Yu Li commented on HBASE-16698:

Ok, here are more performance number with YCSB. First the testing environment:
YCSB 0.7.0
4 physical client nodes, 8 YCSB processes per node, 32 threads per YCSB process
recordcount=3,200,000, fieldcount=1, fieldlength=1024, insertproportion=1, 

1 single RS, regionnumber(presplit)=200, handlercount=128, 

patch applied on not latest but recent branch-1 code (commit 
not latest because using the same package doing PE testing

And the comparison data (two rounds):
|w/o patch|Round-1|66554.48|15263.36|
|w/ patch|Round-1|91472.48|11098.85|
|w/o patch|Round-2|66083.53|15382.01|
|w/ patch|Round-2|91420.26|11104.37|

This should be sufficient to prove the effect of the patch when heavy load on 
multiple regions. Feel free to reproduce the test and let me know if any 
different results.

More data coming for heavy load on one single region to see whether there's 
perf regression for this case.

> Performance issue: handlers stuck waiting for CountDownLatch inside 
> WALKey#getWriteEntry under high writing workload
> --------------------------------------------------------------------------------------------------------------------
>                 Key: HBASE-16698
>                 URL: https://issues.apache.org/jira/browse/HBASE-16698
>             Project: HBase
>          Issue Type: Improvement
>          Components: Performance
>    Affects Versions: 1.2.3
>            Reporter: Yu Li
>            Assignee: Yu Li
>             Fix For: 2.0.0
>         Attachments: HBASE-16698.branch-1.patch, 
> HBASE-16698.branch-1.v2.patch, HBASE-16698.patch, HBASE-16698.v2.patch, 
> hadoop0495.et2.jstack
> As titled, on our production environment we observed 98 out of 128 handlers 
> get stuck waiting for the CountDownLatch {{seqNumAssignedLatch}} inside 
> {{WALKey#getWriteEntry}} under a high writing workload.
> After digging into the problem, we found that the problem is mainly caused by 
> advancing mvcc in the append logic. Below is some detailed analysis:
> Under current branch-1 code logic, all batch puts will call 
> {{WALKey#getWriteEntry}} after appending edit to WAL, and 
> {{seqNumAssignedLatch}} is only released when the relative append call is 
> handled by RingBufferEventHandler (see {{FSWALEntry#stampRegionSequenceId}}). 
> Because currently we're using a single event handler for the ringbuffer, the 
> append calls are handled one by one (actually lot's of our current logic 
> depending on this sequential dealing logic), and this becomes a bottleneck 
> under high writing workload.
> The worst part is that by default we only use one WAL per RS, so appends on 
> all regions are dealt with in sequential, which causes contention among 
> different regions...
> To fix this, we could also take use of the "sequential appends" mechanism, 
> that we could grab the WriteEntry before publishing append onto ringbuffer 
> and use it as sequence id, only that we need to add a lock to make "grab 
> WriteEntry" and "append edit" a transaction. This will still cause contention 
> inside a region but could avoid contention between different regions. This 
> solution is already verified in our online environment and proved to be 
> effective.
> Notice that for master (2.0) branch since we already change the write 
> pipeline to sync before writing memstore (HBASE-15158), this issue only 
> exists for the ASYNC_WAL writes scenario.

This message was sent by Atlassian JIRA

Reply via email to