1 new commit in galaxy-central: https://bitbucket.org/galaxy/galaxy-central/commits/d46b64f12c52/ Changeset: d46b64f12c52 User: natefoo Date: 2013-10-14 18:00:57 Summary: Revert changes from 384240b8cd29 that result in a failure to detect job completion in the drmaa runner on DRMs that do not retain jo b information once a job has exited the queue. Affected #: 1 file diff -r 02b18fd5432eabf7ba88b87ca0a3f6e348c5c6ba -r d46b64f12c5248878baf85b7a764c3e770fb6a09 lib/galaxy/jobs/runners/drmaa.py --- a/lib/galaxy/jobs/runners/drmaa.py +++ b/lib/galaxy/jobs/runners/drmaa.py @@ -212,9 +212,16 @@ try: assert external_job_id not in ( None, 'None' ), '(%s/%s) Invalid job id' % ( galaxy_id_tag, external_job_id ) state = self.ds.jobStatus( external_job_id ) - # TODO: probably need to keep track of InvalidJobException count and remove after it exceeds some configurable - except ( drmaa.DrmCommunicationException, drmaa.InternalException, drmaa.InvalidJobException ), e: - log.warning( "(%s/%s) job check resulted in %s: %s", galaxy_id_tag, external_job_id, e.__class__.__name__, e ) + # InternalException was reported to be necessary on some DRMs, but + # this could cause failures to be detected as completion! Please + # report if you experience problems with this. + except ( drmaa.InvalidJobException, drmaa.InternalException ), e: + # we should only get here if an orphaned job was put into the queue at app startup + log.info( "(%s/%s) job left DRM queue with following message: %s" % ( galaxy_id_tag, external_job_id, e ) ) + self.work_queue.put( ( self.finish_job, ajs ) ) + continue + except drmaa.DrmCommunicationException, e: + log.warning( "(%s/%s) unable to communicate with DRM: %s" % ( galaxy_id_tag, external_job_id, e )) new_watched.append( ajs ) continue except Exception, e: Repository URL: https://bitbucket.org/galaxy/galaxy-central/ -- This is a commit notification from bitbucket.org. You are receiving this because you have the service enabled, addressing the recipient of this email.