[
https://issues.apache.org/jira/browse/HBASE-13876?page=com.atlassian.jira.plugin.system.issuetabpanels:comment-tabpanel&focusedCommentId=14580846#comment-14580846
]
Abhilash commented on HBASE-13876:
----------------------------------
Thanks a lot for the reviews.
Going to use ENUM and introducing NEUTRAL step to remove unnecessary tuning.
Which will have better use of the final variable "tolerance".
Thinking about how to remove constants like 50%. Possibly provide a static
final member to adjust the range when we say memstore/block cache is sufficient
or not.
I was using current value of number of evictCount and number of flushes because
they are non zero if program enter that block but previous evictCount and
flushes may be zero. Thinking about how to use previous values without
introducing lots of checks.
> Improving performance of HeapMemoryManager
> ------------------------------------------
>
> Key: HBASE-13876
> URL: https://issues.apache.org/jira/browse/HBASE-13876
> Project: HBase
> Issue Type: Improvement
> Components: hbase, regionserver
> Affects Versions: 2.0.0, 1.0.1, 1.1.0, 1.1.1
> Reporter: Abhilash
> Assignee: Abhilash
> Priority: Minor
> Attachments: HBASE-13876-v2.patch, HBASE-13876-v3.patch,
> HBASE-13876.patch
>
>
> I am trying to improve the performance of DefaultHeapMemoryTuner by
> introducing some more checks. The current checks under which the
> DefaultHeapMemoryTuner works are very rare so I am trying to weaken these
> checks to improve its performance.
> Check current memstore size and current block cache size. If we are using
> less than 50% of currently available block cache size we say block cache is
> sufficient and same for memstore. This check will be very effective when
> server is either load heavy or write heavy. Earlier version just waited for
> number of evictions / number of flushes to be zero which are very rare.
> Otherwise based on percent change in number of cache misses and number of
> flushes we increase / decrease memory provided for caching / memstore. After
> doing so, on next call of HeapMemoryTuner we verify that last change has
> indeed decreased number of evictions / flush ( combined). I am doing this
> analysis by comparing percent change (which is basically nothing but
> normalized derivative) of number of evictions and number of flushes during
> last two periods. The main motive for doing this was that if we have random
> reads then we will be having a lot of cache misses. But even after increasing
> block cache we wont be able to decrease number of cache misses and we will
> revert back and eventually we will not waste memory on block caches. This
> will also help us ignore random short term spikes in reads / writes.
>
--
This message was sent by Atlassian JIRA
(v6.3.4#6332)
