Re: [hwloc-users] CPUSET shading using xml output of lstopo

Thanks for the info! On 1/31/2017 11:01 PM, Brice Goglin wrote: shade/highlight is included in the "cpuset" and "allowed_cpuset" fields inside the XML (even when not using --pid). By default, only what's "available" is displayed. If you want "disallowed" things to appear (in different colors),

Re: [hwloc-users] CPUSET shading using xml output of lstopo

shade/highlight is included in the "cpuset" and "allowed_cpuset" fields inside the XML (even when not using --pid). By default, only what's "available" is displayed. If you want "disallowed" things to appear (in different colors), add --whole-system when drawing (in the second command-line).

Re: [hwloc-users] CPUSET shading using xml output of lstopo

Thanks Brice, I believe I am rebuilding it as you say, but I can retry tomorrow at my desk. I looked in the XML and can see the taskset data, but since I cannot do --pid ###, it seems to not shade/highlight the tasksets. I'll drop the args that are redundant and try the exact form you list.

[hwloc-users] CPUSET shading using xml output of lstopo

Hi, I seem to be stuck. What I would like to do, is us lstopo to generate files that I can plot on another system (the nodes lack the necessary libraries for graphical output). That is, I would like to see something like lstopo --only core --pid ${pid} --taskset --no-io --no-bridges

Re: [OMPI users] Error using hpcc benchmark

Hi Wodel, As Howard mentioned, this is probably because many ranks and sending to a single one and exhausting the receive requests MQ. You can individually enlarge the receive/send requests queues with the specific variables (PSM_MQ_RECVREQS_MAX/ PSM_MQ_SENDREQS_MAX) or increase both with

Re: [OMPI users] MPI_Comm_spawn question

What version of OMPI are you using? > On Jan 31, 2017, at 7:33 AM, elistrato...@info.sgu.ru wrote: > > Hi, > > I am trying to write trivial master-slave program. Master simply creates > slaves, sends them a string, they print it out and exit. Everything works > just fine, however, when I add a

Re: [OMPI users] MPI_Type_create_struct segfault

Dear Gilles et al, You are correct. I solved the problem based on an email I got privately based on the same idea. I have just posted that private reply so the solution will be more widely known among us amateurs. Thanks, George Reeke On Tue, 2017-01-31 at 09:07 +0900, Gilles

Re: [OMPI users] MPI_Type_create_struct segfault

On Mon, 2017-01-30 at 16:31 -0500, George Reeke wrote: > Dear colleagues, >I am trying MPI_Type_create_struct for the first time. > I want to combine a small structure (two ints) with a vector of > variable length to send in a single message. Here is a simplified > extract of the relevant C

[OMPI users] MPI_Comm_spawn question

Hi, I am trying to write trivial master-slave program. Master simply creates slaves, sends them a string, they print it out and exit. Everything works just fine, however, when I add a delay (more than 2 sec) before calling MPI_Init on slave, MPI fails with MPI_ERR_SPAWN. I am pretty sure that

Re: [OMPI users] Error using hpcc benchmark

Hi Wodel Randomaccess part of HPCC is probably causing this. Perhaps set PSM env. variable - Export PSM_MQ_REVCREQ_MAX=1000 or something like that. Alternatively launch the job using mpirun --mca plm ob1 --host to avoid use of psm. Performance will probably suffer with this option

[OMPI users] Error using hpcc benchmark

Hi, I am n newbie in HPC world I am trying to execute the hpcc benchmark on our cluster, but every time I start the job, I get this error, then the job exits *compute017.22840Exhausted 1048576 MQ irecv request descriptors, which usually indicates a user program error or