You are viewing a plain text version of this content. The canonical link for it is here.
Posted to issues@ozone.apache.org by "mingchao zhao (Jira)" <ji...@apache.org> on 2021/10/25 14:27:00 UTC
[jira] [Comment Edited] (HDDS-5685) Ozone Streaming Performance
Test
[ https://issues.apache.org/jira/browse/HDDS-5685?page=com.atlassian.jira.plugin.system.issuetabpanels:comment-tabpanel&focusedCommentId=17433792#comment-17433792 ]
mingchao zhao edited comment on HDDS-5685 at 10/25/21, 2:26 PM:
----------------------------------------------------------------
Hi [~szetszwo], Recently I did performance test on streaming use pipline model. Here are my results([test doc|https://docs.google.com/document/d/1crXT4BE8ueRakddiVoVl7E_BH--FcU54YWeThHOx2Lg/edit?usp=sharing]):
!image-2021-10-25-22-26-37-764.png!
The fastest performance I measured was 57872 ms, which is very close to HDFS's 54292ms.
But it can also be very slow, although not very often. At this time, I find that datanode always generates a lot of timeout WARNS.
There is very little feedback in the log and I am wondering how to avoid this kind of problem. Do you have any suggestions?
{code:java}
2021-10-25 10:49:05,450 [java.util.concurrent.ThreadPoolExecutor$Worker@4f2d0dbd[State = -1, empty queue]] WARN org.apache.ratis.grpc.GrpcUtil: Timed out gracefully shutting down connection: ManagedChannelOrphanWrapper{delegate=ManagedChannelImpl{logId=1006, target=9.29.167.18:9858}}.
2021-10-25 10:49:11,466 [java.util.concurrent.ThreadPoolExecutor$Worker@7f680468[State = -1, empty queue]] WARN org.apache.ratis.grpc.GrpcUtil: Timed out gracefully shutting down connection: ManagedChannelOrphanWrapper{delegate=ManagedChannelImpl{logId=1019, target=9.29.167.18:9858}}.
{code}
was (Author: micahzhao):
Hi [~szetszwo], Recently I did performance test on streaming use pipline model. Here are my results([test doc|https://docs.google.com/document/d/1crXT4BE8ueRakddiVoVl7E_BH--FcU54YWeThHOx2Lg/edit?usp=sharing]):
!screenshot-4.png!
The fastest performance I measured was 57872 ms, which is very close to HDFS's 54292ms.
But it can also be very slow, although not very often. At this time, I find that datanode always generates a lot of timeout WARNS.
There is very little feedback in the log and I am wondering how to avoid this kind of problem. Do you have any suggestions?
{code:java}
2021-10-25 10:49:05,450 [java.util.concurrent.ThreadPoolExecutor$Worker@4f2d0dbd[State = -1, empty queue]] WARN org.apache.ratis.grpc.GrpcUtil: Timed out gracefully shutting down connection: ManagedChannelOrphanWrapper{delegate=ManagedChannelImpl{logId=1006, target=9.29.167.18:9858}}.
2021-10-25 10:49:11,466 [java.util.concurrent.ThreadPoolExecutor$Worker@7f680468[State = -1, empty queue]] WARN org.apache.ratis.grpc.GrpcUtil: Timed out gracefully shutting down connection: ManagedChannelOrphanWrapper{delegate=ManagedChannelImpl{logId=1019, target=9.29.167.18:9858}}.
{code}
> Ozone Streaming Performance Test
> --------------------------------
>
> Key: HDDS-5685
> URL: https://issues.apache.org/jira/browse/HDDS-5685
> Project: Apache Ozone
> Issue Type: Sub-task
> Reporter: mingchao zhao
> Assignee: mingchao zhao
> Priority: Major
> Attachments: image-2021-08-27-11-07-36-526.png, image-2021-10-25-22-26-37-764.png, screenshot-1.png, screenshot-2.png, screenshot-3.png, screenshot-4.png
>
>
> We can test and discuss the performance of Ozone Streaming under this JIRA.
--
This message was sent by Atlassian Jira
(v8.3.4#803005)
---------------------------------------------------------------------
To unsubscribe, e-mail: issues-unsubscribe@ozone.apache.org
For additional commands, e-mail: issues-help@ozone.apache.org