[ https://issues.apache.org/jira/browse/CASSANDRA-6809?page=com.atlassian.jira.plugin.system.issuetabpanels:comment-tabpanel&focusedCommentId=14289213#comment-14289213 ]
Branimir Lambov commented on CASSANDRA-6809: -------------------------------------------- Thank you, I did not realise you are interested in parallelism between segments only. Of course, what you suggest is the right solution if we are limited to that; I approached the problem with the assumption that we need shorter sections (of the same segment) that are to progress in parallel. I can see that this should work well enough with large sync periods, including the 10s default. I am happy to continue with either approach, or without multithreaded compression altogether. I am now going back to addressing the individual issues Ariel raised. > Compressed Commit Log > --------------------- > > Key: CASSANDRA-6809 > URL: https://issues.apache.org/jira/browse/CASSANDRA-6809 > Project: Cassandra > Issue Type: Improvement > Reporter: Benedict > Assignee: Branimir Lambov > Priority: Minor > Labels: performance > Fix For: 3.0 > > Attachments: ComitLogStress.java, logtest.txt > > > It seems an unnecessary oversight that we don't compress the commit log. > Doing so should improve throughput, but some care will need to be taken to > ensure we use as much of a segment as possible. I propose decoupling the > writing of the records from the segments. Basically write into a (queue of) > DirectByteBuffer, and have the sync thread compress, say, ~64K chunks every X > MB written to the CL (where X is ordinarily CLS size), and then pack as many > of the compressed chunks into a CLS as possible. -- This message was sent by Atlassian JIRA (v6.3.4#6332)