[
https://issues.apache.org/jira/browse/TEZ-3709?page=com.atlassian.jira.plugin.system.issuetabpanels:comment-tabpanel&focusedCommentId=16012451#comment-16012451
]
Rajesh Balamohan commented on TEZ-3709:
---------------------------------------
Checked the patch. LGTM. +1.
Corner case: For {{ioSortFactor=1}}, it can run into infinite loop due to {{n
-= (f - 1);}}. This corner case is there in existing codebase as well. Default
{{io.sort.factor=100}} and no one would set it to 1 intentionally I believe.
> TezMerger is slow for high number of segments
> ---------------------------------------------
>
> Key: TEZ-3709
> URL: https://issues.apache.org/jira/browse/TEZ-3709
> Project: Apache Tez
> Issue Type: Bug
> Reporter: Jonathan Eagles
> Assignee: Jonathan Eagles
> Labels: performance
> Attachments: TEZ-3709.1.patch, TEZ-3709.2.patch, TEZ-3709.3.patch
>
>
> The below code is a bad performer at scale since it has to memcpy the whole
> list of segments for each item in the batch instead of of just once per batch.
> This is true for both computeBytesInMerges and getSegmentDescriptors.
> {code}
> for (int i = 0; i < batch; i++) {
> ArrayList#remove(0)
> }
> {code}
--
This message was sent by Atlassian JIRA
(v6.3.15#6346)
