[ https://issues.apache.org/jira/browse/CASSANDRA-3434?page=com.atlassian.jira.plugin.system.issuetabpanels:all-tabpanel ]
Sylvain Lebresne updated CASSANDRA-3434: ---------------------------------------- Attachment: 3434.patch Patch attached that basically adds the FastBytesComparisons class from HADOOP-7761 and uses it (we need the same variation from the guava code, i.e, being able to compare from offsets). Quick microbenchmark do confirm it's much faster, but I haven't really took the time to do proper Cassandra benchmark with and without. The patch also slightly changes the non-array-backed ByteBuffer case, because at least on my machine it's slightly (but consistenly) faster than our previous code. > Explore using Guava (or guava inspired) faster bytes comparison > --------------------------------------------------------------- > > Key: CASSANDRA-3434 > URL: https://issues.apache.org/jira/browse/CASSANDRA-3434 > Project: Cassandra > Issue Type: Improvement > Components: Core > Reporter: Sylvain Lebresne > Priority: Minor > Attachments: 3434.patch > > > Guava uses un.misc.Unsafe to do a faster byte arrays comparison (on long at a > time) as noted in HADOOP-7761. > We should probably look into it. -- This message is automatically generated by JIRA. If you think it was sent incorrectly, please contact your JIRA administrators: https://issues.apache.org/jira/secure/ContactAdministrators!default.jspa For more information on JIRA, see: http://www.atlassian.com/software/jira