From: Jonathan Morton <chromatix99@gmail.com>
To: Sebastian Moeller <moeller0@gmx.de>
Cc: Jonathan Foulkes <jf@jonathanfoulkes.com>,
bloat <bloat@lists.bufferbloat.net>
Subject: Re: [Bloat] [Bug 1436945] Re: devel: consider fq_codel as the default qdisc for networking
Date: Tue, 5 Jun 2018 22:31:30 +0300 [thread overview]
Message-ID: <6AD85E99-BCD8-4548-AAA4-F5B08599C7AD@gmail.com> (raw)
In-Reply-To: <9675C88A-FCC0-43EB-9C71-CBEFD67408CB@gmx.de>
> On 5 Jun, 2018, at 9:34 pm, Sebastian Moeller <moeller0@gmx.de> wrote:
>
> The rationale for that decision still is valid, at low bandwidth every opportunity to send a packet matters…
Yes, which is why the DRR++ algorithm is used to carefully choose which flow to send a packet from.
> …and every packet being transferred will increase the queued packets delay by its serialization delay.
This is trivially true, but has no effect whatsoever on inter-flow induced latency, only intra-flow delay, which is already managed adequately well by an ECN-aware sender.
May I remind you that Cake never drops the last packet in a flow subqueue due to AQM action, but may still apply an ECN mark to it. That's because dropping a tail packet carries a risk of incurring an RTO before retransmission occurs, rather than "only" an RTT delay. Both RTO and RTT are always greater than the serialisation delay of a single packet.
Which is why ECN remains valuable even on very low-bandwidth links.
- Jonathan Morton
next prev parent reply other threads:[~2018-06-05 19:31 UTC|newest]
Thread overview: 29+ messages / expand[flat|nested] mbox.gz Atom feed top
[not found] <152717340941.28154.812883711295847116.malone@soybean.canonical.com>
2018-05-24 15:38 ` [Bloat] Fwd: " Jan Ceuleers
2018-06-04 11:28 ` Bless, Roland (TM)
2018-06-04 13:16 ` Jonas Mårtensson
2018-06-04 17:08 ` Dave Taht
2018-06-04 18:22 ` Jonas Mårtensson
2018-06-04 21:36 ` Jonathan Morton
2018-06-05 15:10 ` [Bloat] " Jonathan Foulkes
2018-06-05 17:24 ` Jonathan Morton
2018-06-05 18:34 ` Sebastian Moeller
2018-06-05 19:31 ` Jonathan Morton [this message]
2018-06-06 6:53 ` Sebastian Moeller
2018-06-06 13:04 ` Jonathan Morton
2018-06-12 6:39 ` Dave Taht
2018-06-12 6:47 ` Dave Taht
2018-08-11 19:17 ` Dave Taht
2018-08-13 22:29 ` [Bloat] ecn redux Dave Taht
2018-06-06 7:44 ` [Bloat] [Bug 1436945] Re: devel: consider fq_codel as the default qdisc for networking Bless, Roland (TM)
2018-06-06 8:15 ` Sebastian Moeller
2018-06-06 8:55 ` Mario Hock
2018-06-05 0:22 ` [Bloat] Fwd: " Michael Richardson
2018-06-05 6:21 ` Jonas Mårtensson
2018-06-06 4:14 ` Mikael Abrahamsson
2018-06-07 12:56 ` [Bloat] Fwd: [Bug 1436945] -> What other options/bufferbloat-advice ... ? Simon Iremonger (bufferbloat)
2018-06-04 23:00 ` [Bloat] Fwd: [Bug 1436945] Re: devel: consider fq_codel as the default qdisc for networking David Lang
2018-06-05 7:44 ` Mario Hock
2018-06-05 7:49 ` Jonathan Morton
2018-06-05 11:01 ` Mario Hock
2018-08-16 21:08 ` Dave Taht
[not found] <mailman.3.1527177601.17575.bloat@lists.bufferbloat.net>
2018-05-24 16:31 ` [Bloat] " Rich Brown
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/bloat.lists.bufferbloat.net/
* Reply using the --to, --cc, and --in-reply-to
switches of git-send-email(1):
git send-email \
--in-reply-to=6AD85E99-BCD8-4548-AAA4-F5B08599C7AD@gmail.com \
--to=chromatix99@gmail.com \
--cc=bloat@lists.bufferbloat.net \
--cc=jf@jonathanfoulkes.com \
--cc=moeller0@gmx.de \
/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