Open MPI logo

Hardware Locality Users' Mailing List Archives

  |   Home   |   Support   |   FAQ   |   all Hardware Locality Users mailing list

Subject: Re: [hwloc-users] Hwloc error.
From: Brice Goglin (Brice.Goglin_at_[hidden])
Date: 2012-05-30 11:24:41


Le 30/05/2012 17:22, Samuel Thibault a écrit :
> Hello,
>
> John Hanks, le Wed 30 May 2012 17:03:47 +0200, a écrit :
>> * Hwloc has encountered what looks like an error from the operating system.
>> *
>> * object intersection without inclusion!
>> * Error occurred in topology.c line 594
> There is indeed something odd with what the Linux kernel reports:
>
> os node 1 has cpuset 0x0003ffff
> os node 2 has cpuset 0x00fc0000
>
> as can be seen in /sys/devices/system/node/node*/cpumap, but
>
> os socket 0 has cpuset 0x00000fff
> os socket 1 has cpuset 0x00fff000
>
> as can be seen in /sys/devices/system/cpu/cpu*/topology/physical_package_id
>
> i.e. the kernel reports that socket 0 is completely in node 1, while
> socket 1 is half in node 1 and half in node 2. Do you have more
> information about what the machine actually contains socket- and
> NUMA-wise? The dell website is not really felpful, it talks about 4-16
> cores for the DL165 G7, while you have 24.
>

It's a dual-opteron machine with AMD Magny-cours processors. Two 12-core
sockets, with 2 NUMA nodes in each. Maybe the BIOS wasn't updated for
these processors.

Brice