[
https://issues.apache.org/jira/browse/HBASE-20716?page=com.atlassian.jira.plugin.system.issuetabpanels:comment-tabpanel&focusedCommentId=16527215#comment-16527215
]
Sahil Aggarwal commented on HBASE-20716:
----------------------------------------
Benchmark Mode Cnt
Score Error Units
HbaseBytes.testToLongCheckAndDispatch thrpt 6 352925235.054 ±
7423950.697 ops/s
HbaseBytes.testToLongStaticInvoke thrpt 6
353652817.747 ± 6536569.256 ops/s
org.apache.hadoop.hbase.util.Bytes::toLongCheckAndDispatch (73 bytes) -
current impl
org.apache.hadoop.hbase.util.Bytes::toLong (33 bytes) - impl using
BEST_CONVERTER
Reduced the size of method by 40 bytes.
> Unsafe access cleanup
> ---------------------
>
> Key: HBASE-20716
> URL: https://issues.apache.org/jira/browse/HBASE-20716
> Project: HBase
> Issue Type: Improvement
> Components: Performance
> Reporter: stack
> Assignee: Sahil Aggarwal
> Priority: Critical
> Labels: beginner
> Attachments: HBASE-20716.master.001.patch, Screen Shot 2018-06-26 at
> 11.37.49 AM.png
>
>
> We have two means of getting at unsafe; UnsafeAccess and then internal to the
> Bytes class. They are effectively doing the same thing. We should have one
> avenue to Unsafe only.
> Many of our paths to Unsafe via UnsafeAccess traverse flags to check if
> access is available, if it is aligned and the order in which words are
> written on the machine. Each check costs -- especially if done millions of
> times a second -- and on occasion adds bloat in hot code paths. The unsafe
> access inside Bytes checks on startup what the machine is capable off and
> then does a static assign of the appropriate class-to-use from there on out.
> UnsafeAccess does not do this running the checks everytime. Would be good to
> have the Bytes behavior pervasive.
> The benefit of one access to Unsafe only is plain. The benefits we gain
> removing checks will be harder to measure though should be plain when you
> disassemble a hot-path; in a (very) rare case, the saved byte codes could be
> the difference between inlining or not.
--
This message was sent by Atlassian JIRA
(v7.6.3#76005)
