[GitHub] spark issue #22511: [SPARK-25422][CORE] Don't memory map blocks streamed to ...
Github user vanzin commented on the issue: https://github.com/apache/spark/pull/22511 BTW it can be argued that you don't need a dispose in that code path since `serializerManager.dataSerializeWithExplicitClassTag` creates an on-heap buffer that doesn't need to be disposed. But it would be better to audit this stuff again to make sure nothing is being missed... --- - To unsubscribe, e-mail: reviews-unsubscr...@spark.apache.org For additional commands, e-mail: reviews-h...@spark.apache.org
[GitHub] spark issue #22511: [SPARK-25422][CORE] Don't memory map blocks streamed to ...
Github user vanzin commented on the issue: https://github.com/apache/spark/pull/22511 I think the deal with the dispose in TorrentBroadcast is that it's definitely needed in the local read case, but may need adjustments in the remote read case. The local read case (`doGetLocalBytes`) can return a `ByteBufferBlockData` that needs to be disposed by the caller (check comment "The block was not found on disk, so serialize an in-memory copy:", where this happens). --- - To unsubscribe, e-mail: reviews-unsubscr...@spark.apache.org For additional commands, e-mail: reviews-h...@spark.apache.org
[GitHub] spark issue #22511: [SPARK-25422][CORE] Don't memory map blocks streamed to ...
Github user cloud-fan commented on the issue: https://github.com/apache/spark/pull/22511 > but I don't feel confident about making that change for 2.4 Makes sense. cc @vanzin for more context about https://github.com/apache/spark/commit/b56ad2b1ec19fd60fa9d4926d12244fd3f56aca4 . We can revert this change and fix the `TorrentBroadcast` when we are confident. --- - To unsubscribe, e-mail: reviews-unsubscr...@spark.apache.org For additional commands, e-mail: reviews-h...@spark.apache.org
[GitHub] spark issue #22511: [SPARK-25422][CORE] Don't memory map blocks streamed to ...
Github user squito commented on the issue: https://github.com/apache/spark/pull/22511 > This PR is directly heading to branch-2.4 by bypassing master branch YEs good point, sorry I opened this against 2.4 just for testing in case the errors were more likely in 2.4 for some reason. Closing this and opened https://github.com/apache/spark/pull/22546 --- - To unsubscribe, e-mail: reviews-unsubscr...@spark.apache.org For additional commands, e-mail: reviews-h...@spark.apache.org
[GitHub] spark issue #22511: [SPARK-25422][CORE] Don't memory map blocks streamed to ...
Github user squito commented on the issue: https://github.com/apache/spark/pull/22511 > The analysis makes sense to me. The thing I'm not sure is, how can we hit it? The "fetch block to temp file" code path is only enabled for big blocks (> 2GB). The failing tests cases "with replication as stream" turned on fetch to disk for all data: https://github.com/apache/spark/blob/master/core/src/test/scala/org/apache/spark/DistributedSuite.scala#L166-L167 > a possible approach: can we just not dispose the data in TorrentBroadcast? The memory store will dispose them anyway when it's removed. yes I considered this, but I don't feel confident about making that change for 2.4. I need to spend some more time understanding that (seems it came from SPARK-19556 / https://github.com/apache/spark/commit/b56ad2b1ec19fd60fa9d4926d12244fd3f56aca4). I think this change is the right one for the moment. --- - To unsubscribe, e-mail: reviews-unsubscr...@spark.apache.org For additional commands, e-mail: reviews-h...@spark.apache.org
[GitHub] spark issue #22511: [SPARK-25422][CORE] Don't memory map blocks streamed to ...
Github user cloud-fan commented on the issue: https://github.com/apache/spark/pull/22511 a possible approach: can we just not dispose the data in `TorrentBroadcast`? --- - To unsubscribe, e-mail: reviews-unsubscr...@spark.apache.org For additional commands, e-mail: reviews-h...@spark.apache.org
[GitHub] spark issue #22511: [SPARK-25422][CORE] Don't memory map blocks streamed to ...
Github user cloud-fan commented on the issue: https://github.com/apache/spark/pull/22511 The analysis makes sense to me. The thing I'm not sure is, how can we hit it? The "fetch block to temp file" code path is only enabled for big blocks (> 2GB). --- - To unsubscribe, e-mail: reviews-unsubscr...@spark.apache.org For additional commands, e-mail: reviews-h...@spark.apache.org
[GitHub] spark issue #22511: [SPARK-25422][CORE] Don't memory map blocks streamed to ...
Github user AmplabJenkins commented on the issue: https://github.com/apache/spark/pull/22511 Merged build finished. Test PASSed. --- - To unsubscribe, e-mail: reviews-unsubscr...@spark.apache.org For additional commands, e-mail: reviews-h...@spark.apache.org
[GitHub] spark issue #22511: [SPARK-25422][CORE] Don't memory map blocks streamed to ...
Github user AmplabJenkins commented on the issue: https://github.com/apache/spark/pull/22511 Test PASSed. Refer to this link for build results (access rights to CI server needed): https://amplab.cs.berkeley.edu/jenkins//job/SparkPullRequestBuilder/96526/ Test PASSed. --- - To unsubscribe, e-mail: reviews-unsubscr...@spark.apache.org For additional commands, e-mail: reviews-h...@spark.apache.org
[GitHub] spark issue #22511: [SPARK-25422][CORE] Don't memory map blocks streamed to ...
Github user SparkQA commented on the issue: https://github.com/apache/spark/pull/22511 **[Test build #96526 has finished](https://amplab.cs.berkeley.edu/jenkins/job/SparkPullRequestBuilder/96526/testReport)** for PR 22511 at commit [`aee82ab`](https://github.com/apache/spark/commit/aee82abe4cd9fbefa14fb280644276fe491bcf9a). * This patch passes all tests. * This patch merges cleanly. * This patch adds no public classes. --- - To unsubscribe, e-mail: reviews-unsubscr...@spark.apache.org For additional commands, e-mail: reviews-h...@spark.apache.org
[GitHub] spark issue #22511: [SPARK-25422][CORE] Don't memory map blocks streamed to ...
Github user dongjoon-hyun commented on the issue: https://github.com/apache/spark/pull/22511 @squito This PR is directly heading to `branch-2.4` by bypassing `master` branch. Is there a reason to bypass `master` branch? If there is no reason, in order to prevent future regression at Spark 2.5+, could you make a PR to `master` branch first? --- - To unsubscribe, e-mail: reviews-unsubscr...@spark.apache.org For additional commands, e-mail: reviews-h...@spark.apache.org
[GitHub] spark issue #22511: [SPARK-25422][CORE] Don't memory map blocks streamed to ...
Github user vanzin commented on the issue: https://github.com/apache/spark/pull/22511 LGTM. I went back and took a look at the related changes, and agree with Imran that this is basically the same thing that 2.3 did; so no perf regression, just higher memory usage than in the mmap case (which didn't exist before anyway). --- - To unsubscribe, e-mail: reviews-unsubscr...@spark.apache.org For additional commands, e-mail: reviews-h...@spark.apache.org
[GitHub] spark issue #22511: [SPARK-25422][CORE] Don't memory map blocks streamed to ...
Github user AmplabJenkins commented on the issue: https://github.com/apache/spark/pull/22511 Test PASSed. Refer to this link for build results (access rights to CI server needed): https://amplab.cs.berkeley.edu/jenkins//job/testing-k8s-prb-make-spark-distribution-unified/3414/ Test PASSed. --- - To unsubscribe, e-mail: reviews-unsubscr...@spark.apache.org For additional commands, e-mail: reviews-h...@spark.apache.org
[GitHub] spark issue #22511: [SPARK-25422][CORE] Don't memory map blocks streamed to ...
Github user AmplabJenkins commented on the issue: https://github.com/apache/spark/pull/22511 Merged build finished. Test PASSed. --- - To unsubscribe, e-mail: reviews-unsubscr...@spark.apache.org For additional commands, e-mail: reviews-h...@spark.apache.org
[GitHub] spark issue #22511: [SPARK-25422][CORE] Don't memory map blocks streamed to ...
Github user SparkQA commented on the issue: https://github.com/apache/spark/pull/22511 **[Test build #96526 has started](https://amplab.cs.berkeley.edu/jenkins/job/SparkPullRequestBuilder/96526/testReport)** for PR 22511 at commit [`aee82ab`](https://github.com/apache/spark/commit/aee82abe4cd9fbefa14fb280644276fe491bcf9a). --- - To unsubscribe, e-mail: reviews-unsubscr...@spark.apache.org For additional commands, e-mail: reviews-h...@spark.apache.org
[GitHub] spark issue #22511: [SPARK-25422][CORE] Don't memory map blocks streamed to ...
Github user dongjoon-hyun commented on the issue: https://github.com/apache/spark/pull/22511 Retest this please. --- - To unsubscribe, e-mail: reviews-unsubscr...@spark.apache.org For additional commands, e-mail: reviews-h...@spark.apache.org
[GitHub] spark issue #22511: [SPARK-25422][CORE] Don't memory map blocks streamed to ...
Github user AmplabJenkins commented on the issue: https://github.com/apache/spark/pull/22511 Test FAILed. Refer to this link for build results (access rights to CI server needed): https://amplab.cs.berkeley.edu/jenkins//job/SparkPullRequestBuilder/96512/ Test FAILed. --- - To unsubscribe, e-mail: reviews-unsubscr...@spark.apache.org For additional commands, e-mail: reviews-h...@spark.apache.org
[GitHub] spark issue #22511: [SPARK-25422][CORE] Don't memory map blocks streamed to ...
Github user AmplabJenkins commented on the issue: https://github.com/apache/spark/pull/22511 Merged build finished. Test FAILed. --- - To unsubscribe, e-mail: reviews-unsubscr...@spark.apache.org For additional commands, e-mail: reviews-h...@spark.apache.org
[GitHub] spark issue #22511: [SPARK-25422][CORE] Don't memory map blocks streamed to ...
Github user SparkQA commented on the issue: https://github.com/apache/spark/pull/22511 **[Test build #96512 has finished](https://amplab.cs.berkeley.edu/jenkins/job/SparkPullRequestBuilder/96512/testReport)** for PR 22511 at commit [`aee82ab`](https://github.com/apache/spark/commit/aee82abe4cd9fbefa14fb280644276fe491bcf9a). * This patch **fails Spark unit tests**. * This patch merges cleanly. * This patch adds no public classes. --- - To unsubscribe, e-mail: reviews-unsubscr...@spark.apache.org For additional commands, e-mail: reviews-h...@spark.apache.org
[GitHub] spark issue #22511: [SPARK-25422][CORE] Don't memory map blocks streamed to ...
Github user AmplabJenkins commented on the issue: https://github.com/apache/spark/pull/22511 Merged build finished. Test PASSed. --- - To unsubscribe, e-mail: reviews-unsubscr...@spark.apache.org For additional commands, e-mail: reviews-h...@spark.apache.org
[GitHub] spark issue #22511: [SPARK-25422][CORE] Don't memory map blocks streamed to ...
Github user AmplabJenkins commented on the issue: https://github.com/apache/spark/pull/22511 Test PASSed. Refer to this link for build results (access rights to CI server needed): https://amplab.cs.berkeley.edu/jenkins//job/testing-k8s-prb-make-spark-distribution-unified/3407/ Test PASSed. --- - To unsubscribe, e-mail: reviews-unsubscr...@spark.apache.org For additional commands, e-mail: reviews-h...@spark.apache.org
[GitHub] spark issue #22511: [SPARK-25422][CORE] Don't memory map blocks streamed to ...
Github user SparkQA commented on the issue: https://github.com/apache/spark/pull/22511 **[Test build #96512 has started](https://amplab.cs.berkeley.edu/jenkins/job/SparkPullRequestBuilder/96512/testReport)** for PR 22511 at commit [`aee82ab`](https://github.com/apache/spark/commit/aee82abe4cd9fbefa14fb280644276fe491bcf9a). --- - To unsubscribe, e-mail: reviews-unsubscr...@spark.apache.org For additional commands, e-mail: reviews-h...@spark.apache.org
[GitHub] spark issue #22511: [SPARK-25422][CORE] Don't memory map blocks streamed to ...
Github user dongjoon-hyun commented on the issue: https://github.com/apache/spark/pull/22511 Retest this please --- - To unsubscribe, e-mail: reviews-unsubscr...@spark.apache.org For additional commands, e-mail: reviews-h...@spark.apache.org
[GitHub] spark issue #22511: [SPARK-25422][CORE] Don't memory map blocks streamed to ...
Github user AmplabJenkins commented on the issue: https://github.com/apache/spark/pull/22511 Test FAILed. Refer to this link for build results (access rights to CI server needed): https://amplab.cs.berkeley.edu/jenkins//job/SparkPullRequestBuilder/96497/ Test FAILed. --- - To unsubscribe, e-mail: reviews-unsubscr...@spark.apache.org For additional commands, e-mail: reviews-h...@spark.apache.org
[GitHub] spark issue #22511: [SPARK-25422][CORE] Don't memory map blocks streamed to ...
Github user AmplabJenkins commented on the issue: https://github.com/apache/spark/pull/22511 Merged build finished. Test FAILed. --- - To unsubscribe, e-mail: reviews-unsubscr...@spark.apache.org For additional commands, e-mail: reviews-h...@spark.apache.org
[GitHub] spark issue #22511: [SPARK-25422][CORE] Don't memory map blocks streamed to ...
Github user SparkQA commented on the issue: https://github.com/apache/spark/pull/22511 **[Test build #96497 has finished](https://amplab.cs.berkeley.edu/jenkins/job/SparkPullRequestBuilder/96497/testReport)** for PR 22511 at commit [`aee82ab`](https://github.com/apache/spark/commit/aee82abe4cd9fbefa14fb280644276fe491bcf9a). * This patch **fails due to an unknown error code, -9**. * This patch merges cleanly. * This patch adds no public classes. --- - To unsubscribe, e-mail: reviews-unsubscr...@spark.apache.org For additional commands, e-mail: reviews-h...@spark.apache.org
[GitHub] spark issue #22511: [SPARK-25422][CORE] Don't memory map blocks streamed to ...
Github user gatorsmile commented on the issue: https://github.com/apache/spark/pull/22511 Also cc @zsxwing @JoshRosen --- - To unsubscribe, e-mail: reviews-unsubscr...@spark.apache.org For additional commands, e-mail: reviews-h...@spark.apache.org
[GitHub] spark issue #22511: [SPARK-25422][CORE] Don't memory map blocks streamed to ...
Github user AmplabJenkins commented on the issue: https://github.com/apache/spark/pull/22511 Merged build finished. Test PASSed. --- - To unsubscribe, e-mail: reviews-unsubscr...@spark.apache.org For additional commands, e-mail: reviews-h...@spark.apache.org
[GitHub] spark issue #22511: [SPARK-25422][CORE] Don't memory map blocks streamed to ...
Github user AmplabJenkins commented on the issue: https://github.com/apache/spark/pull/22511 Test PASSed. Refer to this link for build results (access rights to CI server needed): https://amplab.cs.berkeley.edu/jenkins//job/testing-k8s-prb-make-spark-distribution-unified/3396/ Test PASSed. --- - To unsubscribe, e-mail: reviews-unsubscr...@spark.apache.org For additional commands, e-mail: reviews-h...@spark.apache.org
[GitHub] spark issue #22511: [SPARK-25422][CORE] Don't memory map blocks streamed to ...
Github user SparkQA commented on the issue: https://github.com/apache/spark/pull/22511 **[Test build #96497 has started](https://amplab.cs.berkeley.edu/jenkins/job/SparkPullRequestBuilder/96497/testReport)** for PR 22511 at commit [`aee82ab`](https://github.com/apache/spark/commit/aee82abe4cd9fbefa14fb280644276fe491bcf9a). --- - To unsubscribe, e-mail: reviews-unsubscr...@spark.apache.org For additional commands, e-mail: reviews-h...@spark.apache.org
[GitHub] spark issue #22511: [SPARK-25422][CORE] Don't memory map blocks streamed to ...
Github user dongjoon-hyun commented on the issue: https://github.com/apache/spark/pull/22511 Retest this please. --- - To unsubscribe, e-mail: reviews-unsubscr...@spark.apache.org For additional commands, e-mail: reviews-h...@spark.apache.org
[GitHub] spark issue #22511: [SPARK-25422][CORE] Don't memory map blocks streamed to ...
Github user SparkQA commented on the issue: https://github.com/apache/spark/pull/22511 **[Test build #4346 has started](https://amplab.cs.berkeley.edu/jenkins/job/NewSparkPullRequestBuilder/4346/testReport)** for PR 22511 at commit [`aee82ab`](https://github.com/apache/spark/commit/aee82abe4cd9fbefa14fb280644276fe491bcf9a). --- - To unsubscribe, e-mail: reviews-unsubscr...@spark.apache.org For additional commands, e-mail: reviews-h...@spark.apache.org
[GitHub] spark issue #22511: [SPARK-25422][CORE] Don't memory map blocks streamed to ...
Github user squito commented on the issue: https://github.com/apache/spark/pull/22511 > this seems like a big change, will we hit perf regression? Not vs. 2.3. It only effects things when stream-to-disk is enabled, and when it is enabled, for reading remote cached blocks, this is actually going back to the old behavior. See https://github.com/apache/spark/pull/19476/files#diff-2b643ea78c1add0381754b1f47eec132R692 -- `FileSegmentManagedBuffer.nioByteBuffer()` reads the entire file into a regular byte buffer. I changed it to memory map the file as an attempted optimization. This change will make things slower, but that's vs. other changes that are only in 2.4. There are TODOs in the code for ways to improve this further but that should not go into 2.4. > is this a long-standing bug? the change here is not fixing a long-standing bug, its just updating new changes for 2.4. however, I'm really wondering why TorrentBroadcast calls dispose on the blocks. For regular buffers, its a no-op, so it hasn't mattered, but I can't come up with a reason that you *do* want to dispose those blocks. Secondly, it seems there is an implicit assumption that you never add memory-mapped byte buffers to the MemoryStore. Maybe that makes sense ... its kind of messing with the Memory / Disk management spark has. But the MemoryStore never checks that you don't add a mapped buffer, you'll just get weird behavior like this later on. Seems there should be a check at the very least, to avoid this kind of issue. As neither of those things are new to 2.4, I don't think we should deal w/ them here. The major motivation for memory mapping the file was not for broadcast blocks, it was for reading large cached blocks. But it actually makes more sense to change the interfaces in BlockManager to allow us to just get the managedBuffer, instead of a ChunkedByteBuffer (thats this TODO: https://github.com/apache/spark/blob/master/core/src/main/scala/org/apache/spark/storage/BlockManager.scala#L728) --- - To unsubscribe, e-mail: reviews-unsubscr...@spark.apache.org For additional commands, e-mail: reviews-h...@spark.apache.org
[GitHub] spark issue #22511: [SPARK-25422][CORE] Don't memory map blocks streamed to ...
Github user AmplabJenkins commented on the issue: https://github.com/apache/spark/pull/22511 Merged build finished. Test PASSed. --- - To unsubscribe, e-mail: reviews-unsubscr...@spark.apache.org For additional commands, e-mail: reviews-h...@spark.apache.org
[GitHub] spark issue #22511: [SPARK-25422][CORE] Don't memory map blocks streamed to ...
Github user AmplabJenkins commented on the issue: https://github.com/apache/spark/pull/22511 Test PASSed. Refer to this link for build results (access rights to CI server needed): https://amplab.cs.berkeley.edu/jenkins//job/SparkPullRequestBuilder/96408/ Test PASSed. --- - To unsubscribe, e-mail: reviews-unsubscr...@spark.apache.org For additional commands, e-mail: reviews-h...@spark.apache.org
[GitHub] spark issue #22511: [SPARK-25422][CORE] Don't memory map blocks streamed to ...
Github user SparkQA commented on the issue: https://github.com/apache/spark/pull/22511 **[Test build #96408 has finished](https://amplab.cs.berkeley.edu/jenkins/job/SparkPullRequestBuilder/96408/testReport)** for PR 22511 at commit [`aee82ab`](https://github.com/apache/spark/commit/aee82abe4cd9fbefa14fb280644276fe491bcf9a). * This patch passes all tests. * This patch merges cleanly. * This patch adds no public classes. --- - To unsubscribe, e-mail: reviews-unsubscr...@spark.apache.org For additional commands, e-mail: reviews-h...@spark.apache.org
[GitHub] spark issue #22511: [SPARK-25422][CORE] Don't memory map blocks streamed to ...
Github user cloud-fan commented on the issue: https://github.com/apache/spark/pull/22511 is this a long-standing bug? --- - To unsubscribe, e-mail: reviews-unsubscr...@spark.apache.org For additional commands, e-mail: reviews-h...@spark.apache.org
[GitHub] spark issue #22511: [SPARK-25422][CORE] Don't memory map blocks streamed to ...
Github user cloud-fan commented on the issue: https://github.com/apache/spark/pull/22511 this seems like a big change, will we hit perf regression? --- - To unsubscribe, e-mail: reviews-unsubscr...@spark.apache.org For additional commands, e-mail: reviews-h...@spark.apache.org
[GitHub] spark issue #22511: [SPARK-25422][CORE] Don't memory map blocks streamed to ...
Github user AmplabJenkins commented on the issue: https://github.com/apache/spark/pull/22511 Merged build finished. Test PASSed. --- - To unsubscribe, e-mail: reviews-unsubscr...@spark.apache.org For additional commands, e-mail: reviews-h...@spark.apache.org
[GitHub] spark issue #22511: [SPARK-25422][CORE] Don't memory map blocks streamed to ...
Github user AmplabJenkins commented on the issue: https://github.com/apache/spark/pull/22511 Test PASSed. Refer to this link for build results (access rights to CI server needed): https://amplab.cs.berkeley.edu/jenkins//job/testing-k8s-prb-make-spark-distribution-unified/3335/ Test PASSed. --- - To unsubscribe, e-mail: reviews-unsubscr...@spark.apache.org For additional commands, e-mail: reviews-h...@spark.apache.org
[GitHub] spark issue #22511: [SPARK-25422][CORE] Don't memory map blocks streamed to ...
Github user SparkQA commented on the issue: https://github.com/apache/spark/pull/22511 **[Test build #96408 has started](https://amplab.cs.berkeley.edu/jenkins/job/SparkPullRequestBuilder/96408/testReport)** for PR 22511 at commit [`aee82ab`](https://github.com/apache/spark/commit/aee82abe4cd9fbefa14fb280644276fe491bcf9a). --- - To unsubscribe, e-mail: reviews-unsubscr...@spark.apache.org For additional commands, e-mail: reviews-h...@spark.apache.org
[GitHub] spark issue #22511: [SPARK-25422][CORE] Don't memory map blocks streamed to ...
Github user cloud-fan commented on the issue: https://github.com/apache/spark/pull/22511 cc @jiangxb1987 --- - To unsubscribe, e-mail: reviews-unsubscr...@spark.apache.org For additional commands, e-mail: reviews-h...@spark.apache.org
[GitHub] spark issue #22511: [SPARK-25422][CORE] Don't memory map blocks streamed to ...
Github user cloud-fan commented on the issue: https://github.com/apache/spark/pull/22511 retest this please --- - To unsubscribe, e-mail: reviews-unsubscr...@spark.apache.org For additional commands, e-mail: reviews-h...@spark.apache.org
[GitHub] spark issue #22511: [SPARK-25422][CORE] Don't memory map blocks streamed to ...
Github user AmplabJenkins commented on the issue: https://github.com/apache/spark/pull/22511 Test FAILed. Refer to this link for build results (access rights to CI server needed): https://amplab.cs.berkeley.edu/jenkins//job/SparkPullRequestBuilder/96394/ Test FAILed. --- - To unsubscribe, e-mail: reviews-unsubscr...@spark.apache.org For additional commands, e-mail: reviews-h...@spark.apache.org
[GitHub] spark issue #22511: [SPARK-25422][CORE] Don't memory map blocks streamed to ...
Github user AmplabJenkins commented on the issue: https://github.com/apache/spark/pull/22511 Merged build finished. Test FAILed. --- - To unsubscribe, e-mail: reviews-unsubscr...@spark.apache.org For additional commands, e-mail: reviews-h...@spark.apache.org
[GitHub] spark issue #22511: [SPARK-25422][CORE] Don't memory map blocks streamed to ...
Github user SparkQA commented on the issue: https://github.com/apache/spark/pull/22511 **[Test build #96394 has finished](https://amplab.cs.berkeley.edu/jenkins/job/SparkPullRequestBuilder/96394/testReport)** for PR 22511 at commit [`aee82ab`](https://github.com/apache/spark/commit/aee82abe4cd9fbefa14fb280644276fe491bcf9a). * This patch **fails due to an unknown error code, -9**. * This patch merges cleanly. * This patch adds no public classes. --- - To unsubscribe, e-mail: reviews-unsubscr...@spark.apache.org For additional commands, e-mail: reviews-h...@spark.apache.org
[GitHub] spark issue #22511: [SPARK-25422][CORE] Don't memory map blocks streamed to ...
Github user AmplabJenkins commented on the issue: https://github.com/apache/spark/pull/22511 Test PASSed. Refer to this link for build results (access rights to CI server needed): https://amplab.cs.berkeley.edu/jenkins//job/testing-k8s-prb-make-spark-distribution-unified/3323/ Test PASSed. --- - To unsubscribe, e-mail: reviews-unsubscr...@spark.apache.org For additional commands, e-mail: reviews-h...@spark.apache.org
[GitHub] spark issue #22511: [SPARK-25422][CORE] Don't memory map blocks streamed to ...
Github user AmplabJenkins commented on the issue: https://github.com/apache/spark/pull/22511 Merged build finished. Test PASSed. --- - To unsubscribe, e-mail: reviews-unsubscr...@spark.apache.org For additional commands, e-mail: reviews-h...@spark.apache.org
[GitHub] spark issue #22511: [SPARK-25422][CORE] Don't memory map blocks streamed to ...
Github user SparkQA commented on the issue: https://github.com/apache/spark/pull/22511 **[Test build #96394 has started](https://amplab.cs.berkeley.edu/jenkins/job/SparkPullRequestBuilder/96394/testReport)** for PR 22511 at commit [`aee82ab`](https://github.com/apache/spark/commit/aee82abe4cd9fbefa14fb280644276fe491bcf9a). --- - To unsubscribe, e-mail: reviews-unsubscr...@spark.apache.org For additional commands, e-mail: reviews-h...@spark.apache.org