[ https://issues.apache.org/jira/browse/CASSANDRA-47?page=com.atlassian.jira.plugin.system.issuetabpanels:comment-tabpanel&focusedCommentId=13062729#comment-13062729 ]
Jonathan Ellis commented on CASSANDRA-47: ----------------------------------------- bq. current implementations uses file holes (reserves free space for the future chunk changes) Is this for where we have to seek back to write the row size on large rows? We're already making two passes when compacting large rows (first to compute the indexes), we could make the first pass compute the serialized size so we don't have to seek after the 2nd pass that writes the data. > SSTable compression > ------------------- > > Key: CASSANDRA-47 > URL: https://issues.apache.org/jira/browse/CASSANDRA-47 > Project: Cassandra > Issue Type: New Feature > Components: Core > Reporter: Jonathan Ellis > Assignee: Pavel Yaskevich > Labels: compression > Fix For: 1.0 > > Attachments: CASSANDRA-47.patch, snappy-java-1.0.3-rc4.jar > > > We should be able to do SSTable compression which would trade CPU for I/O > (almost always a good trade). -- This message is automatically generated by JIRA. For more information on JIRA, see: http://www.atlassian.com/software/jira