cassandra-commits mailing list archives

Site index · List index
Message view « Date » · « Thread »
Top « Date » · « Thread »
From "Ryan King (JIRA)" <>
Subject [jira] Created: (CASSANDRA-1083) Improvement to CompactionManger's submitMinorIfNeeded
Date Wed, 12 May 2010 19:46:44 GMT
Improvement to CompactionManger's submitMinorIfNeeded

                 Key: CASSANDRA-1083
             Project: Cassandra
          Issue Type: Improvement
    Affects Versions: 0.6.1
            Reporter: Ryan King
            Assignee: Ryan King
            Priority: Minor

We've discovered that we are unable to tune compaction the way we want for our production
cluster. I think the current algorithm doesn't do this as well as it could, since it doesn't
sort the sstables by size before doing the bucketing, which means the tuning parameters have
unpredictable results.

I looked at CASSANDRA-792, but it seems like overkill. Here's an alternative proposal:

config operations:

The first two would mean what they currently mean: the bounds on how many sstables to compact
in one compaction operation. The 3rd is a target for how many SSTables you'd like to have.

Pseudo code algorithm for determining whether or not to do a minor compaction:

if sstables.length > targetSSTableCount
 sort sstables from smallest to largest
 if sstables.length - targetSSTableCount  > minimumCompactionThreshold
   compact the up to maximumCompactionThreshold smallest tables

This message is automatically generated by JIRA.
You can reply to this email to add a comment to the issue online.

View raw message