[
https://issues.apache.org/jira/browse/HBASE-28485?page=com.atlassian.jira.plugin.system.issuetabpanels:comment-tabpanel&focusedCommentId=17834068#comment-17834068
]
Charles Connell edited comment on HBASE-28485 at 4/5/24 12:24 AM:
------------------------------------------------------------------
I've attached a flamegraph [^async-prof-pid-1324144-cpu-1.html] showing
{{ZstdDecompressCtx}} constructor taking 0.81% of RegionServer CPU time. This
is during normal operation on one of my company's RegionServer.
I've also attached a flamegraph
[^async-prof-flamegraph-cpu_event-1712150670836-cpu.html] of a pathological
RegionServer performance, where {{ZstdDecompressCtx}} it takes 1.16% of CPU
time, compared to 4% taken by all the rest of the decompression process.
was (Author: charlesconnell):
I've attached a [^async-prof-pid-1324144-cpu-1.html] showing
{{ZstdDecompressCtx}} constructor taking 0.81% of RegionServer CPU time. This
is during normal operation on one of my company's RegionServer.
I've also attached a [^async-prof-flamegraph-cpu_event-1712150670836-cpu.html]
of a pathological RegionServer performance, where {{ZstdDecompressCtx}} it
takes 1.16% of CPU time, compared to 4% taken by all the rest of the
decompression process.
> Re-use ZstdDecompressCtx/ZstdCompressCtx for performance
> --------------------------------------------------------
>
> Key: HBASE-28485
> URL: https://issues.apache.org/jira/browse/HBASE-28485
> Project: HBase
> Issue Type: Improvement
> Reporter: Charles Connell
> Assignee: Charles Connell
> Priority: Major
> Attachments: async-prof-flamegraph-cpu_event-1712150670836-cpu.html,
> async-prof-pid-1324144-cpu-1.html
>
>
> The zstd documentation recommends re-using context objects when possible,
> because their creation has some expense. They can be more cheaply reset than
> re-created. In {{ZstdDecompressor}} and {{ZstdCompressor}}, we create a new
> context object for every call to {{decompress()}} and {{compress()}}. In CPU
> profiles I've taken at my company, the constructor of {{ZstdDecompressCtx}}
> can sometimes represent 10-25% of the time spent in zstd decompression, which
> itself is 5-10% of a RegionServer's total CPU time. Avoiding this performance
> penalty won't lead to any massive performance boost, but is a nice little win.
--
This message was sent by Atlassian Jira
(v8.20.10#820010)
