Refresh support for watchdog and io-watchdog
Open
@rhaas80 is already working on this.
Since Feb 24, 2021.
- Dominant language
- C
- Stars
- 108
- Forks
- 37
- PR merge metrics
- No merged PRs in 30d
Description
With SCR, it's important to catch hanging jobs, so that a checkpoint can be flushed from cache before losing an allocation. We have two ways to do this, using io-watchdog (https://github.com/grondo/io-watchdog) and our own built-in watchdog script https://github.com/LLNL/scr/blob/develop/scripts/common/scr_watchdog.in.
We should test that both of these still work.
As a third option, PMIX defines a ``heartbeat`` API, which is meant to catch hanging jobs. If this works, we should look at using that since it may be a more portable method.
https://github.com/pmix/pmix-standard/blob/master/Chap_API_Job_Mgmt.tex
Contributor guide
First steps
- Read the whole issue, then the project's contributing guide.
- Comment on the issue to say you are picking it up — it saves two people doing the same work.
- Fork the repository and make your change on a branch.
- Open a pull request that references the issue number.
Assessment
This issue has not been assessed yet.