[ https://issues.apache.org/jira/browse/CASSANDRA-1608?page=com.atlassian.jira.plugin.system.issuetabpanels:comment-tabpanel&focusedCommentId=12965233#action_12965233 ]
T Jake Luciani commented on CASSANDRA-1608: ------------------------------------------- This seems to be a brainstorming session on compaction so here are the things I've been thinking. 1) Compaction Coordination: read performance impact can be mitigated if we make sure replicas of data are not doing compaction at the same time as the other replicas. dynamic snitch would do bulk of the work. Just encode compaction workload into gossip? 2) Compaction Sharing: Benefit of splitting SStable by token range is we can send the resulting SStables to replicas of this data rather than have these nodes compact their own data. this could help 1 node do the work of the others. > Redesigned Compaction > --------------------- > > Key: CASSANDRA-1608 > URL: https://issues.apache.org/jira/browse/CASSANDRA-1608 > Project: Cassandra > Issue Type: Improvement > Components: Core > Reporter: Chris Goffinet > Fix For: 0.7.1 > > > After seeing the I/O issues in CASSANDRA-1470, I've been doing some more > thinking on this subject that I wanted to lay out. > I propose we redo the concept of how compaction works in Cassandra. At the > moment, compaction is kicked off based on a write access pattern, not read > access pattern. In most cases, you want the opposite. You want to be able to > track how well each SSTable is performing in the system. If we were to keep > statistics in-memory of each SSTable, prioritize them based on most accessed, > and bloom filter hit/miss ratios, we could intelligently group sstables that > are being read most often and schedule them for compaction. We could also > schedule lower priority maintenance on SSTable's not often accessed. > I also propose we limit the size of each SSTable to a fix sized, that gives > us the ability to better utilize our bloom filters in a predictable manner. > At the moment after a certain size, the bloom filters become less reliable. > This would also allow us to group data most accessed. Currently the size of > an SSTable can grow to a point where large portions of the data might not > actually be accessed as often. -- This message is automatically generated by JIRA. - You can reply to this email to add a comment to the issue online.