<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>
<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;}
/* Style Definitions */
p.MsoNormal, li.MsoNormal, div.MsoNormal
{margin:0cm;
font-size:11.0pt;
font-family:"Calibri",sans-serif;
mso-fareast-language:EN-US;}
a:link, span.MsoHyperlink
{mso-style-priority:99;
color:#0563C1;
text-decoration:underline;}
span.EmailStyle18
{mso-style-type:personal-compose;
font-family:"Calibri",sans-serif;
color:windowtext;}
.MsoChpDefault
{mso-style-type:export-only;
font-size:10.0pt;
font-family:"Calibri",sans-serif;
mso-fareast-language:EN-US;}
@page WordSection1
{size:612.0pt 792.0pt;
margin:70.85pt 70.85pt 70.85pt 70.85pt;}
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="FR" link="#0563C1" vlink="#954F72" style="word-wrap:break-word">
<div class="WordSection1">
<p class="MsoNormal"><span lang="EN-US">Hello,<o:p></o:p></span></p>
<p class="MsoNormal"><span lang="EN-US"><o:p> </o:p></span></p>
<p class="MsoNormal"><span lang="EN-US">I am trying to analyze the IO behavior of our codes with Darshan.
<o:p></o:p></span></p>
<p class="MsoNormal"><span lang="EN-US">Darshan: 3.3.0<o:p></o:p></span></p>
<p class="MsoNormal"><span lang="EN-US">Compilers: Intel 2018<o:p></o:p></span></p>
<p class="MsoNormal"><span lang="EN-US">MPI: Intel MPI 2018<o:p></o:p></span></p>
<p class="MsoNormal"><span lang="EN-US">FS: Lustre (lustre-module disabled in Darshan configuration)<o:p></o:p></span></p>
<p class="MsoNormal"><span lang="EN-US">Darshan profiling: LD_PRELOAD<o:p></o:p></span></p>
<p class="MsoNormal"><span lang="EN-US"><o:p> </o:p></span></p>
<p class="MsoNormal"><span lang="EN-US">I observe a big difference in IO results from Darshan and IPM (v2.0.5) for one of our codes. I guess that both profilers are not profiling the same POSIX calls?
<o:p></o:p></span></p>
<p class="MsoNormal"><span lang="EN-US"><o:p> </o:p></span></p>
<p class="MsoNormal"><span lang="EN-US">The POSIXIO calls profiled in IPM are: <o:p>
</o:p></span></p>
<p class="MsoNormal"><span lang="EN-US"><o:p> </o:p></span></p>
<p class="MsoNormal"><span lang="EN-US" style="font-size:10.0pt;font-family:"Courier New"">fopen, fdopen, freopen, open, open64<o:p></o:p></span></p>
<p class="MsoNormal"><span lang="EN-US" style="font-size:10.0pt;font-family:"Courier New"">fclose, close<o:p></o:p></span></p>
<p class="MsoNormal"><span lang="EN-US" style="font-size:10.0pt;font-family:"Courier New"">fflush<o:p></o:p></span></p>
<p class="MsoNormal"><span lang="EN-US" style="font-size:10.0pt;font-family:"Courier New"">fread, read<o:p></o:p></span></p>
<p class="MsoNormal"><span lang="EN-US" style="font-size:10.0pt;font-family:"Courier New"">fwrite, write<o:p></o:p></span></p>
<p class="MsoNormal"><span lang="EN-US" style="font-size:10.0pt;font-family:"Courier New"">fseek, lseek, lseek64<o:p></o:p></span></p>
<p class="MsoNormal"><span lang="EN-US" style="font-size:10.0pt;font-family:"Courier New"">ftell<o:p></o:p></span></p>
<p class="MsoNormal"><span lang="EN-US" style="font-size:10.0pt;font-family:"Courier New"">rewind<o:p></o:p></span></p>
<p class="MsoNormal"><span lang="EN-US" style="font-size:10.0pt;font-family:"Courier New"">fgetpos, fsetpos, fgetc, getc, ungetc<o:p></o:p></span></p>
<p class="MsoNormal"><span lang="EN-US" style="font-size:10.0pt;font-family:"Courier New"">creat<o:p></o:p></span></p>
<p class="MsoNormal"><span lang="EN-US" style="font-size:10.0pt;font-family:"Courier New"">truncate, ftruncate, truncate64, ftruncate64</span><span lang="EN-US"><o:p></o:p></span></p>
<p class="MsoNormal"><span lang="EN-US"><o:p> </o:p></span></p>
<p class="MsoNormal"><span lang="EN-US">While the ones profiled by Darshan are: <a href="https://github.com/darshan-hpc/darshan/blob/main/darshan-runtime/lib/darshan-posix.c">
https://github.com/darshan-hpc/darshan/blob/main/darshan-runtime/lib/darshan-posix.c</a> ?<o:p></o:p></span></p>
<p class="MsoNormal"><span lang="EN-US"><o:p> </o:p></span></p>
<p class="MsoNormal"><span lang="EN-US">However, the huge difference is observed in the “read” call, which exists in both the profilers.<o:p></o:p></span></p>
<p class="MsoNormal"><span lang="EN-US"><o:p> </o:p></span></p>
<p class="MsoNormal"><span lang="EN-US" style="font-size:10.0pt;font-family:"Courier New"">+-------------------+------------+-----------+<o:p></o:p></span></p>
<p class="MsoNormal"><span lang="EN-US" style="font-size:10.0pt;font-family:"Courier New"">| | IPM | Darshan |<o:p></o:p></span></p>
<p class="MsoNormal"><span lang="EN-US" style="font-size:10.0pt;font-family:"Courier New"">+-------------------+------------+-----------+<o:p></o:p></span></p>
<p class="MsoNormal"><span lang="EN-US" style="font-size:10.0pt;font-family:"Courier New"">| Read (s) | 324.57 | 6.02 |<o:p></o:p></span></p>
<p class="MsoNormal"><span lang="EN-US" style="font-size:10.0pt;font-family:"Courier New"">+-------------------+------------+-----------+<o:p></o:p></span></p>
<p class="MsoNormal"><span lang="EN-US" style="font-size:10.0pt;font-family:"Courier New"">| Agg. Read (count) | 34 766 456 | 2 946 271 |<o:p></o:p></span></p>
<p class="MsoNormal"><span lang="EN-US" style="font-size:10.0pt;font-family:"Courier New"">+-------------------+------------+-----------+</span><span lang="EN-US"><o:p></o:p></span></p>
<p class="MsoNormal"><span lang="EN-US"><o:p> </o:p></span></p>
<p class="MsoNormal"><span lang="EN-US">I tested Darshan and IPM with other codes (reading NOT the same files) to check if this issue is faced in them as well. But, I got the same results.
<o:p></o:p></span></p>
<p class="MsoNormal"><span lang="EN-US">So, I don't understand what could be the reason that this application is not giving the same results.<o:p></o:p></span></p>
<p class="MsoNormal"><span lang="EN-US"><o:p> </o:p></span></p>
<p class="MsoNormal"><span lang="EN-US">Do you have any idea of why this could happen?<o:p></o:p></span></p>
<p class="MsoNormal"><span lang="EN-US"><o:p> </o:p></span></p>
<p class="MsoNormal"><span lang="EN-US">Thanks in advance.<o:p></o:p></span></p>
<p class="MsoNormal"><span lang="EN-US"><o:p> </o:p></span></p>
<p class="MsoNormal"><span lang="EN-US">PS: The application does a lot of IO, and is expected to spend a significant time in read operations.<o:p></o:p></span></p>
<p class="MsoNormal"><span lang="EN-US"><o:p> </o:p></span></p>
<p class="MsoNormal"><span lang="EN-US">Best regards,<o:p></o:p></span></p>
<p class="MsoNormal"><span lang="EN-US">Vineet</span><span lang="EN-US" style="font-family:"Courier New";color:#595959;mso-fareast-language:FR"><o:p></o:p></span></p>
<p class="MsoNormal"><span lang="EN-US"><o:p> </o:p></span></p>
</div>
</body>
</html>