You are viewing a plain text version of this content. The canonical link for it is here.
Posted to issues@flink.apache.org by GitBox <gi...@apache.org> on 2020/05/20 13:22:22 UTC
[GitHub] [flink] pnowojski opened a new pull request #12267: [FLINK-17842][network] Fix performance regression in SpanningWrapper#clear
pnowojski opened a new pull request #12267:
URL: https://github.com/apache/flink/pull/12267
For some reason the following commit:
54155744bd [FLINK-17547][task] Use RefCountedFile in SpanningWrapper
caused a performance regression in various benchmarks. It's hard to tell why
as none of the benchmarks are using spill files (records are too small), so
our best guess is that combination of AtomicInteger inside RefCountedFile
plus NullPointerException handling messed up with JIT ability to get rid
of the memory barrier (from AtomicInteger) on the hot path.
## Verifying this change
This change is covered by existing micro benchmarks.
## Does this pull request potentially affect one of the following parts:
- Dependencies (does it add or upgrade a dependency): (yes / **no**)
- The public API, i.e., is any changed class annotated with `@Public(Evolving)`: (yes / **no**)
- The serializers: (yes / **no** / don't know)
- The runtime per-record code paths (performance sensitive): (**yes** / no / don't know)
- Anything that affects deployment or recovery: JobManager (and its components), Checkpointing, Kubernetes/Yarn/Mesos, ZooKeeper: (yes / **no** / don't know)
- The S3 file system connector: (yes / **no** / don't know)
## Documentation
- Does this pull request introduce a new feature? (yes / **no**)
- If yes, how is the feature documented? (**not applicable** / docs / JavaDocs / not documented)
----------------------------------------------------------------
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
[GitHub] [flink] rkhachatryan commented on pull request #12267: [FLINK-17842][network] Fix performance regression in SpanningWrapper#clear
Posted by GitBox <gi...@apache.org>.
rkhachatryan commented on pull request #12267:
URL: https://github.com/apache/flink/pull/12267#issuecomment-632085825
just for the record, benchmark results (build \#157):
```
"Benchmark","Mode","Threads","Samples","Score","Score Error (99.9%)","Unit","Param: channelsFlushTimeout","Param: outputMode","Param: stateBackend"
"org.apache.flink.benchmark.AsyncWaitOperatorBenchmark.asyncWait","thrpt",1,30,1675.314399,13.661763,"ops/ms",,ORDERED,
"org.apache.flink.benchmark.AsyncWaitOperatorBenchmark.asyncWait","thrpt",1,30,1647.660718,25.408029,"ops/ms",,UNORDERED,
"org.apache.flink.benchmark.BlockingPartitionBenchmark.compressedFilePartition","thrpt",1,30,7587.623968,495.943620,"ops/ms",,,
"org.apache.flink.benchmark.BlockingPartitionBenchmark.uncompressedFilePartition","thrpt",1,30,8049.532009,686.509545,"ops/ms",,,
"org.apache.flink.benchmark.BlockingPartitionBenchmark.uncompressedMmapPartition","thrpt",1,30,8572.416029,1130.753057,"ops/ms",,,
"org.apache.flink.benchmark.ContinuousFileReaderOperatorBenchmark.readFileSplit","thrpt",1,30,13052.659810,309.984908,"ops/ms",,,
"org.apache.flink.benchmark.DataSkewStreamNetworkThroughputBenchmarkExecutor.networkSkewedThroughput","thrpt",1,30,31190.271721,870.263370,"ops/ms",,,
"org.apache.flink.benchmark.InputBenchmark.mapRebalanceMapSink","thrpt",1,30,10180.719563,354.386348,"ops/ms",,,
"org.apache.flink.benchmark.InputBenchmark.mapSink","thrpt",1,30,16854.099393,344.041672,"ops/ms",,,
"org.apache.flink.benchmark.KeyByBenchmarks.arrayKeyBy","thrpt",1,30,3398.131636,172.190394,"ops/ms",,,
"org.apache.flink.benchmark.KeyByBenchmarks.tupleKeyBy","thrpt",1,30,5913.693638,409.171727,"ops/ms",,,
"org.apache.flink.benchmark.MemoryStateBackendBenchmark.stateBackends","thrpt",1,30,4673.754547,63.306818,"ops/ms",,,MEMORY
"org.apache.flink.benchmark.MemoryStateBackendBenchmark.stateBackends","thrpt",1,30,4377.262488,75.459472,"ops/ms",,,FS
"org.apache.flink.benchmark.MemoryStateBackendBenchmark.stateBackends","thrpt",1,30,4660.429485,94.844684,"ops/ms",,,FS_ASYNC
"org.apache.flink.benchmark.RemoteChannelThroughputBenchmark.remoteRebalance","thrpt",1,30,18032.072102,1103.527368,"ops/ms",,,
"org.apache.flink.benchmark.RocksStateBackendBenchmark.stateBackends","thrpt",1,30,326.831671,3.492961,"ops/ms",,,ROCKS
"org.apache.flink.benchmark.RocksStateBackendBenchmark.stateBackends","thrpt",1,30,327.989542,2.881097,"ops/ms",,,ROCKS_INC
"org.apache.flink.benchmark.SerializationFrameworkMiniBenchmarks.serializerAvro","thrpt",1,30,589.743375,11.544982,"ops/ms",,,
"org.apache.flink.benchmark.SerializationFrameworkMiniBenchmarks.serializerHeavyString","thrpt",1,30,241.771995,9.425987,"ops/ms",,,
"org.apache.flink.benchmark.SerializationFrameworkMiniBenchmarks.serializerKryo","thrpt",1,30,243.139002,14.217965,"ops/ms",,,
"org.apache.flink.benchmark.SerializationFrameworkMiniBenchmarks.serializerPojo","thrpt",1,30,670.134967,52.890921,"ops/ms",,,
"org.apache.flink.benchmark.SerializationFrameworkMiniBenchmarks.serializerRow","thrpt",1,30,863.168600,34.835227,"ops/ms",,,
"org.apache.flink.benchmark.SerializationFrameworkMiniBenchmarks.serializerTuple","thrpt",1,30,1001.052118,33.318160,"ops/ms",,,
"org.apache.flink.benchmark.StreamNetworkBroadcastThroughputBenchmarkExecutor.networkBroadcastThroughput","thrpt",1,30,954.221477,42.950052,"ops/ms",,,
"org.apache.flink.benchmark.StreamNetworkThroughputBenchmarkExecutor.networkThroughput","thrpt",1,30,67093.199752,3957.671286,"ops/ms","100,100ms",,
"org.apache.flink.benchmark.StreamNetworkThroughputBenchmarkExecutor.networkThroughput","thrpt",1,30,17223.881108,426.811956,"ops/ms","100,100ms,SSL",,
"org.apache.flink.benchmark.StreamNetworkThroughputBenchmarkExecutor.networkThroughput","thrpt",1,30,44499.732966,1150.701385,"ops/ms","1000,1ms",,
"org.apache.flink.benchmark.StreamNetworkThroughputBenchmarkExecutor.networkThroughput","thrpt",1,30,50776.544079,1534.164574,"ops/ms","1000,100ms",,
"org.apache.flink.benchmark.StreamNetworkThroughputBenchmarkExecutor.networkThroughput","thrpt",1,30,14035.133932,342.266906,"ops/ms","1000,100ms,SSL",,
"org.apache.flink.benchmark.TwoInputBenchmark.twoInputMapSink","thrpt",1,30,16936.372008,2106.132313,"ops/ms",,,
"org.apache.flink.benchmark.TwoInputBenchmark.twoInputOneIdleMapSink","thrpt",1,30,10697.065122,1029.836213,"ops/ms",,,
"org.apache.flink.benchmark.WindowBenchmarks.globalWindow","thrpt",1,30,7608.553032,221.379725,"ops/ms",,,
"org.apache.flink.benchmark.WindowBenchmarks.sessionWindow","thrpt",1,30,896.830459,3.495180,"ops/ms",,,
"org.apache.flink.benchmark.WindowBenchmarks.slidingWindow","thrpt",1,30,761.700982,2.725391,"ops/ms",,,
"org.apache.flink.benchmark.WindowBenchmarks.tumblingWindow","thrpt",1,30,4687.172718,96.650961,"ops/ms",,,
"org.apache.flink.benchmark.StreamNetworkLatencyBenchmarkExecutor.networkLatency1to1","avgt",1,30,10.204875,0.015665,"ms/op",,,
```
Build failure unrelated: https://issues.apache.org/jira/browse/FLINK-17817
----------------------------------------------------------------
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
[GitHub] [flink] flinkbot edited a comment on pull request #12267: [FLINK-17842][network] Fix performance regression in SpanningWrapper#clear
Posted by GitBox <gi...@apache.org>.
flinkbot edited a comment on pull request #12267:
URL: https://github.com/apache/flink/pull/12267#issuecomment-631489829
<!--
Meta data
{
"version" : 1,
"metaDataEntries" : [ {
"hash" : "0afb379748084b4aef0fdf51c57e24044dfc31df",
"status" : "PENDING",
"url" : "https://dev.azure.com/apache-flink/98463496-1af2-4620-8eab-a2ecc1a2e6fe/_build/results?buildId=1949",
"triggerID" : "0afb379748084b4aef0fdf51c57e24044dfc31df",
"triggerType" : "PUSH"
} ]
}-->
## CI report:
* 0afb379748084b4aef0fdf51c57e24044dfc31df Azure: [PENDING](https://dev.azure.com/apache-flink/98463496-1af2-4620-8eab-a2ecc1a2e6fe/_build/results?buildId=1949)
<details>
<summary>Bot commands</summary>
The @flinkbot bot supports the following commands:
- `@flinkbot run travis` re-run the last Travis build
- `@flinkbot run azure` re-run the last Azure build
</details>
----------------------------------------------------------------
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
[GitHub] [flink] rkhachatryan edited a comment on pull request #12267: [FLINK-17842][network] Fix performance regression in SpanningWrapper#clear
Posted by GitBox <gi...@apache.org>.
rkhachatryan edited a comment on pull request #12267:
URL: https://github.com/apache/flink/pull/12267#issuecomment-632085825
just for the record, benchmark results (build 157):
```
"Benchmark","Mode","Threads","Samples","Score","Score Error (99.9%)","Unit","Param: channelsFlushTimeout","Param: outputMode","Param: stateBackend"
"org.apache.flink.benchmark.AsyncWaitOperatorBenchmark.asyncWait","thrpt",1,30,1675.314399,13.661763,"ops/ms",,ORDERED,
"org.apache.flink.benchmark.AsyncWaitOperatorBenchmark.asyncWait","thrpt",1,30,1647.660718,25.408029,"ops/ms",,UNORDERED,
"org.apache.flink.benchmark.BlockingPartitionBenchmark.compressedFilePartition","thrpt",1,30,7587.623968,495.943620,"ops/ms",,,
"org.apache.flink.benchmark.BlockingPartitionBenchmark.uncompressedFilePartition","thrpt",1,30,8049.532009,686.509545,"ops/ms",,,
"org.apache.flink.benchmark.BlockingPartitionBenchmark.uncompressedMmapPartition","thrpt",1,30,8572.416029,1130.753057,"ops/ms",,,
"org.apache.flink.benchmark.ContinuousFileReaderOperatorBenchmark.readFileSplit","thrpt",1,30,13052.659810,309.984908,"ops/ms",,,
"org.apache.flink.benchmark.DataSkewStreamNetworkThroughputBenchmarkExecutor.networkSkewedThroughput","thrpt",1,30,31190.271721,870.263370,"ops/ms",,,
"org.apache.flink.benchmark.InputBenchmark.mapRebalanceMapSink","thrpt",1,30,10180.719563,354.386348,"ops/ms",,,
"org.apache.flink.benchmark.InputBenchmark.mapSink","thrpt",1,30,16854.099393,344.041672,"ops/ms",,,
"org.apache.flink.benchmark.KeyByBenchmarks.arrayKeyBy","thrpt",1,30,3398.131636,172.190394,"ops/ms",,,
"org.apache.flink.benchmark.KeyByBenchmarks.tupleKeyBy","thrpt",1,30,5913.693638,409.171727,"ops/ms",,,
"org.apache.flink.benchmark.MemoryStateBackendBenchmark.stateBackends","thrpt",1,30,4673.754547,63.306818,"ops/ms",,,MEMORY
"org.apache.flink.benchmark.MemoryStateBackendBenchmark.stateBackends","thrpt",1,30,4377.262488,75.459472,"ops/ms",,,FS
"org.apache.flink.benchmark.MemoryStateBackendBenchmark.stateBackends","thrpt",1,30,4660.429485,94.844684,"ops/ms",,,FS_ASYNC
"org.apache.flink.benchmark.RemoteChannelThroughputBenchmark.remoteRebalance","thrpt",1,30,18032.072102,1103.527368,"ops/ms",,,
"org.apache.flink.benchmark.RocksStateBackendBenchmark.stateBackends","thrpt",1,30,326.831671,3.492961,"ops/ms",,,ROCKS
"org.apache.flink.benchmark.RocksStateBackendBenchmark.stateBackends","thrpt",1,30,327.989542,2.881097,"ops/ms",,,ROCKS_INC
"org.apache.flink.benchmark.SerializationFrameworkMiniBenchmarks.serializerAvro","thrpt",1,30,589.743375,11.544982,"ops/ms",,,
"org.apache.flink.benchmark.SerializationFrameworkMiniBenchmarks.serializerHeavyString","thrpt",1,30,241.771995,9.425987,"ops/ms",,,
"org.apache.flink.benchmark.SerializationFrameworkMiniBenchmarks.serializerKryo","thrpt",1,30,243.139002,14.217965,"ops/ms",,,
"org.apache.flink.benchmark.SerializationFrameworkMiniBenchmarks.serializerPojo","thrpt",1,30,670.134967,52.890921,"ops/ms",,,
"org.apache.flink.benchmark.SerializationFrameworkMiniBenchmarks.serializerRow","thrpt",1,30,863.168600,34.835227,"ops/ms",,,
"org.apache.flink.benchmark.SerializationFrameworkMiniBenchmarks.serializerTuple","thrpt",1,30,1001.052118,33.318160,"ops/ms",,,
"org.apache.flink.benchmark.StreamNetworkBroadcastThroughputBenchmarkExecutor.networkBroadcastThroughput","thrpt",1,30,954.221477,42.950052,"ops/ms",,,
"org.apache.flink.benchmark.StreamNetworkThroughputBenchmarkExecutor.networkThroughput","thrpt",1,30,67093.199752,3957.671286,"ops/ms","100,100ms",,
"org.apache.flink.benchmark.StreamNetworkThroughputBenchmarkExecutor.networkThroughput","thrpt",1,30,17223.881108,426.811956,"ops/ms","100,100ms,SSL",,
"org.apache.flink.benchmark.StreamNetworkThroughputBenchmarkExecutor.networkThroughput","thrpt",1,30,44499.732966,1150.701385,"ops/ms","1000,1ms",,
"org.apache.flink.benchmark.StreamNetworkThroughputBenchmarkExecutor.networkThroughput","thrpt",1,30,50776.544079,1534.164574,"ops/ms","1000,100ms",,
"org.apache.flink.benchmark.StreamNetworkThroughputBenchmarkExecutor.networkThroughput","thrpt",1,30,14035.133932,342.266906,"ops/ms","1000,100ms,SSL",,
"org.apache.flink.benchmark.TwoInputBenchmark.twoInputMapSink","thrpt",1,30,16936.372008,2106.132313,"ops/ms",,,
"org.apache.flink.benchmark.TwoInputBenchmark.twoInputOneIdleMapSink","thrpt",1,30,10697.065122,1029.836213,"ops/ms",,,
"org.apache.flink.benchmark.WindowBenchmarks.globalWindow","thrpt",1,30,7608.553032,221.379725,"ops/ms",,,
"org.apache.flink.benchmark.WindowBenchmarks.sessionWindow","thrpt",1,30,896.830459,3.495180,"ops/ms",,,
"org.apache.flink.benchmark.WindowBenchmarks.slidingWindow","thrpt",1,30,761.700982,2.725391,"ops/ms",,,
"org.apache.flink.benchmark.WindowBenchmarks.tumblingWindow","thrpt",1,30,4687.172718,96.650961,"ops/ms",,,
"org.apache.flink.benchmark.StreamNetworkLatencyBenchmarkExecutor.networkLatency1to1","avgt",1,30,10.204875,0.015665,"ms/op",,,
```
Build failure unrelated: https://issues.apache.org/jira/browse/FLINK-17817
----------------------------------------------------------------
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
[GitHub] [flink] flinkbot commented on pull request #12267: [FLINK-17842][network] Fix performance regression in SpanningWrapper#clear
Posted by GitBox <gi...@apache.org>.
flinkbot commented on pull request #12267:
URL: https://github.com/apache/flink/pull/12267#issuecomment-631489829
<!--
Meta data
{
"version" : 1,
"metaDataEntries" : [ {
"hash" : "0afb379748084b4aef0fdf51c57e24044dfc31df",
"status" : "UNKNOWN",
"url" : "TBD",
"triggerID" : "0afb379748084b4aef0fdf51c57e24044dfc31df",
"triggerType" : "PUSH"
} ]
}-->
## CI report:
* 0afb379748084b4aef0fdf51c57e24044dfc31df UNKNOWN
<details>
<summary>Bot commands</summary>
The @flinkbot bot supports the following commands:
- `@flinkbot run travis` re-run the last Travis build
- `@flinkbot run azure` re-run the last Azure build
</details>
----------------------------------------------------------------
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
[GitHub] [flink] flinkbot edited a comment on pull request #12267: [FLINK-17842][network] Fix performance regression in SpanningWrapper#clear
Posted by GitBox <gi...@apache.org>.
flinkbot edited a comment on pull request #12267:
URL: https://github.com/apache/flink/pull/12267#issuecomment-631471721
Thanks a lot for your contribution to the Apache Flink project. I'm the @flinkbot. I help the community
to review your pull request. We will use this comment to track the progress of the review.
## Automated Checks
Last check on commit 0afb379748084b4aef0fdf51c57e24044dfc31df (Fri Oct 16 10:53:25 UTC 2020)
**Warnings:**
* No documentation files were touched! Remember to keep the Flink docs up to date!
<sub>Mention the bot in a comment to re-run the automated checks.</sub>
## Review Progress
* ❓ 1. The [description] looks good.
* ❓ 2. There is [consensus] that the contribution should go into to Flink.
* ❓ 3. Needs [attention] from.
* ❓ 4. The change fits into the overall [architecture].
* ❓ 5. Overall code [quality] is good.
Please see the [Pull Request Review Guide](https://flink.apache.org/contributing/reviewing-prs.html) for a full explanation of the review process.<details>
The Bot is tracking the review progress through labels. Labels are applied according to the order of the review items. For consensus, approval by a Flink committer of PMC member is required <summary>Bot commands</summary>
The @flinkbot bot supports the following commands:
- `@flinkbot approve description` to approve one or more aspects (aspects: `description`, `consensus`, `architecture` and `quality`)
- `@flinkbot approve all` to approve all aspects
- `@flinkbot approve-until architecture` to approve everything until `architecture`
- `@flinkbot attention @username1 [@username2 ..]` to require somebody's attention
- `@flinkbot disapprove architecture` to remove an approval you gave earlier
</details>
----------------------------------------------------------------
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
[GitHub] [flink] pnowojski merged pull request #12267: [FLINK-17842][network] Fix performance regression in SpanningWrapper#clear
Posted by GitBox <gi...@apache.org>.
pnowojski merged pull request #12267:
URL: https://github.com/apache/flink/pull/12267
----------------------------------------------------------------
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
[GitHub] [flink] flinkbot commented on pull request #12267: [FLINK-17842][network] Fix performance regression in SpanningWrapper#clear
Posted by GitBox <gi...@apache.org>.
flinkbot commented on pull request #12267:
URL: https://github.com/apache/flink/pull/12267#issuecomment-631471721
Thanks a lot for your contribution to the Apache Flink project. I'm the @flinkbot. I help the community
to review your pull request. We will use this comment to track the progress of the review.
## Automated Checks
Last check on commit 0afb379748084b4aef0fdf51c57e24044dfc31df (Wed May 20 13:24:59 UTC 2020)
**Warnings:**
* No documentation files were touched! Remember to keep the Flink docs up to date!
<sub>Mention the bot in a comment to re-run the automated checks.</sub>
## Review Progress
* ❓ 1. The [description] looks good.
* ❓ 2. There is [consensus] that the contribution should go into to Flink.
* ❓ 3. Needs [attention] from.
* ❓ 4. The change fits into the overall [architecture].
* ❓ 5. Overall code [quality] is good.
Please see the [Pull Request Review Guide](https://flink.apache.org/contributing/reviewing-prs.html) for a full explanation of the review process.<details>
The Bot is tracking the review progress through labels. Labels are applied according to the order of the review items. For consensus, approval by a Flink committer of PMC member is required <summary>Bot commands</summary>
The @flinkbot bot supports the following commands:
- `@flinkbot approve description` to approve one or more aspects (aspects: `description`, `consensus`, `architecture` and `quality`)
- `@flinkbot approve all` to approve all aspects
- `@flinkbot approve-until architecture` to approve everything until `architecture`
- `@flinkbot attention @username1 [@username2 ..]` to require somebody's attention
- `@flinkbot disapprove architecture` to remove an approval you gave earlier
</details>
----------------------------------------------------------------
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
[GitHub] [flink] flinkbot edited a comment on pull request #12267: [FLINK-17842][network] Fix performance regression in SpanningWrapper#clear
Posted by GitBox <gi...@apache.org>.
flinkbot edited a comment on pull request #12267:
URL: https://github.com/apache/flink/pull/12267#issuecomment-631489829
<!--
Meta data
{
"version" : 1,
"metaDataEntries" : [ {
"hash" : "0afb379748084b4aef0fdf51c57e24044dfc31df",
"status" : "FAILURE",
"url" : "https://dev.azure.com/apache-flink/98463496-1af2-4620-8eab-a2ecc1a2e6fe/_build/results?buildId=1949",
"triggerID" : "0afb379748084b4aef0fdf51c57e24044dfc31df",
"triggerType" : "PUSH"
} ]
}-->
## CI report:
* 0afb379748084b4aef0fdf51c57e24044dfc31df Azure: [FAILURE](https://dev.azure.com/apache-flink/98463496-1af2-4620-8eab-a2ecc1a2e6fe/_build/results?buildId=1949)
<details>
<summary>Bot commands</summary>
The @flinkbot bot supports the following commands:
- `@flinkbot run travis` re-run the last Travis build
- `@flinkbot run azure` re-run the last Azure build
</details>
----------------------------------------------------------------
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