[ https://issues.apache.org/jira/browse/CASSANDRA-15393?page=com.atlassian.jira.plugin.system.issuetabpanels:comment-tabpanel&focusedCommentId=17185510#comment-17185510 ]
Caleb Rackliffe commented on CASSANDRA-15393: --------------------------------------------- bq. The idea of combining the byte array util and the accessor has also been floating around, and I'd prefer we didn't for both the reason above, and because people are pretty used to having ByteBufferUtil handy. Having ByteArrayUtil handy would make the appearance of byte[] everywhere a little less jarring (hopefully). bq. NativeCell prevents moving most of that into AbstractCell. Given the simplicity of the parts that can be factored, I'd lean towards keeping the class hierarchy simple over minimizing the size of the array and buffer cell implementations. Agreed on both points. > Add byte array backed cells > --------------------------- > > Key: CASSANDRA-15393 > URL: https://issues.apache.org/jira/browse/CASSANDRA-15393 > Project: Cassandra > Issue Type: Sub-task > Components: Local/Compaction > Reporter: Blake Eggleston > Assignee: Blake Eggleston > Priority: Normal > Fix For: 4.0-beta > > Time Spent: 20m > Remaining Estimate: 0h > > We currently materialize all values as on heap byte buffers. Byte buffers > have a fairly high overhead given how frequently they’re used, and on the > compaction and local read path we don’t do anything that needs them. Use of > byte buffer methods only happens on the coordinator. Using cells that are > backed by byte arrays instead in these situations reduces compaction and read > garbage up to 22% in many cases. -- This message was sent by Atlassian Jira (v8.3.4#803005) --------------------------------------------------------------------- To unsubscribe, e-mail: commits-unsubscr...@cassandra.apache.org For additional commands, e-mail: commits-h...@cassandra.apache.org