hadoop-common-dev mailing list archives

Site index · List index
Message view « Date » · « Thread »
Top « Date » · « Thread »
From "Raghu Angadi (JIRA)" <j...@apache.org>
Subject [jira] Commented: (HADOOP-2576) Namenode performance degradation over time
Date Wed, 23 Jan 2008 23:28:35 GMT

    [ https://issues.apache.org/jira/browse/HADOOP-2576?page=com.atlassian.jira.plugin.system.issuetabpanels:comment-tabpanel&focusedCommentId=12561866#action_12561866

Raghu Angadi commented on HADOOP-2576:

Another issue that contributes this problem and made worse by large heartbeat :

# For each heartbeat, Namenode asks a datanode to delete blocks only the datanode does not
need to transfer (for replication, rebalancing etc) any blocks. I don't see any reason by
datanode can not do both. If a datanode gets asked to transfer one block in each minute, it
never deletes anything.

# Similarly 'computeDatanodeWork()' does the same: it moves blocks from recentInvalidates
to datanode's list only if no transfers are scheduled on a node.

> Namenode performance degradation over time
> ------------------------------------------
>                 Key: HADOOP-2576
>                 URL: https://issues.apache.org/jira/browse/HADOOP-2576
>             Project: Hadoop Core
>          Issue Type: Bug
>          Components: dfs
>    Affects Versions: 0.16.0
>            Reporter: Christian Kunz
>            Assignee: Raghu Angadi
>            Priority: Blocker
>             Fix For: 0.16.0
>         Attachments: HADOOP-2576.patch
> We have a cluster running the same applications again and again with a high turnover
of files.
> The performance of these applications seem to be correlated to the lifetime of the namenode:
> After starting the namenode, the applications need increasingly more time to complete,
with about 50% more time after 1 week. 
> During that time the namenode average cpu usage increases from typically 10% to 30%,
memory usage nearly doubles (although the average amount of data on dfs stays the same), and
the average load factor increases by a factor of 2-3 (although not  significantly high, <2).
> When looking at the namenode and datanode logs, I see a lot of asks to delete blocks
coming from the namenode for blocks not in the blockmap of the datanodes, repeatedly for the
same blocks.
> When I counted the number of blocks asked by the namenode to be deleted, I noticed a
noticeable increase with the lifetime of the namenode (a factor of 2-3 after 1 week).
> This makes me wonder whether the namenode does not purge the list of invalid blocks from
non-existing blocks.
> But independently, the namenode has a degradation issue.

This message is automatically generated by JIRA.
You can reply to this email to add a comment to the issue online.

View raw message