Skip to content
New issue

Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.

By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.

Already on GitHub? Sign in to your account

Mention coordinated omission in performance docs #26129

Closed
wants to merge 2 commits into from

Conversation

maxandersen
Copy link
Member

trying to explain to users that when doing performance measurements be aware of coordinated ommision in various tools but noticed we did not mention it in our own performance guide.

here is a suggestion on a way we could inform/educate. feedback welcome!

@geoand
Copy link
Contributor

geoand commented Jun 14, 2022

Thanks, I'll have a close look tomorrow

* how we measure memory usage
* how we measure startup time
* which additional flags will Quarkus apply to native-image by default

All of our tests are run on the same hardware for a given batch.
It goes without saying but it's better when you say it.

== Coordinated Omission Problem in Tools

When measuring performance of a framework like Quarkus the latency experience by users are especially interesting and for that there are many different tools. Unfortunately, many fail to measure the latency correctly and instead fall short and create the Coordinate Omission problem. Meaning tools fails to acoomodate for delays to submit new requests when system is under load and aggregate these numbers making the latency and throughput numbers very misleading.
Copy link
Contributor

Choose a reason for hiding this comment

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

Suggested change
When measuring performance of a framework like Quarkus the latency experience by users are especially interesting and for that there are many different tools. Unfortunately, many fail to measure the latency correctly and instead fall short and create the Coordinate Omission problem. Meaning tools fails to acoomodate for delays to submit new requests when system is under load and aggregate these numbers making the latency and throughput numbers very misleading.
When measuring performance of a framework like Quarkus, the latency numbers experienced by users are especially interesting and for measuring that, many different tools exist. Unfortunately, many fail to measure the latency correctly and instead suffer from the Coordinate Omission problem - meaning tools fails to accomodate for delays to submit new requests when system is under load and aggregate these numbers, thus rendering their reported latency and throughput numbers misleading.


A good walkthrough of the issue is https://www.youtube.com/watch?v=lJ8ydIuPFeU[this video] where Gil Tene the author of wrk2 explains the issue and https://www.youtube.com/watch?v=xdG8b9iDYbE[Quarkus Insights #22] have John O'Hara from Quarkus performance team show how it can show up.

Although that video and related papers and articles date all back to 2015 then even today you will find tools that fall short with the coordinated oission problem
Copy link
Contributor

@geoand geoand Jun 15, 2022

Choose a reason for hiding this comment

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

Suggested change
Although that video and related papers and articles date all back to 2015 then even today you will find tools that fall short with the coordinated oission problem
Although that video and related papers and articles all date back to 2015, unfortunately many of the widely used tools even today suffer from Coordinated Omission problem.

@gsmet gsmet changed the title Mention coordinated ommision in performance docs Mention coordinated omission in performance docs Jun 16, 2022
@@ -9,13 +9,34 @@ include::./attributes.adoc[]

This guide covers:

* Coordinated omission Problem in Tools
Copy link
Member

Choose a reason for hiding this comment

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

I wouldn't have this as first bullet. In fact I don't think it belongs in this guide - no strong opinion about that, but at least let's not make this aspect too distracting from the primary content.

@gsmet
Copy link
Member

gsmet commented Aug 9, 2022

@maxandersen friendly ping, see especially @Sanne 's comment above.

@gsmet
Copy link
Member

gsmet commented Feb 2, 2023

Closing for lack of activity.

@gsmet gsmet closed this Feb 2, 2023
@quarkus-bot quarkus-bot bot added the triage/invalid This doesn't seem right label Feb 2, 2023
@github-actions
Copy link

github-actions bot commented Feb 2, 2023

🙈 The PR is closed and the preview is expired.

Sign up for free to join this conversation on GitHub. Already have an account? Sign in to comment
Labels
Projects
None yet
Development

Successfully merging this pull request may close these issues.

4 participants