[torqueusers] reported cpu time during running parallel jobs in
garrick at clusterresources.com
Thu Oct 19 16:55:55 MDT 2006
On Thu, Oct 19, 2006 at 09:17:42AM -0600, Garrick Staples alleged:
> On Thu, Oct 19, 2006 at 01:57:42PM +0100, David Golden alleged:
> > On Thursday 19 October 2006 02:35, Garrick Staples wrote:
> > > I think this fixes both problems. Initial tests are good, but I want to
> > > bang at it some more.
> > >
> > Thanks!
> > Looks like that SVFLG_HERE check was introduced in 2.1 series ? 2.0.0p8
> > doesn't seem to have it.
> Looks like it, but I think I have a much better way to do it now.
This is what I am committing to trunk and 2.1-fixes:
--- src/resmom/mom_comm.c (revision 1057)
+++ src/resmom/mom_comm.c (revision 1058)
@@ -3019,6 +3019,9 @@
if (ret != DIS_SUCCESS)
+ /* get fresh resource usage */
/* ** Send the information tallied for the job. */
ret = diswul(stream,resc_used(pjob,"cput",gettime));
--- src/server/req_jobobit.c (revision 1057)
+++ src/server/req_jobobit.c (revision 1058)
@@ -1626,6 +1626,13 @@
patlist = (svrattrl *)GET_NEXT(preq->rq_ind.rq_jobobit.rq_attr);
+ /* Encode the final resources_used into the job (useful for keep_completed) */
+ ATR_DFLAG_MGWR | ATR_DFLAG_SvWR,
More information about the torqueusers