[
https://issues.apache.org/jira/browse/HBASE-5533?page=com.atlassian.jira.plugin.system.issuetabpanels:all-tabpanel
]
Shaneal Manek updated HBASE-5533:
---------------------------------
Attachment: hbase5533-0.92-v2.patch
Re hadoop-metrics.properties: You are right - I didn't mean to include that
change.
Re BlockingQueue contention: I don't expect much contention since there is only
one (non-blocking) 'offer()' per FS I/O (figure, at the absolute worst with a
large array of fast SSDs, we're doing we're still only doing a a few tens of
thousands of IOs/second). I've attached a microbenchmark showing the current
technique works fine for up to at least a few million offers()/second under
heavy contention (with 99th percentile latencies under 0.001 milliseconds). If
you still suspect this might be troublesome, I'd be happy to stripe the
accesses to reducing contention (we don't need a strict ordering). I think
that's probably unnecessary complexity though.
Re logging: Good point - changed it to not log more than once per 30 seconds.
Re AtomicLong counters: Didn't know about the Cliff Click couhbanters - I
switched to using them.
> Add more metrics to HBase
> -------------------------
>
> Key: HBASE-5533
> URL: https://issues.apache.org/jira/browse/HBASE-5533
> Project: HBase
> Issue Type: Improvement
> Affects Versions: 0.92.0
> Reporter: Shaneal Manek
> Assignee: Shaneal Manek
> Priority: Minor
> Attachments: hbase-5533-0.92.patch, hbase5533-0.92-v2.patch
>
>
> To debub/monitor production clusters, there are some more metrics I wish I
> had available.
> In particular:
> - Although the average FS latencies are useful, a 'histogram' of recent
> latencies (90% of reads completed in under 100ms, 99% in under 200ms, etc)
> would be more useful
> - Similar histograms of latencies on common operations (GET, PUT, DELETE)
> would be useful
> - Counting the number of accesses to each region to detect hotspotting
> - Exposing the current number of HLog files
--
This message is automatically generated by JIRA.
If you think it was sent incorrectly, please contact your JIRA administrators:
https://issues.apache.org/jira/secure/ContactAdministrators!default.jspa
For more information on JIRA, see: http://www.atlassian.com/software/jira
