[
https://issues.apache.org/jira/browse/HDDS-8897?page=com.atlassian.jira.plugin.system.issuetabpanels:comment-tabpanel&focusedCommentId=17737034#comment-17737034
]
GuoHao edited comment on HDDS-8897 at 6/26/23 8:19 AM:
-------------------------------------------------------
Hi [~sodonnell] [~adoroszlai]
Let's continue the discussion on this issue, as requested I conducted the test
and here are my results.
The test config:
* 4 datanodes
* 24disk pre datanode
* ozone.scm.ec.pipeline.minimum is 5
* the test cluster scm ec pipeline num is 42
{code:java}
$ ./ozone admin pipeline list --replication=rs-1-1-512k --type=EC | wc -l
42 {code}
cpu profile for scm:
{code:java}
$ sh profiler.sh -d 60 -e cpu -f /tmp/profile-scm-60s-cpu.svg [PID] {code}
[^profile-scm-60s-cpu.svg]
lock profile for scm:
{code:java}
$ sh profiler.sh -d 60 -e lock -f /tmp/profile-scm-60s-lock.svg [PID] {code}
[^profile-scm-60s-lock.svg]
was (Author: nicholas niu):
The test config:
* 4 datanodes
* 24disk pre datanode
* ozone.scm.ec.pipeline.minimum is 5
* the test cluster scm ec pipeline num is 42
{code:java}
$ ./ozone admin pipeline list --replication=rs-1-1-512k --type=EC | wc -l
42 {code}
cpu profile for scm:
{code:java}
$ sh profiler.sh -d 60 -e cpu -f /tmp/profile-scm-60s-cpu.svg [PID] {code}
[^profile-scm-60s-cpu.svg]
lock profile for scm:
{code:java}
$ sh profiler.sh -d 60 -e lock -f /tmp/profile-scm-60s-lock.svg [PID] {code}
[^profile-scm-60s-lock.svg]
> ec container has too high latency when allocate blocks
> ------------------------------------------------------
>
> Key: HDDS-8897
> URL: https://issues.apache.org/jira/browse/HDDS-8897
> Project: Apache Ozone
> Issue Type: Improvement
> Reporter: GuoHao
> Assignee: Stephen O'Donnell
> Priority: Blocker
> Labels: pull-request-available
> Attachments: image-2023-06-21-21-58-15-052.png,
> image-2023-06-21-21-58-50-518.png, image-2023-06-21-23-53-56-534.png,
> profile-scm-60s-cpu.svg, profile-scm-60s-lock.svg
>
>
> ec container has too high latency when allocate blocks
>
> I use ec in a high concurrency situation, I configure the metric on scm, and
> as concurrency gradually increases, the latency of the allocate block
> increases.
>
> allocate block ops：
> !image-2023-06-21-21-58-50-518.png!
>
> average latency：
> !image-2023-06-21-21-58-15-052.png!
>
--
This message was sent by Atlassian Jira
(v8.20.10#820010)
---------------------------------------------------------------------
To unsubscribe, e-mail: [email protected]
For additional commands, e-mail: [email protected]
