[
https://issues.apache.org/jira/browse/HBASE-11811?page=com.atlassian.jira.plugin.system.issuetabpanels:comment-tabpanel&focusedCommentId=14603342#comment-14603342
]
Vladimir Rodionov commented on HBASE-11811:
-------------------------------------------
I think I know why the patch has been abandoned. PREFIX_TREE encoding solves
the fast search problem inside HFile block - this is why the patch has not
been supported. But, any block encodings in HBase reduces (sometimes,
significantly - read this discussion
http://comments.gmane.org/gmane.comp.java.hadoop.hbase.devel/40477
) overall scan speed.
We need key encoding which is lightweight on scans and fast on search. Having
block encoding NONE and key index solves both, but does not reduce memory
footprint. For applications, there key overhead is not so large this might be a
good feature.
> 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
(v6.3.4#6332)
