[
https://issues.apache.org/jira/browse/HBASE-17471?page=com.atlassian.jira.plugin.system.issuetabpanels:all-tabpanel
]
Allan Yang updated HBASE-17471:
-------------------------------
Attachment: HBASE-17471.v2.patch
Add a init patch to clarify my thought and run through the Hundson.
Thanks for [~Apache9] 's idea of removing the additional lock.
In this patch, I bring the mvcc preassign to the wal.append(), all acquirement
of seqid and ringbuffer's txid is synchronized under mvcc.writeQueue, making
sure the seqid in WAL is increasing monotonically. I also moved the action of
stamping seqid to cell from ringbuffer's single consume thread to increase
throughput. (According to one of my test, acquire mvcc under lock and stamping
them to cell takes 25% time of the append action)
One thing to do is making preAssign configurable.
[~carp84] (the original author of preAssignMVCC) and the others, please give me
some advice.
> Region Seqid will be out of order in WAL if using mvccPreAssign
> ---------------------------------------------------------------
>
> Key: HBASE-17471
> URL: https://issues.apache.org/jira/browse/HBASE-17471
> Project: HBase
> Issue Type: Bug
> Components: wal
> Affects Versions: 2.0.0, 1.4.0
> Reporter: Allan Yang
> Assignee: Allan Yang
> Priority: Critical
> Attachments: HBASE-17471.patch, HBASE-17471.tmp, HBASE-17471.v2.patch
>
>
> mvccPreAssign was brought by HBASE-16698, which truly improved the
> performance of writing, especially in ASYNC_WAL scenario. But mvccPreAssign
> was only used in {{doMiniBatchMutate}}, not in Increment/Append path. If
> Increment/Append and batch put are using against the same region in parallel,
> then seqid of the same region may not monotonically increasing in the WAL.
> Since one write path acquires mvcc/seqid before append, and the other
> acquires in the append/sync consume thread.
> The out of order situation can easily reproduced by a simple UT, which was
> attached in the attachment. I modified the code to assert on the disorder:
> {code}
> if(this.highestSequenceIds.containsKey(encodedRegionName)) {
> assert highestSequenceIds.get(encodedRegionName) < sequenceid;
> }
> {code}
> I'd like to say, If we allow disorder in WALs, then this is not a issue.
> But as far as I know, if {{highestSequenceIds}} is not properly set, some
> WALs may not archive to oldWALs correctly.
> which I haven't figure out yet is that, will disorder in WAL cause data loss
> when recovering from disaster? If so, then it is a big problem need to be
> fixed.
> I have fix this problem in our costom1.1.x branch, my solution is using
> mvccPreAssign everywhere, making it un-configurable. Since mvccPreAssign it
> is indeed a better way than assign seqid in the ringbuffer thread while
> keeping handlers waiting for it.
> If anyone think it is doable, then I will port it to branch-1 and master
> branch and upload it.
>
--
This message was sent by Atlassian JIRA
(v6.3.4#6332)
