<html>
<head>
<meta http-equiv="Content-Type" content="text/html; charset=us-ascii">
</head>
<body style="word-wrap: break-word; -webkit-nbsp-mode: space; -webkit-line-break: after-white-space;" class="">
<style type="text/css" style="display:none;"><!-- P {margin-top:0;margin-bottom:0;} --></style>
<div id="divtagdefaultwrapper" style="font-size:12pt;color:#000000;font-family:Calibri,Arial,Helvetica,sans-serif;">
<p>I haven't found anything suspicious. There doesn't seem to be a <span>code path that generates an out record without updating last renewed field.</span></p>
<p><br>
</p>
<p>Even if there was a bug in the forwarding pipeline and it is not updated somewhere, I think we should not get a negative value:</p>
<p><br>
</p>
<p></p>
<div><i>1477331706.109322 ERROR: [AsfMeasurements] Recording RTT for inFace: 311</i></div>
<div><i><br>
</i></div>
<div><i>1477331706.109335 ERROR: [AsfMeasurements] steady clock now: 2148492683226381 nanoseconds since boot outRecordLastRenewed: 7018100696742452000 <span style="font-size: 12pt;">nanoseconds since boot</span></i></div>
<div><span style="font-size: 12pt;"><i><br>
</i></span></div>
<div><i>1477331706.109351 ERROR: [AsfMeasurements] steadyRtt: -7015952204059211821 nanoseconds</i></div>
<div><i>1477331706.109368 ERROR: [AsfMeasurements] Wrong measurement</i></div>
<div><br>
</div>
This means <span>time::steady_clock::now() is smaller <span>time::steady_clock::TimePoint::min().</span></span>
<p></p>
<p><span><span><br>
</span></span></p>
<p><span><span>(Machine is Ubuntu 14.04, gcc <span>4.9.3.</span></span></span></p>
<p><span><span><span>32 NFDs are running on this machine at the same time. Such wrong measurements happen randomly).</span></span></span></p>
<p><span><span><br>
</span></span></p>
<p><span><span>Ashlesh</span></span></p>
</div>
<hr style="display:inline-block;width:98%" tabindex="-1">
<div id="divRplyFwdMsg" dir="ltr"><font face="Calibri, sans-serif" style="font-size:11pt" color="#000000"><b>From:</b> Lan Wang (lanwang)<br>
<b>Sent:</b> Monday, October 24, 2016 1:21:49 PM<br>
<b>To:</b> Junxiao Shi<br>
<b>Cc:</b> Ashlesh Gawande (agawande); <nfd-dev@lists.cs.ucla.edu><br>
<b>Subject:</b> Re: Help needed with ASF measurement</font>
<div> </div>
</div>
<div>Junxiao,
<div class=""><br class="">
</div>
<div class="">Thank you very much for the quick feedback.</div>
<div class=""><br class="">
</div>
<div class="">Ashlesh: have you found anything suspicious?<br class="">
<div class="">
<div style="color: rgb(0, 0, 0); font-family: Helvetica; font-style: normal; font-variant: normal; font-weight: normal; letter-spacing: normal; line-height: normal; orphans: 2; text-align: -webkit-auto; text-indent: 0px; text-transform: none; white-space: normal; widows: 2; word-spacing: 0px; -webkit-text-size-adjust: auto; -webkit-text-stroke-width: 0px; word-wrap: break-word; -webkit-nbsp-mode: space; -webkit-line-break: after-white-space; " class="">
<div style="color: rgb(0, 0, 0); font-family: Helvetica; font-style: normal; font-variant: normal; font-weight: normal; letter-spacing: normal; line-height: normal; orphans: 2; text-align: -webkit-auto; text-indent: 0px; text-transform: none; white-space: normal; widows: 2; word-spacing: 0px; -webkit-text-size-adjust: auto; -webkit-text-stroke-width: 0px; word-wrap: break-word; -webkit-nbsp-mode: space; -webkit-line-break: after-white-space; " class="">
<span class="Apple-style-span" style="border-collapse: separate; color: rgb(0, 0, 0); font-family: Helvetica; font-style: normal; font-variant: normal; font-weight: normal; letter-spacing: normal; line-height: normal; orphans: 2; text-align: -webkit-auto; text-indent: 0px; text-transform: none; white-space: normal; widows: 2; word-spacing: 0px; border-spacing: 0px; -webkit-text-decorations-in-effect: none; -webkit-text-size-adjust: auto; -webkit-text-stroke-width: 0px; ">
<div style="word-wrap: break-word; -webkit-nbsp-mode: space; -webkit-line-break: after-white-space; " class="">
<div class=""><br class="Apple-interchange-newline">
Lan</div>
</div>
</span></div>
</div>
</div>
<br class="">
<div style="">
<blockquote type="cite" class="">
<div class="">On Oct 24, 2016, at 11:00 AM, Junxiao Shi <<a href="mailto:shijunxiao@email.arizona.edu" class="">shijunxiao@email.arizona.edu</a>> wrote:</div>
<br class="Apple-interchange-newline">
<div class="">
<p dir="ltr" class="">Hi Ashlesh</p>
<p dir="ltr" class="">This is probably a forwarding pipelines bug, but I won't have time to diagnose this until at least Thursday.</p>
<p dir="ltr" class="">Things to look at:</p>
<p dir="ltr" class="">1. Find every code line that updates last renewed field.<br class="">
2. Find which forwarding pipelines calls the function that updates last renewed field.<br class="">
3. Determine if there's a code path that generates an out record without updating last renewed field.</p>
<p dir="ltr" class="">Yours, Junxiao</p>
<div class="gmail_extra"><br class="">
<div class="gmail_quote">On Oct 24, 2016 08:52, "Ashlesh Gawande (agawande)" <<a href="mailto:agawande@memphis.edu" class="">agawande@memphis.edu</a>> wrote:<br type="attribution" class="">
<blockquote class="quote" style="margin:0 0 0 .8ex;border-left:1px #ccc solid;padding-left:1ex">
<div dir="ltr" class="">
<div id="m_-6286110043530299564divtagdefaultwrapper" style="font-size: 12pt; font-family: Calibri, Arial, Helvetica, sans-serif;" class="">
<p class="">Hi Junxiao</p>
<p class=""><br class="">
</p>
<p class="">I am testing ASF in Mini-NDN.</p>
<p class=""><br class="">
</p>
<p class="">The following line calculates the steady RTT by subtracting outRecord-><span class="">getLastRenewed()</span></p>
<p class="">from <span class="">time::steady_clock::now()</span></p>
<p class=""><a href="https://github.com/named-data/NFD/blob/master/daemon/fw/asf-measurements.cpp#L117" class="m_-6286110043530299564OWAAutoLink" id="m_-6286110043530299564LPlnk470837" target="_blank">https://github.com/named-data/<wbr class="">NFD/blob/master/daemon/fw/asf-<wbr class="">measurements.cpp#L117</a><br class="">
</p>
<p class="">(which is called from beforeSatisfyInterest <a href="https://github.com/named-data/NFD/blob/master/daemon/fw/asf-strategy.cpp#L115" class="m_-6286110043530299564OWAAutoLink" id="m_-6286110043530299564LPlnk412952" target="_blank">https://<wbr class="">github.com/named-data/NFD/<wbr class="">blob/master/daemon/fw/asf-<wbr class="">strategy.cpp#L115</a>)</p>
<p class=""><br class="">
</p>
<p class="">Sometimes the value of this steadyRTT is huge (ex: 200000 seconds) or negative.</p>
<p class="">This makes ASF change faces to a higher RTT face.</p>
<p class=""><br class="">
</p>
<p class="">So what could be the reason that this happening? I see much better and expected results if I ignore these high/negative values.</p>
<p class=""><br class="">
</p>
<p class="">(I see that <a href="https://github.com/named-data/NFD/blob/master/daemon/table/pit-face-record.cpp#L34" class="m_-6286110043530299564OWAAutoLink" id="m_-6286110043530299564LPlnk882460" target="_blank">https://github.com/named-<wbr class="">data/NFD/blob/master/daemon/<wbr class="">table/pit-face-record.cpp#L34</a></p>
<p class="">initializes getLastRenewed to <span class="">time::steady_clock::<wbr class="">TimePoint::min(). </span><span style="font-size:12pt" class="">So maybe for some reason getLastRenewed does not get updated?)</span></p>
<p class=""><span style="font-size:12pt" class=""><br class="">
</span></p>
<p class=""><span style="font-size:12pt" class="">Thanks</span></p>
<font color="#888888" class="">
<p class=""><span style="font-size:12pt" class="">Ashlesh</span></p>
</font></div>
</div>
</blockquote>
</div>
<br class="">
</div>
</div>
</blockquote>
</div>
<br class="">
</div>
</div>
</body>
</html>