[jira] [Comment Edited] (HDDS-3254) Datanode memory increase so much

2020-03-26 Thread runzhiwang (Jira)


[ 
https://issues.apache.org/jira/browse/HDDS-3254?page=com.atlassian.jira.plugin.system.issuetabpanels:comment-tabpanel=17067371#comment-17067371
 ] 

runzhiwang edited comment on HDDS-3254 at 3/26/20, 6:06 AM:


[~shashikant] I have stop send request to s3gateway for one day, but the 
datanode physical memory does not come down, and the CPU is more than 100%.  I 
will try to reproduce it with some jvm options. And I will check RetryCache 
object size.

-Xms10g -Xmx10g -Xmn4g  -XX:+UseParallelGC -XX:MetaspaceSize=256m 
-XX:MaxMetaspaceSize=1024m -XX:SurvivorRatio=4 -verbose:gc 
-Xloggc:/var/datanode_gc.log -XX:+PrintGCTimeStamps -XX:+PrintGCDetails 
-XX:+HeapDumpOnOutOfMemoryError -XX:HeapDumpPath=/var/datanode_dump.hprof 
-XX:ParallelGCThreads=8 -XX:CMSInitiatingOccupancyFraction=70 
-XX:+UseCMSInitiatingOccupancyOnly


was (Author: yjxxtd):
[~shashikant] I have stop send request to s3gateway for one day, but the 
datanode physical memory does not come down, and the CPU is more than 100%.  I 
will try to reproduce it with some jvm options. And I will check RetryCache 
object size.

> Datanode memory increase so much
> 
>
> Key: HDDS-3254
> URL: https://issues.apache.org/jira/browse/HDDS-3254
> Project: Hadoop Distributed Data Store
>  Issue Type: Bug
>Reporter: runzhiwang
>Assignee: runzhiwang
>Priority: Major
> Attachments: image-2020-03-24-10-05-41-212.png, 
> image-2020-03-24-16-32-43-973.png, image-2020-03-24-16-33-20-795.png
>
>
> As the image shows, the physical memory of datanode increase to 11.2GB, and 
> then crash. I will find out the root cause.
>  !image-2020-03-24-10-05-41-212.png! 



--
This message was sent by Atlassian Jira
(v8.3.4#803005)

-
To unsubscribe, e-mail: ozone-issues-unsubscr...@hadoop.apache.org
For additional commands, e-mail: ozone-issues-h...@hadoop.apache.org



[jira] [Comment Edited] (HDDS-3254) Datanode memory increase so much

2020-03-26 Thread runzhiwang (Jira)


[ 
https://issues.apache.org/jira/browse/HDDS-3254?page=com.atlassian.jira.plugin.system.issuetabpanels:comment-tabpanel=17067371#comment-17067371
 ] 

runzhiwang edited comment on HDDS-3254 at 3/26/20, 6:06 AM:


[~shashikant] I have stop send request to s3gateway for one day, but the 
datanode physical memory does not come down, and the CPU is more than 100%.  I 
will try to reproduce it with following  jvm options. And I will check 
RetryCache object size.

-Xms10g -Xmx10g -Xmn4g  -XX:+UseParallelGC -XX:MetaspaceSize=256m 
-XX:MaxMetaspaceSize=1024m -XX:SurvivorRatio=4 -verbose:gc 
-Xloggc:/var/datanode_gc.log -XX:+PrintGCTimeStamps -XX:+PrintGCDetails 
-XX:+HeapDumpOnOutOfMemoryError -XX:HeapDumpPath=/var/datanode_dump.hprof 
-XX:ParallelGCThreads=8 -XX:CMSInitiatingOccupancyFraction=70 
-XX:+UseCMSInitiatingOccupancyOnly


was (Author: yjxxtd):
[~shashikant] I have stop send request to s3gateway for one day, but the 
datanode physical memory does not come down, and the CPU is more than 100%.  I 
will try to reproduce it with some jvm options. And I will check RetryCache 
object size.

-Xms10g -Xmx10g -Xmn4g  -XX:+UseParallelGC -XX:MetaspaceSize=256m 
-XX:MaxMetaspaceSize=1024m -XX:SurvivorRatio=4 -verbose:gc 
-Xloggc:/var/datanode_gc.log -XX:+PrintGCTimeStamps -XX:+PrintGCDetails 
-XX:+HeapDumpOnOutOfMemoryError -XX:HeapDumpPath=/var/datanode_dump.hprof 
-XX:ParallelGCThreads=8 -XX:CMSInitiatingOccupancyFraction=70 
-XX:+UseCMSInitiatingOccupancyOnly

> Datanode memory increase so much
> 
>
> Key: HDDS-3254
> URL: https://issues.apache.org/jira/browse/HDDS-3254
> Project: Hadoop Distributed Data Store
>  Issue Type: Bug
>Reporter: runzhiwang
>Assignee: runzhiwang
>Priority: Major
> Attachments: image-2020-03-24-10-05-41-212.png, 
> image-2020-03-24-16-32-43-973.png, image-2020-03-24-16-33-20-795.png
>
>
> As the image shows, the physical memory of datanode increase to 11.2GB, and 
> then crash. I will find out the root cause.
>  !image-2020-03-24-10-05-41-212.png! 



--
This message was sent by Atlassian Jira
(v8.3.4#803005)

-
To unsubscribe, e-mail: ozone-issues-unsubscr...@hadoop.apache.org
For additional commands, e-mail: ozone-issues-h...@hadoop.apache.org