You are viewing a plain text version of this content. The canonical link for it is here.
Posted to reviews@spark.apache.org by GitBox <gi...@apache.org> on 2020/03/04 07:27:14 UTC
[GitHub] [spark] Ngone51 opened a new pull request #27786:
[SPARK-31034][CORE] ShuffleBlockFetcherIterator should always create
request for last block group
Ngone51 opened a new pull request #27786: [SPARK-31034][CORE] ShuffleBlockFetcherIterator should always create request for last block group
URL: https://github.com/apache/spark/pull/27786
<!--
Thanks for sending a pull request! Here are some tips for you:
1. If this is your first time, please read our contributor guidelines: https://spark.apache.org/contributing.html
2. Ensure you have added or run the appropriate tests for your PR: https://spark.apache.org/developer-tools.html
3. If the PR is unfinished, add '[WIP]' in your PR title, e.g., '[WIP][SPARK-XXXX] Your PR title ...'.
4. Be sure to keep the PR description updated to reflect all changes.
5. Please write your PR title to summarize what this PR proposes.
6. If possible, provide a concise example to reproduce the issue for a faster review.
7. If you want to add a new configuration, please read the guideline first for naming configurations in
'core/src/main/scala/org/apache/spark/internal/config/ConfigEntry.scala'.
-->
### What changes were proposed in this pull request?
<!--
Please clarify what changes you are proposing. The purpose of this section is to outline the changes and how this PR fixes the issue.
If possible, please consider writing useful notes for better and faster reviews in your PR. See the examples below.
1. If you refactor some codes with changing classes, showing the class hierarchy will help reviewers.
2. If you fix some SQL features, you can provide some references of other DBMSes.
3. If there is design documentation, please add the link.
4. If there is a discussion in the mailing list, please add the link.
-->
This is a bug fix of #27280. This PR fix the bug where ShuffleBlockFetcherIterator may forget to create request for the last block group.
### Why are the changes needed?
<!--
Please clarify why the changes are needed. For instance,
1. If you propose a new API, clarify the use case for a new API.
2. If you fix a bug, you can clarify why it is a bug.
-->
When all blocks.sum < `targetRemoteRequestSize` and all blocks.length > `maxBlocksInFlightPerAddress` and (last block group).size < `maxBlocksInFlightPerAddress`,
`ShuffleBlockFetcherIterator` will not create a request for the last group. Thus, it will lost data for the reduce task.
### Does this PR introduce any user-facing change?
<!--
If yes, please clarify the previous behavior and the change this PR proposes - provide the console output, description and/or an example to show the behavior difference if possible.
If no, write 'No'.
-->
No.
### How was this patch tested?
<!--
If tests were added, say they were added here. Please make sure to add some test cases that check the changes thoroughly including negative and positive cases if possible.
If it was tested in a way different from regular unit tests, please clarify how you tested step by step, ideally copy and paste-able, so that other reviewers can test and check, and descendants can verify in the future.
If tests were not added, please describe why they were not added and/or why it was difficult to add.
-->
Should be covered by #27767. And I tested it locally to verify this fix.
----------------------------------------------------------------
This is an automated message from the Apache Git Service.
To respond to the message, please log on to GitHub and use the
URL above to go to the specific comment.
For queries about this service, please contact Infrastructure at:
users@infra.apache.org
With regards,
Apache Git Services
---------------------------------------------------------------------
To unsubscribe, e-mail: reviews-unsubscribe@spark.apache.org
For additional commands, e-mail: reviews-help@spark.apache.org
[GitHub] [spark] SparkQA removed a comment on issue #27786:
[SPARK-31034][CORE] ShuffleBlockFetcherIterator should always create
request for last block group
Posted by GitBox <gi...@apache.org>.
SparkQA removed a comment on issue #27786: [SPARK-31034][CORE] ShuffleBlockFetcherIterator should always create request for last block group
URL: https://github.com/apache/spark/pull/27786#issuecomment-594385786
**[Test build #119287 has started](https://amplab.cs.berkeley.edu/jenkins/job/SparkPullRequestBuilder/119287/testReport)** for PR 27786 at commit [`28df4ab`](https://github.com/apache/spark/commit/28df4ab6d6c8c68012ec95492fd56c05bd37463a).
----------------------------------------------------------------
This is an automated message from the Apache Git Service.
To respond to the message, please log on to GitHub and use the
URL above to go to the specific comment.
For queries about this service, please contact Infrastructure at:
users@infra.apache.org
With regards,
Apache Git Services
---------------------------------------------------------------------
To unsubscribe, e-mail: reviews-unsubscribe@spark.apache.org
For additional commands, e-mail: reviews-help@spark.apache.org
[GitHub] [spark] SparkQA removed a comment on issue #27786:
[SPARK-31034][CORE] ShuffleBlockFetcherIterator should always create
request for last block group
Posted by GitBox <gi...@apache.org>.
SparkQA removed a comment on issue #27786: [SPARK-31034][CORE] ShuffleBlockFetcherIterator should always create request for last block group
URL: https://github.com/apache/spark/pull/27786#issuecomment-594400454
**[Test build #119294 has started](https://amplab.cs.berkeley.edu/jenkins/job/SparkPullRequestBuilder/119294/testReport)** for PR 27786 at commit [`778be33`](https://github.com/apache/spark/commit/778be33d71cc70fbff5bb635e3d397ff15981a19).
----------------------------------------------------------------
This is an automated message from the Apache Git Service.
To respond to the message, please log on to GitHub and use the
URL above to go to the specific comment.
For queries about this service, please contact Infrastructure at:
users@infra.apache.org
With regards,
Apache Git Services
---------------------------------------------------------------------
To unsubscribe, e-mail: reviews-unsubscribe@spark.apache.org
For additional commands, e-mail: reviews-help@spark.apache.org
[GitHub] [spark] AmplabJenkins commented on issue #27786:
[SPARK-31034][CORE] ShuffleBlockFetcherIterator should always create
request for last block group
Posted by GitBox <gi...@apache.org>.
AmplabJenkins commented on issue #27786: [SPARK-31034][CORE] ShuffleBlockFetcherIterator should always create request for last block group
URL: https://github.com/apache/spark/pull/27786#issuecomment-594650410
Test FAILed.
Refer to this link for build results (access rights to CI server needed):
https://amplab.cs.berkeley.edu/jenkins//job/SparkPullRequestBuilder/119308/
Test FAILed.
----------------------------------------------------------------
This is an automated message from the Apache Git Service.
To respond to the message, please log on to GitHub and use the
URL above to go to the specific comment.
For queries about this service, please contact Infrastructure at:
users@infra.apache.org
With regards,
Apache Git Services
---------------------------------------------------------------------
To unsubscribe, e-mail: reviews-unsubscribe@spark.apache.org
For additional commands, e-mail: reviews-help@spark.apache.org
[GitHub] [spark] AmplabJenkins commented on issue #27786:
[SPARK-31034][CORE] ShuffleBlockFetcherIterator should always create
request for last block group
Posted by GitBox <gi...@apache.org>.
AmplabJenkins commented on issue #27786: [SPARK-31034][CORE] ShuffleBlockFetcherIterator should always create request for last block group
URL: https://github.com/apache/spark/pull/27786#issuecomment-594650403
Merged build finished. Test FAILed.
----------------------------------------------------------------
This is an automated message from the Apache Git Service.
To respond to the message, please log on to GitHub and use the
URL above to go to the specific comment.
For queries about this service, please contact Infrastructure at:
users@infra.apache.org
With regards,
Apache Git Services
---------------------------------------------------------------------
To unsubscribe, e-mail: reviews-unsubscribe@spark.apache.org
For additional commands, e-mail: reviews-help@spark.apache.org
[GitHub] [spark] AmplabJenkins removed a comment on issue #27786:
[SPARK-31034][CORE] ShuffleBlockFetcherIterator should always create
request for last block group
Posted by GitBox <gi...@apache.org>.
AmplabJenkins removed a comment on issue #27786: [SPARK-31034][CORE] ShuffleBlockFetcherIterator should always create request for last block group
URL: https://github.com/apache/spark/pull/27786#issuecomment-594486498
Test PASSed.
Refer to this link for build results (access rights to CI server needed):
https://amplab.cs.berkeley.edu/jenkins//job/SparkPullRequestBuilder/119287/
Test PASSed.
----------------------------------------------------------------
This is an automated message from the Apache Git Service.
To respond to the message, please log on to GitHub and use the
URL above to go to the specific comment.
For queries about this service, please contact Infrastructure at:
users@infra.apache.org
With regards,
Apache Git Services
---------------------------------------------------------------------
To unsubscribe, e-mail: reviews-unsubscribe@spark.apache.org
For additional commands, e-mail: reviews-help@spark.apache.org
[GitHub] [spark] AmplabJenkins removed a comment on issue #27786:
[SPARK-31034][CORE] ShuffleBlockFetcherIterator should always create
request for last block group
Posted by GitBox <gi...@apache.org>.
AmplabJenkins removed a comment on issue #27786: [SPARK-31034][CORE] ShuffleBlockFetcherIterator should always create request for last block group
URL: https://github.com/apache/spark/pull/27786#issuecomment-594632965
Test PASSed.
Refer to this link for build results (access rights to CI server needed):
https://amplab.cs.berkeley.edu/jenkins//job/SparkPullRequestBuilder-K8s/24057/
Test PASSed.
----------------------------------------------------------------
This is an automated message from the Apache Git Service.
To respond to the message, please log on to GitHub and use the
URL above to go to the specific comment.
For queries about this service, please contact Infrastructure at:
users@infra.apache.org
With regards,
Apache Git Services
---------------------------------------------------------------------
To unsubscribe, e-mail: reviews-unsubscribe@spark.apache.org
For additional commands, e-mail: reviews-help@spark.apache.org
[GitHub] [spark] AmplabJenkins removed a comment on issue #27786:
[SPARK-31034][CORE] ShuffleBlockFetcherIterator should always create
request for last block group
Posted by GitBox <gi...@apache.org>.
AmplabJenkins removed a comment on issue #27786: [SPARK-31034][CORE] ShuffleBlockFetcherIterator should always create request for last block group
URL: https://github.com/apache/spark/pull/27786#issuecomment-594650410
Test FAILed.
Refer to this link for build results (access rights to CI server needed):
https://amplab.cs.berkeley.edu/jenkins//job/SparkPullRequestBuilder/119308/
Test FAILed.
----------------------------------------------------------------
This is an automated message from the Apache Git Service.
To respond to the message, please log on to GitHub and use the
URL above to go to the specific comment.
For queries about this service, please contact Infrastructure at:
users@infra.apache.org
With regards,
Apache Git Services
---------------------------------------------------------------------
To unsubscribe, e-mail: reviews-unsubscribe@spark.apache.org
For additional commands, e-mail: reviews-help@spark.apache.org
[GitHub] [spark] AmplabJenkins removed a comment on issue #27786:
[SPARK-31034][CORE] ShuffleBlockFetcherIterator should always create
request for last block group
Posted by GitBox <gi...@apache.org>.
AmplabJenkins removed a comment on issue #27786: [SPARK-31034][CORE] ShuffleBlockFetcherIterator should always create request for last block group
URL: https://github.com/apache/spark/pull/27786#issuecomment-594481783
Merged build finished. Test FAILed.
----------------------------------------------------------------
This is an automated message from the Apache Git Service.
To respond to the message, please log on to GitHub and use the
URL above to go to the specific comment.
For queries about this service, please contact Infrastructure at:
users@infra.apache.org
With regards,
Apache Git Services
---------------------------------------------------------------------
To unsubscribe, e-mail: reviews-unsubscribe@spark.apache.org
For additional commands, e-mail: reviews-help@spark.apache.org
[GitHub] [spark] AmplabJenkins commented on issue #27786:
[SPARK-31034][CORE] ShuffleBlockFetcherIterator should always create
request for last block group
Posted by GitBox <gi...@apache.org>.
AmplabJenkins commented on issue #27786: [SPARK-31034][CORE] ShuffleBlockFetcherIterator should always create request for last block group
URL: https://github.com/apache/spark/pull/27786#issuecomment-594380039
Test FAILed.
Refer to this link for build results (access rights to CI server needed):
https://amplab.cs.berkeley.edu/jenkins//job/SparkPullRequestBuilder/119285/
Test FAILed.
----------------------------------------------------------------
This is an automated message from the Apache Git Service.
To respond to the message, please log on to GitHub and use the
URL above to go to the specific comment.
For queries about this service, please contact Infrastructure at:
users@infra.apache.org
With regards,
Apache Git Services
---------------------------------------------------------------------
To unsubscribe, e-mail: reviews-unsubscribe@spark.apache.org
For additional commands, e-mail: reviews-help@spark.apache.org
[GitHub] [spark] AmplabJenkins removed a comment on issue #27786:
[SPARK-31034][CORE] ShuffleBlockFetcherIterator should always create
request for last block group
Posted by GitBox <gi...@apache.org>.
AmplabJenkins removed a comment on issue #27786: [SPARK-31034][CORE] ShuffleBlockFetcherIterator should always create request for last block group
URL: https://github.com/apache/spark/pull/27786#issuecomment-594396449
Test PASSed.
Refer to this link for build results (access rights to CI server needed):
https://amplab.cs.berkeley.edu/jenkins//job/SparkPullRequestBuilder-K8s/24034/
Test PASSed.
----------------------------------------------------------------
This is an automated message from the Apache Git Service.
To respond to the message, please log on to GitHub and use the
URL above to go to the specific comment.
For queries about this service, please contact Infrastructure at:
users@infra.apache.org
With regards,
Apache Git Services
---------------------------------------------------------------------
To unsubscribe, e-mail: reviews-unsubscribe@spark.apache.org
For additional commands, e-mail: reviews-help@spark.apache.org
[GitHub] [spark] SparkQA removed a comment on issue #27786:
[SPARK-31034][CORE] ShuffleBlockFetcherIterator should always create
request for last block group
Posted by GitBox <gi...@apache.org>.
SparkQA removed a comment on issue #27786: [SPARK-31034][CORE] ShuffleBlockFetcherIterator should always create request for last block group
URL: https://github.com/apache/spark/pull/27786#issuecomment-594543021
**[Test build #119308 has started](https://amplab.cs.berkeley.edu/jenkins/job/SparkPullRequestBuilder/119308/testReport)** for PR 27786 at commit [`6766c7c`](https://github.com/apache/spark/commit/6766c7c43bd2d22a25e099241a96d78825f63f72).
----------------------------------------------------------------
This is an automated message from the Apache Git Service.
To respond to the message, please log on to GitHub and use the
URL above to go to the specific comment.
For queries about this service, please contact Infrastructure at:
users@infra.apache.org
With regards,
Apache Git Services
---------------------------------------------------------------------
To unsubscribe, e-mail: reviews-unsubscribe@spark.apache.org
For additional commands, e-mail: reviews-help@spark.apache.org
[GitHub] [spark] AmplabJenkins commented on issue #27786:
[SPARK-31034][CORE] ShuffleBlockFetcherIterator should always create
request for last block group
Posted by GitBox <gi...@apache.org>.
AmplabJenkins commented on issue #27786: [SPARK-31034][CORE] ShuffleBlockFetcherIterator should always create request for last block group
URL: https://github.com/apache/spark/pull/27786#issuecomment-594539208
Merged build finished. Test PASSed.
----------------------------------------------------------------
This is an automated message from the Apache Git Service.
To respond to the message, please log on to GitHub and use the
URL above to go to the specific comment.
For queries about this service, please contact Infrastructure at:
users@infra.apache.org
With regards,
Apache Git Services
---------------------------------------------------------------------
To unsubscribe, e-mail: reviews-unsubscribe@spark.apache.org
For additional commands, e-mail: reviews-help@spark.apache.org
[GitHub] [spark] cloud-fan commented on a change in pull request #27786:
[SPARK-31034][CORE] ShuffleBlockFetcherIterator should always create
request for last block group
Posted by GitBox <gi...@apache.org>.
cloud-fan commented on a change in pull request #27786: [SPARK-31034][CORE] ShuffleBlockFetcherIterator should always create request for last block group
URL: https://github.com/apache/spark/pull/27786#discussion_r387570436
##########
File path: core/src/test/scala/org/apache/spark/storage/ShuffleBlockFetcherIteratorSuite.scala
##########
@@ -341,32 +341,84 @@ class ShuffleBlockFetcherIteratorSuite extends SparkFunSuite with PrivateMethodT
assert(blockManager.hostLocalDirManager.get.getCachedHostLocalDirs().size === 1)
}
- test("fetch continuous blocks in batch respects maxSize and maxBlocks") {
+ test("fetch continuous blocks in batch should respect maxBytesInFlight") {
val blockManager = mock(classOf[BlockManager])
val localBmId = BlockManagerId("test-client", "test-local-host", 1)
doReturn(localBmId).when(blockManager).blockManagerId
// Make sure remote blocks would return the merged block
- val remoteBmId = BlockManagerId("test-client-1", "test-client-1", 2)
- val remoteBlocks = Seq[BlockId](
+ val remoteBmId1 = BlockManagerId("test-client-1", "test-client-1", 1)
+ val remoteBmId2 = BlockManagerId("test-client-2", "test-client-2", 2)
+ val remoteBlocks1 = (0 until 15).map(ShuffleBlockId(0, 3, _))
+ val remoteBlocks2 = Seq[BlockId](ShuffleBlockId(0, 4, 0), ShuffleBlockId(0, 4, 1))
+ val mergedRemoteBlocks = Map[BlockId, ManagedBuffer](
+ ShuffleBlockBatchId(0, 3, 0, 3) -> createMockManagedBuffer(),
+ ShuffleBlockBatchId(0, 3, 3, 6) -> createMockManagedBuffer(),
+ ShuffleBlockBatchId(0, 3, 6, 9) -> createMockManagedBuffer(),
+ ShuffleBlockBatchId(0, 3, 9, 12) -> createMockManagedBuffer(),
+ ShuffleBlockBatchId(0, 3, 12, 15) -> createMockManagedBuffer(),
+ ShuffleBlockBatchId(0, 4, 0, 2) -> createMockManagedBuffer())
+ val transfer = createMockTransfer(mergedRemoteBlocks)
+
+ val blocksByAddress = Seq[(BlockManagerId, Seq[(BlockId, Long, Int)])](
+ (remoteBmId1, remoteBlocks1.map(blockId => (blockId, 100L, 1))),
+ (remoteBmId2, remoteBlocks2.map(blockId => (blockId, 100L, 1)))).toIterator
+
+ val taskContext = TaskContext.empty()
+ val metrics = taskContext.taskMetrics.createTempShuffleReadMetrics()
+ val iterator = new ShuffleBlockFetcherIterator(
+ taskContext,
+ transfer,
+ blockManager,
+ blocksByAddress,
+ (_, in) => in,
+ 1500,
+ Int.MaxValue,
+ Int.MaxValue,
+ Int.MaxValue,
+ true,
+ false,
+ metrics,
+ true)
+
+ var numResults = 0
+ // After initialize(), there will be 6 FetchRequests, and the each of the first 5
+ // includes 3 merged blocks and the last one has 1 merged block. So, only the
Review comment:
ok let's update
----------------------------------------------------------------
This is an automated message from the Apache Git Service.
To respond to the message, please log on to GitHub and use the
URL above to go to the specific comment.
For queries about this service, please contact Infrastructure at:
users@infra.apache.org
With regards,
Apache Git Services
---------------------------------------------------------------------
To unsubscribe, e-mail: reviews-unsubscribe@spark.apache.org
For additional commands, e-mail: reviews-help@spark.apache.org
[GitHub] [spark] AmplabJenkins removed a comment on issue #27786:
[SPARK-31034][CORE] ShuffleBlockFetcherIterator should always create
request for last block group
Posted by GitBox <gi...@apache.org>.
AmplabJenkins removed a comment on issue #27786: [SPARK-31034][CORE] ShuffleBlockFetcherIterator should always create request for last block group
URL: https://github.com/apache/spark/pull/27786#issuecomment-594791562
Merged build finished. Test PASSed.
----------------------------------------------------------------
This is an automated message from the Apache Git Service.
To respond to the message, please log on to GitHub and use the
URL above to go to the specific comment.
For queries about this service, please contact Infrastructure at:
users@infra.apache.org
With regards,
Apache Git Services
---------------------------------------------------------------------
To unsubscribe, e-mail: reviews-unsubscribe@spark.apache.org
For additional commands, e-mail: reviews-help@spark.apache.org
[GitHub] [spark] AmplabJenkins removed a comment on issue #27786:
[SPARK-31034][CORE] ShuffleBlockFetcherIterator should always create
request for last block group
Posted by GitBox <gi...@apache.org>.
AmplabJenkins removed a comment on issue #27786: [SPARK-31034][CORE] ShuffleBlockFetcherIterator should always create request for last block group
URL: https://github.com/apache/spark/pull/27786#issuecomment-594380031
Merged build finished. Test FAILed.
----------------------------------------------------------------
This is an automated message from the Apache Git Service.
To respond to the message, please log on to GitHub and use the
URL above to go to the specific comment.
For queries about this service, please contact Infrastructure at:
users@infra.apache.org
With regards,
Apache Git Services
---------------------------------------------------------------------
To unsubscribe, e-mail: reviews-unsubscribe@spark.apache.org
For additional commands, e-mail: reviews-help@spark.apache.org
[GitHub] [spark] AmplabJenkins commented on issue #27786:
[SPARK-31034][CORE] ShuffleBlockFetcherIterator should always create
request for last block group
Posted by GitBox <gi...@apache.org>.
AmplabJenkins commented on issue #27786: [SPARK-31034][CORE] ShuffleBlockFetcherIterator should always create request for last block group
URL: https://github.com/apache/spark/pull/27786#issuecomment-594481783
Merged build finished. Test FAILed.
----------------------------------------------------------------
This is an automated message from the Apache Git Service.
To respond to the message, please log on to GitHub and use the
URL above to go to the specific comment.
For queries about this service, please contact Infrastructure at:
users@infra.apache.org
With regards,
Apache Git Services
---------------------------------------------------------------------
To unsubscribe, e-mail: reviews-unsubscribe@spark.apache.org
For additional commands, e-mail: reviews-help@spark.apache.org
[GitHub] [spark] AmplabJenkins removed a comment on issue #27786:
[SPARK-31034][CORE] ShuffleBlockFetcherIterator should always create
request for last block group
Posted by GitBox <gi...@apache.org>.
AmplabJenkins removed a comment on issue #27786: [SPARK-31034][CORE] ShuffleBlockFetcherIterator should always create request for last block group
URL: https://github.com/apache/spark/pull/27786#issuecomment-594486487
Merged build finished. Test PASSed.
----------------------------------------------------------------
This is an automated message from the Apache Git Service.
To respond to the message, please log on to GitHub and use the
URL above to go to the specific comment.
For queries about this service, please contact Infrastructure at:
users@infra.apache.org
With regards,
Apache Git Services
---------------------------------------------------------------------
To unsubscribe, e-mail: reviews-unsubscribe@spark.apache.org
For additional commands, e-mail: reviews-help@spark.apache.org
[GitHub] [spark] AmplabJenkins removed a comment on issue #27786:
[SPARK-31034][CORE] ShuffleBlockFetcherIterator should always create
request for last block group
Posted by GitBox <gi...@apache.org>.
AmplabJenkins removed a comment on issue #27786: [SPARK-31034][CORE] ShuffleBlockFetcherIterator should always create request for last block group
URL: https://github.com/apache/spark/pull/27786#issuecomment-594387558
Test PASSed.
Refer to this link for build results (access rights to CI server needed):
https://amplab.cs.berkeley.edu/jenkins//job/SparkPullRequestBuilder-K8s/24027/
Test PASSed.
----------------------------------------------------------------
This is an automated message from the Apache Git Service.
To respond to the message, please log on to GitHub and use the
URL above to go to the specific comment.
For queries about this service, please contact Infrastructure at:
users@infra.apache.org
With regards,
Apache Git Services
---------------------------------------------------------------------
To unsubscribe, e-mail: reviews-unsubscribe@spark.apache.org
For additional commands, e-mail: reviews-help@spark.apache.org
[GitHub] [spark] Ngone51 commented on a change in pull request #27786:
[SPARK-31034][CORE] ShuffleBlockFetcherIterator should always create
request for last block group
Posted by GitBox <gi...@apache.org>.
Ngone51 commented on a change in pull request #27786: [SPARK-31034][CORE] ShuffleBlockFetcherIterator should always create request for last block group
URL: https://github.com/apache/spark/pull/27786#discussion_r387528372
##########
File path: core/src/test/scala/org/apache/spark/storage/ShuffleBlockFetcherIteratorSuite.scala
##########
@@ -375,25 +427,27 @@ class ShuffleBlockFetcherIteratorSuite extends SparkFunSuite with PrivateMethodT
blockManager,
blocksByAddress,
(_, in) => in,
- 35,
+ Int.MaxValue,
Int.MaxValue,
2,
Int.MaxValue,
true,
false,
metrics,
true)
-
var numResults = 0
+ // After initialize(), there will be 2 FetchRequests that one has 2 merged blocks and another
Review comment:
note: `2 merged blocks` -> `2 ShuffleBlockBatch`
----------------------------------------------------------------
This is an automated message from the Apache Git Service.
To respond to the message, please log on to GitHub and use the
URL above to go to the specific comment.
For queries about this service, please contact Infrastructure at:
users@infra.apache.org
With regards,
Apache Git Services
---------------------------------------------------------------------
To unsubscribe, e-mail: reviews-unsubscribe@spark.apache.org
For additional commands, e-mail: reviews-help@spark.apache.org
[GitHub] [spark] AmplabJenkins removed a comment on issue #27786:
[SPARK-31034][CORE] ShuffleBlockFetcherIterator should always create
request for last block group
Posted by GitBox <gi...@apache.org>.
AmplabJenkins removed a comment on issue #27786: [SPARK-31034][CORE] ShuffleBlockFetcherIterator should always create request for last block group
URL: https://github.com/apache/spark/pull/27786#issuecomment-594396436
Merged build finished. Test PASSed.
----------------------------------------------------------------
This is an automated message from the Apache Git Service.
To respond to the message, please log on to GitHub and use the
URL above to go to the specific comment.
For queries about this service, please contact Infrastructure at:
users@infra.apache.org
With regards,
Apache Git Services
---------------------------------------------------------------------
To unsubscribe, e-mail: reviews-unsubscribe@spark.apache.org
For additional commands, e-mail: reviews-help@spark.apache.org
[GitHub] [spark] AmplabJenkins commented on issue #27786:
[SPARK-31034][CORE] ShuffleBlockFetcherIterator should always create
request for last block group
Posted by GitBox <gi...@apache.org>.
AmplabJenkins commented on issue #27786: [SPARK-31034][CORE] ShuffleBlockFetcherIterator should always create request for last block group
URL: https://github.com/apache/spark/pull/27786#issuecomment-594369875
Test PASSed.
Refer to this link for build results (access rights to CI server needed):
https://amplab.cs.berkeley.edu/jenkins//job/SparkPullRequestBuilder-K8s/24025/
Test PASSed.
----------------------------------------------------------------
This is an automated message from the Apache Git Service.
To respond to the message, please log on to GitHub and use the
URL above to go to the specific comment.
For queries about this service, please contact Infrastructure at:
users@infra.apache.org
With regards,
Apache Git Services
---------------------------------------------------------------------
To unsubscribe, e-mail: reviews-unsubscribe@spark.apache.org
For additional commands, e-mail: reviews-help@spark.apache.org
[GitHub] [spark] cloud-fan closed pull request #27786: [SPARK-31034][CORE]
ShuffleBlockFetcherIterator should always create request for last block group
Posted by GitBox <gi...@apache.org>.
cloud-fan closed pull request #27786: [SPARK-31034][CORE] ShuffleBlockFetcherIterator should always create request for last block group
URL: https://github.com/apache/spark/pull/27786
----------------------------------------------------------------
This is an automated message from the Apache Git Service.
To respond to the message, please log on to GitHub and use the
URL above to go to the specific comment.
For queries about this service, please contact Infrastructure at:
users@infra.apache.org
With regards,
Apache Git Services
---------------------------------------------------------------------
To unsubscribe, e-mail: reviews-unsubscribe@spark.apache.org
For additional commands, e-mail: reviews-help@spark.apache.org
[GitHub] [spark] Ngone51 commented on issue #27786: [SPARK-31034][CORE]
ShuffleBlockFetcherIterator should always create request for last block group
Posted by GitBox <gi...@apache.org>.
Ngone51 commented on issue #27786: [SPARK-31034][CORE] ShuffleBlockFetcherIterator should always create request for last block group
URL: https://github.com/apache/spark/pull/27786#issuecomment-595277915
thanks all!
----------------------------------------------------------------
This is an automated message from the Apache Git Service.
To respond to the message, please log on to GitHub and use the
URL above to go to the specific comment.
For queries about this service, please contact Infrastructure at:
users@infra.apache.org
With regards,
Apache Git Services
---------------------------------------------------------------------
To unsubscribe, e-mail: reviews-unsubscribe@spark.apache.org
For additional commands, e-mail: reviews-help@spark.apache.org
[GitHub] [spark] SparkQA commented on issue #27786: [SPARK-31034][CORE]
ShuffleBlockFetcherIterator should always create request for last block group
Posted by GitBox <gi...@apache.org>.
SparkQA commented on issue #27786: [SPARK-31034][CORE] ShuffleBlockFetcherIterator should always create request for last block group
URL: https://github.com/apache/spark/pull/27786#issuecomment-594481335
**[Test build #119294 has finished](https://amplab.cs.berkeley.edu/jenkins/job/SparkPullRequestBuilder/119294/testReport)** for PR 27786 at commit [`778be33`](https://github.com/apache/spark/commit/778be33d71cc70fbff5bb635e3d397ff15981a19).
* This patch **fails Spark unit tests**.
* This patch merges cleanly.
* This patch adds no public classes.
----------------------------------------------------------------
This is an automated message from the Apache Git Service.
To respond to the message, please log on to GitHub and use the
URL above to go to the specific comment.
For queries about this service, please contact Infrastructure at:
users@infra.apache.org
With regards,
Apache Git Services
---------------------------------------------------------------------
To unsubscribe, e-mail: reviews-unsubscribe@spark.apache.org
For additional commands, e-mail: reviews-help@spark.apache.org
[GitHub] [spark] AmplabJenkins removed a comment on issue #27786:
[SPARK-31034][CORE] ShuffleBlockFetcherIterator should always create
request for last block group
Posted by GitBox <gi...@apache.org>.
AmplabJenkins removed a comment on issue #27786: [SPARK-31034][CORE] ShuffleBlockFetcherIterator should always create request for last block group
URL: https://github.com/apache/spark/pull/27786#issuecomment-594632953
Merged build finished. Test PASSed.
----------------------------------------------------------------
This is an automated message from the Apache Git Service.
To respond to the message, please log on to GitHub and use the
URL above to go to the specific comment.
For queries about this service, please contact Infrastructure at:
users@infra.apache.org
With regards,
Apache Git Services
---------------------------------------------------------------------
To unsubscribe, e-mail: reviews-unsubscribe@spark.apache.org
For additional commands, e-mail: reviews-help@spark.apache.org
[GitHub] [spark] SparkQA commented on issue #27786: [SPARK-31034][CORE]
ShuffleBlockFetcherIterator should always create request for last block group
Posted by GitBox <gi...@apache.org>.
SparkQA commented on issue #27786: [SPARK-31034][CORE] ShuffleBlockFetcherIterator should always create request for last block group
URL: https://github.com/apache/spark/pull/27786#issuecomment-594400454
**[Test build #119294 has started](https://amplab.cs.berkeley.edu/jenkins/job/SparkPullRequestBuilder/119294/testReport)** for PR 27786 at commit [`778be33`](https://github.com/apache/spark/commit/778be33d71cc70fbff5bb635e3d397ff15981a19).
----------------------------------------------------------------
This is an automated message from the Apache Git Service.
To respond to the message, please log on to GitHub and use the
URL above to go to the specific comment.
For queries about this service, please contact Infrastructure at:
users@infra.apache.org
With regards,
Apache Git Services
---------------------------------------------------------------------
To unsubscribe, e-mail: reviews-unsubscribe@spark.apache.org
For additional commands, e-mail: reviews-help@spark.apache.org
[GitHub] [spark] Ngone51 commented on a change in pull request #27786:
[SPARK-31034][CORE] ShuffleBlockFetcherIterator should always create
request for last block group
Posted by GitBox <gi...@apache.org>.
Ngone51 commented on a change in pull request #27786: [SPARK-31034][CORE] ShuffleBlockFetcherIterator should always create request for last block group
URL: https://github.com/apache/spark/pull/27786#discussion_r387527734
##########
File path: core/src/test/scala/org/apache/spark/storage/ShuffleBlockFetcherIteratorSuite.scala
##########
@@ -341,32 +341,84 @@ class ShuffleBlockFetcherIteratorSuite extends SparkFunSuite with PrivateMethodT
assert(blockManager.hostLocalDirManager.get.getCachedHostLocalDirs().size === 1)
}
- test("fetch continuous blocks in batch respects maxSize and maxBlocks") {
+ test("fetch continuous blocks in batch should respect maxBytesInFlight") {
val blockManager = mock(classOf[BlockManager])
val localBmId = BlockManagerId("test-client", "test-local-host", 1)
doReturn(localBmId).when(blockManager).blockManagerId
// Make sure remote blocks would return the merged block
- val remoteBmId = BlockManagerId("test-client-1", "test-client-1", 2)
- val remoteBlocks = Seq[BlockId](
+ val remoteBmId1 = BlockManagerId("test-client-1", "test-client-1", 1)
+ val remoteBmId2 = BlockManagerId("test-client-2", "test-client-2", 2)
+ val remoteBlocks1 = (0 until 15).map(ShuffleBlockId(0, 3, _))
+ val remoteBlocks2 = Seq[BlockId](ShuffleBlockId(0, 4, 0), ShuffleBlockId(0, 4, 1))
+ val mergedRemoteBlocks = Map[BlockId, ManagedBuffer](
+ ShuffleBlockBatchId(0, 3, 0, 3) -> createMockManagedBuffer(),
+ ShuffleBlockBatchId(0, 3, 3, 6) -> createMockManagedBuffer(),
+ ShuffleBlockBatchId(0, 3, 6, 9) -> createMockManagedBuffer(),
+ ShuffleBlockBatchId(0, 3, 9, 12) -> createMockManagedBuffer(),
+ ShuffleBlockBatchId(0, 3, 12, 15) -> createMockManagedBuffer(),
+ ShuffleBlockBatchId(0, 4, 0, 2) -> createMockManagedBuffer())
+ val transfer = createMockTransfer(mergedRemoteBlocks)
+
+ val blocksByAddress = Seq[(BlockManagerId, Seq[(BlockId, Long, Int)])](
+ (remoteBmId1, remoteBlocks1.map(blockId => (blockId, 100L, 1))),
+ (remoteBmId2, remoteBlocks2.map(blockId => (blockId, 100L, 1)))).toIterator
+
+ val taskContext = TaskContext.empty()
+ val metrics = taskContext.taskMetrics.createTempShuffleReadMetrics()
+ val iterator = new ShuffleBlockFetcherIterator(
+ taskContext,
+ transfer,
+ blockManager,
+ blocksByAddress,
+ (_, in) => in,
+ 1500,
+ Int.MaxValue,
+ Int.MaxValue,
+ Int.MaxValue,
+ true,
+ false,
+ metrics,
+ true)
+
+ var numResults = 0
+ // After initialize(), there will be 6 FetchRequests, and the each of the first 5
+ // includes 3 merged blocks and the last one has 1 merged block. So, only the
Review comment:
Yes, it's shuffle blocks in this case. But it seems inconsistent with comment in the below test....I need reword it.
----------------------------------------------------------------
This is an automated message from the Apache Git Service.
To respond to the message, please log on to GitHub and use the
URL above to go to the specific comment.
For queries about this service, please contact Infrastructure at:
users@infra.apache.org
With regards,
Apache Git Services
---------------------------------------------------------------------
To unsubscribe, e-mail: reviews-unsubscribe@spark.apache.org
For additional commands, e-mail: reviews-help@spark.apache.org
[GitHub] [spark] cloud-fan commented on a change in pull request #27786:
[SPARK-31034][CORE] ShuffleBlockFetcherIterator should always create
request for last block group
Posted by GitBox <gi...@apache.org>.
cloud-fan commented on a change in pull request #27786: [SPARK-31034][CORE] ShuffleBlockFetcherIterator should always create request for last block group
URL: https://github.com/apache/spark/pull/27786#discussion_r387524638
##########
File path: core/src/test/scala/org/apache/spark/storage/ShuffleBlockFetcherIteratorSuite.scala
##########
@@ -341,32 +341,84 @@ class ShuffleBlockFetcherIteratorSuite extends SparkFunSuite with PrivateMethodT
assert(blockManager.hostLocalDirManager.get.getCachedHostLocalDirs().size === 1)
}
- test("fetch continuous blocks in batch respects maxSize and maxBlocks") {
+ test("fetch continuous blocks in batch should respect maxBytesInFlight") {
val blockManager = mock(classOf[BlockManager])
val localBmId = BlockManagerId("test-client", "test-local-host", 1)
doReturn(localBmId).when(blockManager).blockManagerId
// Make sure remote blocks would return the merged block
- val remoteBmId = BlockManagerId("test-client-1", "test-client-1", 2)
- val remoteBlocks = Seq[BlockId](
+ val remoteBmId1 = BlockManagerId("test-client-1", "test-client-1", 1)
+ val remoteBmId2 = BlockManagerId("test-client-2", "test-client-2", 2)
+ val remoteBlocks1 = (0 until 15).map(ShuffleBlockId(0, 3, _))
+ val remoteBlocks2 = Seq[BlockId](ShuffleBlockId(0, 4, 0), ShuffleBlockId(0, 4, 1))
+ val mergedRemoteBlocks = Map[BlockId, ManagedBuffer](
+ ShuffleBlockBatchId(0, 3, 0, 3) -> createMockManagedBuffer(),
+ ShuffleBlockBatchId(0, 3, 3, 6) -> createMockManagedBuffer(),
+ ShuffleBlockBatchId(0, 3, 6, 9) -> createMockManagedBuffer(),
+ ShuffleBlockBatchId(0, 3, 9, 12) -> createMockManagedBuffer(),
+ ShuffleBlockBatchId(0, 3, 12, 15) -> createMockManagedBuffer(),
+ ShuffleBlockBatchId(0, 4, 0, 2) -> createMockManagedBuffer())
+ val transfer = createMockTransfer(mergedRemoteBlocks)
+
+ val blocksByAddress = Seq[(BlockManagerId, Seq[(BlockId, Long, Int)])](
+ (remoteBmId1, remoteBlocks1.map(blockId => (blockId, 100L, 1))),
+ (remoteBmId2, remoteBlocks2.map(blockId => (blockId, 100L, 1)))).toIterator
+
+ val taskContext = TaskContext.empty()
+ val metrics = taskContext.taskMetrics.createTempShuffleReadMetrics()
+ val iterator = new ShuffleBlockFetcherIterator(
+ taskContext,
+ transfer,
+ blockManager,
+ blocksByAddress,
+ (_, in) => in,
+ 1500,
+ Int.MaxValue,
+ Int.MaxValue,
+ Int.MaxValue,
+ true,
+ false,
+ metrics,
+ true)
+
+ var numResults = 0
+ // After initialize(), there will be 6 FetchRequests, and the each of the first 5
+ // includes 3 merged blocks and the last one has 1 merged block. So, only the
Review comment:
or do you mean shuffle blocks?
----------------------------------------------------------------
This is an automated message from the Apache Git Service.
To respond to the message, please log on to GitHub and use the
URL above to go to the specific comment.
For queries about this service, please contact Infrastructure at:
users@infra.apache.org
With regards,
Apache Git Services
---------------------------------------------------------------------
To unsubscribe, e-mail: reviews-unsubscribe@spark.apache.org
For additional commands, e-mail: reviews-help@spark.apache.org
[GitHub] [spark] AmplabJenkins commented on issue #27786:
[SPARK-31034][CORE] ShuffleBlockFetcherIterator should always create
request for last block group
Posted by GitBox <gi...@apache.org>.
AmplabJenkins commented on issue #27786: [SPARK-31034][CORE] ShuffleBlockFetcherIterator should always create request for last block group
URL: https://github.com/apache/spark/pull/27786#issuecomment-594481796
Test FAILed.
Refer to this link for build results (access rights to CI server needed):
https://amplab.cs.berkeley.edu/jenkins//job/SparkPullRequestBuilder/119294/
Test FAILed.
----------------------------------------------------------------
This is an automated message from the Apache Git Service.
To respond to the message, please log on to GitHub and use the
URL above to go to the specific comment.
For queries about this service, please contact Infrastructure at:
users@infra.apache.org
With regards,
Apache Git Services
---------------------------------------------------------------------
To unsubscribe, e-mail: reviews-unsubscribe@spark.apache.org
For additional commands, e-mail: reviews-help@spark.apache.org
[GitHub] [spark] Ngone51 commented on a change in pull request #27786:
[SPARK-31034][CORE] ShuffleBlockFetcherIterator should always create
request for last block group
Posted by GitBox <gi...@apache.org>.
Ngone51 commented on a change in pull request #27786: [SPARK-31034][CORE] ShuffleBlockFetcherIterator should always create request for last block group
URL: https://github.com/apache/spark/pull/27786#discussion_r387528676
##########
File path: core/src/test/scala/org/apache/spark/storage/ShuffleBlockFetcherIteratorSuite.scala
##########
@@ -341,32 +341,84 @@ class ShuffleBlockFetcherIteratorSuite extends SparkFunSuite with PrivateMethodT
assert(blockManager.hostLocalDirManager.get.getCachedHostLocalDirs().size === 1)
}
- test("fetch continuous blocks in batch respects maxSize and maxBlocks") {
+ test("fetch continuous blocks in batch should respect maxBytesInFlight") {
val blockManager = mock(classOf[BlockManager])
val localBmId = BlockManagerId("test-client", "test-local-host", 1)
doReturn(localBmId).when(blockManager).blockManagerId
// Make sure remote blocks would return the merged block
- val remoteBmId = BlockManagerId("test-client-1", "test-client-1", 2)
- val remoteBlocks = Seq[BlockId](
+ val remoteBmId1 = BlockManagerId("test-client-1", "test-client-1", 1)
+ val remoteBmId2 = BlockManagerId("test-client-2", "test-client-2", 2)
+ val remoteBlocks1 = (0 until 15).map(ShuffleBlockId(0, 3, _))
+ val remoteBlocks2 = Seq[BlockId](ShuffleBlockId(0, 4, 0), ShuffleBlockId(0, 4, 1))
+ val mergedRemoteBlocks = Map[BlockId, ManagedBuffer](
+ ShuffleBlockBatchId(0, 3, 0, 3) -> createMockManagedBuffer(),
+ ShuffleBlockBatchId(0, 3, 3, 6) -> createMockManagedBuffer(),
+ ShuffleBlockBatchId(0, 3, 6, 9) -> createMockManagedBuffer(),
+ ShuffleBlockBatchId(0, 3, 9, 12) -> createMockManagedBuffer(),
+ ShuffleBlockBatchId(0, 3, 12, 15) -> createMockManagedBuffer(),
+ ShuffleBlockBatchId(0, 4, 0, 2) -> createMockManagedBuffer())
+ val transfer = createMockTransfer(mergedRemoteBlocks)
+
+ val blocksByAddress = Seq[(BlockManagerId, Seq[(BlockId, Long, Int)])](
+ (remoteBmId1, remoteBlocks1.map(blockId => (blockId, 100L, 1))),
+ (remoteBmId2, remoteBlocks2.map(blockId => (blockId, 100L, 1)))).toIterator
+
+ val taskContext = TaskContext.empty()
+ val metrics = taskContext.taskMetrics.createTempShuffleReadMetrics()
+ val iterator = new ShuffleBlockFetcherIterator(
+ taskContext,
+ transfer,
+ blockManager,
+ blocksByAddress,
+ (_, in) => in,
+ 1500,
+ Int.MaxValue,
+ Int.MaxValue,
+ Int.MaxValue,
+ true,
+ false,
+ metrics,
+ true)
+
+ var numResults = 0
+ // After initialize(), there will be 6 FetchRequests, and the each of the first 5
+ // includes 3 merged blocks and the last one has 1 merged block. So, only the
Review comment:
note: `3 merged blocks` -> `3 shuffle block(not batch)`
----------------------------------------------------------------
This is an automated message from the Apache Git Service.
To respond to the message, please log on to GitHub and use the
URL above to go to the specific comment.
For queries about this service, please contact Infrastructure at:
users@infra.apache.org
With regards,
Apache Git Services
---------------------------------------------------------------------
To unsubscribe, e-mail: reviews-unsubscribe@spark.apache.org
For additional commands, e-mail: reviews-help@spark.apache.org
[GitHub] [spark] AmplabJenkins removed a comment on issue #27786:
[SPARK-31034][CORE] ShuffleBlockFetcherIterator should always create
request for last block group
Posted by GitBox <gi...@apache.org>.
AmplabJenkins removed a comment on issue #27786: [SPARK-31034][CORE] ShuffleBlockFetcherIterator should always create request for last block group
URL: https://github.com/apache/spark/pull/27786#issuecomment-594539208
Merged build finished. Test PASSed.
----------------------------------------------------------------
This is an automated message from the Apache Git Service.
To respond to the message, please log on to GitHub and use the
URL above to go to the specific comment.
For queries about this service, please contact Infrastructure at:
users@infra.apache.org
With regards,
Apache Git Services
---------------------------------------------------------------------
To unsubscribe, e-mail: reviews-unsubscribe@spark.apache.org
For additional commands, e-mail: reviews-help@spark.apache.org
[GitHub] [spark] AmplabJenkins commented on issue #27786:
[SPARK-31034][CORE] ShuffleBlockFetcherIterator should always create
request for last block group
Posted by GitBox <gi...@apache.org>.
AmplabJenkins commented on issue #27786: [SPARK-31034][CORE] ShuffleBlockFetcherIterator should always create request for last block group
URL: https://github.com/apache/spark/pull/27786#issuecomment-594539216
Test PASSed.
Refer to this link for build results (access rights to CI server needed):
https://amplab.cs.berkeley.edu/jenkins//job/SparkPullRequestBuilder-K8s/24048/
Test PASSed.
----------------------------------------------------------------
This is an automated message from the Apache Git Service.
To respond to the message, please log on to GitHub and use the
URL above to go to the specific comment.
For queries about this service, please contact Infrastructure at:
users@infra.apache.org
With regards,
Apache Git Services
---------------------------------------------------------------------
To unsubscribe, e-mail: reviews-unsubscribe@spark.apache.org
For additional commands, e-mail: reviews-help@spark.apache.org
[GitHub] [spark] AmplabJenkins commented on issue #27786:
[SPARK-31034][CORE] ShuffleBlockFetcherIterator should always create
request for last block group
Posted by GitBox <gi...@apache.org>.
AmplabJenkins commented on issue #27786: [SPARK-31034][CORE] ShuffleBlockFetcherIterator should always create request for last block group
URL: https://github.com/apache/spark/pull/27786#issuecomment-594387558
Test PASSed.
Refer to this link for build results (access rights to CI server needed):
https://amplab.cs.berkeley.edu/jenkins//job/SparkPullRequestBuilder-K8s/24027/
Test PASSed.
----------------------------------------------------------------
This is an automated message from the Apache Git Service.
To respond to the message, please log on to GitHub and use the
URL above to go to the specific comment.
For queries about this service, please contact Infrastructure at:
users@infra.apache.org
With regards,
Apache Git Services
---------------------------------------------------------------------
To unsubscribe, e-mail: reviews-unsubscribe@spark.apache.org
For additional commands, e-mail: reviews-help@spark.apache.org
[GitHub] [spark] AmplabJenkins commented on issue #27786:
[SPARK-31034][CORE] ShuffleBlockFetcherIterator should always create
request for last block group
Posted by GitBox <gi...@apache.org>.
AmplabJenkins commented on issue #27786: [SPARK-31034][CORE] ShuffleBlockFetcherIterator should always create request for last block group
URL: https://github.com/apache/spark/pull/27786#issuecomment-594791562
Merged build finished. Test PASSed.
----------------------------------------------------------------
This is an automated message from the Apache Git Service.
To respond to the message, please log on to GitHub and use the
URL above to go to the specific comment.
For queries about this service, please contact Infrastructure at:
users@infra.apache.org
With regards,
Apache Git Services
---------------------------------------------------------------------
To unsubscribe, e-mail: reviews-unsubscribe@spark.apache.org
For additional commands, e-mail: reviews-help@spark.apache.org
[GitHub] [spark] AmplabJenkins commented on issue #27786:
[SPARK-31034][CORE] ShuffleBlockFetcherIterator should always create
request for last block group
Posted by GitBox <gi...@apache.org>.
AmplabJenkins commented on issue #27786: [SPARK-31034][CORE] ShuffleBlockFetcherIterator should always create request for last block group
URL: https://github.com/apache/spark/pull/27786#issuecomment-594369869
Merged build finished. Test PASSed.
----------------------------------------------------------------
This is an automated message from the Apache Git Service.
To respond to the message, please log on to GitHub and use the
URL above to go to the specific comment.
For queries about this service, please contact Infrastructure at:
users@infra.apache.org
With regards,
Apache Git Services
---------------------------------------------------------------------
To unsubscribe, e-mail: reviews-unsubscribe@spark.apache.org
For additional commands, e-mail: reviews-help@spark.apache.org
[GitHub] [spark] AmplabJenkins removed a comment on issue #27786:
[SPARK-31034][CORE] ShuffleBlockFetcherIterator should always create
request for last block group
Posted by GitBox <gi...@apache.org>.
AmplabJenkins removed a comment on issue #27786: [SPARK-31034][CORE] ShuffleBlockFetcherIterator should always create request for last block group
URL: https://github.com/apache/spark/pull/27786#issuecomment-594400920
Merged build finished. Test PASSed.
----------------------------------------------------------------
This is an automated message from the Apache Git Service.
To respond to the message, please log on to GitHub and use the
URL above to go to the specific comment.
For queries about this service, please contact Infrastructure at:
users@infra.apache.org
With regards,
Apache Git Services
---------------------------------------------------------------------
To unsubscribe, e-mail: reviews-unsubscribe@spark.apache.org
For additional commands, e-mail: reviews-help@spark.apache.org
[GitHub] [spark] AmplabJenkins commented on issue #27786:
[SPARK-31034][CORE] ShuffleBlockFetcherIterator should always create
request for last block group
Posted by GitBox <gi...@apache.org>.
AmplabJenkins commented on issue #27786: [SPARK-31034][CORE] ShuffleBlockFetcherIterator should always create request for last block group
URL: https://github.com/apache/spark/pull/27786#issuecomment-594486487
Merged build finished. Test PASSed.
----------------------------------------------------------------
This is an automated message from the Apache Git Service.
To respond to the message, please log on to GitHub and use the
URL above to go to the specific comment.
For queries about this service, please contact Infrastructure at:
users@infra.apache.org
With regards,
Apache Git Services
---------------------------------------------------------------------
To unsubscribe, e-mail: reviews-unsubscribe@spark.apache.org
For additional commands, e-mail: reviews-help@spark.apache.org
[GitHub] [spark] AmplabJenkins commented on issue #27786:
[SPARK-31034][CORE] ShuffleBlockFetcherIterator should always create
request for last block group
Posted by GitBox <gi...@apache.org>.
AmplabJenkins commented on issue #27786: [SPARK-31034][CORE] ShuffleBlockFetcherIterator should always create request for last block group
URL: https://github.com/apache/spark/pull/27786#issuecomment-594396449
Test PASSed.
Refer to this link for build results (access rights to CI server needed):
https://amplab.cs.berkeley.edu/jenkins//job/SparkPullRequestBuilder-K8s/24034/
Test PASSed.
----------------------------------------------------------------
This is an automated message from the Apache Git Service.
To respond to the message, please log on to GitHub and use the
URL above to go to the specific comment.
For queries about this service, please contact Infrastructure at:
users@infra.apache.org
With regards,
Apache Git Services
---------------------------------------------------------------------
To unsubscribe, e-mail: reviews-unsubscribe@spark.apache.org
For additional commands, e-mail: reviews-help@spark.apache.org
[GitHub] [spark] Ngone51 commented on issue #27786: [SPARK-31034][CORE]
ShuffleBlockFetcherIterator should always create request for last block group
Posted by GitBox <gi...@apache.org>.
Ngone51 commented on issue #27786: [SPARK-31034][CORE] ShuffleBlockFetcherIterator should always create request for last block group
URL: https://github.com/apache/spark/pull/27786#issuecomment-594367935
cc @cloud-fan @xuanyuanking
----------------------------------------------------------------
This is an automated message from the Apache Git Service.
To respond to the message, please log on to GitHub and use the
URL above to go to the specific comment.
For queries about this service, please contact Infrastructure at:
users@infra.apache.org
With regards,
Apache Git Services
---------------------------------------------------------------------
To unsubscribe, e-mail: reviews-unsubscribe@spark.apache.org
For additional commands, e-mail: reviews-help@spark.apache.org
[GitHub] [spark] SparkQA removed a comment on issue #27786:
[SPARK-31034][CORE] ShuffleBlockFetcherIterator should always create
request for last block group
Posted by GitBox <gi...@apache.org>.
SparkQA removed a comment on issue #27786: [SPARK-31034][CORE] ShuffleBlockFetcherIterator should always create request for last block group
URL: https://github.com/apache/spark/pull/27786#issuecomment-594369497
**[Test build #119285 has started](https://amplab.cs.berkeley.edu/jenkins/job/SparkPullRequestBuilder/119285/testReport)** for PR 27786 at commit [`fc36eb1`](https://github.com/apache/spark/commit/fc36eb10856943fbeb6b0d099d130041d587edc6).
----------------------------------------------------------------
This is an automated message from the Apache Git Service.
To respond to the message, please log on to GitHub and use the
URL above to go to the specific comment.
For queries about this service, please contact Infrastructure at:
users@infra.apache.org
With regards,
Apache Git Services
---------------------------------------------------------------------
To unsubscribe, e-mail: reviews-unsubscribe@spark.apache.org
For additional commands, e-mail: reviews-help@spark.apache.org
[GitHub] [spark] AmplabJenkins commented on issue #27786:
[SPARK-31034][CORE] ShuffleBlockFetcherIterator should always create
request for last block group
Posted by GitBox <gi...@apache.org>.
AmplabJenkins commented on issue #27786: [SPARK-31034][CORE] ShuffleBlockFetcherIterator should always create request for last block group
URL: https://github.com/apache/spark/pull/27786#issuecomment-594387549
Merged build finished. Test PASSed.
----------------------------------------------------------------
This is an automated message from the Apache Git Service.
To respond to the message, please log on to GitHub and use the
URL above to go to the specific comment.
For queries about this service, please contact Infrastructure at:
users@infra.apache.org
With regards,
Apache Git Services
---------------------------------------------------------------------
To unsubscribe, e-mail: reviews-unsubscribe@spark.apache.org
For additional commands, e-mail: reviews-help@spark.apache.org
[GitHub] [spark] SparkQA commented on issue #27786: [SPARK-31034][CORE]
ShuffleBlockFetcherIterator should always create request for last block group
Posted by GitBox <gi...@apache.org>.
SparkQA commented on issue #27786: [SPARK-31034][CORE] ShuffleBlockFetcherIterator should always create request for last block group
URL: https://github.com/apache/spark/pull/27786#issuecomment-594485405
**[Test build #119287 has finished](https://amplab.cs.berkeley.edu/jenkins/job/SparkPullRequestBuilder/119287/testReport)** for PR 27786 at commit [`28df4ab`](https://github.com/apache/spark/commit/28df4ab6d6c8c68012ec95492fd56c05bd37463a).
* This patch passes all tests.
* This patch merges cleanly.
* This patch adds no public classes.
----------------------------------------------------------------
This is an automated message from the Apache Git Service.
To respond to the message, please log on to GitHub and use the
URL above to go to the specific comment.
For queries about this service, please contact Infrastructure at:
users@infra.apache.org
With regards,
Apache Git Services
---------------------------------------------------------------------
To unsubscribe, e-mail: reviews-unsubscribe@spark.apache.org
For additional commands, e-mail: reviews-help@spark.apache.org
[GitHub] [spark] SparkQA commented on issue #27786: [SPARK-31034][CORE]
ShuffleBlockFetcherIterator should always create request for last block group
Posted by GitBox <gi...@apache.org>.
SparkQA commented on issue #27786: [SPARK-31034][CORE] ShuffleBlockFetcherIterator should always create request for last block group
URL: https://github.com/apache/spark/pull/27786#issuecomment-594369497
**[Test build #119285 has started](https://amplab.cs.berkeley.edu/jenkins/job/SparkPullRequestBuilder/119285/testReport)** for PR 27786 at commit [`fc36eb1`](https://github.com/apache/spark/commit/fc36eb10856943fbeb6b0d099d130041d587edc6).
----------------------------------------------------------------
This is an automated message from the Apache Git Service.
To respond to the message, please log on to GitHub and use the
URL above to go to the specific comment.
For queries about this service, please contact Infrastructure at:
users@infra.apache.org
With regards,
Apache Git Services
---------------------------------------------------------------------
To unsubscribe, e-mail: reviews-unsubscribe@spark.apache.org
For additional commands, e-mail: reviews-help@spark.apache.org
[GitHub] [spark] AmplabJenkins removed a comment on issue #27786:
[SPARK-31034][CORE] ShuffleBlockFetcherIterator should always create
request for last block group
Posted by GitBox <gi...@apache.org>.
AmplabJenkins removed a comment on issue #27786: [SPARK-31034][CORE] ShuffleBlockFetcherIterator should always create request for last block group
URL: https://github.com/apache/spark/pull/27786#issuecomment-594369869
Merged build finished. Test PASSed.
----------------------------------------------------------------
This is an automated message from the Apache Git Service.
To respond to the message, please log on to GitHub and use the
URL above to go to the specific comment.
For queries about this service, please contact Infrastructure at:
users@infra.apache.org
With regards,
Apache Git Services
---------------------------------------------------------------------
To unsubscribe, e-mail: reviews-unsubscribe@spark.apache.org
For additional commands, e-mail: reviews-help@spark.apache.org
[GitHub] [spark] SparkQA removed a comment on issue #27786:
[SPARK-31034][CORE] ShuffleBlockFetcherIterator should always create
request for last block group
Posted by GitBox <gi...@apache.org>.
SparkQA removed a comment on issue #27786: [SPARK-31034][CORE] ShuffleBlockFetcherIterator should always create request for last block group
URL: https://github.com/apache/spark/pull/27786#issuecomment-594632225
**[Test build #119319 has started](https://amplab.cs.berkeley.edu/jenkins/job/SparkPullRequestBuilder/119319/testReport)** for PR 27786 at commit [`dc94365`](https://github.com/apache/spark/commit/dc9436573976e9ba227836dc7e1ce271cd91c7fb).
----------------------------------------------------------------
This is an automated message from the Apache Git Service.
To respond to the message, please log on to GitHub and use the
URL above to go to the specific comment.
For queries about this service, please contact Infrastructure at:
users@infra.apache.org
With regards,
Apache Git Services
---------------------------------------------------------------------
To unsubscribe, e-mail: reviews-unsubscribe@spark.apache.org
For additional commands, e-mail: reviews-help@spark.apache.org
[GitHub] [spark] AmplabJenkins removed a comment on issue #27786:
[SPARK-31034][CORE] ShuffleBlockFetcherIterator should always create
request for last block group
Posted by GitBox <gi...@apache.org>.
AmplabJenkins removed a comment on issue #27786: [SPARK-31034][CORE] ShuffleBlockFetcherIterator should always create request for last block group
URL: https://github.com/apache/spark/pull/27786#issuecomment-594481796
Test FAILed.
Refer to this link for build results (access rights to CI server needed):
https://amplab.cs.berkeley.edu/jenkins//job/SparkPullRequestBuilder/119294/
Test FAILed.
----------------------------------------------------------------
This is an automated message from the Apache Git Service.
To respond to the message, please log on to GitHub and use the
URL above to go to the specific comment.
For queries about this service, please contact Infrastructure at:
users@infra.apache.org
With regards,
Apache Git Services
---------------------------------------------------------------------
To unsubscribe, e-mail: reviews-unsubscribe@spark.apache.org
For additional commands, e-mail: reviews-help@spark.apache.org
[GitHub] [spark] AmplabJenkins removed a comment on issue #27786:
[SPARK-31034][CORE] ShuffleBlockFetcherIterator should always create
request for last block group
Posted by GitBox <gi...@apache.org>.
AmplabJenkins removed a comment on issue #27786: [SPARK-31034][CORE] ShuffleBlockFetcherIterator should always create request for last block group
URL: https://github.com/apache/spark/pull/27786#issuecomment-594400926
Test PASSed.
Refer to this link for build results (access rights to CI server needed):
https://amplab.cs.berkeley.edu/jenkins//job/SparkPullRequestBuilder-K8s/24035/
Test PASSed.
----------------------------------------------------------------
This is an automated message from the Apache Git Service.
To respond to the message, please log on to GitHub and use the
URL above to go to the specific comment.
For queries about this service, please contact Infrastructure at:
users@infra.apache.org
With regards,
Apache Git Services
---------------------------------------------------------------------
To unsubscribe, e-mail: reviews-unsubscribe@spark.apache.org
For additional commands, e-mail: reviews-help@spark.apache.org
[GitHub] [spark] SparkQA commented on issue #27786: [SPARK-31034][CORE]
ShuffleBlockFetcherIterator should always create request for last block group
Posted by GitBox <gi...@apache.org>.
SparkQA commented on issue #27786: [SPARK-31034][CORE] ShuffleBlockFetcherIterator should always create request for last block group
URL: https://github.com/apache/spark/pull/27786#issuecomment-594632225
**[Test build #119319 has started](https://amplab.cs.berkeley.edu/jenkins/job/SparkPullRequestBuilder/119319/testReport)** for PR 27786 at commit [`dc94365`](https://github.com/apache/spark/commit/dc9436573976e9ba227836dc7e1ce271cd91c7fb).
----------------------------------------------------------------
This is an automated message from the Apache Git Service.
To respond to the message, please log on to GitHub and use the
URL above to go to the specific comment.
For queries about this service, please contact Infrastructure at:
users@infra.apache.org
With regards,
Apache Git Services
---------------------------------------------------------------------
To unsubscribe, e-mail: reviews-unsubscribe@spark.apache.org
For additional commands, e-mail: reviews-help@spark.apache.org
[GitHub] [spark] AmplabJenkins commented on issue #27786:
[SPARK-31034][CORE] ShuffleBlockFetcherIterator should always create
request for last block group
Posted by GitBox <gi...@apache.org>.
AmplabJenkins commented on issue #27786: [SPARK-31034][CORE] ShuffleBlockFetcherIterator should always create request for last block group
URL: https://github.com/apache/spark/pull/27786#issuecomment-594400920
Merged build finished. Test PASSed.
----------------------------------------------------------------
This is an automated message from the Apache Git Service.
To respond to the message, please log on to GitHub and use the
URL above to go to the specific comment.
For queries about this service, please contact Infrastructure at:
users@infra.apache.org
With regards,
Apache Git Services
---------------------------------------------------------------------
To unsubscribe, e-mail: reviews-unsubscribe@spark.apache.org
For additional commands, e-mail: reviews-help@spark.apache.org
[GitHub] [spark] AmplabJenkins removed a comment on issue #27786:
[SPARK-31034][CORE] ShuffleBlockFetcherIterator should always create
request for last block group
Posted by GitBox <gi...@apache.org>.
AmplabJenkins removed a comment on issue #27786: [SPARK-31034][CORE] ShuffleBlockFetcherIterator should always create request for last block group
URL: https://github.com/apache/spark/pull/27786#issuecomment-594539216
Test PASSed.
Refer to this link for build results (access rights to CI server needed):
https://amplab.cs.berkeley.edu/jenkins//job/SparkPullRequestBuilder-K8s/24048/
Test PASSed.
----------------------------------------------------------------
This is an automated message from the Apache Git Service.
To respond to the message, please log on to GitHub and use the
URL above to go to the specific comment.
For queries about this service, please contact Infrastructure at:
users@infra.apache.org
With regards,
Apache Git Services
---------------------------------------------------------------------
To unsubscribe, e-mail: reviews-unsubscribe@spark.apache.org
For additional commands, e-mail: reviews-help@spark.apache.org
[GitHub] [spark] cloud-fan commented on a change in pull request #27786:
[SPARK-31034][CORE] ShuffleBlockFetcherIterator should always create
request for last block group
Posted by GitBox <gi...@apache.org>.
cloud-fan commented on a change in pull request #27786: [SPARK-31034][CORE] ShuffleBlockFetcherIterator should always create request for last block group
URL: https://github.com/apache/spark/pull/27786#discussion_r387497757
##########
File path: core/src/main/scala/org/apache/spark/storage/ShuffleBlockFetcherIterator.scala
##########
@@ -367,12 +367,12 @@ final class ShuffleBlockFetcherIterator(
// For batch fetch, the actual block in flight should count for merged block.
val mayExceedsMaxBlocks = !doBatchFetch && curBlocks.size >= maxBlocksInFlightPerAddress
if (curRequestSize >= targetRemoteRequestSize || mayExceedsMaxBlocks) {
- createFetchRequests()
+ createFetchRequests(true)
Review comment:
let's write down the parameter name.
----------------------------------------------------------------
This is an automated message from the Apache Git Service.
To respond to the message, please log on to GitHub and use the
URL above to go to the specific comment.
For queries about this service, please contact Infrastructure at:
users@infra.apache.org
With regards,
Apache Git Services
---------------------------------------------------------------------
To unsubscribe, e-mail: reviews-unsubscribe@spark.apache.org
For additional commands, e-mail: reviews-help@spark.apache.org
[GitHub] [spark] SparkQA commented on issue #27786: [SPARK-31034][CORE]
ShuffleBlockFetcherIterator should always create request for last block group
Posted by GitBox <gi...@apache.org>.
SparkQA commented on issue #27786: [SPARK-31034][CORE] ShuffleBlockFetcherIterator should always create request for last block group
URL: https://github.com/apache/spark/pull/27786#issuecomment-594543021
**[Test build #119308 has started](https://amplab.cs.berkeley.edu/jenkins/job/SparkPullRequestBuilder/119308/testReport)** for PR 27786 at commit [`6766c7c`](https://github.com/apache/spark/commit/6766c7c43bd2d22a25e099241a96d78825f63f72).
----------------------------------------------------------------
This is an automated message from the Apache Git Service.
To respond to the message, please log on to GitHub and use the
URL above to go to the specific comment.
For queries about this service, please contact Infrastructure at:
users@infra.apache.org
With regards,
Apache Git Services
---------------------------------------------------------------------
To unsubscribe, e-mail: reviews-unsubscribe@spark.apache.org
For additional commands, e-mail: reviews-help@spark.apache.org
[GitHub] [spark] AmplabJenkins removed a comment on issue #27786:
[SPARK-31034][CORE] ShuffleBlockFetcherIterator should always create
request for last block group
Posted by GitBox <gi...@apache.org>.
AmplabJenkins removed a comment on issue #27786: [SPARK-31034][CORE] ShuffleBlockFetcherIterator should always create request for last block group
URL: https://github.com/apache/spark/pull/27786#issuecomment-594380039
Test FAILed.
Refer to this link for build results (access rights to CI server needed):
https://amplab.cs.berkeley.edu/jenkins//job/SparkPullRequestBuilder/119285/
Test FAILed.
----------------------------------------------------------------
This is an automated message from the Apache Git Service.
To respond to the message, please log on to GitHub and use the
URL above to go to the specific comment.
For queries about this service, please contact Infrastructure at:
users@infra.apache.org
With regards,
Apache Git Services
---------------------------------------------------------------------
To unsubscribe, e-mail: reviews-unsubscribe@spark.apache.org
For additional commands, e-mail: reviews-help@spark.apache.org
[GitHub] [spark] cloud-fan commented on a change in pull request #27786:
[SPARK-31034][CORE] ShuffleBlockFetcherIterator should always create
request for last block group
Posted by GitBox <gi...@apache.org>.
cloud-fan commented on a change in pull request #27786: [SPARK-31034][CORE] ShuffleBlockFetcherIterator should always create request for last block group
URL: https://github.com/apache/spark/pull/27786#discussion_r387497646
##########
File path: core/src/main/scala/org/apache/spark/storage/ShuffleBlockFetcherIterator.scala
##########
@@ -339,14 +339,14 @@ final class ShuffleBlockFetcherIterator(
+ s"with ${blocks.size} blocks")
}
- def createFetchRequests(): Unit = {
+ def createFetchRequests(hasMore: Boolean): Unit = {
Review comment:
nit: `isLast`?
----------------------------------------------------------------
This is an automated message from the Apache Git Service.
To respond to the message, please log on to GitHub and use the
URL above to go to the specific comment.
For queries about this service, please contact Infrastructure at:
users@infra.apache.org
With regards,
Apache Git Services
---------------------------------------------------------------------
To unsubscribe, e-mail: reviews-unsubscribe@spark.apache.org
For additional commands, e-mail: reviews-help@spark.apache.org
[GitHub] [spark] AmplabJenkins removed a comment on issue #27786:
[SPARK-31034][CORE] ShuffleBlockFetcherIterator should always create
request for last block group
Posted by GitBox <gi...@apache.org>.
AmplabJenkins removed a comment on issue #27786: [SPARK-31034][CORE] ShuffleBlockFetcherIterator should always create request for last block group
URL: https://github.com/apache/spark/pull/27786#issuecomment-594387549
Merged build finished. Test PASSed.
----------------------------------------------------------------
This is an automated message from the Apache Git Service.
To respond to the message, please log on to GitHub and use the
URL above to go to the specific comment.
For queries about this service, please contact Infrastructure at:
users@infra.apache.org
With regards,
Apache Git Services
---------------------------------------------------------------------
To unsubscribe, e-mail: reviews-unsubscribe@spark.apache.org
For additional commands, e-mail: reviews-help@spark.apache.org
[GitHub] [spark] AmplabJenkins commented on issue #27786:
[SPARK-31034][CORE] ShuffleBlockFetcherIterator should always create
request for last block group
Posted by GitBox <gi...@apache.org>.
AmplabJenkins commented on issue #27786: [SPARK-31034][CORE] ShuffleBlockFetcherIterator should always create request for last block group
URL: https://github.com/apache/spark/pull/27786#issuecomment-594791573
Test PASSed.
Refer to this link for build results (access rights to CI server needed):
https://amplab.cs.berkeley.edu/jenkins//job/SparkPullRequestBuilder/119319/
Test PASSed.
----------------------------------------------------------------
This is an automated message from the Apache Git Service.
To respond to the message, please log on to GitHub and use the
URL above to go to the specific comment.
For queries about this service, please contact Infrastructure at:
users@infra.apache.org
With regards,
Apache Git Services
---------------------------------------------------------------------
To unsubscribe, e-mail: reviews-unsubscribe@spark.apache.org
For additional commands, e-mail: reviews-help@spark.apache.org
[GitHub] [spark] SparkQA commented on issue #27786: [SPARK-31034][CORE]
ShuffleBlockFetcherIterator should always create request for last block group
Posted by GitBox <gi...@apache.org>.
SparkQA commented on issue #27786: [SPARK-31034][CORE] ShuffleBlockFetcherIterator should always create request for last block group
URL: https://github.com/apache/spark/pull/27786#issuecomment-594379915
**[Test build #119285 has finished](https://amplab.cs.berkeley.edu/jenkins/job/SparkPullRequestBuilder/119285/testReport)** for PR 27786 at commit [`fc36eb1`](https://github.com/apache/spark/commit/fc36eb10856943fbeb6b0d099d130041d587edc6).
* This patch **fails due to an unknown error code, -9**.
* This patch merges cleanly.
* This patch adds no public classes.
----------------------------------------------------------------
This is an automated message from the Apache Git Service.
To respond to the message, please log on to GitHub and use the
URL above to go to the specific comment.
For queries about this service, please contact Infrastructure at:
users@infra.apache.org
With regards,
Apache Git Services
---------------------------------------------------------------------
To unsubscribe, e-mail: reviews-unsubscribe@spark.apache.org
For additional commands, e-mail: reviews-help@spark.apache.org
[GitHub] [spark] AmplabJenkins commented on issue #27786:
[SPARK-31034][CORE] ShuffleBlockFetcherIterator should always create
request for last block group
Posted by GitBox <gi...@apache.org>.
AmplabJenkins commented on issue #27786: [SPARK-31034][CORE] ShuffleBlockFetcherIterator should always create request for last block group
URL: https://github.com/apache/spark/pull/27786#issuecomment-594396436
Merged build finished. Test PASSed.
----------------------------------------------------------------
This is an automated message from the Apache Git Service.
To respond to the message, please log on to GitHub and use the
URL above to go to the specific comment.
For queries about this service, please contact Infrastructure at:
users@infra.apache.org
With regards,
Apache Git Services
---------------------------------------------------------------------
To unsubscribe, e-mail: reviews-unsubscribe@spark.apache.org
For additional commands, e-mail: reviews-help@spark.apache.org
[GitHub] [spark] SparkQA commented on issue #27786: [SPARK-31034][CORE]
ShuffleBlockFetcherIterator should always create request for last block group
Posted by GitBox <gi...@apache.org>.
SparkQA commented on issue #27786: [SPARK-31034][CORE] ShuffleBlockFetcherIterator should always create request for last block group
URL: https://github.com/apache/spark/pull/27786#issuecomment-594649777
**[Test build #119308 has finished](https://amplab.cs.berkeley.edu/jenkins/job/SparkPullRequestBuilder/119308/testReport)** for PR 27786 at commit [`6766c7c`](https://github.com/apache/spark/commit/6766c7c43bd2d22a25e099241a96d78825f63f72).
* This patch **fails Spark unit tests**.
* This patch merges cleanly.
* This patch adds no public classes.
----------------------------------------------------------------
This is an automated message from the Apache Git Service.
To respond to the message, please log on to GitHub and use the
URL above to go to the specific comment.
For queries about this service, please contact Infrastructure at:
users@infra.apache.org
With regards,
Apache Git Services
---------------------------------------------------------------------
To unsubscribe, e-mail: reviews-unsubscribe@spark.apache.org
For additional commands, e-mail: reviews-help@spark.apache.org
[GitHub] [spark] cloud-fan commented on a change in pull request #27786:
[SPARK-31034][CORE] ShuffleBlockFetcherIterator should always create
request for last block group
Posted by GitBox <gi...@apache.org>.
cloud-fan commented on a change in pull request #27786: [SPARK-31034][CORE] ShuffleBlockFetcherIterator should always create request for last block group
URL: https://github.com/apache/spark/pull/27786#discussion_r387524362
##########
File path: core/src/test/scala/org/apache/spark/storage/ShuffleBlockFetcherIteratorSuite.scala
##########
@@ -341,32 +341,84 @@ class ShuffleBlockFetcherIteratorSuite extends SparkFunSuite with PrivateMethodT
assert(blockManager.hostLocalDirManager.get.getCachedHostLocalDirs().size === 1)
}
- test("fetch continuous blocks in batch respects maxSize and maxBlocks") {
+ test("fetch continuous blocks in batch should respect maxBytesInFlight") {
val blockManager = mock(classOf[BlockManager])
val localBmId = BlockManagerId("test-client", "test-local-host", 1)
doReturn(localBmId).when(blockManager).blockManagerId
// Make sure remote blocks would return the merged block
- val remoteBmId = BlockManagerId("test-client-1", "test-client-1", 2)
- val remoteBlocks = Seq[BlockId](
+ val remoteBmId1 = BlockManagerId("test-client-1", "test-client-1", 1)
+ val remoteBmId2 = BlockManagerId("test-client-2", "test-client-2", 2)
+ val remoteBlocks1 = (0 until 15).map(ShuffleBlockId(0, 3, _))
+ val remoteBlocks2 = Seq[BlockId](ShuffleBlockId(0, 4, 0), ShuffleBlockId(0, 4, 1))
+ val mergedRemoteBlocks = Map[BlockId, ManagedBuffer](
+ ShuffleBlockBatchId(0, 3, 0, 3) -> createMockManagedBuffer(),
+ ShuffleBlockBatchId(0, 3, 3, 6) -> createMockManagedBuffer(),
+ ShuffleBlockBatchId(0, 3, 6, 9) -> createMockManagedBuffer(),
+ ShuffleBlockBatchId(0, 3, 9, 12) -> createMockManagedBuffer(),
+ ShuffleBlockBatchId(0, 3, 12, 15) -> createMockManagedBuffer(),
+ ShuffleBlockBatchId(0, 4, 0, 2) -> createMockManagedBuffer())
+ val transfer = createMockTransfer(mergedRemoteBlocks)
+
+ val blocksByAddress = Seq[(BlockManagerId, Seq[(BlockId, Long, Int)])](
+ (remoteBmId1, remoteBlocks1.map(blockId => (blockId, 100L, 1))),
+ (remoteBmId2, remoteBlocks2.map(blockId => (blockId, 100L, 1)))).toIterator
+
+ val taskContext = TaskContext.empty()
+ val metrics = taskContext.taskMetrics.createTempShuffleReadMetrics()
+ val iterator = new ShuffleBlockFetcherIterator(
+ taskContext,
+ transfer,
+ blockManager,
+ blocksByAddress,
+ (_, in) => in,
+ 1500,
+ Int.MaxValue,
+ Int.MaxValue,
+ Int.MaxValue,
+ true,
+ false,
+ metrics,
+ true)
+
+ var numResults = 0
+ // After initialize(), there will be 6 FetchRequests, and the each of the first 5
+ // includes 3 merged blocks and the last one has 1 merged block. So, only the
Review comment:
there are 6 merged blocks in total, how can each request includes 3 merged blocks?
----------------------------------------------------------------
This is an automated message from the Apache Git Service.
To respond to the message, please log on to GitHub and use the
URL above to go to the specific comment.
For queries about this service, please contact Infrastructure at:
users@infra.apache.org
With regards,
Apache Git Services
---------------------------------------------------------------------
To unsubscribe, e-mail: reviews-unsubscribe@spark.apache.org
For additional commands, e-mail: reviews-help@spark.apache.org
[GitHub] [spark] cloud-fan commented on a change in pull request #27786:
[SPARK-31034][CORE] ShuffleBlockFetcherIterator should always create
request for last block group
Posted by GitBox <gi...@apache.org>.
cloud-fan commented on a change in pull request #27786: [SPARK-31034][CORE] ShuffleBlockFetcherIterator should always create request for last block group
URL: https://github.com/apache/spark/pull/27786#discussion_r387717872
##########
File path: core/src/test/scala/org/apache/spark/storage/ShuffleBlockFetcherIteratorSuite.scala
##########
@@ -341,32 +341,86 @@ class ShuffleBlockFetcherIteratorSuite extends SparkFunSuite with PrivateMethodT
assert(blockManager.hostLocalDirManager.get.getCachedHostLocalDirs().size === 1)
}
- test("fetch continuous blocks in batch respects maxSize and maxBlocks") {
+ test("fetch continuous blocks in batch should respect maxBytesInFlight") {
val blockManager = mock(classOf[BlockManager])
val localBmId = BlockManagerId("test-client", "test-local-host", 1)
doReturn(localBmId).when(blockManager).blockManagerId
// Make sure remote blocks would return the merged block
- val remoteBmId = BlockManagerId("test-client-1", "test-client-1", 2)
- val remoteBlocks = Seq[BlockId](
+ val remoteBmId1 = BlockManagerId("test-client-1", "test-client-1", 1)
+ val remoteBmId2 = BlockManagerId("test-client-2", "test-client-2", 2)
+ val remoteBlocks1 = (0 until 15).map(ShuffleBlockId(0, 3, _))
+ val remoteBlocks2 = Seq[BlockId](ShuffleBlockId(0, 4, 0), ShuffleBlockId(0, 4, 1))
+ val mergedRemoteBlocks = Map[BlockId, ManagedBuffer](
+ ShuffleBlockBatchId(0, 3, 0, 3) -> createMockManagedBuffer(),
+ ShuffleBlockBatchId(0, 3, 3, 6) -> createMockManagedBuffer(),
+ ShuffleBlockBatchId(0, 3, 6, 9) -> createMockManagedBuffer(),
+ ShuffleBlockBatchId(0, 3, 9, 12) -> createMockManagedBuffer(),
+ ShuffleBlockBatchId(0, 3, 12, 15) -> createMockManagedBuffer(),
+ ShuffleBlockBatchId(0, 4, 0, 2) -> createMockManagedBuffer())
+ val transfer = createMockTransfer(mergedRemoteBlocks)
+
+ val blocksByAddress = Seq[(BlockManagerId, Seq[(BlockId, Long, Int)])](
+ (remoteBmId1, remoteBlocks1.map(blockId => (blockId, 100L, 1))),
+ (remoteBmId2, remoteBlocks2.map(blockId => (blockId, 100L, 1)))).toIterator
+
+ val taskContext = TaskContext.empty()
+ val metrics = taskContext.taskMetrics.createTempShuffleReadMetrics()
+ val iterator = new ShuffleBlockFetcherIterator(
+ taskContext,
+ transfer,
+ blockManager,
+ blocksByAddress,
+ (_, in) => in,
+ 1500,
+ Int.MaxValue,
+ Int.MaxValue,
+ Int.MaxValue,
+ true,
+ false,
+ metrics,
+ true)
+
+ var numResults = 0
+ // After initialize(), there will be 6 FetchRequests. And each of the first 5 requests
+ // includes 1 merged block which is merged from 3 shuffle blocks. The last request has 1 merged
+ // block which merged from 2 shuffle blocks. So, only the first 5 requests(5 * 3 * 100 >= 1500)
+ // can be sent. The second FetchRequest will hit maxBlocksInFlightPerAddress so it won't
Review comment:
`The second` -> `The 6th`?
----------------------------------------------------------------
This is an automated message from the Apache Git Service.
To respond to the message, please log on to GitHub and use the
URL above to go to the specific comment.
For queries about this service, please contact Infrastructure at:
users@infra.apache.org
With regards,
Apache Git Services
---------------------------------------------------------------------
To unsubscribe, e-mail: reviews-unsubscribe@spark.apache.org
For additional commands, e-mail: reviews-help@spark.apache.org
[GitHub] [spark] AmplabJenkins commented on issue #27786:
[SPARK-31034][CORE] ShuffleBlockFetcherIterator should always create
request for last block group
Posted by GitBox <gi...@apache.org>.
AmplabJenkins commented on issue #27786: [SPARK-31034][CORE] ShuffleBlockFetcherIterator should always create request for last block group
URL: https://github.com/apache/spark/pull/27786#issuecomment-594632953
Merged build finished. Test PASSed.
----------------------------------------------------------------
This is an automated message from the Apache Git Service.
To respond to the message, please log on to GitHub and use the
URL above to go to the specific comment.
For queries about this service, please contact Infrastructure at:
users@infra.apache.org
With regards,
Apache Git Services
---------------------------------------------------------------------
To unsubscribe, e-mail: reviews-unsubscribe@spark.apache.org
For additional commands, e-mail: reviews-help@spark.apache.org
[GitHub] [spark] SparkQA commented on issue #27786: [SPARK-31034][CORE]
ShuffleBlockFetcherIterator should always create request for last block group
Posted by GitBox <gi...@apache.org>.
SparkQA commented on issue #27786: [SPARK-31034][CORE] ShuffleBlockFetcherIterator should always create request for last block group
URL: https://github.com/apache/spark/pull/27786#issuecomment-594385786
**[Test build #119287 has started](https://amplab.cs.berkeley.edu/jenkins/job/SparkPullRequestBuilder/119287/testReport)** for PR 27786 at commit [`28df4ab`](https://github.com/apache/spark/commit/28df4ab6d6c8c68012ec95492fd56c05bd37463a).
----------------------------------------------------------------
This is an automated message from the Apache Git Service.
To respond to the message, please log on to GitHub and use the
URL above to go to the specific comment.
For queries about this service, please contact Infrastructure at:
users@infra.apache.org
With regards,
Apache Git Services
---------------------------------------------------------------------
To unsubscribe, e-mail: reviews-unsubscribe@spark.apache.org
For additional commands, e-mail: reviews-help@spark.apache.org
[GitHub] [spark] AmplabJenkins removed a comment on issue #27786:
[SPARK-31034][CORE] ShuffleBlockFetcherIterator should always create
request for last block group
Posted by GitBox <gi...@apache.org>.
AmplabJenkins removed a comment on issue #27786: [SPARK-31034][CORE] ShuffleBlockFetcherIterator should always create request for last block group
URL: https://github.com/apache/spark/pull/27786#issuecomment-594369875
Test PASSed.
Refer to this link for build results (access rights to CI server needed):
https://amplab.cs.berkeley.edu/jenkins//job/SparkPullRequestBuilder-K8s/24025/
Test PASSed.
----------------------------------------------------------------
This is an automated message from the Apache Git Service.
To respond to the message, please log on to GitHub and use the
URL above to go to the specific comment.
For queries about this service, please contact Infrastructure at:
users@infra.apache.org
With regards,
Apache Git Services
---------------------------------------------------------------------
To unsubscribe, e-mail: reviews-unsubscribe@spark.apache.org
For additional commands, e-mail: reviews-help@spark.apache.org
[GitHub] [spark] AmplabJenkins removed a comment on issue #27786:
[SPARK-31034][CORE] ShuffleBlockFetcherIterator should always create
request for last block group
Posted by GitBox <gi...@apache.org>.
AmplabJenkins removed a comment on issue #27786: [SPARK-31034][CORE] ShuffleBlockFetcherIterator should always create request for last block group
URL: https://github.com/apache/spark/pull/27786#issuecomment-594650403
Merged build finished. Test FAILed.
----------------------------------------------------------------
This is an automated message from the Apache Git Service.
To respond to the message, please log on to GitHub and use the
URL above to go to the specific comment.
For queries about this service, please contact Infrastructure at:
users@infra.apache.org
With regards,
Apache Git Services
---------------------------------------------------------------------
To unsubscribe, e-mail: reviews-unsubscribe@spark.apache.org
For additional commands, e-mail: reviews-help@spark.apache.org
[GitHub] [spark] cloud-fan commented on issue #27786: [SPARK-31034][CORE]
ShuffleBlockFetcherIterator should always create request for last block group
Posted by GitBox <gi...@apache.org>.
cloud-fan commented on issue #27786: [SPARK-31034][CORE] ShuffleBlockFetcherIterator should always create request for last block group
URL: https://github.com/apache/spark/pull/27786#issuecomment-595230852
thanks, merging to master/3.0!
----------------------------------------------------------------
This is an automated message from the Apache Git Service.
To respond to the message, please log on to GitHub and use the
URL above to go to the specific comment.
For queries about this service, please contact Infrastructure at:
users@infra.apache.org
With regards,
Apache Git Services
---------------------------------------------------------------------
To unsubscribe, e-mail: reviews-unsubscribe@spark.apache.org
For additional commands, e-mail: reviews-help@spark.apache.org
[GitHub] [spark] AmplabJenkins commented on issue #27786:
[SPARK-31034][CORE] ShuffleBlockFetcherIterator should always create
request for last block group
Posted by GitBox <gi...@apache.org>.
AmplabJenkins commented on issue #27786: [SPARK-31034][CORE] ShuffleBlockFetcherIterator should always create request for last block group
URL: https://github.com/apache/spark/pull/27786#issuecomment-594632965
Test PASSed.
Refer to this link for build results (access rights to CI server needed):
https://amplab.cs.berkeley.edu/jenkins//job/SparkPullRequestBuilder-K8s/24057/
Test PASSed.
----------------------------------------------------------------
This is an automated message from the Apache Git Service.
To respond to the message, please log on to GitHub and use the
URL above to go to the specific comment.
For queries about this service, please contact Infrastructure at:
users@infra.apache.org
With regards,
Apache Git Services
---------------------------------------------------------------------
To unsubscribe, e-mail: reviews-unsubscribe@spark.apache.org
For additional commands, e-mail: reviews-help@spark.apache.org
[GitHub] [spark] AmplabJenkins commented on issue #27786:
[SPARK-31034][CORE] ShuffleBlockFetcherIterator should always create
request for last block group
Posted by GitBox <gi...@apache.org>.
AmplabJenkins commented on issue #27786: [SPARK-31034][CORE] ShuffleBlockFetcherIterator should always create request for last block group
URL: https://github.com/apache/spark/pull/27786#issuecomment-594380031
Merged build finished. Test FAILed.
----------------------------------------------------------------
This is an automated message from the Apache Git Service.
To respond to the message, please log on to GitHub and use the
URL above to go to the specific comment.
For queries about this service, please contact Infrastructure at:
users@infra.apache.org
With regards,
Apache Git Services
---------------------------------------------------------------------
To unsubscribe, e-mail: reviews-unsubscribe@spark.apache.org
For additional commands, e-mail: reviews-help@spark.apache.org
[GitHub] [spark] AmplabJenkins commented on issue #27786:
[SPARK-31034][CORE] ShuffleBlockFetcherIterator should always create
request for last block group
Posted by GitBox <gi...@apache.org>.
AmplabJenkins commented on issue #27786: [SPARK-31034][CORE] ShuffleBlockFetcherIterator should always create request for last block group
URL: https://github.com/apache/spark/pull/27786#issuecomment-594486498
Test PASSed.
Refer to this link for build results (access rights to CI server needed):
https://amplab.cs.berkeley.edu/jenkins//job/SparkPullRequestBuilder/119287/
Test PASSed.
----------------------------------------------------------------
This is an automated message from the Apache Git Service.
To respond to the message, please log on to GitHub and use the
URL above to go to the specific comment.
For queries about this service, please contact Infrastructure at:
users@infra.apache.org
With regards,
Apache Git Services
---------------------------------------------------------------------
To unsubscribe, e-mail: reviews-unsubscribe@spark.apache.org
For additional commands, e-mail: reviews-help@spark.apache.org
[GitHub] [spark] AmplabJenkins removed a comment on issue #27786:
[SPARK-31034][CORE] ShuffleBlockFetcherIterator should always create
request for last block group
Posted by GitBox <gi...@apache.org>.
AmplabJenkins removed a comment on issue #27786: [SPARK-31034][CORE] ShuffleBlockFetcherIterator should always create request for last block group
URL: https://github.com/apache/spark/pull/27786#issuecomment-594791573
Test PASSed.
Refer to this link for build results (access rights to CI server needed):
https://amplab.cs.berkeley.edu/jenkins//job/SparkPullRequestBuilder/119319/
Test PASSed.
----------------------------------------------------------------
This is an automated message from the Apache Git Service.
To respond to the message, please log on to GitHub and use the
URL above to go to the specific comment.
For queries about this service, please contact Infrastructure at:
users@infra.apache.org
With regards,
Apache Git Services
---------------------------------------------------------------------
To unsubscribe, e-mail: reviews-unsubscribe@spark.apache.org
For additional commands, e-mail: reviews-help@spark.apache.org
[GitHub] [spark] SparkQA commented on issue #27786: [SPARK-31034][CORE]
ShuffleBlockFetcherIterator should always create request for last block group
Posted by GitBox <gi...@apache.org>.
SparkQA commented on issue #27786: [SPARK-31034][CORE] ShuffleBlockFetcherIterator should always create request for last block group
URL: https://github.com/apache/spark/pull/27786#issuecomment-594789989
**[Test build #119319 has finished](https://amplab.cs.berkeley.edu/jenkins/job/SparkPullRequestBuilder/119319/testReport)** for PR 27786 at commit [`dc94365`](https://github.com/apache/spark/commit/dc9436573976e9ba227836dc7e1ce271cd91c7fb).
* This patch passes all tests.
* This patch merges cleanly.
* This patch adds no public classes.
----------------------------------------------------------------
This is an automated message from the Apache Git Service.
To respond to the message, please log on to GitHub and use the
URL above to go to the specific comment.
For queries about this service, please contact Infrastructure at:
users@infra.apache.org
With regards,
Apache Git Services
---------------------------------------------------------------------
To unsubscribe, e-mail: reviews-unsubscribe@spark.apache.org
For additional commands, e-mail: reviews-help@spark.apache.org
[GitHub] [spark] AmplabJenkins commented on issue #27786:
[SPARK-31034][CORE] ShuffleBlockFetcherIterator should always create
request for last block group
Posted by GitBox <gi...@apache.org>.
AmplabJenkins commented on issue #27786: [SPARK-31034][CORE] ShuffleBlockFetcherIterator should always create request for last block group
URL: https://github.com/apache/spark/pull/27786#issuecomment-594400926
Test PASSed.
Refer to this link for build results (access rights to CI server needed):
https://amplab.cs.berkeley.edu/jenkins//job/SparkPullRequestBuilder-K8s/24035/
Test PASSed.
----------------------------------------------------------------
This is an automated message from the Apache Git Service.
To respond to the message, please log on to GitHub and use the
URL above to go to the specific comment.
For queries about this service, please contact Infrastructure at:
users@infra.apache.org
With regards,
Apache Git Services
---------------------------------------------------------------------
To unsubscribe, e-mail: reviews-unsubscribe@spark.apache.org
For additional commands, e-mail: reviews-help@spark.apache.org