[
https://issues.apache.org/jira/browse/HDFS-3023?page=com.atlassian.jira.plugin.system.issuetabpanels:comment-tabpanel&focusedCommentId=13218365#comment-13218365
]
Eli Collins commented on HDFS-3023:
-----------------------------------
Is log size a proxy for performance? Ie do we have data to suggest the
slowdown is due to the log size (# of bytes we're writing) vs just an increase
in the # of transactions, which may increase eg the # flushes, or have you
isolated for those already (eg there are no net new flushes) and it's down to
just the # bytes going across the wire? I guess another way to phrase this is
how much of the overhead in the HDFS-3010 for real workloads is option #2 vs
option #3.
> Optimize entries in edits log for persistBlocks calls
> -----------------------------------------------------
>
> Key: HDFS-3023
> URL: https://issues.apache.org/jira/browse/HDFS-3023
> Project: Hadoop HDFS
> Issue Type: Improvement
> Components: name-node, performance
> Affects Versions: HA branch (HDFS-1623), 0.23.2
> Reporter: Todd Lipcon
> Assignee: Todd Lipcon
> Attachments: hdfs-3023-HDFS-1623.txt
>
>
> One of the performance issues noticed in the HA branch is due to the much
> larger edit logs, now that we are writing OP_ADD transactions to the edit log
> on every block allocation. We can condense these calls down in two ways:
> 1) use variable-length integers for the block list length, size, and genstamp
> (most of these end up fitting in far less than 8 bytes)
> 2) use delta-coding for the genstamp and block size for any blocks after the
> first block (most blocks will be the same size and only slightly higher
> genstamps)
> 3) introduce a new OP_UPDATE_BLOCKS transaction that doesn't re-serialize
> metadata information like lease owner, permissions, etc
> 4) allow OP_UPDATE_BLOCKS to only re-serialize the blocks that have changed
> for a given transaction
--
This message is automatically generated by JIRA.
If you think it was sent incorrectly, please contact your JIRA administrators:
https://issues.apache.org/jira/secure/ContactAdministrators!default.jspa
For more information on JIRA, see: http://www.atlassian.com/software/jira
