rkhachatryan commented on a change in pull request #17229:
URL: https://github.com/apache/flink/pull/17229#discussion_r747884871
##########
File path:
flink-streaming-java/src/main/java/org/apache/flink/streaming/runtime/tasks/StreamTask.java
##########
@@ -303,6 +304,8 @@
@GuardedBy("shouldInterruptOnCancelLock")
private boolean shouldInterruptOnCancel = true;
+ private final AvailabilityProvider changelogWriterAvailabilityProvider;
Review comment:
These are the top 10 regressions when comparing [this
PR](http://codespeed.dak8s.net:8080/job/flink-benchmark-request/553/artifact/jmh-result.csv/*view*/)
and
[master](http://codespeed.dak8s.net:8080/job/flink-master-benchmarks/8589/artifact/jmh-result.csv/*view*/):
MultiInputCheckpointingTimeBenchmark.checkpointMultiInput | 2.57734 | 89.77%
-- | -- | --
SerializationFrameworkMiniBenchmarks.serializerPojo | 629.770475 | 91.29%
StreamNetworkThroughputBenchmarkExecutor.networkThroughput | 36497.36957 |
93.05%
BlockingPartitionBenchmark.compressedFilePartition | 8733.624685 | 94.31%
WindowBenchmarks.globalWindow | 6870.474052 | 96.32%
MultipleInputBenchmark.multiInputMapSink | 18164.0954 | 97.22%
SerializationFrameworkMiniBenchmarks.serializerRow | 848.132961 | 97.31%
TwoInputBenchmark.twoInputMapSink | 17246.67162 | 97.93%
WindowBenchmarks.sessionWindow | 820.272928 | 98.18%
InputBenchmark.mapSink | 30215.03625 | 98.28%
All these benchmarks seem to be noisy, so I think the performance is fine,
WDYT?
(I ran with and without `null` optimization without any significant
difference; these results are without `null`, i.e. lambda).
--
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.
To unsubscribe, e-mail: [email protected]
For queries about this service, please contact Infrastructure at:
[email protected]
