Creating nightly hwloc snapshot git tarball was a success.
Snapshot: hwloc dev-1173-g49e5de9
Start time: Fri Jul 1 21:01:02 EDT 2016
End time: Fri Jul 1 21:02:55 EDT 2016
Your friendly daemon,
Cyrador
Sweet; thanks Josh.
> On Jul 1, 2016, at 10:50 AM, Josh Hursey wrote:
>
> I added a user note here:
>
> https://github.com/open-mpi/ompi/wiki/PRJenkins#how-to-re-trigger-jenkins-testing
>
> I added a developer setup note here:
>
>
Josh: many thanks, this will be super useful.
Do we have a wiki page on setting up your own CI? Adding this kind of regexp
to your Jenkins would seem like some knowledge that we should capture for
others to use.
> On Jul 1, 2016, at 9:37 AM, Josh Hursey wrote:
>
> I
I added a feature to IBM's Jenkins setup yesterday that other orgs doing
Jenkins CI testing might find helpful to add as well.
We have the retest target for all of the Jenkins systems to re-test a
particular PR:
*bot:retest*
I wanted an additional target that would trigger only the IBM Jenkins
I filed https://github.com/open-mpi/ompi/issues/1839 to track this issue.
Thanks!
> On Jul 1, 2016, at 6:57 AM, Håkon Bugge wrote:
>
> To me, it looks like Open MPI in xoob_send_qp_connect() attempts to set the
> max_dest_rd_atomic attribute in the transition from INIT
To me, it looks like Open MPI in xoob_send_qp_connect() attempts to set the
max_dest_rd_atomic attribute in the transition from INIT to RTR, even for
XRC_INI QPs. This is illegal, according to the ib_modify_qp_is_ok() function in
ib_core. In particular, IBV_QP_MAX_DEST_RD_ATOMIC is not part of