accumulo-notifications mailing list archives

Site index · List index
Message view « Date » · « Thread »
Top « Date » · « Thread »
From "ASF subversion and git services (JIRA)" <j...@apache.org>
Subject [jira] [Commented] (ACCUMULO-2834) Immediately re-queue files which have more data to replicate
Date Thu, 22 May 2014 22:39:02 GMT

    [ https://issues.apache.org/jira/browse/ACCUMULO-2834?page=com.atlassian.jira.plugin.system.issuetabpanels:comment-tabpanel&focusedCommentId=14006547#comment-14006547
] 

ASF subversion and git services commented on ACCUMULO-2834:
-----------------------------------------------------------

Commit 0f6b6d0fb091440ad4780db1cf3c11f4a606de59 in accumulo's branch refs/heads/ACCUMULO-378
from [~elserj]
[ https://git-wip-us.apache.org/repos/asf?p=accumulo.git;h=0f6b6d0 ]

ACCUMULO-2834 First attempt at immediately requeueing a file for replication when more work
is needed.


> Immediately re-queue files which have more data to replicate
> ------------------------------------------------------------
>
>                 Key: ACCUMULO-2834
>                 URL: https://issues.apache.org/jira/browse/ACCUMULO-2834
>             Project: Accumulo
>          Issue Type: Sub-task
>          Components: replication
>            Reporter: Josh Elser
>            Assignee: Josh Elser
>             Fix For: 1.7.0
>
>
> Noticed that during high ingest load, there's a bit of downtime between iterations as,
after the batch size is reached, the tserver records the progress it made, and it waits for
the master to re-queue the file.
> This is a bit silly as the tserver could just continue to replicate from where it left
off to reduce the latency in waiting to replicate the file. The remote side will still buffer,
so we shouldn't be oversaturating the remote.



--
This message was sent by Atlassian JIRA
(v6.2#6252)

Mime
View raw message