<html>
<head>
<meta content="text/html; charset=utf-8" http-equiv="Content-Type">
</head>
<body text="#000000" bgcolor="#FFFFFF">
<br>
<br>
<div class="moz-cite-prefix">On 08/27/2016 11:06, David Lang wrote:<br>
</div>
<blockquote
cite="mid:alpine.DEB.2.02.1608261758530.18129@nftneq.ynat.uz"
type="cite">On Fri, 26 Aug 2016, Kathleen Nichols wrote:
<br>
<br>
</blockquote>
[..]<br>
<blockquote
cite="mid:alpine.DEB.2.02.1608261758530.18129@nftneq.ynat.uz"
type="cite">
<blockquote type="cite">
<blockquote type="cite">so you can call it large queues instead
of large buffers, but the result
<br>
is that packets end up being 'in transit' for a long time.
<br>
</blockquote>
<br>
No, a large queue is a bunch of packets waiting in a queue
(which is contained in a buffer). A large buffer with zero or a
small number of packets in it is not going to result in packets
being in transit for a long time.
<br>
</blockquote>
</blockquote>
[..]<br>
<blockquote
cite="mid:alpine.DEB.2.02.1608261758530.18129@nftneq.ynat.uz"
type="cite">
<br>
I don't understand what you are trying to call out by trying to
change the terminology.
<br>
</blockquote>
<br>
I think you're almost in violent agreement, except that Kathy is
differentiating between the space set aside for holding between 0
and N packets (or bytes) of data for delivery (a <i>buffer</i>) and
an instance of packets queued up to a particular depth in a buffer
(a <i>queue</i>) . Given that terminology, a bottleneck may
implement a large buffer, but with proper congestion signals (or eg.
delay-based congestion inference by end points) there might only
ever be small queues build up in the (large) buffer.<br>
<br>
cheers,<br>
gja<br>
<br>
</body>
</html>