Re: [myrinet] Re: [Myricom help #8298] smpi_post_send_ok_to_send_out got corrupted handle

Craig,

    we've tried this on the maximum number of stable nodes. It's 370 (740
CPUs). We've not tried to run it with less number of nodes - we've not
enough time because of the user load (this cluster serves number of users).
mpich-1.2..8 works fine, but mpich-1.2.1..7 not (both with gm-1.4 & gm-1.5).
Sometimes it's solves 30000 system and locks (???) with 50000, sometimes
locks with 30000 (we're using config with the test sizes of 10000, 30000 and
50000). I've checked - every process, which was spawned consumes CPU fully
(i.e. we've loadavg of 2.0 on all the nodes), but nothing happens...

Regards,
    Oleg.

----- Original Message -----
From: "Craig Tierney" <[email protected]>
To: "Oleg I. Vdovikin" <[email protected]>
Cc: <[email protected]>; <[email protected]>; <[email protected]>
Sent: Thursday, November 29, 2001 8:10 PM
Subject: Re: [myrinet] Re: [Myricom help #8298]
smpi_post_send_ok_to_send_out got corrupted handle


> Oleg,
>   How many nodes are you trying to run Linpack on right now?  Or
> more importantly, how many nodes does it take to reproduce your problem?
>
> Craig
>
> --
> Craig Tierney ([email protected])
>
> On Thu, Nov 29, 2001 at 06:02:44PM +0300, Oleg I. Vdovikin wrote:
> > Hi Patrick,
> >
> >     thanks. Be sure to apply this patch too. pkt_p->len should be
zeroed.
> >
> > -----------------------------------------------------------------------
> >
> > --- mpich-1.2.1..7/mpid/ch_gm/smppriv.c.orig Tue Nov 27 14:36:33 2001
> > +++ mpich-1.2.1..7/mpid/ch_gm/smppriv.c Tue Nov 27 14:37:39 2001
> > @@ -594,7 +594,7 @@
> > pkt_p->mode = MPID_PKT_FLOW;
> > pkt_p->send_id = send_handle_id;
> > pkt_p->recv_id = recv_handle_id;
> > - pkt_len = 0;
> > + pkt_p->len = 0;
> > shandle->gm.current_expected++;
> >
> > DEBUG_PRINT_SMP_SEND_PKT("S Sending in the send_queue", pkt_p);
> >
>
> -------------------------------------------------------------------------
> >
> >     Patrick, we've tried using mpich-1.2.1..7 & gm-1.5. Even with those
two
> > patches Linpack never completes. It's works, but does not produce any
result
> > for the problems of size above 30000 during large amount of time. We've
also
> > tried mpich-1.2.1..7 & gm-1.4 with the same results... I don't know what
> > happens... Now we're using mpich-1.2..8 & gm-1.4 and everything works
fine
> > with problems of size up too 230000.
> >
> >     So, basicaly mpich-1.2.1..7 does not work properly on Alphas... We
need
> > to do more investigation on the purpose, and then possibly we will find
the
> > solution. Any ideas?
> >
> > Regards,
> >     Oleg.
> >
> >
>
>