hyperqueue

hyperqueue copied to clipboard

* Some changes are summarized in docs and changelog * Benchmarks are not ported yet * ~~PyHQ is not ported yet.~~

spirali

Automatic allocation behavior clarification / feature request

3

Running `hyperqueue 0.12.0` (prebuilt downloaded from github) using slurm 21.08.7 on "Red Hat Enterprise Linux Server 7.9 " Is it intended behavior that a HQ job submission will trigger a...

Nortamo

Closes: #480

User3574

Now that the `hq task info` table is vertical, we can expand the previously merged attributes (Paths -> stdout/stderr/workdir, Times -> Timespan/...). I would also move the `Error` value as...

Kobzol

I think that it should be possible to select multiple tasks, e.g. `hq task info 1 2-3`. The task tables should just be printed below one another. Also it would...

Kobzol

Sometimes it's quite important to know on which NUMA nodes and sockets was some task running. We should have this data available in the log (individual cores of a task...

Kobzol

Pass the expected remaining time to tasks

2

For some tasks it might be useful to know what is the expected time for which they might run (for example so that they can shorten their run or do...

Kobzol

This would give the users a chance to pause new allocations momentarily, for example to change the submitted script or to avoid overloading the system.

Kobzol

Too many failed allocations

1

Hi, I've been running into the error in the attached screenshot when running an `alloc` with `slurm` that used to work (before recent maintenance on the cluster). I was wondering,...

louisponet

Alloc crash + new allocs have (deleted) in jobscript

3

Hi, I've been running hq on a slurm based cluster, with autoallocs. Sometimes for some reason the server will become inactive/not reachable after which usually all my `allocs` have crashed....

louisponet