[
https://issues.apache.org/jira/browse/HDFS-11194?page=com.atlassian.jira.plugin.system.issuetabpanels:comment-tabpanel&focusedCommentId=15813493#comment-15813493
]
Xiaobing Zhou edited comment on HDFS-11194 at 1/10/17 1:38 AM:
---------------------------------------------------------------
Thank you [~arpitagarwal] for the patch.
I've some comments.
# RollingAverages#getStats is using non-rolling mean states, it should use
rolling ones instead. See RollingAverages#snapshot for calculation of rolling
averages.
# DFS_METRICS_ROLLING_AVERAGES_WINDOW_SIZE_DEFAULT should be changed to the
same naming with DFS_METRICS_ROLLING_AVERAGE_WINDOW_LENGTH_KEY
# These parameters can be changed to be configurable.
SlowNodeDetector#minOutlierDetectionPeers
DataNodePeerMetrics#LOW_THRESHOLD_MS
SlowPeerTracker#MAX_NODES_TO_REPORT
# In BlockReceiver#receivePacket, after
trackSendPacketToLastNodeInPipeline(duration); It may need to change a bit,
e.g. if (duration > DataNodePeerMetrics#LOW_THRESHOLD_MS). or remove the
warning msg at all.
was (Author: xiaobingo):
Thank you [~arpitagarwal] for the patch.
I've some comments.
# RollingAverages#getStats is using non-rolling mean states, it should use
rolling ones instead. See RollingAverages#snapshot for calculation of rolling
averages.
# DFS_METRICS_ROLLING_AVERAGES_WINDOW_SIZE_DEFAULT should be changed to the
same naming with DFS_METRICS_ROLLING_AVERAGE_WINDOW_LENGTH_KEY
# These parameters can be changed to be configurable.
SlowNodeDetector#minOutlierDetectionPeers
DataNodePeerMetrics#LOW_THRESHOLD_MS
SlowPeerTracker#MAX_NODES_TO_REPORT
# In BlockReceiver#receivePacket, after
trackSendPacketToLastNodeInPipeline(duration); It may need to change a bit,
e.g. if (duration > DataNodePeerMetrics#LOW_THRESHOLD_MS). or remove the
warning msg at all.
> Maintain aggregated peer performance metrics on NameNode
> --------------------------------------------------------
>
> Key: HDFS-11194
> URL: https://issues.apache.org/jira/browse/HDFS-11194
> Project: Hadoop HDFS
> Issue Type: Bug
> Components: namenode
> Affects Versions: 2.8.0
> Reporter: Xiaobing Zhou
> Assignee: Arpit Agarwal
> Attachments: HDFS-11194-03-04.delta, HDFS-11194.01.patch,
> HDFS-11194.02.patch, HDFS-11194.03.patch, HDFS-11194.04.patch
>
>
> The metrics collected in HDFS-10917 should be reported to and aggregated on
> NameNode as part of heart beat messages. This will make is easy to expose it
> through JMX to users who are interested in them.
--
This message was sent by Atlassian JIRA
(v6.3.4#6332)
---------------------------------------------------------------------
To unsubscribe, e-mail: [email protected]
For additional commands, e-mail: [email protected]
