- 02 Sep, 2003 1 commit
-
-
Mark Grondona authored
not SIGXCPU on reaching timelimit.
-
- 20 Aug, 2003 1 commit
-
-
jwindley authored
-
- 14 Aug, 2003 2 commits
- 13 Aug, 2003 13 commits
-
-
Mark Grondona authored
-
Moe Jette authored
to match that of a job's run time (TIME).
-
Mark Grondona authored
-
Moe Jette authored
hand if race condition starting all daemons).
-
Moe Jette authored
-
Mark Grondona authored
-
Moe Jette authored
-
Mark Grondona authored
o Export SLURM_NODELIST environment var in all cases
-
Mark Grondona authored
o Changed correspondingly calls to above o Removed unnecessary envc member of job structure, along with references to said member
-
Moe Jette authored
-
Moe Jette authored
-
Mark Grondona authored
is through with them. o added new function unsetenvp() to support above
-
Moe Jette authored
the old_job_allocation response so as to conform with job step's specification. For example, remove nodes that are excluded (-x), set the node count to that requested (-N, eliminate nodes as required), etc. This requires modifying the node list including the slurm_addr, and cpu_count arrays.
-
- 12 Aug, 2003 3 commits
- 08 Aug, 2003 2 commits
- 07 Aug, 2003 5 commits
-
-
Moe Jette authored
By default, logging is to syslog. Expanded usage description to be more complete.
-
Moe Jette authored
-
Moe Jette authored
without duplicates. For example, we want to convert a users request for nodes "lx1,lx2,lx1,lx3" to "lx[1-3]".
-
Moe Jette authored
entry counting function. As a job is completing the bitmap gets cleared as nodes complete, resulting in incorrect values.
-
Moe Jette authored
-
- 06 Aug, 2003 1 commit
-
-
Moe Jette authored
-
- 05 Aug, 2003 4 commits
-
-
Moe Jette authored
job is scheduled.
-
Moe Jette authored
required by a pending job. NOTE: On heterogeneous systems or if the requested number of nodes is a range then the actual number of nodes allocated may differ from the value displayed.
-
Moe Jette authored
required by a pending job.
-
Moe Jette authored
-
- 04 Aug, 2003 1 commit
-
-
Moe Jette authored
batch_job_launch RPC, then deallocate those resources and requeue the job. If a node registers and fails to show a batch job that should have a script running there (node zero of allocation), then consider the job complete.
-
- 02 Aug, 2003 5 commits
-
-
Moe Jette authored
"Can't connect to node" with every ping failure.
-
Moe Jette authored
-
Moe Jette authored
Changed the logging level of a few other message.
-
Moe Jette authored
until the previous one completes. This avoids having too many cycles active (and a bunch of threads too). Ping_nodes control functions moved to a new module.
-
Moe Jette authored
reportted in log (via #define PRINT_TIMES). Resolution of time stamps changed from 10msec to 1usec by changing to gettimeofday instead of clock.
-
- 31 Jul, 2003 2 commits
-
-
Mark Grondona authored
-
Mark Grondona authored
-