<!-- BaNnErBlUrFlE-BoDy-start -->
<!-- Preheader Text : BEGIN -->
<div style="display:none !important;display:none;visibility:hidden;mso-hide:all;font-size:1px;color:#ffffff;line-height:1px;height:0px;max-height:0px;opacity:0;overflow:hidden;">
Hm, I attempted to attach my full code, but maybe it didn’t get through correctly. Weirdly though when I look at the web view of this discussion group, *only* the code shows up (initially): https: //lists. mpich. org/pipermail/discuss/2024-April/006578. html
</div>
<!-- Preheader Text : END -->
<!-- Email Banner : BEGIN -->
<div style="display:none !important;display:none;visibility:hidden;mso-hide:all;font-size:1px;color:#ffffff;line-height:1px;height:0px;max-height:0px;opacity:0;overflow:hidden;">ZjQcmQRYFpfptBannerStart</div>
<!--[if ((ie)|(mso))]>
<table border="0" cellspacing="0" cellpadding="0" width="100%" style="padding: 16px 0px 16px 0px; direction: ltr" ><tr><td>
<table border="0" cellspacing="0" cellpadding="0" style="padding: 0px 10px 5px 6px; width: 100%; border-radius:4px; border-top:4px solid #90a4ae;background-color:#D0D8DC;"><tr><td valign="top">
<table align="left" border="0" cellspacing="0" cellpadding="0" style="padding: 4px 8px 4px 8px">
<tr><td style="color:#000000; font-family: 'Arial', sans-serif; font-weight:bold; font-size:14px; direction: ltr">
This Message Is From an External Sender
</td></tr>
<tr><td style="color:#000000; font-weight:normal; font-family: 'Arial', sans-serif; font-size:12px; direction: ltr">
This message came from outside your organization.
</td></tr>
</table>
</td></tr></table>
</td></tr></table>
<![endif]-->
<![if !((ie)|(mso))]>
<div dir="ltr" id="pfptBannertwhofti" style="all: revert !important; display:block !important; text-align: left !important; margin:16px 0px 16px 0px !important; padding:8px 16px 8px 16px !important; border-radius: 4px !important; min-width: 200px !important; background-color: #D0D8DC !important; background-color: #D0D8DC; border-top: 4px solid #90a4ae !important; border-top: 4px solid #90a4ae;">
<div id="pfptBannertwhofti" style="all: unset !important; float:left !important; display:block !important; margin: 0px 0px 1px 0px !important; max-width: 600px !important;">
<div id="pfptBannertwhofti" style="all: unset !important; display:block !important; visibility: visible !important; background-color: #D0D8DC !important; color:#000000 !important; color:#000000; font-family: 'Arial', sans-serif !important; font-family: 'Arial', sans-serif; font-weight:bold !important; font-weight:bold; font-size:14px !important; line-height:18px !important; line-height:18px">
This Message Is From an External Sender
</div>
<div id="pfptBannertwhofti" style="all: unset !important; display:block !important; visibility: visible !important; background-color: #D0D8DC !important; color:#000000 !important; color:#000000; font-weight:normal; font-family: 'Arial', sans-serif !important; font-family: 'Arial', sans-serif; font-size:12px !important; line-height:18px !important; line-height:18px; margin-top:2px !important;">
This message came from outside your organization.
</div>
</div>
<div style="clear: both !important; display: block !important; visibility: hidden !important; line-height: 0 !important; font-size: 0.01px !important; height: 0px"> </div>
</div>
<![endif]>
<div style="display:none !important;display:none;visibility:hidden;mso-hide:all;font-size:1px;color:#ffffff;line-height:1px;height:0px;max-height:0px;opacity:0;overflow:hidden;">ZjQcmQRYFpfptBannerEnd</div>
<!-- Email Banner : END -->
<!-- BaNnErBlUrFlE-BoDy-end -->
<html xmlns:v="urn:schemas-microsoft-com:vml" xmlns:o="urn:schemas-microsoft-com:office:office" xmlns:w="urn:schemas-microsoft-com:office:word" xmlns:m="http://schemas.microsoft.com/office/2004/12/omml" xmlns="http://www.w3.org/TR/REC-html40">
<head><!-- BaNnErBlUrFlE-HeAdEr-start -->
<style>
#pfptBannertwhofti { all: revert !important; display: block !important;
visibility: visible !important; opacity: 1 !important;
background-color: #D0D8DC !important;
max-width: none !important; max-height: none !important }
.pfptPrimaryButtontwhofti:hover, .pfptPrimaryButtontwhofti:focus {
background-color: #b4c1c7 !important; }
.pfptPrimaryButtontwhofti:active {
background-color: #90a4ae !important; }
</style>
<!-- BaNnErBlUrFlE-HeAdEr-end -->
<meta http-equiv="Content-Type" content="text/html; charset=utf-8">
<meta name="Generator" content="Microsoft Word 15 (filtered medium)">
<style><!--
/* Font Definitions */
@font-face
{font-family:"Cambria Math";
panose-1:2 4 5 3 5 4 6 3 2 4;}
@font-face
{font-family:Calibri;
panose-1:2 15 5 2 2 2 4 3 2 4;}
@font-face
{font-family:Consolas;
panose-1:2 11 6 9 2 2 4 3 2 4;}
@font-face
{font-family:Aptos;}
/* Style Definitions */
p.MsoNormal, li.MsoNormal, div.MsoNormal
{margin:0cm;
font-size:12.0pt;
font-family:"Aptos",sans-serif;}
a:link, span.MsoHyperlink
{mso-style-priority:99;
color:#467886;
text-decoration:underline;}
pre
{mso-style-priority:99;
mso-style-link:"HTML Preformatted Char";
margin:0cm;
margin-bottom:.0001pt;
font-size:10.0pt;
font-family:"Courier New";}
span.HTMLPreformattedChar
{mso-style-name:"HTML Preformatted Char";
mso-style-priority:99;
mso-style-link:"HTML Preformatted";
font-family:Consolas;}
span.EmailStyle22
{mso-style-type:personal-reply;
font-family:"Calibri",sans-serif;
color:windowtext;}
.MsoChpDefault
{mso-style-type:export-only;
font-size:10.0pt;
mso-ligatures:none;}
@page WordSection1
{size:612.0pt 792.0pt;
margin:72.0pt 72.0pt 72.0pt 72.0pt;}
div.WordSection1
{page:WordSection1;}
--></style><!--[if gte mso 9]><xml>
<o:shapedefaults v:ext="edit" spidmax="1026" />
</xml><![endif]--><!--[if gte mso 9]><xml>
<o:shapelayout v:ext="edit">
<o:idmap v:ext="edit" data="1" />
</o:shapelayout></xml><![endif]-->
</head>
<body lang="EN-GB" link="#467886" vlink="#96607D" style="word-wrap:break-word">
<div class="WordSection1">
<p class="MsoNormal"><span style="font-size:11.0pt;font-family:"Calibri",sans-serif;mso-fareast-language:EN-US">Hm, I attempted to attach my full code, but maybe it didn’t get through correctly. Weirdly though when I look at the web view of this discussion
group, *<b>only</b>* the code shows up (initially):<o:p></o:p></span></p>
<p class="MsoNormal"><span style="font-size:11.0pt;font-family:"Calibri",sans-serif;mso-fareast-language:EN-US"><o:p> </o:p></span></p>
<p class="MsoNormal"><span style="font-size:11.0pt;font-family:"Calibri",sans-serif;mso-fareast-language:EN-US"><a href="https://urldefense.us/v3/__https://lists.mpich.org/pipermail/discuss/2024-April/006578.html__;!!G_uCfscf7eWS!dMPBNIcfC4U_UYaGzoh3rU-i7QhBDnAdh1zo0sC8SnytRIlGThRVjCONSrYU_SSHHqdH9riWwFtj_3c$">https://lists.mpich.org/pipermail/discuss/2024-April/006578.html</a><o:p></o:p></span></p>
<p class="MsoNormal"><span style="font-size:11.0pt;font-family:"Calibri",sans-serif;mso-fareast-language:EN-US"><o:p> </o:p></span></p>
<p class="MsoNormal"><span style="font-size:11.0pt;font-family:"Calibri",sans-serif;mso-fareast-language:EN-US">Hopefully that is visible? (I think the problem shows up only when using 2 hosts)<o:p></o:p></span></p>
<p class="MsoNormal"><span style="font-size:11.0pt;font-family:"Calibri",sans-serif;mso-fareast-language:EN-US"><o:p> </o:p></span></p>
<p class="MsoNormal"><span style="font-size:11.0pt;font-family:"Calibri",sans-serif;mso-fareast-language:EN-US">(On looking again at that code, there’s a stray logging message about MPI_Comm_free – initially I was using separate communicators for the ISend
and the Barrier – but that seems to make no difference).<o:p></o:p></span></p>
<p class="MsoNormal"><span style="font-size:11.0pt;font-family:"Calibri",sans-serif;mso-fareast-language:EN-US"><o:p> </o:p></span></p>
<p class="MsoNormal"><span style="font-size:11.0pt;font-family:"Calibri",sans-serif;mso-fareast-language:EN-US">Cheers,<o:p></o:p></span></p>
<p class="MsoNormal"><span style="font-size:11.0pt;font-family:"Calibri",sans-serif;mso-fareast-language:EN-US">Edric.<o:p></o:p></span></p>
<p class="MsoNormal"><span style="font-size:11.0pt;font-family:"Calibri",sans-serif;mso-fareast-language:EN-US"><o:p> </o:p></span></p>
<div>
<div style="border:none;border-top:solid #E1E1E1 1.0pt;padding:3.0pt 0cm 0cm 0cm">
<p class="MsoNormal"><b><span lang="EN-US" style="font-size:11.0pt;font-family:"Calibri",sans-serif">From:</span></b><span lang="EN-US" style="font-size:11.0pt;font-family:"Calibri",sans-serif"> Raffenetti, Ken <raffenet@anl.gov>
<br>
<b>Sent:</b> Thursday, April 25, 2024 7:00 PM<br>
<b>To:</b> discuss@mpich.org<br>
<b>Cc:</b> Edric Ellis <eellis@mathworks.com><br>
<b>Subject:</b> Re: [mpich-discuss] Differences between ch3:nemesis and ch4:ofi:tcp with MPI_Barrier before completion of MPI_Isend<o:p></o:p></span></p>
</div>
</div>
<p class="MsoNormal"><o:p> </o:p></p>
<p class="MsoNormal"><span lang="EN-US" style="font-size:11.0pt">Hi Edric,<o:p></o:p></span></p>
<p class="MsoNormal"><span lang="EN-US" style="font-size:11.0pt"><o:p> </o:p></span></p>
<p class="MsoNormal"><span lang="EN-US" style="font-size:11.0pt">I don’t see anything wrong in your pseudo code. I believe it is a correct pattern. I ran some experiments myself on some local machines and could not cause a hang, so if you come up with a reproducer
please send it along.<o:p></o:p></span></p>
<p class="MsoNormal"><span lang="EN-US" style="font-size:11.0pt"><o:p> </o:p></span></p>
<p class="MsoNormal"><span lang="EN-US" style="font-size:11.0pt">Ken<o:p></o:p></span></p>
<p class="MsoNormal"><span lang="EN-US" style="font-size:11.0pt"><o:p> </o:p></span></p>
<div style="border:none;border-top:solid #B5C4DF 1.0pt;padding:3.0pt 0cm 0cm 0cm">
<p class="MsoNormal" style="margin-left:36.0pt"><b><span lang="EN-US" style="font-family:"Calibri",sans-serif;color:black">From:
</span></b><span lang="EN-US" style="font-family:"Calibri",sans-serif;color:black">Edric Ellis via discuss <<a href="mailto:discuss@mpich.org">discuss@mpich.org</a>><br>
<b>Reply-To: </b>"<a href="mailto:discuss@mpich.org">discuss@mpich.org</a>" <<a href="mailto:discuss@mpich.org">discuss@mpich.org</a>><br>
<b>Date: </b>Wednesday, April 24, 2024 at 3:05 AM<br>
<b>To: </b>"<a href="mailto:discuss@mpich.org">discuss@mpich.org</a>" <<a href="mailto:discuss@mpich.org">discuss@mpich.org</a>><br>
<b>Cc: </b>Edric Ellis <<a href="mailto:eellis@mathworks.com">eellis@mathworks.com</a>><br>
<b>Subject: </b>[mpich-discuss] Differences between ch3:nemesis and ch4:ofi:tcp with MPI_Barrier before completion of MPI_Isend<o:p></o:p></span></p>
</div>
<div>
<p class="MsoNormal" style="margin-left:36.0pt"><span lang="EN-US"><o:p> </o:p></span></p>
</div>
<div>
<p class="MsoNormal" style="margin-left:36.0pt;mso-line-height-alt:.75pt"><span lang="EN-US" style="font-size:1.0pt;color:white">I'm trying to understand if a change in behaviour I'm seeing is expected or not. My code initiates an MPI_Isend on rank==1, and
before waiting for completion of that send, all ranks perform an MPI_Barrier. This works fine on ch3:</span><span lang="EN-US" style="font-size:1.0pt;font-family:"Arial",sans-serif;color:white"> </span><span lang="EN-US" style="font-size:1.0pt;color:white">nemesis.
It <o:p></o:p></span></p>
</div>
<div>
<p class="MsoNormal" style="margin-left:36.0pt;mso-line-height-alt:.75pt"><span lang="EN-US" style="font-size:1.0pt;color:white">ZjQcmQRYFpfptBannerStart<o:p></o:p></span></p>
</div>
<table class="MsoNormalTable" border="0" cellspacing="0" cellpadding="0" width="100%" style="width:100.0%;margin-left:36.0pt;border-radius:4px">
<tbody>
<tr>
<td style="padding:12.0pt 0cm 12.0pt 0cm">
<table class="MsoNormalTable" border="1" cellspacing="0" cellpadding="0" width="100%" style="width:100.0%;background:#D0D8DC;border:none;border-top:solid #90A4AE 3.0pt">
<tbody>
<tr>
<td valign="top" style="border:none;padding:0cm 7.5pt 3.75pt 4.5pt">
<table class="MsoNormalTable" border="0" cellspacing="0" cellpadding="0" align="left">
<tbody>
<tr>
<td style="padding:3.0pt 6.0pt 3.0pt 6.0pt">
<p class="MsoNormal"><b><span style="font-size:10.5pt;font-family:"Arial",sans-serif;color:black">This Message Is From an External Sender
<o:p></o:p></span></b></p>
</td>
</tr>
<tr>
<td style="padding:3.0pt 6.0pt 3.0pt 6.0pt">
<p class="MsoNormal"><span style="font-size:9.0pt;font-family:"Arial",sans-serif;color:black">This message came from outside your organization.
<o:p></o:p></span></p>
</td>
</tr>
</tbody>
</table>
</td>
</tr>
</tbody>
</table>
</td>
</tr>
</tbody>
</table>
<div>
<p class="MsoNormal" style="margin-left:36.0pt;mso-line-height-alt:.75pt"><span lang="EN-US" style="font-size:1.0pt;color:white">ZjQcmQRYFpfptBannerEnd<o:p></o:p></span></p>
</div>
<pre style="margin-left:36.0pt;white-space:pre-wrap"><span lang="EN-US" style="font-size:12.0pt;font-family:"Arial",sans-serif">I'm trying to understand if a change in behaviour I'm seeing is expected or not. My code initiates an MPI_Isend on rank==1, and before waiting for completion of that send, all ranks perform an MPI_Barrier. This works fine on ch3:nemesis. It works fine on ch4:ofi when the message is small (presumably using the "eager" protocol). When using ch4:ofi (the embedded tcp provider) and the message is large (presumably switching to "rendezvous" protocol), rank 0 never leaves the MPI_Barrier call. (I think the SHM piece of ch4 does not show the problem)<o:p></o:p></span></pre>
<pre style="margin-left:36.0pt"><span lang="EN-US" style="font-size:12.0pt;font-family:"Arial",sans-serif"><o:p> </o:p></span></pre>
<pre style="margin-left:36.0pt"><span lang="EN-US" style="font-size:12.0pt;font-family:"Arial",sans-serif">Should this work? I cannot find anything in the MPI standard that says it should not, but perhaps I'm not looking in the right place. <o:p></o:p></span></pre>
<pre style="margin-left:36.0pt"><span lang="EN-US" style="font-size:12.0pt;font-family:"Arial",sans-serif"><o:p> </o:p></span></pre>
<pre style="margin-left:36.0pt"><span lang="EN-US" style="font-size:12.0pt;font-family:"Arial",sans-serif">I'm using mpich-4.1.2 in both cases, either in "--with-device=ch3:nemesis" mode or "--with-libfabric=embedded --with-device=ch4:ofi:tcp". <o:p></o:p></span></pre>
<pre style="margin-left:36.0pt"><span lang="EN-US" style="font-size:12.0pt;font-family:"Arial",sans-serif"><o:p> </o:p></span></pre>
<pre style="margin-left:36.0pt"><span lang="EN-US" style="font-size:12.0pt;font-family:"Arial",sans-serif">Here's a sketch of the problematic section of code, I'll attempt to attach a full reproduction (but I'm not sure if that works?)<o:p></o:p></span></pre>
<pre style="margin-left:36.0pt"><span lang="EN-US" style="font-size:12.0pt;font-family:"Arial",sans-serif"><o:p> </o:p></span></pre>
<pre style="margin-left:36.0pt"><span lang="EN-US" style="font-size:12.0pt;font-family:"Arial",sans-serif">// setup code...<o:p></o:p></span></pre>
<pre style="margin-left:36.0pt"><span lang="EN-US" style="font-size:12.0pt;font-family:"Arial",sans-serif">if (rank == 1) {<o:p></o:p></span></pre>
<pre style="margin-left:36.0pt"><span lang="EN-US" style="font-size:12.0pt;font-family:"Arial",sans-serif"> MPI_Isend(data, count, MPI_INT, 0, TAG, comm, &req);<o:p></o:p></span></pre>
<pre style="margin-left:36.0pt"><span lang="EN-US" style="font-size:12.0pt;font-family:"Arial",sans-serif">} else {<o:p></o:p></span></pre>
<pre style="margin-left:36.0pt"><span lang="EN-US" style="font-size:12.0pt;font-family:"Arial",sans-serif"> std::this_thread::sleep_for(std::chrono::seconds(1));<o:p></o:p></span></pre>
<pre style="margin-left:36.0pt"><span lang="EN-US" style="font-size:12.0pt;font-family:"Arial",sans-serif">}<o:p></o:p></span></pre>
<pre style="margin-left:36.0pt"><span lang="EN-US" style="font-size:12.0pt;font-family:"Arial",sans-serif">MPI_Barrier(comm);<o:p></o:p></span></pre>
<pre style="margin-left:36.0pt"><span lang="EN-US" style="font-size:12.0pt;font-family:"Arial",sans-serif">MPI_Barrier(comm);<o:p></o:p></span></pre>
<pre style="margin-left:36.0pt"><span lang="EN-US" style="font-size:12.0pt;font-family:"Arial",sans-serif">// cleanup code, receive the message etc...<o:p></o:p></span></pre>
<pre style="margin-left:36.0pt"><span lang="EN-US" style="font-size:12.0pt;font-family:"Arial",sans-serif"><o:p> </o:p></span></pre>
<pre style="margin-left:36.0pt"><span lang="EN-US" style="font-size:12.0pt;font-family:"Arial",sans-serif">Cheers,<o:p></o:p></span></pre>
<pre style="margin-left:36.0pt"><span lang="EN-US" style="font-size:12.0pt;font-family:"Arial",sans-serif">Edric.<o:p></o:p></span></pre>
</div>
</body>
</html>