1 |
On Thu, 2 Jun 2016 10:42:03 -0500 james wrote: |
2 |
> On 06/01/2016 06:20 PM, Justin Bronder wrote: |
3 |
> > Due to a lack of time and the fact I don't use any of these packages |
4 |
> > anymore, they are all up for grabs. |
5 |
> > |
6 |
> > - media-gfx/openmesh [no project] |
7 |
> > - sys-cluster/ganglia [cluster] |
8 |
> > - sys-cluster/ganglia-web [cluster] |
9 |
> > - sys-cluster/torque [cluster] |
10 |
> > - sys-cluster/munge [cluster] dependency of sys-cluster/torque |
11 |
> > - sys-cluster/mpe2 [cluster] |
12 |
> > |
13 |
> > Also, if there's anyone out there using the science overlay and empi |
14 |
> > who's feeling motivated, that work still needs a champion to get it |
15 |
> > into the main tree. If not, I'll probably drop it in a few months |
16 |
> > and open openmpi and mpich2 to project maintenance as well. I |
17 |
> > haven't been involved in HPC for over a decade now, it's time to |
18 |
> > pass the torch. |
19 |
> |
20 |
> |
21 |
> Hello Justin, |
22 |
> |
23 |
> I've been working on cluster ebuilds for a while (Apache Mesos, spark, |
24 |
> etc). I'm willing to proxy maintain these except torque. Assuming there |
25 |
> are no users of torque on gentoo (bgo seems inactive...it's dead; how |
26 |
> would I know?). |
27 |
|
28 |
Hey, don't be too quick on your judgement :) We are using torque |
29 |
(and maui) on three HPC setups, though we had to patch torque for |
30 |
various features. |
31 |
|
32 |
By the way, what scheduler/resource manager are you using for HPC? |
33 |
slurm ebuild seems to be even in worse state than torque one (2.6.3 |
34 |
is present, 16.05.0 is the latest upstream). |
35 |
|
36 |
Best regards, |
37 |
Andrew Savchenko |