dongjoon-hyun opened a new pull request, #56782: URL: https://github.com/apache/spark/pull/56782
### What changes were proposed in this pull request? This PR aims to install `libjemalloc2` in the Spark Docker image and add a symlink `/usr/lib/libjemalloc.so.2`while the default allocator is unchanged — the library is not preloaded unless a user opts in: ``` spark.executorEnv.LD_PRELOAD=/usr/lib/libjemalloc.so.2 spark.kubernetes.driverEnv.LD_PRELOAD=/usr/lib/libjemalloc.so.2 ``` ### Why are the changes needed? jemalloc reduces native/off-heap memory fragmentation, most notably the RocksDB state store RSS growth that leads to `OOMKilled` pods. Shipping the package lets operators enable it with one env var instead of building a custom image, with no regression for anyone else. ### Does this PR introduce _any_ user-facing change? No. The default allocator is unchanged; the image just additionally ships `libjemalloc2`. ### How was this patch tested? Pass the CIs. ### Was this patch authored or co-authored using generative AI tooling? Generated-by: Claude Opus 4.8 -- 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]
