From: Jonathan Morton <chromatix99@gmail.com>
To: Polina Goltsman <polina.goltsman@student.kit.edu>
Cc: Roland Bless <roland.bless@kit.edu>,
codel@lists.bufferbloat.net, aqm@ietf.org
Subject: Re: [Codel] [aqm] Codel's count variable and re-entering dropping state at small time intervals
Date: Fri, 14 Aug 2015 18:59:08 +0300 [thread overview]
Message-ID: <29E9D01D-F0B3-4F1B-A4B3-057668148E82@gmail.com> (raw)
In-Reply-To: <55CE085F.5080700@student.kit.edu>
> On 14 Aug, 2015, at 18:25, Polina Goltsman <polina.goltsman@student.kit.edu> wrote:
>
> What is the default value of "threshold" for default interval and target?
From sch_cake.c 694-696:
fqcd->cparams.target = max(byte_target_ns, ns_target);
fqcd->cparams.interval = max(MS2TIME(100) + fqcd->cparams.target - ns_target, fqcd->cparams.target * 8);
fqcd->cparams.threshold = (fqcd->cparams.target >> 15) * (fqcd->cparams.interval >> 15) * 2;
Given default interval is 100ms (100,000,000 ns) and target is 5ms (5,000,000 ns), threshold will be about 931,322. This is compared to the scaled product of sojourn time and the time since the target was first exceeded, so its units are not time but time-squared.
The calculation is designed to place the trigger when the queue is growing as slowly as possible (ie. resting just above the target sojourn time) at twice the nominal interval. This also places the fastest possible trigger at about a third of the nominal interval.
- Jonathan Morton
next prev parent reply other threads:[~2015-08-14 15:59 UTC|newest]
Thread overview: 6+ messages / expand[flat|nested] mbox.gz Atom feed top
[not found] <55AD2695.8050605@kit.edu>
2015-07-20 17:04 ` [Codel] Fwd: " Dave Taht
2015-07-20 19:34 ` [Codel] " Jonathan Morton
[not found] ` <55CDE8E3.4080207@student.kit.edu>
2015-08-14 14:52 ` Jonathan Morton
[not found] ` <55CE085F.5080700@student.kit.edu>
2015-08-14 15:59 ` Jonathan Morton [this message]
2015-08-14 16:11 ` Jonathan Morton
[not found] ` <7A2801D5E40DD64A85E38DF22117852C70AE040F@wdc1exchmbxp05.hq.corp.viasat.com>
[not found] ` <87a8rlvmxy.fsf@toke.dk>
[not found] ` <7A2801D5E40DD64A85E38DF22117852C8812F7E5@wdc1exchmbxp05.hq.corp.viasat.com>
[not found] ` <87io69twyi.fsf@toke.dk>
[not found] ` <7A2801D5E40DD64A85E38DF22117852C8812FD9E@wdc1exchmbxp05.hq.corp.viasat.com>
[not found] ` <703269EE-2B09-4F2B-9462-6CB644371875@toke.dk>
[not found] ` <7A2801D5E40DD64A85E38DF22117852C8813002D@wdc1exchmbxp05.hq.corp.viasat.com>
2015-10-14 19:05 ` Dave Taht
Reply instructions:
You may reply publicly to this message via plain-text email
using any one of the following methods:
* Save the following mbox file, import it into your mail client,
and reply-to-all from there: mbox
Avoid top-posting and favor interleaved quoting:
https://en.wikipedia.org/wiki/Posting_style#Interleaved_style
List information: https://lists.bufferbloat.net/postorius/lists/codel.lists.bufferbloat.net/
* Reply using the --to, --cc, and --in-reply-to
switches of git-send-email(1):
git send-email \
--in-reply-to=29E9D01D-F0B3-4F1B-A4B3-057668148E82@gmail.com \
--to=chromatix99@gmail.com \
--cc=aqm@ietf.org \
--cc=codel@lists.bufferbloat.net \
--cc=polina.goltsman@student.kit.edu \
--cc=roland.bless@kit.edu \
/path/to/YOUR_REPLY
https://kernel.org/pub/software/scm/git/docs/git-send-email.html
* If your mail client supports setting the In-Reply-To header
via mailto: links, try the mailto: link
Be sure your reply has a Subject: header at the top and a blank line
before the message body.
This is a public inbox, see mirroring instructions
for how to clone and mirror all data and code used for this inbox