[
https://issues.apache.org/jira/browse/YARN-5995?page=com.atlassian.jira.plugin.system.issuetabpanels:comment-tabpanel&focusedCommentId=15812620#comment-15812620
]
Jian He commented on YARN-5995:
-------------------------------
As said earlier, read won't be that useful as it only happens on RM start up to
load the data. It's a one-time value which dos not require metrics.
IMO, We need to think about how the metrics can actually be used for
performance analysis, that is, how much impact the store operation can affect
RM's execution, i.e. how much delay it can incur. Metrics like data written per
sec looks more like measuring ZK throughput which may not be that useful.
I think what we need is to surface the time spent on write operation. With that
in mind, we may have
1) a Histogram for the time spent for each write op ?
2) total no of write operations
> Add RMStateStore metrics to monitor all RMStateStoreEventTypeTransition
> performance
> -----------------------------------------------------------------------------------
>
> Key: YARN-5995
> URL: https://issues.apache.org/jira/browse/YARN-5995
> Project: Hadoop YARN
> Issue Type: Improvement
> Components: metrics, resourcemanager
> Affects Versions: 2.7.1
> Environment: CentOS7.2 Hadoop-2.7.1
> Reporter: zhangyubiao
> Assignee: zhangyubiao
> Labels: patch
> Attachments: YARN-5995.0001.patch, YARN-5995.0002.patch,
> YARN-5995.patch
>
>
> Add RMStateStore metrics to monitor all RMStateStoreEventTypeTransition
> performance
--
This message was sent by Atlassian JIRA
(v6.3.4#6332)
---------------------------------------------------------------------
To unsubscribe, e-mail: [email protected]
For additional commands, e-mail: [email protected]
