[
https://issues.apache.org/jira/browse/HBASE-11811?page=com.atlassian.jira.plugin.system.issuetabpanels:all-tabpanel
]
Lars Hofhansl updated HBASE-11811:
----------------------------------
Attachment: 11811-wip-v4.txt
Slightly updated version.
In all my local testing I see great improvement for Gets and no measurable
penalty for Scans.
In the worst case (if each block only receives a single Get request) we can
expect that on average we now look through twice as many KV. If the block is
indeed loaded from HDFS each time, this is negligible.
I'll try to test with a real cluster and PE soon.
> Use binary search for seeking into a block
> ------------------------------------------
>
> Key: HBASE-11811
> URL: https://issues.apache.org/jira/browse/HBASE-11811
> Project: HBase
> Issue Type: Brainstorming
> Reporter: Lars Hofhansl
> Attachments: 11811-wip-v2.txt, 11811-wip-v4.txt, block_index-v2.txt
>
>
> Currently upon every seek (including Gets) we need to linearly look through
> the block from the beginning until we find the Cell we are looking for.
> It should be possible to build a simple cache of offsets of Cells for each
> block as it is loaded and then use binary search to find the Cell in question.
--
This message was sent by Atlassian JIRA
(v6.2#6252)
