In thread 'stopped SparkContext remaining active' on mailing list, Andres observed the following in driver log:
```
15/07/29 15:17:09 WARN YarnSchedulerBackend$YarnSchedulerEndpoint: ApplicationMaster has disassociated: <address removed>
15/07/29 15:17:09 INFO YarnClientSchedulerBackend: Shutting down all executors
Exception in thread "Yarn application state monitor" org.apache.spark.SparkException: Error asking standalone scheduler to shut down executors
at org.apache.spark.scheduler.cluster.CoarseGrainedSchedulerBackend.stopExecutors(CoarseGrainedSchedulerBackend.scala:261)
at org.apache.spark.scheduler.cluster.CoarseGrainedSchedulerBackend.stop(CoarseGrainedSchedulerBackend.scala:266)
at org.apache.spark.scheduler.cluster.YarnClientSchedulerBackend.stop(YarnClientSchedulerBackend.scala:158)
at org.apache.spark.scheduler.TaskSchedulerImpl.stop(TaskSchedulerImpl.scala:416)
at org.apache.spark.scheduler.DAGScheduler.stop(DAGScheduler.scala:1411)
at org.apache.spark.SparkContext.stop(SparkContext.scala:1644)
at org.apache.spark.scheduler.cluster.YarnClientSchedulerBackend$$anon$1.run(YarnClientSchedulerBackend.scala:139)
Caused by: java.lang.InterruptedException
at java.util.concurrent.locks.AbstractQueuedSynchronizer.tryAcquireSharedNanos(AbstractQueuedSynchronizer.java:1325)
at scala.concurrent.impl.Promise$DefaultPromise.tryAwait(Promise.scala:208)
at scala.concurrent.impl.Promise$DefaultPromise.ready(Promise.scala:218)
at scala.concurrent.impl.Promise$DefaultPromise.result(Promise.scala:223)
at scala.concurrent.Await$$anonfun$result$1.apply(package.scala:190)
at scala.concurrent.BlockContext$DefaultBlockContext$.blockOn(BlockContext.scala:53)
at scala.concurrent.Await$.result(package.scala:190)15/07/29 15:17:09 INFO YarnClientSchedulerBackend: Asking each executor to shut down
at org.apache.spark.rpc.RpcEndpointRef.askWithRetry(RpcEndpointRef.scala:102)
at org.apache.spark.rpc.RpcEndpointRef.askWithRetry(RpcEndpointRef.scala:78)
at org.apache.spark.scheduler.cluster.CoarseGrainedSchedulerBackend.stopExecutors(CoarseGrainedSchedulerBackend.scala:257)
... 6 more
```
Effect of the above exception is that a stopped SparkContext is returned to user since SparkContext.clearActiveContext() is not called.
Author: tedyu <yuzhihong@gmail.com>
Closes#7756 from tedyu/master and squashes the following commits:
7339ff2 [tedyu] Move null assignment out of tryLogNonFatalError block
6e02cd9 [tedyu] Use Utils.tryLogNonFatalError to guard resource release
f5fb519 [tedyu] Clear Active SparkContext in stop() method using finally
`RpcEndpointRef.askWithRetry` throws `SparkException` rather than `TimeoutException`. Use ask to replace it because we don't need to retry here.
Author: zsxwing <zsxwing@gmail.com>
Closes#7824 from zsxwing/SPARK-9497 and squashes the following commits:
7bfc2b4 [zsxwing] Use ask instead of askWithRetry
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.
No new dependencies are added. The exclusion changes are due to the change in tachyon-client 0.7.0's project structure.
There is no client side API change in Tachyon 0.7.0 so no code changes are required.
Author: Calvin Jia <jia.calvin@gmail.com>
Closes#7577 from calvinjia/SPARK-9199 and squashes the following commits:
4e81e40 [Calvin Jia] Update Tachyon dependency from 0.6.4 -> 0.7.0
This patch improves SparkR error message reporting, especially with DataFrame API. When there is a user error (e.g., malformed SQL query), the message of the cause is sent back through the RPC and the R client reads it and returns it back to user.
cc shivaram
Author: Hossein <hossein@databricks.com>
Closes#7742 from falaki/SPARK-8742 and squashes the following commits:
4f643c9 [Hossein] Not logging exceptions in RBackendHandler
4a8005c [Hossein] Returning stack track of causing exception from RBackendHandler
5cf17f0 [Hossein] Adding unit test for error messages from SQLContext
2af75d5 [Hossein] Reading error message in case of failure and stoping with that message
f479c99 [Hossein] Wrting exception cause message in JVM
https://issues.apache.org/jira/browse/SPARK-9437
Author: Imran Rashid <irashid@cloudera.com>
Closes#7750 from squito/SPARK-9437_size_estimator_overflow and squashes the following commits:
29493f1 [Imran Rashid] prevent another potential overflow
bc1cb82 [Imran Rashid] avoid overflow
This pull request enables Unsafe mode by default in Spark SQL. In order to do this, we had to fix a number of small issues:
**List of fixed blockers**:
- [x] Make some default buffer sizes configurable so that HiveCompatibilitySuite can run properly (#7741).
- [x] Memory leak on grouped aggregation of empty input (fixed by #7560 to fix this)
- [x] Update planner to also check whether codegen is enabled before planning unsafe operators.
- [x] Investigate failing HiveThriftBinaryServerSuite test. This turns out to be caused by a ClassCastException that occurs when Exchange tries to apply an interpreted RowOrdering to an UnsafeRow when range partitioning an RDD. This could be fixed by #7408, but a shorter-term fix is to just skip the Unsafe exchange path when RangePartitioner is used.
- [x] Memory leak exceptions masking exceptions that actually caused tasks to fail (will be fixed by #7603).
- [x] ~~https://issues.apache.org/jira/browse/SPARK-9162, to implement code generation for ScalaUDF. This is necessary for `UDFSuite` to pass. For now, I've just ignored this test in order to try to find other problems while we wait for a fix.~~ This is no longer necessary as of #7682.
- [x] Memory leaks from Limit after UnsafeExternalSort cause the memory leak detector to fail tests. This is a huge problem in the HiveCompatibilitySuite (fixed by f4ac642a4e5b2a7931c5e04e086bb10e263b1db6).
- [x] Tests in `AggregationQuerySuite` are failing due to NaN-handling issues in UnsafeRow, which were fixed in #7736.
- [x] `org.apache.spark.sql.ColumnExpressionSuite.rand` needs to be updated so that the planner check also matches `TungstenProject`.
- [x] After having lowered the buffer sizes to 4MB so that most of HiveCompatibilitySuite runs:
- [x] Wrong answer in `join_1to1` (fixed by #7680)
- [x] Wrong answer in `join_nulls` (fixed by #7680)
- [x] Managed memory OOM / leak in `lateral_view`
- [x] Seems to hang indefinitely in `partcols1`. This might be a deadlock in script transformation or a bug in error-handling code? The hang was fixed by #7710.
- [x] Error while freeing memory in `partcols1`: will be fixed by #7734.
- [x] After fixing the `partcols1` hang, it appears that a number of later tests have issues as well.
- [x] Fix thread-safety bug in codegen fallback expression evaluation (#7759).
Author: Josh Rosen <joshrosen@databricks.com>
Closes#7564 from JoshRosen/unsafe-by-default and squashes the following commits:
83c0c56 [Josh Rosen] Merge remote-tracking branch 'origin/master' into unsafe-by-default
f4cc859 [Josh Rosen] Merge remote-tracking branch 'origin/master' into unsafe-by-default
963f567 [Josh Rosen] Reduce buffer size for R tests
d6986de [Josh Rosen] Lower page size in PySpark tests
013b9da [Josh Rosen] Also match TungstenProject in checkNumProjects
5d0b2d3 [Josh Rosen] Add task completion callback to avoid leak in limit after sort
ea250da [Josh Rosen] Disable unsafe Exchange path when RangePartitioning is used
715517b [Josh Rosen] Enable Unsafe by default
This change adds code to notify the scheduler backend when a container dies in YARN.
Author: Mridul Muralidharan <mridulm@yahoo-inc.com>
Author: Marcelo Vanzin <vanzin@cloudera.com>
Closes#7431 from vanzin/SPARK-8297 and squashes the following commits:
471e4a0 [Marcelo Vanzin] Fix unit test after merge.
d4adf4e [Marcelo Vanzin] Merge branch 'master' into SPARK-8297
3b262e8 [Marcelo Vanzin] Merge branch 'master' into SPARK-8297
537da6f [Marcelo Vanzin] Make an expected log less scary.
04dc112 [Marcelo Vanzin] Use driver <-> AM communication to send "remove executor" request.
8855b97 [Marcelo Vanzin] Merge remote-tracking branch 'mridul/fix_yarn_scheduler_bug' into SPARK-8297
687790f [Mridul Muralidharan] Merge branch 'fix_yarn_scheduler_bug' of github.com:mridulm/spark into fix_yarn_scheduler_bug
e1b0067 [Mridul Muralidharan] Fix failing testcase, fix merge issue from our 1.3 -> master
9218fcc [Mridul Muralidharan] Fix failing testcase
362d64a [Mridul Muralidharan] Merge branch 'fix_yarn_scheduler_bug' of github.com:mridulm/spark into fix_yarn_scheduler_bug
62ad0cc [Mridul Muralidharan] Merge branch 'fix_yarn_scheduler_bug' of github.com:mridulm/spark into fix_yarn_scheduler_bug
bbf8811 [Mridul Muralidharan] Merge branch 'fix_yarn_scheduler_bug' of github.com:mridulm/spark into fix_yarn_scheduler_bug
9ee1307 [Mridul Muralidharan] Fix SPARK-8297
a3a0f01 [Mridul Muralidharan] Fix SPARK-8297
cc srowen
Author: François Garillot <francois@garillot.net>
Closes#7678 from huitseeker/master and squashes the following commits:
5e99f57 [François Garillot] [SPARK-9267][Core] Retire stringify(Partial)?Value from Accumulators
Users can now get the file name of the partition being read in. A thread local variable is in `SQLNewHadoopRDD` and is set when the partition is computed. `SQLNewHadoopRDD` is moved to core so that the catalyst package can reach it.
This supports:
`df.select(inputFileName())`
and
`sqlContext.sql("select input_file_name() from table")`
Author: Joseph Batchik <josephbatchik@gmail.com>
Closes#7743 from JDrit/input_file_name and squashes the following commits:
abb8609 [Joseph Batchik] fixed failing test and changed the default value to be an empty string
d2f323d [Joseph Batchik] updates per review
102061f [Joseph Batchik] updates per review
75313f5 [Joseph Batchik] small fixes
c7f7b5a [Joseph Batchik] addeding input file name to Spark SQL
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
Author: Ryan Williams <ryan.blake.williams@gmail.com>
Closes#7681 from ryan-williams/task-stage-attempt and squashes the following commits:
d6d5f0f [Ryan Williams] use task's stageAttemptId in TaskEnd event
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
A lock file is used to ensure multiple executors running on the
same machine don't download the same file concurrently. Spark never
closes these lock files (releasing the lock does not close the
underlying file); this commit fixes that.
cc vanzin (looks like you've been involved in various other fixes surrounding these lock files)
Author: Kay Ousterhout <kayousterhout@gmail.com>
Closes#7650 from kayousterhout/SPARK-9326 and squashes the following commits:
0401bd1 [Kay Ousterhout] Close lock file used for file downloads.
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
Current scheduling algorithm allocates one core at a time and in doing so ends up ignoring spark.executor.cores. As a result, when spark.cores.max/spark.executor.cores (i.e, num_executors) < num_workers, executors are not launched and the app hangs. This PR fixes and refactors the scheduling algorithm.
andrewor14
Author: Nishkam Ravi <nravi@cloudera.com>
Author: nishkamravi2 <nishkamravi@gmail.com>
Closes#7274 from nishkamravi2/master_scheduler and squashes the following commits:
b998097 [nishkamravi2] Update Master.scala
da0f491 [Nishkam Ravi] Update Master.scala
79084e8 [Nishkam Ravi] Update Master.scala
1daf25f [Nishkam Ravi] Update Master.scala
f279cdf [Nishkam Ravi] Update Master.scala
adec84b [Nishkam Ravi] Update Master.scala
a06da76 [nishkamravi2] Update Master.scala
40c8f9f [nishkamravi2] Update Master.scala (to trigger retest)
c11c689 [nishkamravi2] Update EventLoggingListenerSuite.scala
5d6a19c [nishkamravi2] Update Master.scala (for the purpose of issuing a retest)
2d6371c [Nishkam Ravi] Update Master.scala
66362d5 [nishkamravi2] Update Master.scala
ee7cf0e [Nishkam Ravi] Improved scheduling algorithm for executors
JIRA: https://issues.apache.org/jira/browse/SPARK-9067
According to the description of the JIRA ticket, calling `reader.close()` only after the task is finished will cause memory and file open limit problem since these resources are occupied even we don't need that anymore.
This PR simply closes the reader early when we know there is no more data to read.
Author: Liang-Chi Hsieh <viirya@appier.com>
Closes#7424 from viirya/close_reader and squashes the following commits:
3ff64e5 [Liang-Chi Hsieh] For comments.
3d20267 [Liang-Chi Hsieh] Merge remote-tracking branch 'upstream/master' into close_reader
e152182 [Liang-Chi Hsieh] For comments.
5116cbe [Liang-Chi Hsieh] Merge remote-tracking branch 'upstream/master' into close_reader
3ceb755 [Liang-Chi Hsieh] For comments.
e34d98e [Liang-Chi Hsieh] For comments.
50ed729 [Liang-Chi Hsieh] Merge remote-tracking branch 'upstream/master' into close_reader
216912f [Liang-Chi Hsieh] Fix it.
f429016 [Liang-Chi Hsieh] Release reader if we don't need it.
a305621 [Liang-Chi Hsieh] Merge remote-tracking branch 'upstream/master' into close_reader
67569da [Liang-Chi Hsieh] Close reader early if there is no more data.
Doing this may cause weird errors when tests are run on maven, depending
on the flags used. Instead, expose the needed functionality through methods
that do not expose shaded classes.
Author: Marcelo Vanzin <vanzin@cloudera.com>
Closes#7601 from vanzin/SPARK-9261 and squashes the following commits:
4f64a16 [Marcelo Vanzin] [SPARK-9261] [streaming] Avoid calling APIs that expose shaded classes.
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
JIRA: https://issues.apache.org/jira/browse/SPARK-9183
cc rxin
Author: Yijie Shen <henry.yijieshen@gmail.com>
Closes#7613 from yjshen/npe_udf and squashes the following commits:
44f58f2 [Yijie Shen] add jira ticket number
903c963 [Yijie Shen] add explanation comments
f44dd3c [Yijie Shen] Change two hive class LogLevel to avoid annoying messages
1. When build the latest code with sbt, it throws exception like:
[error] /home/hcheng/git/catalyst/core/src/main/scala/org/apache/spark/ui/jobs/AllJobsPage.scala:78: match may not be exhaustive.
[error] It would fail on the following input: UNKNOWN
[error] val classNameByStatus = status match {
[error]
2. Potential performance issue when implicitly convert an Array[Any] to Seq[Any]
Author: Cheng Hao <hao.cheng@intel.com>
Closes#7611 from chenghao-intel/toseq and squashes the following commits:
cab75c5 [Cheng Hao] remove the toArray
24df682 [Cheng Hao] fix building error & performance
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
Author: Perinkulam I. Ganesh <gip@us.ibm.com>
Closes#7397 from piganesh/SPARK-8695 and squashes the following commits:
041620c [Perinkulam I. Ganesh] [SPARK-8695][CORE][MLlib] TreeAggregation shouldn't be triggered when it doesn't save wall-clock time.
9ad067c [Perinkulam I. Ganesh] [SPARK-8695] [core] [WIP] TreeAggregation shouldn't be triggered for 5 partitions
a6fed07 [Perinkulam I. Ganesh] [SPARK-8695] [core] [WIP] TreeAggregation shouldn't be triggered for 5 partitions
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
I've seen a few cases in the past few weeks that the compiler is throwing warnings that are caused by legitimate bugs. This patch upgrades warnings to errors, except deprecation warnings.
Note that ideally we should be able to mark deprecation warnings as errors as well. However, due to the lack of ability to suppress individual warning messages in the Scala compiler, we cannot do that (since we do need to access deprecated APIs in Hadoop).
Most of the work are done by ericl.
Author: Reynold Xin <rxin@databricks.com>
Author: Eric Liang <ekl@databricks.com>
Closes#7598 from rxin/warnings and squashes the following commits:
beb311b [Reynold Xin] Fixed tests.
542c031 [Reynold Xin] Fixed one more warning.
87c354a [Reynold Xin] Fixed all non-deprecation warnings.
78660ac [Eric Liang] first effort to fix warnings
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
Make `DiskMapIterator.cleanup` idempotent and register a TaskCompletionListener to make sure call `cleanup`.
Author: zsxwing <zsxwing@gmail.com>
Closes#7529 from zsxwing/SPARK-5423 and squashes the following commits:
3e3c413 [zsxwing] Remove TODO
9556c78 [zsxwing] Fix NullPointerException for tests
3d574d9 [zsxwing] Register a TaskCompletionListener to make sure release all resources
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
Now, when some executors are killed by dynamic-allocation, it leads to some mis-assignment onto lost executors sometimes. Such kind of mis-assignment causes task failure(s) or even job failure if it repeats that errors for 4 times.
The root cause is that ***killExecutors*** doesn't remove those executors under killing ASAP. It depends on the ***OnDisassociated*** event to refresh the active working list later. The delay time really depends on your cluster status (from several milliseconds to sub-minute). When new tasks to be scheduled during that period of time, it will be assigned to those "active" but "under killing" executors. Then the tasks will be failed due to "executor lost". The better way is to exclude those executors under killing in the makeOffers(). Then all those tasks won't be allocated onto those executors "to be lost" any more.
Author: Grace <jie.huang@intel.com>
Closes#7528 from GraceH/AssignToLostExecutor and squashes the following commits:
ecc1da6 [Grace] scala style fix
6e2ed96 [Grace] Re-word makeOffers by more readable lines
b5546ce [Grace] Add comments about the fix
30a9ad0 [Grace] Avoid assigning tasks to lost executors
These commits address a few minor issues in the Scala cross-version support in the build:
1. Correct two missing `${scala.binary.version}` pom file substitutions.
2. Don't update `scala.binary.version` in parent POM. This property is set through profiles.
3. Update the source of the generated scaladocs in `docs/_plugins/copy_api_dirs.rb`.
4. Factor common code out of `dev/change-version-to-*.sh` and add some validation. We also test `sed` to see if it's GNU sed and try `gsed` as an alternative if not. This prevents the script from running with a non-GNU sed.
This is my original work and I license this work to the Spark project under the Apache License.
Author: Michael Allman <michael@videoamp.com>
Closes#6832 from mallman/scala-versions and squashes the following commits:
cde2f17 [Michael Allman] Delete dev/change-version-to-*.sh, replacing them with single dev/change-scala-version.sh script that takes a version as argument
02296f2 [Michael Allman] Make the scala version change scripts cross-platform by restricting ourselves to POSIX sed syntax instead of looking for GNU sed
ad9b40a [Michael Allman] Factor change-scala-version.sh out of change-version-to-*.sh, adding command line argument validation and testing for GNU sed
bdd20bf [Michael Allman] Update source of scaladocs when changing Scala version
475088e [Michael Allman] Replace jackson-module-scala_2.10 with jackson-module-scala_${scala.binary.version}
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.
For running tasks, the executorRunTime metrics is 0 which causes negative executorComputingTime in the timeline. It also causes an incorrect SchedulerDelay time.
Author: Carson Wang <carson.wang@intel.com>
Closes#7526 from carsonwang/timeline-negValue and squashes the following commits:
7b17db2 [Carson Wang] Fix negative value in timeline view
This PR tries to accelerate Parquet schema discovery and `HadoopFsRelation` partition discovery. The acceleration is done by the following means:
- Turning off schema merging by default
Schema merging is not the most common case, but requires reading footers of all Parquet part-files and can be very slow.
- Avoiding `FileSystem.globStatus()` call when possible
`FileSystem.globStatus()` may issue multiple synchronous RPC calls, and can be very slow (esp. on S3). This PR adds `SparkHadoopUtil.globPathIfNecessary()`, which only issues RPC calls when the path contain glob-pattern specific character(s) (`{}[]*?\`).
This is especially useful when converting a metastore Parquet table with lots of partitions, since Spark SQL adds all partition directories as the input paths, and currently we do a `globStatus` call on each input path sequentially.
- Listing leaf files in parallel when the number of input paths exceeds a threshold
Listing leaf files is required by partition discovery. Currently it is done on driver side, and can be slow when there are lots of (nested) directories, since each `FileSystem.listStatus()` call issues an RPC. In this PR, we list leaf files in a BFS style, and resort to a Spark job once we found that the number of directories need to be listed exceed a threshold.
The threshold is controlled by `SQLConf` option `spark.sql.sources.parallelPartitionDiscovery.threshold`, which defaults to 32.
- Discovering Parquet schema in parallel
Currently, schema merging is also done on driver side, and needs to read footers of all part-files. This PR uses a Spark job to do schema merging. Together with task side metadata reading in Parquet 1.7.0, we never read any footers on driver side now.
Author: Cheng Lian <lian@databricks.com>
Closes#7396 from liancheng/accel-parquet and squashes the following commits:
5598efc [Cheng Lian] Uses ParquetInputFormat[InternalRow] instead of ParquetInputFormat[Row]
ff32cd0 [Cheng Lian] Excludes directories while listing leaf files
3c580f1 [Cheng Lian] Fixes test failure caused by making "mergeSchema" default to "false"
b1646aa [Cheng Lian] Should allow empty input paths
32e5f0d [Cheng Lian] Moves schema merging to executor side
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
Author: Wenchen Fan <cloud0fan@outlook.com>
Closes#7496 from cloud-fan/tests and squashes the following commits:
0958f90 [Wenchen Fan] improve test for nondeterministic expressions
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
In client side, the flow is SparkSubmit -> SparkContext -> yarn/Client. Since the yarn client only gets a cloned config and the staging dir is set here, it is not really possible to do re-logins in the SparkContext. So, do the initial logins in Spark Submit and do re-logins as we do now in the AM, but the Client behaves like an executor in this specific context and reads the credentials file to update the tokens. This way, even if the streaming context is started up from checkpoint - it is fine since we have logged in from SparkSubmit itself itself.
Author: Hari Shreedharan <hshreedharan@apache.org>
Closes#7394 from harishreedharan/yarn-client-login and squashes the following commits:
9a2166f [Hari Shreedharan] make it possible to use command line args and config parameters together.
de08f57 [Hari Shreedharan] Fix import order.
5c4fa63 [Hari Shreedharan] Add a comment explaining what is being done in YarnClientSchedulerBackend.
c872caa [Hari Shreedharan] Fix typo in log message.
2c80540 [Hari Shreedharan] Move token renewal to YarnClientSchedulerBackend.
0c48ac2 [Hari Shreedharan] Remove direct use of ExecutorDelegationTokenUpdater in Client.
26f8bfa [Hari Shreedharan] [SPARK-8851][YARN] In Client mode, make sure the client logs in and updates tokens.
58b1969 [Hari Shreedharan] Simple attempt 1.
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
