Skip to content
This repository has been archived by the owner on Oct 30, 2020. It is now read-only.

Allow evaluating scaling performance on real-world data #45

Open
jonnor opened this issue Nov 18, 2015 · 1 comment
Open

Allow evaluating scaling performance on real-world data #45

jonnor opened this issue Nov 18, 2015 · 1 comment
Milestone

Comments

@jonnor
Copy link
Member

jonnor commented Nov 18, 2015

For a particular config, the scaling info (GuvScaled) and end-to-end job info - it should be possible to see how we actually did. That is, how often, and under what conditions, did jobs miss their deadline.

Somewhat related to #43

@jonnor jonnor added this to the 0.2 milestone Nov 18, 2015
@jonnor jonnor changed the title Allow analyzing scaling decisions performance on real-world data Allow evaluating scaling performance on real-world data Nov 18, 2015
@jonnor
Copy link
Member Author

jonnor commented Mar 14, 2016

Being able to extract the input rates is interesting for #43 - so we can see if changing max config would/may have solved a scenario, or if bringing it down would have caused problems in the past.
This may realistically require #96

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

No branches or pull requests

1 participant