[jira] [Updated] (CASSANDRA-5727) Evaluate default LCS sstable size

["Wei Deng (JIRA)" <ji...@apache.org>]

     [ https://issues.apache.org/jira/browse/CASSANDRA-5727?page=com.atlassian.jira.plugin.system.issuetabpanels:all-tabpanel ]

Wei Deng updated CASSANDRA-5727:
--------------------------------
    Labels: lcs  (was: )

> Evaluate default LCS sstable size
> ---------------------------------
>
>                 Key: CASSANDRA-5727
>                 URL: https://issues.apache.org/jira/browse/CASSANDRA-5727
>             Project: Cassandra
>          Issue Type: Task
>            Reporter: Jonathan Ellis
>            Assignee: Daniel Meyer
>              Labels: lcs
>             Fix For: 1.2.9
>
>         Attachments: BytesRead_vs_LCS.png, ReadLatency_vs_LCS.png, Throughtput_vs_LCS.png, UpdateLatency_vs_LCS.png
>
>
> What we're not sure about is the effect on compaction efficiency --
> larger files mean that each level contains more data, so reads will
> have to touch less sstables, but we're also compacting less unchanged
> data when we merge forward.
> So the question is, how big can we make the sstables to get the benefits of the
> first effect, before the second effect starts to dominate?



--
This message was sent by Atlassian JIRA
(v6.3.4#6332)