If a batch job is discovered to be missing from it's head node, set its exit code to 1 rather than leaving it as zero.
Bug 833

Was printing unsigned as int

Replace round-robin front-end node selection with least-loaded algorithm.

No changes to logic

compiler would treat 1 as a 32 bit number and wrap.

more of a hey, the user is asking for something out of the norm.

not able to be separated into multiply patches.

If EnforcePartLimits=Yes and QOS job is using can override limits, allow
it.

Fix issues if partition allows or denys account's or QOS' and either are
not set.

If a job requests a partition and it doesn't allow a QOS or account the
job is requesting pend unless EnforcePartLimits=Yes.  Before it would
always kill the job at submit.

Fix the limit at which slow suspend/resumes are logged

Array of active job suspend IDs was using -1 to indicated empty slots in the array, but the array was of type uint32_t. Cray might have noted a problem in this.

Increase the number of simultaneous job suspends or resumes that
slurmd can handle from 8 to 64.
See bug 826

Increase MAX_THREAD from 130 to 256

If specialized cores are allocated for a job and that job request
CPU binding using a cpu_map, the cpu_map was being interpretted
as a cpu_mask and a cpu_map of zero was being treated as invalid.
This is now fixed.

This reverts commit 859839a7
The ntasks_per_core option was previously really treated like number of CPUs (rather than tasks) to allocate per core, which seems to be what is desired.

This needs a lot of work, but checking in the framework for now.

wait for.

based on the mask given.

task/affinity.

thread in a core.

it can bind cyclically across sockets.