[
https://issues.apache.org/jira/browse/HBASE-1364?page=com.atlassian.jira.plugin.system.issuetabpanels:comment-tabpanel&focusedCommentId=13045670#comment-13045670
]
Prakash Khemani commented on HBASE-1364:
----------------------------------------
splitLog is called for one region server at a time - it is not called directly
on the .logs directory. The servername passed is the name of the regionserver's
log directory under .logs. It is called at startup by the function
splitLogAfterStartup(). It is splitLogAfterStartup() that calls splitLog() for
one regionserver at a time and that can take a long time.
It is probably better to call splitLog() for all region servers simultaneously.
A large number of splitlog tasks will get scheduled - one for each log file.
But a splitlog-worker (region server) executes only one task at a time and
there shouldn't be a danger of DFS overload.
> [performance] Distributed splitting of regionserver commit logs
> ---------------------------------------------------------------
>
> Key: HBASE-1364
> URL: https://issues.apache.org/jira/browse/HBASE-1364
> Project: HBase
> Issue Type: Improvement
> Components: coprocessors
> Reporter: stack
> Assignee: Prakash Khemani
> Priority: Critical
> Fix For: 0.92.0
>
> Attachments: 1364-v5.txt, HBASE-1364.patch,
> org.apache.hadoop.hbase.master.TestDistributedLogSplitting-output.txt
>
> 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.
For more information on JIRA, see: http://www.atlassian.com/software/jira
