Previously I had tried to solve this with by adding a line in Spark's log4j-defaults.properties.
The issue with the message in log4j-defaults.properties was that the log4j.properties packaged inside Hadoop was getting picked up instead. While it would be ideal to fix that as well, we still want to quiet this in situations where a user supplies their own custom log4j properties.
Author: Sandy Ryza <sandy@cloudera.com>
Closes#4192 from sryza/sandy-spark-5393 and squashes the following commits:
4d5dedc [Sandy Ryza] Only set log level if unset
46e07c5 [Sandy Ryza] SPARK-5393. Flood of util.RackResolver log messages after SPARK-1714
We have seen many use cases of `treeAggregate`/`treeReduce` outside the ML domain. Maybe it is time to move them to Core. pwendell
Author: Xiangrui Meng <meng@databricks.com>
Closes#4228 from mengxr/SPARK-5430 and squashes the following commits:
20ad40d [Xiangrui Meng] exclude tree* from mima
e89a43e [Xiangrui Meng] fix compile and update java doc
3ae1a4b [Xiangrui Meng] add treeReduce/treeAggregate to Python
6f948c5 [Xiangrui Meng] add treeReduce/treeAggregate to JavaRDDLike
d600b6c [Xiangrui Meng] move treeReduce and treeAggregate to core
SerDeUtil.pairRDDToPython and SerDeUtil.pythonToPairRDD now both support empty RDDs by checking the result of take(1) instead of calling first which throws an exception.
Author: Michael Nazario <mnazario@palantir.com>
Closes#4236 from mnazario/feature/empty-first and squashes the following commits:
a531c0c [Michael Nazario] Added regression tests for SPARK-5441
e3b2fb6 [Michael Nazario] Added acceptance of the empty case
In DriverSuite, we currently set a timeout of 60 seconds. If after this time the process has not terminated, we leak the process because we never destroy it.
In SparkSubmitSuite, we currently do not have a timeout so the test can hang indefinitely.
Author: Andrew Or <andrew@databricks.com>
Closes#4230 from andrewor14/fix-driver-suite and squashes the following commits:
f5c80fd [Andrew Or] Fix timeout behaviors in both suites
8092c36 [Andrew Or] Stop SparkContext after every individual test
Recently `SparkListenerExecutorAdded` and `SparkListenerExecutorRemoved` are added.
I think it's useful if they have timestamp and the reason why an executor is removed.
Author: Kousuke Saruta <sarutak@oss.nttdata.co.jp>
Closes#4082 from sarutak/SPARK-5291 and squashes the following commits:
a026ff2 [Kousuke Saruta] Merge branch 'master' of git://git.apache.org/spark into SPARK-5291
979dfe1 [Kousuke Saruta] Merge branch 'master' of git://git.apache.org/spark into SPARK-5291
cf9f9080 [Kousuke Saruta] Fixed test case
1f2a89b [Kousuke Saruta] Merge branch 'master' of git://git.apache.org/spark into SPARK-5291
243f2a60 [Kousuke Saruta] Modified MesosSchedulerBackendSuite
a527c35 [Kousuke Saruta] Added timestamp to SparkListenerExecutorAdded
...mbineFileSplits
Author: Sandy Ryza <sandy@cloudera.com>
Closes#4050 from sryza/sandy-spark-5199 and squashes the following commits:
864514b [Sandy Ryza] Add tests and fix bug
0d504f1 [Sandy Ryza] Prettify
915c7e6 [Sandy Ryza] Get metrics from all filesystems
cdbc3e8 [Sandy Ryza] SPARK-5199. Input metrics should show up for InputFormats that return CombineFileSplits
This reenables and fixes this test, after addressing two issues:
- The Semaphore that was intended to be shared locally was being serialized and copied; it's now a static member in the companion object as in other tests
- Later changes to Spark means that cancelling the first task will not cancel the shared stage and therefore the second task should succeed
Author: Sean Owen <sowen@cloudera.com>
Closes#4180 from srowen/SPARK-960 and squashes the following commits:
43da66f [Sean Owen] Fix 'two jobs sharing the same stage' test and reenable it: truly share a Semaphore locally as intended, and update expectation of failure in non-cancelled task
j.u.c.ConcurrentHashMap is more battle tested.
cc rxin JoshRosen pwendell
Author: Davies Liu <davies@databricks.com>
Closes#4208 from davies/safe-conf and squashes the following commits:
c2182dc [Davies Liu] address comments, fix tests
3a1d821 [Davies Liu] fix test
da14ced [Davies Liu] Merge branch 'master' of github.com:apache/spark into safe-conf
ae4d305 [Davies Liu] change to j.u.c.ConcurrentMap
f8fa1cf [Davies Liu] change to TrieMap
a1d769a [Davies Liu] make SparkConf thread-safe
`FsHistoryProvider` tries to update application status but if `checkForLogs` is called before `.inprogress` file is renamed to completed file, the file is not recognized as completed.
Author: Kousuke Saruta <sarutak@oss.nttdata.co.jp>
Closes#4132 from sarutak/SPARK-5344 and squashes the following commits:
9658008 [Kousuke Saruta] Merge branch 'master' of git://git.apache.org/spark into SPARK-5344
d2c72b6 [Kousuke Saruta] Fixed update issue of FsHistoryProvider
Author: zsxwing <zsxwing@gmail.com>
Closes#4174 from zsxwing/SPARK-5214-unittest and squashes the following commits:
443e564 [zsxwing] Change the check interval to 5ms
7aaa2d7 [zsxwing] Add a test to demonstrate EventLoop can be stopped in the event thread
This patch adds more helpful error messages for invalid programs that define nested RDDs, broadcast RDDs, perform actions inside of transformations (e.g. calling `count()` from inside of `map()`), and call certain methods on stopped SparkContexts. Currently, these invalid programs lead to confusing NullPointerExceptions at runtime and have been a major source of questions on the mailing list and StackOverflow.
In a few cases, I chose to log warnings instead of throwing exceptions in order to avoid any chance that this patch breaks programs that worked "by accident" in earlier Spark releases (e.g. programs that define nested RDDs but never run any jobs with them).
In SparkContext, the new `assertNotStopped()` method is used to check whether methods are being invoked on a stopped SparkContext. In some cases, user programs will not crash in spite of calling methods on stopped SparkContexts, so I've only added `assertNotStopped()` calls to methods that always throw exceptions when called on stopped contexts (e.g. by dereferencing a null `dagScheduler` pointer).
Author: Josh Rosen <joshrosen@databricks.com>
Closes#3884 from JoshRosen/SPARK-5063 and squashes the following commits:
a38774b [Josh Rosen] Fix spelling typo
a943e00 [Josh Rosen] Convert two exceptions into warnings in order to avoid breaking user programs in some edge-cases.
2d0d7f7 [Josh Rosen] Fix test to reflect 1.2.1 compatibility
3f0ea0c [Josh Rosen] Revert two unintentional formatting changes
8e5da69 [Josh Rosen] Remove assertNotStopped() calls for methods that were sometimes safe to call on stopped SC's in Spark 1.2
8cff41a [Josh Rosen] IllegalStateException fix
6ef68d0 [Josh Rosen] Fix Python line length issues.
9f6a0b8 [Josh Rosen] Add improved error messages to PySpark.
13afd0f [Josh Rosen] SparkException -> IllegalStateException
8d404f3 [Josh Rosen] Merge remote-tracking branch 'origin/master' into SPARK-5063
b39e041 [Josh Rosen] Fix BroadcastSuite test which broadcasted an RDD
99cc09f [Josh Rosen] Guard against calling methods on stopped SparkContexts.
34833e8 [Josh Rosen] Add more descriptive error message.
57cc8a1 [Josh Rosen] Add error message when directly broadcasting RDD.
15b2e6b [Josh Rosen] [SPARK-5063] Useful error messages for nested RDDs and actions inside of transformations
Pretty minor, but submitted for consideration -- this would at least help people make this check in the most efficient way I know.
Author: Sean Owen <sowen@cloudera.com>
Closes#4074 from srowen/SPARK-5270 and squashes the following commits:
66885b8 [Sean Owen] Add note that JavaRDDLike should not be implemented by user code
2e9b490 [Sean Owen] More tests, and Mima-exclude the new isEmpty method in JavaRDDLike
28395ff [Sean Owen] Add isEmpty to Java, Python
7dd04b7 [Sean Owen] Add efficient RDD.isEmpty()
This PR adds a simple `EventLoop` and use it to replace Actor in DAGScheduler. `EventLoop` is a general class to support that posting events in multiple threads and handling events in a single event thread.
Author: zsxwing <zsxwing@gmail.com>
Closes#4016 from zsxwing/event-loop and squashes the following commits:
aefa1ce [zsxwing] Add protected to on*** methods
5cfac83 [zsxwing] Remove null check of eventProcessLoop
dba35b2 [zsxwing] Add a test that onReceive swallows InterruptException
460f7b3 [zsxwing] Use volatile instead of Atomic things in unit tests
227bf33 [zsxwing] Add a stop flag and some tests
37f79c6 [zsxwing] Fix docs
55fb6f6 [zsxwing] Add private[spark] to EventLoop
1f73eac [zsxwing] Fix the import order
3b2e59c [zsxwing] Add EventLoop and change DAGScheduler to an EventLoop
Author: Jongyoul Lee <jongyoul@gmail.com>
Closes#3897 from jongyoul/SPARK-5088 and squashes the following commits:
8232aa8 [Jongyoul Lee] [SPARK-5088] Use spark-class for running executors directly - Added a listenerBus for fixing test cases
932289f [Jongyoul Lee] [SPARK-5088] Use spark-class for running executors directly - Rebased from master
613cb47 [Jongyoul Lee] [SPARK-5088] Use spark-class for running executors directly - Fixed code if spark.executor.uri doesn't have any value - Added test cases
ff57bda [Jongyoul Lee] [SPARK-5088] Use spark-class for running executors directly - Adjusted orders of import
97e4bd4 [Jongyoul Lee] [SPARK-5088] Use spark-class for running executors directly - Changed command for using spark-class directly - Delete sbin/spark-executor and moved some codes into spark-class' case statement
I've updated the fields and all usages of these fields in the Spark code. I've verified that this did not break anything on my local repo.
Author: Ilya Ganelin <ilya.ganelin@capitalone.com>
Closes#4020 from ilganeli/SPARK-3288 and squashes the following commits:
39f3810 [Ilya Ganelin] resolved merge issues
e446287 [Ilya Ganelin] Merge remote-tracking branch 'upstream/master' into SPARK-3288
b8c05cb [Ilya Ganelin] Missed making a variable private
6444391 [Ilya Ganelin] Made inc/dec functions private[spark]
1149e78 [Ilya Ganelin] Merge remote-tracking branch 'upstream/master' into SPARK-3288
26b312b [Ilya Ganelin] Debugging tests
17146c2 [Ilya Ganelin] Merge remote-tracking branch 'upstream/master' into SPARK-3288
5525c20 [Ilya Ganelin] Completed refactoring to make vars in TaskMetrics class private
c64da4f [Ilya Ganelin] Partially updated task metrics to make some vars private
History Server doesn't show collect job submission time.
It's because `JobProgressListener` updates job submission time every time `onJobStart` method is invoked from `ReplayListenerBus`.
Author: Kousuke Saruta <sarutak@oss.nttdata.co.jp>
Closes#4029 from sarutak/SPARK-5231 and squashes the following commits:
0af9e22 [Kousuke Saruta] Merge branch 'master' of git://git.apache.org/spark into SPARK-5231
da8bd14 [Kousuke Saruta] Made submissionTime in SparkListenerJobStartas and completionTime in SparkListenerJobEnd as regular Long
0412a6a [Kousuke Saruta] Merge branch 'master' of git://git.apache.org/spark into SPARK-5231
26b9b99 [Kousuke Saruta] Fixed the test cases
2d47bd3 [Kousuke Saruta] Fixed to record job submission time and completion time collectly
There is an int overflow in the ParallelCollectionRDD.slice method. That's originally reported by SaintBacchus.
```
sc.makeRDD(1 to (Int.MaxValue)).count // result = 0
sc.makeRDD(1 to (Int.MaxValue - 1)).count // result = 2147483646 = Int.MaxValue - 1
sc.makeRDD(1 until (Int.MaxValue)).count // result = 2147483646 = Int.MaxValue - 1
```
see https://github.com/apache/spark/pull/2874 for more details.
This pr try to fix the overflow. However, There's another issue I don't address.
```
val largeRange = Int.MinValue to Int.MaxValue
largeRange.length // throws java.lang.IllegalArgumentException: -2147483648 to 2147483647 by 1: seqs cannot contain more than Int.MaxValue elements.
```
So, the range we feed to sc.makeRDD cannot contain more than Int.MaxValue elements. This is the limitation of Scala. However I think we may want to support that kind of range. But the fix is beyond this pr.
srowen andrewor14 would you mind take a look at this pr?
Author: Ye Xianjin <advancedxy@gmail.com>
Closes#4002 from advancedxy/SPARk-5201 and squashes the following commits:
96265a1 [Ye Xianjin] Update slice method comment and some responding docs.
e143d7a [Ye Xianjin] Update inclusive range check for splitting inclusive range.
b3f5577 [Ye Xianjin] We can include the last element in the last slice in general for inclusive range, hence eliminate the need to check Int.MaxValue or Int.MinValue.
7d39b9e [Ye Xianjin] Convert the two cases pattern matching to one case.
651c959 [Ye Xianjin] rename sign to needsInclusiveRange. add some comments
196f8a8 [Ye Xianjin] Add test cases for ranges end with Int.MaxValue or Int.MinValue
e66e60a [Ye Xianjin] Deal with inclusive and exclusive ranges in one case. If the range is inclusive and the end of the range is (Int.MaxValue or Int.MinValue), we should use inclusive range instead of exclusive
When calculating the input metrics there was an assumption that one task only reads from one block - this is not true for some operations including coalesce. This patch simply increments the task's input metrics if previous ones existed of the same read method.
A limitation to this patch is that if a task reads from two different blocks of different read methods, one will override the other.
Author: Kostas Sakellis <kostas@cloudera.com>
Closes#3120 from ksakellis/kostas-spark-4092 and squashes the following commits:
54e6658 [Kostas Sakellis] Drops metrics if conflicting read methods exist
f0e0cc5 [Kostas Sakellis] Add bytesReadCallback to InputMetrics
a2a36d4 [Kostas Sakellis] CR feedback
5a0c770 [Kostas Sakellis] [SPARK-4092] [CORE] Fix InputMetrics for coalesce'd Rdds
Adds onExecutorAdded and onExecutorRemoved events to the SparkListener. This will allow a client to get notified when an executor has been added/removed and provide additional information such as how many vcores it is consuming.
In addition, this commit adds a SparkListenerAdapter to the Java API that provides default implementations to the SparkListener. This is to get around the fact that default implementations for traits don't work in Java. Having Java clients extend SparkListenerAdapter moving forward will prevent breakage in java when we add new events to SparkListener.
Author: Kostas Sakellis <kostas@cloudera.com>
Closes#3711 from ksakellis/kostas-spark-4857 and squashes the following commits:
946d2c5 [Kostas Sakellis] Added executorAdded/Removed events to MesosSchedulerBackend
b1d054a [Kostas Sakellis] Remove executorInfo from ExecutorRemoved event
1727b38 [Kostas Sakellis] Renamed ExecutorDetails back to ExecutorInfo and other CR feedback
14fe78d [Kostas Sakellis] Added executor added/removed events to json protocol
93d087b [Kostas Sakellis] [SPARK-4857] [CORE] Adds Executor membership events to SparkListener
`TaskContext.attemptId` is misleadingly-named, since it currently returns a taskId, which uniquely identifies a particular task attempt within a particular SparkContext, instead of an attempt number, which conveys how many times a task has been attempted.
This patch deprecates `TaskContext.attemptId` and add `TaskContext.taskId` and `TaskContext.attemptNumber` fields. Prior to this change, it was impossible to determine whether a task was being re-attempted (or was a speculative copy), which made it difficult to write unit tests for tasks that fail on early attempts or speculative tasks that complete faster than original tasks.
Earlier versions of the TaskContext docs suggest that `attemptId` behaves like `attemptNumber`, so there's an argument to be made in favor of changing this method's implementation. Since we've decided against making that change in maintenance branches, I think it's simpler to add better-named methods and retain the old behavior for `attemptId`; if `attemptId` behaved differently in different branches, then this would cause confusing build-breaks when backporting regression tests that rely on the new `attemptId` behavior.
Most of this patch is fairly straightforward, but there is a bit of trickiness related to Mesos tasks: since there's no field in MesosTaskInfo to encode the attemptId, I packed it into the `data` field alongside the task binary.
Author: Josh Rosen <joshrosen@databricks.com>
Closes#3849 from JoshRosen/SPARK-4014 and squashes the following commits:
89d03e0 [Josh Rosen] Merge remote-tracking branch 'origin/master' into SPARK-4014
5cfff05 [Josh Rosen] Introduce wrapper for serializing Mesos task launch data.
38574d4 [Josh Rosen] attemptId -> taskAttemptId in PairRDDFunctions
a180b88 [Josh Rosen] Merge remote-tracking branch 'origin/master' into SPARK-4014
1d43aa6 [Josh Rosen] Merge remote-tracking branch 'origin/master' into SPARK-4014
eee6a45 [Josh Rosen] Merge remote-tracking branch 'origin/master' into SPARK-4014
0b10526 [Josh Rosen] Use putInt instead of putLong (silly mistake)
8c387ce [Josh Rosen] Use local with maxRetries instead of local-cluster.
cbe4d76 [Josh Rosen] Preserve attemptId behavior and deprecate it:
b2dffa3 [Josh Rosen] Address some of Reynold's minor comments
9d8d4d1 [Josh Rosen] Doc typo
1e7a933 [Josh Rosen] [SPARK-4014] Change TaskContext.attemptId to return attempt number instead of task ID.
fd515a5 [Josh Rosen] Add failing test for SPARK-4014
A few changes to fix this issue:
1. Handle the case that receiving `SparkListenerTaskStart` before `SparkListenerBlockManagerAdded`.
2. Don't add `executorId` to `removeTimes` when the executor is busy.
3. Use `HashMap.retain` to safely traverse the HashMap and remove items.
4. Use the same lock in ExecutorAllocationManager and ExecutorAllocationListener to fix the race condition in `totalPendingTasks`.
5. Move the blocking codes out of the message processing code in YarnSchedulerActor.
Author: zsxwing <zsxwing@gmail.com>
Closes#3783 from zsxwing/SPARK-4951 and squashes the following commits:
d51fa0d [zsxwing] Add comments
2e365ce [zsxwing] Remove expired executors from 'removeTimes' and add idle executors back when a new executor joins
49f61a9 [zsxwing] Eliminate duplicate executor registered warnings
d4c4e9a [zsxwing] Minor fixes for the code style
05f6238 [zsxwing] Move the blocking codes out of the message processing code
105ba3a [zsxwing] Fix the race condition in totalPendingTasks
d5c615d [zsxwing] Fix the issue that a busy executor may be killed
Dealing with [SPARK-4737], the handling of serialization errors should not be the DAGScheduler's responsibility. The task set manager now catches the error and aborts the stage.
If the TaskSetManager throws a TaskNotSerializableException, the TaskSchedulerImpl will return an empty list of task descriptions, because no tasks were started. The scheduler should abort the stage gracefully.
Note that I'm not too familiar with this part of the codebase and its place in the overall architecture of the Spark stack. If implementing it this way will have any averse side effects please voice that loudly.
Author: mcheah <mcheah@palantir.com>
Closes#3638 from mccheah/task-set-manager-properly-handle-ser-err and squashes the following commits:
1545984 [mcheah] Some more style fixes from Andrew Or.
5267929 [mcheah] Fixing style suggestions from Andrew Or.
dfa145b [mcheah] Fixing style from Josh Rosen's feedback
b2a430d [mcheah] Not returning empty seq when a task set cannot be serialized.
94844d7 [mcheah] Fixing compilation error, one brace too many
5f486f4 [mcheah] Adding license header for fake task class
bf5e706 [mcheah] Fixing indentation.
097e7a2 [mcheah] [SPARK-4737] Catching task serialization exception in TaskSetManager
The current TaskSchedulerImplSuite includes some tests that are
actually for the TaskSchedulerImpl, but the remainder of the tests avoid using
the TaskSchedulerImpl entirely, and actually test the pool and scheduling
algorithm mechanisms. This commit separates the pool/scheduling algorithm
tests into their own suite, and also simplifies those tests.
The pull request replaces #339.
Author: Kay Ousterhout <kayousterhout@gmail.com>
Closes#3967 from kayousterhout/SPARK-1143 and squashes the following commits:
8a898c4 [Kay Ousterhout] [SPARK-1143] Separate pool tests into their own suite.
This change does a few things to make the hadoop-provided profile more useful:
- Create new profiles for other libraries / services that might be provided by the infrastructure
- Simplify and fix the poms so that the profiles are only activated while building assemblies.
- Fix tests so that they're able to run when the profiles are activated
- Add a new env variable to be used by distributions that use these profiles to provide the runtime
classpath for Spark jobs and daemons.
Author: Marcelo Vanzin <vanzin@cloudera.com>
Closes#2982 from vanzin/SPARK-4048 and squashes the following commits:
82eb688 [Marcelo Vanzin] Add a comment.
eb228c0 [Marcelo Vanzin] Fix borked merge.
4e38f4e [Marcelo Vanzin] Merge branch 'master' into SPARK-4048
9ef79a3 [Marcelo Vanzin] Alternative way to propagate test classpath to child processes.
371ebee [Marcelo Vanzin] Review feedback.
52f366d [Marcelo Vanzin] Merge branch 'master' into SPARK-4048
83099fc [Marcelo Vanzin] Merge branch 'master' into SPARK-4048
7377e7b [Marcelo Vanzin] Merge branch 'master' into SPARK-4048
322f882 [Marcelo Vanzin] Fix merge fail.
f24e9e7 [Marcelo Vanzin] Merge branch 'master' into SPARK-4048
8b00b6a [Marcelo Vanzin] Merge branch 'master' into SPARK-4048
9640503 [Marcelo Vanzin] Cleanup child process log message.
115fde5 [Marcelo Vanzin] Simplify a comment (and make it consistent with another pom).
e3ab2da [Marcelo Vanzin] Fix hive-thriftserver profile.
7820d58 [Marcelo Vanzin] Fix CliSuite with provided profiles.
1be73d4 [Marcelo Vanzin] Restore flume-provided profile.
d1399ed [Marcelo Vanzin] Restore jetty dependency.
82a54b9 [Marcelo Vanzin] Remove unused profile.
5c54a25 [Marcelo Vanzin] Fix HiveThriftServer2Suite with *-provided profiles.
1fc4d0b [Marcelo Vanzin] Update dependencies for hive-thriftserver.
f7b3bbe [Marcelo Vanzin] Add snappy to hadoop-provided list.
9e4e001 [Marcelo Vanzin] Remove duplicate hive profile.
d928d62 [Marcelo Vanzin] Redirect child stderr to parent's log.
4d67469 [Marcelo Vanzin] Propagate SPARK_DIST_CLASSPATH on Yarn.
417d90e [Marcelo Vanzin] Introduce "SPARK_DIST_CLASSPATH".
2f95f0d [Marcelo Vanzin] Propagate classpath to child processes during testing.
1adf91c [Marcelo Vanzin] Re-enable maven-install-plugin for a few projects.
284dda6 [Marcelo Vanzin] Rework the "hadoop-provided" profile, add new ones.
Because `actorSelection` will return `deadLetters` for an invalid path, Worker keeps quiet for an invalid master url. It's better to log an error so that people can find such problem quickly.
This PR will check the url before sending to `actorSelection`, throw and log a SparkException for an invalid url.
Author: zsxwing <zsxwing@gmail.com>
Closes#3927 from zsxwing/SPARK-5126 and squashes the following commits:
9d429ee [zsxwing] Create a utility method in Utils to parse Spark url; verify urls before creating Actors so that invalid urls can crash the process.
8286e51 [zsxwing] Check the url before sending to Akka and log the error if the url is invalid
Enabled HistoryServer to show incomplete applications.
We can see the log for incomplete applications by clicking the bottom link.
Author: Masayoshi TSUZUKI <tsudukim@oss.nttdata.co.jp>
Closes#3467 from tsudukim/feature/SPARK-2458-2 and squashes the following commits:
76205d2 [Masayoshi TSUZUKI] Fixed and added test code.
29a04a9 [Masayoshi TSUZUKI] Merge branch 'master' of github.com:tsudukim/spark into feature/SPARK-2458-2
f9ef854 [Masayoshi TSUZUKI] Added space between "if" and "(". Fixed "Incomplete" as capitalized in the web UI. Modified double negative variable name.
9b465b0 [Masayoshi TSUZUKI] Modified typo and better implementation.
3ed8a41 [Masayoshi TSUZUKI] Modified too long lines.
08ea14d [Masayoshi TSUZUKI] [SPARK-2458] Make failed application log visible on History Server
This PR:
- Reenables `surefire`, and copies config from `scalatest` (which is itself an old fork of `surefire`, so similar)
- Tells `surefire` to test only Java tests
- Enables `surefire` and `scalatest` for all children, and in turn eliminates some duplication.
For me this causes the Scala and Java tests to be run once each, it seems, as desired. It doesn't affect the SBT build but works for Maven. I still need to verify that all of the Scala tests and Java tests are being run.
Author: Sean Owen <sowen@cloudera.com>
Closes#3651 from srowen/SPARK-4159 and squashes the following commits:
2e8a0af [Sean Owen] Remove specialized SPARK_HOME setting for REPL, YARN tests as it appears to be obsolete
12e4558 [Sean Owen] Append to unit-test.log instead of overwriting, so that both surefire and scalatest output is preserved. Also standardize/correct comments a bit.
e6f8601 [Sean Owen] Reenable Java tests by reenabling surefire with config cloned from scalatest; centralize test config in the parent
Add `assert(sc.listenerBus.waitUntilEmpty(WAIT_TIMEOUT_MILLIS))` to make sure `sparkListener` receive the message.
Author: zsxwing <zsxwing@gmail.com>
Closes#3889 from zsxwing/SPARK-5074 and squashes the following commits:
e61c198 [zsxwing] Fix a non-deterministic test failure
Because `sparkEnv.blockManager.master.removeBlock` is asynchronous, we need to make sure the block has already been removed before calling `super.enqueueSuccessfulTask`.
Author: zsxwing <zsxwing@gmail.com>
Closes#3894 from zsxwing/SPARK-5083 and squashes the following commits:
d97c03d [zsxwing] Fix a flaky test in TaskResultGetterSuite
It's not necessary to set `TaskSchedulerImpl.dagScheduler` in preStart. It's safe to set it after `initializeEventProcessActor()`.
Author: zsxwing <zsxwing@gmail.com>
Closes#3887 from zsxwing/SPARK-5069 and squashes the following commits:
d95894f [zsxwing] Fix the race condition of TaskSchedulerImpl.dagScheduler
A simple fix would be adding `assert(e1.appId == e2.appId)` for `SparkListenerApplicationStart`. But actually we can use `===` for well-defined case class directly. Therefore, instead of fixing this issue, I use `===` to compare those well-defined case classes (all fields have implemented a correct `equals` method, such as primitive types)
Author: zsxwing <zsxwing@gmail.com>
Closes#3886 from zsxwing/SPARK-5067 and squashes the following commits:
0a51711 [zsxwing] Use '===' to compare well-defined case class
The job launched by DriverSuite should bind the web UI to an ephemeral port, since it looks like port contention in this test has caused a large number of Jenkins failures when many builds are started simultaneously. Our tests already disable the web UI, but this doesn't affect subprocesses launched by our tests. In this case, I've opted to bind to an ephemeral port instead of disabling the UI because disabling features in this test may mask its ability to catch certain bugs.
See also: e24d3a9
Author: Josh Rosen <joshrosen@databricks.com>
Closes#3873 from JoshRosen/driversuite-webui-port and squashes the following commits:
48cd05c [Josh Rosen] [HOTFIX] Bind web UI to ephemeral port in DriverSuite.
Several of our tests call System.setProperty (or test code which implicitly sets system properties) and don't always reset/clear the modified properties, which can create ordering dependencies between tests and cause hard-to-diagnose failures.
This patch removes most uses of System.setProperty from our tests, since in most cases we can use SparkConf to set these configurations (there are a few exceptions, including the tests of SparkConf itself).
For the cases where we continue to use System.setProperty, this patch introduces a `ResetSystemProperties` ScalaTest mixin class which snapshots the system properties before individual tests and to automatically restores them on test completion / failure. See the block comment at the top of the ResetSystemProperties class for more details.
Author: Josh Rosen <joshrosen@databricks.com>
Closes#3739 from JoshRosen/cleanup-system-properties-in-tests and squashes the following commits:
0236d66 [Josh Rosen] Replace setProperty uses in two example programs / tools
3888fe3 [Josh Rosen] Remove setProperty use in LocalJavaStreamingContext
4f4031d [Josh Rosen] Add note on why SparkSubmitSuite needs ResetSystemProperties
4742a5b [Josh Rosen] Clarify ResetSystemProperties trait inheritance ordering.
0eaf0b6 [Josh Rosen] Remove setProperty call in TaskResultGetterSuite.
7a3d224 [Josh Rosen] Fix trait ordering
3fdb554 [Josh Rosen] Remove setProperty call in TaskSchedulerImplSuite
bee20df [Josh Rosen] Remove setProperty calls in SparkContextSchedulerCreationSuite
655587c [Josh Rosen] Remove setProperty calls in JobCancellationSuite
3f2f955 [Josh Rosen] Remove System.setProperty calls in DistributedSuite
cfe9cce [Josh Rosen] Remove use of system properties in SparkContextSuite
8783ab0 [Josh Rosen] Remove TestUtils.setSystemProperty, since it is subsumed by the ResetSystemProperties trait.
633a84a [Josh Rosen] Remove use of system properties in FileServerSuite
25bfce2 [Josh Rosen] Use ResetSystemProperties in UtilsSuite
1d1aa5a [Josh Rosen] Use ResetSystemProperties in SizeEstimatorSuite
dd9492b [Josh Rosen] Use ResetSystemProperties in AkkaUtilsSuite
b0daff2 [Josh Rosen] Use ResetSystemProperties in BlockManagerSuite
e9ded62 [Josh Rosen] Use ResetSystemProperties in TaskSchedulerImplSuite
5b3cb54 [Josh Rosen] Use ResetSystemProperties in SparkListenerSuite
0995c4b [Josh Rosen] Use ResetSystemProperties in SparkContextSchedulerCreationSuite
c83ded8 [Josh Rosen] Use ResetSystemProperties in SparkConfSuite
51aa870 [Josh Rosen] Use withSystemProperty in ShuffleSuite
60a63a1 [Josh Rosen] Use ResetSystemProperties in JobCancellationSuite
14a92e4 [Josh Rosen] Use withSystemProperty in FileServerSuite
628f46c [Josh Rosen] Use ResetSystemProperties in DistributedSuite
9e3e0dd [Josh Rosen] Add ResetSystemProperties test fixture mixin; use it in SparkSubmitSuite.
4dcea38 [Josh Rosen] Move withSystemProperty to TestUtils class.
This PR fixes an issue where PySpark broadcast variables caused NullPointerExceptions if KryoSerializer was used. The fix is to register PythonBroadcast with Kryo so that it's deserialized with a KryoJavaSerializer.
Author: Josh Rosen <joshrosen@databricks.com>
Closes#3831 from JoshRosen/SPARK-4882 and squashes the following commits:
0466c7a [Josh Rosen] Register PythonBroadcast with Kryo.
d5b409f [Josh Rosen] Enable registrationRequired, which would have caught this bug.
069d8a7 [Josh Rosen] Add failing test for SPARK-4882
There are a number of warnings generated in a normal, successful build right now. They're mostly Java unchecked cast warnings, which can be suppressed. But there's a grab bag of other Scala language warnings and so on that can all be easily fixed. The forthcoming PR fixes about 90% of the build warnings I see now.
Author: Sean Owen <sowen@cloudera.com>
Closes#3157 from srowen/SPARK-4297 and squashes the following commits:
8c9e469 [Sean Owen] Suppress unchecked cast warnings, and several other build warning fixes
Commit 7aacb7bfa added support for sharing downloaded files among multiple
executors of the same app. That works great in Yarn, since the app's directory
is cleaned up after the app is done.
But Spark standalone mode didn't do that, so the lock/cache files created
by that change were left around and could eventually fill up the disk hosting
/tmp.
To solve that, create app-specific directories under the local dirs when
launching executors. Multiple executors launched by the same Worker will
use the same app directories, so they should be able to share the downloaded
files. When the application finishes, a new message is sent to all workers
telling them the application has finished; once that message has been received,
and all executors registered for the application shut down, then those
directories will be cleaned up by the Worker.
Note: Unit testing this is hard (if even possible), since local-cluster mode
doesn't seem to leave the Master/Worker daemons running long enough after
`sc.stop()` is called for the clean up protocol to take effect.
Author: Marcelo Vanzin <vanzin@cloudera.com>
Closes#3705 from vanzin/SPARK-4834 and squashes the following commits:
b430534 [Marcelo Vanzin] Remove seemingly unnecessary synchronization.
50eb4b9 [Marcelo Vanzin] Review feedback.
c0e5ea5 [Marcelo Vanzin] [SPARK-4834] [standalone] Clean up application files after app finishes.
This commit consolidates some of the exceptions thrown if compression codecs are not available. If a bad configuration string was passed in, a ClassNotFoundException was through. Also, if Snappy was not available, it would throw an InvocationTargetException when the codec was being used (not when it was being initialized). Now, an IllegalArgumentException is thrown when a codec is not available at creation time - either because the class does not exist or the codec itself is not available in the system. This will allow us to have a better message and fail faster.
Author: Kostas Sakellis <kostas@cloudera.com>
Closes#3119 from ksakellis/kostas-spark-4079 and squashes the following commits:
9709c7c [Kostas Sakellis] Removed unnecessary Logging class
63bfdd0 [Kostas Sakellis] Removed isAvailable to preserve binary compatibility
1d0ef2f [Kostas Sakellis] [SPARK-4079] [CORE] Added more information to exception
64f3d27 [Kostas Sakellis] [SPARK-4079] [CORE] Code review feedback
52dfa8f [Kostas Sakellis] [SPARK-4079] [CORE] Default to LZF if Snappy not available
Fix small Hadoop 1 compile error from SPARK-2261. In Hadoop 1.x, all we have is FileStatus.isDir, so these "is file" assertions are changed to "is not a dir". This is how similar checks are done so far in the code base.
Author: Sean Owen <sowen@cloudera.com>
Closes#3754 from srowen/SPARK-4910 and squashes the following commits:
52c5e4e [Sean Owen] Fix small Hadoop 1 compile error from SPARK-2261
Currently the event logger uses a directory and several files to
describe an app's event log, all but one of which are empty. This
is not very HDFS-friendly, since creating lots of nodes in HDFS
(especially when they don't contain any data) is frowned upon due
to the node metadata being kept in the NameNode's memory.
Instead, add a header section to the event log file that contains metadata
needed to read the events. This metadata includes things like the Spark
version (for future code that may need it for backwards compatibility) and
the compression codec used for the event data.
With the new approach, aside from reducing the load on the NN, there's
also a lot less remote calls needed when reading the log directory.
Author: Marcelo Vanzin <vanzin@cloudera.com>
Closes#1222 from vanzin/hist-server-single-log and squashes the following commits:
cc8f5de [Marcelo Vanzin] Store header in plain text.
c7e6123 [Marcelo Vanzin] Update comment.
59c561c [Marcelo Vanzin] Review feedback.
216c5a3 [Marcelo Vanzin] Review comments.
dce28e9 [Marcelo Vanzin] Fix log overwrite test.
f91c13e [Marcelo Vanzin] Handle "spark.eventLog.overwrite", and add unit test.
346f0b4 [Marcelo Vanzin] Review feedback.
ed0023e [Marcelo Vanzin] Merge branch 'master' into hist-server-single-log
3f4500f [Marcelo Vanzin] Unit test for SPARK-3697.
45c7a1f [Marcelo Vanzin] Version of SPARK-3697 for this branch.
b3ee30b [Marcelo Vanzin] Merge branch 'master' into hist-server-single-log
a6d5c50 [Marcelo Vanzin] Merge branch 'master' into hist-server-single-log
16fd491 [Marcelo Vanzin] Use unique log directory for each codec.
0ef3f70 [Marcelo Vanzin] Merge branch 'master' into hist-server-single-log
d93c44a [Marcelo Vanzin] Add a newline to make the header more readable.
9e928ba [Marcelo Vanzin] Add types.
bd6ba8c [Marcelo Vanzin] Review feedback.
a624a89 [Marcelo Vanzin] Merge branch 'master' into hist-server-single-log
04364dc [Marcelo Vanzin] Merge branch 'master' into hist-server-single-log
bb7c2d3 [Marcelo Vanzin] Fix scalastyle warning.
16661a3 [Marcelo Vanzin] Simplify some internal code.
cc6bce4 [Marcelo Vanzin] Some review feedback.
a722184 [Marcelo Vanzin] Do not encode metadata in log file name.
3700586 [Marcelo Vanzin] Restore log flushing.
f677930 [Marcelo Vanzin] Fix botched rebase.
ae571fa [Marcelo Vanzin] Fix end-to-end event logger test.
9db0efd [Marcelo Vanzin] Show prettier name in UI.
8f42274 [Marcelo Vanzin] Make history server parse old-style log directories.
6251dd7 [Marcelo Vanzin] Make event logger use a single file.
The driver hangs sometimes when we coalesce RDD partitions. See JIRA for more details and reproduction.
This is because our use of empty string as default preferred location in `CoalescedRDDPartition` causes the `TaskSetManager` to schedule the corresponding task on host `""` (empty string). The intended semantics here, however, is that the partition does not have a preferred location, and the TSM should schedule the corresponding task accordingly.
Author: Andrew Or <andrew@databricks.com>
Closes#3633 from andrewor14/coalesce-preferred-loc and squashes the following commits:
e520d6b [Andrew Or] Oops
3ebf8bd [Andrew Or] A few comments
f370a4e [Andrew Or] Fix tests
2f7dfb6 [Andrew Or] Avoid using empty string as default preferred location
Currently this doesn't do anything in other modes, so we might as well just disable it rather than having the user mistakenly rely on it.
Author: Andrew Or <andrew@databricks.com>
Closes#3615 from andrewor14/dynamic-allocation-yarn-only and squashes the following commits:
ce6487a [Andrew Or] Allow requesting / killing executors only in YARN mode
My original 'fix' didn't fix at all. Now, there's a unit test to check whether it works. Of the two options to really fix it -- copy the `Map` to a `java.util.HashMap`, or copy and modify Scala's implementation in `Wrappers.MapWrapper`, I went with the latter.
Author: Sean Owen <sowen@cloudera.com>
Closes#3587 from srowen/SPARK-3926 and squashes the following commits:
8586bb9 [Sean Owen] Remove unneeded no-arg constructor, and add additional note about copied code in LICENSE
7bb0e66 [Sean Owen] Make SerializableMapWrapper actually serialize, and add unit test
Please see https://issues.apache.org/jira/browse/SPARK-4459
Author: Saldanha <saldaal1@phusca-l24858.wlan.na.novartis.net>
Closes#3327 from alokito/master and squashes the following commits:
54b1095 [Saldanha] [SPARK-4459] changed type parameter for keyBy from K to U
d5f73c3 [Saldanha] [SPARK-4459] added keyBy test
316ad77 [Saldanha] SPARK-4459 changed type parameter for groupBy from K to U.
62ddd4b [Saldanha] SPARK-4459 added failing unit test
MappedRDD, MappedValuesRDD, FlatMappedValuesRDD, FilteredRDD, GlommedRDD, FlatMappedRDD are not necessary. They can be implemented trivially using MapPartitionsRDD.
Author: Reynold Xin <rxin@databricks.com>
Closes#3578 from rxin/SPARK-4719 and squashes the following commits:
eed9853 [Reynold Xin] Preserve partitioning for filter.
eb1a89b [Reynold Xin] [SPARK-4719][API] Consolidate various narrow dep RDD classes with MapPartitionsRDD.
cc aarondav kayousterhout pwendell
This should go into 1.2?
Author: Reynold Xin <rxin@databricks.com>
Closes#3579 from rxin/SPARK-4085 and squashes the following commits:
255b4fd [Reynold Xin] Updated test.
f9814d9 [Reynold Xin] Code review feedback.
2afaf35 [Reynold Xin] [SPARK-4085] Propagate FetchFailedException when Spark fails to read local shuffle file.
ShuffleMemoryManager.tryToAcquire may return a negative value. The unit test demonstrates this bug. It will output `0 did not equal -200 granted is negative`.
Author: zsxwing <zsxwing@gmail.com>
Closes#3575 from zsxwing/SPARK-4715 and squashes the following commits:
a193ae6 [zsxwing] Make sure tryToAcquire won't return a negative value
This PR cleans up `import SparkContext._` in core for SPARK-4397(#3262) to prove it really works well.
Author: zsxwing <zsxwing@gmail.com>
Closes#3530 from zsxwing/SPARK-4397-cleanup and squashes the following commits:
04e2273 [zsxwing] Cleanup 'import SparkContext._' in core
Author: zsxwing <zsxwing@gmail.com>
Closes#3521 from zsxwing/SPARK-4661 and squashes the following commits:
03cbe3f [zsxwing] Minor code and docs cleanup
This PR introduces a set of Java APIs for using `JdbcRDD`:
1. Trait (interface) `JdbcRDD.ConnectionFactory`: equivalent to the `getConnection: () => Connection` parameter in `JdbcRDD` constructor.
2. Two overloaded versions of `Jdbc.create`: used to create `JavaRDD` that wraps a `JdbcRDD`.
<!-- Reviewable:start -->
[<img src="https://reviewable.io/review_button.png" height=40 alt="Review on Reviewable"/>](https://reviewable.io/reviews/apache/spark/3478)
<!-- Reviewable:end -->
Author: Cheng Lian <lian@databricks.com>
Closes#3478 from liancheng/japi-jdbc-rdd and squashes the following commits:
9a54625 [Cheng Lian] Only shutdowns a single DB rather than the whole Derby driver
d4cedc5 [Cheng Lian] Moves Java JdbcRDD test case to a separate test suite
ffcdf2e [Cheng Lian] Java API for JdbcRDD
https://issues.apache.org/jira/browse/SPARK-3628
In current implementation, the accumulator will be updated for every successfully finished task, even the task is from a resubmitted stage, which makes the accumulator counter-intuitive
In this patch, I changed the way for the DAGScheduler to update the accumulator,
DAGScheduler maintains a HashTable, mapping the stage id to the received <accumulator_id , value> pairs. Only when the stage becomes independent, (no job needs it any more), we accumulate the values of the <accumulator_id , value> pairs, when a task finished, we check if the HashTable has contained such stageId, it saves the accumulator_id, value only when the task is the first finished task of a new stage or the stage is running for the first attempt...
Author: CodingCat <zhunansjtu@gmail.com>
Closes#2524 from CodingCat/SPARK-732-1 and squashes the following commits:
701a1e8 [CodingCat] roll back change on Accumulator.scala
1433e6f [CodingCat] make MIMA happy
b233737 [CodingCat] address Matei's comments
02261b8 [CodingCat] rollback some changes
6b0aff9 [CodingCat] update document
2b2e8cf [CodingCat] updateAccumulator
83b75f8 [CodingCat] style fix
84570d2 [CodingCat] re-enable the bad accumulator guard
1e9e14d [CodingCat] add NPE guard
21b6840 [CodingCat] simplify the patch
88d1f03 [CodingCat] fix rebase error
f74266b [CodingCat] add test case for resubmitted result stage
5cf586f [CodingCat] de-duplicate on task level
138f9b3 [CodingCat] make MIMA happy
67593d2 [CodingCat] make if allowing duplicate update as an option of accumulator
Fix [SPARK-4471](https://issues.apache.org/jira/browse/SPARK-4471): blockManagerIdFromJson function throws exception while BlockManagerId be null in MetadataFetchFailedException
Author: hushan[胡珊] <hushan@xiaomi.com>
Closes#3340 from suyanNone/fix-blockmanagerId-jnothing-2 and squashes the following commits:
159f9a3 [hushan[胡珊]] Refine test code for blockmanager is null
4380d73 [hushan[胡珊]] remove useless blank line
3ccf651 [hushan[胡珊]] Fix SPARK-4471: blockManagerIdFromJson function throws exception while metadata fetch failed
Functionally, this is just a small change on top of #3393 (by jongyoul). The issue being addressed is discussed in the comments there. I have not yet added a test for the bug there. I will add one shortly.
I've also done some minor renaming/clean-up of variables in this class and tests.
Author: Patrick Wendell <pwendell@gmail.com>
Author: Jongyoul Lee <jongyoul@gmail.com>
Closes#3436 from pwendell/mesos-issue and squashes the following commits:
58c35b5 [Patrick Wendell] Adding unit test for this situation
c4f0697 [Patrick Wendell] Additional clean-up and fixes on top of existing fix
f20f1b3 [Jongyoul Lee] [SPARK-4525] MesosSchedulerBackend.resourceOffers cannot decline unused offers from acceptedOffers - Added code for declining unused offers among acceptedOffers - Edited testCase for checking declining unused offers
This reverts commit b043c27424.
I accidentally committed this using my own authorship credential. However,
I should have given authoriship to the original author: Jongyoul Lee.
Functionally, this is just a small change on top of #3393 (by jongyoul). The issue being addressed is discussed in the comments there. I have not yet added a test for the bug there. I will add one shortly.
I've also done some minor renaming/clean-up of variables in this class and tests.
Author: Patrick Wendell <pwendell@gmail.com>
Author: Jongyoul Lee <jongyoul@gmail.com>
Closes#3436 from pwendell/mesos-issue and squashes the following commits:
58c35b5 [Patrick Wendell] Adding unit test for this situation
c4f0697 [Patrick Wendell] Additional clean-up and fixes on top of existing fix
f20f1b3 [Jongyoul Lee] [SPARK-4525] MesosSchedulerBackend.resourceOffers cannot decline unused offers from acceptedOffers - Added code for declining unused offers among acceptedOffers - Edited testCase for checking declining unused offers
This PR adds two new pages to the Spark Web UI:
- A jobs overview page, which shows details on running / completed / failed jobs.
- A job details page, which displays information on an individual job's stages.
The jobs overview page is now the default UI homepage; the old homepage is still accessible at `/stages`.
### Screenshots
#### New UI homepage
#### Job details page
(This is effectively a per-job version of the stages page that can be extended later with other things, such as DAG visualizations)
### Key changes in this PR
- Rename `JobProgressPage` to `AllStagesPage`
- Expose `StageInfo` objects in the ``SparkListenerJobStart` event; add backwards-compatibility tests to JsonProtocol.
- Add additional data structures to `JobProgressListener` to map from stages to jobs.
- Add several fields to `JobUIData`.
I also added ~150 lines of Selenium tests as I uncovered UI issues while developing this patch.
### Limitations
If a job contains stages that aren't run, then its overall job progress bar may be an underestimate of the total job progress; in other words, a completed job may appear to have a progress bar that's not at 100%.
If stages or tasks fail, then the progress bar will not go backwards to reflect the true amount of remaining work.
Author: Josh Rosen <joshrosen@databricks.com>
Closes#3009 from JoshRosen/job-page and squashes the following commits:
eb05e90 [Josh Rosen] Disable kill button in completed stages tables.
f00c851 [Josh Rosen] Fix JsonProtocol compatibility
b89c258 [Josh Rosen] More JSON protocol backwards-compatibility fixes.
ff804cd [Josh Rosen] Don't write "Stage Ids" field in JobStartEvent JSON.
6f17f3f [Josh Rosen] Only store StageInfos in SparkListenerJobStart event.
2bbf41a [Josh Rosen] Update job progress bar to reflect skipped tasks/stages.
61c265a [Josh Rosen] Add “skipped stages” table; only display non-empty tables.
1f45d44 [Josh Rosen] Incorporate a bunch of minor review feedback.
0b77e3e [Josh Rosen] More bug fixes for phantom stages.
034aa8d [Josh Rosen] Use `.max()` to find result stage for job.
eebdc2c [Josh Rosen] Don’t display pending stages for completed jobs.
67080ba [Josh Rosen] Ensure that "phantom stages" don't cause memory leaks.
7d10b97 [Josh Rosen] Merge remote-tracking branch 'apache/master' into job-page
d69c775 [Josh Rosen] Fix table sorting on all jobs page.
5eb39dc [Josh Rosen] Add pending stages table to job page.
f2a15da [Josh Rosen] Add status field to job details page.
171b53c [Josh Rosen] Move `startTime` to the start of SparkContext.
e2f2c43 [Josh Rosen] Fix sorting of stages in job details page.
8955f4c [Josh Rosen] Display information for pending stages on jobs page.
8ab6c28 [Josh Rosen] Compute numTasks from job start stage infos.
5884f91 [Josh Rosen] Add StageInfos to SparkListenerJobStart event.
79793cd [Josh Rosen] Track indices of completed stage to avoid overcounting when failures occur.
d62ea7b [Josh Rosen] Add failing Selenium test for stage overcounting issue.
1145c60 [Josh Rosen] Display text instead of progress bar for stages.
3d0a007 [Josh Rosen] Merge remote-tracking branch 'origin/master' into job-page
8a2351b [Josh Rosen] Add help tooltip to Spark Jobs page.
b7bf30e [Josh Rosen] Add stages progress bar; fix bug where active stages show as completed.
4846ce4 [Josh Rosen] Hide "(Job Group") if no jobs were submitted in job groups.
4d58e55 [Josh Rosen] Change label to "Tasks (for all stages)"
85e9c85 [Josh Rosen] Extract startTime into separate variable.
1cf4987 [Josh Rosen] Fix broken kill links; add Selenium test to avoid future regressions.
56701fa [Josh Rosen] Move last stage name / description logic out of markup.
a475ea1 [Josh Rosen] Add progress bars to jobs page.
45343b8 [Josh Rosen] More comments
4b206fb [Josh Rosen] Merge remote-tracking branch 'origin/master' into job-page
bfce2b9 [Josh Rosen] Address review comments, except for progress bar.
4487dcb [Josh Rosen] [SPARK-4145] Web UI job pages
2568a6c [Josh Rosen] Rename JobProgressPage to AllStagesPage:
This PR is a workaround for SPARK-4479. Two changes are introduced: when merge sort is bypassed in `ExternalSorter`,
1. also bypass RDD elements buffering as buffering is the reason that `MutableRow` backed row objects must be copied, and
2. avoids defensive copies in `Exchange` operator
<!-- Reviewable:start -->
[<img src="https://reviewable.io/review_button.png" height=40 alt="Review on Reviewable"/>](https://reviewable.io/reviews/apache/spark/3422)
<!-- Reviewable:end -->
Author: Cheng Lian <lian@databricks.com>
Closes#3422 from liancheng/avoids-defensive-copies and squashes the following commits:
591f2e9 [Cheng Lian] Passes all shuffle suites
0c3c91e [Cheng Lian] Fixes shuffle write metrics when merge sort is bypassed
ed5df3c [Cheng Lian] Fixes styling changes
f75089b [Cheng Lian] Avoids unnecessary defensive copies when sort based shuffle is on
This PR moved `implicit`s to `package object` and `companion object` to enable the Scala compiler search them automatically without explicit importing.
It should not break any API. A test project for backforward compatibility is [here](https://github.com/zsxwing/SPARK-4397-Backforward-Compatibility). It proves the codes compiled with Spark 1.1.0 can run with this PR.
To summarize, the changes are:
* Deprecated the old implicit conversion functions: this preserves binary compatibility for code compiled against earlier versions of Spark.
* Removed "implicit" from them so they are just normal functions: this made sure the compiler doesn't get confused and warn about multiple implicits in scope.
* Created new implicit functions in package rdd object, which is part of the scope that scalac will search when looking for implicit conversions on various RDD objects.
The disadvantage is there are duplicated codes in SparkContext for backforward compatibility.
Author: zsxwing <zsxwing@gmail.com>
Closes#3262 from zsxwing/SPARK-4397 and squashes the following commits:
fc30314 [zsxwing] Update the comments
9c27aff [zsxwing] Move implicit functions to object RDD and forward old functions to new implicit ones directly
2b5f5a4 [zsxwing] Comments for the deprecated functions
52353de [zsxwing] Remove private[spark] from object WritableConverter
34641d4 [zsxwing] Move ImplicitSuite to org.apache.sparktest
7266218 [zsxwing] Add comments to warn the duplicate codes in SparkContext
185c12f [zsxwing] Remove simpleWritableConverter from SparkContext
3bdcae2 [zsxwing] Move WritableConverter implicits to object WritableConverter
9b73188 [zsxwing] Fix the code style issue
3ac4f07 [zsxwing] Add license header
1eda9e4 [zsxwing] Reorganize 'implicit's to improve the API convenience
**Summary.** Currently, we may spill many small files in `ExternalAppendOnlyMap` and `ExternalSorter`. The underlying root cause of this is summarized in [SPARK-4452](https://issues.apache.org/jira/browse/SPARK-4452). This PR does not address this root cause, but simply provides the guarantee that we never spill the in-memory data structure if its size is less than a configurable threshold of 5MB. This config is not documented because we don't want users to set it themselves, and it is not hard-coded because we need to change it in tests.
**Symptom.** Each spill is orders of magnitude smaller than 1MB, and there are many spills. In environments where the ulimit is set, this frequently causes "too many open file" exceptions observed in [SPARK-3633](https://issues.apache.org/jira/browse/SPARK-3633).
```
14/11/13 19:20:43 INFO collection.ExternalSorter: Thread 60 spilling in-memory batch of 4792 B to disk (292769 spills so far)
14/11/13 19:20:43 INFO collection.ExternalSorter: Thread 60 spilling in-memory batch of 4760 B to disk (292770 spills so far)
14/11/13 19:20:43 INFO collection.ExternalSorter: Thread 60 spilling in-memory batch of 4520 B to disk (292771 spills so far)
14/11/13 19:20:43 INFO collection.ExternalSorter: Thread 60 spilling in-memory batch of 4560 B to disk (292772 spills so far)
14/11/13 19:20:43 INFO collection.ExternalSorter: Thread 60 spilling in-memory batch of 4792 B to disk (292773 spills so far)
14/11/13 19:20:43 INFO collection.ExternalSorter: Thread 60 spilling in-memory batch of 4784 B to disk (292774 spills so far)
```
**Reproduction.** I ran the following on a small 4-node cluster with 512MB executors. Note that the back-to-back shuffle here is necessary for reasons described in [SPARK-4522](https://issues.apache.org/jira/browse/SPARK-4452). The second shuffle is a `reduceByKey` because it performs a map-side combine.
```
sc.parallelize(1 to 100000000, 100)
.map { i => (i, i) }
.groupByKey()
.reduceByKey(_ ++ _)
.count()
```
Before the change, I notice that each thread may spill up to 1000 times, and the size of each spill is on the order of 10KB. After the change, each thread spills only up to 20 times in the worst case, and the size of each spill is on the order of 1MB.
Author: Andrew Or <andrew@databricks.com>
Closes#3353 from andrewor14/avoid-small-spills and squashes the following commits:
49f380f [Andrew Or] Merge branch 'master' of https://git-wip-us.apache.org/repos/asf/spark into avoid-small-spills
27d6966 [Andrew Or] Merge branch 'master' of github.com:apache/spark into avoid-small-spills
f4736e3 [Andrew Or] Fix tests
a919776 [Andrew Or] Avoid many small spills
The check for maxResultSize > 0 is missing, results in failures. Also, error message needs to be improved so the developers know that there is a new parameter to be configured
Author: Nishkam Ravi <nravi@cloudera.com>
Author: nravi <nravi@c1704.halxg.cloudera.com>
Author: nishkamravi2 <nishkamravi@gmail.com>
Closes#3360 from nishkamravi2/master_nravi and squashes the following commits:
5c9a4cb [nishkamravi2] Update TaskSetManagerSuite.scala
535295a [nishkamravi2] Update TaskSetManager.scala
3e1b616 [Nishkam Ravi] Modify test for maxResultSize
9f6583e [Nishkam Ravi] Changes to maxResultSize code (improve error message and add condition to check if maxResultSize > 0)
5f8f9ed [Nishkam Ravi] Merge branch 'master' of https://github.com/apache/spark into master_nravi
636a9ff [nishkamravi2] Update YarnAllocator.scala
8f76c8b [Nishkam Ravi] Doc change for yarn memory overhead
35daa64 [Nishkam Ravi] Slight change in the doc for yarn memory overhead
5ac2ec1 [Nishkam Ravi] Remove out
dac1047 [Nishkam Ravi] Additional documentation for yarn memory overhead issue
42c2c3d [Nishkam Ravi] Additional changes for yarn memory overhead issue
362da5e [Nishkam Ravi] Additional changes for yarn memory overhead
c726bd9 [Nishkam Ravi] Merge branch 'master' of https://github.com/apache/spark into master_nravi
f00fa31 [Nishkam Ravi] Improving logging for AM memoryOverhead
1cf2d1e [nishkamravi2] Update YarnAllocator.scala
ebcde10 [Nishkam Ravi] Modify default YARN memory_overhead-- from an additive constant to a multiplier (redone to resolve merge conflicts)
2e69f11 [Nishkam Ravi] Merge branch 'master' of https://github.com/apache/spark into master_nravi
efd688a [Nishkam Ravi] Merge branch 'master' of https://github.com/apache/spark
2b630f9 [nravi] Accept memory input as "30g", "512M" instead of an int value, to be consistent with rest of Spark
3bf8fad [nravi] Merge branch 'master' of https://github.com/apache/spark
5423a03 [nravi] Merge branch 'master' of https://github.com/apache/spark
eb663ca [nravi] Merge branch 'master' of https://github.com/apache/spark
df2aeb1 [nravi] Improved fix for ConcurrentModificationIssue (Spark-1097, Hadoop-10456)
6b840f0 [nravi] Undo the fix for SPARK-1758 (the problem is fixed)
5108700 [nravi] Fix in Spark for the Concurrent thread modification issue (SPARK-1097, HADOOP-10456)
681b36f [nravi] Fix for SPARK-1758: failing test org.apache.spark.JavaAPISuite.wholeTextFiles
This commit fixes a memory leak in JobProgressListener that I introduced in SPARK-2321 and adds a testing framework to ensure that it’s very difficult to inadvertently introduce new memory leaks.
This solution might be overkill, but the main idea is to partition JobProgressListener's state into three buckets: collections that should be empty once Spark is idle, collections that must obey some hard size limit, and collections that have a soft size limit (they can grow arbitrarily large when Spark is active but must shrink to fit within some bound after Spark becomes idle).
Based on this, we can write fairly generic tests that run workloads that submit more than `spark.ui.retainedStages` stages and `spark.ui.retainedJobs` jobs then check that these various collections' sizes obey their contracts.
Author: Josh Rosen <joshrosen@databricks.com>
Closes#3372 from JoshRosen/SPARK-4495 and squashes the following commits:
c73fab5 [Josh Rosen] "data structures" -> collections
be72e81 [Josh Rosen] [SPARK-4495] Fix memory leaks in JobProgressListener
Spark hangs with the following code:
~~~
sc.parallelize(1 to 10).zipWithIndex.repartition(10).count()
~~~
This is because ZippedWithIndexRDD triggers a job in getPartitions and it causes a deadlock in DAGScheduler.getPreferredLocs (synced). The fix is to compute `startIndices` during construction.
This should be applied to branch-1.0, branch-1.1, and branch-1.2.
pwendell
Author: Xiangrui Meng <meng@databricks.com>
Closes#3291 from mengxr/SPARK-4433 and squashes the following commits:
c284d9f [Xiangrui Meng] fix a racing condition in zipWithIndex
This PR adds a regression test for SPARK-4434.
Author: Kousuke Saruta <sarutak@oss.nttdata.co.jp>
Closes#3326 from sarutak/add-triple-slash-testcase and squashes the following commits:
82bc9cc [Kousuke Saruta] Fixed wrong grammar in comment
9149027 [Kousuke Saruta] Merge branch 'master' of git://git.apache.org/spark into add-triple-slash-testcase
c1c80ca [Kousuke Saruta] Fixed style
4f30210 [Kousuke Saruta] Modified comments
9e09da2 [Kousuke Saruta] Fixed URI validation for jar file
d4b99ef [Kousuke Saruta] [SPARK-4075] [Deploy] Jar url validation is not enough for Jar file
ac79906 [Kousuke Saruta] Merge branch 'master' of git://git.apache.org/spark into add-triple-slash-testcase
6d4f47e [Kousuke Saruta] Added a test case as a regression check for SPARK-4434
This patch adds error-detection logic to throw an exception when attempting to create multiple active SparkContexts in the same JVM, since this is currently unsupported and has been known to cause confusing behavior (see SPARK-2243 for more details).
**The solution implemented here is only a partial fix.** A complete fix would have the following properties:
1. Only one SparkContext may ever be under construction at any given time.
2. Once a SparkContext has been successfully constructed, any subsequent construction attempts should fail until the active SparkContext is stopped.
3. If the SparkContext constructor throws an exception, then all resources created in the constructor should be cleaned up (SPARK-4194).
4. If a user attempts to create a SparkContext but the creation fails, then the user should be able to create new SparkContexts.
This PR only provides 2) and 4); we should be able to provide all of these properties, but the correct fix will involve larger changes to SparkContext's construction / initialization, so we'll target it for a different Spark release.
### The correct solution:
I think that the correct way to do this would be to move the construction of SparkContext's dependencies into a static method in the SparkContext companion object. Specifically, we could make the default SparkContext constructor `private` and change it to accept a `SparkContextDependencies` object that contains all of SparkContext's dependencies (e.g. DAGScheduler, ContextCleaner, etc.). Secondary constructors could call a method on the SparkContext companion object to create the `SparkContextDependencies` and pass the result to the primary SparkContext constructor. For example:
```scala
class SparkContext private (deps: SparkContextDependencies) {
def this(conf: SparkConf) {
this(SparkContext.getDeps(conf))
}
}
object SparkContext(
private[spark] def getDeps(conf: SparkConf): SparkContextDependencies = synchronized {
if (anotherSparkContextIsActive) { throw Exception(...) }
var dagScheduler: DAGScheduler = null
try {
dagScheduler = new DAGScheduler(...)
[...]
} catch {
case e: Exception =>
Option(dagScheduler).foreach(_.stop())
[...]
}
SparkContextDependencies(dagScheduler, ....)
}
}
```
This gives us mutual exclusion and ensures that any resources created during the failed SparkContext initialization are properly cleaned up.
This indirection is necessary to maintain binary compatibility. In retrospect, it would have been nice if SparkContext had no private constructors and could only be created through builder / factory methods on its companion object, since this buys us lots of flexibility and makes dependency injection easier.
### Alternative solutions:
As an alternative solution, we could refactor SparkContext's primary constructor to perform all object creation in a giant `try-finally` block. Unfortunately, this will require us to turn a bunch of `vals` into `vars` so that they can be assigned from the `try` block. If we still want `vals`, we could wrap each `val` in its own `try` block (since the try block can return a value), but this will lead to extremely messy code and won't guard against the introduction of future code which doesn't properly handle failures.
The more complex approach outlined above gives us some nice dependency injection benefits, so I think that might be preferable to a `var`-ification.
### This PR's solution:
- At the start of the constructor, check whether some other SparkContext is active; if so, throw an exception.
- If another SparkContext might be under construction (or has thrown an exception during construction), allow the new SparkContext to begin construction but log a warning (since resources might have been leaked from a failed creation attempt).
- At the end of the SparkContext constructor, check whether some other SparkContext constructor has raced and successfully created an active context. If so, throw an exception.
This guarantees that no two SparkContexts will ever be active and exposed to users (since we check at the very end of the constructor). If two threads race to construct SparkContexts, then one of them will win and another will throw an exception.
This exception can be turned into a warning by setting `spark.driver.allowMultipleContexts = true`. The exception is disabled in unit tests, since there are some suites (such as Hive) that may require more significant refactoring to clean up their SparkContexts. I've made a few changes to other suites' test fixtures to properly clean up SparkContexts so that the unit test logs contain fewer warnings.
Author: Josh Rosen <joshrosen@databricks.com>
Closes#3121 from JoshRosen/SPARK-4180 and squashes the following commits:
23c7123 [Josh Rosen] Merge remote-tracking branch 'origin/master' into SPARK-4180
d38251b [Josh Rosen] Address latest round of feedback.
c0987d3 [Josh Rosen] Accept boolean instead of SparkConf in methods.
85a424a [Josh Rosen] Incorporate more review feedback.
372d0d3 [Josh Rosen] Merge remote-tracking branch 'origin/master' into SPARK-4180
f5bb78c [Josh Rosen] Update mvn build, too.
d809cb4 [Josh Rosen] Improve handling of failed SparkContext creation attempts.
79a7e6f [Josh Rosen] Fix commented out test
a1cba65 [Josh Rosen] Merge remote-tracking branch 'origin/master' into SPARK-4180
7ba6db8 [Josh Rosen] Add utility to set system properties in tests.
4629d5c [Josh Rosen] Set spark.driver.allowMultipleContexts=true in tests.
ed17e14 [Josh Rosen] Address review feedback; expose hack workaround for existing unit tests.
1c66070 [Josh Rosen] Merge remote-tracking branch 'origin/master' into SPARK-4180
06c5c54 [Josh Rosen] Add / improve SparkContext cleanup in streaming BasicOperationsSuite
d0437eb [Josh Rosen] StreamingContext.stop() should stop SparkContext even if StreamingContext has not been started yet.
c4d35a2 [Josh Rosen] Log long form of creation site to aid debugging.
918e878 [Josh Rosen] Document "one SparkContext per JVM" limitation.
afaa7e3 [Josh Rosen] [SPARK-4180] Prevent creations of multiple active SparkContexts.
This PR refactors / extends the status API introduced in #2696.
- Change StatusAPI from a mixin trait to a class. Before, the new status API methods were directly accessible through SparkContext, whereas now they're accessed through a `sc.statusAPI` field. As long as we were going to add these methods directly to SparkContext, the mixin trait seemed like a good idea, but this might be simpler to reason about and may avoid pitfalls that I've run into while attempting to refactor other parts of SparkContext to use mixins (see #3071, for example).
- Change the name from SparkStatusAPI to SparkStatusTracker.
- Make `getJobIdsForGroup(null)` return ids for jobs that aren't associated with any job group.
- Add `getActiveStageIds()` and `getActiveJobIds()` methods that return the ids of whatever's currently active in this SparkContext. This should simplify davies's progress bar code.
Author: Josh Rosen <joshrosen@databricks.com>
Closes#3197 from JoshRosen/progress-api-improvements and squashes the following commits:
30b0afa [Josh Rosen] Rename SparkStatusAPI to SparkStatusTracker.
d1b08d8 [Josh Rosen] Add missing newlines
2cc7353 [Josh Rosen] Add missing file.
d5eab1f [Josh Rosen] Add getActive[Stage|Job]Ids() methods.
a227984 [Josh Rosen] getJobIdsForGroup(null) should return jobs for default group
c47e294 [Josh Rosen] Remove StatusAPI mixin trait.
... executors than pending tasks need.
WIP. Still need to add and fix tests.
Author: Sandy Ryza <sandy@cloudera.com>
Closes#3204 from sryza/sandy-spark-4214 and squashes the following commits:
35cf0e0 [Sandy Ryza] Add comment
13b53df [Sandy Ryza] Review feedback
067465f [Sandy Ryza] Whitespace fix
6ae080c [Sandy Ryza] Add tests and get num pending tasks from ExecutorAllocationListener
531e2b6 [Sandy Ryza] SPARK-4214. With dynamic allocation, avoid outstanding requests for more executors than pending tasks need.
Author: Jeff Hammerbacher <jeff.hammerbacher@gmail.com>
Closes#3242 from hammer/patch-1 and squashes the following commits:
f88d635 [Jeff Hammerbacher] Update failed assert text to match code in SizeEstimatorSuite
Author: Aaron Davidson <aaron@databricks.com>
Closes#3155 from aarondav/conf and squashes the following commits:
7045e77 [Aaron Davidson] Add mesos comment
4770f6e [Aaron Davidson] [SPARK-4370] [Core] Limit number of Netty cores based on executor size
The wholeFile() can not read compressed files, it should be, just like textFile().
Author: Davies Liu <davies@databricks.com>
Closes#3005 from davies/whole and squashes the following commits:
a43fcfb [Davies Liu] remove semicolon
c83571a [Davies Liu] remove = if return type is Unit
83c844f [Davies Liu] Merge branch 'master' of github.com:apache/spark into whole
22e8b3e [Davies Liu] support compressed file in wholeTextFile
Before:
```
Exception in thread "main" java.lang.Exception: Could not load user defined classes inside of executors
at org.apache.spark.deploy.JarCreationTest$.main(SparkSubmitSuite.scala:471)
at org.apache.spark.deploy.JarCreationTest.main(SparkSubmitSuite.scala)
at sun.reflect.NativeMethodAccessorImpl.invoke0(Native Method)
```
After:
```
Exception in thread "main" java.lang.Exception: Could not load user class from jar:
java.lang.UnsupportedClassVersionError: SparkSubmitClassA : Unsupported major.minor version 51.0
java.lang.ClassLoader.defineClass1(Native Method)
java.lang.ClassLoader.defineClass(ClassLoader.java:643)
...
at org.apache.spark.deploy.JarCreationTest$.main(SparkSubmitSuite.scala:472)
at org.apache.spark.deploy.JarCreationTest.main(SparkSubmitSuite.scala)
at sun.reflect.NativeMethodAccessorImpl.invoke0(Native Method)
```
Author: Andrew Or <andrew@databricks.com>
Closes#3212 from andrewor14/submit-suite-message and squashes the following commits:
7779248 [Andrew Or] Format exception
8fe6719 [Andrew Or] Better exception message from failed test
Author: Timothy Chen <tnachen@gmail.com>
Closes#1487 from tnachen/resource_offer_refactor and squashes the following commits:
4ea5dec [Timothy Chen] Rebase from master and address comments
9ccab09 [Timothy Chen] Address review comments
e6494dc [Timothy Chen] Refactor class loading
8207428 [Timothy Chen] Refactor mesos scheduler resourceOffers and add unit test
Netty's DefaultFileRegion requires a FileDescriptor in its constructor, which means we need to have a opened file handle. In super large workloads, this could lead to too many open files due to the way these file descriptors are cleaned. This pull request creates a new LazyFileRegion that initializes the FileDescriptor when we are sending data for the first time.
Author: Reynold Xin <rxin@databricks.com>
Author: Reynold Xin <rxin@apache.org>
Closes#3172 from rxin/lazyFD and squashes the following commits:
0bdcdc6 [Reynold Xin] Added reference to Netty's DefaultFileRegion
d4564ae [Reynold Xin] Added SparkConf to the ctor argument of IndexShuffleBlockManager.
6ed369e [Reynold Xin] Code review feedback.
04cddc8 [Reynold Xin] [SPARK-4307] Initialize FileDescriptor lazily in FileRegion.
For me the core tests failed because there are two locale dependent parts in the code.
Look at the Jira ticket for details.
Why is it necessary to check the exception message in isBindCollision in
https://github.com/apache/spark/blob/master/core/src/main/scala/org/apache/spark/util/Utils.scala#L1686
?
Author: Niklas Wilcke <1wilcke@informatik.uni-hamburg.de>
Closes#3036 from numbnut/core-test-fix and squashes the following commits:
1fb0d04 [Niklas Wilcke] Fixing locale dependend code and tests
Make Tachyon related unit tests execute without deploying a Tachyon system locally.
Author: RongGu <gurongwalker@gmail.com>
Closes#3030 from RongGu/SPARK-2703 and squashes the following commits:
ad08827 [RongGu] Make Tachyon related unit tests execute without deploying a Tachyon system locally
Author: Sandy Ryza <sandy@cloudera.com>
This patch had conflicts when merged, resolved by
Committer: Kay Ousterhout <kayousterhout@gmail.com>
Closes#2968 from sryza/sandy-spark-3179 and squashes the following commits:
dce4784 [Sandy Ryza] More review feedback
8d350d1 [Sandy Ryza] Fix test against Hadoop 2.5+
e7c74d0 [Sandy Ryza] More review feedback
6cff9c4 [Sandy Ryza] Review feedback
fb2dde0 [Sandy Ryza] SPARK-3179
This PR elimiantes the network package's usage of the Java serializer and replaces it with Encodable, which is a lightweight binary protocol. Each message is preceded by a type id, which will allow us to change messages (by only adding new ones), or to change the format entirely by switching to a special id (such as -1).
This protocol has the advantage over Java that we can guarantee that messages will remain compatible across compiled versions and JVMs, though it does not provide a clean way to do schema migration. In the future, it may be good to use a more heavy-weight serialization format like protobuf, thrift, or avro, but these all add several dependencies which are unnecessary at the present time.
Additionally this unifies the RPC messages of NettyBlockTransferService and ExternalShuffleClient.
Author: Aaron Davidson <aaron@databricks.com>
Closes#3146 from aarondav/free and squashes the following commits:
ed1102a [Aaron Davidson] Remove some unused imports
b8e2a49 [Aaron Davidson] Add appId to test
538f2a3 [Aaron Davidson] [SPARK-4187] [Core] Switch to binary protocol for external shuffle service messages
This PR fixed `Utils.exceptionString` to output the full exception information. However, the stack trace may become very huge, so I also updated the Web UI to collapse the error information by default (display the first line and clicking `+detail` will display the full info).
Here are the screenshots:
Stages:
Details for one stage:
The full information in the gray text field is:
```Java
org.apache.spark.shuffle.FetchFailedException: Connection reset by peer
at org.apache.spark.shuffle.hash.BlockStoreShuffleFetcher$.org$apache$spark$shuffle$hash$BlockStoreShuffleFetcher$$unpackBlock$1(BlockStoreShuffleFetcher.scala:67)
at org.apache.spark.shuffle.hash.BlockStoreShuffleFetcher$$anonfun$3.apply(BlockStoreShuffleFetcher.scala:83)
at org.apache.spark.shuffle.hash.BlockStoreShuffleFetcher$$anonfun$3.apply(BlockStoreShuffleFetcher.scala:83)
at scala.collection.Iterator$$anon$13.hasNext(Iterator.scala:371)
at org.apache.spark.util.CompletionIterator.hasNext(CompletionIterator.scala:30)
at org.apache.spark.InterruptibleIterator.hasNext(InterruptibleIterator.scala:39)
at scala.collection.Iterator$$anon$11.hasNext(Iterator.scala:327)
at scala.collection.Iterator$$anon$11.hasNext(Iterator.scala:327)
at org.apache.spark.util.collection.ExternalAppendOnlyMap.insertAll(ExternalAppendOnlyMap.scala:129)
at org.apache.spark.rdd.CoGroupedRDD$$anonfun$compute$5.apply(CoGroupedRDD.scala:160)
at org.apache.spark.rdd.CoGroupedRDD$$anonfun$compute$5.apply(CoGroupedRDD.scala:159)
at scala.collection.TraversableLike$WithFilter$$anonfun$foreach$1.apply(TraversableLike.scala:772)
at scala.collection.mutable.ResizableArray$class.foreach(ResizableArray.scala:59)
at scala.collection.mutable.ArrayBuffer.foreach(ArrayBuffer.scala:47)
at scala.collection.TraversableLike$WithFilter.foreach(TraversableLike.scala:771)
at org.apache.spark.rdd.CoGroupedRDD.compute(CoGroupedRDD.scala:159)
at org.apache.spark.rdd.RDD.computeOrReadCheckpoint(RDD.scala:263)
at org.apache.spark.rdd.RDD.iterator(RDD.scala:230)
at org.apache.spark.rdd.MappedValuesRDD.compute(MappedValuesRDD.scala:31)
at org.apache.spark.rdd.RDD.computeOrReadCheckpoint(RDD.scala:263)
at org.apache.spark.rdd.RDD.iterator(RDD.scala:230)
at org.apache.spark.rdd.FlatMappedValuesRDD.compute(FlatMappedValuesRDD.scala:31)
at org.apache.spark.rdd.RDD.computeOrReadCheckpoint(RDD.scala:263)
at org.apache.spark.rdd.RDD.iterator(RDD.scala:230)
at org.apache.spark.scheduler.ResultTask.runTask(ResultTask.scala:61)
at org.apache.spark.scheduler.Task.run(Task.scala:56)
at org.apache.spark.executor.Executor$TaskRunner.run(Executor.scala:189)
at java.util.concurrent.ThreadPoolExecutor$Worker.runTask(ThreadPoolExecutor.java:886)
at java.util.concurrent.ThreadPoolExecutor$Worker.run(ThreadPoolExecutor.java:908)
at java.lang.Thread.run(Thread.java:662)
Caused by: java.io.IOException: Connection reset by peer
at sun.nio.ch.FileDispatcher.read0(Native Method)
at sun.nio.ch.SocketDispatcher.read(SocketDispatcher.java:21)
at sun.nio.ch.IOUtil.readIntoNativeBuffer(IOUtil.java:198)
at sun.nio.ch.IOUtil.read(IOUtil.java:166)
at sun.nio.ch.SocketChannelImpl.read(SocketChannelImpl.java:245)
at io.netty.buffer.PooledUnsafeDirectByteBuf.setBytes(PooledUnsafeDirectByteBuf.java:311)
at io.netty.buffer.AbstractByteBuf.writeBytes(AbstractByteBuf.java:881)
at io.netty.channel.socket.nio.NioSocketChannel.doReadBytes(NioSocketChannel.java:225)
at io.netty.channel.nio.AbstractNioByteChannel$NioByteUnsafe.read(AbstractNioByteChannel.java:119)
at io.netty.channel.nio.NioEventLoop.processSelectedKey(NioEventLoop.java:511)
at io.netty.channel.nio.NioEventLoop.processSelectedKeysOptimized(NioEventLoop.java:468)
at io.netty.channel.nio.NioEventLoop.processSelectedKeys(NioEventLoop.java:382)
at io.netty.channel.nio.NioEventLoop.run(NioEventLoop.java:354)
at io.netty.util.concurrent.SingleThreadEventExecutor$2.run(SingleThreadEventExecutor.java:116)
... 1 more
```
/cc aarondav
Author: zsxwing <zsxwing@gmail.com>
Closes#3073 from zsxwing/SPARK-4204 and squashes the following commits:
176d1e3 [zsxwing] Add comments to explain the stack trace difference
ca509d3 [zsxwing] Add fullStackTrace to the constructor of ExceptionFailure
a07057b [zsxwing] Core style fix
dfb0032 [zsxwing] Backward compatibility for old history server
1e50f71 [zsxwing] Update as per review and increase the max height of the stack trace details
94f2566 [zsxwing] Change Utils.exceptionString to contain the inner exceptions and make the error information in Web UI more friendly
This relies on a hook from whoever is hosting the shuffle service to invoke removeApplication() when the application is completed. Once invoked, we will clean up all the executors' shuffle directories we know about.
Author: Aaron Davidson <aaron@databricks.com>
Closes#3126 from aarondav/cleanup and squashes the following commits:
33a64a9 [Aaron Davidson] Missing brace
e6e428f [Aaron Davidson] Address comments
16a0d27 [Aaron Davidson] Cleanup
e4df3e7 [Aaron Davidson] [SPARK-4236] Cleanup removed applications' files in shuffle service
Author: Aaron Davidson <aaron@databricks.com>
Closes#3142 from aarondav/worker and squashes the following commits:
3780bd7 [Aaron Davidson] Address comments
2dcdfc1 [Aaron Davidson] Add private[worker]
47f49d3 [Aaron Davidson] NettyBlockTransferService shouldn't care about app ids (it's only b/t executors)
258417c [Aaron Davidson] [SPARK-4277] Support external shuffle service on executor
Author: Aaron Davidson <aaron@databricks.com>
Closes#3128 from aarondav/compiter and squashes the following commits:
698e4be [Aaron Davidson] [SPARK-4264] Completion iterator should only invoke callback once
Does three things: (1) Adds SASL to ExternalShuffleClient, (2) puts SecurityManager in BlockManager's constructor, and (3) adds unit test.
Author: Aaron Davidson <aaron@databricks.com>
Closes#3108 from aarondav/sasl-client and squashes the following commits:
48b622d [Aaron Davidson] Screw it, let's just get LimitedInputStream
3543b70 [Aaron Davidson] Back out of pom change due to unknown test issue?
b58518a [Aaron Davidson] ByteStreams.limit() not available :(
cbe451a [Aaron Davidson] Address comments
2bf2908 [Aaron Davidson] [SPARK-4242] [Core] Add SASL to external shuffle service
Author: zsxwing <zsxwing@gmail.com>
Closes#3085 from zsxwing/SPARK-4166-back-comp and squashes the following commits:
89329f4 [zsxwing] Add a backward compatibility test for ExecutorLostFailure
/cc aarondav
Author: zsxwing <zsxwing@gmail.com>
Closes#3086 from zsxwing/SPARK-4163-back-comp and squashes the following commits:
21cb2a8 [zsxwing] Add a backward compatibility test for FetchFailed
A leak of event loops may be causing test failures.
Author: Aaron Davidson <aaron@databricks.com>
Closes#3053 from aarondav/leak and squashes the following commits:
e676d18 [Aaron Davidson] Typo!
8f96475 [Aaron Davidson] Keep original ssc semantics
7e49f10 [Aaron Davidson] A leak of event loops may be causing test failures.
Now when ExecutorLostFailure happens, it only displays `ExecutorLostFailure (executor lost)`. Adding the executor id will help locate the faulted executor.
Author: zsxwing <zsxwing@gmail.com>
Closes#3033 from zsxwing/SPARK-4166 and squashes the following commits:
ff4664c [zsxwing] Backward-compatible support
c5c4cf2 [zsxwing] Display the executor ID in the Web UI when ExecutorLostFailure happens
Right now, operations like collect() and take() can crash the driver with an OOM if they bring back too many data.
This PR will introduce spark.driver.maxResultSize, after setting it, the driver will abort a job if its result is bigger than it.
By default, it's 1g (for backward compatibility for most the cases).
In local mode, the driver and executor share the same JVM, the default setting can not protect JVM from OOM.
cc mateiz
Author: Davies Liu <davies@databricks.com>
Closes#3003 from davies/collect and squashes the following commits:
248ed5e [Davies Liu] fix compile
272522e [Davies Liu] address comments
2c35773 [Davies Liu] add sizes in message of abort()
5d62303 [Davies Liu] address comments
bc3c077 [Davies Liu] Merge branch 'master' of github.com:apache/spark into collect
11f97c5 [Davies Liu] address comments
47b144f [Davies Liu] check the size of result before send and fetch
3d81af2 [Davies Liu] address comments
ca8267d [Davies Liu] limit the size of data by collect
This patch introduces the tooling necessary to construct an external shuffle service which is independent of Spark executors, and then use this service inside Spark. An example (just for the sake of this PR) of the service creation can be found in Worker, and the service itself is used by plugging in the StandaloneShuffleClient as Spark's ShuffleClient (setup in BlockManager).
This PR continues the work from #2753, which extracted out the transport layer of Spark's block transfer into an independent package within Spark. A new package was created which contains the Spark business logic necessary to retrieve the actual shuffle data, which is completely independent of the transport layer introduced in the previous patch. Similar to the transport layer, this package must not depend on Spark as we anticipate plugging this service as a lightweight process within, say, the YARN NodeManager, and do not wish to include Spark's dependencies (including Scala itself).
There are several outstanding tasks which must be complete before this PR can be merged:
- [x] Complete unit testing of network/shuffle package.
- [x] Performance and correctness testing on a real cluster.
- [x] Remove example service instantiation from Worker.scala.
There are even more shortcomings of this PR which should be addressed in followup patches:
- Don't use Java serializer for RPC layer! It is not cross-version compatible.
- Handle shuffle file cleanup for dead executors once the application terminates or the ContextCleaner triggers.
- Documentation of the feature in the Spark docs.
- Improve behavior if the shuffle service itself goes down (right now we don't blacklist it, and new executors cannot spawn on that machine).
- SSL and SASL integration
- Nice to have: Handle shuffle file consolidation (this would requires changes to Spark's implementation).
Author: Aaron Davidson <aaron@databricks.com>
Closes#3001 from aarondav/shuffle-service and squashes the following commits:
4d1f8c1 [Aaron Davidson] Remove changes to Worker
705748f [Aaron Davidson] Rename Standalone* to External*
fd3928b [Aaron Davidson] Do not unregister executor outputs unduly
9883918 [Aaron Davidson] Make suggested build changes
3d62679 [Aaron Davidson] Add Spark integration test
7fe51d5 [Aaron Davidson] Fix SBT integration
56caa50 [Aaron Davidson] Address comments
c8d1ac3 [Aaron Davidson] Add unit tests
2f70c0c [Aaron Davidson] Fix unit tests
5483e96 [Aaron Davidson] Fix unit tests
46a70bf [Aaron Davidson] Whoops, bracket
5ea4df6 [Aaron Davidson] [SPARK-3796] Create external service which can serve shuffle files
The additions add the abstract BinaryFileInputFormat and BinaryRecordReader classes for reading in data as a byte stream and converting it to another format using the ```def parseByteArray(inArray: Array[Byte]): T``` function.
As a trivial example ```ByteInputFormat``` and ```ByteRecordReader``` are included which just return the Array[Byte] from a given file.
Finally a RDD for ```BinaryFileInputFormat``` (to allow for easier partitioning changes as was done for WholeFileInput) was added and the appropriate byteFiles to the ```SparkContext``` so the functions can be easily used by others.
A common use case might be to read in a folder
```
sc.byteFiles("s3://mydrive/tif/*.tif").map(rawData => ReadTiffFromByteArray(rawData))
```
Author: Kevin Mader <kevinmader@gmail.com>
Author: Kevin Mader <kmader@users.noreply.github.com>
Closes#1658 from kmader/master and squashes the following commits:
3c49a30 [Kevin Mader] fixing wholetextfileinput to it has the same setMinPartitions function as in BinaryData files
359a096 [Kevin Mader] making the final corrections suggested by @mateiz and renaming a few functions to make their usage clearer
6379be4 [Kevin Mader] reorganizing code
7b9d181 [Kevin Mader] removing developer API, cleaning up imports
8ac288b [Kevin Mader] fixed a single slightly over 100 character line
92bda0d [Kevin Mader] added new tests, renamed files, fixed several of the javaapi functions, formatted code more nicely
a32fef7 [Kevin Mader] removed unneeded classes added DeveloperApi note to portabledatastreams since the implementation might change
49174d9 [Kevin Mader] removed unneeded classes added DeveloperApi note to portabledatastreams since the implementation might change
c27a8f1 [Kevin Mader] jenkins crashed before running anything last time, so making minor change
b348ce1 [Kevin Mader] fixed order in check (prefix only appears on jenkins not when I run unit tests locally)
0588737 [Kevin Mader] filename check in "binary file input as byte array" test now ignores prefixes and suffixes which might get added by Hadoop
4163e38 [Kevin Mader] fixing line length and output from FSDataInputStream to DataInputStream to minimize sensitivity to Hadoop API changes
19812a8 [Kevin Mader] Fixed the serialization issue with PortableDataStream since neither CombineFileSplit nor TaskAttemptContext implement the Serializable interface, by using ByteArrays for storing both and then recreating the objects from these bytearrays as needed.
238c83c [Kevin Mader] fixed several scala-style issues, changed structure of binaryFiles, removed excessive classes added new tests. The caching tests still have a serialization issue, but that should be easily fixed as well.
932a206 [Kevin Mader] Update RawFileInput.scala
a01c9cf [Kevin Mader] Update RawFileInput.scala
441f79a [Kevin Mader] fixed a few small comments and dependency
12e7be1 [Kevin Mader] removing imglib from maven (definitely not ready yet)
5deb79e [Kevin Mader] added new portabledatastream to code so that it can be serialized correctly
f032bc0 [Kevin Mader] fixed bug in path name, renamed tests
bc5c0b9 [Kevin Mader] made minor stylistic adjustments from mateiz
df8e528 [Kevin Mader] fixed line lengths and changed java test
9a313d5 [Kevin Mader] making classes that needn't be public private, adding automatic file closure, adding new tests
edf5829 [Kevin Mader] fixing line lengths, adding new lines
f4841dc [Kevin Mader] un-optimizing imports, silly intellij
eacfaa6 [Kevin Mader] Added FixedLengthBinaryInputFormat and RecordReader from freeman-lab and added them to both the JavaSparkContext and the SparkContext as fixedLengthBinaryFile
1622935 [Kevin Mader] changing the line lengths to make jenkins happy
1cfa38a [Kevin Mader] added apache headers, added datainputstream directly as an output option for more complicated readers (HDF5 perhaps), and renamed several of the functions and files to be more consistent. Also added parallel functions to the java api
84035f1 [Kevin Mader] adding binary and byte file support spark
81c5f12 [Kevin Mader] Merge pull request #1 from apache/master
More efficient sampling, based on Gap Sampling optimization:
http://erikerlandson.github.io/blog/2014/09/11/faster-random-samples-with-gap-sampling/
Author: Erik Erlandson <eerlands@redhat.com>
Closes#2455 from erikerlandson/spark-3250-pr and squashes the following commits:
72496bc [Erik Erlandson] [SPARK-3250] Implement Gap Sampling optimization for random sampling
We use "\<driver\>" everywhere. Let's not do that.
Author: Andrew Or <andrew@databricks.com>
Closes#3020 from andrewor14/consolidate-driver and squashes the following commits:
c1c2204 [Andrew Or] Just use "<driver>" for local executor ID
3d751e9 [Andrew Or] Consolidate usages of <driver>
The bulk of this PR is comprised of tests. All changes in functionality are made in `SparkSubmit.scala` (~20 lines).
**SPARK-3319.** There is currently a divergence in behavior when the user passes in additional jars through `--jars` and through setting `spark.jars` in the default properties file. The former will happily resolve the paths (e.g. convert `my.jar` to `file:/absolute/path/to/my.jar`), while the latter does not. We should resolve paths consistently in both cases. This also applies to the following pairs of command line arguments and Spark configs:
- `--jars` ~ `spark.jars`
- `--files` ~ `spark.files` / `spark.yarn.dist.files`
- `--archives` ~ `spark.yarn.dist.archives`
- `--py-files` ~ `spark.submit.pyFiles`
**SPARK-3338.** This PR also fixes the following bug: if the user sets `spark.submit.pyFiles` in his/her properties file, it does not actually get picked up even if `--py-files` is not set. This is simply because the config is overridden by an empty string.
Author: Andrew Or <andrewor14@gmail.com>
Author: Andrew Or <andrew@databricks.com>
Closes#2232 from andrewor14/resolve-config-paths and squashes the following commits:
fff2869 [Andrew Or] Add spark.yarn.jar
da3a1c1 [Andrew Or] Merge branch 'master' of github.com:apache/spark into resolve-config-paths
f0fae64 [Andrew Or] Merge branch 'master' of github.com:apache/spark into resolve-config-paths
05e03d6 [Andrew Or] Add tests for resolving both command line and config paths
460117e [Andrew Or] Resolve config paths properly
fe039d3 [Andrew Or] Beef up tests to test fixed-pointed-ness of Utils.resolveURI(s)
This is part of a bigger effort to provide elastic scaling of executors within a Spark application ([SPARK-3174](https://issues.apache.org/jira/browse/SPARK-3174)). This PR does not provide any functionality by itself; it is a skeleton that is missing a mechanism to be added later in [SPARK-3822](https://issues.apache.org/jira/browse/SPARK-3822).
Comments and feedback are most welcome. For those of you reviewing this in detail, I highly recommend doing it through your favorite IDE instead of through the diff here.
Author: Andrew Or <andrewor14@gmail.com>
Author: Andrew Or <andrew@databricks.com>
Closes#2746 from andrewor14/scaling-heuristics and squashes the following commits:
8a4fdaa [Andrew Or] Merge branch 'master' of github.com:apache/spark into scaling-heuristics
e045df8 [Andrew Or] Add warning message (minor)
dfa31ec [Andrew Or] Fix tests
c0becc4 [Andrew Or] Merging with SPARK-3822
4784f93 [Andrew Or] Reword an awkward log message
181f27f [Andrew Or] Merge branch 'master' of github.com:apache/spark into scaling-heuristics
c79e907 [Andrew Or] Merge branch 'master' of github.com:apache/spark into scaling-heuristics
4672b90 [Andrew Or] It's nano time.
a6a30f2 [Andrew Or] Do not allow min/max executors of 0
c60ec33 [Andrew Or] Rewrite test logic with clocks
b00b680 [Andrew Or] Fix style
c3caa65 [Andrew Or] Merge branch 'master' of github.com:apache/spark into scaling-heuristics
7f9da14 [Andrew Or] Factor out logic to verify bounds on # executors (minor)
f279019 [Andrew Or] Add time mocking tests for polling loop
685e347 [Andrew Or] Factor out clock in polling loop to facilitate testing
3cea7f7 [Andrew Or] Use PrivateMethodTester to keep original class private
3156d81 [Andrew Or] Update comments and exception messages
92f36f9 [Andrew Or] Address minor review comments
abdea61 [Andrew Or] Merge branch 'master' of github.com:apache/spark into scaling-heuristics
2aefd09 [Andrew Or] Correct listener behavior
9fe6e44 [Andrew Or] Rename variables and configs + update comments and log messages
149cc32 [Andrew Or] Fix style
254c958 [Andrew Or] Merge branch 'master' of github.com:apache/spark into scaling-heuristics
5ff829b [Andrew Or] Add tests for ExecutorAllocationManager
19c6c4b [Andrew Or] Merge branch 'master' of github.com:apache/spark into scaling-heuristics
5896515 [Andrew Or] Move ExecutorAllocationManager out of scheduler package
9ca8945 [Andrew Or] Rewrite callbacks through the listener interface
5e336b9 [Andrew Or] Remove code from backend to avoid conflict with SPARK-3822
092d1fd [Andrew Or] Remove timeout logic for pending requests
1309fab [Andrew Or] Request executors by specifying the number pending
8bc0e9d [Andrew Or] Add logic to expire pending requests after timeouts
b750ee1 [Andrew Or] Express timers in terms of expiration times + remove retry logic
7f8dd47 [Andrew Or] Merge branch 'master' of github.com:apache/spark into scaling-heuristics
9d516cc [Andrew Or] Bug fix: Actually trigger the add timer / add retry timer
44f1832 [Andrew Or] Rename configs to include time units
eaae7ef [Andrew Or] Address various review comments
6f8be6c [Andrew Or] Beef up comments on what each of the timers mean
baaa403 [Andrew Or] Simplify variable names (minor)
42beec8 [Andrew Or] Reset whether the add threshold is crossed on cancellation
9bcc0bc [Andrew Or] ExecutorScalingManager -> ExecutorAllocationManager
2784398 [Andrew Or] Merge branch 'master' of github.com:apache/spark into scaling-heuristics
5a97d9e [Andrew Or] Log retry attempts in INFO + clean up logging
2f55c9f [Andrew Or] Do not keep requesting executors even after max attempts
0acd1cb [Andrew Or] Rewrite timer logic with polling
b3c7d44 [Andrew Or] Start the retry timer for adding executors at the right time
9b5f2ea [Andrew Or] Wording changes in comments and log messages
c2203a5 [Andrew Or] Simplify code to access the scheduler backend
e519d08 [Andrew Or] Simplify initialization code
2cc87a7 [Andrew Or] Add retry logic for removing executors
d0b34a6 [Andrew Or] Add retry logic for adding executors
9cc4649 [Andrew Or] Simplifying synchronization logic
67c03c7 [Andrew Or] Correct semantics of adding executors + update comments
6c48ab0 [Andrew Or] Update synchronization comment
8901900 [Andrew Or] Simplify remove policy + change the semantics of add policy
1cc8444 [Andrew Or] Minor wording change
ae5b64a [Andrew Or] Add synchronization
20ec6b9 [Andrew Or] First cut implementation of removing executors dynamically
4077ae2 [Andrew Or] Minor code re-organization
6f1fa66 [Andrew Or] First cut implementation of adding executors dynamically
b2e6dcc [Andrew Or] Add skeleton interface for requesting / killing executors
This is part of a broader effort to enable dynamic scaling of executors ([SPARK-3174](https://issues.apache.org/jira/browse/SPARK-3174)). This is intended to work alongside SPARK-3795 (#2746), SPARK-3796 and SPARK-3797, but is functionally independently of these other issues.
The logic is built on top of PraveenSeluka's changes at #2798. This is different from the changes there in a few major ways: (1) the mechanism is implemented within the existing scheduler backend framework rather than in new `Actor` classes. This also introduces a parent abstract class `YarnSchedulerBackend` to encapsulate common logic to communicate with the Yarn `ApplicationMaster`. (2) The interface of requesting executors exposed to the `SparkContext` is the same, but the communication between the scheduler backend and the AM uses total number executors desired instead of an incremental number. This is discussed in #2746 and explained in the comments in the code.
I have tested this significantly on a stable Yarn cluster.
------------
A remaining task for this issue is to tone down the error messages emitted when an executor is removed.
Currently, `SparkContext` and its components react as if the executor has failed, resulting in many scary error messages and eventual timeouts. While it's not strictly necessary to fix this as of the first-cut implementation of this mechanism, it would be good to add logic to distinguish this case. I prefer to address this in a separate PR. I have filed a separate JIRA for this task at SPARK-4134.
Author: Andrew Or <andrew@databricks.com>
Author: Andrew Or <andrewor14@gmail.com>
Closes#2840 from andrewor14/yarn-scaling-mechanism and squashes the following commits:
485863e [Andrew Or] Minor log message changes
4920be8 [Andrew Or] Clarify that public API is only for Yarn mode for now
1c57804 [Andrew Or] Reword a few comments + other review comments
6321140 [Andrew Or] Merge branch 'master' of github.com:apache/spark into yarn-scaling-mechanism
02836c0 [Andrew Or] Limit scope of synchronization
4e2ed7f [Andrew Or] Fix bug: keep track of removed executors properly
73ade46 [Andrew Or] Wording changes (minor)
2a7a6da [Andrew Or] Add `sc.killExecutor` as a shorthand (minor)
665f229 [Andrew Or] Mima excludes
79aa2df [Andrew Or] Simplify the request interface by asking for a total
04f625b [Andrew Or] Fix race condition that causes over-allocation of executors
f4783f8 [Andrew Or] Change the semantics of requesting executors
005a124 [Andrew Or] Fix tests
4628b16 [Andrew Or] Merge branch 'master' of github.com:apache/spark into yarn-scaling-mechanism
db4a679 [Andrew Or] Merge branch 'master' of github.com:apache/spark into yarn-scaling-mechanism
572f5c5 [Andrew Or] Unused import (minor)
f30261c [Andrew Or] Kill multiple executors rather than one at a time
de260d9 [Andrew Or] Simplify by skipping useless null check
9c52542 [Andrew Or] Simplify by skipping the TaskSchedulerImpl
97dd1a8 [Andrew Or] Merge branch 'master' of github.com:apache/spark into yarn-scaling-mechanism
d987b3e [Andrew Or] Move addWebUIFilters to Yarn scheduler backend
7b76d0a [Andrew Or] Expose mechanism in SparkContext as developer API
47466cd [Andrew Or] Refactor common Yarn scheduler backend logic
c4dfaac [Andrew Or] Avoid thrashing when removing executors
53e8145 [Andrew Or] Start yarn actor early to listen for AM registration message
bbee669 [Andrew Or] Add mechanism in yarn client mode
This PR encapsulates #2330, which is itself a continuation of #2240. The first goal of this PR is to provide an alternate, simpler implementation of the ConnectionManager which is based on Netty.
In addition to this goal, however, we want to resolve [SPARK-3796](https://issues.apache.org/jira/browse/SPARK-3796), which calls for a standalone shuffle service which can be integrated into the YARN NodeManager, Standalone Worker, or on its own. This PR makes the first step in this direction by ensuring that the actual Netty service is as small as possible and extracted from Spark core. Given this, we should be able to construct this standalone jar which can be included in other JVMs without incurring significant dependency or runtime issues. The actual work to ensure that such a standalone shuffle service would work in Spark will be left for a future PR, however.
In order to minimize dependencies and allow for the service to be long-running (possibly much longer-running than Spark, and possibly having to support multiple version of Spark simultaneously), the entire service has been ported to Java, where we have full control over the binary compatibility of the components and do not depend on the Scala runtime or version.
These issues: have been addressed by folding in #2330:
SPARK-3453: Refactor Netty module to use BlockTransferService interface
SPARK-3018: Release all buffers upon task completion/failure
SPARK-3002: Create a connection pool and reuse clients across different threads
SPARK-3017: Integration tests and unit tests for connection failures
SPARK-3049: Make sure client doesn't block when server/connection has error(s)
SPARK-3502: SO_RCVBUF and SO_SNDBUF should be bootstrap childOption, not option
SPARK-3503: Disable thread local cache in PooledByteBufAllocator
TODO before mergeable:
- [x] Implement uploadBlock()
- [x] Unit tests for RPC side of code
- [x] Performance testing (see comments [here](https://github.com/apache/spark/pull/2753#issuecomment-59475022))
- [x] Turn OFF by default (currently on for unit testing)
Author: Reynold Xin <rxin@apache.org>
Author: Aaron Davidson <aaron@databricks.com>
Author: cocoatomo <cocoatomo77@gmail.com>
Author: Patrick Wendell <pwendell@gmail.com>
Author: Prashant Sharma <prashant.s@imaginea.com>
Author: Davies Liu <davies.liu@gmail.com>
Author: Anand Avati <avati@redhat.com>
Closes#2753 from aarondav/netty and squashes the following commits:
cadfd28 [Aaron Davidson] Turn netty off by default
d7be11b [Aaron Davidson] Turn netty on by default
4a204b8 [Aaron Davidson] Fail block fetches if client connection fails
2b0d1c0 [Aaron Davidson] 100ch
0c5bca2 [Aaron Davidson] Merge branch 'master' of https://github.com/apache/spark into netty
14e37f7 [Aaron Davidson] Address Reynold's comments
8dfcceb [Aaron Davidson] Merge branch 'master' of https://github.com/apache/spark into netty
322dfc1 [Aaron Davidson] Address Reynold's comments, including major rename
e5675a4 [Aaron Davidson] Fail outstanding RPCs as well
ccd4959 [Aaron Davidson] Don't throw exception if client immediately fails
9da0bc1 [Aaron Davidson] Add RPC unit tests
d236dfd [Aaron Davidson] Remove no-op serializer :)
7b7a26c [Aaron Davidson] Fix Nio compile issue
dd420fd [Aaron Davidson] Merge branch 'master' of https://github.com/apache/spark into netty-test
939f276 [Aaron Davidson] Attempt to make comm. bidirectional
aa58f67 [cocoatomo] [SPARK-3909][PySpark][Doc] A corrupted format in Sphinx documents and building warnings
8dc1ded [cocoatomo] [SPARK-3867][PySpark] ./python/run-tests failed when it run with Python 2.6 and unittest2 is not installed
5b5dbe6 [Prashant Sharma] [SPARK-2924] Required by scala 2.11, only one fun/ctor amongst overriden alternatives, can have default argument(s).
2c5d9dc [Patrick Wendell] HOTFIX: Fix build issue with Akka 2.3.4 upgrade.
020691e [Davies Liu] [SPARK-3886] [PySpark] use AutoBatchedSerializer by default
ae4083a [Anand Avati] [SPARK-2805] Upgrade Akka to 2.3.4
29c6dcf [Aaron Davidson] [SPARK-3453] Netty-based BlockTransferService, extracted from Spark core
f7e7568 [Reynold Xin] Fixed spark.shuffle.io.receiveBuffer setting.
5d98ce3 [Reynold Xin] Flip buffer.
f6c220d [Reynold Xin] Merge with latest master.
407e59a [Reynold Xin] Fix style violation.
a0518c7 [Reynold Xin] Implemented block uploads.
4b18db2 [Reynold Xin] Copy the buffer in fetchBlockSync.
bec4ea2 [Reynold Xin] Removed OIO and added num threads settings.
1bdd7ee [Reynold Xin] Fixed tests.
d68f328 [Reynold Xin] Logging close() in case close() fails.
f63fb4c [Reynold Xin] Add more debug message.
6afc435 [Reynold Xin] Added logging.
c066309 [Reynold Xin] Implement java.io.Closeable interface.
519d64d [Reynold Xin] Mark private package visibility and MimaExcludes.
f0a16e9 [Reynold Xin] Fixed test hanging.
14323a5 [Reynold Xin] Removed BlockManager.getLocalShuffleFromDisk.
b2f3281 [Reynold Xin] Added connection pooling.
d23ed7b [Reynold Xin] Incorporated feedback from Norman: - use same pool for boss and worker - remove ioratio - disable caching of byte buf allocator - childoption sendbuf/receivebuf - fire exception through pipeline
9e0cb87 [Reynold Xin] Fixed BlockClientHandlerSuite
5cd33d7 [Reynold Xin] Fixed style violation.
cb589ec [Reynold Xin] Added more test cases covering cleanup when fault happens in ShuffleBlockFetcherIteratorSuite
1be4e8e [Reynold Xin] Shorten NioManagedBuffer and NettyManagedBuffer class names.
108c9ed [Reynold Xin] Forgot to add TestSerializer to the commit list.
b5c8d1f [Reynold Xin] Fixed ShuffleBlockFetcherIteratorSuite.
064747b [Reynold Xin] Reference count buffers and clean them up properly.
2b44cf1 [Reynold Xin] Added more documentation.
1760d32 [Reynold Xin] Use Epoll.isAvailable in BlockServer as well.
165eab1 [Reynold Xin] [SPARK-3453] Refactor Netty module to use BlockTransferService.
I forgot to disable the benchmark code in #2937, which increased the Jenkins build time by couple minutes.
aarondav
Author: Xiangrui Meng <meng@databricks.com>
Closes#2990 from mengxr/disable-benchmark and squashes the following commits:
c58f070 [Xiangrui Meng] disable benchmark code
`zeroValue` will be serialized by `spark.closure.serializer` but `spark.closure.serializer` only supports the default Java serializer. So it must not be `ClassWithoutNoArgConstructor`, which can not be serialized by the Java serializer.
This PR changed `zeroValue` to null and updated the test to make it work correctly.
Author: zsxwing <zsxwing@gmail.com>
Closes#2856 from zsxwing/SPARK-4008 and squashes the following commits:
51da655 [zsxwing] [SPARK-4008] Fix "kryo with fold" in KryoSerializerSuite
Sorter uses generic-typed key for sorting. When data is large, it creates lots of key objects, which is not efficient. We should reuse the key in Sorter for memory efficiency. This change is part of the petabyte sort implementation from rxin .
The `Sorter` class was written in Java and marked package private. So it is only available to `org.apache.spark.util.collection`. I renamed it to `TimSort` and add a simple wrapper of it, still called `Sorter`, in Scala, which is `private[spark]`.
The benchmark code is updated, which now resets the array before each run. Here is the result on sorting primitive Int arrays of size 25 million using Sorter:
~~~
[info] - Sorter benchmark for key-value pairs !!! IGNORED !!!
Java Arrays.sort() on non-primitive int array: Took 13237 ms
Java Arrays.sort() on non-primitive int array: Took 13320 ms
Java Arrays.sort() on non-primitive int array: Took 15718 ms
Java Arrays.sort() on non-primitive int array: Took 13283 ms
Java Arrays.sort() on non-primitive int array: Took 13267 ms
Java Arrays.sort() on non-primitive int array: Took 15122 ms
Java Arrays.sort() on non-primitive int array: Took 15495 ms
Java Arrays.sort() on non-primitive int array: Took 14877 ms
Java Arrays.sort() on non-primitive int array: Took 16429 ms
Java Arrays.sort() on non-primitive int array: Took 14250 ms
Java Arrays.sort() on non-primitive int array: (13878 ms first try, 14499 ms average)
Java Arrays.sort() on primitive int array: Took 2683 ms
Java Arrays.sort() on primitive int array: Took 2683 ms
Java Arrays.sort() on primitive int array: Took 2701 ms
Java Arrays.sort() on primitive int array: Took 2746 ms
Java Arrays.sort() on primitive int array: Took 2685 ms
Java Arrays.sort() on primitive int array: Took 2735 ms
Java Arrays.sort() on primitive int array: Took 2669 ms
Java Arrays.sort() on primitive int array: Took 2693 ms
Java Arrays.sort() on primitive int array: Took 2680 ms
Java Arrays.sort() on primitive int array: Took 2642 ms
Java Arrays.sort() on primitive int array: (2948 ms first try, 2691 ms average)
Sorter without key reuse on primitive int array: Took 10732 ms
Sorter without key reuse on primitive int array: Took 12482 ms
Sorter without key reuse on primitive int array: Took 10718 ms
Sorter without key reuse on primitive int array: Took 12650 ms
Sorter without key reuse on primitive int array: Took 10747 ms
Sorter without key reuse on primitive int array: Took 10783 ms
Sorter without key reuse on primitive int array: Took 12721 ms
Sorter without key reuse on primitive int array: Took 10604 ms
Sorter without key reuse on primitive int array: Took 10622 ms
Sorter without key reuse on primitive int array: Took 11843 ms
Sorter without key reuse on primitive int array: (11089 ms first try, 11390 ms average)
Sorter with key reuse on primitive int array: Took 5141 ms
Sorter with key reuse on primitive int array: Took 5298 ms
Sorter with key reuse on primitive int array: Took 5066 ms
Sorter with key reuse on primitive int array: Took 5164 ms
Sorter with key reuse on primitive int array: Took 5203 ms
Sorter with key reuse on primitive int array: Took 5274 ms
Sorter with key reuse on primitive int array: Took 5186 ms
Sorter with key reuse on primitive int array: Took 5159 ms
Sorter with key reuse on primitive int array: Took 5164 ms
Sorter with key reuse on primitive int array: Took 5078 ms
Sorter with key reuse on primitive int array: (5311 ms first try, 5173 ms average)
~~~
So with key reuse, it is faster and less likely to trigger GC.
Author: Xiangrui Meng <meng@databricks.com>
Author: Reynold Xin <rxin@apache.org>
Closes#2937 from mengxr/SPARK-4084 and squashes the following commits:
d73c3d0 [Xiangrui Meng] address comments
0b7b682 [Xiangrui Meng] fix mima
a72f53c [Xiangrui Meng] update timeIt
38ba50c [Xiangrui Meng] update timeIt
720f731 [Xiangrui Meng] add doc about JIT specialization
78f2879 [Xiangrui Meng] update tests
7de2efd [Xiangrui Meng] update the Sorter benchmark code to be correct
8626356 [Xiangrui Meng] add prepare to timeIt and update testsin SorterSuite
5f0d530 [Xiangrui Meng] update method modifiers of SortDataFormat
6ffbe66 [Xiangrui Meng] rename Sorter to TimSort and add a Scala wrapper that is private[spark]
b00db4d [Xiangrui Meng] doc and tests
cf94e8a [Xiangrui Meng] renaming
464ddce [Reynold Xin] cherry-pick rxin's commit
A global UTF8 constant is very helpful to handle encoding problems when converting between String and bytes. There are several solutions here:
1. Add `val UTF_8 = Charset.forName("UTF-8")` to Utils.scala
2. java.nio.charset.StandardCharsets.UTF_8 (require JDK7)
3. io.netty.util.CharsetUtil.UTF_8
4. com.google.common.base.Charsets.UTF_8
5. org.apache.commons.lang.CharEncoding.UTF_8
6. org.apache.commons.lang3.CharEncoding.UTF_8
IMO, I prefer option 1) because people can find it easily.
This is a PR for option 1) and only fixes Spark Core.
Author: zsxwing <zsxwing@gmail.com>
Closes#2781 from zsxwing/SPARK-3922 and squashes the following commits:
f974edd [zsxwing] Merge branch 'master' into SPARK-3922
2d27423 [zsxwing] Refactor spark-core to use Refactor spark-core to use Utils.UTF_8
This avoids reading torrent broadcast variables when they are referenced in the closure but not used in the closure. This is done by using a `lazy val` to read broadcast blocks
cc rxin JoshRosen for review
Author: Shivaram Venkataraman <shivaram@cs.berkeley.edu>
Closes#2871 from shivaram/broadcast-read-value and squashes the following commits:
1456d65 [Shivaram Venkataraman] Use getUsedTimeMs and remove readObject
d6c5ee9 [Shivaram Venkataraman] Use laxy val to implement readBroadcastBlock
0b34df7 [Shivaram Venkataraman] Merge branch 'master' of https://github.com/apache/spark into broadcast-read-value
9cec507 [Shivaram Venkataraman] Test if broadcast variables are read lazily
768b40b [Shivaram Venkataraman] Merge branch 'master' of https://github.com/apache/spark into broadcast-read-value
8792ed8 [Shivaram Venkataraman] Make torrent broadcast read blocks on use. This avoids reading broadcast variables when they are referenced in the closure but not used by the code.
`read()` may return fewer bytes than requested; when this occurred, the old code would silently return less data than requested, which might cause stream corruption errors. `skip()` faces similar issues, too.
This patch fixes several cases where we mis-handle these methods' return values.
Author: Josh Rosen <joshrosen@databricks.com>
Closes#2969 from JoshRosen/file-channel-read-fix and squashes the following commits:
e724a9f [Josh Rosen] Fix similar issue of not checking skip() return value.
cbc03ce [Josh Rosen] Update the other log message, too.
01e6015 [Josh Rosen] file.getName -> file.getAbsolutePath
d961d95 [Josh Rosen] Fix another issue in FileServerSuite.
b9265d2 [Josh Rosen] Fix a similar (minor) issue in TestUtils.
cd9d76f [Josh Rosen] Fix a similar error in Tachyon:
3db0008 [Josh Rosen] Fix a similar read() error in Utils.offsetBytes().
db985ed [Josh Rosen] Fix unsafe usage of FileChannel.read():
This change replaces usages of colt with commons-math3 equivalents, and makes some minor necessary adjustments to related code and tests to match.
Author: Sean Owen <sowen@cloudera.com>
Closes#2928 from srowen/SPARK-4022 and squashes the following commits:
61a232f [Sean Owen] Fix failure due to different sampling in JavaAPISuite.sample()
16d66b8 [Sean Owen] Simplify seeding with call to reseedRandomGenerator
a1a78e0 [Sean Owen] Use Well19937c
31c7641 [Sean Owen] Fix Python Poisson test by choosing a different seed; about 88% of seeds should work but 1 didn't, it seems
5c9c67f [Sean Owen] Additional test fixes from review
d8f88e0 [Sean Owen] Replace colt with commons-math3. Some tests do not pass yet.
The patch takes advantage an API provided in Hadoop 2.5 that allows getting accurate data on Hadoop FileSystem bytes read. It eliminates the old method, which naively accepts the split size as the input bytes. An impact of this change will be that input metrics go away when using against Hadoop versions earlier thatn 2.5. I can add this back in, but my opinion is that no metrics are better than inaccurate metrics.
This is difficult to write a test for because we don't usually build against a version of Hadoop that contains the function we need. I've tested it manually on a pseudo-distributed cluster.
Author: Sandy Ryza <sandy@cloudera.com>
Closes#2087 from sryza/sandy-spark-2621 and squashes the following commits:
23010b8 [Sandy Ryza] Missing style fixes
74fc9bb [Sandy Ryza] Make getFSBytesReadOnThreadCallback private
1ab662d [Sandy Ryza] Clear things up a bit
984631f [Sandy Ryza] Switch from pull to push model and add test
7ef7b22 [Sandy Ryza] Add missing curly braces
219abc9 [Sandy Ryza] Fall back to split size
90dbc14 [Sandy Ryza] SPARK-2621. Update task InputMetrics incrementally
This change makes the destroy function public for broadcast variables. Motivation for the change is described in https://issues.apache.org/jira/browse/SPARK-4030.
This patch also logs where destroy was called from if a broadcast variable is used after destruction.
Author: Shivaram Venkataraman <shivaram@cs.berkeley.edu>
Closes#2922 from shivaram/broadcast-destroy and squashes the following commits:
a11abab [Shivaram Venkataraman] Fix scala style in Utils.scala
bed9c9d [Shivaram Venkataraman] Make destroy blocking by default
e80c1ab [Shivaram Venkataraman] Make destroy public for broadcast variables Also log where destroy was called from if a broadcast variable is used after destruction.
This patch adds Selenium tests for Spark's web UI. To avoid adding extra
dependencies to the test environment, the tests use Selenium's HtmlUnitDriver,
which is pure-Java, instead of, say, ChromeDriver.
I added new tests to try to reproduce a few UI bugs reported on JIRA, namely
SPARK-3021, SPARK-2105, and SPARK-2527. I wasn't able to reproduce these bugs;
I suspect that the older ones might have been fixed by other patches.
In order to use HtmlUnitDriver, I added an explicit dependency on the
org.apache.httpcomponents version of httpclient in order to prevent jets3t's
older version from taking precedence on the classpath.
I also upgraded ScalaTest to 2.2.1.
Author: Josh Rosen <joshrosen@apache.org>
Author: Josh Rosen <joshrosen@databricks.com>
Closes#2474 from JoshRosen/webui-selenium-tests and squashes the following commits:
fcc9e83 [Josh Rosen] scalautils -> scalactic package rename
510e54a [Josh Rosen] [SPARK-3616] Add basic Selenium tests to WebUISuite.
This pull request is a first step towards the implementation of a stable, pull-based progress / status API for Spark (see [SPARK-2321](https://issues.apache.org/jira/browse/SPARK-2321)). For now, I'd like to discuss the basic implementation, API names, and overall interface design. Once we arrive at a good design, I'll go back and add additional methods to expose more information via these API.
#### Design goals:
- Pull-based API
- Usable from Java / Scala / Python (eventually, likely with a wrapper)
- Can be extended to expose more information without introducing binary incompatibilities.
- Returns immutable objects.
- Don't leak any implementation details, preserving our freedom to change the implementation.
#### Implementation:
- Add public methods (`getJobInfo`, `getStageInfo`) to SparkContext to allow status / progress information to be retrieved.
- Add public interfaces (`SparkJobInfo`, `SparkStageInfo`) for our API return values. These interfaces consist entirely of Java-style getter methods. The interfaces are currently implemented in Java. I decided to explicitly separate the interface from its implementation (`SparkJobInfoImpl`, `SparkStageInfoImpl`) in order to prevent users from constructing these responses themselves.
-Allow an existing JobProgressListener to be used when constructing a live SparkUI. This allows us to re-use this listeners in the implementation of this status API. There are a few reasons why this listener re-use makes sense:
- The status API and web UI are guaranteed to show consistent information.
- These listeners are already well-tested.
- The same garbage-collection / information retention configurations can apply to both this API and the web UI.
- Extend JobProgressListener to maintain `jobId -> Job` and `stageId -> Stage` mappings.
The progress API methods are implemented in a separate trait that's mixed into SparkContext. This helps to avoid SparkContext.scala from becoming larger and more difficult to read.
Author: Josh Rosen <joshrosen@databricks.com>
Author: Josh Rosen <joshrosen@apache.org>
Closes#2696 from JoshRosen/progress-reporting-api and squashes the following commits:
e6aa78d [Josh Rosen] Add tests.
b585c16 [Josh Rosen] Accept SparkListenerBus instead of more specific subclasses.
c96402d [Josh Rosen] Address review comments.
2707f98 [Josh Rosen] Expose current stage attempt id
c28ba76 [Josh Rosen] Update demo code:
646ff1d [Josh Rosen] Document spark.ui.retainedJobs.
7f47d6d [Josh Rosen] Clean up SparkUI constructors, per Andrew's feedback.
b77b3d8 [Josh Rosen] Merge remote-tracking branch 'origin/master' into progress-reporting-api
787444c [Josh Rosen] Move status API methods into trait that can be mixed into SparkContext.
f9a9a00 [Josh Rosen] More review comments:
3dc79af [Josh Rosen] Remove creation of unused listeners in SparkContext.
249ca16 [Josh Rosen] Address several review comments:
da5648e [Josh Rosen] Add example of basic progress reporting in Java.
7319ffd [Josh Rosen] Add getJobIdsForGroup() and num*Tasks() methods.
cc568e5 [Josh Rosen] Add note explaining that interfaces should not be implemented outside of Spark.
6e840d4 [Josh Rosen] Remove getter-style names and "consistent snapshot" semantics:
08cbec9 [Josh Rosen] Begin to sketch the interfaces for a stable, public status API.
ac2d13a [Josh Rosen] Add jobId->stage, stageId->stage mappings in JobProgressListener
24de263 [Josh Rosen] Create UI listeners in SparkContext instead of in Tabs:
In deploy.ClientArguments.isValidJarUrl, the url is checked as follows.
def isValidJarUrl(s: String): Boolean = s.matches("(.+):(.+)jar")
So, it allows like 'hdfs:file.jar' (no authority).
Author: Kousuke Saruta <sarutak@oss.nttdata.co.jp>
Closes#2925 from sarutak/uri-syntax-check-improvement and squashes the following commits:
cf06173 [Kousuke Saruta] Improved URI syntax checking
This commit fixes a bug in MapStatus that could cause jobs to wrongly return
empty results if those jobs contained stages with more than 2000 partitions
where most of those partitions were empty.
For jobs with > 2000 partitions, MapStatus uses HighlyCompressedMapStatus,
which only stores the average size of blocks. If the average block size is
zero, then this will cause all blocks to be reported as empty, causing
BlockFetcherIterator to mistakenly skip them.
For example, this would return an empty result:
sc.makeRDD(0 until 10, 1000).repartition(2001).collect()
This can also lead to deserialization errors (e.g. Snappy decoding errors)
for jobs with > 2000 partitions where the average block size is non-zero but
there is at least one empty block. In this case, the BlockFetcher attempts to
fetch empty blocks and fails when trying to deserialize them.
The root problem here is that MapStatus has a (previously undocumented)
correctness property that was violated by HighlyCompressedMapStatus:
If a block is non-empty, then getSizeForBlock must be non-zero.
I fixed this by modifying HighlyCompressedMapStatus to store the average size
of _non-empty_ blocks and to use a compressed bitmap to track which blocks are
empty.
I also removed a test which was broken as originally written: it attempted
to check that HighlyCompressedMapStatus's size estimation error was < 10%,
but this was broken because HighlyCompressedMapStatus is only used for map
statuses with > 2000 partitions, but the test only created 50.
Author: Josh Rosen <joshrosen@databricks.com>
Closes#2866 from JoshRosen/spark-4019 and squashes the following commits:
fc8b490 [Josh Rosen] Roll back hashset change, which didn't improve performance.
5faa0a4 [Josh Rosen] Incorporate review feedback
c8b8cae [Josh Rosen] Two performance fixes:
3b892dd [Josh Rosen] Address Reynold's review comments
ba2e71c [Josh Rosen] Add missing newline
609407d [Josh Rosen] Use Roaring Bitmap to track non-empty blocks.
c23897a [Josh Rosen] Use sets when comparing collect() results
91276a3 [Josh Rosen] [SPARK-4019] Fix MapStatus compression bug that could lead to empty results.
This PR fixes SPARK-3426, an issue where sort-based shuffle crashes if the
`spark.shuffle.spill.compress` and `spark.shuffle.compress` settings have
different values.
The problem is that sort-based shuffle's read and write paths use different
settings for determining whether to apply compression. ExternalSorter writes
runs to files using `TempBlockId` ids, which causes
`spark.shuffle.spill.compress` to be used for enabling compression, but these
spilled files end up being shuffled over the network and read as shuffle files
using `ShuffleBlockId` by BlockStoreShuffleFetcher, which causes
`spark.shuffle.compress` to be used for enabling decompression. As a result,
this leads to errors when these settings disagree.
Based on the discussions in #2247 and #2178, it sounds like we don't want to
remove the `spark.shuffle.spill.compress` setting. Therefore, I've tried to
come up with a fix where `spark.shuffle.spill.compress` is used to compress
data that's read and written locally and `spark.shuffle.compress` is used to
compress any data that will be fetched / read as shuffle blocks.
To do this, I split `TempBlockId` into two new id types, `TempLocalBlockId` and
`TempShuffleBlockId`, which map to `spark.shuffle.spill.compress` and
`spark.shuffle.compress`, respectively. ExternalAppendOnlyMap also used temp
blocks for spilling data. It looks like ExternalSorter was designed to be
a generic sorter but its configuration already happens to be tied to sort-based
shuffle, so I think it's fine if we use `spark.shuffle.compress` to compress
its spills; we can move the compression configuration to the constructor in
a later commit if we find that ExternalSorter is being used in other contexts
where we want different configuration options to control compression. To
summarize:
**Before:**
| | ExternalAppendOnlyMap | ExternalSorter |
|-------|------------------------------|------------------------------|
| Read | spark.shuffle.spill.compress | spark.shuffle.compress |
| Write | spark.shuffle.spill.compress | spark.shuffle.spill.compress |
**After:**
| | ExternalAppendOnlyMap | ExternalSorter |
|-------|------------------------------|------------------------|
| Read | spark.shuffle.spill.compress | spark.shuffle.compress |
| Write | spark.shuffle.spill.compress | spark.shuffle.compress |
Thanks to andrewor14 for debugging this with me!
Author: Josh Rosen <joshrosen@databricks.com>
Closes#2890 from JoshRosen/SPARK-3426 and squashes the following commits:
1921cf6 [Josh Rosen] Minor edit for clarity.
c8dd8f2 [Josh Rosen] Add comment explaining use of createTempShuffleBlock().
2c687b9 [Josh Rosen] Fix SPARK-3426.
91e7e40 [Josh Rosen] Combine tests into single test of all combinations
76ca65e [Josh Rosen] Add regression test for SPARK-3426.
Author: Sandy Ryza <sandy@cloudera.com>
Closes#789 from sryza/sandy-spark-1813 and squashes the following commits:
48b05e9 [Sandy Ryza] Simplify
b824932 [Sandy Ryza] Allow both spark.kryo.classesToRegister and spark.kryo.registrator at the same time
6a15bb7 [Sandy Ryza] Small fix
a2278c0 [Sandy Ryza] Respond to review comments
6ef592e [Sandy Ryza] SPARK-1813. Add a utility to SparkConf that makes using Kryo really easy
This PR makes several changes to TorrentBroadcast in order to make
it easier to reason about, which should help when debugging SPARK-3958.
The key changes:
- Remove all state from the global TorrentBroadcast object. This state
consisted mainly of configuration options, like the block size and
compression codec, and was read by the blockify / unblockify methods.
Unfortunately, the use of `lazy val` for `BLOCK_SIZE` meant that the block
size was always determined by the first SparkConf that TorrentBroadast was
initialized with; as a result, unit tests could not properly test
TorrentBroadcast with different block sizes.
Instead, blockifyObject and unBlockifyObject now accept compression codecs
and blockSizes as arguments. These arguments are supplied at the call sites
inside of TorrentBroadcast instances. Each TorrentBroadcast instance
determines these values from SparkEnv's SparkConf. I was careful to ensure
that we do not accidentally serialize CompressionCodec or SparkConf objects
as part of the TorrentBroadcast object.
- Remove special-case handling of local-mode in TorrentBroadcast. I don't
think that broadcast implementations should know about whether we're running
in local mode. If we want to optimize the performance of broadcast in local
mode, then we should detect this at a higher level and use a dummy
LocalBroadcastFactory implementation instead.
Removing this code fixes a subtle error condition: in the old local mode
code, a failure to find the broadcast in the local BlockManager would lead
to an attempt to deblockify zero blocks, which could lead to confusing
deserialization or decompression errors when we attempted to decompress
an empty byte array. This should never have happened, though: a failure to
find the block in local mode is evidence of some other error. The changes
here will make it easier to debug those errors if they ever happen.
- Add a check that throws an exception when attempting to deblockify an
empty array.
- Use ScalaCheck to add a test to check that TorrentBroadcast's
blockifyObject and unBlockifyObject methods are inverses.
- Misc. cleanup and logging improvements.
Author: Josh Rosen <joshrosen@databricks.com>
Closes#2844 from JoshRosen/torrentbroadcast-bugfix and squashes the following commits:
1e8268d [Josh Rosen] Address Reynold's review comments
2a9fdfd [Josh Rosen] Address Reynold's review comments.
c3b08f9 [Josh Rosen] Update TorrentBroadcast tests to reflect removal of special local-mode optimizations.
5c22782 [Josh Rosen] Store broadcast variable's value in the driver.
33fc754 [Josh Rosen] Change blockify/unblockifyObject to accept serializer as argument.
618a872 [Josh Rosen] [SPARK-3958] TorrentBroadcast cleanup / debugging improvements.
This PR adds a Java API for AsyncRDDActions and promotes the API from `Experimental` to stable.
Author: Josh Rosen <joshrosen@apache.org>
Author: Josh Rosen <joshrosen@databricks.com>
Closes#2760 from JoshRosen/async-rdd-actions-in-java and squashes the following commits:
0d45fbc [Josh Rosen] Whitespace fix.
ad3ae53 [Josh Rosen] Merge remote-tracking branch 'origin/master' into async-rdd-actions-in-java
c0153a5 [Josh Rosen] Remove unused variable.
e8e2867 [Josh Rosen] Updates based on Marcelo's review feedback
7a1417f [Josh Rosen] Removed unnecessary java.util import.
6f8f6ac [Josh Rosen] Fix import ordering.
ff28e49 [Josh Rosen] Add MiMa excludes and fix a scalastyle error.
346e46e [Josh Rosen] [SPARK-3902] Stabilize AsyncRDDActions; add Java API.
This is a small number of clean-up changes on top of #2782. Closes#2782.
Author: Prashant Sharma <prashant.s@imaginea.com>
Author: Patrick Wendell <pwendell@gmail.com>
Closes#2803 from pwendell/pr-2782 and squashes the following commits:
56d5b7a [Patrick Wendell] Minor clean-up
44089ec [Patrick Wendell] Clean-up the TaskContext API.
ed551ce [Prashant Sharma] Fixed a typo
df261d0 [Prashant Sharma] Josh's suggestion
facf3b1 [Prashant Sharma] Fixed the mima issue.
7ecc2fe [Prashant Sharma] CR, Moved implementations to TaskContextImpl
bbd9e05 [Prashant Sharma] adding missed out files to git.
ef633f5 [Prashant Sharma] SPARK-3874, Provide stable TaskContext API
This is another implementation about #1256
cc andrewor14 vanzin
Author: GuoQiang Li <witgo@qq.com>
Closes#2379 from witgo/SPARK-2098-new and squashes the following commits:
4ef1cbd [GuoQiang Li] review commit
49ef70e [GuoQiang Li] Refactor getDefaultPropertiesFile
c45d20c [GuoQiang Li] All Spark processes should support spark-defaults.conf, config file
Validate the memory is greater than zero when set from the SPARK_WORKER_MEMORY environment variable or command line without a g or m label. Added unit tests. If memory is 0 an IllegalStateException is thrown. Updated unit tests to mock environment variables by subclassing SparkConf (tip provided by Josh Rosen). Updated WorkerArguments to use SparkConf.getenv instead of System.getenv for reading the SPARK_WORKER_MEMORY environment variable.
Author: Bill Bejeck <bbejeck@gmail.com>
Closes#2309 from bbejeck/spark-memory-worker and squashes the following commits:
51cf915 [Bill Bejeck] SPARK-3178 - Validate the memory is greater than zero when set from the SPARK_WORKER_MEMORY environment variable or command line without a g or m label. Added unit tests. If memory is 0 an IllegalStateException is thrown. Updated unit tests to mock environment variables by subclassing SparkConf (tip provided by Josh Rosen). Updated WorkerArguments to use SparkConf.getenv instead of System.getenv for reading the SPARK_WORKER_MEMORY environment variable.
The goal of this patch is to fix the swapped arguments in standalone mode, which was caused by 79e45c9323 (diff-79391110e9f26657e415aa169a004998R153).
More details can be found in the JIRA: [SPARK-3921](https://issues.apache.org/jira/browse/SPARK-3921)
Tested in Standalone mode, but not in Mesos.
Author: Aaron Davidson <aaron@databricks.com>
Closes#2779 from aarondav/fix-standalone and squashes the following commits:
725227a [Aaron Davidson] Fix ExecutorRunnerTest
9d703fe [Aaron Davidson] [SPARK-3921] Fix CoarseGrainedExecutorBackend's arguments for Standalone mode
val path = ... //path to seq file with BytesWritable as type of both key and value
val file = sc.sequenceFile[Array[Byte],Array[Byte]](path)
file.take(1)(0)._1
This prints incorrect content of byte array. Actual content starts with correct one and some "random" bytes and zeros are appended. BytesWritable has two methods:
getBytes() - return content of all internal array which is often longer then actual value stored. It usually contains the rest of previous longer values
copyBytes() - return just begining of internal array determined by internal length property
It looks like in implicit conversion between BytesWritable and Array[byte] getBytes is used instead of correct copyBytes.
dbtsai
Author: Jakub Dubovský <james64@inMail.sk>
Author: Dubovsky Jakub <dubovsky@avast.com>
Closes#2712 from james64/3121-bugfix and squashes the following commits:
f85d24c [Jakub Dubovský] Test name changed, comments added
1b20d51 [Jakub Dubovský] Import placed correctly
406e26c [Jakub Dubovský] Scala style fixed
f92ffa6 [Dubovsky Jakub] performance tuning
480f9cd [Dubovsky Jakub] Bug 3121 fixed
When reporting that a remote error occurred, the ConnectionManager should also log the stacktrace of the remote exception. This PR accomplishes this by sending the remote exception's stacktrace as the payload in the "negative ACK / error message."
Author: Josh Rosen <joshrosen@apache.org>
Closes#2741 from JoshRosen/propagate-cm-exceptions-to-sender and squashes the following commits:
b5366cc [Josh Rosen] Explicitly encode error messages using UTF-8.
cef18b3 [Josh Rosen] [SPARK-3887] Send stracktrace in ConnectionManager error messages.
...riden alternatives, can have default argument.
Author: Prashant Sharma <prashant.s@imaginea.com>
Closes#2750 from ScrapCodes/SPARK-2924/default-args-removed and squashes the following commits:
d9785c3 [Prashant Sharma] [SPARK-2924] Required by scala 2.11, only one function/ctor amongst overriden alternatives, can have default argument.
This is a second rev of the Akka upgrade (earlier merged, but reverted). I made a slight modification which is that I also upgrade Hive to deal with a compatibility issue related to the protocol buffers library.
Author: Anand Avati <avati@redhat.com>
Author: Patrick Wendell <pwendell@gmail.com>
Closes#2752 from pwendell/akka-upgrade and squashes the following commits:
4c7ca3f [Patrick Wendell] Upgrading to new hive->protobuf version
57a2315 [Anand Avati] SPARK-1812: streaming - remove tests which depend on akka.actor.IO
2a551d3 [Anand Avati] SPARK-1812: core - upgrade to akka 2.3.4
I noticed a few issues with how temp directories are created and deleted:
*Minor*
* Guava's `Files.createTempDir()` plus `File.deleteOnExit()` is used in many tests to make a temp dir, but `Utils.createTempDir()` seems to be the standard Spark mechanism
* Call to `File.deleteOnExit()` could be pushed into `Utils.createTempDir()` as well, along with this replacement
* _I messed up the message in an exception in `Utils` in SPARK-3794; fixed here_
*Bit Less Minor*
* `Utils.deleteRecursively()` fails immediately if any `IOException` occurs, instead of trying to delete any remaining files and subdirectories. I've observed this leave temp dirs around. I suggest changing it to continue in the face of an exception and throw one of the possibly several exceptions that occur at the end.
* `Utils.createTempDir()` will add a JVM shutdown hook every time the method is called. Even if the subdir is the parent of another parent dir, since this check is inside the hook. However `Utils` manages a set of all dirs to delete on shutdown already, called `shutdownDeletePaths`. A single hook can be registered to delete all of these on exit. This is how Tachyon temp paths are cleaned up in `TachyonBlockManager`.
I noticed a few other things that might be changed but wanted to ask first:
* Shouldn't the set of dirs to delete be `File`, not just `String` paths?
* `Utils` manages the set of `TachyonFile` that have been registered for deletion, but the shutdown hook is managed in `TachyonBlockManager`. Should this logic not live together, and not in `Utils`? it's more specific to Tachyon, and looks a slight bit odd to import in such a generic place.
Author: Sean Owen <sowen@cloudera.com>
Closes#2670 from srowen/SPARK-3811 and squashes the following commits:
071ae60 [Sean Owen] Update per @vanzin's review
da0146d [Sean Owen] Make Utils.deleteRecursively try to delete all paths even when an exception occurs; use one shutdown hook instead of one per method call to delete temp dirs
3a0faa4 [Sean Owen] Standardize on Utils.createTempDir instead of Files.createTempDir
Upgrade to akka 2.3.4
Author: Anand Avati <avati@redhat.com>
Closes#1685 from avati/SPARK-1812-akka-2.3 and squashes the following commits:
57a2315 [Anand Avati] SPARK-1812: streaming - remove tests which depend on akka.actor.IO
2a551d3 [Anand Avati] SPARK-1812: core - upgrade to akka 2.3.4
First contribution to the project, so apologize for any significant errors.
This PR addresses [SPARK-1860]. The application directories are now cleaned up in a more conservative manner.
Previously, app-* directories were cleaned up if the directory's timestamp was older than a given time. However, the timestamp on a directory does not reflect the modification times of the files in that directory. Therefore, app-* directories were wiped out even if the files inside them were created recently and possibly being used by Executor tasks.
The solution is to change the cleanup logic to inspect all files within the app-* directory and only eliminate the app-* directory if all files in the directory are stale.
Author: mcheah <mcheah@palantir.com>
Closes#2609 from mccheah/worker-better-app-dir-cleanup and squashes the following commits:
87b5d03 [mcheah] [SPARK-1860] Using more string interpolation. Better error logging.
802473e [mcheah] [SPARK-1860] Cleaning up the logs generated when cleaning directories.
e0a1f2e [mcheah] [SPARK-1860] Fixing broken unit test.
77a9de0 [mcheah] [SPARK-1860] More conservative app directory cleanup.
This PR is another solution for #2250
I'm using codahale base MetricsSystem of Spark with JMX or Graphite, and I saw following 2 problems.
(1) When applications which have same spark.app.name run on cluster at the same time, some metrics names are mixed. For instance, if 2+ application is running on the cluster at the same time, each application emits the same named metric like "SparkPi.DAGScheduler.stage.failedStages" and Graphite cannot distinguish the metrics is for which application.
(2) When 2+ executors run on the same machine, JVM metrics of each executors are mixed. For instance, 2+ executors running on the same node can emit the same named metric "jvm.memory" and Graphite cannot distinguish the metrics is from which application.
And there is an similar issue. The directory for event logs is named using application name.
Application name is defined by user and the name can includes illegal character for path names.
Further more, the directory name consists of application name and System.currentTimeMillis even though each application has unique Application ID so if we run jobs which have same name, it's difficult to identify which directory is for which application.
Closes#2250Closes#1067
Author: Kousuke Saruta <sarutak@oss.nttdata.co.jp>
Closes#2432 from sarutak/metrics-structure-improvement2 and squashes the following commits:
3288b2b [Kousuke Saruta] Merge branch 'master' of git://git.apache.org/spark into metrics-structure-improvement2
39169e4 [Kousuke Saruta] Fixed style
6570494 [Kousuke Saruta] Merge branch 'master' of git://git.apache.org/spark into metrics-structure-improvement2
817e4f0 [Kousuke Saruta] Simplified MetricsSystem#buildRegistryName
67fa5eb [Kousuke Saruta] Unified MetricsSystem#registerSources and registerSinks in start
10be654 [Kousuke Saruta] Fixed style.
990c078 [Kousuke Saruta] Merge branch 'master' of git://git.apache.org/spark into metrics-structure-improvement2
f0c7fba [Kousuke Saruta] Merge branch 'master' of git://git.apache.org/spark into metrics-structure-improvement2
59cc2cd [Kousuke Saruta] Modified SparkContextSchedulerCreationSuite
f9b6fb3 [Kousuke Saruta] Modified style.
2cf8a0f [Kousuke Saruta] Merge branch 'master' of git://git.apache.org/spark into metrics-structure-improvement2
389090d [Kousuke Saruta] Replaced taskScheduler.applicationId() with getApplicationId in SparkContext#postApplicationStart
ff45c89 [Kousuke Saruta] Added some test cases to MetricsSystemSuite
69c46a6 [Kousuke Saruta] Added warning logging logic to MetricsSystem#buildRegistryName
5cca0d2 [Kousuke Saruta] Added Javadoc comment to SparkContext#getApplicationId
16a9f01 [Kousuke Saruta] Added data types to be returned to some methods
6434b06 [Kousuke Saruta] Reverted changes related to ApplicationId
0413b90 [Kousuke Saruta] Deleted ApplicationId.java and ApplicationIdSuite.java
a42300c [Kousuke Saruta] Merge branch 'master' of git://git.apache.org/spark into metrics-structure-improvement2
0fc1b09 [Kousuke Saruta] Merge branch 'master' of git://git.apache.org/spark into metrics-structure-improvement2
42bea55 [Kousuke Saruta] Merge branch 'master' of git://git.apache.org/spark into metrics-structure-improvement2
248935d [Kousuke Saruta] Merge branch 'master' of git://git.apache.org/spark into metrics-structure-improvement2
f6af132 [Kousuke Saruta] Modified SchedulerBackend and TaskScheduler to return System.currentTimeMillis as an unique Application Id
1b8b53e [Kousuke Saruta] Merge branch 'master' of git://git.apache.org/spark into metrics-structure-improvement2
97cb85c [Kousuke Saruta] Modified confliction of MimExcludes
2cdd009 [Kousuke Saruta] Modified defailt implementation of applicationId
9aadb0b [Kousuke Saruta] Modified NetworkReceiverSuite to ensure "executor.start()" is finished in test "network receiver life cycle"
3011efc [Kousuke Saruta] Added ApplicationIdSuite.scala
d009c55 [Kousuke Saruta] Modified ApplicationId#equals to compare appIds
dfc83fd [Kousuke Saruta] Modified ApplicationId to implement Serializable
9ff4851 [Kousuke Saruta] Modified MimaExcludes.scala to ignore createTaskScheduler method in SparkContext
4567ffc [Kousuke Saruta] Merge branch 'master' of git://git.apache.org/spark into metrics-structure-improvement2
6a91b14 [Kousuke Saruta] Modified SparkContextSchedulerCreationSuite, ExecutorRunnerTest and EventLoggingListenerSuite
0325caf [Kousuke Saruta] Added ApplicationId.scala
0a2fc14 [Kousuke Saruta] Modified style
eabda80 [Kousuke Saruta] Merge branch 'master' of git://git.apache.org/spark into metrics-structure-improvement2
0f890e6 [Kousuke Saruta] Modified SparkDeploySchedulerBackend and Master to pass baseLogDir instead f eventLogDir
bcf25bf [Kousuke Saruta] Modified directory name for EventLogs
28d4d93 [Kousuke Saruta] Modified SparkContext and EventLoggingListener so that the directory for EventLogs is named same for Application ID
203634e [Kousuke Saruta] Modified comment in SchedulerBackend#applicationId and TaskScheduler#applicationId
424fea4 [Kousuke Saruta] Modified the subclasses of TaskScheduler and SchedulerBackend so that they can return non-optional Unique Application ID
b311806 [Kousuke Saruta] Swapped last 2 arguments passed to CoarseGrainedExecutorBackend
8a2b6ec [Kousuke Saruta] Merge branch 'master' of git://git.apache.org/spark into metrics-structure-improvement2
086ee25 [Kousuke Saruta] Merge branch 'metrics-structure-improvement2' of github.com:sarutak/spark into metrics-structure-improvement2
e705386 [Kousuke Saruta] Merge branch 'master' of git://git.apache.org/spark into metrics-structure-improvement2
36d2f7a [Kousuke Saruta] Added warning message for the situation we cannot get application id for the prefix for the name of metrics
eea6e19 [Kousuke Saruta] Modified CoarseGrainedMesosSchedulerBackend and MesosSchedulerBackend so that we can get Application ID
c229fbe [Kousuke Saruta] Merge branch 'master' of git://git.apache.org/spark into metrics-structure-improvement2
e719c39 [Kousuke Saruta] Merge branch 'master' of git://git.apache.org/spark into metrics-structure-improvement2
4a93c7f [Kousuke Saruta] Merge branch 'master' of git://git.apache.org/spark into metrics-structure-improvement2
4776f9e [Kousuke Saruta] Modified MetricsSystemSuite.scala
efcb6e1 [Kousuke Saruta] Modified to add application id to metrics name
2ec848a [Kousuke Saruta] Merge branch 'master' of git://git.apache.org/spark into metrics-structure-improvement
3ea7896 [Kousuke Saruta] Merge branch 'master' of git://git.apache.org/spark into metrics-structure-improvement
ead8966 [Kousuke Saruta] Merge branch 'master' of git://git.apache.org/spark into metrics-structure-improvement
08e627e [Kousuke Saruta] Revert "tmp"
7b67f5a [Kousuke Saruta] Merge branch 'master' of git://git.apache.org/spark into metrics-structure-improvement
45bd33d [Kousuke Saruta] Merge branch 'master' of git://git.apache.org/spark into metrics-structure-improvement
93e263a [Kousuke Saruta] Merge branch 'master' of git://git.apache.org/spark into metrics-structure-improvement
848819c [Kousuke Saruta] Merge branch 'metrics-structure-improvement' of github.com:sarutak/spark into metrics-structure-improvement
912a637 [Kousuke Saruta] Merge branch 'master' of git://git.apache.org/spark into metrics-structure-improvement
e4a4593 [Kousuke Saruta] tmp
3e098d8 [Kousuke Saruta] Merge branch 'master' of git://git.apache.org/spark into metrics-structure-improvement
4603a39 [Kousuke Saruta] Merge branch 'master' of git://git.apache.org/spark into metrics-structure-improvement
fa7175b [Kousuke Saruta] Merge branch 'master' of git://git.apache.org/spark into metrics-structure-improvement
15f88a3 [Kousuke Saruta] Modified MetricsSystem#buildRegistryName because conf.get does not return null when correspondin entry is absent
6f7dcd4 [Kousuke Saruta] Modified constructor of DAGSchedulerSource and BlockManagerSource because the instance of SparkContext is no longer used
6fc5560 [Kousuke Saruta] Modified sourceName of ExecutorSource, DAGSchedulerSource and BlockManagerSource
4e057c9 [Kousuke Saruta] Merge branch 'master' of git://git.apache.org/spark into metrics-structure-improvement
85ffc02 [Kousuke Saruta] Revert "Modified sourceName of ExecutorSource, DAGSchedulerSource and BlockManagerSource"
868e326 [Kousuke Saruta] Modified MetricsSystem to set registry name with unique application-id and driver/executor-id
71609f5 [Kousuke Saruta] Modified sourceName of ExecutorSource, DAGSchedulerSource and BlockManagerSource
55debab [Kousuke Saruta] Modified SparkContext and Executor to set spark.executor.id to identifiers
4180993 [Kousuke Saruta] Modified SparkContext to retain spark.unique.app.name property in SparkConf
Update of PR #997.
With this PR, setting SPARK_CONF_DIR overrides SPARK_HOME/conf (not only spark-defaults.conf and spark-env).
Author: EugenCepoi <cepoi.eugen@gmail.com>
Closes#2481 from EugenCepoi/SPARK-2058 and squashes the following commits:
0bb32c2 [EugenCepoi] use orElse orNull and fixing trailing percent in compute-classpath.cmd
77f35d7 [EugenCepoi] SPARK-2058: Overriding SPARK_HOME/conf with SPARK_CONF_DIR
If a block manager (say, A) wants to replicate a block and the node chosen for replication (say, B) is dead, then the attempt to send the block to B fails. However, this continues to fail indefinitely. Even if the driver learns about the demise of the B, A continues to try replicating to B and failing miserably.
The reason behind this bug is that A initially fetches a list of peers from the driver (when B was active), but never updates it after B is dead. This affects Spark Streaming as its receiver uses block replication.
The solution in this patch adds the following.
- Changed BlockManagerMaster to return all the peers of a block manager, rather than the requested number. It also filters out driver BlockManager.
- Refactored BlockManager's replication code to handle peer caching correctly.
+ The peer for replication is randomly selected. This is different from past behavior where for a node A, a node B was deterministically chosen for the lifetime of the application.
+ If replication fails to one node, the peers are refetched.
+ The peer cached has a TTL of 1 second to enable discovery of new peers and using them for replication.
- Refactored use of \<driver\> in BlockManager into a new method `BlockManagerId.isDriver`
- Added replication unit tests (replication was not tested till now, duh!)
This should not make a difference in performance of Spark workloads where replication is not used.
@andrewor14 @JoshRosen
Author: Tathagata Das <tathagata.das1565@gmail.com>
Closes#2366 from tdas/replication-fix and squashes the following commits:
9690f57 [Tathagata Das] Moved replication tests to a new BlockManagerReplicationSuite.
0661773 [Tathagata Das] Minor changes based on PR comments.
a55a65c [Tathagata Das] Added a unit test to test replication behavior.
012afa3 [Tathagata Das] Bug fix
89f91a0 [Tathagata Das] Minor change.
68e2c72 [Tathagata Das] Made replication peer selection logic more efficient.
08afaa9 [Tathagata Das] Made peer selection for replication deterministic to block id
3821ab9 [Tathagata Das] Fixes based on PR comments.
08e5646 [Tathagata Das] More minor changes.
d402506 [Tathagata Das] Fixed imports.
4a20531 [Tathagata Das] Filtered driver block manager from peer list, and also consolidated the use of <driver> in BlockManager.
7598f91 [Tathagata Das] Minor changes.
03de02d [Tathagata Das] Change replication logic to correctly refetch peers from master on failure and on new worker addition.
d081bf6 [Tathagata Das] Fixed bug in get peers and unit tests to test get-peers and replication under executor churn.
9f0ac9f [Tathagata Das] Modified replication tests to fail on replication bug.
af0c1da [Tathagata Das] Added replication unit tests to BlockManagerSuite
This change reorders the replicas returned by
HadoopRDD#getPreferredLocations so that replicas cached by HDFS are at
the start of the list. This requires Hadoop 2.5 or higher; previous
versions of Hadoop do not expose the information needed to determine
whether a replica is cached.
Author: Colin Patrick Mccabe <cmccabe@cloudera.com>
Closes#1486 from cmccabe/SPARK-1767 and squashes the following commits:
338d4f8 [Colin Patrick Mccabe] SPARK-1767: Prefer HDFS-cached replicas when scheduling data-local tasks
FutureAction is the only type exposed through the async APIs, so
for job IDs to be useful they need to be exposed there. The complication
is that some async jobs run more than one job (e.g. takeAsync),
so the exposed ID has to actually be a list of IDs that can actually
change over time. So the interface doesn't look very nice, but...
Change is actually small, I just added a basic test to make sure
it works.
Author: Marcelo Vanzin <vanzin@cloudera.com>
Closes#2337 from vanzin/SPARK-3446 and squashes the following commits:
e166a68 [Marcelo Vanzin] Fix comment.
1fed2bc [Marcelo Vanzin] [SPARK-3446] Expose underlying job ids in FutureAction.
Thread names are useful for correlating failures.
Author: Reynold Xin <rxin@apache.org>
Closes#2600 from rxin/log4j and squashes the following commits:
83ffe88 [Reynold Xin] [SPARK-3748] Log thread name in unit test logs
This changes the way we send MapStatus from executors back to driver for large stages (>2000 tasks). For large stages, we no longer send one byte per block. Instead, we just send the average block size.
This makes large jobs (tens of thousands of tasks) much more reliable since the driver no longer sends huge amount of data.
Author: Reynold Xin <rxin@apache.org>
Closes#2470 from rxin/mapstatus and squashes the following commits:
822ff54 [Reynold Xin] Code review feedback.
3b86f56 [Reynold Xin] Added MimaExclude.
f89d182 [Reynold Xin] Fixed a bug in MapStatus
6a0401c [Reynold Xin] [SPARK-3613] Record only average block size in MapStatus for large stages.
Previous key comparison in `ExternalSorter` will get wrong sorting result or exception when key comparison overflows, details can be seen in [SPARK-3032](https://issues.apache.org/jira/browse/SPARK-3032). Here fix this and add a unit test to prove it.
Author: jerryshao <saisai.shao@intel.com>
Closes#2514 from jerryshao/SPARK-3032 and squashes the following commits:
6f3c302 [jerryshao] Improve the unit test according to comments
01911e6 [jerryshao] Change the test to show the contract violate exception
83acb38 [jerryshao] Minor changes according to comments
fa2a08f [jerryshao] Fix key comparison integer overflow introduced sorting exception
Author: Reynold Xin <rxin@apache.org>
Closes#2560 from rxin/TaskContext and squashes the following commits:
9eff95a [Reynold Xin] [SPARK-3543] remaining cleanup work.
Author: Reynold Xin <rxin@apache.org>
Closes#2555 from rxin/cleanup and squashes the following commits:
6add199 [Reynold Xin] Minor cleanup to tighten visibility and remove compilation warning.
Author: Prashant Sharma <prashant.s@imaginea.com>
Author: Shashank Sharma <shashank21j@gmail.com>
Closes#2425 from ScrapCodes/SPARK-3543/withTaskContext and squashes the following commits:
8ae414c [Shashank Sharma] CR
ee8bd00 [Prashant Sharma] Added internal API in docs comments.
ddb8cbe [Prashant Sharma] Moved setting the thread local to where TaskContext is instantiated.
a7d5e23 [Prashant Sharma] Added doc comments.
edf945e [Prashant Sharma] Code review git add -A
f716fd1 [Prashant Sharma] introduced thread local for getting the task context.
333c7d6 [Prashant Sharma] Translated Task context from scala to java.
leftOuterJoin and rightOuterJoin are already implemented. This patch adds fullOuterJoin.
Author: Aaron Staple <aaron.staple@gmail.com>
Closes#1395 from staple/SPARK-546 and squashes the following commits:
1f5595c [Aaron Staple] Fix python style
7ac0aa9 [Aaron Staple] [SPARK-546] Add full outer join to RDD and DStream.
3b5d137 [Aaron Staple] In JavaPairDStream, make class tag specification in rightOuterJoin consistent with other functions.
31f2956 [Aaron Staple] Fix left outer join documentation comments.
Guava's Optional refers to some package private classes / methods, and
when those are relocated the code stops working, throwing exceptions.
So add the affected classes to the exception list too, and add a unit
test.
(Note that this unit test only really makes sense in maven, since we
don't relocate in the sbt build. Also, JavaAPISuite doesn't seem to
be run by "mvn test" - I had to manually add command line options to
enable it.)
Author: Marcelo Vanzin <vanzin@cloudera.com>
Closes#2496 from vanzin/SPARK-3647 and squashes the following commits:
84f58d7 [Marcelo Vanzin] [SPARK-3647] Add more exceptions to Guava relocation.
Addresses the issue in https://issues.apache.org/jira/browse/SPARK-3595, namely saveAsHadoopFile hardcoding the OutputCommitter. This is not ideal when running Spark jobs that write to S3, especially when running them from an EMR cluster where the default OutputCommitter is a DirectOutputCommitter.
Author: Ian Hummel <ian@themodernlife.net>
Closes#2450 from themodernlife/spark-3595 and squashes the following commits:
f37a0e5 [Ian Hummel] Update based on comments from pwendell
a11d9f3 [Ian Hummel] Fix formatting
4359664 [Ian Hummel] Add an example showing usage
8b6be94 [Ian Hummel] Add ability to specify OutputCommitter, espcially useful when writing to an S3 bucket from an EMR cluster
The included test waits 100 ms after job completion for task completion events to come in so it can verify they have reasonable finish times. Does anyone know a better way to wait on listener events that are expected to come in?
Author: Sandy Ryza <sandy@cloudera.com>
Closes#2440 from sryza/sandy-spark-3574 and squashes the following commits:
c81439b [Sandy Ryza] Fix test failure
b340956 [Sandy Ryza] SPARK-3574. Remove shuffleFinishTime metric
Author: Victsm <victor.nju@gmail.com>
Author: Min Shen <mshen@linkedin.com>
Closes#2449 from Victsm/SPARK-3560 and squashes the following commits:
918405a [Victsm] Removed the additional space
4502a2a [Min Shen] [SPARK-3560] Fixed setting spark.jars system property in yarn-cluster mode.
(cherry picked from commit 832dff64dd)
Signed-off-by: Andrew Or <andrewor14@gmail.com>
https://issues.apache.org/jira/browse/SPARK-3565
"spark.ports.maxRetries" should be "spark.port.maxRetries". Make the configuration keys in document and code consistent.
Author: WangTaoTheTonic <barneystinson@aliyun.com>
Closes#2427 from WangTaoTheTonic/fixPortRetries and squashes the following commits:
c178813 [WangTaoTheTonic] Use blank lines trigger Jenkins
646f3fe [WangTaoTheTonic] also in SparkBuild.scala
3700dba [WangTaoTheTonic] Fix configuration item not consistent with document
The test "jetty selects different port under contention" is flaky.
If another process binds to 4040 before the test starts, then the first server we start there will fail, and the subsequent servers we start thereafter may successfully bind to 4040 if it was released between the servers starting. Instead, we should just let Java find a random free port for us and hold onto it for the duration of the test.
Author: Andrew Or <andrewor14@gmail.com>
Closes#2418 from andrewor14/fix-port-contention and squashes the following commits:
0cd4974 [Andrew Or] Stop them servers
a7071fe [Andrew Or] Pick random port instead of 4040
This is necessary because we rely on this callback interface to clean resources up. The old behavior would lead to resource leaks.
Note that this also changes the fault semantics of TaskCompletionListener. Previously failures in TaskCompletionListeners would result in the task being reported immediately. With this change, we report the exception at the end, and the reported exception is a TaskCompletionListenerException that contains all the exception messages.
Author: Reynold Xin <rxin@apache.org>
Closes#2343 from rxin/taskcontext-callback and squashes the following commits:
a3845b2 [Reynold Xin] Mark TaskCompletionListenerException as private[spark].
ac5baea [Reynold Xin] Removed obsolete comment.
aa68ea4 [Reynold Xin] Throw an exception if task completion callback fails.
29b6162 [Reynold Xin] oops compilation failed.
1cb444d [Reynold Xin] [SPARK-3469] Call all TaskCompletionListeners even if some fail.
At the same time, import the `scala.language.postfixOps` and ` org.scalatest.time.SpanSugar._` cause `scala.language.postfixOps` doesn't work
Author: witgo <witgo@qq.com>
Closes#1330 from witgo/sbt_warnings3 and squashes the following commits:
179ba61 [witgo] Resolve sbt warnings during build
We currently open many ephemeral ports during the tests, and as a result we occasionally can't bind to new ones. This has caused the `DriverSuite` and the `SparkSubmitSuite` to fail intermittently.
By disabling the `SparkUI` when it's not needed, we already cut down on the number of ports opened significantly, on the order of the number of `SparkContexts` ever created. We must keep it enabled for a few tests for the UI itself, however.
Author: Andrew Or <andrewor14@gmail.com>
Closes#2363 from andrewor14/disable-ui-for-tests and squashes the following commits:
332a7d5 [Andrew Or] No need to set spark.ui.port to 0 anymore
30c93a2 [Andrew Or] Simplify streaming UISuite
a431b84 [Andrew Or] Fix streaming test failures
8f5ae53 [Andrew Or] Fix no new line at the end
29c9b5b [Andrew Or] Disable SparkUI for tests
https://issues.apache.org/jira/browse/SPARK-3193
I noticed that sometimes pr tests failed due to the Process exitcode != 0,refer to
https://amplab.cs.berkeley.edu/jenkins/job/SparkPullRequestBuilder/18688/consoleFullhttps://amplab.cs.berkeley.edu/jenkins/job/SparkPullRequestBuilder/19118/consoleFull
[info] SparkSubmitSuite:
[info] - prints usage on empty input
[info] - prints usage with only --help
[info] - prints error with unrecognized options
[info] - handle binary specified but not class
[info] - handles arguments with --key=val
[info] - handles arguments to user program
[info] - handles arguments to user program with name collision
[info] - handles YARN cluster mode
[info] - handles YARN client mode
[info] - handles standalone cluster mode
[info] - handles standalone client mode
[info] - handles mesos client mode
[info] - handles confs with flag equivalents
[info] - launch simple application with spark-submit *** FAILED ***
[info] org.apache.spark.SparkException: Process List(./bin/spark-submit, --class, org.apache.spark.deploy.SimpleApplicationTest, --name, testApp, --master, local, file:/tmp/1408854098404-0/testJar-1408854098404.jar) exited with code 1
[info] at org.apache.spark.util.Utils$.executeAndGetOutput(Utils.scala:872)
[info] at org.apache.spark.deploy.SparkSubmitSuite.runSparkSubmit(SparkSubmitSuite.scala:311)
[info] at org.apache.spark.deploy.SparkSubmitSuite$$anonfun$14.apply$mcV$sp(SparkSubmitSuite.scala:291)
[info] at org.apache.spark.deploy.SparkSubmitSuite$$anonfun$14.apply(SparkSubmitSuite.scala:284)
[info] at org.apacSpark assembly has been built with Hive, including Datanucleus jars on classpath
this PR output the process error info when failed, it can be helpful for diagnosis.
Author: scwf <wangfei1@huawei.com>
Closes#2108 from scwf/output-test-error-info and squashes the following commits:
0c48082 [scwf] minor fix according to comments
563fde1 [scwf] output errer info when Process exitcode not zero
Author: Sandy Ryza <sandy@cloudera.com>
Closes#2324 from sryza/sandy-spark-3422 and squashes the following commits:
6446175 [Sandy Ryza] SPARK-3422. JavaAPISuite.getHadoopInputSplits isn't used anywhere.
This pull request creates a new BlockTransferService interface for block fetch/upload and refactors the existing ConnectionManager to implement BlockTransferService (NioBlockTransferService).
Most of the changes are simply moving code around. The main class to inspect is ShuffleBlockFetcherIterator.
Review guide:
- Most of the ConnectionManager code is now in network.cm package
- ManagedBuffer is a new buffer abstraction backed by several different implementations (file segment, nio ByteBuffer, Netty ByteBuf)
- BlockTransferService is the main internal interface introduced in this PR
- NioBlockTransferService implements BlockTransferService and replaces the old BlockManagerWorker
- ShuffleBlockFetcherIterator replaces the told BlockFetcherIterator to use the new interface
TODOs that should be separate PRs:
- Implement NettyBlockTransferService
- Finalize the API/semantics for ManagedBuffer.release()
Author: Reynold Xin <rxin@apache.org>
Closes#2240 from rxin/blockTransferService and squashes the following commits:
64cd9d7 [Reynold Xin] Merge branch 'master' into blockTransferService
1dfd3d7 [Reynold Xin] Limit the length of the FileInputStream.
1332156 [Reynold Xin] Fixed style violation from refactoring.
2960c93 [Reynold Xin] Added ShuffleBlockFetcherIteratorSuite.
e29c721 [Reynold Xin] Updated comment for ShuffleBlockFetcherIterator.
8a1046e [Reynold Xin] Code review feedback:
2c6b1e1 [Reynold Xin] Removed println in test cases.
2a907e4 [Reynold Xin] Merge branch 'master' into blockTransferService-merge
07ccf0d [Reynold Xin] Added init check to CMBlockTransferService.
98c668a [Reynold Xin] Added failure handling and fixed unit tests.
ae05fcd [Reynold Xin] Updated tests, although DistributedSuite is hanging.
d8d595c [Reynold Xin] Merge branch 'master' of github.com:apache/spark into blockTransferService
9ef279c [Reynold Xin] Initial refactoring to move ConnectionManager to use the BlockTransferService.
I didn't add this to the transformations list in the docs because it's kind of obscure, but would be happy to do so if others think it would be helpful.
Author: Sandy Ryza <sandy@cloudera.com>
Closes#2274 from sryza/sandy-spark-2978 and squashes the following commits:
4a5332a [Sandy Ryza] Fix Java test
c04b447 [Sandy Ryza] Fix Python doc and add back deleted code
433ad5b [Sandy Ryza] Add Java test
4c25a54 [Sandy Ryza] Add s at the end and a couple other fixes
9b0ba99 [Sandy Ryza] Fix compilation
36e0571 [Sandy Ryza] Fix import ordering
48c12c2 [Sandy Ryza] Add Java version and additional doc
e5381cd [Sandy Ryza] Fix python style warnings
f147634 [Sandy Ryza] SPARK-2978. Transformation with MR shuffle semantics
Sort-based shuffle has lower memory usage and seems to outperform hash-based in almost all of our testing.
Author: Reynold Xin <rxin@apache.org>
Closes#2178 from rxin/sort-shuffle and squashes the following commits:
713d341 [Reynold Xin] Fixed test failures by setting spark.shuffle.compress to the same value as spark.shuffle.spill.compress.
85165e6 [Reynold Xin] Fixed a comment typo.
aa0d372 [Reynold Xin] [SPARK-3280] Made sort-based shuffle the default implementation
This resolves https://issues.apache.org/jira/browse/SPARK-3394
Author: Eric Liang <ekl@google.com>
Closes#2264 from ericl/spark-3394 and squashes the following commits:
c87355b [Eric Liang] refactor
bfb6140 [Eric Liang] change RDD takeOrdered instead
7a51528 [Eric Liang] fix takeordered when limit = 0
Previously parent stages had higher stage id, but parent stages are executed first. This pull request changes the behavior so parent stages would have lower stage id.
For example, command:
```scala
sc.parallelize(1 to 10).map(x=>(x,x)).reduceByKey(_+_).count
```
breaks down into 2 stages.
The old web UI:
Web UI with this patch:
Author: Reynold Xin <rxin@apache.org>
Closes#2273 from rxin/lower-stage-id and squashes the following commits:
abbb4c6 [Reynold Xin] Fixed SparkListenerSuite.
0e02379 [Reynold Xin] Updated DAGSchedulerSuite.
54ccea3 [Reynold Xin] [SPARK-3353] parent stage should have lower stage id.
Author: GuoQiang Li <witgo@qq.com>
Closes#2175 from witgo/SPARK-3273 and squashes the following commits:
cf9c65a [GuoQiang Li] We should read the version information from the same place
2a44e2f [GuoQiang Li] The spark version in the welcome message of pyspark is not correct
Author: Kousuke Saruta <sarutak@oss.nttdata.co.jp>
Closes#2138 from sarutak/SPARK-3233 and squashes the following commits:
c0205b7 [Kousuke Saruta] Merge branch 'SPARK-3233' of github.com:sarutak/spark into SPARK-3233
064679d [Kousuke Saruta] Merge branch 'master' of git://git.apache.org/spark into SPARK-3233
d3005fd [Kousuke Saruta] Modified Class definition format of BlockManagerMaster
039b747 [Kousuke Saruta] Modified style
889e2d1 [Kousuke Saruta] Modified BlockManagerMaster to be able to be past isDriver flag
4da8535 [Kousuke Saruta] Modified BlockManagerMaster#stop to send StopBlockManagerMaster message when sender is Driver
6518c3a [Kousuke Saruta] Merge branch 'master' of git://git.apache.org/spark into SPARK-3233
d5ab19a [Kousuke Saruta] Merge branch 'master' of git://git.apache.org/spark into SPARK-3233
6bce25c [Kousuke Saruta] Merge branch 'master' of git://git.apache.org/spark into SPARK-3233
6058a58 [Kousuke Saruta] Modified Executor not to invoke SparkEnv#stop in local mode
e5ad9d3 [Kousuke Saruta] Modified Executor to stop SparnEnv at the end of itself
This change exposes the application ID generated by the Spark Master, Mesos or Yarn
via the SparkListenerApplicationStart event. It then uses that information to expose the
application via its ID in the history server, instead of using the internal directory name
generated by the event logger as an application id. This allows someone who knows
the application ID to easily figure out the URL for the application's entry in the HS, aside
from looking better.
In Yarn mode, this is used to generate a direct link from the RM application list to the
Spark history server entry (thus providing a fix for SPARK-2150).
Note this sort of assumes that the different managers will generate app ids that are
sufficiently different from each other that clashes will not occur.
Author: Marcelo Vanzin <vanzin@cloudera.com>
This patch had conflicts when merged, resolved by
Committer: Andrew Or <andrewor14@gmail.com>
Closes#1218 from vanzin/yarn-hs-link-2 and squashes the following commits:
2d19f3c [Marcelo Vanzin] Review feedback.
6706d3a [Marcelo Vanzin] Implement applicationId() in base classes.
56fe42e [Marcelo Vanzin] Fix cluster mode history address, plus a cleanup.
44112a8 [Marcelo Vanzin] Merge branch 'master' into yarn-hs-link-2
8278316 [Marcelo Vanzin] Merge branch 'master' into yarn-hs-link-2
a86bbcf [Marcelo Vanzin] Merge branch 'master' into yarn-hs-link-2
a0056e6 [Marcelo Vanzin] Unbreak test.
4b10cfd [Marcelo Vanzin] Merge branch 'master' into yarn-hs-link-2
cb0cab2 [Marcelo Vanzin] Merge branch 'master' into yarn-hs-link-2
25f2826 [Marcelo Vanzin] Add MIMA excludes.
f0ba90f [Marcelo Vanzin] Use BufferedIterator.
c90a08d [Marcelo Vanzin] Remove unused code.
3f8ec66 [Marcelo Vanzin] Review feedback.
21aa71b [Marcelo Vanzin] Fix JSON test.
b022bae [Marcelo Vanzin] Undo SparkContext cleanup.
c6d7478 [Marcelo Vanzin] Merge branch 'master' into yarn-hs-link-2
4e3483f [Marcelo Vanzin] Fix test.
57517b8 [Marcelo Vanzin] Review feedback. Mostly, more consistent use of Scala's Option.
311e49d [Marcelo Vanzin] Merge branch 'master' into yarn-hs-link-2
d35d86f [Marcelo Vanzin] Fix yarn backend after rebase.
36dc362 [Marcelo Vanzin] Don't use Iterator::takeWhile().
0afd696 [Marcelo Vanzin] Wait until master responds before returning from start().
abc4697 [Marcelo Vanzin] Make FsHistoryProvider keep a map of applications by id.
26b266e [Marcelo Vanzin] Use Mesos framework ID as Spark application ID.
b3f3664 [Marcelo Vanzin] [yarn] Make the RM link point to the app direcly in the HS.
2fb7de4 [Marcelo Vanzin] Expose the application ID in the ApplicationStart event.
ed10348 [Marcelo Vanzin] Expose application id to spark context.
These are not used by the UI but are useful when analysing the
logs from a spark job.
Author: Marcelo Vanzin <vanzin@cloudera.com>
Closes#654 from vanzin/bm-event-tstamp and squashes the following commits:
d5d6e66 [Marcelo Vanzin] Fix tests.
ec06218 [Marcelo Vanzin] Review feedback.
f134dbc [Marcelo Vanzin] Merge branch 'master' into bm-event-tstamp
b495b7c [Marcelo Vanzin] Merge branch 'master' into bm-event-tstamp
7d2fe9e [Marcelo Vanzin] Review feedback.
d6f381c [Marcelo Vanzin] Update tests added after patch was created.
45e3bf8 [Marcelo Vanzin] Fix unit test after merge.
b37a10f [Marcelo Vanzin] Use === in test assertions.
ef72824 [Marcelo Vanzin] Handle backwards compatibility with 1.0.0.
aca1151 [Marcelo Vanzin] Fix unit test to check new fields.
efdda8e [Marcelo Vanzin] Add timestamps to block manager events.
This also enables supporting broadcast variables larger than 2G.
Author: Reynold Xin <rxin@apache.org>
Closes#2054 from rxin/ByteArrayChunkOutputStream and squashes the following commits:
618d9c8 [Reynold Xin] Code review.
93f5a51 [Reynold Xin] Added comments.
ee88e73 [Reynold Xin] to -> until
bbd1cb1 [Reynold Xin] Renamed a variable.
36f4d01 [Reynold Xin] Sort imports.
8f1a8eb [Reynold Xin] [SPARK-3135] Created ByteArrayChunkOutputStream and used it to avoid memory copy in TorrentBroadcast.
Different places in the code were instantiating Configuration / YarnConfiguration objects in different ways. This could lead to confusion for people who actually expected "spark.hadoop.*" options to end up in the configs used by Spark code, since that would only happen for the SparkContext's config.
This change modifies most places to use SparkHadoopUtil to initialize configs, and make that method do the translation that previously was only done inside SparkContext.
The places that were not changed fall in one of the following categories:
- Test code where this doesn't really matter
- Places deep in the code where plumbing SparkConf would be too difficult for very little gain
- Default values for arguments - since the caller can provide their own config in that case
Author: Marcelo Vanzin <vanzin@cloudera.com>
Closes#1843 from vanzin/SPARK-2889 and squashes the following commits:
52daf35 [Marcelo Vanzin] Merge branch 'master' into SPARK-2889
f179013 [Marcelo Vanzin] Merge branch 'master' into SPARK-2889
51e71cf [Marcelo Vanzin] Add test to ensure that overriding Yarn configs works.
53f9506 [Marcelo Vanzin] Add DeveloperApi annotation.
3d345cb [Marcelo Vanzin] Restore old method for backwards compat.
fc45067 [Marcelo Vanzin] Merge branch 'master' into SPARK-2889
0ac3fdf [Marcelo Vanzin] Merge branch 'master' into SPARK-2889
3f26760 [Marcelo Vanzin] Compilation fix.
f16cadd [Marcelo Vanzin] Initialize config in SparkHadoopUtil.
b8ab173 [Marcelo Vanzin] Update Utils API to take a Configuration argument.
1e7003f [Marcelo Vanzin] Replace explicit Configuration instantiation with SparkHadoopUtil.
By Hiding the shuffleblockmanager behind Shufflemanager, we decouple the shuffle data's block mapping management work from Diskblockmananger. This give a more clear interface and more easy for other shuffle manager to implement their own block management logic. the jira ticket have more details.
Author: Raymond Liu <raymond.liu@intel.com>
Closes#1241 from colorant/shuffle and squashes the following commits:
0e01ae3 [Raymond Liu] Move ShuffleBlockmanager behind shuffleManager
This is a simplified fix for SPARK-1912.
Author: Reynold Xin <rxin@apache.org>
Closes#2179 from rxin/SPARK-1912 and squashes the following commits:
b2f0e9e [Reynold Xin] Fix unit tests.
a8eddfe [Reynold Xin] [SPARK-1912] Lazily initialize buffers for local shuffle blocks.
**Summary of the changes**
The bulk of this PR is comprised of tests and documentation; the actual fix is really just adding 1 line of code (see `BlockObjectWriter.scala`). We currently do not run the `External*` test suites with different compression codecs, and this would have caught the bug reported in [SPARK-3277](https://issues.apache.org/jira/browse/SPARK-3277). This PR extends the existing code to test spilling using all compression codecs known to Spark, including `LZ4`.
**The bug itself**
In `DiskBlockObjectWriter`, we only report the shuffle bytes written before we close the streams. With `LZ4`, all the bytes written reported by our metrics were 0 because `flush()` was not taking effect for some reason. In general, compression codecs may write additional bytes to the file after we call `close()`, and so we must also capture those bytes in our shuffle write metrics.
Thanks mridulm and pwendell for help with debugging.
Author: Andrew Or <andrewor14@gmail.com>
Author: Patrick Wendell <pwendell@gmail.com>
Closes#2187 from andrewor14/fix-lz4-spilling and squashes the following commits:
1b54bdc [Andrew Or] Speed up tests by not compressing everything
1c4624e [Andrew Or] Merge branch 'master' of github.com:apache/spark into fix-lz4-spilling
6b2e7d1 [Andrew Or] Fix compilation error
92e251b [Patrick Wendell] Better documentation for BlockObjectWriter.
a1ad536 [Andrew Or] Fix tests
089593f [Andrew Or] Actually fix SPARK-3277 (tests still fail)
4bbcf68 [Andrew Or] Update tests to actually test all compression codecs
b264a84 [Andrew Or] ExternalAppendOnlyMapSuite code style fixes (minor)
1bfa743 [Andrew Or] Add more information to assert for better debugging
Netty functionality will be added back in subsequent PRs by using the BlockTransferService interface.
Author: Reynold Xin <rxin@apache.org>
Closes#2181 from rxin/SPARK-3281 and squashes the following commits:
5494b0e [Reynold Xin] Fix extra port.
ff6d1e1 [Reynold Xin] [SPARK-3281] Remove Netty specific code in BlockManager.
compeleted stage only need to remove its own partitions that are no longer cached. However, "StorageTab" may lost some rdds which are cached actually. Not only in "StorageTab", "ExectutorTab" may also lose some rdd info which have been overwritten by last rdd in a same task.
1. "StorageTab": when multiple stages run simultaneously, completed stage will remove rdd info which belong to other stages that are still running.
2. "ExectutorTab": taskcontext may lose some "updatedBlocks" info of rdds in a dependency chain. Like the following example:
val r1 = sc.paralize(..).cache()
val r2 = r1.map(...).cache()
val n = r2.count()
When count the r2, r1 and r2 will be cached finally. So in CacheManager.getOrCompute, the taskcontext should contain "updatedBlocks" of r1 and r2. Currently, the "updatedBlocks" only contain the info of r2.
Author: uncleGen <hustyugm@gmail.com>
Closes#2131 from uncleGen/master_ui_fix and squashes the following commits:
a6a8a0b [uncleGen] fix some coding style
3a1bc15 [uncleGen] fix some error in unit test
56ea488 [uncleGen] there's some line too long
c82ba82 [uncleGen] Bug Fix: RDD info loss in "StorageTab" and "ExecutorTab"
As a workaround for SPARK-3015, the ContextCleaner was made "blocking", that is, it cleaned items one-by-one. But shuffles can take a long time to be deleted. Given that the RC for 1.1 is imminent, this PR makes a narrow change in the context cleaner - not wait for shuffle cleanups to complete. Also it changes the error messages on failure to delete to be milder warnings, as exceptions in the delete code path for one item does not really stop the actual functioning of the system.
Author: Tathagata Das <tathagata.das1565@gmail.com>
Closes#2143 from tdas/cleaner-shuffle-fix and squashes the following commits:
9c84202 [Tathagata Das] Restoring default blocking behavior in ContextCleanerSuite, and added docs to identify that spark.cleaner.referenceTracking.blocking does not control shuffle.
2181329 [Tathagata Das] Mark shuffle cleanup as non-blocking.
e337cc2 [Tathagata Das] Changed semantics based on PR comments.
387b578 [Tathagata Das] Made ContextCleaner to not block on shuffles
This is a HOTFIX for 1.1.
Author: Reynold Xin <rxin@apache.org>
Author: Kay Ousterhout <kayousterhout@gmail.com>
Closes#2127 from rxin/SPARK-3224 and squashes the following commits:
effb1ce [Reynold Xin] Move log message.
49282b3 [Reynold Xin] Kay's feedback.
3f01847 [Reynold Xin] Merge pull request #2 from kayousterhout/SPARK-3224
796d282 [Kay Ousterhout] Added unit test for SPARK-3224
3d3d356 [Reynold Xin] Remove map output loc even for repeated FetchFaileds.
1dd3eb5 [Reynold Xin] [SPARK-3224] FetchFailed reduce stages should only show up once in the failed stages UI.
Simple way to reproduce this in the UI:
```scala
val f = new java.io.File("/tmp/test")
f.delete()
sc.parallelize(1 to 2, 2).map(x => (x,x )).repartition(3).mapPartitionsWithContext { case (context, iter) =>
if (context.partitionId == 0) {
val f = new java.io.File("/tmp/test")
if (!f.exists) {
f.mkdir()
System.exit(0);
}
}
iter
}.count()
```
Author: Reynold Xin <rxin@apache.org>
Closes#1545 from rxin/stage-attempt and squashes the following commits:
3ee1d2a [Reynold Xin] - Rename attempt to retry in UI. - Properly report stage failure in FetchFailed.
40a6bd5 [Reynold Xin] Updated test suites.
c414c36 [Reynold Xin] Fixed the hanging in JobCancellationSuite.
b3e2eed [Reynold Xin] Oops previous code didn't compile.
0f36075 [Reynold Xin] Mark unknown stage attempt with id -1 and drop that in JobProgressListener.
6c08b07 [Reynold Xin] Addressed code review feedback.
4e5faa2 [Reynold Xin] [SPARK-2298] Encode stage attempt in SparkListener & UI.
This PR fixes two bugs related to `spark.local.dirs` and `SPARK_LOCAL_DIRS`, one where `Utils.getLocalDir()` might return an invalid directory (SPARK-2974) and another where the `SPARK_LOCAL_DIRS` override didn't affect the driver, which could cause problems when running tasks in local mode (SPARK-2975).
This patch fixes both issues: the new `Utils.getOrCreateLocalRootDirs(conf: SparkConf)` utility method manages the creation of local directories and handles the precedence among the different configuration options, so we should see the same behavior whether we're running in local mode or on a worker.
It's kind of a pain to mock out environment variables in tests (no easy way to mock System.getenv), so I added a `private[spark]` method to SparkConf for accessing environment variables (by default, it just delegates to System.getenv). By subclassing SparkConf and overriding this method, we can mock out SPARK_LOCAL_DIRS in tests.
I also fixed a typo in PySpark where we used `SPARK_LOCAL_DIR` instead of `SPARK_LOCAL_DIRS` (I think this was technically innocuous, but it seemed worth fixing).
Author: Josh Rosen <joshrosen@apache.org>
Closes#2002 from JoshRosen/local-dirs and squashes the following commits:
efad8c6 [Josh Rosen] Address review comments:
1dec709 [Josh Rosen] Minor updates to Javadocs.
7f36999 [Josh Rosen] Use env vars to detect if running in YARN container.
399ac25 [Josh Rosen] Update getLocalDir() documentation.
bb3ad89 [Josh Rosen] Remove duplicated YARN getLocalDirs() code.
3e92d44 [Josh Rosen] Move local dirs override logic into Utils; fix bugs:
b2c4736 [Josh Rosen] Add failing tests for SPARK-2974 and SPARK-2975.
007298b [Josh Rosen] Allow environment variables to be mocked in tests.
6d9259b [Josh Rosen] Fix typo in PySpark: SPARK_LOCAL_DIR should be SPARK_LOCAL_DIRS
This is a re-implementation of TorrentBroadcast, with the following changes:
1. Removes most of the mutable, transient state from TorrentBroadcast (e.g. totalBytes, num of blocks fetched).
2. Removes TorrentInfo and TorrentBlock
3. Replaces the BlockManager.getSingle call in readObject with a getLocal, resuling in one less RPC call to the BlockManagerMasterActor to find the location of the block.
4. Removes the metadata block, resulting in one less block to fetch.
5. Removes an extra memory copy for deserialization (by using Java's SequenceInputStream).
Basically for a regular broadcasted object with only one block, the number of RPC calls goes from 5+1 to 2+1).
Old TorrentBroadcast for object of a single block:
1 RPC to ask for location of the broadcast variable
1 RPC to ask for location of the metadata block
1 RPC to fetch the metadata block
1 RPC to ask for location of the first data block
1 RPC to fetch the first data block
1 RPC to tell the driver we put the first data block in
i.e. 5 + 1
New TorrentBroadcast for object of a single block:
1 RPC to ask for location of the first data block
1 RPC to get the first data block
1 RPC to tell the driver we put the first data block in
i.e. 2 + 1
Author: Reynold Xin <rxin@apache.org>
Closes#2030 from rxin/torrentBroadcast and squashes the following commits:
5bacb9d [Reynold Xin] Always add the object to driver's block manager.
0d8ed5b [Reynold Xin] Added getBytes to BlockManager and uses that in TorrentBroadcast.
2d6a5fb [Reynold Xin] Use putBytes/getRemoteBytes throughout.
3670f00 [Reynold Xin] Code review feedback.
c1185cd [Reynold Xin] [SPARK-3119] Re-implementation of TorrentBroadcast.
Previous pull request (#1907) was reverted. This brings it back. Still looking into the hang.
Author: Reynold Xin <rxin@apache.org>
Closes#1971 from rxin/netty1 and squashes the following commits:
b0be96f [Reynold Xin] Added test to make sure outstandingRequests are cleaned after firing the events.
4c6d0ee [Reynold Xin] Pass callbacks cleanly.
603dce7 [Reynold Xin] Upgrade Netty to 4.0.23 to fix the DefaultFileRegion bug.
88be1d4 [Reynold Xin] Downgrade to 4.0.21 to work around a bug in writing DefaultFileRegion.
002626a [Reynold Xin] Remove netty-test-file.txt.
db6e6e0 [Reynold Xin] Revert "Revert "[SPARK-2468] Netty based block server / client module""
Author: Chandan Kumar <chandan.kumar@imaginea.com>
Closes#1787 from nrchandan/spark-2862 and squashes the following commits:
a76bbf6 [Chandan Kumar] [SPARK-2862] Fix for a broken test case and add new test cases
4211eea [Chandan Kumar] [SPARK-2862] Add Scala bug id
13854f1 [Chandan Kumar] [SPARK-2862] Use shorthand range notation to avoid Scala bug
This is intended to fix SPARK-2977. Before, there was an implicit ordering dependency where we needed to know the ShuffleManager implementation before creating the ShuffleBlockManager. This patch makes that dependency explicit by adding ShuffleManager to a bunch of constructors.
I think it's a little odd for BlockManager to take a ShuffleManager only to pass it to ShuffleBlockManager without using it itself; there's an opportunity to clean this up later if we sever the circular dependencies between BlockManager and other components and pass those components to BlockManager's constructor.
Author: Josh Rosen <joshrosen@apache.org>
Closes#1976 from JoshRosen/SPARK-2977 and squashes the following commits:
a9cd1e1 [Josh Rosen] [SPARK-2977] Ensure ShuffleManager is created before ShuffleBlockManager.
Author: Reynold Xin <rxin@apache.org>
Closes#1948 from rxin/kryo and squashes the following commits:
a3a80d8 [Reynold Xin] [SPARK-3046] use executor's class loader as the default serializer classloader
3d13277 [Reynold Xin] Reverted that in TestJavaSerializerImpl too.
196f3dc [Reynold Xin] Ok one more commit to revert the classloader change.
c49b50c [Reynold Xin] Removed JavaSerializer change.
afbf37d [Reynold Xin] Moved the test case also.
a2e693e [Reynold Xin] Removed the Kryo bug fix from this pull request.
c81bd6c [Reynold Xin] Use defaultClassLoader when executing user specified custom registrator.
68f261e [Reynold Xin] Added license check excludes.
0c28179 [Reynold Xin] [SPARK-3045] Make Serializer interface Java friendly [SPARK-3046] Set executor's class loader as the default serializer class loader
The serializer is not always used in an executor thread (e.g. connection manager, broadcast), in which case the classloader might not have the user jar set, leading to corruption in deserialization.
https://issues.apache.org/jira/browse/SPARK-3046https://issues.apache.org/jira/browse/SPARK-2878
Author: Reynold Xin <rxin@apache.org>
Closes#1972 from rxin/kryoBug and squashes the following commits:
c1c7bf0 [Reynold Xin] Made change to JavaSerializer.
7204c33 [Reynold Xin] Added imports back.
d879e67 [Reynold Xin] [SPARK-3046] use executor's class loader as the default serializer class loader.
This is a rewrite of the original Netty module that was added about 1.5 years ago. The old code was turned off by default and didn't really work because it lacked a frame decoder (only worked with very very small blocks).
For this pull request, I tried to make the changes non-instrusive to the rest of Spark. I only added an init and shutdown to BlockManager/DiskBlockManager, and a bunch of comments to help me understand the existing code base.
Compared with the old Netty module, this one features:
- It appears to work :)
- SPARK-2941: option to specicy nio vs oio vs epoll for channel/transport. By default nio is used. (Not using Epoll yet because I have found some bugs with its implementation)
- SPARK-2943: options to specify send buf and receive buf for users who want to do hyper tuning
- SPARK-2942: io errors are reported from server to client (the protocol uses negative length to indicate error)
- SPARK-2940: fetching multiple blocks in a single request to reduce syscalls
- SPARK-2959: clients share a single thread pool
- SPARK-2990: use PooledByteBufAllocator to reduce GC (basically a Netty managed pool of buffers with jmalloc)
- SPARK-2625: added fetchWaitTime metric and fixed thread-safety issue in metrics update.
- SPARK-2367: bump Netty version to 4.0.21.Final to address an Epoll bug (https://groups.google.com/forum/#!topic/netty/O7m-HxCJpCA)
Compared with the existing communication manager, this one features:
- IMO it is substantially easier to understand
- zero-copy send for the server for on-disk blocks
- one-copy receive (due to a frame decoder)
- don't quote me on this, but I think a lot less sys calls
- SPARK-2990: use PooledByteBufAllocator to reduce GC (basically a Netty managed pool of buffers with jmalloc)
- SPARK-2941: option to specicy nio vs oio vs epoll for channel/transport. By default nio is used. (Not using Epoll yet because I have found some bugs with its implementation)
- SPARK-2943: options to specify send buf and receive buf for users who want to do hyper tuning
TODOs before it can fully replace the existing ConnectionManager, if that ever happens (most of them should probably be done in separate PRs since this needs to be turned on explicitly)
- [x] Basic test cases
- [ ] More unit/integration tests for failures
- [ ] Performance analysis
- [ ] Support client connection reuse so we don't need to keep opening new connections (not sure how useful this would be)
- [ ] Support putting blocks in addition to fetching blocks (i.e. two way transfer)
- [x] Support serving non-disk blocks
- [ ] Support SASL authentication
For a more comprehensive list, see https://issues.apache.org/jira/browse/SPARK-2468
Thanks to @coderplay for peer coding with me on a Sunday.
Author: Reynold Xin <rxin@apache.org>
Closes#1907 from rxin/netty and squashes the following commits:
f921421 [Reynold Xin] Upgrade Netty to 4.0.22.Final to fix another Epoll bug.
4b174ca [Reynold Xin] Shivaram's code review comment.
4a3dfe7 [Reynold Xin] Switched to nio for default (instead of epoll on Linux).
56bfb9d [Reynold Xin] Bump Netty version to 4.0.21.Final for some bug fixes.
b443a4b [Reynold Xin] Added debug message to help debug Jenkins failures.
57fc4d7 [Reynold Xin] Added test cases for BlockHeaderEncoder and BlockFetchingClientHandlerSuite.
22623e9 [Reynold Xin] Added exception handling and test case for BlockServerHandler and BlockFetchingClientHandler.
6550dd7 [Reynold Xin] Fixed block mgr init bug.
60c2edf [Reynold Xin] Beefed up server/client integration tests.
38d88d5 [Reynold Xin] Added missing test files.
6ce3f3c [Reynold Xin] Added some basic test cases.
47f7ce0 [Reynold Xin] Created server and client packages and moved files there.
b16f412 [Reynold Xin] Added commit count.
f13022d [Reynold Xin] Remove unused clone() in BlockFetcherIterator.
c57d68c [Reynold Xin] Added back missing files.
842dfa7 [Reynold Xin] Made everything work with proper reference counting.
3fae001 [Reynold Xin] Connected the new netty network module with rest of Spark.
1a8f6d4 [Reynold Xin] Completed protocol documentation.
2951478 [Reynold Xin] New Netty implementation.
cc7843d [Reynold Xin] Basic skeleton.
Note this also passes the TaskContext itself to the TaskCompletionListener. In the future we can mark TaskContext with the exception object if exception occurs during task execution.
Author: Reynold Xin <rxin@apache.org>
Closes#1938 from rxin/TaskContext and squashes the following commits:
145de43 [Reynold Xin] Added JavaTaskCompletionListenerImpl for Java API friendly guarantee.
f435ea5 [Reynold Xin] Added license header for TaskCompletionListener.
dc4ed27 [Reynold Xin] [SPARK-3027] TaskContext: tighten the visibility and provide Java friendly callback API
The previous behaviour of swallowing ClassNotFound exceptions when running a custom Kryo registrator could lead to difficult to debug problems later on at serialisation / deserialisation time, see SPARK-2878. Instead it is better to fail fast.
Added test case.
Author: Graham Dennis <graham.dennis@gmail.com>
Closes#1827 from GrahamDennis/feature/spark-2893 and squashes the following commits:
fbe4cb6 [Graham Dennis] [SPARK-2878]: Update the test case to match the updated exception message
65e53c5 [Graham Dennis] [SPARK-2893]: Improve message when a spark.kryo.registrator fails.
f480d85 [Graham Dennis] [SPARK-2893] Fix typo.
b59d2c2 [Graham Dennis] SPARK-2893: Do not swallow Exceptions when running a custom spark.kryo.registrator
Currently, local execution of Spark jobs is only used by take(), and it can be problematic as it can load a significant amount of data onto the driver. The worst case scenarios occur if the RDD is cached (guaranteed to load whole partition), has very large elements, or the partition is just large and we apply a filter with high selectivity or computational overhead.
Additionally, jobs that run locally in this manner do not show up in the web UI, and are thus harder to track or understand what is occurring.
This PR adds a flag to disable local execution, which is turned OFF by default, with the intention of perhaps eventually removing this functionality altogether. Removing it now is a tougher proposition since it is part of the public runJob API. An alternative solution would be to limit the flag to take()/first() to avoid impacting any external users of this API, but such usage (or, at least, reliance upon the feature) is hopefully minimal.
Author: Aaron Davidson <aaron@databricks.com>
Closes#1321 from aarondav/allowlocal and squashes the following commits:
136b253 [Aaron Davidson] Fix DAGSchedulerSuite
5599d55 [Aaron Davidson] [RFC] Disable local execution of Spark jobs by default
Instead of requiring "org.apache.spark.io.LZ4CompressionCodec", it is easier for users if Spark just accepts "lz4", "lzf", "snappy".
Author: Reynold Xin <rxin@apache.org>
Closes#1873 from rxin/compressionCodecShortForm and squashes the following commits:
9f50962 [Reynold Xin] Specify short-form compression codec names first.
63f78ee [Reynold Xin] Updated configuration documentation.
47b3848 [Reynold Xin] [SPARK-2953] Allow using short names for io compression codecs
This addresses SPARK-2931, a bug where getAllowedLocalityLevel() could throw ArrayIndexOutOfBoundsException. The fix here is to reset currentLocalityIndex after recomputing the locality levels.
Thanks to kayousterhout, mridulm, and lirui-intel for helping me to debug this.
Author: Josh Rosen <joshrosen@apache.org>
Closes#1896 from JoshRosen/SPARK-2931 and squashes the following commits:
48b60b5 [Josh Rosen] Move FakeRackUtil.cleanUp() info beforeEach().
6fec474 [Josh Rosen] Set currentLocalityIndex after recomputing locality levels.
9384897 [Josh Rosen] Update SPARK-2931 test to reflect changes in 63bdb1f41b.
9ecd455 [Josh Rosen] Apply @mridulm's patch for reproducing SPARK-2931.
To enable Python consistency and `Experimental` label of the `sampleByKeyExact` API.
Author: Doris Xin <doris.s.xin@gmail.com>
Author: Xiangrui Meng <meng@databricks.com>
Closes#1866 from dorx/stratified and squashes the following commits:
0ad97b2 [Doris Xin] reviewer comments.
2948aae [Doris Xin] remove unrelated changes
e990325 [Doris Xin] Merge branch 'master' into stratified
555a3f9 [Doris Xin] separate out sampleByKeyExact as its own API
616e55c [Doris Xin] merge master
245439e [Doris Xin] moved minSamplingRate to getUpperBound
eaf5771 [Doris Xin] bug fixes.
17a381b [Doris Xin] fixed a merge issue and a failed unit
ea7d27f [Doris Xin] merge master
b223529 [Xiangrui Meng] use approx bounds for poisson fix poisson mean for waitlisting add unit tests for Java
b3013a4 [Xiangrui Meng] move math3 back to test scope
eecee5f [Doris Xin] Merge branch 'master' into stratified
f4c21f3 [Doris Xin] Reviewer comments
a10e68d [Doris Xin] style fix
a2bf756 [Doris Xin] Merge branch 'master' into stratified
680b677 [Doris Xin] use mapPartitionWithIndex instead
9884a9f [Doris Xin] style fix
bbfb8c9 [Doris Xin] Merge branch 'master' into stratified
ee9d260 [Doris Xin] addressed reviewer comments
6b5b10b [Doris Xin] Merge branch 'master' into stratified
254e03c [Doris Xin] minor fixes and Java API.
4ad516b [Doris Xin] remove unused imports from PairRDDFunctions
bd9dc6e [Doris Xin] unit bug and style violation fixed
1fe1cff [Doris Xin] Changed fractionByKey to a map to enable arg check
944a10c [Doris Xin] [SPARK-2145] Add lower bound on sampling rate
0214a76 [Doris Xin] cleanUp
90d94c0 [Doris Xin] merge master
9e74ab5 [Doris Xin] Separated out most of the logic in sampleByKey
7327611 [Doris Xin] merge master
50581fc [Doris Xin] added a TODO for logging in python
46f6c8c [Doris Xin] fixed the NPE caused by closures being cleaned before being passed into the aggregate function
7e1a481 [Doris Xin] changed the permission on SamplingUtil
1d413ce [Doris Xin] fixed checkstyle issues
9ee94ee [Doris Xin] [SPARK-2082] stratified sampling in PairRDDFunctions that guarantees exact sample size
e3fd6a6 [Doris Xin] Merge branch 'master' into takeSample
7cab53a [Doris Xin] fixed import bug in rdd.py
ffea61a [Doris Xin] SPARK-1939: Refactor takeSample method in RDD
1441977 [Doris Xin] SPARK-1939 Refactor takeSample method in RDD to use ScaSRS
Author: GuoQiang Li <witgo@qq.com>
Closes#1836 from witgo/SPARK-2897 and squashes the following commits:
23cdc5b [GuoQiang Li] review commit
ada4fba [GuoQiang Li] TorrentBroadcast does not support broadcast compression
fb91792 [GuoQiang Li] org.apache.spark.broadcast.TorrentBroadcast does use the serializer class specified in the spark option "spark.serializer"
Author: Erik Erlandson <eerlands@redhat.com>
Closes#1841 from erikerlandson/spark-2911-pr and squashes the following commits:
4699e2f [Erik Erlandson] [SPARK-2911]: provide rdd.parent[T](j) to obtain jth parent RDD
Author: Sandy Ryza <sandy@cloudera.com>
Closes#1507 from sryza/sandy-spark-2565 and squashes the following commits:
74dad41 [Sandy Ryza] SPARK-2565. Update ShuffleReadMetrics as blocks are fetched
As described in https://issues.apache.org/jira/browse/SPARK-2787, right now sort-based shuffle is more expensive than hash-based for map operations that do no partial aggregation or sorting, such as groupByKey. This is because it has to serialize each data item twice (once when spilling to intermediate files, and then again when merging these files object-by-object). This patch adds a code path to just write separate files directly if the # of output partitions is small, and concatenate them at the end to produce a sorted file.
On the unit test side, I added some tests that force or don't force this bypass path to be used, and checked that our tests for other features (e.g. all the operations) cover both cases.
Author: Matei Zaharia <matei@databricks.com>
Closes#1799 from mateiz/SPARK-2787 and squashes the following commits:
88cf26a [Matei Zaharia] Fix rebase
10233af [Matei Zaharia] Review comments
398cb95 [Matei Zaharia] Fix looking up shuffle manager in conf
ca3efd9 [Matei Zaharia] Add docs for shuffle manager properties, and allow short names for them
d0ae3c5 [Matei Zaharia] Fix some comments
90d084f [Matei Zaharia] Add code path to bypass merge-sort in ExternalSorter, and tests
31e5d7c [Matei Zaharia] Move existing logic for writing partitioned files into ExternalSorter
fix bug of countApproxDistinct() when have more than one partition
Author: Davies Liu <davies.liu@gmail.com>
Closes#1812 from davies/approx and squashes the following commits:
bf757ce [Davies Liu] fix bug of countApproxDistinct() when have more than one partition
This patch modifies the ConnectionManager so that error messages are sent in reply when uncaught exceptions occur during message processing. This prevents message senders from hanging while waiting for an acknowledgment if the remote message processing failed.
This is an updated version of sarutak's PR, #1490. The main change is to use Futures / Promises to signal errors.
Author: Kousuke Saruta <sarutak@oss.nttdata.co.jp>
Author: Josh Rosen <joshrosen@apache.org>
Closes#1758 from JoshRosen/connection-manager-fixes and squashes the following commits:
68620cb [Josh Rosen] Fix test in BlockFetcherIteratorSuite:
83673de [Josh Rosen] Error ACKs should trigger IOExceptions, so catch only those exceptions in the test.
b8bb4d4 [Josh Rosen] Fix manager.id vs managerServer.id typo that broke security tests.
659521f [Josh Rosen] Include previous exception when throwing new one
a2f745c [Josh Rosen] Remove sendMessageReliablySync; callers can wait themselves.
c01c450 [Josh Rosen] Return Try[Message] from sendMessageReliablySync.
f1cd1bb [Josh Rosen] Clean up @sarutak's PR #1490 for [SPARK-2583]: ConnectionManager error reporting
7399c6b [Josh Rosen] Merge remote-tracking branch 'origin/pr/1490' into connection-manager-fixes
ee91bb7 [Kousuke Saruta] Modified BufferMessage.scala to keep the spark code style
9dfd0d8 [Kousuke Saruta] Merge branch 'master' of git://git.apache.org/spark into SPARK-2583
e7d9aa6 [Kousuke Saruta] rebase to master
326a17f [Kousuke Saruta] Add test cases to ConnectionManagerSuite.scala for SPARK-2583
2a18d6b [Kousuke Saruta] Merge branch 'master' of git://git.apache.org/spark into SPARK-2583
22d7ebd [Kousuke Saruta] Add test cases to BlockManagerSuite for SPARK-2583
e579302 [Kousuke Saruta] Merge branch 'master' of git://git.apache.org/spark into SPARK-2583
281589c [Kousuke Saruta] Add a test case to BlockFetcherIteratorSuite.scala for fetching block from remote from successfully
0654128 [Kousuke Saruta] Merge branch 'master' of git://git.apache.org/spark into SPARK-2583
ffaa83d [Kousuke Saruta] Merge branch 'master' of git://git.apache.org/spark into SPARK-2583
12d3de8 [Kousuke Saruta] Added BlockFetcherIteratorSuite.scala
4117b8f [Kousuke Saruta] Modified ConnectionManager to be alble to handle error during processing message
717c9c3 [Kousuke Saruta] Merge branch 'master' of git://git.apache.org/spark into SPARK-2583
6635467 [Kousuke Saruta] Merge branch 'master' of git://git.apache.org/spark into SPARK-2583
e2b8c4a [Kousuke Saruta] Modify to propagete error using ConnectionManager
I haven't tested this out on a cluster yet, but wanted to make sure the approach (passing ShuffleWriteMetrics down to DiskBlockObjectWriter) was ok
Author: Sandy Ryza <sandy@cloudera.com>
Closes#1481 from sryza/sandy-spark-2566 and squashes the following commits:
8090d88 [Sandy Ryza] Fix ExternalSorter
b2a62ed [Sandy Ryza] Fix more test failures
8be6218 [Sandy Ryza] Fix test failures and mark a couple variables private
c5e68e5 [Sandy Ryza] SPARK-2566. Update ShuffleWriteMetrics incrementally
JIRA issues:
- Main: [SPARK-2678](https://issues.apache.org/jira/browse/SPARK-2678)
- Related: [SPARK-2874](https://issues.apache.org/jira/browse/SPARK-2874)
Related PR:
- #1715
This PR is both a fix for SPARK-2874 and a workaround for SPARK-2678. Fixing SPARK-2678 completely requires some API level changes that need further discussion, and we decided not to include it in Spark 1.1 release. As currently SPARK-2678 only affects Spark SQL scripts, this workaround is enough for Spark 1.1. Command line option handling logic in bash scripts looks somewhat dirty and duplicated, but it helps to provide a cleaner user interface as well as retain full downward compatibility for now.
Author: Cheng Lian <lian.cs.zju@gmail.com>
Closes#1801 from liancheng/spark-2874 and squashes the following commits:
8045d7a [Cheng Lian] Make sure test suites pass
8493a9e [Cheng Lian] Using eval to retain quoted arguments
aed523f [Cheng Lian] Fixed typo in bin/spark-sql
f12a0b1 [Cheng Lian] Worked arount SPARK-2678
daee105 [Cheng Lian] Fixed usage messages of all Spark SQL related scripts
The goal of this PR is to allow users of Spark to write tight firewall rules for their clusters. This is currently not possible because Spark uses random ports in many places, notably the communication between executors and drivers. The changes in this PR are based on top of ash211's changes in #1107.
The list covered here may or may not be the complete set of port needed for Spark to operate perfectly. However, as of the latest commit there are no known sources of random ports (except in tests). I have not documented a few of the more obscure configs.
My spark-env.sh looks like this:
```
export SPARK_MASTER_PORT=6060
export SPARK_WORKER_PORT=7070
export SPARK_MASTER_WEBUI_PORT=9090
export SPARK_WORKER_WEBUI_PORT=9091
```
and my spark-defaults.conf looks like this:
```
spark.master spark://andrews-mbp:6060
spark.driver.port 5001
spark.fileserver.port 5011
spark.broadcast.port 5021
spark.replClassServer.port 5031
spark.blockManager.port 5041
spark.executor.port 5051
```
Author: Andrew Or <andrewor14@gmail.com>
Author: Andrew Ash <andrew@andrewash.com>
Closes#1777 from andrewor14/configure-ports and squashes the following commits:
621267b [Andrew Or] Merge branch 'master' of github.com:apache/spark into configure-ports
8a6b820 [Andrew Or] Use a random UI port during tests
7da0493 [Andrew Or] Fix tests
523c30e [Andrew Or] Add test for isBindCollision
b97b02a [Andrew Or] Minor fixes
c22ad00 [Andrew Or] Merge branch 'master' of github.com:apache/spark into configure-ports
93d359f [Andrew Or] Executors connect to wrong port when collision occurs
d502e5f [Andrew Or] Handle port collisions when creating Akka systems
a2dd05c [Andrew Or] Patrick's comment nit
86461e2 [Andrew Or] Remove spark.executor.env.port and spark.standalone.client.port
1d2d5c6 [Andrew Or] Fix ports for standalone cluster mode
cb3be88 [Andrew Or] Various doc fixes (broken link, format etc.)
e837cde [Andrew Or] Remove outdated TODOs
bfbab28 [Andrew Or] Merge branch 'master' of github.com:apache/spark into configure-ports
de1b207 [Andrew Or] Update docs to reflect new ports
b565079 [Andrew Or] Add spark.ports.maxRetries
2551eb2 [Andrew Or] Remove spark.worker.watcher.port
151327a [Andrew Or] Merge branch 'master' of github.com:apache/spark into configure-ports
9868358 [Andrew Or] Add a few miscellaneous ports
6016e77 [Andrew Or] Add spark.executor.port
8d836e6 [Andrew Or] Also document SPARK_{MASTER/WORKER}_WEBUI_PORT
4d9e6f3 [Andrew Or] Fix super subtle bug
3f8e51b [Andrew Or] Correct erroneous docs...
e111d08 [Andrew Or] Add names for UI services
470f38c [Andrew Or] Special case non-"Address already in use" exceptions
1d7e408 [Andrew Or] Treat 0 ports specially + return correct ConnectionManager port
ba32280 [Andrew Or] Minor fixes
6b550b0 [Andrew Or] Assorted fixes
73fbe89 [Andrew Or] Move start service logic to Utils
ec676f4 [Andrew Or] Merge branch 'SPARK-2157' of github.com:ash211/spark into configure-ports
038a579 [Andrew Ash] Trust the server start function to report the port the service started on
7c5bdc4 [Andrew Ash] Fix style issue
0347aef [Andrew Ash] Unify port fallback logic to a single place
24a4c32 [Andrew Ash] Remove type on val to match surrounding style
9e4ad96 [Andrew Ash] Reformat for style checker
5d84e0e [Andrew Ash] Document new port configuration options
066dc7a [Andrew Ash] Fix up HttpServer port increments
cad16da [Andrew Ash] Add fallover increment logic for HttpServer
c5a0568 [Andrew Ash] Fix ConnectionManager to retry with increment
b80d2fd [Andrew Ash] Make Spark's block manager port configurable
17c79bb [Andrew Ash] Add a configuration option for spark-shell's class server
f34115d [Andrew Ash] SPARK-1176 Add port configuration for HttpBroadcast
49ee29b [Andrew Ash] SPARK-1174 Add port configuration for HttpFileServer
1c0981a [Andrew Ash] Make port in HttpServer configurable
copied from original JIRA (https://issues.apache.org/jira/browse/SPARK-2294):
If an executor E is free, a task may be speculatively assigned to E when there are other tasks in the job that have not been launched (at all) yet. Similarly, a task without any locality preferences may be assigned to E when there was another NODE_LOCAL task that could have been scheduled.
This happens because TaskSchedulerImpl calls TaskSetManager.resourceOffer (which in turn calls TaskSetManager.findTask) with increasing locality levels, beginning with PROCESS_LOCAL, followed by NODE_LOCAL, and so on until the highest currently allowed level. Now, supposed NODE_LOCAL is the highest currently allowed locality level. The first time findTask is called, it will be called with max level PROCESS_LOCAL; if it cannot find any PROCESS_LOCAL tasks, it will try to schedule tasks with no locality preferences or speculative tasks. As a result, speculative tasks or tasks with no preferences may be scheduled instead of NODE_LOCAL tasks.
----
I added an additional parameter in resourceOffer and findTask, maxLocality, indicating when we should consider the tasks without locality preference
Author: CodingCat <zhunansjtu@gmail.com>
Closes#1313 from CodingCat/SPARK-2294 and squashes the following commits:
bf3f13b [CodingCat] rollback some forgotten changes
89f9bc0 [CodingCat] address matei's comments
18cae02 [CodingCat] add test case for node-local tasks
2ba6195 [CodingCat] fix failed test cases
87dd09e [CodingCat] fix style
9b9432f [CodingCat] remove hasNodeLocalOnlyTasks
fdd1573 [CodingCat] fix failed test cases
941a4fd [CodingCat] see my shocked face..........
f600085 [CodingCat] remove hasNodeLocalOnlyTasks checking
0b8a46b [CodingCat] test whether hasNodeLocalOnlyTasks affect the results
73ceda8 [CodingCat] style fix
b3a430b [CodingCat] remove fine granularity tracking for node-local only tasks
f9a2ad8 [CodingCat] simplify the logic in TaskSchedulerImpl
c8c1de4 [CodingCat] simplify the patch
be652ed [CodingCat] avoid unnecessary delay when we only have nopref tasks
dee9e22 [CodingCat] fix locality inversion bug in TaskManager by moving nopref branch
This patch adds support for giving accumulators user-visible names and displaying accumulator values in the web UI. This allows users to create custom counters that can display in the UI. The current approach displays both the accumulator deltas caused by each task and a "current" value of the accumulator totals for each stage, which gets update as tasks finish.
Currently in Spark developers have been extending the `TaskMetrics` functionality to provide custom instrumentation for RDD's. This provides a potentially nicer alternative of going through the existing accumulator framework (actually `TaskMetrics` and accumulators are on an awkward collision course as we add more features to the former). The current patch demo's how we can use the feature to provide instrumentation for RDD input sizes. The nice thing about going through accumulators is that users can read the current value of the data being tracked in their programs. This could be useful to e.g. decide to short-circuit a Spark stage depending on how things are going.
Author: Patrick Wendell <pwendell@gmail.com>
Closes#1309 from pwendell/metrics and squashes the following commits:
8815308 [Patrick Wendell] Merge remote-tracking branch 'apache/master' into HEAD
93fbe0f [Patrick Wendell] Other minor fixes
cc43f68 [Patrick Wendell] Updating unit tests
c991b1b [Patrick Wendell] Moving some code into the Accumulators class
9a9ba3c [Patrick Wendell] More merge fixes
c5ace9e [Patrick Wendell] More merge conflicts
1da15e3 [Patrick Wendell] Merge remote-tracking branch 'apache/master' into metrics
9860c55 [Patrick Wendell] Potential solution to posting listener events
0bb0e33 [Patrick Wendell] Remove "display" variable and assume display = name.isDefined
0ec4ac7 [Patrick Wendell] Java API's
e95bf69 [Patrick Wendell] Stash
be97261 [Patrick Wendell] Style fix
8407308 [Patrick Wendell] Removing examples in Hadoop and RDD class
64d405f [Patrick Wendell] Adding missing file
5d8b156 [Patrick Wendell] Changes based on Kay's review.
9f18bad [Patrick Wendell] Minor style changes and tests
7a63abc [Patrick Wendell] Adding Json serialization and responding to Reynold's feedback
ad85076 [Patrick Wendell] Example of using named accumulators for custom RDD metrics.
0b72660 [Patrick Wendell] Initial WIP example of supporing globally named accumulators.
It was easier to combine these 2 jira since they touch many of the same places. This pr adds the following:
- adds modify acls
- adds admin acls (list of admins/users that get added to both view and modify acls)
- modify Kill button on UI to take modify acls into account
- changes config name of spark.ui.acls.enable to spark.acls.enable since I choose poorly in original name. We keep backwards compatibility so people can still use spark.ui.acls.enable. The acls should apply to any web ui as well as any CLI interfaces.
- send view and modify acls information on to YARN so that YARN interfaces can use (yarn cli for killing applications for example).
Author: Thomas Graves <tgraves@apache.org>
Closes#1196 from tgravescs/SPARK-1890 and squashes the following commits:
8292eb1 [Thomas Graves] review comments
b92ec89 [Thomas Graves] remove unneeded variable from applistener
4c765f4 [Thomas Graves] Add in admin acls
72eb0ac [Thomas Graves] Add modify acls
This tracks memory properly if there are multiple spilling collections in the same task (which was a problem before), and also implements an algorithm that lets each thread grow up to 1 / 2N of the memory pool (where N is the number of threads) before spilling, which avoids an inefficiency with small spills we had before (some threads would spill many times at 0-1 MB because the pool was allocated elsewhere).
Author: Matei Zaharia <matei@databricks.com>
Closes#1707 from mateiz/spark-2711 and squashes the following commits:
debf75b [Matei Zaharia] Review comments
24f28f3 [Matei Zaharia] Small rename
c8f3a8b [Matei Zaharia] Update ShuffleMemoryManager to be able to partially grant requests
315e3a5 [Matei Zaharia] Some review comments
b810120 [Matei Zaharia] Create central manager to track memory for all spilling collections
Author: Reynold Xin <rxin@apache.org>
Closes#1772 from rxin/accumulator-dagscheduler and squashes the following commits:
6a58520 [Reynold Xin] [SPARK-2323] Exception in accumulator update should not crash DAGScheduler & SparkContext.
All these changes are from mridulm's work in #1609, but extracted here to fix this specific issue and make it easier to merge not 1.1. This particular set of changes is to make sure that we read exactly the right range of bytes from each spill file in EAOM: some serializers can write bytes after the last object (e.g. the TC_RESET flag in Java serialization) and that would confuse the previous code into reading it as part of the next batch. There are also improvements to cleanup to make sure files are closed.
In addition to bringing in the changes to ExternalAppendOnlyMap, I also copied them to the corresponding code in ExternalSorter and updated its test suite to test for the same issues.
Author: Matei Zaharia <matei@databricks.com>
Closes#1722 from mateiz/spark-2792 and squashes the following commits:
5d4bfb5 [Matei Zaharia] Make objectStreamReset counter count the last object written too
18fe865 [Matei Zaharia] Update docs on objectStreamReset
576ee83 [Matei Zaharia] Allow objectStreamReset to be 0
0374217 [Matei Zaharia] Remove super paranoid code to close file handles
bda37bb [Matei Zaharia] Implement Mridul's ExternalAppendOnlyMap fixes in ExternalSorter too
0d6dad7 [Matei Zaharia] Added Mridul's test changes for ExternalAppendOnlyMap
9a78e4b [Matei Zaharia] Add @mridulm's fixes to ExternalAppendOnlyMap for batch sizes
`spark.test.home` was introduced in #1734. This is fine for SBT but is failing maven tests. Either way it shouldn't throw an NPE.
Author: Andrew Or <andrewor14@gmail.com>
Closes#1739 from andrewor14/fix-spark-test-home and squashes the following commits:
ce2624c [Andrew Or] Do not throw NPE if spark.test.home is not set
When standalone Workers launch executors, they inherit the Spark home set by the driver. This means if the worker machines do not share the same directory structure as the driver node, the Workers will attempt to run scripts (e.g. bin/compute-classpath.sh) that do not exist locally and fail. This is a common scenario if the driver is launched from outside of the cluster.
The solution is to simply not pass the driver's Spark home to the Workers. This PR further makes an attempt to avoid overloading the usages of `spark.home`, which is now only used for setting executor Spark home on Mesos and in python.
This is based on top of #1392 and originally reported by YanTangZhai. Tested on standalone cluster.
Author: Andrew Or <andrewor14@gmail.com>
Closes#1734 from andrewor14/spark-home-reprise and squashes the following commits:
f71f391 [Andrew Or] Revert changes in python
1c2532c [Andrew Or] Merge branch 'master' of github.com:apache/spark into spark-home-reprise
188fc5d [Andrew Or] Avoid using spark.home where possible
09272b7 [Andrew Or] Always use Worker's working directory as spark home
The existing code in `StorageUtils` is not the most efficient. Every time we want to update an `RDDInfo` we end up iterating through all blocks on all block managers just to discard most of them. The symptoms manifest themselves in the bountiful UI bugs observed in the wild. Many of these bugs are caused by the slow consumption of events in `LiveListenerBus`, which frequently leads to the event queue overflowing and `SparkListenerEvent`s being dropped on the floor. The changes made in this PR avoid this by first filtering out only the blocks relevant to us before computing storage information from them.
It's worth a mention that this corner of the Spark code is also not very well-tested at all. The bulk of the changes in this PR (more than 60%) is actually test cases for the various logic in `StorageUtils.scala` as well as `StorageTab.scala`. These will eventually be extended to cover the various listeners that constitute the `SparkUI`.
Author: Andrew Or <andrewor14@gmail.com>
Closes#1679 from andrewor14/fix-drop-events and squashes the following commits:
f80c1fa [Andrew Or] Rewrite fold and reduceOption as sum
e132d69 [Andrew Or] Merge branch 'master' of github.com:apache/spark into fix-drop-events
14fa1c3 [Andrew Or] Simplify some code + update a few comments
a91be46 [Andrew Or] Make ExecutorsPage blazingly fast
bf6f09b [Andrew Or] Minor changes
8981de1 [Andrew Or] Merge branch 'master' of github.com:apache/spark into fix-drop-events
af19bc0 [Andrew Or] *UsedByRDD -> *UsedByRdd (minor)
6970bc8 [Andrew Or] Add extensive tests for StorageListener and the new code in StorageUtils
e080b9e [Andrew Or] Reduce run time of StorageUtils.updateRddInfo to near constant
2c3ef6a [Andrew Or] Actually filter out only the relevant RDDs
6fef86a [Andrew Or] Add extensive tests for new code in StorageStatus
b66b6b0 [Andrew Or] Use more efficient underlying data structures for blocks
6a7b7c0 [Andrew Or] Avoid chained operations on TraversableLike
a9ec384 [Andrew Or] Merge branch 'master' of github.com:apache/spark into fix-drop-events
b12fcd7 [Andrew Or] Fix tests + simplify sc.getRDDStorageInfo
da8e322 [Andrew Or] Merge branch 'master' of github.com:apache/spark into fix-drop-events
8e91921 [Andrew Or] Iterate through a filtered set of blocks when updating RDDInfo
7b2c4aa [Andrew Or] Rewrite blockLocationsFromStorageStatus + clean up method signatures
41fa50d [Andrew Or] Add a legacy constructor for StorageStatus
53af15d [Andrew Or] Refactor StorageStatus + add a bunch of tests
All changes from this PR are by mridulm and are drawn from his work in #1609. This patch is intended to fix all major issues related to shuffle file consolidation that mridulm found, while minimizing changes to the code, with the hope that it may be more easily merged into 1.1.
This patch is **not** intended as a replacement for #1609, which provides many additional benefits, including fixes to ExternalAppendOnlyMap, improvements to DiskBlockObjectWriter's API, and several new unit tests.
If it is feasible to merge #1609 for the 1.1 deadline, that is a preferable option.
Author: Aaron Davidson <aaron@databricks.com>
Closes#1678 from aarondav/consol and squashes the following commits:
53b3f6d [Aaron Davidson] Correct behavior when writing unopened file
701d045 [Aaron Davidson] Rebase with sort-based shuffle
9160149 [Aaron Davidson] SPARK-2532: Minimal shuffle consolidation fixes
getPreferredLocs traverses a dependency graph of partitions using depth first search. Given a complex dependency graph, the old implementation may explore a set of paths in the graph that is exponential in the number of nodes. By maintaining a set of visited nodes the new implementation avoids revisiting nodes, preventing exponential blowup.
Some comment and whitespace cleanups are also included.
Author: Aaron Staple <aaron.staple@gmail.com>
Closes#1362 from staple/SPARK-695 and squashes the following commits:
ecea0f3 [Aaron Staple] address review comments
751c661 [Aaron Staple] [SPARK-695] Add a unit test.
5adf326 [Aaron Staple] Replace getPreferredLocsInternal's HashMap argument with a simpler HashSet.
58e37d0 [Aaron Staple] Replace comment documenting NarrowDependency.
6751ced [Aaron Staple] Revert "Remove unused variable."
04c7097 [Aaron Staple] Fix indentation.
0030884 [Aaron Staple] Remove unused variable.
33f67c6 [Aaron Staple] Clarify comment.
4e42b46 [Aaron Staple] Remove apparently incorrect comment describing NarrowDependency.
65c2d3d [Aaron Staple] [SPARK-695] In DAGScheduler's getPreferredLocs, track set of visited partitions.
This is a sketch of a patch that allows the UI to show metrics for tasks that have not yet completed. It adds a heartbeat every 2 seconds from the executors to the driver, reporting metrics for all of the executor's tasks.
It still needs unit tests, polish, and cluster testing, but I wanted to put it up to get feedback on the approach.
Author: Sandy Ryza <sandy@cloudera.com>
Closes#1056 from sryza/sandy-spark-2099 and squashes the following commits:
93b9fdb [Sandy Ryza] Up heartbeat interval to 10 seconds and other tidying
132aec7 [Sandy Ryza] Heartbeat and HeartbeatResponse are already Serializable as case classes
38dffde [Sandy Ryza] Additional review feedback and restore test that was removed in BlockManagerSuite
51fa396 [Sandy Ryza] Remove hostname race, add better comments about threading, and some stylistic improvements
3084f10 [Sandy Ryza] Make TaskUIData a case class again
3bda974 [Sandy Ryza] Stylistic fixes
0dae734 [Sandy Ryza] SPARK-2099. Report progress while task is running.
[SPARK-2557](https://issues.apache.org/jira/browse/SPARK-2557)
Author: Ye Xianjin <advancedxy@gmail.com>
Closes#1464 from advancedxy/SPARK-2557 and squashes the following commits:
d844d67 [Ye Xianjin] add local-*-n-failures, bad-local-n, bad-local-n-failures test case
3bbc668 [Ye Xianjin] fix LOCAL_N_REGEX regular expression and make local_n_failures accept * as all cores on the computer
This patch simply uses the ExternalSorter class from sort-based shuffle.
Closes#931 and Closes#1090
Author: Matei Zaharia <matei@databricks.com>
Closes#1677 from mateiz/spark-983 and squashes the following commits:
96b3fda [Matei Zaharia] SPARK-983. Support external sorting in sortByKey()
Author: Kousuke Saruta <sarutak@oss.nttdata.co.jp>
Closes#1578 from sarutak/SPARK-2670 and squashes the following commits:
85c8938 [Kousuke Saruta] Removed useless results.put for fail fast
e8713cc [Kousuke Saruta] Merge branch 'master' of git://git.apache.org/spark into SPARK-2670
d353984 [Kousuke Saruta] Refined assertion messages in BlockFetcherIteratorSuite.scala
03bcb02 [Kousuke Saruta] Merge branch 'SPARK-2670' of github.com:sarutak/spark into SPARK-2670
5d05855 [Kousuke Saruta] Merge branch 'master' of git://git.apache.org/spark into SPARK-2670
4fca130 [Kousuke Saruta] Added test cases for BasicBlockFetcherIterator
b7b8250 [Kousuke Saruta] Modified BasicBlockFetchIterator to fail fast when local fetch error has been occurred
a3a9be1 [Kousuke Saruta] Modified BlockFetcherIterator for SPARK-2670
460dc01 [Kousuke Saruta] Merge branch 'master' of git://git.apache.org/spark into SPARK-2670
e310c0b [Kousuke Saruta] Modified BlockFetcherIterator to handle local fetch failure as fatch fail
Author: Sandy Ryza <sandy@cloudera.com>
Closes#1642 from sryza/sandy-spark-2738 and squashes the following commits:
a923e4e [Sandy Ryza] SPARK-2738. Remove redundant imports in BlockManagerSuite
...ags
Author: Sandy Ryza <sandy@cloudera.com>
Closes#1665 from sryza/sandy-spark-2664 and squashes the following commits:
0518c63 [Sandy Ryza] SPARK-2664. Deal with `--conf` options in spark-submit that relate to flags
This allows users to gain access to the InputSplit which backs each partition.
An alternative solution would have been to have a .withInputSplit() method which returns a new RDD[(InputSplit, (K, V))], but this is confusing because you could not cache this RDD or shuffle it, as InputSplit is not inherently serializable.
Author: Aaron Davidson <aaron@databricks.com>
Closes#973 from aarondav/hadoop and squashes the following commits:
9c9112b [Aaron Davidson] Add JavaAPISuite test
9942cd7 [Aaron Davidson] Add Java API
1284a3a [Aaron Davidson] SPARK-2028: Expose mapPartitionsWithInputSplit in HadoopRDD
The Java API's use of fake ClassTags doesn't seem to cause any problems for Java users, but it can lead to issues when passing JavaRDDs' underlying RDDs to Scala code (e.g. in the MLlib Java API wrapper code). If we call collect() on a Scala RDD with an incorrect ClassTag, this causes ClassCastExceptions when we try to allocate an array of the wrong type (for example, see SPARK-2197).
There are a few possible fixes here. An API-breaking fix would be to completely remove the fake ClassTags and require Java API users to pass java.lang.Class instances to all parallelize() calls and add returnClass fields to all Function implementations. This would be extremely verbose.
Instead, this patch adds internal APIs to "repair" a Scala RDD with an incorrect ClassTag by wrapping it and overriding its ClassTag. This should be okay for cases where the Scala code that calls collect() knows what type of array should be allocated, which is the case in the MLlib wrappers.
Author: Josh Rosen <joshrosen@apache.org>
Closes#1639 from JoshRosen/SPARK-2737 and squashes the following commits:
572b4c8 [Josh Rosen] Replace newRDD[T] with mapPartitions().
469d941 [Josh Rosen] Preserve partitioner in retag().
af78816 [Josh Rosen] Allow retag() to get classTag implicitly.
d1d54e6 [Josh Rosen] [SPARK-2737] Add retag() method for changing RDDs' ClassTags.
We resolve relative paths to the local `file:/` system for `--jars` and `--files` in spark submit (#853). We should do the same for the history server.
Author: Andrew Or <andrewor14@gmail.com>
Closes#1280 from andrewor14/hist-serv-fix and squashes the following commits:
13ff406 [Andrew Or] Merge branch 'master' of github.com:apache/spark into hist-serv-fix
b393e17 [Andrew Or] Strip trailing "/" from logging directory
622a471 [Andrew Or] Fix test in EventLoggingListenerSuite
0e20f71 [Andrew Or] Shift responsibility of resolving paths up one level
b037c0c [Andrew Or] Use resolved paths for everything in history server
c7e36ee [Andrew Or] Resolve paths for event logging too
40e3933 [Andrew Or] Resolve history server file paths
Author: Reynold Xin <rxin@apache.org>
Closes#1675 from rxin/unionrdd and squashes the following commits:
941d316 [Reynold Xin] Clear RDDs for checkpointing.
c9f05f2 [Reynold Xin] [SPARK-2758] UnionRDD's UnionPartition should not reference parent RDDs
This adds a new ShuffleManager based on sorting, as described in https://issues.apache.org/jira/browse/SPARK-2045. The bulk of the code is in an ExternalSorter class that is similar to ExternalAppendOnlyMap, but sorts key-value pairs by partition ID and can be used to create a single sorted file with a map task's output. (Longer-term I think this can take on the remaining functionality in ExternalAppendOnlyMap and replace it so we don't have code duplication.)
The main TODOs still left are:
- [x] enabling ExternalSorter to merge across spilled files
- [x] with an Ordering
- [x] without an Ordering, using the keys' hash codes
- [x] adding more tests (e.g. a version of our shuffle suite that runs on this)
- [x] rebasing on top of the size-tracking refactoring in #1165 when that is merged
- [x] disabling spilling if spark.shuffle.spill is set to false
Despite this though, this seems to work pretty well (running successfully in cases where the hash shuffle would OOM, such as 1000 reduce tasks on executors with only 1G memory), and it seems to be comparable in speed or faster than hash-based shuffle (it will create much fewer files for the OS to keep track of). So I'm posting it to get some early feedback.
After these TODOs are done, I'd also like to enable ExternalSorter to sort data within each partition by a key as well, which will allow us to use it to implement external spilling in reduce tasks in `sortByKey`.
Author: Matei Zaharia <matei@databricks.com>
Closes#1499 from mateiz/sort-based-shuffle and squashes the following commits:
bd841f9 [Matei Zaharia] Various review comments
d1c137fd [Matei Zaharia] Various review comments
a611159 [Matei Zaharia] Compile fixes due to rebase
62c56c8 [Matei Zaharia] Fix ShuffledRDD sometimes not returning Tuple2s.
f617432 [Matei Zaharia] Fix a failing test (seems to be due to change in SizeTracker logic)
9464d5f [Matei Zaharia] Simplify code and fix conflicts after latest rebase
0174149 [Matei Zaharia] Add cleanup behavior and cleanup tests for sort-based shuffle
eb4ee0d [Matei Zaharia] Remove customizable element type in ShuffledRDD
fa2e8db [Matei Zaharia] Allow nextBatchStream to be called after we're done looking at all streams
a34b352 [Matei Zaharia] Fix tracking of indices within a partition in SpillReader, and add test
03e1006 [Matei Zaharia] Add a SortShuffleSuite that runs ShuffleSuite with sort-based shuffle
3c7ff1f [Matei Zaharia] Obey the spark.shuffle.spill setting in ExternalSorter
ad65fbd [Matei Zaharia] Rebase on top of Aaron's Sorter change, and use Sorter in our buffer
44d2a93 [Matei Zaharia] Use estimateSize instead of atGrowThreshold to test collection sizes
5686f71 [Matei Zaharia] Optimize merging phase for in-memory only data:
5461cbb [Matei Zaharia] Review comments and more tests (e.g. tests with 1 element per partition)
e9ad356 [Matei Zaharia] Update ContextCleanerSuite to make sure shuffle cleanup tests use hash shuffle (since they were written for it)
c72362a [Matei Zaharia] Added bug fix and test for when iterators are empty
de1fb40 [Matei Zaharia] Make trait SizeTrackingCollection private[spark]
4988d16 [Matei Zaharia] tweak
c1b7572 [Matei Zaharia] Small optimization
ba7db7f [Matei Zaharia] Handle null keys in hash-based comparator, and add tests for collisions
ef4e397 [Matei Zaharia] Support for partial aggregation even without an Ordering
4b7a5ce [Matei Zaharia] More tests, and ability to sort data if a total ordering is given
e1f84be [Matei Zaharia] Fix disk block manager test
5a40a1c [Matei Zaharia] More tests
614f1b4 [Matei Zaharia] Add spill metrics to map tasks
cc52caf [Matei Zaharia] Add more error handling and tests for error cases
bbf359d [Matei Zaharia] More work
3a56341 [Matei Zaharia] More partial work towards sort-based shuffle
7a0895d [Matei Zaharia] Some more partial work towards sort-based shuffle
b615476 [Matei Zaharia] Scaffolding for sort-based shuffle
This is a resubmission of #1452. It was reverted because it broke the build.
Currently (as of Spark 1.0.1), Spark sends RDD object (which contains closures) using Akka along with the task itself to the executors. This is inefficient because all tasks in the same stage use the same RDD object, but we have to send RDD object multiple times to the executors. This is especially bad when a closure references some variable that is very large. The current design led to users having to explicitly broadcast large variables.
The patch uses broadcast to send RDD objects and the closures to executors, and use Akka to only send a reference to the broadcast RDD/closure along with the partition specific information for the task. For those of you who know more about the internals, Spark already relies on broadcast to send the Hadoop JobConf every time it uses the Hadoop input, because the JobConf is large.
The user-facing impact of the change include:
1. Users won't need to decide what to broadcast anymore, unless they would want to use a large object multiple times in different operations
2. Task size will get smaller, resulting in faster scheduling and higher task dispatch throughput.
In addition, the change will simplify some internals of Spark, eliminating the need to maintain task caches and the complex logic to broadcast JobConf (which also led to a deadlock recently).
A simple way to test this:
```scala
val a = new Array[Byte](1000*1000); scala.util.Random.nextBytes(a);
sc.parallelize(1 to 1000, 1000).map { x => a; x }.groupBy { x => a; x }.count
```
Numbers on 3 r3.8xlarge instances on EC2
```
master branch: 5.648436068 s, 4.715361895 s, 5.360161877 s
with this change: 3.416348793 s, 1.477846558 s, 1.553432156 s
```
Author: Reynold Xin <rxin@apache.org>
Closes#1498 from rxin/broadcast-task and squashes the following commits:
f7364db [Reynold Xin] Code review feedback.
f8535dc [Reynold Xin] Fixed the style violation.
252238d [Reynold Xin] Serialize the final task closure as well as ShuffleDependency in taskBinary.
111007d [Reynold Xin] Fix broadcast tests.
797c247 [Reynold Xin] Properly send SparkListenerStageSubmitted and SparkListenerStageCompleted.
bab1d8b [Reynold Xin] Check for NotSerializableException in submitMissingTasks.
cf38450 [Reynold Xin] Use TorrentBroadcastFactory.
991c002 [Reynold Xin] Use HttpBroadcast.
de779f8 [Reynold Xin] Fix TaskContextSuite.
cc152fc [Reynold Xin] Don't cache the RDD broadcast variable.
d256b45 [Reynold Xin] Fixed unit test failures. One more to go.
cae0af3 [Reynold Xin] [SPARK-2521] Broadcast RDD object (instead of sending it along with every task).
Author: Koert Kuipers <koert@tresata.com>
Closes#735 from koertkuipers/feat-kryo-max-buffersize and squashes the following commits:
15f6d81 [Koert Kuipers] change default for spark.kryoserializer.buffer.max.mb to 64mb and add some documentation
1bcc22c [Koert Kuipers] Merge branch 'master' into feat-kryo-max-buffersize
0c9f8eb [Koert Kuipers] make default for kryo max buffer size 16MB
143ec4d [Koert Kuipers] test resizable buffer in kryo Output
0732445 [Koert Kuipers] support setting maxCapacity to something different than capacity in kryo Output
The main thing was that spark configs were not propagated to the driver, and so applications that do not specify `master` or `appName` automatically failed. This PR fixes that and a couple of miscellaneous things that are related.
One thing that may or may not be an issue is that the jars must be available on the driver node. In `standalone-cluster` mode, this effectively means these jars must be available on all the worker machines, since the driver is launched on one of them. The semantics here are not the same as `yarn-cluster` mode, where all the relevant jars are uploaded to a distributed cache automatically and shipped to the containers. This is probably not a concern, but still worth a mention.
Author: Andrew Or <andrewor14@gmail.com>
Closes#1538 from andrewor14/standalone-cluster and squashes the following commits:
8c11a0d [Andrew Or] Clean up imports / comments (minor)
2678d13 [Andrew Or] Handle extraJavaOpts properly
7660547 [Andrew Or] Merge branch 'master' of github.com:apache/spark into standalone-cluster
6f64a9b [Andrew Or] Revert changes in YARN
2f2908b [Andrew Or] Fix tests
ed01491 [Andrew Or] Don't go overboard with escaping
8e105e1 [Andrew Or] Merge branch 'master' of github.com:apache/spark into standalone-cluster
b890949 [Andrew Or] Abstract usages of converting spark opts to java opts
79f63a3 [Andrew Or] Move sparkProps into javaOpts
78752f8 [Andrew Or] Fix tests
5a9c6c7 [Andrew Or] Fix line too long
c141a00 [Andrew Or] Don't display "unknown app" on driver log pages
d7e2728 [Andrew Or] Avoid deprecation warning in standalone Client
6ceb14f [Andrew Or] Allow relevant configs to propagate to standalone Driver
7f854bc [Andrew Or] Fix test
855256e [Andrew Or] Fix standalone-cluster mode
fd9da51 [Andrew Or] Formatting changes (minor)
As of Spark 1.0, RangePartitioner goes through data twice: once to compute the count and once to do sampling. As a result, to do sortByKey, Spark goes through data 3 times (once to count, once to sample, and once to sort).
`RangePartitioner` should go through data only once, collecting samples from input partitions as well as counting. If the data is balanced, this should give us a good sketch. If we see big partitions, we re-sample from them in order to collect enough items.
The downside is that we need to collect more from each partition in the first pass. An alternative solution is caching the intermediate result and decide whether to fetch the data after.
Author: Xiangrui Meng <meng@databricks.com>
Author: Reynold Xin <rxin@apache.org>
Closes#1562 from mengxr/range-partitioner and squashes the following commits:
6cc2551 [Xiangrui Meng] change foreach to for
eb39b08 [Xiangrui Meng] Merge branch 'master' into range-partitioner
eb95dd8 [Xiangrui Meng] separate sketching and determining bounds impl
c436d30 [Xiangrui Meng] fix binary metrics unit tests
db58a55 [Xiangrui Meng] add unit tests
a6e35d6 [Xiangrui Meng] minor update
60be09e [Xiangrui Meng] remove importance sampler
9ee9992 [Xiangrui Meng] update range partitioner to run only one job on roughly balanced data
cc12f47 [Xiangrui Meng] Merge remote-tracking branch 'apache/master' into range-part
06ac2ec [Xiangrui Meng] Merge remote-tracking branch 'apache/master' into range-part
17bcbf3 [Reynold Xin] Added seed.
badf20d [Reynold Xin] Renamed the method.
6940010 [Reynold Xin] Reservoir sampling implementation.
Implemented stratified sampling that guarantees exact sample size using ScaRSR with two passes over the RDD for sampling without replacement and three passes for sampling with replacement.
Author: Doris Xin <doris.s.xin@gmail.com>
Author: Xiangrui Meng <meng@databricks.com>
Closes#1025 from dorx/stratified and squashes the following commits:
245439e [Doris Xin] moved minSamplingRate to getUpperBound
eaf5771 [Doris Xin] bug fixes.
17a381b [Doris Xin] fixed a merge issue and a failed unit
ea7d27f [Doris Xin] merge master
b223529 [Xiangrui Meng] use approx bounds for poisson fix poisson mean for waitlisting add unit tests for Java
b3013a4 [Xiangrui Meng] move math3 back to test scope
eecee5f [Doris Xin] Merge branch 'master' into stratified
f4c21f3 [Doris Xin] Reviewer comments
a10e68d [Doris Xin] style fix
a2bf756 [Doris Xin] Merge branch 'master' into stratified
680b677 [Doris Xin] use mapPartitionWithIndex instead
9884a9f [Doris Xin] style fix
bbfb8c9 [Doris Xin] Merge branch 'master' into stratified
ee9d260 [Doris Xin] addressed reviewer comments
6b5b10b [Doris Xin] Merge branch 'master' into stratified
254e03c [Doris Xin] minor fixes and Java API.
4ad516b [Doris Xin] remove unused imports from PairRDDFunctions
bd9dc6e [Doris Xin] unit bug and style violation fixed
1fe1cff [Doris Xin] Changed fractionByKey to a map to enable arg check
944a10c [Doris Xin] [SPARK-2145] Add lower bound on sampling rate
0214a76 [Doris Xin] cleanUp
90d94c0 [Doris Xin] merge master
9e74ab5 [Doris Xin] Separated out most of the logic in sampleByKey
7327611 [Doris Xin] merge master
50581fc [Doris Xin] added a TODO for logging in python
46f6c8c [Doris Xin] fixed the NPE caused by closures being cleaned before being passed into the aggregate function
7e1a481 [Doris Xin] changed the permission on SamplingUtil
1d413ce [Doris Xin] fixed checkstyle issues
9ee94ee [Doris Xin] [SPARK-2082] stratified sampling in PairRDDFunctions that guarantees exact sample size
e3fd6a6 [Doris Xin] Merge branch 'master' into takeSample
7cab53a [Doris Xin] fixed import bug in rdd.py
ffea61a [Doris Xin] SPARK-1939: Refactor takeSample method in RDD
1441977 [Doris Xin] SPARK-1939 Refactor takeSample method in RDD to use ScaSRS
**Problem.** When caching, we currently unroll the entire RDD partition before making sure we have enough free memory. This is a common cause for OOMs especially when (1) the BlockManager has little free space left in memory, and (2) the partition is large.
**Solution.** We maintain a global memory pool of `M` bytes shared across all threads, similar to the way we currently manage memory for shuffle aggregation. Then, while we unroll each partition, periodically check if there is enough space to continue. If not, drop enough RDD blocks to ensure we have at least `M` bytes to work with, then try again. If we still don't have enough space to unroll the partition, give up and drop the block to disk directly if applicable.
**New configurations.**
- `spark.storage.bufferFraction` - the value of `M` as a fraction of the storage memory. (default: 0.2)
- `spark.storage.safetyFraction` - a margin of safety in case size estimation is slightly off. This is the equivalent of the existing `spark.shuffle.safetyFraction`. (default 0.9)
For more detail, see the [design document](https://issues.apache.org/jira/secure/attachment/12651793/spark-1777-design-doc.pdf). Tests pending for performance and memory usage patterns.
Author: Andrew Or <andrewor14@gmail.com>
Closes#1165 from andrewor14/them-rdd-memories and squashes the following commits:
e77f451 [Andrew Or] Merge branch 'master' of github.com:apache/spark into them-rdd-memories
c7c8832 [Andrew Or] Simplify logic + update a few comments
269d07b [Andrew Or] Very minor changes to tests
6645a8a [Andrew Or] Merge branch 'master' of github.com:apache/spark into them-rdd-memories
b7e165c [Andrew Or] Add new tests for unrolling blocks
f12916d [Andrew Or] Slightly clean up tests
71672a7 [Andrew Or] Update unrollSafely tests
369ad07 [Andrew Or] Correct ensureFreeSpace and requestMemory behavior
f4d035c [Andrew Or] Allow one thread to unroll multiple blocks
a66fbd2 [Andrew Or] Rename a few things + update comments
68730b3 [Andrew Or] Fix weird scalatest behavior
e40c60d [Andrew Or] Fix MIMA excludes
ff77aa1 [Andrew Or] Fix tests
1a43c06 [Andrew Or] Merge branch 'master' of github.com:apache/spark into them-rdd-memories
b9a6eee [Andrew Or] Simplify locking behavior on unrollMemoryMap
ed6cda4 [Andrew Or] Formatting fix (super minor)
f9ff82e [Andrew Or] putValues -> putIterator + putArray
beb368f [Andrew Or] Merge branch 'master' of github.com:apache/spark into them-rdd-memories
8448c9b [Andrew Or] Fix tests
a49ba4d [Andrew Or] Do not expose unroll memory check period
69bc0a5 [Andrew Or] Always synchronize on putLock before unrollMemoryMap
3f5a083 [Andrew Or] Simplify signature of ensureFreeSpace
dce55c8 [Andrew Or] Merge branch 'master' of github.com:apache/spark into them-rdd-memories
8288228 [Andrew Or] Synchronize put and unroll properly
4f18a3d [Andrew Or] bufferFraction -> unrollFraction
28edfa3 [Andrew Or] Update a few comments / log messages
728323b [Andrew Or] Do not synchronize every 1000 elements
5ab2329 [Andrew Or] Merge branch 'master' of github.com:apache/spark into them-rdd-memories
129c441 [Andrew Or] Fix bug: Use toArray rather than array
9a65245 [Andrew Or] Update a few comments + minor control flow changes
57f8d85 [Andrew Or] Merge branch 'master' of github.com:apache/spark into them-rdd-memories
abeae4f [Andrew Or] Add comment clarifying the MEMORY_AND_DISK case
3dd96aa [Andrew Or] AppendOnlyBuffer -> Vector (+ a few small changes)
f920531 [Andrew Or] Merge branch 'master' of github.com:apache/spark into them-rdd-memories
0871835 [Andrew Or] Add an effective storage level interface to BlockManager
64e7d4c [Andrew Or] Add/modify a few comments (minor)
8af2f35 [Andrew Or] Merge branch 'master' of github.com:apache/spark into them-rdd-memories
4f4834e [Andrew Or] Use original storage level for blocks dropped to disk
ecc8c2d [Andrew Or] Fix binary incompatibility
24185ea [Andrew Or] Avoid dropping a block back to disk if reading from disk
2b7ee66 [Andrew Or] Fix bug in SizeTracking*
9b9a273 [Andrew Or] Fix tests
20eb3e5 [Andrew Or] Merge branch 'master' of github.com:apache/spark into them-rdd-memories
649bdb3 [Andrew Or] Document spark.storage.bufferFraction
a10b0e7 [Andrew Or] Add initial memory request threshold + rename a few things
e9c3cb0 [Andrew Or] cacheMemoryMap -> unrollMemoryMap
198e374 [Andrew Or] Unfold -> unroll
0d50155 [Andrew Or] Merge branch 'master' of github.com:apache/spark into them-rdd-memories
d9d02a8 [Andrew Or] Remove unused param in unfoldSafely
ec728d8 [Andrew Or] Add tests for safe unfolding of blocks
22b2209 [Andrew Or] Merge branch 'master' of github.com:apache/spark into them-rdd-memories
078eb83 [Andrew Or] Add check for hasNext in PrimitiveVector.iterator
0871535 [Andrew Or] Fix tests in BlockManagerSuite
d68f31e [Andrew Or] Safely unfold blocks for all memory puts
5961f50 [Andrew Or] Fix tests
195abd7 [Andrew Or] Refactor: move unfold logic to MemoryStore
1e82d00 [Andrew Or] Merge branch 'master' of github.com:apache/spark into them-rdd-memories
3ce413e [Andrew Or] Merge branch 'master' of github.com:apache/spark into them-rdd-memories
d5dd3b4 [Andrew Or] Free buffer memory in finally
ea02eec [Andrew Or] Fix tests
b8e1d9c [Andrew Or] Merge branch 'master' of github.com:apache/spark into them-rdd-memories
a8704c1 [Andrew Or] Merge branch 'master' of github.com:apache/spark into them-rdd-memories
e1b8b25 [Andrew Or] Merge branch 'master' of github.com:apache/spark into them-rdd-memories
87aa75c [Andrew Or] Fix mima excludes again (typo)
11eb921 [Andrew Or] Clarify comment (minor)
50cae44 [Andrew Or] Remove now duplicate mima exclude
7de5ef9 [Andrew Or] Merge branch 'master' of github.com:apache/spark into them-rdd-memories
df47265 [Andrew Or] Fix binary incompatibility
6d05a81 [Andrew Or] Merge branch 'master' of github.com:apache/spark into them-rdd-memories
f94f5af [Andrew Or] Update a few comments (minor)
776aec9 [Andrew Or] Prevent OOM if a single RDD partition is too large
bbd3eea [Andrew Or] Fix CacheManagerSuite to use Array
97ea499 [Andrew Or] Change BlockManager interface to use Arrays
c12f093 [Andrew Or] Add SizeTrackingAppendOnlyBuffer and tests
This will decrease object allocation from the "update" closure used in map.changeValue.
Author: Matei Zaharia <matei@databricks.com>
Closes#1607 from mateiz/spark-2684 and squashes the following commits:
b7d89e6 [Matei Zaharia] Add insertAll for Iterables too, and fix some code style
561fc97 [Matei Zaharia] Update ExternalAppendOnlyMap to take an iterator as input
Added emptyRDD method to Java API with tests.
Author: bpaulin <bob@bobpaulin.com>
Closes#1597 from bobpaulin/SPARK-2279 and squashes the following commits:
5ad57c2 [bpaulin] [SPARK-2279] Added emptyRDD method to Java API
This is part of the scheduler cleanup/refactoring effort to make the scheduler code easier to maintain.
@kayousterhout @markhamstra please take a look ...
Author: Reynold Xin <rxin@apache.org>
Closes#1561 from rxin/dagSchedulerHashMaps and squashes the following commits:
1c44e15 [Reynold Xin] Clear pending tasks in submitMissingTasks.
620a0d1 [Reynold Xin] Use filterKeys.
5b54404 [Reynold Xin] Code review feedback.
c1e9a1c [Reynold Xin] Removed some HashMaps from DAGScheduler by storing information in Stage.
Due to problems with when we update runningStages (in DAGScheduler.scala)
and how we decide to send a SparkListenerStageCompleted message to
SparkListeners, sometimes stages can be shown as "running" in the UI forever
(even after they have failed). This issue can manifest when stages are
resubmitted with 0 tasks, or when the DAGScheduler catches non-serializable
tasks. The problem also resulted in a (small) memory leak in the DAGScheduler,
where stages can stay in runningStages forever. This commit fixes
that problem and adds a unit test.
Thanks tsudukim for helping to look into this issue!
cc markhamstra rxin
Author: Kay Ousterhout <kayousterhout@gmail.com>
Closes#1566 from kayousterhout/dag_fix and squashes the following commits:
217d74b [Kay Ousterhout] [SPARK-1726] [SPARK-2567] Eliminate zombie stages in UI.
Renaming `short` to `shortForm` and `long` to `longForm`.
JIRA: https://issues.apache.org/jira/browse/SPARK-2683
Author: Yin Huai <huai@cse.ohio-state.edu>
Closes#1585 from yhuai/SPARK-2683 and squashes the following commits:
5ddb843 [Yin Huai] "short" and "long" are Java keyworks. In order to generate javadoc, renaming "short" to "shortForm" and "long" to "longForm".
JIRA: https://issues.apache.org/jira/browse/SPARK-2657
Our current code uses ArrayBuffers for each group of values in groupBy, as well as for the key's elements in CoGroupedRDD. ArrayBuffers have a lot of overhead if there are few values in them, which is likely to happen in cases such as join. In particular, they have a pointer to an Object[] of size 16 by default, which is 24 bytes for the array header + 128 for the pointers in there, plus at least 32 for the ArrayBuffer data structure. This patch replaces the per-group buffers with a CompactBuffer class that can store up to 2 elements more efficiently (in fields of itself) and acts like an ArrayBuffer beyond that. For a key's elements in CoGroupedRDD, we use an Array of CompactBuffers instead of an ArrayBuffer of ArrayBuffers.
There are some changes throughout the code to deal with CoGroupedRDD returning Array instead. We can also decide not to do that but CoGroupedRDD is a `DeveloperAPI` so I think it's okay to change it here.
Author: Matei Zaharia <matei@databricks.com>
Closes#1555 from mateiz/compact-groupby and squashes the following commits:
845a356 [Matei Zaharia] Lower initial size of CompactBuffer's vector to 8
07621a7 [Matei Zaharia] Review comments
0c1cd12 [Matei Zaharia] Don't use varargs in CompactBuffer.apply
bdc8a39 [Matei Zaharia] Small tweak to +=, and typos
f61f040 [Matei Zaharia] Fix line lengths
59da88b0 [Matei Zaharia] Fix line lengths
197cde8 [Matei Zaharia] Make CompactBuffer extend Seq to make its toSeq more efficient
775110f [Matei Zaharia] Change CoGroupedRDD to give (K, Array[Iterable[_]]) to avoid wrappers
9b4c6e8 [Matei Zaharia] Use CompactBuffer in CoGroupedRDD
ed577ab [Matei Zaharia] Use CompactBuffer in groupByKey
10f0de1 [Matei Zaharia] A CompactBuffer that's more memory-efficient than ArrayBuffer for small buffers
...spark-submit
The PR allows invocations like
spark-submit --class org.MyClass --spark.shuffle.spill false myjar.jar
Author: Sandy Ryza <sandy@cloudera.com>
Closes#1253 from sryza/sandy-spark-2310 and squashes the following commits:
1dc9855 [Sandy Ryza] More doc and cleanup
00edfb9 [Sandy Ryza] Review comments
91b244a [Sandy Ryza] Change format to --conf PROP=VALUE
8fabe77 [Sandy Ryza] SPARK-2310. Support arbitrary Spark properties on the command line with spark-submit
Hi mridulm, I just think of this issue of [#1212](https://github.com/apache/spark/pull/1212): I added FakeRackUtil to hold the host -> rack mapping. It should be cleaned up after use so that it won't mess up with test cases others may add later.
Really sorry about this.
Author: Rui Li <rui.li@intel.com>
Closes#1454 from lirui-intel/SPARK-2277-fix-UT and squashes the following commits:
f8ea25c [Rui Li] SPARK-2277: clear host->rack info properly
The name `preservesPartitioning` is ambiguous: 1) preserves the indices of partitions, 2) preserves the partitioner. The latter is correct and `preservesPartitioning` should really be called `preservesPartitioner` to avoid confusion. Unfortunately, this is already part of the API and we cannot change. We should be clear in the doc and fix wrong usages.
This PR
1. adds notes in `maPartitions*`,
2. makes `RDD.sample` preserve partitioner,
3. changes `preservesPartitioning` to false in `RDD.zip` because the keys of the first RDD are no longer the keys of the zipped RDD,
4. fixes some wrong usages in MLlib.
Author: Xiangrui Meng <meng@databricks.com>
Closes#1526 from mengxr/preserve-partitioner and squashes the following commits:
b361e65 [Xiangrui Meng] update doc based on pwendell's comments
3b1ba19 [Xiangrui Meng] update doc
357575c [Xiangrui Meng] fix unit test
20b4816 [Xiangrui Meng] Merge branch 'master' into preserve-partitioner
d1caa65 [Xiangrui Meng] add doc to explain preservesPartitioning fix wrong usage of preservesPartitioning make sample preserse partitioning
### Why and what?
Currently, the AppendOnlyMap performs an "in-place" sort by converting its array of [key, value, key, value] pairs into a an array of [(key, value), (key, value)] pairs. However, this causes us to allocate many Tuple2 objects, which come at a nontrivial overhead.
This patch adds a Sorter API, intended for in memory sorts, which simply ports the Android Timsort implementation (available under Apache v2) and abstracts the interface in a way which introduces no more than 1 virtual function invocation of overhead at each abstraction point.
Please compare our port of the Android Timsort sort with the original implementation: http://www.diffchecker.com/wiwrykcl
### Memory implications
An AppendOnlyMap contains N kv pairs, which results in roughly 2N elements within its underlying array. Each of these elements is 4 bytes wide in a [compressed OOPS](https://wikis.oracle.com/display/HotSpotInternals/CompressedOops) system, which is the default.
Today's approach immediately allocates N Tuple2 objects, which take up 24N bytes in total (exposed via YourKit), and undergoes a Java sort. The Java 6 version immediately copies the entire array (4N bytes here), while the Java 7 version has a worst-case allocation of half the array (2N bytes).
This results in a worst-case sorting overhead of 24N + 2N = 26N bytes (for Java 7).
The Sorter does not require allocating any tuples, but since it uses Timsort, it may copy up to half the entire array in the worst case.
This results in a worst-case sorting overhead of 4N bytes.
Thus, we have reduced the worst-case overhead of the sort by roughly 22 bytes times the number of elements.
### Performance implications
As the destructiveSortedIterator is used for spilling in an ExternalAppendOnlyMap, the purpose of this patch is to provide stability by reducing memory usage rather than improve performance. However, because it implements Timsort, it also brings a substantial performance boost over our prior implementation.
Here are the results of a microbenchmark that sorted 25 million, randomly distributed (Float, Int) pairs. The Java Arrays.sort() tests were run **only on the keys**, and thus moved less data. Our current implementation is called "Tuple-sort using Arrays.sort()" while the new implementation is "KV-array using Sorter".
<table>
<tr><th>Test</th><th>First run (JDK6)</th><th>Average of 10 (JDK6)</th><th>First run (JDK7)</th><th>Average of 10 (JDK7)</th></tr>
<tr><td>primitive Arrays.sort()</td><td>3216 ms</td><td>1190 ms</td><td>2724 ms</td><td>131 ms (!!)</td></tr>
<tr><td>Arrays.sort()</td><td>18564 ms</td><td>2006 ms</td><td>13201 ms</td><td>878 ms</td></tr>
<tr><td>Tuple-sort using Arrays.sort()</td><td>31813 ms</td><td>3550 ms</td><td>20990 ms</td><td>1919 ms</td></tr>
<tr><td><b>KV-array using Sorter</b></td><td></td><td></td><td><b>15020 ms</b></td><td><b>834 ms</b></td></tr>
</table>
The results show that this Sorter performs exactly as expected (after the first run) -- it is as fast as the Java 7 Arrays.sort() (which shares the same algorithm), but is significantly faster than the Tuple-sort on Java 6 or 7.
In short, this patch should significantly improve performance for users running either Java 6 or 7.
Author: Aaron Davidson <aaron@databricks.com>
Closes#1502 from aarondav/sort and squashes the following commits:
652d936 [Aaron Davidson] Update license, move Sorter to java src
a7b5b1c [Aaron Davidson] fix licenses
5c0efaf [Aaron Davidson] Update tmpLength
ec395c8 [Aaron Davidson] Ignore benchmark (again) and fix docs
034bf10 [Aaron Davidson] Change to Apache v2 Timsort
b97296c [Aaron Davidson] Don't try to run benchmark on Jenkins + private[spark]
6307338 [Aaron Davidson] SPARK-2047: Introduce an in-mem Sorter, and use it to reduce mem usage
Author: Sandy Ryza <sandy@cloudera.com>
Closes#1474 from sryza/sandy-spark-2564 and squashes the following commits:
35b8388 [Sandy Ryza] Fix compile error on upmerge
7b985fb [Sandy Ryza] Fix test compile error
43f79e6 [Sandy Ryza] SPARK-2564. ShuffleReadMetrics.totalBlocksRead is redundant
We should fix this in branch-1.0 as well.
Author: Reynold Xin <rxin@apache.org>
Closes#1500 from rxin/rangePartitioner and squashes the following commits:
c0a94f5 [Reynold Xin] [SPARK-2598] RangePartitioner's binary search does not use the given Ordering.
Currently (as of Spark 1.0.1), Spark sends RDD object (which contains closures) using Akka along with the task itself to the executors. This is inefficient because all tasks in the same stage use the same RDD object, but we have to send RDD object multiple times to the executors. This is especially bad when a closure references some variable that is very large. The current design led to users having to explicitly broadcast large variables.
The patch uses broadcast to send RDD objects and the closures to executors, and use Akka to only send a reference to the broadcast RDD/closure along with the partition specific information for the task. For those of you who know more about the internals, Spark already relies on broadcast to send the Hadoop JobConf every time it uses the Hadoop input, because the JobConf is large.
The user-facing impact of the change include:
1. Users won't need to decide what to broadcast anymore, unless they would want to use a large object multiple times in different operations
2. Task size will get smaller, resulting in faster scheduling and higher task dispatch throughput.
In addition, the change will simplify some internals of Spark, eliminating the need to maintain task caches and the complex logic to broadcast JobConf (which also led to a deadlock recently).
A simple way to test this:
```scala
val a = new Array[Byte](1000*1000); scala.util.Random.nextBytes(a);
sc.parallelize(1 to 1000, 1000).map { x => a; x }.groupBy { x => a; x }.count
```
Numbers on 3 r3.8xlarge instances on EC2
```
master branch: 5.648436068 s, 4.715361895 s, 5.360161877 s
with this change: 3.416348793 s, 1.477846558 s, 1.553432156 s
```
Author: Reynold Xin <rxin@apache.org>
Closes#1452 from rxin/broadcast-task and squashes the following commits:
762e0be [Reynold Xin] Warn large broadcasts.
ade6eac [Reynold Xin] Log broadcast size.
c3b6f11 [Reynold Xin] Added a unit test for clean up.
754085f [Reynold Xin] Explain why broadcasting serialized copy of the task.
04b17f0 [Reynold Xin] [SPARK-2521] Broadcast RDD object once per TaskSet (instead of sending it for every task).
Currently, shuffle read metrics are incorrectly reported when stages have multiple shuffle dependencies (they are set to be the metrics from just one of the shuffle dependencies, rather than the accumulated metrics from all of the shuffle dependencies). This fixes that problem, and should probably be back-ported to the 0.9 branch.
Thanks ryanra for discovering this problem!
cc rxin andrewor14
Author: Kay Ousterhout <kayousterhout@gmail.com>
Closes#1476 from kayousterhout/join_bug and squashes the following commits:
0203a16 [Kay Ousterhout] Fix broken unit tests.
f463c2e [Kay Ousterhout] [SPARK-2571] Correctly report shuffle read metrics.
This is going to be used in https://issues.apache.org/jira/browse/SPARK-2568
Author: Reynold Xin <rxin@apache.org>
Closes#1478 from rxin/reservoirSample and squashes the following commits:
17bcbf3 [Reynold Xin] Added seed.
badf20d [Reynold Xin] Renamed the method.
6940010 [Reynold Xin] Reservoir sampling implementation.
This should reduce memory usage for the web ui as well as slightly increase its speed in draining the UI event queue.
@andrewor14
Author: Reynold Xin <rxin@apache.org>
Closes#1262 from rxin/ui-consolidate-hashtables and squashes the following commits:
1ac3f97 [Reynold Xin] Oops. Properly handle description.
f5736ad [Reynold Xin] Code review comments.
b8828dc [Reynold Xin] Merge branch 'master' into ui-consolidate-hashtables
7a7b6c4 [Reynold Xin] Revert css change.
f959bb8 [Reynold Xin] [SPARK-2299] Consolidate various stageIdTo* hash maps in JobProgressListener to speed it up.
63256f5 [Reynold Xin] [SPARK-2320] Reduce <pre> block font size.
If the first pass of CoalescedRDD does not find the target number of locations AND the second pass finds new locations, an exception is thrown, as "groupHash.get(nxt_replica).get" is not valid.
The fix is just to add an ArrayBuffer to groupHash for that replica if it didn't already exist.
Author: Aaron Davidson <aaron@databricks.com>
Closes#1337 from aarondav/2412 and squashes the following commits:
f587b5d [Aaron Davidson] getOrElseUpdate
3ad8a3c [Aaron Davidson] [SPARK-2412] CoalescedRDD throws exception with certain pref locs
We use TID to indicate task logging. However, TID itself does not capture stage or retries, making it harder to correlate with the application itself. This pull request changes all logging messages for tasks to include both the TID and the stage id, stage attempt, task id, and task attempt. I've consulted various people but unfortunately this is a really hard task.
Driver log looks like:
```
14/06/28 18:53:29 INFO DAGScheduler: Submitting 10 missing tasks from Stage 0 (MappedRDD[1] at map at <console>:13)
14/06/28 18:53:29 INFO TaskSchedulerImpl: Adding task set 0.0 with 10 tasks
14/06/28 18:53:29 INFO TaskSetManager: Re-computing pending task lists.
14/07/15 19:44:40 INFO TaskSetManager: Starting task 0.0 in stage 1.0 (TID 0, localhost, PROCESS_LOCAL, 1855 bytes)
14/07/15 19:44:40 INFO TaskSetManager: Starting task 1.0 in stage 1.0 (TID 1, localhost, PROCESS_LOCAL, 1855 bytes)
14/07/15 19:44:40 INFO TaskSetManager: Starting task 2.0 in stage 1.0 (TID 2, localhost, PROCESS_LOCAL, 1855 bytes)
14/07/15 19:44:40 INFO TaskSetManager: Starting task 3.0 in stage 1.0 (TID 3, localhost, PROCESS_LOCAL, 1855 bytes)
14/07/15 19:44:40 INFO TaskSetManager: Starting task 4.0 in stage 1.0 (TID 4, localhost, PROCESS_LOCAL, 1855 bytes)
14/07/15 19:44:40 INFO TaskSetManager: Starting task 5.0 in stage 1.0 (TID 5, localhost, PROCESS_LOCAL, 1855 bytes)
14/07/15 19:44:40 INFO TaskSetManager: Starting task 6.0 in stage 1.0 (TID 6, localhost, PROCESS_LOCAL, 1855 bytes)
...
14/07/15 19:44:40 INFO TaskSetManager: Finished task 1.0 in stage 1.0 (TID 1) in 64 ms on localhost (4/10)
14/07/15 19:44:40 INFO TaskSetManager: Finished task 4.0 in stage 1.0 (TID 4) in 63 ms on localhost (5/10)
14/07/15 19:44:40 INFO TaskSetManager: Finished task 2.0 in stage 1.0 (TID 2) in 63 ms on localhost (6/10)
14/07/15 19:44:40 INFO TaskSetManager: Finished task 7.0 in stage 1.0 (TID 7) in 62 ms on localhost (7/10)
14/07/15 19:44:40 INFO TaskSetManager: Finished task 6.0 in stage 1.0 (TID 6) in 63 ms on localhost (8/10)
14/07/15 19:44:40 INFO TaskSetManager: Finished task 9.0 in stage 1.0 (TID 9) in 8 ms on localhost (9/10)
14/07/15 19:44:40 INFO TaskSetManager: Finished task 8.0 in stage 1.0 (TID 8) in 9 ms on localhost (10/10)
```
Executor log looks like
```
14/07/15 19:44:40 INFO Executor: Running task 0.0 in stage 1.0 (TID 0)
14/07/15 19:44:40 INFO Executor: Running task 3.0 in stage 1.0 (TID 3)
14/07/15 19:44:40 INFO Executor: Running task 1.0 in stage 1.0 (TID 1)
14/07/15 19:44:40 INFO Executor: Running task 4.0 in stage 1.0 (TID 4)
14/07/15 19:44:40 INFO Executor: Running task 2.0 in stage 1.0 (TID 2)
14/07/15 19:44:40 INFO Executor: Running task 5.0 in stage 1.0 (TID 5)
14/07/15 19:44:40 INFO Executor: Running task 6.0 in stage 1.0 (TID 6)
14/07/15 19:44:40 INFO Executor: Running task 7.0 in stage 1.0 (TID 7)
14/07/15 19:44:40 INFO Executor: Finished task 3.0 in stage 1.0 (TID 3). 847 bytes result sent to driver
14/07/15 19:44:40 INFO Executor: Finished task 2.0 in stage 1.0 (TID 2). 847 bytes result sent to driver
14/07/15 19:44:40 INFO Executor: Finished task 0.0 in stage 1.0 (TID 0). 847 bytes result sent to driver
14/07/15 19:44:40 INFO Executor: Finished task 1.0 in stage 1.0 (TID 1). 847 bytes result sent to driver
14/07/15 19:44:40 INFO Executor: Finished task 5.0 in stage 1.0 (TID 5). 847 bytes result sent to driver
14/07/15 19:44:40 INFO Executor: Finished task 4.0 in stage 1.0 (TID 4). 847 bytes result sent to driver
14/07/15 19:44:40 INFO Executor: Finished task 6.0 in stage 1.0 (TID 6). 847 bytes result sent to driver
14/07/15 19:44:40 INFO Executor: Finished task 7.0 in stage 1.0 (TID 7). 847 bytes result sent to driver
```
Author: Reynold Xin <rxin@apache.org>
Closes#1259 from rxin/betterTaskLogging and squashes the following commits:
c28ada1 [Reynold Xin] Fix unit test failure.
987d043 [Reynold Xin] Updated log messages.
c6cfd46 [Reynold Xin] Merge branch 'master' into betterTaskLogging
b7b1bcc [Reynold Xin] Fixed a typo.
f9aba3c [Reynold Xin] Made it compile.
f8a5c06 [Reynold Xin] Merge branch 'master' into betterTaskLogging
07264e6 [Reynold Xin] Defensive check against unknown TaskEndReason.
76bbd18 [Reynold Xin] FailureSuite not serializable reporting.
4659b20 [Reynold Xin] Remove unused variable.
53888e3 [Reynold Xin] [SPARK-2317] Improve task logging.
Author: Reynold Xin <rxin@apache.org>
Closes#1433 from rxin/compile-warning and squashes the following commits:
8d0b890 [Reynold Xin] Remove some compiler warnings.
Hi mateiz, I've created [SPARK-2277](https://issues.apache.org/jira/browse/SPARK-2277) to make TaskScheduler track hosts on each rack. Please help to review, thanks.
Author: Rui Li <rui.li@intel.com>
Closes#1212 from lirui-intel/trackHostOnRack and squashes the following commits:
2b4bd0f [Rui Li] SPARK-2277: refine UT
fbde838 [Rui Li] SPARK-2277: add UT
7bbe658 [Rui Li] SPARK-2277: rename the method
5e4ef62 [Rui Li] SPARK-2277: remove unnecessary import
79ac750 [Rui Li] SPARK-2277: make TaskScheduler track hosts on rack
This reduces shuffle compression memory usage by 3x.
Author: Reynold Xin <rxin@apache.org>
Closes#1415 from rxin/snappy and squashes the following commits:
06c1a01 [Reynold Xin] SPARK-2469: Use Snappy (instead of LZF) for default shuffle compression codec.
Based on Greg Bowyer's patch from JIRA https://issues.apache.org/jira/browse/SPARK-2399
Author: Reynold Xin <rxin@apache.org>
Closes#1416 from rxin/lz4 and squashes the following commits:
6c8fefe [Reynold Xin] Fixed typo.
8a14d38 [Reynold Xin] [SPARK-2399] Add support for LZ4 compression.
Just move some test suite to corresponding package
Author: Daoyuan <daoyuan.wang@intel.com>
Closes#1401 from adrian-wang/movetestfiles and squashes the following commits:
d1a6803 [Daoyuan] move some test file to match src code
This makes it possible to read classes from the object file which were specified in the user-provided jars. (By default ObjectInputStream uses latestUserDefinedLoader, which may or may not be the right one.)
I created this because I ran into the following problem. I have x:RDD[X] with X being defined in the jar that I provide to SparkContext. I save it with x.saveAsObjectFile("x"). I try to load it with sc.objectFile\[X\]("x"). It fails with ClassNotFoundException.
After a good while of debugging I figured out that Utils.deserialize() most likely uses the ClassLoader of Utils. This is the bootstrap ClassLoader, so it is not aware of the dynamically added jars. This patch fixes the issue.
A more robust fix would be to always default to Thread.currentThread.getContextClassLoader. This would prevent this problem from biting anyone in the future. It would be a bit harder to test though. On the topic of testing, if you'd like to see tests for this, I will need some hand-holding. Thanks!
Author: Daniel Darabos <darabos.daniel@gmail.com>
Closes#181 from darabos/master and squashes the following commits:
45a011a [Daniel Darabos] Add test for SPARK-1877. (Fixed in 52eb54d.)
e13e090 [Daniel Darabos] Merge branch 'master' of https://github.com/apache/spark
61fe0d0 [Daniel Darabos] Fix style (line too long).
1b5df2c [Daniel Darabos] Use the Executor's ClassLoader in sc.objectFile(). This makes it possible to read classes from the object file which were specified in the user-provided jars. (By default ObjectInputStream uses latestUserDefinedLoader, which may or may not be the right one.)
Author: witgo <witgo@qq.com>
Closes#1153 from witgo/expectResult and squashes the following commits:
97541d8 [witgo] merge master
ead26e7 [witgo] Resolve sbt warnings during build
**Problem.** The existing code in `ExecutorPage.scala` requires a linear scan through all the blocks to filter out the uncached ones. Every refresh could be expensive if there are many blocks and many executors.
**Solution.** The proper semantics should be the following: `StorageStatusListener` should contain only block statuses that are cached. This means as soon as a block is unpersisted by any mean, its status should be removed. This is reflected in the changes made in `StorageStatusListener.scala`.
Further, the `StorageTab` must stop relying on the `StorageStatusListener` changing a dropped block's status to `StorageLevel.NONE` (which no longer happens). This is reflected in the changes made in `StorageTab.scala` and `StorageUtils.scala`.
----------
If you have been following this chain of PRs like pwendell, you will quickly notice that this reverts the changes in #1249, which reverts the changes in #1080. In other words, we are adding back the changes from #1080, and fixing SPARK-2307 on top of those changes. Please ask questions if you are confused.
Author: Andrew Or <andrewor14@gmail.com>
Closes#1255 from andrewor14/storage-ui-fix-reprise and squashes the following commits:
45416fa [Andrew Or] Merge branch 'master' of github.com:apache/spark into storage-ui-fix-reprise
a82ea25 [Andrew Or] Add tests for StorageStatusListener
8773b01 [Andrew Or] Update comment / minor changes
3afde3f [Andrew Or] Correctly report the number of blocks on SparkUI
It did not handle null keys very gracefully before.
Author: Andrew Or <andrewor14@gmail.com>
Closes#1288 from andrewor14/fix-external and squashes the following commits:
312b8d8 [Andrew Or] Abstract key hash code
ed5adf9 [Andrew Or] Fix NPE for ExternalAppendOnlyMap
This functionality was added in an earlier commit but shortly
after was removed due to a bad git merge (totally my fault).
Author: Kay Ousterhout <kayousterhout@gmail.com>
Closes#1149 from kayousterhout/warning_bug and squashes the following commits:
3f1bb00 [Kay Ousterhout] Fixed Json tests
462a664 [Kay Ousterhout] Removed task set name from warning message
e89b2f6 [Kay Ousterhout] Fixed Json tests.
7af424c [Kay Ousterhout] Emit warning when task size exceeds a threshold.
This should go into 1.0.1.
Author: Reynold Xin <rxin@apache.org>
Closes#1264 from rxin/SPARK-2322 and squashes the following commits:
c77c07f [Reynold Xin] Added comment to SparkDriverExecutionException and a test case for accumulator.
5d8d920 [Reynold Xin] [SPARK-2322] Exception in resultHandler could crash DAGScheduler and shutdown SparkContext.
These commits cause `ClosureCleaner.clean` to attempt to serialize the cleaned closure with the default closure serializer and throw a `SparkException` if doing so fails. This behavior is enabled by default but can be disabled at individual callsites of `SparkContext.clean`.
Commit 98e01ae8 fixes some no-op assertions in `GraphSuite` that this work exposed; I'm happy to put that in a separate PR if that would be more appropriate.
Author: William Benton <willb@redhat.com>
Closes#143 from willb/spark-897 and squashes the following commits:
bceab8a [William Benton] Commented DStream corner cases for serializability checking.
64d04d2 [William Benton] FailureSuite now checks both messages and causes.
3b3f74a [William Benton] Stylistic and doc cleanups.
b215dea [William Benton] Fixed spurious failures in ImplicitOrderingSuite
be1ecd6 [William Benton] Don't check serializability of DStream transforms.
abe816b [William Benton] Make proactive serializability checking optional.
5bfff24 [William Benton] Adds proactive closure-serializablilty checking
ed2ccf0 [William Benton] Test cases for SPARK-897.
Details can be see in [SPARK-2104](https://issues.apache.org/jira/browse/SPARK-2104). This work is based on Reynold's work, add some unit tests to validate the issue.
@rxin , would you please take a look at this PR, thanks a lot.
Author: jerryshao <saisai.shao@intel.com>
Closes#1245 from jerryshao/SPARK-2104 and squashes the following commits:
c8ee362 [jerryshao] Make field partitions transient
2b41917 [jerryshao] Minor changes
47d763c [jerryshao] Fix task serializing issue when sort with Java non serializable class
This commit adds a new metric in TaskMetrics to record
the input data size and displays this information in the UI.
An earlier version of this commit also added the read time,
which can be useful for diagnosing straggler problems,
but unfortunately that change introduced a significant performance
regression for jobs that don't do much computation. In order to
track read time, we'll need to do sampling.
The screenshots below show the UI with the new "Input" field,
which I added to the stage summary page, the executor summary page,
and the per-stage page.
Author: Kay Ousterhout <kayousterhout@gmail.com>
Closes#962 from kayousterhout/read_metrics and squashes the following commits:
f13b67d [Kay Ousterhout] Correctly format input bytes on executor page
8b70cde [Kay Ousterhout] Added comment about potential inaccuracy of bytesRead
d1016e8 [Kay Ousterhout] Udated SparkListenerSuite test
8461492 [Kay Ousterhout] Miniscule style fix
ae04d99 [Kay Ousterhout] Remove input metrics for parallel collections
719f19d [Kay Ousterhout] Style fixes
bb6ec62 [Kay Ousterhout] Small fixes
869ac7b [Kay Ousterhout] Updated Json tests
44a0301 [Kay Ousterhout] Fixed accidentally added line
4bd0568 [Kay Ousterhout] Added input source, renamed Hdfs to Hadoop.
f27e535 [Kay Ousterhout] Updates based on review comments and to fix rebase
bf41029 [Kay Ousterhout] Updated Json tests to pass
0fc33e0 [Kay Ousterhout] Added explicit backward compatibility test
4e52925 [Kay Ousterhout] Added Json output and associated tests.
365400b [Kay Ousterhout] [SPARK-1683] Track task read metrics.
The following code is very likely to throw an exception:
~~~
val rdd = sc.parallelize(0 until 111, 10).sample(false, 0.1)
rdd.zip(rdd).count()
~~~
because the same random number generator is used in compute partitions.
Author: Xiangrui Meng <meng@databricks.com>
Closes#1229 from mengxr/fix-sample and squashes the following commits:
f1ee3d7 [Xiangrui Meng] fix concurrency issues in random sampler
New UI:
Author: Reynold Xin <rxin@apache.org>
Closes#1236 from rxin/ui-task-attempt and squashes the following commits:
3b645dd [Reynold Xin] Expose attemptId in Stage.
c0474b1 [Reynold Xin] Beefed up unit test.
c404bdd [Reynold Xin] Fix ReplayListenerSuite.
f56be4b [Reynold Xin] Fixed JsonProtocolSuite.
e29e0f7 [Reynold Xin] Minor update.
5e4354a [Reynold Xin] [SPARK-2297][UI] Make task attempt and speculation more explicit in UI.
FetchFailedException used to have a Throwable field, but in reality we never propagate any of the throwable/exceptions back to the driver because Executor explicitly looks for FetchFailedException and then sends FetchFailed as the TaskEndReason.
This pull request removes the throwable and adds a MetadataFetchFailedException that extends FetchFailedException (so now MapOutputTracker throws MetadataFetchFailedException instead).
Author: Reynold Xin <rxin@apache.org>
Closes#1227 from rxin/metadataFetchException and squashes the following commits:
5cb1e0a [Reynold Xin] MetadataFetchFailedException extends FetchFailedException.
8861ee2 [Reynold Xin] Throw MetadataFetchFailedException in MapOutputTracker.
Previously only tasks failed with ExceptionFailure reason was marked as failure.
Author: Reynold Xin <rxin@apache.org>
Closes#1224 from rxin/SPARK-2284 and squashes the following commits:
be79dbd [Reynold Xin] [SPARK-2284][UI] Mark all failed tasks as failures.
This is a fixed up version of #686 (cc @markhamstra @pwendell). The last commit (the only one I authored) reflects the changes I made from Mark's original patch.
Author: Mark Hamstra <markhamstra@gmail.com>
Author: Kay Ousterhout <kayousterhout@gmail.com>
Closes#1219 from kayousterhout/mark-SPARK-1749 and squashes the following commits:
42dfa7e [Kay Ousterhout] Got rid of terrible double-negative name
80b3205 [Kay Ousterhout] Don't notify listeners of job failure if it wasn't successfully cancelled.
d156d33 [Mark Hamstra] Do nothing in no-kill submitTasks
9312baa [Mark Hamstra] code review update
cc353c8 [Mark Hamstra] scalastyle
e61f7f8 [Mark Hamstra] Catch UnsupportedOperationException when DAGScheduler tries to cancel a job on a SchedulerBackend that does not implement killTask
and thus groupBy/cogroup are broken in Java APIs when Kryo is used).
@pwendell this should be merged into 1.0.1.
Thanks @sorenmacbeth for reporting this & helping out with the fix.
Author: Reynold Xin <rxin@apache.org>
Closes#1206 from rxin/kryo-iterable-2270 and squashes the following commits:
09da0aa [Reynold Xin] Updated the comment.
009bf64 [Reynold Xin] [SPARK-2270] Kryo cannot serialize results returned by asJavaIterable (and thus groupBy/cogroup are broken in Java APIs when Kryo is used).
Author: witgo <witgo@qq.com>
Closes#1194 from witgo/SPARK-2248 and squashes the following commits:
6ac950b [witgo] spark.default.parallelism does not apply in local mode
This is an alternative solution to #1124 . Before launching the executor backend, we first fetch driver's spark properties and use it to overwrite executor's spark properties. This should be better than #1124.
@pwendell Are there spark properties that might be different on the driver and on the executors?
Author: Xiangrui Meng <meng@databricks.com>
Closes#1132 from mengxr/akka-bootstrap and squashes the following commits:
77ff32d [Xiangrui Meng] organize imports
68e1dfb [Xiangrui Meng] use timeout from AkkaUtils; remove props from RegisteredExecutor
46d332d [Xiangrui Meng] fix a test
7947c18 [Xiangrui Meng] increase slack size for akka
4ab696a [Xiangrui Meng] bootstrap to retrieve driver spark conf
The assertJsonStringEquals method was missing an "assert" so
did not actually check that the strings were equal. This commit
adds the missing assert and fixes subsequently revealed problems
with the JsonProtocolSuite.
@andrewor14 I changed some of the test functionality to match what it
looks like you intended based on the expected strings -- let me know if
anything here looks wrong.
Author: Kay Ousterhout <kayousterhout@gmail.com>
Closes#1198 from kayousterhout/json_test_fix and squashes the following commits:
77f858f [Kay Ousterhout] Fix broken Json tests.
Don't check executor/host availability when creating a TaskSetManager. Because the executors may haven't been registered when the TaskSetManager is created, in which case all tasks will be considered "has no preferred locations", and thus losing data locality in later scheduling.
Author: Rui Li <rui.li@intel.com>
Author: lirui-intel <rui.li@intel.com>
Closes#892 from lirui-intel/delaySchedule and squashes the following commits:
8444d7c [Rui Li] fix code style
fafd57f [Rui Li] keep locality constraints within the valid levels
18f9e05 [Rui Li] restrict allowed locality
5b3fb2f [Rui Li] refine UT
99f843e [Rui Li] add unit test and fix bug
fff4123 [Rui Li] fix computing valid locality levels
685ed3d [Rui Li] remove delay shedule for pendingTasksWithNoPrefs
7b0177a [Rui Li] remove redundant code
c7b93b5 [Rui Li] revise patch
3d7da02 [lirui-intel] Update TaskSchedulerImpl.scala
cab4c71 [Rui Li] revised patch
539a578 [Rui Li] fix code style
cf0d6ac [Rui Li] fix code style
3dfae86 [Rui Li] re-compute pending tasks when new host is added
a225ac2 [Rui Li] SPARK-1937: fix issue with task locality
This PR is a sub-task of SPARK-2044 to move the execution of aggregation into shuffle implementations.
I leave `CoGoupedRDD` and `SubtractedRDD` unchanged because they have their implementations of aggregation. I'm not sure is it suitable to change these two RDDs.
Also I do not move sort related code of `OrderedRDDFunctions` into shuffle, this will be solved in another sub-task.
Author: jerryshao <saisai.shao@intel.com>
Closes#1064 from jerryshao/SPARK-2124 and squashes the following commits:
4a05a40 [jerryshao] Modify according to comments
1f7dcc8 [jerryshao] Style changes
50a2fd6 [jerryshao] Fix test suite issue after moving aggregator to Shuffle reader and writer
1a96190 [jerryshao] Code modification related to the ShuffledRDD
308f635 [jerryshao] initial works of move combiner to ShuffleManager's reader and writer
Commons IO is actually barely used, and is not a declared dependency. This just replaces with equivalents from the JDK and Guava.
Author: Sean Owen <sowen@cloudera.com>
Closes#1173 from srowen/SPARK-1316 and squashes the following commits:
2eb53db [Sean Owen] Reorder Guava import
8fde404 [Sean Owen] Remove use of Commons IO, which is not actually a dependency
- JavaAPISuite was trying to compare a bare path with a URI. Fix by
extracting the path from the URI, since we know it should be a
local path anyway/
- b9be1609 excluded the ASM dependency everywhere, but easymock needs
it (because cglib needs it). So re-add the dependency, with test
scope this time.
The second one above actually uncovered a weird situation: the maven
test target works, even though I can't find the class sbt complains
about in its classpath. sbt complains with:
[error] Uncaught exception when running org.apache.spark.util
.random.RandomSamplerSuite: java.lang.NoClassDefFoundError:
org/objectweb/asm/Type
To avoid more weirdness caused by that, I explicitly added the asm
dependency to both maven and sbt (for tests only), and verified
the classes don't end up in the final assembly.
Author: Marcelo Vanzin <vanzin@cloudera.com>
Closes#917 from vanzin/flaky-tests and squashes the following commits:
d022320 [Marcelo Vanzin] Fix some tests.
The jira for the issue can be found at: https://issues.apache.org/jira/browse/SPARK-2061
Most of spark has used over to consistently using `partitions` instead of `splits`. We should do likewise and add a `partitions` method to JavaRDDLike and have `splits` just call that. We should also go through all cases where other API's (e.g. Python) call `splits` and we should change those to use the newer API.
Author: Anant <anant.asty@gmail.com>
Closes#1062 from anantasty/SPARK-2061 and squashes the following commits:
b83ce6b [Anant] Fixed syntax issue
21f9210 [Anant] Fixed version number in deprecation string
9315b76 [Anant] made related changes to use partitions in python api
8c62dd1 [Anant] Made splits deprecated in JavaRDDLike
Updating the chisquare unit test in XORShiftRandomSuite to use the ChiSquareTest in commons-math3 instead of hardcoding the chisquare statistic for the desired confidence interval.
Author: Doris Xin <doris.s.xin@gmail.com>
Closes#1073 from dorx/math3Unit and squashes the following commits:
da0e891 [Doris Xin] remove math3 from common pom
9954143 [Doris Xin] merge master
c19948f [Doris Xin] Merge branch 'master' into math3Unit
8f84f19 [Doris Xin] [SPARK-1970] unit test in XORShiftRandomSuite
ffea61a [Doris Xin] SPARK-1939: Refactor takeSample method in RDD
1441977 [Doris Xin] SPARK-1939 Refactor takeSample method in RDD to use ScaSRS
Adds cogroup for 4 RDDs.
Author: Allan Douglas R. de Oliveira <allandouglas@gmail.com>
Closes#813 from douglaz/more_cogroups and squashes the following commits:
f8d6273 [Allan Douglas R. de Oliveira] Test python groupWith for one more case
0e9009c [Allan Douglas R. de Oliveira] Added scala tests
c3ffcdd [Allan Douglas R. de Oliveira] Added java tests
517a67f [Allan Douglas R. de Oliveira] Added tests for python groupWith
2f402d5 [Allan Douglas R. de Oliveira] Removed TODO
17474f4 [Allan Douglas R. de Oliveira] Use new cogroup function
7877a2a [Allan Douglas R. de Oliveira] Fixed code
ba02414 [Allan Douglas R. de Oliveira] Added varargs cogroup to pyspark
c4a8a51 [Allan Douglas R. de Oliveira] Added java cogroup 4
e94963c [Allan Douglas R. de Oliveira] Fixed spacing
f1ee57b [Allan Douglas R. de Oliveira] Fixed scala style issues
d7196f1 [Allan Douglas R. de Oliveira] Allow the cogroup of 4 RDDs
Author: Patrick Wendell <pwendell@gmail.com>
Closes#1141 from pwendell/hotfix and squashes the following commits:
83e4c79 [Patrick Wendell] HOTFIX: SPARK-2208 local metrics tests can fail on fast machines
@tdas
Author: Mark Hamstra <markhamstra@gmail.com>
Closes#1100 from markhamstra/SPARK-2158 and squashes the following commits:
ae8e069 [Mark Hamstra] Response to TD's review
2f1e201 [Mark Hamstra] Cleanup 'stdout' file within FileAppenderSuite
This never got merged from the apache/incubator-spark repo (which is now deleted) but there had been several rounds of code review on this PR there.
I think this is ready for merging.
Author: Andrew Ash <andrew@andrewash.com>
This patch had conflicts when merged, resolved by
Committer: Reynold Xin <rxin@apache.org>
Closes#369 from ash211/sortby and squashes the following commits:
d09147a [Andrew Ash] Fix Ordering import
43d0a53 [Andrew Ash] Fix missing .collect()
29a54ed [Andrew Ash] Re-enable test by converting to a closure
5a95348 [Andrew Ash] Add license for RDDSuiteUtils
64ed6e3 [Andrew Ash] Remove leaked diff
d4de69a [Andrew Ash] Remove scar tissue
63638b5 [Andrew Ash] Add Python version of .sortBy()
45e0fde [Andrew Ash] Add Java version of .sortBy()
adf84c5 [Andrew Ash] Re-indent to keep line lengths under 100 chars
9d9b9d8 [Andrew Ash] Use parentheses on .collect() calls
0457b69 [Andrew Ash] Ignore failing test
99f0baf [Andrew Ash] Merge branch 'master' into sortby
222ae97 [Andrew Ash] Try moving Ordering objects out to a different class
3fd0dd3 [Andrew Ash] Add (failing) test for sortByKey with explicit Ordering
b8b5bbc [Andrew Ash] Align remove extra spaces that were used to align ='s in test code
8c53298 [Andrew Ash] Actually use ascending and numPartitions parameters
381eef2 [Andrew Ash] Correct silly typo
7db3e84 [Andrew Ash] Support ascending and numPartitions params in sortBy()
0f685fd [Andrew Ash] Merge remote-tracking branch 'origin/master' into sortby
ca4490d [Andrew Ash] Add .sortBy(f) method on RDD
I'm not sure about the test -- I get a lot of unrelated failures for some reason. I'll try to sort it out. But hopefully the automation will test this for me if I send a pull request :).
I'll attach a demo HTML in [Jira](https://issues.apache.org/jira/browse/SPARK-2035).
Author: Daniel Darabos <darabos.daniel@gmail.com>
Author: Patrick Wendell <pwendell@gmail.com>
Closes#981 from darabos/darabos-call-stack and squashes the following commits:
f7c6bfa [Daniel Darabos] Fix bad merge. I undid 83c226d454 by Doris.
3d0a48d [Daniel Darabos] Merge remote-tracking branch 'upstream/master' into darabos-call-stack
b857849 [Daniel Darabos] Style: Break long line.
ecb5690 [Daniel Darabos] Include the last Spark method in the full stack trace. Otherwise it is not visible if the stage name is overridden.
d00a85b [Patrick Wendell] Make call sites for stages non-optional and well defined
b9eba24 [Daniel Darabos] Make StageInfo.details non-optional. Add JSON serialization code for the new field. Verify JSON backward compatibility.
4312828 [Daniel Darabos] Remove Mima excludes for CallSite. They should be unnecessary now, with SPARK-2070 fixed.
0920750 [Daniel Darabos] Merge remote-tracking branch 'upstream/master' into darabos-call-stack
a4b1faf [Daniel Darabos] Add Mima exclusions for the CallSite changes it has picked up. They are private methods/classes, so we ought to be safe.
932f810 [Daniel Darabos] Use empty CallSite instead of null in DAGSchedulerSuite. Outside of testing, this parameter always originates in SparkContext.scala, and will never be null.
ccd89d1 [Daniel Darabos] Fix long lines.
ac173e4 [Daniel Darabos] Hide "show details" if there are no details to show.
6182da6 [Daniel Darabos] Set a configurable limit on maximum call stack depth. It can be useful in memory-constrained situations with large numbers of stages.
8fe2e34 [Daniel Darabos] Store call stack for stages, display it on the UI.
... sequences
Author: Kan Zhang <kzhang@apache.org>
Closes#776 from kanzhang/SPARK-1837 and squashes the following commits:
e48f018 [Kan Zhang] [SPARK-1837] code refactoring
67c33b5 [Kan Zhang] minor change
403f9b1 [Kan Zhang] [SPARK-1837] NumericRange should be partitioned in the same way as other sequences
Modified the takeSample method in RDD to use the ScaSRS sampling technique to improve performance. Added a private method that computes sampling rate > sample_size/total to ensure sufficient sample size with success rate >= 0.9999. Added a unit test for the private method to validate choice of sampling rate.
Author: Doris Xin <doris.s.xin@gmail.com>
Author: dorx <doris.s.xin@gmail.com>
Author: Xiangrui Meng <meng@databricks.com>
Closes#916 from dorx/takeSample and squashes the following commits:
5b061ae [Doris Xin] merge master
444e750 [Doris Xin] edge cases
3de882b [dorx] Merge pull request #2 from mengxr/SPARK-1939
82dde31 [Xiangrui Meng] update pyspark's takeSample
48d954d [Doris Xin] remove unused imports from RDDSuite
fb1452f [Doris Xin] allowing num to be greater than count in all cases
1481b01 [Doris Xin] washing test tubes and making coffee
dc699f3 [Doris Xin] give back imports removed by accident in rdd.py
64e445b [Doris Xin] logwarnning as soon as it enters the while loop
55518ed [Doris Xin] added TODO for logging in rdd.py
eff89e2 [Doris Xin] addressed reviewer comments.
ecab508 [Doris Xin] "fixed checkstyle violation
0a9b3e3 [Doris Xin] "reviewer comment addressed"
f80f270 [Doris Xin] Merge branch 'master' into takeSample
ae3ad04 [Doris Xin] fixed edge cases to prevent overflow
065ebcd [Doris Xin] Merge branch 'master' into takeSample
9bdd36e [Doris Xin] Check sample size and move computeFraction
e3fd6a6 [Doris Xin] Merge branch 'master' into takeSample
7cab53a [Doris Xin] fixed import bug in rdd.py
ffea61a [Doris Xin] SPARK-1939: Refactor takeSample method in RDD
1441977 [Doris Xin] SPARK-1939 Refactor takeSample method in RDD to use ScaSRS
After deserialization, the transient field creationSiteInfo does not get backfilled with the default value, but the toString method, which is invoked by the serializer, expects the field to always be non-null. An NPE is thrown when toString is called by the serializer when creationSiteInfo is null.
Author: Doris Xin <doris.s.xin@gmail.com>
Closes#1028 from dorx/toStringNPE and squashes the following commits:
f20021e [Doris Xin] unit test for toString after desrialization
6f0a586 [Doris Xin] Merge branch 'master' into toStringNPE
f47fecf [Doris Xin] Merge branch 'master' into toStringNPE
76199c6 [Doris Xin] [SPARK-2088] fix NPE in toString
This is a first cut at moving shuffle logic behind a pluggable interface, as described at https://issues.apache.org/jira/browse/SPARK-2044, to let us more easily experiment with new shuffle implementations. It moves the existing shuffle code to a class HashShuffleManager behind a general ShuffleManager interface.
Two things are still missing to make this complete:
* MapOutputTracker needs to be hidden behind the ShuffleManager interface; this will also require adding methods to ShuffleManager that will let the DAGScheduler interact with it as it does with the MapOutputTracker today
* The code to do map-sides and reduce-side combine in ShuffledRDD, PairRDDFunctions, etc needs to be moved into the ShuffleManager's readers and writers
However, some of these may also be done later after we merge the current interface.
Author: Matei Zaharia <matei@databricks.com>
Closes#1009 from mateiz/pluggable-shuffle and squashes the following commits:
7a09862 [Matei Zaharia] review comments
be33d3f [Matei Zaharia] review comments
1513d4e [Matei Zaharia] Add ASF header
ac56831 [Matei Zaharia] Bug fix and better error message
4f681ba [Matei Zaharia] Move write part of ShuffleMapTask to ShuffleManager
f6f011d [Matei Zaharia] Move hash shuffle reader behind ShuffleManager interface
55c7717 [Matei Zaharia] Changed RDD code to use ShuffleReader
75cc044 [Matei Zaharia] Partial work to move hash shuffle in
Author: witgo <witgo@qq.com>
Closes#1032 from witgo/ShouldMatchers and squashes the following commits:
7ebf34c [witgo] Resolve scalatest warnings during build
Currently, in the default log4j configuration, all the executor logs get sent to the file <code>[executor-working-dir]/stderr</code>. This does not all log files to be rolled, so old logs cannot be removed.
Using log4j RollingFileAppender allows log4j logs to be rolled, but all the logs get sent to a different set of files, other than the files <code>stdout</code> and <code>stderr</code> . So the logs are not visible in the Spark web UI any more as Spark web UI only reads the files <code>stdout</code> and <code>stderr</code>. Furthermore, it still does not allow the stdout and stderr to be cleared periodically in case a large amount of stuff gets written to them (e.g. by explicit `println` inside map function).
This PR solves this by implementing a simple `RollingFileAppender` within Spark (disabled by default). When enabled (using configuration parameter `spark.executor.rollingLogs.enabled`), the logs can get rolled over either by time interval (set with `spark.executor.rollingLogs.interval`, set to daily by default), or by size of logs (set with `spark.executor.rollingLogs.size`). Finally, old logs can be automatically deleted by specifying how many of the latest log files to keep (set with `spark.executor.rollingLogs.keepLastN`). The web UI has also been modified to show the logs across the rolled-over files.
You can test this locally (without waiting a whole day) by setting configuration `spark.executor.rollingLogs.enabled=true` and `spark.executor.rollingLogs.interval=minutely`. Continuously generate logs by running spark jobs and the generated logs files would look like this (`stderr` and `stdout` are the most current log file that are being written to).
```
stderr
stderr--2014-05-27--14-37
stderr--2014-05-27--14-47
stderr--2014-05-27--15-05
stdout
stdout--2014-05-27--14-47
```
The web ui should show logs across these files.
Author: Tathagata Das <tathagata.das1565@gmail.com>
Closes#895 from tdas/rolling-logs and squashes the following commits:
fd8f87f [Tathagata Das] Minor change.
d326aee [Tathagata Das] Merge remote-tracking branch 'apache-github/master' into rolling-logs
ad956c1 [Tathagata Das] Scala style fix.
1f0a6ec [Tathagata Das] Some more changes based on Patrick's PR comments.
c8bfe4e [Tathagata Das] Refactore FileAppender to a package spark.util.logging and broke up the file into multiple files. Changed configuration parameter names.
4224409 [Tathagata Das] Style fix.
108a9f8 [Tathagata Das] Added better constraint handling for rolling policies.
f7da977 [Tathagata Das] Merge remote-tracking branch 'apache-github/master' into rolling-logs
9134495 [Tathagata Das] Simplified rolling logs by removing Daily/Hourly/MinutelyRollingFileAppender, and removing the setting rollingLogs.enabled
312d874 [Tathagata Das] Minor fixes based on PR comments.
8a67d83 [Tathagata Das] Fixed comments.
b36cfd6 [Tathagata Das] Implemented RollingPolicy, TimeBasedRollingPolicy and SizeBasedRollingPolicy, and changed RollingFileAppender accordingly.
b7e8272 [Tathagata Das] Style fix,
374c9a9 [Tathagata Das] Added missing license.
24354ea [Tathagata Das] Merge remote-tracking branch 'apache-github/master' into rolling-logs
6cc09c7 [Tathagata Das] Fixed bugs in rolling logs, and added more debug statements.
adf4910 [Tathagata Das] Merge remote-tracking branch 'apache-github/master' into rolling-logs
931f8fb [Tathagata Das] Changed log viewer in Spark web UI to handle rolling log files.
cb4fb6d [Tathagata Das] Added FileAppender and RollingFileAppender to generate rolling executor logs.
This test ensures that when there are no
alive executors that satisfy a particular locality level,
the TaskSetManager doesn't ever use that as the maximum
allowed locality level (this optimization ensures that a
job doesn't wait extra time in an attempt to satisfy
a scheduling locality level that is impossible).
@mateiz and @lirui-intel this unit test illustrates an issue
with #892 (it fails with that patch).
Author: Kay Ousterhout <kayousterhout@gmail.com>
Closes#1024 from kayousterhout/scheduler_unit_test and squashes the following commits:
de6a08f [Kay Ousterhout] Added a TaskSetManager unit test.
The current implementation reads one key with the next hash code as it finishes reading the keys with the current hash code, which may cause it to miss some matches of the next key. This can cause operations like join to give the wrong result when reduce tasks spill to disk and there are hash collisions, as values won't be matched together. This PR fixes it by not reading in that next key, using a peeking iterator instead.
Author: Matei Zaharia <matei@databricks.com>
Closes#986 from mateiz/spark-2043 and squashes the following commits:
0959514 [Matei Zaharia] Added unit test for having many hash collisions
892debb [Matei Zaharia] SPARK-2043: don't read a key with the next hash code in ExternalAppendOnlyMap, instead use a buffered iterator to only read values with the current hash code.
https://issues.apache.org/jira/browse/SPARK-1677
For compatibility with older versions of Spark it would be nice to have an option `spark.hadoop.validateOutputSpecs` (default true) for the user to disable the output directory existence checking
Author: CodingCat <zhunansjtu@gmail.com>
Closes#947 from CodingCat/SPARK-1677 and squashes the following commits:
7930f83 [CodingCat] miao
c0c0e03 [CodingCat] bug fix and doc update
5318562 [CodingCat] bug fix
13219b5 [CodingCat] allow user to disable output dir existence checking
I'd like to use randomSplit through the Java API, and would like to add a convenience wrapper for this method to JavaRDD. This is fairly trivial. (In fact, is the intent that JavaRDD not wrap every RDD method? and that sometimes users should just use JavaRDD.wrapRDD()?)
Along the way, I added tests for it, and also touched up the Java API test style and behavior. This is maybe the more useful part of this small change.
Author: Sean Owen <sowen@cloudera.com>
Author: Xiangrui Meng <meng@databricks.com>
This patch had conflicts when merged, resolved by
Committer: Xiangrui Meng <meng@databricks.com>
Closes#919 from srowen/SPARK-1973 and squashes the following commits:
148cb7b [Sean Owen] Some final Java test polish, while we are at it
1fc3f3e [Xiangrui Meng] more cleaning on Java 8 tests
9ebc57f [Sean Owen] Use accumulator instead of temp files to test foreach
5efb0be [Sean Owen] Add Java randomSplit, and unit tests (including for sample)
5dcc158 [Sean Owen] Simplified Java 8 test with new language features, and fixed the name of MLB's greatest team
91a1769 [Sean Owen] Touch up minor style issues in existing Java API suite test
RDD.zip() will throw an exception if it finds partition sizes are not the same.
Author: Kan Zhang <kzhang@apache.org>
Closes#944 from kanzhang/SPARK-1817 and squashes the following commits:
c073848 [Kan Zhang] [SPARK-1817] Cosmetic updates
524c670 [Kan Zhang] [SPARK-1817] RDD.zip() should verify partition sizes for each partition
I also corrected some errors made in the previous HLL count approximate API, including relativeSD wasn't really a measure for error (and we used it to test error bounds in test results).
Author: Reynold Xin <rxin@apache.org>
Closes#897 from rxin/hll and squashes the following commits:
4d83f41 [Reynold Xin] New error bound and non-randomness.
f154ea0 [Reynold Xin] Added a comment on the value bound for testing.
e367527 [Reynold Xin] One more round of code review.
41e649a [Reynold Xin] Update final mima list.
9e320c8 [Reynold Xin] Incorporate code review feedback.
e110d70 [Reynold Xin] Merge branch 'master' into hll
354deb8 [Reynold Xin] Added comment on the Mima exclude rules.
acaa524 [Reynold Xin] Added the right exclude rules in MimaExcludes.
6555bfe [Reynold Xin] Added a default method and re-arranged MimaExcludes.
1db1522 [Reynold Xin] Excluded util.SerializableHyperLogLog from MIMA check.
9221b27 [Reynold Xin] Merge branch 'master' into hll
88cfe77 [Reynold Xin] Updated documentation and restored the old incorrect API to maintain API compatibility.
1294be6 [Reynold Xin] Updated HLL+.
e7786cb [Reynold Xin] Merge branch 'master' into hll
c0ef0c2 [Reynold Xin] SPARK-1941: Update streamlib to 2.7.0 and use HyperLogLogPlus instead of HyperLogLog.
stop resetting spark.driver.port in unit tests (scala, java and python).
Author: Syed Hashmi <shashmi@cloudera.com>
Author: CodingCat <zhunansjtu@gmail.com>
Closes#943 from syedhashmi/master and squashes the following commits:
885f210 [Syed Hashmi] Removing unnecessary file (created by mergetool)
b8bd4b5 [Syed Hashmi] Merge remote-tracking branch 'upstream/master'
b895e59 [Syed Hashmi] Revert "[SPARK-1784] Add a new partitioner"
57b6587 [Syed Hashmi] Revert "[SPARK-1784] Add a balanced partitioner"
1574769 [Syed Hashmi] [SPARK-1942] Stop clearing spark.driver.port in unit tests
4354836 [Syed Hashmi] Revert "SPARK-1686: keep schedule() calling in the main thread"
fd36542 [Syed Hashmi] [SPARK-1784] Add a balanced partitioner
6668015 [CodingCat] SPARK-1686: keep schedule() calling in the main thread
4ca94cc [Syed Hashmi] [SPARK-1784] Add a new partitioner
DAGScheduler does not handle local task OOM properly, and will wait for the job result forever.
Author: Zhen Peng <zhenpeng01@baidu.com>
Closes#883 from zhpengg/bugfix-dag-scheduler-oom and squashes the following commits:
76f7eda [Zhen Peng] remove redundant memory allocations
aa63161 [Zhen Peng] SPARK-1929 DAGScheduler suspended by local task OOM
If I run the following on a YARN cluster
```
bin/spark-submit sheep.py --master yarn-client
```
it fails because of a mismatch in paths: `spark-submit` thinks that `sheep.py` resides on HDFS, and balks when it can't find the file there. A natural workaround is to add the `file:` prefix to the file:
```
bin/spark-submit file:/path/to/sheep.py --master yarn-client
```
However, this also fails. This time it is because python does not understand URI schemes.
This PR fixes this by automatically resolving all paths passed as command line argument to `spark-submit` properly. This has the added benefit of keeping file and jar paths consistent across different cluster modes. For python, we strip the URI scheme before we actually try to run it.
Much of the code is originally written by @mengxr. Tested on YARN cluster. More tests pending.
Author: Andrew Or <andrewor14@gmail.com>
Closes#853 from andrewor14/submit-paths and squashes the following commits:
0bb097a [Andrew Or] Format path correctly before adding it to PYTHONPATH
323b45c [Andrew Or] Include --py-files on PYTHONPATH for pyspark shell
3c36587 [Andrew Or] Improve error messages (minor)
854aa6a [Andrew Or] Guard against NPE if user gives pathological paths
6638a6b [Andrew Or] Fix spark-shell jar paths after #849 went in
3bb0359 [Andrew Or] Update more comments (minor)
2a1f8a0 [Andrew Or] Update comments (minor)
6af2c77 [Andrew Or] Merge branch 'master' of github.com:apache/spark into submit-paths
a68c4d1 [Andrew Or] Handle Windows python file path correctly
427a250 [Andrew Or] Resolve paths properly for Windows
a591a4a [Andrew Or] Update tests for resolving URIs
6c8621c [Andrew Or] Move resolveURIs to Utils
db8255e [Andrew Or] Merge branch 'master' of github.com:apache/spark into submit-paths
f542dce [Andrew Or] Fix outdated tests
691c4ce [Andrew Or] Ignore special primary resource names
5342ac7 [Andrew Or] Add missing space in error message
02f77f3 [Andrew Or] Resolve command line arguments to spark-submit properly
Due to perhaps zombie processes on Jenkins, it seems that at least 10
Spark ports are in use. It also doesn't matter that the port increases
when used, it could in fact go down -- the only part that matters is
that it selects a different port rather than failing to bind.
Changed test to match this.
Thanks to @andrewor14 for helping diagnose this.
Author: Aaron Davidson <aaron@databricks.com>
Closes#857 from aarondav/tiny and squashes the following commits:
c199ec8 [Aaron Davidson] Fix UISuite unit test that fails under Jenkins contention
It was in the wrong package
Author: Andrew Or <andrewor14@gmail.com>
Closes#839 from andrewor14/jdbc-suite and squashes the following commits:
f948c5a [Andrew Or] cache -> cache()
b215279 [Andrew Or] Move JdbcRDDSuite to the correct package
