[
https://issues.apache.org/jira/browse/CASSANDRA-8714?page=com.atlassian.jira.plugin.system.issuetabpanels:comment-tabpanel&focusedCommentId=14348475#comment-14348475
]
Robert Stupp commented on CASSANDRA-8714:
-----------------------------------------
I tried it anyway - just to know the results. Mixed workloads are a bit slower
- hard at the edge of measurement error ;)
{noformat:title=1kB}
[java] Benchmark Mode
Samples Score Error Units
[java] o.a.c.t.m.SetBytesAllocationBench.branch thrpt
10 148,969 ± 10,966 ops/us
[java] o.a.c.t.m.SetBytesAllocationBench.branch:branchDirect thrpt
10 74,985 ± 4,788 ops/us
[java] o.a.c.t.m.SetBytesAllocationBench.branch:branchHeap thrpt
10 73,985 ± 6,478 ops/us
[java] o.a.c.t.m.SetBytesAllocationBench.branchMixed thrpt
10 137,510 ± 11,395 ops/us
[java] o.a.c.t.m.SetBytesAllocationBench.trunk thrpt
10 141,650 ± 7,305 ops/us
[java] o.a.c.t.m.SetBytesAllocationBench.trunk:trunkDirect thrpt
10 72,715 ± 3,163 ops/us
[java] o.a.c.t.m.SetBytesAllocationBench.trunk:trunkHeap thrpt
10 68,935 ± 4,610 ops/us
[java] o.a.c.t.m.SetBytesAllocationBench.trunkMixed thrpt
10 136,652 ± 9,841 ops/us
{noformat}
{noformat:title=16b}
[java] Benchmark Mode
Samples Score Error Units
[java] o.a.c.t.m.SetBytesAllocationBench.branch thrpt
10 483,192 ± 17,577 ops/us
[java] o.a.c.t.m.SetBytesAllocationBench.branch:branchDirect thrpt
10 251,906 ± 20,247 ops/us
[java] o.a.c.t.m.SetBytesAllocationBench.branch:branchHeap thrpt
10 231,286 ± 12,939 ops/us
[java] o.a.c.t.m.SetBytesAllocationBench.branchMixed thrpt
10 439,530 ± 21,149 ops/us
[java] o.a.c.t.m.SetBytesAllocationBench.trunk thrpt
10 456,457 ± 37,239 ops/us
[java] o.a.c.t.m.SetBytesAllocationBench.trunk:trunkDirect thrpt
10 237,172 ± 34,706 ops/us
[java] o.a.c.t.m.SetBytesAllocationBench.trunk:trunkHeap thrpt
10 219,285 ± 12,587 ops/us
[java] o.a.c.t.m.SetBytesAllocationBench.trunkMixed thrpt
10 432,359 ± 22,173 ops/us
{noformat}
> row-cache: use preloaded jemalloc w/ Unsafe
> -------------------------------------------
>
> Key: CASSANDRA-8714
> URL: https://issues.apache.org/jira/browse/CASSANDRA-8714
> Project: Cassandra
> Issue Type: Sub-task
> Reporter: Robert Stupp
> Assignee: Robert Stupp
> Fix For: 3.0
>
> Attachments: 8714-2.txt, 8714-3.txt, 8714-4.txt, 8714.txt
>
>
> Using jemalloc via Java's {{Unsafe}} is a better alternative on Linux than
> using jemalloc via JNA.
--
This message was sent by Atlassian JIRA
(v6.3.4#6332)
