diff --git a/NEWS b/NEWS index 348707ec48a9f9a22874ebed9d98f280989212c3..77df888d4e76bfa67db8e5dcc931c57e1ad99d70 100644 --- a/NEWS +++ b/NEWS @@ -203,9 +203,6 @@ documents those changes that are of interest to users and admins. -- Sched/backfill - Change default max_job_bf parameter from 50 to 100. -- Added -I|--item-extract option to sh5util to extract data item from series. -* Changes in Slurm 2.6.7 -======================== - * Changes in Slurm 2.6.6 ======================== -- sched/backfill - Fix bug that could result in failing to reserve resources @@ -243,6 +240,7 @@ documents those changes that are of interest to users and admins. -- Update documentation about QOS limits -- Retry task exit message from slurmstepd to srun on message timeout. -- Correction to logic reserving all nodes in a specified partition. + -- Added support for selecting AMD GPU by setting GPU_DEVICE_ORDINAL env var. * Changes in Slurm 2.6.5 ======================== diff --git a/doc/html/team.shtml b/doc/html/team.shtml index 1d122ce6bf7c0987297f7cc9df5a2643457b5b1a..ed04a9a42a421f32cd86e9b6f11106000622b22f 100644 --- a/doc/html/team.shtml +++ b/doc/html/team.shtml @@ -35,6 +35,7 @@ Lead Slurm developers are: <li>Leith Bade (Australian National University)</li> <li>Troy Baer (The University of Tennessee, Knoxville)</li> <li>Susanne Balle (HP)</li> +<li>Dominik Bartkiewicz (University of Warsaw, Poland)</li> <li>Ralph Bean (Rochester Institute of Technology)</li> <li>Alexander Bersenev (Institute of Mathematics and Mechanics, Russia)</li> <li>David Bigagli (SchedMD)</li> @@ -187,6 +188,6 @@ Lead Slurm developers are: <!-- INDIVIDUALS, PLEASE KEEP IN ALPHABETICAL ORDER --> </ul> -<p style="text-align:center;">Last modified 18 November 2013</p> +<p style="text-align:center;">Last modified 5 February 2014</p> <!--#include virtual="footer.txt"--> diff --git a/doc/html/topology.shtml b/doc/html/topology.shtml index 542dc7c481d223747ceffc81ebaa1b4ec0d0a8fa..9a63de4ca151e227206764b311df8bcd2faf061e 100644 --- a/doc/html/topology.shtml +++ b/doc/html/topology.shtml @@ -132,6 +132,16 @@ SwitchName=s3 Nodes=tux[12-15] SwitchName=s4 Switches=s[0-3] </pre> +<p>Note that compute nodes on switches that lack a common parent switch can +be used, but no job will span leaf switches without a common parent. +For example, it is legal to remove the line "SwitchName=s4 Switches=s[0-3]" +from the above topology.conf file. +In that case, no job will span more than four compute nodes on any single leaf +switch. +This configuration can be useful if one wants to schedule multiple phyisical +clusters as a single logical cluster under the control of a single slurmctld +daemon.</p> + <h2>User Options</h2> <p>For use with the topology/tree plugin, user can also specify the maximum @@ -161,6 +171,6 @@ The value will be set component types listed in SLURM_TOPOLOGY_ADDR. Each component will be identified as either "switch" or "node". A period is used to separate each hardware component type.</p> -<p style="text-align:center;">Last modified 13 January 2014</p> +<p style="text-align:center;">Last modified 5 February 2014</p> <!--#include virtual="footer.txt"--> diff --git a/src/plugins/gres/gpu/gres_gpu.c b/src/plugins/gres/gpu/gres_gpu.c index ca7100d9e98f45906c9fd71a36e2db372006882f..b270f6c959404566be7b70e03157fad6efbe78bf 100644 --- a/src/plugins/gres/gpu/gres_gpu.c +++ b/src/plugins/gres/gpu/gres_gpu.c @@ -250,6 +250,8 @@ extern void job_set_env(char ***job_env_ptr, void *gres_ptr) if (dev_list) { env_array_overwrite(job_env_ptr,"CUDA_VISIBLE_DEVICES", dev_list); + env_array_overwrite(job_env_ptr,"GPU_DEVICE_ORDINAL", + dev_list); xfree(dev_list); } } @@ -294,6 +296,8 @@ extern void step_set_env(char ***job_env_ptr, void *gres_ptr) if (dev_list) { env_array_overwrite(job_env_ptr,"CUDA_VISIBLE_DEVICES", dev_list); + env_array_overwrite(job_env_ptr,"GPU_DEVICE_ORDINAL", + dev_list); xfree(dev_list); } }