[
https://issues.apache.org/jira/browse/HBASE-9679?page=com.atlassian.jira.plugin.system.issuetabpanels:comment-tabpanel&focusedCommentId=13781256#comment-13781256
]
Lars Hofhansl commented on HBASE-9679:
--------------------------------------
Agreed. Binary search is not possible, because the KVs have variable length and
there is no index to indicate where each KV start. We can change that of course
- for example we can build up the index when a block is cached.
In that case, why not just index the KVs accordingly. (In fact I tried that
once using a lazily build, sparsely populated SkiplistSet as index, but that
did not yield any appreciable performance improvement).
> Binary search in HFile block
> ----------------------------
>
> Key: HBASE-9679
> URL: https://issues.apache.org/jira/browse/HBASE-9679
> Project: HBase
> Issue Type: Improvement
> Components: HFile
> Affects Versions: 0.95.2, 0.94.12
> Reporter: Liang Xie
> Assignee: Liang Xie
> Priority: Minor
>
> It's not a top priority issue, seems to me.
> Right now hbase do a linear scan to search a key within a hfile block on
> interst, in special case, e.g. 100% read scenario or high read/write ratio
> scanario, it's useful to do a binary search improvement to reduce the CPU
> cost and response time, i think the biggest benefit should be the cpu:)
--
This message was sent by Atlassian JIRA
(v6.1#6144)
