[torquedev] 2.4.9 Is Released
David Beer
dbeer at adaptivecomputing.com
Wed Jul 21 11:04:13 MDT 2010
Hi all,
TORQUE 2.4.9 has now been officially released. It can be downloaded at http://www.clusterresources.com/downloads/torque/torque-2.4.9.tar.gz
Here is a copy of 2.4.9's CHANGELOG:
b - Backed out enhancement for preempted jobs. This was SVN revision 3784.
This patch cased qrun to hang and not return when executing jobs.
e - Commited changes that changed how preempted jobs are killed.
This change uses a SIGTERM followed by a kill_delay SIGKILL
to give preemted jobs time to checkpoint before terminating.
e - Patch to correctly log attempts to create a cpuset as debug messages.
The function im_request() in src/resmom/mom_comm.c logs the message:
pbs_mom: LOG_ERROR::im_request, about to create cpuset for job 55100.blah.
as an error rather than a debug message (as used in src/resmom/start_exec.c).
The fix is to replace:
log_err(-1, id, log_buffer);
with:
log_ext(-1, id, log_buffer, LOG_INFO);
b - Modified fix in qmgr.c in is_attr to check for the '.' character
on resource attributes such as resources_available.nodect. The
attribute is striped of the '.' and the element and just the attribute
name is used to compare for a valid attribute.
b - Made a fix to qmgr.c in is_attr. When checking node names against
attribute keywords is_attr used strncmp and limited the length of the
compare to the length of the keyword. So node names like stateless
were tagged as an error. I replaced strncmp with strcmp. This fix was
added to trunk first. Version 2.5.0
b - Bugzilla bug 57. Check return value of malloc for tracejob for Linux
(Chris Samuel - Univ. of Melbourne)
b - fix so "gres" config gets displayed by pbsnodes
b - use QSUBHOST as the default host for output files when no host is
specified. (RT 7678)
e - allow users to use cpusets and geometry requests at the same time by
specifying both at configure time.
b - Bugzilla bug 55. Check return value of malloc for pbs_mom for Linux
(Chris Samuel - Univ. of Melbourne)
e - added server parameter job_force_cancel_time. When configured to X
seconds, a job that is still there X seconds after a qdel will be
purged. Useful for freeing nodes from a job when one node goes down
midjob.
b - fixed gcc warnings reported by Skip Montanaro
e - added RPT_BAVAIL define that allows pbs_mom to report f_bavail instead of
f_bfree on Linux systems
b - no longer consider -t and -T the same in qsub
e - make PBS_O_WORKDIR accessible in the environment for prolog scripts
e - Bugzilla 59. Applied patch to allow '=' for qdel -m.
(Chris Samuel - Univ. of Melbourne)
b - properly escape characters (&"'<>) in XML output)
b - ignore port when checking host in svr_get_privilege()
b - restore ability to parse -W x=geometry:{...,...}
e - from Simon Toth: If no available amount is specified for a resource
and the max limit is set, the requirement should be checked against
the maximum only (for scheduler, bugzilla 23).
b - check return values from fwrite in cpuset.c to avoid warnings
e - expand acl host checking to allow * in the middle of hostnames, not
just at the beginning. Also allow ranges like a[10-15] to mean a10,
a11, ..., a15.
This will be posted on the website soon. Enjoy!
--
David Beer | Senior Software Engineer
Adaptive Computing
More information about the torquedev
mailing list