[ 
https://issues.apache.org/jira/browse/HBASE-13142?page=com.atlassian.jira.plugin.system.issuetabpanels:comment-tabpanel&focusedCommentId=14356322#comment-14356322
 ] 

stack commented on HBASE-13142:
-------------------------------

Addendum fixes possible leak discovered trying to backport this to 0.98.

0.98 is different -- has MetaEditor etc. -- and I was able to fix one issue 
where we were leaking ByteBuffers and just ran out of memory but now tests 
won't start a minicluster.... master stuck trying to assign a region, RS stuck 
trying to report for duty.

> [PERF] Reuse the IPCUtil#buildCellBlock buffer
> ----------------------------------------------
>
>                 Key: HBASE-13142
>                 URL: https://issues.apache.org/jira/browse/HBASE-13142
>             Project: HBase
>          Issue Type: Improvement
>          Components: Performance
>            Reporter: stack
>            Assignee: Liang Xie
>              Labels: beginner
>             Fix For: 2.0.0, 1.1.0
>
>         Attachments: 13142.txt, 13142v2.txt, 13142v3.txt, 13142v5.0.98.txt, 
> 13142v5.txt, 13142v5.txt, buffers.svg, clean.svg, gc.png, gc_time_spent.png, 
> hits.png, net.png, traces.2.svg, traces.svg
>
>
> Running some scan profiling, flight recorder was mildly fingering resize of 
> the buffer allocated in IPCUtil#buildCellBlock as a point of contention.  It 
> was half-hearted blaming it for a few hundreds of ms over a five minute 
> sampling with a few tens of instances showing.
> I tried then w/ flamegraph/lightweight profiler and this reported the buffer 
> allocations taking 22% of our total CPU. See attachment trace.svg.
> I enabled TRACE-level logging on org.apache.hadoop.hbase.ipc.IPCUtil and 
> indeed every allocation was doing a resize from initial allocation of 16k -- 
> the default up to 220k (this test returns ten randomly sized rows zipfian 
> sized between 0 and 8k).
> Upping the allocation to 220k meant we now avoided the resize but the initial 
> allocation was now blamed for 10% of allocations (see trace.2.svg attached).
> Lets do buffer reuse.  Will save a bunch of allocation and CPU.



--
This message was sent by Atlassian JIRA
(v6.3.4#6332)

Reply via email to