Responding to both of Ralph's e-mails in one, just to confuse people :).
First, the issue of the recursive locks... Back in the day, ompi_proc_t
instances could be created as a side effect of other operations.
Therefore, to maintain sanity, the procs were implicitly added to the
master proc l
On Jul 6, 2008, at 1:28 PM, Patrick Geoffray wrote:
WHAT: make mpi_leave_pinned=1 by default when a BTL is used that
would benefit from it (when possible; 0 when not, obviously)
The probable reason registration cache (aka leave_pinned) is
disabled by default is that it may be unsafe. Even i
Brian W. Barrett wrote:
On Mon, 7 Jul 2008, Terry Dontje wrote:
Just curious has anyone done comparisons of latency measurements as
one changes the size of a job. That is changing the size of the job
(and number of nodes used) and just taking the half roundtrip latency
of two of the processe
On Mon, 7 Jul 2008, Terry Dontje wrote:
Just curious has anyone done comparisons of latency measurements as one
changes the size of a job. That is changing the size of the job (and number
of nodes used) and just taking the half roundtrip latency of two of the
processes in the job. I am rough
Just curious has anyone done comparisons of latency measurements as one
changes the size of a job. That is changing the size of the job (and
number of nodes used) and just taking the half roundtrip latency of two
of the processes in the job. I am roughly seeing an addition of 5% to
the latenc
I will have to correct something here. From what I can see, it appears the
MPI code may not be creating ompi_proc_t structures, but rather creating
arrays of ompi_proc_t* pointers that are then filled with values equal to
the pointers in the ompi_proc_list held inside of ompi/proc/proc.c.
It appea
I am seeking input before making a change to the ompi/proc/proc.c code to
resolve the referenced ticket. The change could potentially impact how the
ompi_proc_t struct is used in the rest of the MPI code base. If this doesn't
impact you, please ignore the remainder of this note.
I was asked last
On Sun, 6 Jul 2008, Pavel Shamis (Pasha) wrote:
I added patch to the ticked, please review.
The patch works for me when applied to 1.3a1r18769. After running
configure with '--disable-openib-ibcm' linking to libibcm.so was
disabled, so no more error messages appear at job start-up. The RDMAC
On Jul 6, 2008, at 12:31 PM, Pavel Shamis (Pasha) wrote:
I see the same issue on my Mellanox OFED 1.3. IBCM module is loaded
but is no such device in system.
Jeff, looks like some bug in IBCM stuff... (not ompi)
This is likely related to:
https://bugs.openfabrics.org/show_bug.cgi?id=963
