[
https://issues.apache.org/jira/browse/HBASE-15160?page=com.atlassian.jira.plugin.system.issuetabpanels:comment-tabpanel&focusedCommentId=16035209#comment-16035209
]
Enis Soztutar commented on HBASE-15160:
---------------------------------------
Good finding. The histogram is supposed to adjust itself everytime
{{snapshotAndReset()}} is called which is every collection interval (10 secs
for example). Maybe this mechanism is not working as well as it should.
Anyways, we can pursue further in HBASE-18151.
Using millis is fine for now until HBASE-18151 is fixed. We typically use nanos
in newer code bases to have more granularity, but in this specific instance it
is better to have millis metrics than no metrics at all. Let me commmit v7
patch with a small renaming of latencyNanos to latencyMillis.
> Put back HFile's HDFS op latency sampling code and add metrics for monitoring
> -----------------------------------------------------------------------------
>
> Key: HBASE-15160
> URL: https://issues.apache.org/jira/browse/HBASE-15160
> Project: HBase
> Issue Type: Sub-task
> Affects Versions: 2.0.0, 1.1.2
> Reporter: Yu Li
> Assignee: Yu Li
> Priority: Critical
> Attachments: HBASE-15160.patch, HBASE-15160_v2.patch,
> HBASE-15160_v3.patch, hbase-15160_v4.patch, hbase-15160_v5.patch,
> hbase-15160_v6.patch, hbase-15160_v7.patch
>
>
> In HBASE-11586 all HDFS op latency sampling code, including fsReadLatency,
> fsPreadLatency and fsWriteLatency, have been removed. There was some
> discussion about putting them back in a new JIRA but never happened.
> According to our experience, these metrics are useful to judge whether issue
> lies on HDFS when slow request occurs, so we propose to put them back in this
> JIRA, and add the metrics for monitoring as well.
--
This message was sent by Atlassian JIRA
(v6.3.15#6346)
