Hello This is a widespread problem with AMD machines. Buggy platform reporting invalid L3 cache information in this case. Upgrading the BIOS may help. Anyway, I guess Slurm doesn't care much about L3 cache affinity, so you can ignore the error by setting HWLOC_HIDE_ERRORS=1 in the environment. More details also http://www.open-mpi.org/projects/hwloc/doc/v1.10.0/a00028.php#faq_os_error Brice
Le 17/01/2015 20:41, Joseph Mingrone a écrit : > Hello, > > Here is the error message we see when staring slurmd or running > hwloc-info. > > **************************************************************************** > * hwloc has encountered what looks like an error from the operating system. > * > * L3 (P#6 cpuset 0x000003f0) intersects with NUMANode (P#0 cpuset 0x0000003f) > without inclusion! > * Error occurred in topology.c line 940 > * > * Please report this error message to the hwloc user's mailing list, > * along with any relevant topology information from your platform. > **************************************************************************** > depth 0: 1 Machine (type #1) > depth 1: 4 Socket (type #3) > depth 2: 8 NUMANode (type #2) > depth 3: 8 L3Cache (type #4) > depth 4: 24 L2Cache (type #4) > depth 5: 24 L1iCache (type #4) > depth 6: 48 L1dCache (type #4) > depth 7: 48 Core (type #5) > depth 8: 48 PU (type #6) > > This is a system with four 12-core 6348 AMD CPUs. > > Other nodes with older AMD CPUs also running FreeBSD 10.1 don't report > the error. > > If there is any other information I can provide, please let me know. > > Joseph > _______________________________________________ > hwloc-users mailing list > hwloc-us...@open-mpi.org > Subscription: http://www.open-mpi.org/mailman/listinfo.cgi/hwloc-users > Link to this post: > http://www.open-mpi.org/community/lists/hwloc-users/2015/01/1150.php
