- 16 Jun, 2014 2 commits
-
-
Morris Jette authored
-
Morris Jette authored
-
- 14 Jun, 2014 3 commits
-
-
jette authored
-
jette authored
If FastSchedule=0 is configured and some nodes have not registered for service (so we do not know their actual resource counts), then leave the job pending rather than rejecting it without knowing if it can run later (when the node registers and we know its specs). bug 872
-
jette authored
-
- 13 Jun, 2014 9 commits
-
-
jette authored
Conflicts: src/common/slurm_protocol_defs.c
-
jette authored
Rather than the numeric value
-
jette authored
If a numeric value is not found in the function's table, print that number rather than UNKNOWN.
-
jette authored
On slurmdbd error, print the message type by name rather than number.
-
jette authored
In rpc_num2string(), if the message type number is not known, then print its numeric value rather than "UNKNOWN_PROTOCOL_MESSAGE".
-
David Bigagli authored
to JOB_PENDING and preserve the flags.
-
David Bigagli authored
-
Morris Jette authored
Update FSF address
-
Andrew Elwell authored
No functional changes, just updating the last couple of files with the old FSF address in the comment.
-
- 12 Jun, 2014 21 commits
-
-
Marlys Kohnke authored
won't appear before Cray's libpmi in the linker cache. This means we can now include the Slurm libpmi on Cray systems - this is needed for some third-party MPIs.
-
Danny Auble authored
-
Danny Auble authored
-
Morris Jette authored
-
Morris Jette authored
For "scontrol --details show job" report the correct CPU_IDs when thre are multiple threads per core (we are translating a core bitmap to CPU IDs). This is an enhancement of commit 83d626ca so the node table is only loaded once for the entire job table. bug 850
-
David Bigagli authored
-
Martin Perry authored
Correct the record of CPU_IDs allocated to a job if there is more than one CPU per core.
-
Morris Jette authored
-
Morris Jette authored
If job requests --exclusive then do not use nodes which have any cores in an advanced reservation. Also prevents case where nodes can be shared by other jobs.
-
Morris Jette authored
Disable some logging that would be very slow unless the _DEBUG flag is set in the plugin
-
Morris Jette authored
If job requests --exclusive then do not use nodes which have any cores in an advanced reservation. Previously the job would be allocated all of the cores outside of the advanced reservation.
-
Morris Jette authored
Correct support for partition with Shared=YES configuration. Previous logic would share resources for jobs by default (i.e. if user did not explicitly request --exclusive). bug 758
-
Jens Dreger authored
-
Morris Jette authored
This reording of some code results in cleaner logic
-
Morris Jette authored
-
Morris Jette authored
collapse the scheduling table when possible to reduce the number of time slots to check for pending jobs. This should improve performance considerably.
-
Morris Jette authored
-
David Bigagli authored
-
Morris Jette authored
-
Morris Jette authored
-
Morris Jette authored
Previous logic was sometimes building incomplete map
-
- 11 Jun, 2014 5 commits
-
-
David Bigagli authored
-
David Bigagli authored
-
Morris Jette authored
-
Morris Jette authored
When a decision is made to start a job, if for some reason that job's start failed, the backfill scheduler would previously just exit. With this change, it logs the event and reserves the resources expected to be used and continues down the job queue.
-
Morris Jette authored
This change prevents creation of some back-to-back records with the same resources, but different times.
-