You are viewing a plain text version of this content. The canonical link for it is here.

Posted to issues@hbase.apache.org by "stack (JIRA)" <ji...@apache.org> on 2011/09/17 19:57:09 UTC

[jira] [Updated] (HBASE-3855) Performance degradation of memstore because reseek is linear

     [ https://issues.apache.org/jira/browse/HBASE-3855?page=com.atlassian.jira.plugin.system.issuetabpanels:all-tabpanel ]

stack updated HBASE-3855:
-------------------------

    Fix Version/s:     (was: 0.92.0)
                   0.90.5

OK. Moving to 0.90.5.  I did not apply 4195 to the branch BECAUSE it does not apply over on the branch (which means I must have been dreaming yesterday when I thought I was testing 4195 on 0.90 -- I must have been running it on TRUNK).  Leaving this as open against 0.90.5 rather than against 0.92 since we don't seem to have the issue that caused the reopen in TRUNK (and 4195 improves on the original patch here anyways).

> Performance degradation of memstore because reseek is linear
> ------------------------------------------------------------
>
>                 Key: HBASE-3855
>                 URL: https://issues.apache.org/jira/browse/HBASE-3855
>             Project: HBase
>          Issue Type: Improvement
>            Reporter: dhruba borthakur
>            Priority: Blocker
>             Fix For: 0.90.5
>
>         Attachments: memstoreReseek.txt, memstoreReseek2.txt
>
>
> The scanner use reseek to find the next row (or next column) as part of a scan. The reseek code iterates over a Set to position itself at the right place. If there are many thousands of kvs that need to be skipped over, then the time-cost is very high. In this case, a seek would be far lesser in cost than a reseek.

--
This message is automatically generated by JIRA.
For more information on JIRA, see: http://www.atlassian.com/software/jira