #6634
This PR adds `SparkListenerBlockUpdated` to SparkListener so that it can monitor all block update infos that are sent to `BlockManagerMasaterEndpoint`, and also add new tables in the Storage tab to display the stream block infos.
Author: zsxwing <zsxwing@gmail.com>
Closes#6672 from zsxwing/SPARK-4072-2 and squashes the following commits:
df2c1d8 [zsxwing] Use xml query to check the xml elements
54d54af [zsxwing] Add unit tests for StoragePage
e29fb53 [zsxwing] Update as per TD's comments
ccbee07 [zsxwing] Fix the code style
6dc42b4 [zsxwing] Fix the replication level of blocks
450fad1 [zsxwing] Merge branch 'master' into SPARK-4072-2
1e9ef52 [zsxwing] Don't categorize by Executor ID
ca0ab69 [zsxwing] Fix the code style
3de2762 [zsxwing] Make object BlockUpdatedInfo private
e95b594 [zsxwing] Add 'Aggregated Stream Block Metrics by Executor' table
ba5d0d1 [zsxwing] Refactor the unit test to improve the readability
4bbe341 [zsxwing] Revert JsonProtocol and don't log SparkListenerBlockUpdated
b464dd1 [zsxwing] Add onBlockUpdated to EventLoggingListener
5ba014c [zsxwing] Fix the code style
0b1e47b [zsxwing] Add a developer api BlockUpdatedInfo
04838a9 [zsxwing] Fix the code style
2baa161 [zsxwing] Add unit tests
80f6c6d [zsxwing] Address comments
797ee4b [zsxwing] Display Streaming blocks in Streaming UI
BlockObjectWriter has only one concrete non-test class, DiskBlockObjectWriter. In order to simplify the code in preparation for other refactorings, I think that we should remove this base class and have only DiskBlockObjectWriter.
While at one time we may have planned to have multiple BlockObjectWriter implementations, that doesn't seem to have happened, so the extra abstraction seems unnecessary.
Author: Josh Rosen <joshrosen@databricks.com>
Closes#7391 from JoshRosen/shuffle-write-interface-refactoring and squashes the following commits:
c418e33 [Josh Rosen] Fix compilation
5047995 [Josh Rosen] Fix comments
d5dc548 [Josh Rosen] Update references in comments
89dc797 [Josh Rosen] Rename test suite.
5755918 [Josh Rosen] Remove unnecessary val in case class
1607c91 [Josh Rosen] Merge BlockObjectWriter and DiskBlockObjectWriter
This PR enables SparkR to dynamically ship the SparkR binary package to the AM node in YARN cluster mode, thus it is no longer required that the SparkR package be installed on each worker node.
This PR uses the JDK jar tool to package the SparkR package, because jar is thought to be available on both Linux/Windows platforms where JDK has been installed.
This PR does not address the R worker involved in RDD API. Will address it in a separate JIRA issue.
This PR does not address SBT build. SparkR installation and packaging by SBT will be addressed in a separate JIRA issue.
R/install-dev.bat is not tested. shivaram , Could you help to test it?
Author: Sun Rui <rui.sun@intel.com>
Closes#6743 from sun-rui/SPARK-6797 and squashes the following commits:
ca63c86 [Sun Rui] Adjust MimaExcludes after rebase.
7313374 [Sun Rui] Fix unit test errors.
72695fb [Sun Rui] Fix unit test failures.
193882f [Sun Rui] Fix Mima test error.
fe25a33 [Sun Rui] Fix Mima test error.
35ecfa3 [Sun Rui] Fix comments.
c38a005 [Sun Rui] Unzipped SparkR binary package is still required for standalone and Mesos modes.
b05340c [Sun Rui] Fix scala style.
2ca5048 [Sun Rui] Fix comments.
1acefd1 [Sun Rui] Fix scala style.
0aa1e97 [Sun Rui] Fix scala style.
41d4f17 [Sun Rui] Add support for locating SparkR package for R workers required by RDD APIs.
49ff948 [Sun Rui] Invoke jar.exe with full path in install-dev.bat.
7b916c5 [Sun Rui] Use 'rem' consistently.
3bed438 [Sun Rui] Add a comment.
681afb0 [Sun Rui] Fix a bug that RRunner does not handle client deployment modes.
cedfbe2 [Sun Rui] [SPARK-6797][SPARKR] Add support for YARN cluster mode.
This patch adds a cache-friendly external sorter which operates on serialized bytes and uses this sorter to implement a new sort operator for Spark SQL and DataFrames.
### Overview of the new sorter
The new sorter design is inspired by [Alphasort](http://research.microsoft.com/pubs/68249/alphasort.doc) and implements a key-prefix optimization in order to improve the cache friendliness of the sort. In naive sort implementations, the sorting algorithm operates on an array of record pointers. To compare two records for ordering, the sorter must dereference these pointers, which likely involves random memory access, then compare the objects themselves.
In a key-prefix sort, the sort operates on an array which stores the record pointer alongside a prefix of the record's key. When comparing two records for ordering, the sorter first compares the the stored key prefixes. If the ordering can be determined from the key prefixes (i.e. the prefixes are unequal), then the sort can avoid directly comparing the records, avoiding random memory accesses and full record comparisons. For example, if we're sorting a list of strings then we can store the first 8 bytes of the UTF-8 encoded string as the key-prefix and can perform unsigned byte-at-a-time comparisons to determine the ordering of strings based on their prefixes, only resorting to full comparisons for strings that share a common prefix. In cases where the sort key can fit entirely in the space allotted for the key prefix (e.g. the sorting key is an integer), we completely avoid direct record comparison.
In this patch's implementation of key-prefix sorting, our sorter's internal array stores a 64-bit long and 64-bit pointer for each record being sorted. The key prefixes are generated by the user when inserting records into the sorter, which uses a user-defined comparison function for comparing them. The `PrefixComparators` object implements a set of comparators for many common types, including primitive numeric types and UTF-8 strings.
The actual sorting is implemented by `UnsafeInMemorySorter`. Most consumers will not use this directly, but instead will use `UnsafeExternalSorter`, a class which implements a sort that can spill to disk in response to memory pressure. Internally, `UnsafeExternalSorter` creates `UnsafeInMemorySorters` to perform sorting and uses `UnsafeSortSpillReader/Writer` to spill and read back runs of sorted records and `UnsafeSortSpillMerger` to merge multiple sorted spills into a single sorted iterator. This external sorter integrates with Spark's existing ShuffleMemoryManager for controlling spilling.
Many parts of this sorter's design are based on / copied from the more specialized external sort implementation that I designed for the new UnsafeShuffleManager write path; see #5868 for more details on that patch.
### Sorting rows in Spark SQL
For now, `UnsafeExternalSorter` is only used by Spark SQL, which uses it to implement a new sort operator, `UnsafeExternalSort`. This sort operator uses a SQL-specific class called `UnsafeExternalRowSorter` that configures an `UnsafeExternalSorter` to use prefix generators and comparators that operate on rows encoded in the UnsafeRow format that was designed for Project Tungsten.
I used some interesting unit-testing techniques to test this patch's SQL-specific components. `UnsafeExternalSortSuite` uses the SQL random data generators introduced in #7176 to test the UnsafeSort operator with all atomic types both with and without nullability and in both ascending and descending sort orders. `PrefixComparatorsSuite` contains a cool use of ScalaCheck + ScalaTest's `GeneratorDrivenPropertyChecks` in order to test UTF8String prefix comparison.
### Misc. additional improvements made in this patch
This patch made several miscellaneous improvements to related code in Spark SQL:
- The logic for selecting physical sort operator implementations, which was partially duplicated in both `Exchange` and `SparkStrategies, has now been consolidated into a `getSortOperator()` helper function in `SparkStrategies`.
- The `SparkPlanTest` unit testing helper trait has been extended with new methods for comparing the output produced by two different physical plans. This makes it easy to write tests which assert that two physical operator implementations should produce the same output. I also added a method for disabling the implicit sorting of outputs prior to comparing them, a change which is necessary in order to be able to write proper SparkPlan tests for sort operators.
### Tasks deferred to followup patches
While most of this patch's features are reasonably well-tested and complete, there are a number of tasks that are intentionally being deferred to followup patches:
- Add tests which mock the ShuffleMemoryManager to check that memory pressure properly triggers spilling (there are examples of this type of test in #5868).
- Add tests to ensure that spill files are properly cleaned up after errors. I'd like to do this in the context of a patch which introduces more general metrics for ensuring proper cleanup of tasks' temporary files; see https://issues.apache.org/jira/browse/SPARK-8966 for more details.
- Metrics integration: there are some open questions regarding how to track / report spill metrics for non-shuffle operations, so I've deferred most of the IO / shuffle metrics integration for now.
- Performance profiling.
<!-- Reviewable:start -->
[<img src="https://reviewable.io/review_button.png" height=40 alt="Review on Reviewable"/>](https://reviewable.io/reviews/apache/spark/6444)
<!-- Reviewable:end -->
Author: Josh Rosen <joshrosen@databricks.com>
Closes#6444 from JoshRosen/sql-external-sort and squashes the following commits:
6beb467 [Josh Rosen] Remove a bunch of overloaded methods to avoid default args. issue
2bbac9c [Josh Rosen] Merge remote-tracking branch 'origin/master' into sql-external-sort
35dad9f [Josh Rosen] Make sortAnswers = false the default in SparkPlanTest
5135200 [Josh Rosen] Fix spill reading for large rows; add test
2f48777 [Josh Rosen] Add test and fix bug for sorting empty arrays
d1e28bc [Josh Rosen] Merge remote-tracking branch 'origin/master' into sql-external-sort
cd05866 [Josh Rosen] Fix scalastyle
3947fc1 [Josh Rosen] Merge remote-tracking branch 'origin/master' into sql-external-sort
d13ac55 [Josh Rosen] Hacky approach to copying of UnsafeRows for sort followed by limit.
845bea3 [Josh Rosen] Remove unnecessary zeroing of row conversion buffer
c56ec18 [Josh Rosen] Clean up final row copying code.
d31f180 [Josh Rosen] Re-enable NullType sorting test now that SPARK-8868 is fixed
844f4ca [Josh Rosen] Merge remote-tracking branch 'origin/master' into sql-external-sort
293f109 [Josh Rosen] Add missing license header.
f99a612 [Josh Rosen] Fix bugs in string prefix comparison.
9d00afc [Josh Rosen] Clean up prefix comparators for integral types
88aff18 [Josh Rosen] NULL_PREFIX has to be negative infinity for floating point types
613e16f [Josh Rosen] Test with larger data.
1d7ffaa [Josh Rosen] Somewhat hacky fix for descending sorts
08701e7 [Josh Rosen] Fix prefix comparison of null primitives.
b86e684 [Josh Rosen] Set global = true in UnsafeExternalSortSuite.
1c7bad8 [Josh Rosen] Make sorting of answers explicit in SparkPlanTest.checkAnswer().
b81a920 [Josh Rosen] Temporarily enable only the passing sort tests
5d6109d [Josh Rosen] Fix inconsistent handling / encoding of record lengths.
87b6ed9 [Josh Rosen] Fix critical issues in test which led to false negatives.
8d7fbe7 [Josh Rosen] Fixes to multiple spilling-related bugs.
82e21c1 [Josh Rosen] Force spilling in UnsafeExternalSortSuite.
88b72db [Josh Rosen] Test ascending and descending sort orders.
f27be09 [Josh Rosen] Fix tests by binding attributes.
0a79d39 [Josh Rosen] Revert "Undo part of a SparkPlanTest change in #7162 that broke my test."
7c3c864 [Josh Rosen] Undo part of a SparkPlanTest change in #7162 that broke my test.
9969c14 [Josh Rosen] Merge remote-tracking branch 'origin/master' into sql-external-sort
5822e6f [Josh Rosen] Fix test compilation issue
939f824 [Josh Rosen] Remove code gen experiment.
0dfe919 [Josh Rosen] Implement prefix sort for strings (albeit inefficiently).
66a813e [Josh Rosen] Prefix comparators for float and double
b310c88 [Josh Rosen] Integrate prefix comparators for Int and Long (others coming soon)
95058d9 [Josh Rosen] Add missing SortPrefixUtils file
4c37ba6 [Josh Rosen] Add tests for sorting on all primitive types.
6890863 [Josh Rosen] Fix memory leak on empty inputs.
d246e29 [Josh Rosen] Fix consideration of column types when choosing sort implementation.
6b156fb [Josh Rosen] Some WIP work on prefix comparison.
7f875f9 [Josh Rosen] Commit failing test demonstrating bug in handling objects in spills
41b8881 [Josh Rosen] Get UnsafeInMemorySorterSuite to pass (WIP)
90c2b6a [Josh Rosen] Update test name
6d6a1e6 [Josh Rosen] Centralize logic for picking sort operator implementations
9869ec2 [Josh Rosen] Clean up Exchange code a bit
82bb0ec [Josh Rosen] Fix IntelliJ complaint due to negated if condition
1db845a [Josh Rosen] Many more changes to harmonize with shuffle sorter
ebf9eea [Josh Rosen] Harmonization with shuffle's unsafe sorter
206bfa2 [Josh Rosen] Add some missing newlines at the ends of files
26c8931 [Josh Rosen] Back out some Hive changes that aren't needed anymore
62f0bb8 [Josh Rosen] Update to reflect SparkPlanTest changes
21d7d93 [Josh Rosen] Back out of BlockObjectWriter change
7eafecf [Josh Rosen] Port test to SparkPlanTest
d468a88 [Josh Rosen] Update for InternalRow refactoring
269cf86 [Josh Rosen] Back out SMJ operator change; isolate changes to selection of sort op.
1b841ca [Josh Rosen] WIP towards copying
b420a71 [Josh Rosen] Move most of the existing SMJ code into Java.
dfdb93f [Josh Rosen] SparkFunSuite change
73cc761 [Josh Rosen] Fix whitespace
9cc98f5 [Josh Rosen] Move more code to Java; fix bugs in UnsafeRowConverter length type.
c8792de [Josh Rosen] Remove some debug logging
dda6752 [Josh Rosen] Commit some missing code from an old git stash.
58f36d0 [Josh Rosen] Merge in a sketch of a unit test for the new sorter (now failing).
2bd8c9a [Josh Rosen] Import my original tests and get them to pass.
d5d3106 [Josh Rosen] WIP towards external sorter for Spark SQL.
Author: Jonathan Alter <jonalter@users.noreply.github.com>
Closes#7093 from jonalter/SPARK-7977 and squashes the following commits:
ccd44cc [Jonathan Alter] Changed println to log in ThreadingSuite
7fcac3e [Jonathan Alter] Reverting to println in ThreadingSuite
10724b6 [Jonathan Alter] Changing some printlns to logs in tests
eeec1e7 [Jonathan Alter] Merge branch 'master' of github.com:apache/spark into SPARK-7977
0b1dcb4 [Jonathan Alter] More println cleanup
aedaf80 [Jonathan Alter] Merge branch 'master' of github.com:apache/spark into SPARK-7977
925fd98 [Jonathan Alter] Merge branch 'master' of github.com:apache/spark into SPARK-7977
0c16fa3 [Jonathan Alter] Replacing some printlns with logs
45c7e05 [Jonathan Alter] Merge branch 'master' of github.com:apache/spark into SPARK-7977
5c8e283 [Jonathan Alter] Allowing println in audit-release examples
5b50da1 [Jonathan Alter] Allowing printlns in example files
ca4b477 [Jonathan Alter] Merge branch 'master' of github.com:apache/spark into SPARK-7977
83ab635 [Jonathan Alter] Fixing new printlns
54b131f [Jonathan Alter] Merge branch 'master' of github.com:apache/spark into SPARK-7977
1cd8a81 [Jonathan Alter] Removing some unnecessary comments and printlns
b837c3a [Jonathan Alter] Disallowing println
This is largely based on extracting the dynamic allocation parts from tnachen's #3861.
Author: Iulian Dragos <jaguarul@gmail.com>
Closes#4984 from dragos/issue/mesos-coarse-dynamicAllocation and squashes the following commits:
39df8cd [Iulian Dragos] Update tests to latest changes in core.
9d2c9fa [Iulian Dragos] Remove adjustment of executorLimitOption in doKillExecutors.
8b00f52 [Iulian Dragos] Latest round of reviews.
0cd00e0 [Iulian Dragos] Add persistent shuffle directory
15c45c1 [Iulian Dragos] Add dynamic allocation to the Spark coarse-grained scheduler.
Currently, the mesos scheduler only looks at the 'cpu' and 'mem' resources when trying to determine the usablility of a resource offer from a mesos slave node. It may be preferable for the user to be able to ensure that the spark jobs are only started on a certain set of nodes (based on attributes).
For example, If the user sets a property, let's say `spark.mesos.constraints` is set to `tachyon=true;us-east-1=false`, then the resource offers will be checked to see if they meet both these constraints and only then will be accepted to start new executors.
Author: Ankur Chauhan <achauhan@brightcove.com>
Closes#5563 from ankurcha/mesos_attribs and squashes the following commits:
902535b [Ankur Chauhan] Fix line length
d83801c [Ankur Chauhan] Update code as per code review comments
8b73f2d [Ankur Chauhan] Fix imports
c3523e7 [Ankur Chauhan] Added docs
1a24d0b [Ankur Chauhan] Expand scope of attributes matching to include all data types
482fd71 [Ankur Chauhan] Update access modifier to private[this] for offer constraints
5ccc32d [Ankur Chauhan] Fix nit pick whitespace
1bce782 [Ankur Chauhan] Fix nit pick whitespace
c0cbc75 [Ankur Chauhan] Use offer id value for debug message
7fee0ea [Ankur Chauhan] Add debug statements
fc7eb5b [Ankur Chauhan] Fix import codestyle
00be252 [Ankur Chauhan] Style changes as per code review comments
662535f [Ankur Chauhan] Incorporate code review comments + use SparkFunSuite
fdc0937 [Ankur Chauhan] Decline offers that did not meet criteria
67b58a0 [Ankur Chauhan] Add documentation for spark.mesos.constraints
63f53f4 [Ankur Chauhan] Update codestyle - uniform style for config values
02031e4 [Ankur Chauhan] Fix scalastyle warnings in tests
c09ed84 [Ankur Chauhan] Fixed the access modifier on offerConstraints val to private[mesos]
0c64df6 [Ankur Chauhan] Rename overhead fractions to memory_*, fix spacing
8cc1e8f [Ankur Chauhan] Make exception message more explicit about the source of the error
addedba [Ankur Chauhan] Added test case for malformed constraint string
ec9d9a6 [Ankur Chauhan] Add tests for parse constraint string
72fe88a [Ankur Chauhan] Fix up tests + remove redundant method override, combine utility class into new mesos scheduler util trait
92b47fd [Ankur Chauhan] Add attributes based constraints support to MesosScheduler
Latest changes after refactoring to the RPC layer. I rebased against trunk to make sure to get any recent changes since it had been a while. I wasn't crazy about the name `ConfigureTimeout` and `RpcTimeout` seemed to fit better, but I'm open to suggestions!
I ran most of the tests and they pass, but others would get stuck with "WARN TaskSchedulerImpl: Initial job has not accepted any resources". I think its just my machine, so I'd though I would push what I have anyway.
Still left to do:
* I only added a couple unit tests so far, there are probably some more cases to test
* Make sure all uses require a `RpcTimeout`
* Right now, both the `ask` and `Await.result` use the same timeout, should we differentiate between these in the TimeoutException message?
* I wrapped `Await.result` in `RpcTimeout`, should we also wrap `Await.ready`?
* Proper scoping of classes and methods
hardmettle, feel free to help out with any of these!
Author: Bryan Cutler <bjcutler@us.ibm.com>
Author: Harsh Gupta <harsh@Harshs-MacBook-Pro.local>
Author: BryanCutler <cutlerb@gmail.com>
Closes#6205 from BryanCutler/configTimeout-6980 and squashes the following commits:
46c8d48 [Bryan Cutler] [SPARK-6980] Changed RpcEnvSuite test to never reply instead of just sleeping, to avoid possible sync issues
06afa53 [Bryan Cutler] [SPARK-6980] RpcTimeout class extends Serializable, was causing error in MasterSuite
7bb70f1 [Bryan Cutler] Merge branch 'master' into configTimeout-6980
dbd5f73 [Bryan Cutler] [SPARK-6980] Changed RpcUtils askRpcTimeout and lookupRpcTimeout scope to private[spark] and improved deprecation warning msg
4e89c75 [Bryan Cutler] [SPARK-6980] Missed one usage of deprecated RpcUtils.askTimeout in YarnSchedulerBackend although it is not being used, and fixed SparkConfSuite UT to not use deprecated RpcUtils functions
6a1c50d [Bryan Cutler] [SPARK-6980] Minor cleanup of test case
7f4d78e [Bryan Cutler] [SPARK-6980] Fixed scala style checks
287059a [Bryan Cutler] [SPARK-6980] Removed extra import in AkkaRpcEnvSuite
3d8b1ff [Bryan Cutler] [SPARK-6980] Cleaned up imports in AkkaRpcEnvSuite
3a168c7 [Bryan Cutler] [SPARK-6980] Rewrote Akka RpcTimeout UTs in RpcEnvSuite
7636189 [Bryan Cutler] [SPARK-6980] Fixed call to askWithReply in DAGScheduler to use RpcTimeout - this was being compiled by auto-tupling and changing the message type of BlockManagerHeartbeat
be11c4e [Bryan Cutler] Merge branch 'master' into configTimeout-6980
039afed [Bryan Cutler] [SPARK-6980] Corrected import organization
218aa50 [Bryan Cutler] [SPARK-6980] Corrected issues from feedback
fadaf6f [Bryan Cutler] [SPARK-6980] Put back in deprecated RpcUtils askTimeout and lookupTimout to fix MiMa errors
fa6ed82 [Bryan Cutler] [SPARK-6980] Had to increase timeout on positive test case because a processor slowdown could trigger an Future TimeoutException
b05d449 [Bryan Cutler] [SPARK-6980] Changed constructor to use val duration instead of getter function, changed name of string property from conf to timeoutProp for consistency
c6cfd33 [Bryan Cutler] [SPARK-6980] Changed UT ask message timeout to explicitly intercept a SparkException
1394de6 [Bryan Cutler] [SPARK-6980] Moved MessagePrefix to createRpcTimeoutException directly
1517721 [Bryan Cutler] [SPARK-6980] RpcTimeout object scope should be private[spark]
2206b4d [Bryan Cutler] [SPARK-6980] Added unit test for ask then immediat awaitReply
1b9beab [Bryan Cutler] [SPARK-6980] Cleaned up import ordering
08f5afc [Bryan Cutler] [SPARK-6980] Added UT for constructing RpcTimeout with default value
d3754d1 [Bryan Cutler] [SPARK-6980] Added akkaConf to prevent dead letter logging
995d196 [Bryan Cutler] [SPARK-6980] Cleaned up import ordering, comments, spacing from PR feedback
7774d56 [Bryan Cutler] [SPARK-6980] Cleaned up UT imports
4351c48 [Bryan Cutler] [SPARK-6980] Added UT for addMessageIfTimeout, cleaned up UTs
1607a5f [Bryan Cutler] [SPARK-6980] Changed addMessageIfTimeout to PartialFunction, cleanup from PR comments
2f94095 [Bryan Cutler] [SPARK-6980] Added addMessageIfTimeout for when a Future is completed with TimeoutException
235919b [Bryan Cutler] [SPARK-6980] Resolved conflicts after master merge
c07d05c [Bryan Cutler] Merge branch 'master' into configTimeout-6980-tmp
b7fb99f [BryanCutler] Merge pull request #2 from hardmettle/configTimeoutUpdates_6980
4be3a8d [Harsh Gupta] Modifying loop condition to find property match
0ee5642 [Harsh Gupta] Changing the loop condition to halt at the first match in the property list for RpcEnv exception catch
f74064d [Harsh Gupta] Retrieving properties from property list using iterator and while loop instead of chained functions
a294569 [Bryan Cutler] [SPARK-6980] Added creation of RpcTimeout with Seq of property keys
23d2f26 [Bryan Cutler] [SPARK-6980] Fixed await result not being handled by RpcTimeout
49f9f04 [Bryan Cutler] [SPARK-6980] Minor cleanup and scala style fix
5b59a44 [Bryan Cutler] [SPARK-6980] Added some RpcTimeout unit tests
78a2c0a [Bryan Cutler] [SPARK-6980] Using RpcTimeout.awaitResult for future in AppClient now
97523e0 [Bryan Cutler] [SPARK-6980] Akka ask timeout description refactored to RPC layer
