[
https://issues.apache.org/jira/browse/HBASE-15160?page=com.atlassian.jira.plugin.system.issuetabpanels:comment-tabpanel&focusedCommentId=16034497#comment-16034497
]
Phil Yang commented on HBASE-15160:
-----------------------------------
[~carp84] I think the performance issue is not because the performance of
nanoTime (although it is a little slower than currentTimeMillis), the issue is
Histogram use several buckets to estimate percentile and it assums a uniform
distribution within a range and the max value is only 1000 or maybe less (see
https://github.com/apache/hbase/blob/master/hbase-metrics/src/main/java/org/apache/hadoop/hbase/metrics/impl/FastLongHistogram.java#L69-L93
) So if you use nanoTime, all values is much longer than 1000 and they are all
in the last bucket. Then the bottleneck is single one LongAdder.
> 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)
