[
https://issues.apache.org/jira/browse/HBASE-16213?page=com.atlassian.jira.plugin.system.issuetabpanels:comment-tabpanel&focusedCommentId=16143316#comment-16143316
]
Yu Li commented on HBASE-16213:
-------------------------------
bq. I think V2 can replace V1, V2 have space optimize and the same seek perf.
Let's get HBASE-16594 in then if no objections ([~anoop.hbase] please let us
know if any comments here sir, thanks), then people like our mighty
[~yangzhe1991] could use it and further improve it (smile).
> A new HFileBlock structure for fast random get
> ----------------------------------------------
>
> Key: HBASE-16213
> URL: https://issues.apache.org/jira/browse/HBASE-16213
> Project: HBase
> Issue Type: New Feature
> Components: Performance
> Reporter: binlijin
> Assignee: binlijin
> Fix For: 2.0.0, 1.4.0
>
> Attachments: HBASE-16213.branch-1.v1.patch,
> HBASE-16213_branch1_v3.patch, HBASE-16213.branch-1.v4.patch,
> HBASE-16213.branch-1.v4.patch, HBASE-16213-master_v1.patch,
> HBASE-16213-master_v3.patch, HBASE-16213-master_v4.patch,
> HBASE-16213-master_v5.patch, HBASE-16213-master_v6.patch, HBASE-16213.patch,
> HBASE-16213_v2.patch, hfile_block_performance2.pptx,
> hfile_block_performance_E2E.pptx, hfile_block_performance.pptx, hfile-cpu.png
>
>
> HFileBlock store cells sequential, current when to get a row from the block,
> it scan from the first cell until the row's cell.
> The new structure store every row's start offset with data, so it can find
> the exact row with binarySearch.
> I use EncodedSeekPerformanceTest test the performance.
> First use ycsb write 100w data, every row have only one qualifier, and
> valueLength=16B/64/256B/1k.
> Then use EncodedSeekPerformanceTest to test random read 1w or 100w row, and
> also record HFileBlock's dataSize/dataWithMetaSize in the encoding.
--
This message was sent by Atlassian JIRA
(v6.4.14#64029)
