- 28 Sep, 2011 1 commit
-
-
Danny Auble authored
-
- 27 Sep, 2011 1 commit
-
-
Mark A. Grondona authored
The slurmctld code that processes job notify messages unecessarily restricts these messages to be from the slurm user or root. This patch allows users to send notifications to their own jobs.
-
- 26 Sep, 2011 4 commits
-
-
Danny Auble authored
-
Danny Auble authored
-
Danny Auble authored
-
Morris Jette authored
Many cosmetic modifications to eliminate warning message from GCC version 4.6 compiler, mostly due to unused variables.
-
- 19 Sep, 2011 1 commit
-
-
Danny Auble authored
-
- 17 Sep, 2011 1 commit
-
-
Danny Auble authored
jobs happen to be running on blocks not in the new config.
-
- 16 Sep, 2011 2 commits
-
-
Morris Jette authored
salloc/mpirun does not play well together with task affinity socket binding. The following example illustrates the problem. [sulu] (slurm) mnp> salloc -p bones-only -N1-1 -n3 --cpu_bind=socket mpirun cat /proc/self/status | grep Cpus_allowed_list salloc: Granted job allocation 387 -------------------------------------------------------------------------- An invalid physical processor id was returned ... The problem is that with mpirun jobs Slurm launches only a single task, regardless of the value of -n. This confuses the socket binding logic in task affinity. The result is that task affinity binds the task to only a single cpu, instead of all the allocated cpus on the socket. When mpi attempts to bind to any of the other allocated cpus on the socket, it gets the "invalid physical processor id" error. Note that the problem may occur even if socket binding is not explicitly requested by the user. If task/affinity is configured and the allocated CPUs are a whole number of sockets, Slurm will use "implicit auto binding" to sockets, triggering the problem. Patch from Martin Perry (Bull).
-
Morris Jette authored
Update reservation web page to describe mechanism to reserve CPUs rather than whole nodes and provide an example.
-
- 15 Sep, 2011 3 commits
-
-
Morris Jette authored
Avoid clearing a job's reason from JobHeldAdmin or JobHeldUser when it is otherwise updated using scontrol or sview commands. Patch based upon work by Phil Eckert (LLNL).
-
Morris Jette authored
Do not remove the backup slurmctld's pid file when it assumes control, only when it actually shuts down. Patch from Andriy Grytsenko (Massive Solutions Limited).
-
Danny Auble authored
-
- 14 Sep, 2011 3 commits
-
-
Danny Auble authored
-
Danny Auble authored
variable wasn't initialized in the job structure making it so that job wouldn't run.
-
Danny Auble authored
-
- 13 Sep, 2011 1 commit
-
-
Danny Auble authored
-
- 12 Sep, 2011 16 commits
-
-
Danny Auble authored
on a L/P system or Q.
-
Danny Auble authored
-
Danny Auble authored
switching from a bluegene to a regular system with sview.
-
Danny Auble authored
-
Danny Auble authored
-
Danny Auble authored
-
Danny Auble authored
when using multi-cluster mode in sview
-
Danny Auble authored
-
Danny Auble authored
-
Danny Auble authored
type set it that way right off the start.
-
Danny Auble authored
conn_types.
-
Danny Auble authored
-
Danny Auble authored
-
Morris Jette authored
This should eliminate an abort reported by Sam Long when a message unpack from the slurmdbd is invalid. Based upon patch from Sam Lang.
-
Morris Jette authored
was reporting -1 if unknown, new code avoids printing any uid if not known. Patch by Don Albert, Bull.
-
Morris Jette authored
The "+" sign only appears to indicate that there is more information than the current field width can hold. For example "CANCELLED+" can indicate that the state is actually "CANCELLED by nnn". Increasing the field width with the %NUMBER format modifier will show this. Patch by Don Albert, Bull.
-
- 10 Sep, 2011 4 commits
-
-
Danny Auble authored
-
Danny Auble authored
conn_types in a block definition.
-
Danny Auble authored
allow them on Q systems.
-
Danny Auble authored
allocation with jobs running on blocks that don't exist in the static setup.
-
- 09 Sep, 2011 3 commits
-
-
Morris Jette authored
This modifcation improves the performance of SLURM's preemption logic be reducing the execution time of the scheduling logic and doing a better job of minimizing the number of job's preempted to initiate a new job. Based largely upon work by Phil Eckert, LLNL.
-
Morris Jette authored
-
Morris Jette authored
When a user changes a job's configuration (e.g. size), then recalculate it's priority. Based upon a patch from Phil Eckert, LLNL.
-