Joe McDonnell created IMPALA-14900:
--------------------------------------
Summary: Add support for running Impala without tcmalloc's
aggressive decommit mode
Key: IMPALA-14900
URL: https://issues.apache.org/jira/browse/IMPALA-14900
Project: IMPALA
Issue Type: Task
Components: Backend
Affects Versions: Impala 5.0.0
Reporter: Joe McDonnell
Impala currently sets tcmalloc's aggressive decommit mode and asserts that it
is set. This forces tcmalloc to return all free spans to the operating system.
Impala does this for a couple reasons:
# Without aggressive decommit, tcmalloc doesn't release memory fast enough for
Impala's memory access patterns. Impala would need to manually force tcmalloc
to free memory with a background thread and integration with the process memory
tracker's garbage collection. A long time ago, there were performance issues
with the way this was implemented. See IMPALA-2800.
# When Impala uses huge pages, we don't want tcmalloc to reuse the huge page
as smaller pieces. This can potentially cause inaccuracy in our memory use
statistics. See this comment in system-allocator.cc:
https://github.com/apache/impala/blob/cefeb760a886d28c05f98917cdfeac864728f270/be/src/runtime/bufferpool/system-allocator.cc#L152-L157
However, aggressive decommit increases the memory allocation / deallocation
rate and can lead to extra interactions with the operating system and
contention on tcmalloc locks. We have seen issues when Parquet files have large
data pages. We have also seen issues with queries operating on nested data.
It would be useful to have a way to run Impala with aggressive decommit
disabled. This will require a background thread monitoring memory use and
integration with the process mem tracker's garbage collection. One option is to
allow aggressive decommit to be disabled when huge pages are disabled. Another
option is to use mmap for huge pages to allow using huge pages with aggressive
decommit disabled.
--
This message was sent by Atlassian Jira
(v8.20.10#820010)
