Skip to content

Add a metric that exposes IO thread utilization#192

Draft
jasonk000 wants to merge 1 commit into
masterfrom
jkoch/loop-cpu-utilization-metric
Draft

Add a metric that exposes IO thread utilization#192
jasonk000 wants to merge 1 commit into
masterfrom
jkoch/loop-cpu-utilization-metric

Conversation

@jasonk000
Copy link
Copy Markdown
Member

This allows to spot issues where evcache is overloaded and supports some basic prediction of whether an instance might become overloaded with a significant traffic increase or whether the thread pool could be tuned.

This allows to spot issues where evcache is overloaded and supports
some basic prediction of whether an instance might become overloaded
with a significant traffic increase or whether the thread pool could be
tuned.
if (cpuNs < 0L) {
if (!negativeCpuTimeLogged) {
negativeCpuTimeLogged = true;
log.warn("Thread CPU time returned a negative value; skipping EVCache loop CPU utilization publish");
Copy link
Copy Markdown

Choose a reason for hiding this comment

The reason will be displayed to describe this comment to others. Learn more.

I'm a little confused as to what we're measuring in this PR - is this different from looking the values reported for CPU time on a thread dump?

Copy link
Copy Markdown
Member Author

Choose a reason for hiding this comment

The reason will be displayed to describe this comment to others. Learn more.

Yes, that's exactly it. Exposing this as a metric allows us to look at it easily and assess this as a potential tuning/hotspot if we move a client to a larger instance type (e.g. will 2x the traffic lead to congestion at evcache client).

Sign up for free to join this conversation on GitHub. Already have an account? Sign in to comment

Labels

None yet

Projects

None yet

Development

Successfully merging this pull request may close these issues.

2 participants