hbase-issues mailing list archives

Site index · List index
Message view « Date » · « Thread »
Top « Date » · « Thread »
From "Todd Lipcon (JIRA)" <j...@apache.org>
Subject [jira] Commented: (HBASE-1364) [performance] Distributed splitting of regionserver commit logs
Date Mon, 07 Jun 2010 21:15:53 GMT

    [ https://issues.apache.org/jira/browse/HBASE-1364?page=com.atlassian.jira.plugin.system.issuetabpanels:comment-tabpanel&focusedCommentId=12876425#action_12876425
] 

Todd Lipcon commented on HBASE-1364:
------------------------------------

bq. Is their any reason why we are targeting 22.0 vs 21.0 for this patch?

My personal opinion is that this should not be default in 0.21, since it doesn't quite fit
with the current priorities (durability, stability, correctness) and may actually introduce
new complicated bugs in the above. The most carefully programmed distributed operation is
usually buggier than the least carefully programmed single-node operation :)

Having it be configurable seems like a great thing for 0.21 so people can try it out, and
if it seems bug-free we can make it default in the next release. Of course that's just my
opinion, and if others disagree, happy to be outvoted.

> [performance] Distributed splitting of regionserver commit logs
> ---------------------------------------------------------------
>
>                 Key: HBASE-1364
>                 URL: https://issues.apache.org/jira/browse/HBASE-1364
>             Project: HBase
>          Issue Type: Improvement
>            Reporter: stack
>            Assignee: Alex Newman
>            Priority: Critical
>             Fix For: 0.22.0
>
>         Attachments: 1364-v2.patch, 1364.patch
>
>          Time Spent: 8h
>  Remaining Estimate: 0h
>
> HBASE-1008 has some improvements to our log splitting on regionserver crash; but it needs
to run even faster.
> (Below is from HBASE-1008)
> In bigtable paper, the split is distributed. If we're going to have 1000 logs, we need
to distribute or at least multithread the splitting.
> 1. As is, regions starting up expect to find one reconstruction log only. Need to make
it so pick up a bunch of edit logs and it should be fine that logs are elsewhere in hdfs in
an output directory written by all split participants whether multithreaded or a mapreduce-like
distributed process (Lets write our distributed sort first as a MR so we learn whats involved;
distributed sort, as much as possible should use MR framework pieces). On startup, regions
go to this directory and pick up the files written by split participants deleting and clearing
the dir when all have been read in. Making it so can take multiple logs for input, can also
make the split process more robust rather than current tenuous process which loses all edits
if it doesn't make it to the end without error.
> 2. Each column family rereads the reconstruction log to find its edits. Need to fix that.
Split can sort the edits by column family so store only reads its edits.

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


Mime
View raw message