Jouni Hartikainen created CASSANDRA-5384:
--------------------------------------------
Summary: SSTables are evicted from the page cache during
compaction even if populate_io_cache_on_flush is true
Key: CASSANDRA-5384
URL: https://issues.apache.org/jira/browse/CASSANDRA-5384
Project: Cassandra
Issue Type: Improvement
Affects Versions: 1.2.3
Reporter: Jouni Hartikainen
Priority: Minor
AbstractCompactionStrategy acquires direct scanners on SSTables to be
compacted. These scanners are always created with skipIOCache set true. Because
of this, compactions even for CFs that have populate_io_cache_on_flush set to
true will evict source SSTables from the page cache after 128MB
(CACHE_FLUSH_INTERVAL_IN_BYTES in RandomAccessReader) have been read from them.
This leads to disk reads even in cases where the dataset completely fits into
memory and unnecessarily limits compaction throughput on nodes that have lots
of RAM.
Maybe compaction strategy should try to avoid skipping IO cache if CF has
populate_io_cache_on_flush set to true?
--
This message is automatically generated by JIRA.
If you think it was sent incorrectly, please contact your JIRA administrators
For more information on JIRA, see: http://www.atlassian.com/software/jira
