Mark Grondona

If you think about the use case in a system instance, there are likely to be many users running `flux resource list` regularly, so caching the result even if it...

> I think this is a good idea, and I think would include assembling some sort of graph deltas that could be used to update R all, R down, and...

Yes, that is a known issue (though I'd forgotten how bad it was). The command is in Python and also has to go through gyrations to collect identical lines of...

Since flux-framework/flux-core#5796 is being merged, solving this issue is not a priority.

Here's a first attempt at a parameter study that investigates different job sizes and counts with `rv1` vs `rv1_nosched`. Each test instance runs the script found at the bottom of...

Ran similar tests without node exclusive matching. All I did was change `-N NNODES` to `-n 48*NNODES`. Similar results, but a few of the larger `rv1` OOMed, so I didn't...

I was going to try this same set of experiments with `sched-simple`, but it turns out this test setup won't work with the simple scheduler. This is because the instance...

> That sounds like a bug, if ironically a useful one for testing this. Agree. Issue opened: #1040

Ok, figured out the core `resource` module can be loaded with the `monitor-force-up` option and was able to run these same tests with sched-simple juts for comparison: ``` FORMAT NJOBS...

FYI - I edited the test script above to add the `monitor-force-up` option to `flux module load resource`. This will be required once #1042 is merged.