<!DOCTYPE HTML PUBLIC "-//W3C//DTD HTML 4.0 Transitional//EN">
<HTML><HEAD>
<META content="text/html; charset=us-ascii" http-equiv=Content-Type>
<META name=GENERATOR content="MSHTML 8.00.6001.18812"></HEAD>
<BODY>
<DIV dir=ltr align=left><FONT color=#0000ff size=2 face=Arial><SPAN
class=056332320-13102009>Hi,</SPAN></FONT></DIV>
<DIV dir=ltr align=left><FONT color=#0000ff size=2 face=Arial><SPAN
class=056332320-13102009> You should easily be able to increase the number
of nodes in your cluster. AFAIK, our users run on bigger clusters than
yours. Let us know if you have any problems.</SPAN></FONT></DIV>
<DIV dir=ltr align=left><FONT color=#0000ff size=2 face=Arial><SPAN
class=056332320-13102009></SPAN></FONT> </DIV>
<DIV dir=ltr align=left><FONT color=#0000ff size=2 face=Arial><SPAN
class=056332320-13102009>(PS: I don't think the MPI standard imposes such
hard limits on the number of processes (MAX_INT would be the hard limit)
)</SPAN></FONT></DIV>
<DIV dir=ltr align=left><FONT color=#0000ff size=2 face=Arial><SPAN
class=056332320-13102009></SPAN></FONT> </DIV>
<DIV dir=ltr align=left><FONT color=#0000ff size=2 face=Arial><SPAN
class=056332320-13102009>Regards,</SPAN></FONT></DIV>
<DIV dir=ltr align=left><FONT color=#0000ff size=2 face=Arial><SPAN
class=056332320-13102009>Jayesh</SPAN></FONT></DIV><BR>
<DIV dir=ltr lang=en-us class=OutlookMessageHeader align=left>
<HR tabIndex=-1>
<FONT size=2 face=Tahoma><B>From:</B> abhishek pandey
[mailto:hipandey@gmail.com] <BR><B>Sent:</B> Tuesday, October 13, 2009 3:18
PM<BR><B>To:</B> Jayesh Krishna<BR><B>Subject:</B> Re: [mpich-discuss] If one
process of Cluster crashes<BR></FONT><BR></DIV>
<DIV></DIV>Hi,<BR><BR>Actually I am using 10-12 machines with winxp64 installed
on each of them. The number of machines can be increased. So I want to know the
MPI limit to handle the number of processes and machines before going for
increasing it.<BR><BR>Thanks,<BR>Abhishek.<BR><BR><BR>
<DIV class=gmail_quote>On Wed, Oct 14, 2009 at 6:06 AM, Jayesh Krishna <SPAN
dir=ltr><<A
href="mailto:jayesh@mcs.anl.gov">jayesh@mcs.anl.gov</A>></SPAN> wrote:<BR>
<BLOCKQUOTE
style="BORDER-LEFT: rgb(204,204,204) 1px solid; MARGIN: 0pt 0pt 0pt 0.8ex; PADDING-LEFT: 1ex"
class=gmail_quote>
<DIV>
<DIV dir=ltr align=left><FONT color=#0000ff size=2
face=Arial><SPAN>Hi,</SPAN></FONT></DIV>
<DIV dir=ltr align=left><FONT color=#0000ff size=2 face=Arial><SPAN> You
can spawn processes dynamically (MPI_Comm_spawn()) with MPI (Is that what you
mean ?). How many processes are you trying to launch on your cluster (The
number of processes that can be launched would depend on the capability of the
OS to handle them - perf could get affected if you launch too many procs on a
single node)?</SPAN></FONT></DIV>
<DIV dir=ltr align=left><FONT color=#0000ff size=2
face=Arial><SPAN></SPAN></FONT> </DIV>
<DIV dir=ltr align=left><FONT color=#0000ff size=2
face=Arial><SPAN>Regards,</SPAN></FONT></DIV>
<DIV dir=ltr align=left><FONT color=#0000ff size=2
face=Arial><SPAN>Jayesh</SPAN></FONT></DIV><BR>
<DIV dir=ltr lang=en-us align=left>
<HR>
<FONT size=2 face=Tahoma>
<DIV class=im><B>From:</B> abhishek pandey [mailto:<A
href="mailto:hipandey@gmail.com" target=_blank>hipandey@gmail.com</A>]
<BR></DIV><B>Sent:</B> Tuesday, October 13, 2009 12:42 PM
<DIV>
<DIV></DIV>
<DIV class=h5><BR><B>To:</B> Jayesh Krishna<BR><B>Subject:</B> Re:
[mpich-discuss] If one process of Cluster
crashes<BR></DIV></DIV></FONT><BR></DIV>
<DIV>
<DIV></DIV>
<DIV class=h5>
<DIV></DIV>Hi Jayesh,<BR><BR>I haven't, I'll try it. Thanks.<BR><BR>BTW, can
any process be dynamically added/removed from a cluster ? Is there any
upper limit on the number of processes in cluster on window
?<BR><BR>Thanks,<BR>Abhishek<BR><BR>
<DIV class=gmail_quote>On Wed, Oct 14, 2009 at 2:37 AM, Jayesh Krishna <SPAN
dir=ltr><<A href="mailto:jayesh@mcs.anl.gov"
target=_blank>jayesh@mcs.anl.gov</A>></SPAN> wrote:<BR>
<BLOCKQUOTE
style="BORDER-LEFT: rgb(204,204,204) 1px solid; MARGIN: 0pt 0pt 0pt 0.8ex; PADDING-LEFT: 1ex"
class=gmail_quote>
<DIV>
<DIV dir=ltr align=left><FONT color=#0000ff size=2
face=Arial><SPAN>Hi,</SPAN></FONT></DIV>
<DIV dir=ltr align=left><FONT color=#0000ff size=2
face=Arial><SPAN> Did you try using the MPI error handlers
(MPI_Comm_create_errhandler() / MPI_ERRORS_RETURN)?</SPAN></FONT></DIV>
<DIV dir=ltr align=left><FONT color=#0000ff size=2
face=Arial><SPAN></SPAN></FONT> </DIV>
<DIV dir=ltr align=left><FONT color=#0000ff size=2
face=Arial><SPAN>Regards,</SPAN></FONT></DIV>
<DIV dir=ltr align=left><FONT color=#0000ff size=2
face=Arial><SPAN>Jayesh</SPAN></FONT></DIV>
<DIV dir=ltr align=left><FONT color=#0000ff size=2
face=Arial><SPAN></SPAN></FONT> </DIV>
<DIV dir=ltr align=left>
<HR>
</DIV>
<DIV dir=ltr align=left><FONT size=2 face=Tahoma><B>From:</B> abhishek
pandey [mailto:<A href="mailto:hipandey@gmail.com"
target=_blank>hipandey@gmail.com</A>] <BR><B>Sent:</B> Tuesday, October 13,
2009 11:02 AM<BR><B>To:</B> Jayesh Krishna<BR><B>Subject:</B> Re:
[mpich-discuss] If one process of Cluster crashes<BR></FONT><BR></DIV>
<DIV>
<DIV></DIV>
<DIV>
<DIV></DIV>Hi Jayesh,<BR><BR>Thanks for reply.<BR><BR>This is an
application/network error. I am running several instances of my application
on different machines for very long time. So there is possibility of either
crash of one process or loss of network connectivity to any machine.
In this case, the cluster would goes down for now. But I want to ensure the
other processes should be running irrespective of one or more process
failure.<BR><BR>Is there any way, I can handle this situation ?
<BR><BR>Thanks,<BR>Abhishek<BR><BR>
<DIV class=gmail_quote>On Tue, Oct 13, 2009 at 8:20 PM, Jayesh Krishna <SPAN
dir=ltr><<A href="mailto:jayesh@mcs.anl.gov"
target=_blank>jayesh@mcs.anl.gov</A>></SPAN> wrote:<BR>
<BLOCKQUOTE
style="BORDER-LEFT: rgb(204,204,204) 1px solid; MARGIN: 0pt 0pt 0pt 0.8ex; PADDING-LEFT: 1ex"
class=gmail_quote>
<DIV>
<DIV dir=ltr align=left><FONT color=#0000ff size=2
face=Arial><SPAN>Hi,</SPAN></FONT></DIV>
<DIV dir=ltr align=left><FONT color=#0000ff size=2
face=Arial><SPAN> We are currently working on adding fault-tolerance
to MPICH2. So in couple of months we might have something that you can
work with.</SPAN></FONT></DIV>
<DIV dir=ltr align=left><FONT color=#0000ff size=2
face=Arial><SPAN> On a side note, what kind of process crash do you
see ? Is this an application error (which you should fix anyway)? Is it
due to an internal MPICH2 error ? Please provide us more
details.</SPAN></FONT></DIV>
<DIV dir=ltr align=left><FONT color=#0000ff size=2
face=Arial><SPAN></SPAN></FONT> </DIV>
<DIV dir=ltr align=left><FONT color=#0000ff size=2
face=Arial><SPAN>Regards,</SPAN></FONT></DIV>
<DIV dir=ltr align=left><FONT color=#0000ff size=2
face=Arial><SPAN>Jayesh</SPAN></FONT></DIV><BR>
<DIV dir=ltr lang=en-us align=left>
<HR>
<FONT size=2 face=Tahoma><B>From:</B> <A
href="mailto:mpich-discuss-bounces@mcs.anl.gov"
target=_blank>mpich-discuss-bounces@mcs.anl.gov</A> [mailto:<A
href="mailto:mpich-discuss-bounces@mcs.anl.gov"
target=_blank>mpich-discuss-bounces@mcs.anl.gov</A>] <B>On Behalf Of
</B>abhishek pandey<BR><B>Sent:</B> Tuesday, October 13, 2009 7:23
AM<BR><B>To:</B> <A href="mailto:mpich-discuss@mcs.anl.gov"
target=_blank>mpich-discuss@mcs.anl.gov</A><BR><B>Subject:</B>
[mpich-discuss] If one process of Cluster crashes<BR></FONT><BR></DIV>
<DIV>
<DIV></DIV>
<DIV>
<DIV></DIV>Hi,<BR><BR>I am using MPICH2 on windows and sometime I face the
problem of crashing of one process in cluster. Is there any way to handle
this ? I do not want to start the cluster all over again.<BR>As far as I
know, if one process of cluster goes down anyhow then the cluster also
goes down.
<BR><BR><BR>Thanks,<BR>Abhishek.<BR></DIV></DIV></DIV></BLOCKQUOTE></DIV><BR></DIV></DIV></DIV></BLOCKQUOTE></DIV><BR></DIV></DIV></DIV></BLOCKQUOTE></DIV><BR></BODY></HTML>