LakshSingla commented on PR #16322:
URL: https://github.com/apache/druid/pull/16322#issuecomment-2103270147
Benchmarked the pre-existing code, there isn't a regression in the byte
comparable types:
```
master
Benchmark (channelDistributionString)
(keyGeneratorString) (keyLength) (numChannels) (numRows) (rowLength) Mode
Cnt Score Error Units
FrameChannelMergerBenchmark.mergeChannels round_robin
random 20 2 5000000 100 avgt 5
1020.405 ± 70.317 ms/op
FrameChannelMergerBenchmark.mergeChannels round_robin
random 20 16 5000000 100 avgt 5
1583.528 ± 523.469 ms/op
FrameChannelMergerBenchmark.mergeChannels round_robin
sequential 20 2 5000000 100 avgt 5
1206.522 ± 323.548 ms/op
FrameChannelMergerBenchmark.mergeChannels round_robin
sequential 20 16 5000000 100 avgt 5
1996.365 ± 339.964 ms/op
FrameChannelMergerBenchmark.mergeChannels clustered
random 20 2 5000000 100 avgt 5
860.327 ± 65.100 ms/op
FrameChannelMergerBenchmark.mergeChannels clustered
random 20 16 5000000 100 avgt 5
1346.599 ± 38.168 ms/op
FrameChannelMergerBenchmark.mergeChannels clustered
sequential 20 2 5000000 100 avgt 5
955.820 ± 167.006 ms/op
FrameChannelMergerBenchmark.mergeChannels clustered
sequential 20 16 5000000 100 avgt 5
1162.238 ± 52.815 ms/op
This patch:
Benchmark (channelDistributionString)
(keyGeneratorString) (keyLength) (numChannels) (numRows) (rowLength) Mode
Cnt Score Error Units
FrameChannelMergerBenchmark.mergeChannels round_robin
random 20 2 5000000 100 avgt 5
938.234 ± 38.388 ms/op
FrameChannelMergerBenchmark.mergeChannels round_robin
random 20 16 5000000 100 avgt 5
1392.245 ± 46.723 ms/op
FrameChannelMergerBenchmark.mergeChannels round_robin
sequential 20 2 5000000 100 avgt 5
1001.648 ± 24.656 ms/op
FrameChannelMergerBenchmark.mergeChannels round_robin
sequential 20 16 5000000 100 avgt 5
1902.121 ± 115.118 ms/op
FrameChannelMergerBenchmark.mergeChannels clustered
random 20 2 5000000 100 avgt 5
915.268 ± 39.973 ms/op
FrameChannelMergerBenchmark.mergeChannels clustered
random 20 16 5000000 100 avgt 5
1458.134 ± 240.780 ms/op
FrameChannelMergerBenchmark.mergeChannels clustered
sequential 20 2 5000000 100 avgt 5
895.689 ± 38.291 ms/op
FrameChannelMergerBenchmark.mergeChannels clustered
sequential 20 16 5000000 100 avgt 5
1218.842 ± 266.408 ms/op
```
I'll update this comment once I benchmark the complex comparison code as
well
--
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]
---------------------------------------------------------------------
To unsubscribe, e-mail: [email protected]
For additional commands, e-mail: [email protected]
