From: David Lang <david@lang.hm>
To: Sebastian Moeller <moeller0@gmx.de>
Cc: Jonathan Morton <chromatix99@gmail.com>,
"cake@lists.bufferbloat.net" <cake@lists.bufferbloat.net>
Subject: Re: [Cake] CAKE upstreaming - testers wanted, ACK filtering rescuers needed
Date: Thu, 26 Apr 2018 17:17:08 -0700 (PDT) [thread overview]
Message-ID: <alpine.DEB.2.02.1804261715350.4538@nftneq.ynat.uz> (raw)
In-Reply-To: <51A5A6AB-4B1C-4795-8136-9EB63E59598B@gmx.de>
[-- Attachment #1: Type: TEXT/PLAIN, Size: 1880 bytes --]
On Thu, 26 Apr 2018, Sebastian Moeller wrote:
>> On Apr 26, 2018, at 09:26, Jonathan Morton <chromatix99@gmail.com> wrote:
>>
>>> Genuine question: I have a superpacket circa 64K, this is a lump of data in a tcp flow. I have another small VOIP packet, it’s latency sensitive. If I split the super packet into individual 1.5K packets as they would be on the wire, I can insert my VOIP packet at suitable place in time such that jitter targets are not exceeded. If I don’t split the super packet, surely I have to wait till the end of the superpacket’s queue (for want of a better word) and possibly exceed my latency target. That looks to me like ‘GSO/TSO’ is potentially bad for interflow latencies.
>>
>>> What don’t I understand here?
>>
>> You have it exactly right. For some reason, Eric is failing to consider the general case of flow-isolating queues at low link rates, and only considering high-rate FIFOs.
>>
>> More to the point, at 64Kbps a maximal GSO packet can take 8 seconds to clear, while an MTU packet takes less than a quarter second!
>
> I venture a guess that it is not so much the concept but rather the
> terminology that irritates Eric? If at all Superpackets lighten the kernel's
> load and will in all likelihood make in-kernel processing faster which if at
> all decreases latency. The effect on flow fairness that we are concerned about
> might simply not register under "latency" for the kernel developers; I am sure
> they see the issue and this is really about which words to use to describe
> this... Also I point at the fact that Eric did not object to the feature per
> se, but rather the unconditionality and the rationale.
Keep in mind that he was also griping about the focus on <100M bandwidth limits
and talking about >10G links. At those speeds, the large GSO packet is not a
significant factor.
David Lang
next prev parent reply other threads:[~2018-04-27 0:17 UTC|newest]
Thread overview: 18+ messages / expand[flat|nested] mbox.gz Atom feed top
2018-04-25 20:45 Toke Høiland-Jørgensen
2018-04-26 1:10 ` Ryan Mounce
2018-04-26 1:32 ` Stephen Hemminger
2018-04-26 3:23 ` Dave Taht
2018-04-26 6:39 ` Toke Høiland-Jørgensen
2018-04-26 6:54 ` Ryan Mounce
2018-04-26 7:14 ` Toke Høiland-Jørgensen
2018-04-26 7:19 ` Kevin Darbyshire-Bryant
2018-04-26 7:34 ` Toke Høiland-Jørgensen
2018-04-26 8:43 ` Jonas Mårtensson
2018-04-26 8:55 ` Toke Høiland-Jørgensen
2018-04-26 12:02 ` Jonas Mårtensson
[not found] ` <mailman.301.1524727201.3573.cake@lists.bufferbloat.net>
2018-04-26 7:26 ` Jonathan Morton
2018-04-26 7:43 ` Sebastian Moeller
2018-04-26 14:42 ` Jonathan Morton
2018-04-26 15:25 ` Sebastian Moeller
2018-04-27 0:17 ` David Lang [this message]
2018-04-26 8:16 ` Kevin Darbyshire-Bryant
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/cake.lists.bufferbloat.net/
* Reply using the --to, --cc, and --in-reply-to
switches of git-send-email(1):
git send-email \
--in-reply-to=alpine.DEB.2.02.1804261715350.4538@nftneq.ynat.uz \
--to=david@lang.hm \
--cc=cake@lists.bufferbloat.net \
--cc=chromatix99@gmail.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