Mark Grondona
Mark Grondona
As noted in #3744, it would be useful to have some way for a process to determine the context in which it is running as it relates to Flux jobs,...
At least some Flux Python API calls that take a jobid expect an integer jobid and do not take any other jobid representations documented in [RFC 19](https://flux-framework.readthedocs.io/projects/flux-rfc/en/latest/spec_19.html). This is slightly...
A user was seeing this error from mvapich2-2.3.6: ```console $ flux mini run -N2 ./hello 0.627s: job.exception type=exec severity=0 MPI_Abort: Fatal error in MPI_Init: Other MPI error, error stack: MPIR_Init_thread(493)........:...
Just noticed this minor annoyance. When the `flux` bash completions are loaded, it ends up preventing filename completion, e.g. when using `flux mini batch -N1 `. It might take a...
Currently there is no design for this feature. Possibilities include: - simple job shell plugin for email notification. This may not allow an email notification in all cases such as...
As we discuss user job and queue limits (related #4302 #4306), we realized that it may be impossible to handle certain use cases for limits given current job manager design,...
This issue tracks the development of support for job notification (e.g. email on job events) for Flux jobs as required for the rollout of Flux as the native resource manager...
This issue tracks support for containing jobs to the resources they've been allocated using cgroups or other mechanisms as required for using Flux as the native resource manager on shared...
As described by @kathrynmohror in #2040: > From what Dong said, you are discussing the case where something like SCR would need to hold on to allocation resources after the...
It might be good to add ABI checks to CI to warn if and when PRs break ABI. See https://github.com/buildsi/libabigail-action for an example of how this might be done. Since...