<html>
<head>
<style>
.hmmessage P
{
margin:0px;
padding:0px
}
body.hmmessage
{
font-size: 10pt;
font-family:Verdana
}
</style>
</head>
<body class='hmmessage'>
<BR>
<BR>
Quiecence is certainly a interesting topic, I wasn't able to finish my comments towards the end of the discussion yesterday. One philosophy of a middleware quiecence is to act as a mechanism to tell the middleware to prepare for a recovery, fail if it cannot prepare, and wait until it is told to resume. In the context of a one-sided library by the name ARMCI, a long time ago, I implemented some of the semantics for such a quiecence. <BR>
<BR>
What we were trying to accomplish in general there required a un-coordinated global quiecence. What we were discussing yesterday is certainly more general.<BR>
<BR>
Yet, a paper discussing the work is at <A href="http://domino.research.ibm.com/comm/research_people.nsf/pages/scarpazza.pubs.html/$FILE/2007-09-17-cluster.pdf">http://<FONT color=#008000>domino.research.ibm.com/comm/research_people.nsf/pages/scarpazza.pubs.<WBR>html/$FILE/2007-09-17-cluster.pdf</A> </FONT><BR>
<FONT color=#008000></FONT> <BR>
Thanks,<BR>
Vinod Tipparaju.<BR><BR>> From: jjhursey@open-mpi.org<BR>> Date: Wed, 28 Jan 2009 12:13:44 -0500<BR>> To: mpi3-ft@lists.mpi-forum.org<BR>> Subject: Re: [Mpi3-ft] Quiescence Interface<BR>> <BR>> Starting discussion on this proposal at the next forum meeting sounds <BR>> fine to me. I don't know if we need to devote the whole time to this <BR>> proposal, but I can prepare a few things for our discussion. I hope <BR>> to have a basic prototype ready by then too.<BR>> <BR>> I can contact Paul Hargrove (BLCR) to see if he would be interested <BR>> in attending this discussion. Since this proposal is a collective <BR>> operation, it might be useful to have someone from the collective <BR>> working group sit in to make sure the proposal is phrased appropriately.<BR>> <BR>> Cheers,<BR>> Josh<BR>> <BR>> On Jan 28, 2009, at 10:22 AM, Richard Graham wrote:<BR>> <BR>> > Josh,<BR>> > Thanks for sending this around.<BR>> > I would like to schedule a time to start discussion this <BR>> > proposal. To do<BR>> > so, I think we need to have the impacted parties at the table. <BR>> > Since the<BR>> > Evergrid (sp) folks and the BLCR folks are in the Bay area, would <BR>> > it make<BR>> > sense to devote our working group time at the Forum to this <BR>> > subject, and<BR>> > invite then to attend ? Who else would we want to have participate <BR>> > in this<BR>> > discussion ?<BR>> ><BR>> > Thanks,<BR>> > Rich<BR>> ><BR>> ><BR>> > On 1/22/09 10:21 AM, "Josh Hursey" <jjhursey@open-mpi.org> wrote:<BR>> ><BR>> >> I have updated the Quiescence Interface proposal on the wiki:<BR>> >> https://svn.mpi-forum.org/trac/mpi-forum-web/wiki/Quiescence<BR>> >><BR>> >> I am interested in questions and comments from the group regarding <BR>> >> the<BR>> >> interface, and use-cases. The primary use-case is for application<BR>> >> initiated checkpoint/restart, but the semantics of the proposed API<BR>> >> likely also open doors to other use-cases.<BR>> >><BR>> >> Let me know what you think.<BR>> >><BR>> >> Cheers,<BR>> >> Josh<BR>> >><BR>> >> _______________________________________________<BR>> >> mpi3-ft mailing list<BR>> >> mpi3-ft@lists.mpi-forum.org<BR>> >> http://lists.mpi-forum.org/mailman/listinfo.cgi/mpi3-ft<BR>> ><BR>> > _______________________________________________<BR>> > mpi3-ft mailing list<BR>> > mpi3-ft@lists.mpi-forum.org<BR>> > http://lists.mpi-forum.org/mailman/listinfo.cgi/mpi3-ft<BR>> <BR>> _______________________________________________<BR>> mpi3-ft mailing list<BR>> mpi3-ft@lists.mpi-forum.org<BR>> http://lists.mpi-forum.org/mailman/listinfo.cgi/mpi3-ft<BR><BR></body>
</html>