[
https://issues.apache.org/jira/browse/CASSANDRA-20250?page=com.atlassian.jira.plugin.system.issuetabpanels:comment-tabpanel&focusedCommentId=17927124#comment-17927124
]
Benedict Elliott Smith commented on CASSANDRA-20250:
----------------------------------------------------
I think it's broadly ready for review yes, though I expect I will have further
suggestions once I have time to properly review it. I agree with your suggested
improvements.
I think when it comes to reclaiming ids, we should keep it simple. If we have
cleaned up all of the old metrics due to the threads all referencing it being
dead, we can immediately re-use the id. I would consider maintaining a
{{BitSet}} of ids where we know this is true, that is maintained in a
synchronised block.
One thing I have been thinking about is whether we really should use
PhantomReference for managing lifetimes of unused metrics, as otherwise we are
holding onto a strong reference to a Thread - so if anything causes our metric
maintenance to get behind we may hold onto many GC roots. This isn't a likely
event, but it does make me slightly uneasy. The additional GC cost of tracking
one PhantomReference per Thread allocated should be very low, and would avoid
any concern here.
> Provide the ability to disable specific metrics collection
> ----------------------------------------------------------
>
> Key: CASSANDRA-20250
> URL: https://issues.apache.org/jira/browse/CASSANDRA-20250
> Project: Apache Cassandra
> Issue Type: New Feature
> Components: Observability/Metrics
> Reporter: Dmitry Konstantinov
> Assignee: Dmitry Konstantinov
> Priority: Normal
> Attachments: 5.1_profile_cpu.html,
> 5.1_profile_cpu_without_metrics.html, 5.1_tl4_profile_cpu.html,
> Histogram_AtomicLong.png, async_profiler_cpu_profiles.zip,
> cpu_profile_insert.html, jmh-result.json, vmstat.log,
> vmstat_without_metrics.log
>
>
> Cassandra has a lot of metrics collected, many of them are collected per
> table, so their instance number is multiplied by number of tables. From one
> side it gives a better observability, from another side metrics are not for
> free, there is an overhead associated with them:
> 1) CPU overhead: in case of simple CPU bound load: I already see like 5.5% of
> total CPU spent for metrics in cpu framegraphs for read load and 11% for
> write load.
> Example: [^cpu_profile_insert.html] (search by "codahale" pattern). The
> framegraph is captured using Async profiler build:
> async-profiler-3.0-29ee888-linux-x64
> 2) memory overhead: we spend memory for entities used to aggregate metrics
> such as LongAdders and reservoirs + for MBeans (String concatenation within
> object names is a major cause of it, for each table+metric name combination a
> new String is created)
>
> The idea of this ticket is to allow an operator to configure a list of
> disabled metrics in cassandra.yaml, like:
> {code:java}
> disabled_metrics:
> - metric_a
> - metric_b
> {code}
> From implementation point of view I see two possible approaches (which can be
> combined):
> # Generic: when a metric is registering if it is listed in disabled_metrics
> we do not publish it via JMX and provide a noop implementation of metric
> object (such as histogram) for it.
> Logging analogy: log level check within log method
> # Specialized: for some metrics the process of value calculation is not for
> free and introduces an overhead as well, in such cases it would be useful to
> check within specific logic using an API (like: isMetricEnabled) do we need
> to do it. Example of such metric:
> ClientRequestSizeMetrics.recordRowAndColumnCountMetrics
> Logging analogy: an explicit 'if (isDebugEnabled())' condition used when a
> message parameter is expensive.
--
This message was sent by Atlassian Jira
(v8.20.10#820010)
---------------------------------------------------------------------
To unsubscribe, e-mail: commits-unsubscr...@cassandra.apache.org
For additional commands, e-mail: commits-h...@cassandra.apache.org
