[
https://issues.apache.org/jira/browse/HBASE-12411?page=com.atlassian.jira.plugin.system.issuetabpanels:comment-tabpanel&focusedCommentId=14215729#comment-14215729
]
ramkrishna.s.vasudevan commented on HBASE-12411:
------------------------------------------------
Patch looks great. This ensures that the readers of compaction do not
interfere with user reads. As Stack's comments says we may end up in opening
more streams in the NN on the same HDFS blocks. (May be am wrong as how HDFS
would handle it).
But this patch would ensure that the on going compaction would not affect the
user scans by sharing the same reader.
> Avoid seek + read completely?
> -----------------------------
>
> Key: HBASE-12411
> URL: https://issues.apache.org/jira/browse/HBASE-12411
> Project: HBase
> Issue Type: Brainstorming
> Components: Performance
> Reporter: Lars Hofhansl
> Attachments: 12411-v2.txt, 12411-v3.txt, 12411.txt
>
>
> In the light of HDFS-6735 we might want to consider refraining from seek +
> read completely and only perform preads.
> For example currently a compaction can lock out every other scanner over the
> file which the compaction is currently reading for compaction.
> At the very least we can introduce an option to avoid seek + read, so we can
> allow testing this in various scenarios.
> This will definitely be of great importance for projects like Phoenix which
> parallelize queries intra region (and hence readers will used concurrently by
> multiple scanner with high likelihood.)
--
This message was sent by Atlassian JIRA
(v6.3.4#6332)
