Hi,
I think your case is mentioned in the FAQ Q30 in the "NOTE".
-- according to this you set CR_CPU and "CPU" only; no cores, no
threads, ...:
http://slurm.schedmd.com/faq.html
[...]
30. Slurm documentation refers to CPUs, cores and threads. What exactly
is considered a CPU?
If your nodes are
Am only guessing here, because we don't use hyper-threading with
Shared/OverSubscribe, but from the ThreadsPerCore entry in the man page:
If your system is configured with more than one thread per core, execution of
a different job on each thread is not supported unless you configure
Select
p.s. same issue on v16
On Wed, Sep 7, 2016 at 9:57 AM, andrealphus wrote:
>
> p.s. it's listing 36 processors with sinfo, and that theyre all being
> used, but it only running 18 jobs. So it looks like while it can see
> the 36 "processors" its only allocating on the core level and not the
> thr
p.s. it's listing 36 processors with sinfo, and that theyre all being
used, but it only running 18 jobs. So it looks like while it can see
the 36 "processors" its only allocating on the core level and not the
thread level;
squeue
JOBID PARTITION NAME USER ST TIME NODE
I tried changing the CPU flag int eh compute node section of the conf
file to 36, but it didnt make a difference, still limited to 18. Also
tried removing the flag and letting slurm calculate it from the other
info, e.g.;
Sockets=1 CoresPerSocket=18 ThreadsPerCore=2
also no change. Could it be a
a..I'll give that a try. Thanks Lachlan, feel better!
On Tue, Sep 6, 2016 at 6:49 PM, Lachlan Musicman wrote:
> No, sorry, I meant that your config file line needs to change:
>
>
> NodeName=localhost CPUs=36 RealMemory=12 Sockets=1 CoresPerSocket=18
> ThreadsPerCore=2 State=UNKNOWN
>
No, sorry, I meant that your config file line needs to change:
NodeName=localhost CPUs=36 RealMemory=12 Sockets=1 CoresPerSocket=18
ThreadsPerCore=2 State=UNKNOWN
--
The most dangerous phrase in the language is, "We've always done it this
way."
- Grace Hopper
On 7 September 2016 at 11:
Yup, thats what I expect too! Since Im brand new to slurm, not sure if
there is some other config option or srun flag to enable
multithreading
On Tue, Sep 6, 2016 at 5:42 PM, Lachlan Musicman wrote:
> Oh, I'm not 100% sure on this (home sick actually), but I think:
>
> NodeName=localhost CPUs=1
Oh, I'm not 100% sure on this (home sick actually), but I think:
NodeName=localhost CPUs=1 RealMemory=12 Sockets=1 CoresPerSocket=18
ThreadsPerCore=2 State=UNKNOWN
should have CPUs=36 (ie, ThreadsperCore*CoresPerSocket*Sockets)
cheers
L,
--
The most dangerous phrase in the language is,
Thanks Lachman, took threads-per-core and out same behavior, still
limited to 18.
On Tue, Sep 6, 2016 at 5:33 PM, Lachlan Musicman wrote:
> You don't need --threads-per-core.
>
> It's sufficient to have
>
> SelectType=select/cons_res
> SelectTypeParameters=CR_CPU
>
> then you should be able to g
You don't need --threads-per-core.
It's sufficient to have
SelectType=select/cons_res
SelectTypeParameters=CR_CPU
then you should be able to get to all 36.
cheers
L.
--
The most dangerous phrase in the language is, "We've always done it this
way."
- Grace Hopper
On 7 September 2016 at 10
one more follow up
This seems to limited to the number of cores. Anyway to change it so
that I can run up to the thread limit (18x2) concurrently?
Thanks!
On Tue, Sep 6, 2016 at 3:21 PM, andrealphus wrote:
>
> spoke too soon, so for posterity
>
> need to set, in the conf;
> SelectType=
spoke too soon, so for posterity
need to set, in the conf;
SelectType=select/con_res
SelectTypeParameters=CR_CPU
and in the script;
#SBATCH --threads-per-core=1
and DefMemPerCPU, did not matter...
On Tue, Sep 6, 2016 at 3:08 PM, andrealphus wrote:
>
> Hi all,
>
> Long time Torque user,
13 matches
Mail list logo
