<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:x="urn:schemas-microsoft-com:office:excel" xmlns:p="urn:schemas-microsoft-com:office:powerpoint" xmlns:a="urn:schemas-microsoft-com:office:access" xmlns:dt="uuid:C2F41010-65B3-11d1-A29F-00AA00C14882" xmlns:s="uuid:BDC6E3F0-6DA3-11d1-A2A3-00AA00C14882" xmlns:rs="urn:schemas-microsoft-com:rowset" xmlns:z="#RowsetSchema" xmlns:b="urn:schemas-microsoft-com:office:publisher" xmlns:ss="urn:schemas-microsoft-com:office:spreadsheet" xmlns:c="urn:schemas-microsoft-com:office:component:spreadsheet" xmlns:odc="urn:schemas-microsoft-com:office:odc" xmlns:oa="urn:schemas-microsoft-com:office:activation" xmlns:html="http://www.w3.org/TR/REC-html40" xmlns:q="http://schemas.xmlsoap.org/soap/envelope/" xmlns:rtc="http://microsoft.com/officenet/conferencing" xmlns:D="DAV:" xmlns:Repl="http://schemas.microsoft.com/repl/" xmlns:mt="http://schemas.microsoft.com/sharepoint/soap/meetings/" xmlns:x2="http://schemas.microsoft.com/office/excel/2003/xml" xmlns:ppda="http://www.passport.com/NameSpace.xsd" xmlns:ois="http://schemas.microsoft.com/sharepoint/soap/ois/" xmlns:dir="http://schemas.microsoft.com/sharepoint/soap/directory/" xmlns:ds="http://www.w3.org/2000/09/xmldsig#" xmlns:dsp="http://schemas.microsoft.com/sharepoint/dsp" xmlns:udc="http://schemas.microsoft.com/data/udc" xmlns:xsd="http://www.w3.org/2001/XMLSchema" xmlns:sub="http://schemas.microsoft.com/sharepoint/soap/2002/1/alerts/" xmlns:ec="http://www.w3.org/2001/04/xmlenc#" xmlns:sp="http://schemas.microsoft.com/sharepoint/" xmlns:sps="http://schemas.microsoft.com/sharepoint/soap/" xmlns:xsi="http://www.w3.org/2001/XMLSchema-instance" xmlns:udcs="http://schemas.microsoft.com/data/udc/soap" xmlns:udcxf="http://schemas.microsoft.com/data/udc/xmlfile" xmlns:udcp2p="http://schemas.microsoft.com/data/udc/parttopart" xmlns:wf="http://schemas.microsoft.com/sharepoint/soap/workflow/" xmlns:dsss="http://schemas.microsoft.com/office/2006/digsig-setup" xmlns:dssi="http://schemas.microsoft.com/office/2006/digsig" xmlns:mdssi="http://schemas.openxmlformats.org/package/2006/digital-signature" xmlns:mver="http://schemas.openxmlformats.org/markup-compatibility/2006" xmlns:m="http://schemas.microsoft.com/office/2004/12/omml" xmlns:mrels="http://schemas.openxmlformats.org/package/2006/relationships" xmlns:spwp="http://microsoft.com/sharepoint/webpartpages" xmlns:ex12t="http://schemas.microsoft.com/exchange/services/2006/types" xmlns:ex12m="http://schemas.microsoft.com/exchange/services/2006/messages" xmlns:pptsl="http://schemas.microsoft.com/sharepoint/soap/SlideLibrary/" xmlns:spsl="http://microsoft.com/webservices/SharePointPortalServer/PublishedLinksService" xmlns:Z="urn:schemas-microsoft-com:" xmlns:st="" xmlns="http://www.w3.org/TR/REC-html40">

<head>
<meta http-equiv=Content-Type content="text/html; charset=us-ascii">
<meta name=Generator content="Microsoft Word 12 (filtered medium)">
<style>
<!--
 /* Font Definitions */
 @font-face
        {font-family:Calibri;
        panose-1:2 15 5 2 2 2 4 3 2 4;}
@font-face
        {font-family:Tahoma;
        panose-1:2 11 6 4 3 5 4 4 2 4;}
 /* Style Definitions */
 p.MsoNormal, li.MsoNormal, div.MsoNormal
        {margin:0in;
        margin-bottom:.0001pt;
        font-size:12.0pt;
        font-family:"Times New Roman","serif";}
a:link, span.MsoHyperlink
        {mso-style-priority:99;
        color:blue;
        text-decoration:underline;}
a:visited, span.MsoHyperlinkFollowed
        {mso-style-priority:99;
        color:purple;
        text-decoration:underline;}
span.EmailStyle17
        {mso-style-type:personal-reply;
        font-family:"Calibri","sans-serif";
        color:#1F497D;}
.MsoChpDefault
        {mso-style-type:export-only;
        font-size:10.0pt;}
@page Section1
        {size:8.5in 11.0in;
        margin:1.0in 1.0in 1.0in 1.0in;}
div.Section1
        {page:Section1;}
-->
</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-US link=blue vlink=purple>

<div class=Section1>

<p class=MsoNormal><span style='font-size:11.0pt;font-family:"Calibri","sans-serif";
color:#1F497D'>Applied at 2936<o:p></o:p></span></p>

<p class=MsoNormal><span style='font-size:11.0pt;font-family:"Calibri","sans-serif";
color:#1F497D'><o:p> </o:p></span></p>

<div>

<div style='border:none;border-top:solid #B5C4DF 1.0pt;padding:3.0pt 0in 0in 0in'>

<p class=MsoNormal><b><span style='font-size:10.0pt;font-family:"Tahoma","sans-serif"'>From:</span></b><span
style='font-size:10.0pt;font-family:"Tahoma","sans-serif"'> Alex Naslednikov <br>
<b>Sent:</b> Sunday, May 23, 2010 10:07 AM<br>
<b>To:</b> Tzachi Dar; Uri Habusha<br>
<b>Cc:</b> ofw@lists.openfabrics.org<br>
<b>Subject:</b> [Patch][Tools] Change Peak BW calculation when the difference
between post and completion is abnormal<o:p></o:p></span></p>

</div>

</div>

<p class=MsoNormal><o:p> </o:p></p>

<div>

<div>

<p class=MsoNormal><span style='font-size:10.0pt;font-family:"Arial","sans-serif"'>The
function that used for time measuring  -
QueryPerformanceCounter()  - not always returns proper results.</span><o:p></o:p></p>

</div>

<div>

<p class=MsoNormal><span style='font-size:10.0pt;font-family:"Arial","sans-serif"'>According
to MS (<a
href="http://msdn.microsoft.com/en-us/library/ms644904%28VS.85%29.aspx">http://msdn.microsoft.com/en-us/library/ms644904%28VS.85%29.aspx</a>)</span><o:p></o:p></p>

</div>

<div>

<p class=MsoNormal><span style='font-size:10.0pt;font-family:"Arial","sans-serif"'>1.
It can return 0</span><o:p></o:p></p>

</div>

<div>

<p class=MsoNormal><span style='font-size:10.0pt;font-family:"Arial","sans-serif"'>2.
By default, one does not set the affinity and thus this function' call can be
adressed to any of the CPUs and you can get different results</span><o:p></o:p></p>

</div>

<div>

<p class=MsoNormal><span style='font-size:10.0pt;font-family:"Arial","sans-serif"'>3.
As a consequence, a time difference between post and completion can be
infinitely close to 0.</span><o:p></o:p></p>

</div>

<div>

<p class=MsoNormal><span style='font-size:10.0pt;font-family:"Arial","sans-serif"'>4.
It will not affect the BW but may affect Peak BW on some computers</span><o:p></o:p></p>

</div>

</div>

<div>

<p class=MsoNormal> <o:p></o:p></p>

</div>

<div>

<p class=MsoNormal><span style='font-size:10.0pt;font-family:"Arial","sans-serif"'>signed-off
by: Alexander Naslednikov (xalex at mellanox.co.il)</span><o:p></o:p></p>

</div>

<div>

<p class=MsoNormal><span style='font-size:10.0pt;font-family:"Arial","sans-serif"'>Index:
D:/windows/MLNX_VPI_trunk/tools/perftests/user/send_bw/send_bw.c<br>
===================================================================<br>
---
D:/windows/MLNX_VPI_trunk/tools/perftests/user/send_bw/send_bw.c (revision
5893)<br>
+++
D:/windows/MLNX_VPI_trunk/tools/perftests/user/send_bw/send_bw.c (revision
5894)<br>
@@ -571,13 +571,17 @@<br>
  cycles_t   t;<br>
 <br>
 <br>
+ tsize = duplex ? 2 : 1;<br>
+ tsize = tsize * size;<br>
+<br>
  opt_delta = tcompleted[opt_posted] - tposted[opt_completed];<br>
-<br>
+#define MAX_AVAILABLE_BW 40000000<br>
  /* Find the peak bandwidth */<br>
  for (i = 0; i < (int)iters; ++i)<br>
   for (j = i; j < (int)iters; ++j) {<br>
    t = (tcompleted[j] - tposted[i]) / (j - i + 1);<br>
-   if (t < opt_delta) {<br>
+   if (t < opt_delta && t > (tsize /
MAX_AVAILABLE_BW)) {<br>
+    // Avoid the sitatuation when opt_delta is infinitely
close to 0<br>
     opt_delta  = t;<br>
     opt_posted = i;<br>
     opt_completed = j;<br>
@@ -586,8 +590,6 @@<br>
 <br>
  cycles_to_units = get_cpu_mhz();<br>
 <br>
- tsize = duplex ? 2 : 1;<br>
- tsize = tsize * size;<br>
  printf("%7d       
%d           
%7.2f              
%7.2f \n",<br>
         size,iters,tsize *
cycles_to_units / opt_delta / 0x100000,<br>
   (uint64_t)tsize * iters * cycles_to_units /(tcompleted[iters
- 1] - tposted[0]) / 0x100000);<br>
Index: D:/windows/MLNX_VPI_trunk/tools/perftests/user/write_bw/write_bw.c<br>
===================================================================<br>
--- D:/windows/MLNX_VPI_trunk/tools/perftests/user/write_bw/write_bw.c (revision
5893)<br>
+++
D:/windows/MLNX_VPI_trunk/tools/perftests/user/write_bw/write_bw.c (revision
5894)<br>
@@ -501,13 +501,17 @@<br>
  cycles_t   t;<br>
 <br>
 <br>
+ tsize = duplex ? 2 : 1;<br>
+ tsize = tsize * size;<br>
+<br>
  opt_delta = tcompleted[opt_posted] - tposted[opt_completed];<br>
-<br>
+#define MAX_AVAILABLE_BW 40000000<br>
  /* Find the peak bandwidth */<br>
  for (i = 0; i < iters * user_param->numofqps; ++i)<br>
   for (j = i; j < iters * user_param->numofqps; ++j) {<br>
    t = (tcompleted[j] - tposted[i]) / (j - i + 1);<br>
-   if (t < opt_delta) {<br>
+   if (t < opt_delta && t > (tsize /
MAX_AVAILABLE_BW)) {<br>
+    // Avoid the sitatuation when opt_delta is infinitely
close to 0<br>
     opt_delta  = t;<br>
     opt_posted = i;<br>
     opt_completed = j;<br>
@@ -517,8 +521,6 @@<br>
  <br>
  cycles_to_units = get_cpu_mhz();<br>
 <br>
- tsize = duplex ? 2 : 1;<br>
- tsize = tsize * size;<br>
  printf("%7d       
%d           
%7.2f              
%7.2f\n",<br>
   size,iters,tsize * cycles_to_units / opt_delta / 0x100000,<br>
   (uint64_t)tsize * iters * user_param->numofqps * cycles_to_units
/(tcompleted[(iters* user_param->numofqps) - 1] - tposted[0]) / 0x100000);<br>
Index: D:/windows/MLNX_VPI_trunk/tools/perftests/user/read_bw/read_bw.c<br>
===================================================================<br>
--- D:/windows/MLNX_VPI_trunk/tools/perftests/user/read_bw/read_bw.c (revision
5893)<br>
+++
D:/windows/MLNX_VPI_trunk/tools/perftests/user/read_bw/read_bw.c (revision
5894)<br>
@@ -467,13 +467,17 @@<br>
  cycles_t   t;<br>
 <br>
 <br>
+ tsize = duplex ? 2 : 1;<br>
+ tsize = tsize * size;<br>
+<br>
  opt_delta = tcompleted[opt_posted] - tposted[opt_completed];<br>
-<br>
+#define MAX_AVAILABLE_BW 40000000<br>
  /* Find the peak bandwidth */<br>
  for (i = 0; i < iters; ++i)<br>
   for (j = i; j < iters; ++j) {<br>
    t = (tcompleted[j] - tposted[i]) / (j - i + 1);<br>
-   if (t < opt_delta) {<br>
+   if (t < opt_delta && t > (tsize /
MAX_AVAILABLE_BW)) {<br>
+    // Avoid the sitatuation when opt_delta is infinitely
close to 0<br>
     opt_delta  = t;<br>
     opt_posted = i;<br>
     opt_completed = j;<br>
@@ -482,8 +486,6 @@<br>
 <br>
  cycles_to_units = get_cpu_mhz() ;<br>
 <br>
- tsize = duplex ? 2 : 1;<br>
- tsize = tsize * size;<br>
  printf("%7d       
%d           
%7.2f              
%7.2f\n",<br>
         size,iters,tsize *
cycles_to_units / opt_delta / 0x100000,<br>
         (uint64_t)tsize * iters *
cycles_to_units /(tcompleted[iters - 1] - tposted[0]) / 0x100000);<o:p></o:p></span></p>

</div>

</div>

</body>

</html>