-
Notifications
You must be signed in to change notification settings - Fork 28.2k
Commit
This commit does not belong to any branch on this repository, and may belong to a fork outside of the repository.
[SPARK-46216][CORE] Improve
FileSystemPersistenceEngine
to support …
…compressions ### What changes were proposed in this pull request? This PR aims to improve `FileSystemPersistenceEngine` to support compressions via a new configuration, `spark.deploy.recoveryCompressionCodec`. ### Why are the changes needed? To allow the users to choose a proper compression codec for their workloads. For `JavaSerializer` case, `LZ4` compression is **2x** faster than the baseline (no compression). ``` OpenJDK 64-Bit Server VM 17.0.9+9-LTS on Linux 5.15.0-1051-azure AMD EPYC 7763 64-Core Processor 2000 Workers: Best Time(ms) Avg Time(ms) Stdev(ms) Rate(M/s) Per Row(ns) Relative ---------------------------------------------------------------------------------------------------------------------------------------- ZooKeeperPersistenceEngine with JavaSerializer 2276 2360 115 0.0 1137909.6 1.0X ZooKeeperPersistenceEngine with KryoSerializer 1883 1906 34 0.0 941364.2 1.2X FileSystemPersistenceEngine with JavaSerializer 431 436 7 0.0 215436.9 5.3X FileSystemPersistenceEngine with JavaSerializer (lz4) 209 216 9 0.0 104404.1 10.9X FileSystemPersistenceEngine with JavaSerializer (lzf) 199 202 2 0.0 99489.5 11.4X FileSystemPersistenceEngine with JavaSerializer (snappy) 192 199 9 0.0 95872.9 11.9X FileSystemPersistenceEngine with JavaSerializer (zstd) 258 264 6 0.0 129249.4 8.8X FileSystemPersistenceEngine with KryoSerializer 139 151 13 0.0 69374.5 16.4X FileSystemPersistenceEngine with KryoSerializer (lz4) 159 165 8 0.0 79588.9 14.3X FileSystemPersistenceEngine with KryoSerializer (lzf) 180 195 18 0.0 89844.0 12.7X FileSystemPersistenceEngine with KryoSerializer (snappy) 164 183 18 0.0 82016.0 13.9X FileSystemPersistenceEngine with KryoSerializer (zstd) 206 218 11 0.0 102838.9 11.1X BlackHolePersistenceEngine 0 0 0 35.1 28.5 39908.5X ``` ### Does this PR introduce _any_ user-facing change? No, this is a new feature. ### How was this patch tested? Pass the CIs with the newly added test case. ### Was this patch authored or co-authored using generative AI tooling? No. Closes #44129 from dongjoon-hyun/SPARK-46216. Authored-by: Dongjoon Hyun <[email protected]> Signed-off-by: Dongjoon Hyun <[email protected]>
- Loading branch information
1 parent
a3d7019
commit 3da2e5c
Showing
8 changed files
with
118 additions
and
21 deletions.
There are no files selected for viewing
This file contains bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
This file contains bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
This file contains bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
This file contains bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
This file contains bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
This file contains bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
This file contains bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
This file contains bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters