<html><head>
<meta http-equiv="Content-Type" content="text/html; charset=utf-8">
</head>
<body>
<p><br>
</p>
<div class="moz-cite-prefix">On 12.08.2020 09:31, Hank Nussbacher
wrote:<br>
</div>
<blockquote type="cite" cite="mid:2bb12aaf-422a-1f34-464d-33fe9dfbfdc7@interall.co.il">
<style type="text/css">body p { margin-bottom: 0cm; margin-top: 0pt; } </style>
<p>At what point do commercial ISPs upgrade links in their
backbone as well as peering and transit links that are
congested? At 80% capacity? 90%? 95%? </p>
</blockquote>
<p><br>
</p>
<p>Hi,</p>
<p><br>
</p>
<p>Wouldn't it be better to measure the basic performance like
packet drop rates and queue sizes ?</p>
<p>These days live video is needed and these parameters are
essential to the quality.</p>
<p>Queues are building up in milliseconds and people are averaging
over minutes to estimate quality.<br>
</p>
<p><br>
</p>
<p>If you are measuring queue delay with high frequent one-way-delay
measurements <br>
</p>
<p>you would then be able to advice better on what the consequences
of a highly loaded link are.</p>
<p><br>
</p>
<p>We are running a research project on end-to-end quality and the
enclosed image is yesterdays report on</p>
<p>queuesize(h_ddelay) in ms. It shows stats on delays between some
peers.</p>
<p>I would have looked at the trends on the involved links to see if
upgrade is necessary - <br>
</p>
<p>421 ms might be too much ig it happens often.<br>
</p>
<p><br>
</p>
<p>Best regards<br>
</p>
<p><br>
</p>
<p> Olav Kvittem<br>
</p>
<p><img src="cid:part1.9D548DEA.5A943FD2@uninett.no" alt=""></p>
<p><br>
</p>
<blockquote type="cite" cite="mid:2bb12aaf-422a-1f34-464d-33fe9dfbfdc7@interall.co.il">
<p><br>
</p>
<p>Thanks,<br>
Hank</p>
<p><br>
</p>
<p>Caveat: The views expressed above are solely my own and do not
express the views or opinions of my employer <br>
</p>
</blockquote>
</body>
</html>