From: Kevin Darbyshire-Bryant <kevin@darbyshire-bryant.me.uk>
To: Jesper Dangaard Brouer <brouer@redhat.com>,
Eric Dumazet <eric.dumazet@gmail.com>,
Felix Fietkau <nbd@openwrt.org>, Dave Taht <dave.taht@gmail.com>
Cc: <make-wifi-fast@lists.bufferbloat.net>, <zajec5@gmail.com>,
ath10k <ath10k@lists.infradead.org>,
"netdev@vger.kernel.org" <netdev@vger.kernel.org>,
"codel@lists.bufferbloat.net" <codel@lists.bufferbloat.net>,
Jonathan Morton <chromatix99@gmail.com>,
Roman Yeryomin <leroi.lists@gmail.com>
Subject: Re: [Make-wifi-fast] OpenWRT wrong adjustment of fq_codel defaults (Was: [Codel] fq_codel_drop vs a udp flood)
Date: Sat, 7 May 2016 10:57:53 +0100 [thread overview]
Message-ID: <572DBC21.10209@darbyshire-bryant.me.uk> (raw)
In-Reply-To: <20160506114243.4eb4f95e@redhat.com>
[-- Attachment #1: Type: text/plain, Size: 1814 bytes --]
On 06/05/16 10:42, Jesper Dangaard Brouer wrote:
> Hi Felix,
>
> This is an important fix for OpenWRT, please read!
>
> OpenWRT changed the default fq_codel sch->limit from 10240 to 1024,
> without also adjusting q->flows_cnt. Eric explains below that you must
> also adjust the buckets (q->flows_cnt) for this not to break. (Just
> adjust it to 128)
>
> Problematic OpenWRT commit in question:
> http://git.openwrt.org/?p=openwrt.git;a=patch;h=12cd6578084e
> 12cd6578084e ("kernel: revert fq_codel quantum override to prevent it from causing too much cpu load with higher speed (#21326)")
I 'pull requested' this to the lede-staging tree on github.
https://github.com/lede-project/staging/pull/11
One way or another Felix & co should see the change :-)
>
>
> I also highly recommend you cherry-pick this very recent commit:
> net-next: 9d18562a2278 ("fq_codel: add batch ability to fq_codel_drop()")
> https://git.kernel.org/davem/net-next/c/9d18562a227
>
> This should fix very high CPU usage in-case fq_codel goes into drop mode.
> The problem is that drop mode was considered rare, and implementation
> wise it was chosen to be more expensive (to save cycles on normal mode).
> Unfortunately is it easy to trigger with an UDP flood. Drop mode is
> especially expensive for smaller devices, as it scans a 4K big array,
> thus 64 cache misses for small devices!
>
> The fix is to allow drop-mode to bulk-drop more packets when entering
> drop-mode (default 64 bulk drop). That way we don't suddenly
> experience a significantly higher processing cost per packet, but
> instead can amortize this.
I haven't done the above cherry-pick patch & backport patch creation for
4.4/4.1/3.18 yet - maybe if $dayjob permits time and no one else beats
me to it :-)
Kevin
[-- Attachment #2: S/MIME Cryptographic Signature --]
[-- Type: application/pkcs7-signature, Size: 4816 bytes --]
next prev parent reply other threads:[~2016-05-07 9:58 UTC|newest]
Thread overview: 80+ messages / expand[flat|nested] mbox.gz Atom feed top
2016-05-01 3:41 [Make-wifi-fast] fq_codel_drop vs a udp flood Dave Taht
2016-05-01 4:46 ` Jonathan Morton
2016-05-01 5:08 ` Ben Greear
2016-05-01 5:23 ` Dave Taht
2016-05-01 14:47 ` dpreed
[not found] ` <CAJq5cE2woA3yb6i_7NLPpxjzvhsVk5uL8BnSTAY7Lp-M0KiPNg@mail.gmail.com>
[not found] ` <CAJq5cE2K0yrz6ALAoKWu23RSJZX9Y_P7Mqcy9ba8e-L3AVhOaA@mail.gmail.com>
2016-05-01 15:51 ` Jonathan Morton
2016-05-02 14:03 ` Roman Yeryomin
2016-05-02 18:40 ` Dave Taht
2016-05-02 20:17 ` [Make-wifi-fast] [Codel] " Isaac Konikoff
2016-05-05 13:55 ` [Make-wifi-fast] " Roman Yeryomin
2016-05-05 14:55 ` Roman Yeryomin
2016-05-02 19:47 ` David Lang
2016-05-01 17:59 ` [Make-wifi-fast] [Codel] " Eric Dumazet
2016-05-01 18:20 ` Jonathan Morton
2016-05-01 18:46 ` Eric Dumazet
2016-05-01 19:55 ` Eric Dumazet
2016-05-02 7:47 ` Jesper Dangaard Brouer
2016-05-01 20:35 ` Jonathan Morton
2016-05-01 20:55 ` Eric Dumazet
2016-05-02 14:18 ` Roman Yeryomin
2016-05-02 15:07 ` Eric Dumazet
2016-05-02 15:43 ` Roman Yeryomin
2016-05-02 16:14 ` Eric Dumazet
2016-05-02 17:08 ` Dave Taht
2016-05-02 17:44 ` Eric Dumazet
2016-05-05 14:32 ` Roman Yeryomin
2016-05-05 14:53 ` Roman Yeryomin
2016-05-05 15:32 ` Dave Taht
2016-05-05 16:07 ` Roman Yeryomin
2016-05-05 16:59 ` Jonathan Morton
2016-05-05 17:39 ` Roman Yeryomin
2016-05-05 18:16 ` Dave Taht
2016-05-05 18:33 ` Dave Taht
2016-05-05 16:12 ` Eric Dumazet
2016-05-05 16:25 ` Roman Yeryomin
2016-05-05 16:42 ` Roman Yeryomin
2016-05-06 10:55 ` Roman Yeryomin
2016-05-05 19:23 ` Eric Dumazet
2016-05-05 19:41 ` Dave Taht
2016-05-06 8:41 ` moeller0
2016-05-06 11:33 ` Jesper Dangaard Brouer
2016-05-06 11:46 ` moeller0
2016-05-06 13:25 ` Eric Dumazet
2016-05-06 15:25 ` moeller0
2016-05-06 15:58 ` Eric Dumazet
2016-05-06 16:30 ` moeller0
2016-05-06 9:42 ` [Make-wifi-fast] OpenWRT wrong adjustment of fq_codel defaults (Was: [Codel] fq_codel_drop vs a udp flood) Jesper Dangaard Brouer
2016-05-06 12:47 ` Jesper Dangaard Brouer
2016-05-06 18:43 ` Roman Yeryomin
2016-05-06 18:56 ` Roman Yeryomin
2016-05-06 19:43 ` Dave Taht
2016-05-15 22:34 ` Roman Yeryomin
2016-05-15 23:07 ` Eric Dumazet
2016-05-15 23:27 ` Roman Yeryomin
2016-05-16 8:12 ` David Lang
2016-05-16 8:26 ` Roman Yeryomin
2016-05-16 8:46 ` David Lang
2016-05-16 10:34 ` [Make-wifi-fast] [OpenWrt-Devel] " Sebastian Moeller
2016-05-16 8:14 ` [Make-wifi-fast] " Roman Yeryomin
2016-05-16 14:23 ` Eric Dumazet
2016-05-16 16:04 ` Dave Taht
2016-05-16 19:46 ` Roman Yeryomin
2016-05-07 9:57 ` Kevin Darbyshire-Bryant [this message]
2016-05-15 22:47 ` Roman Yeryomin
2016-05-03 2:26 ` [Make-wifi-fast] [Codel] fq_codel_drop vs a udp flood Dave Taht
2016-05-03 5:21 ` Dave Taht
2016-05-03 12:39 ` Agarwal, Anil
2016-05-03 12:50 ` Agarwal, Anil
2016-05-03 13:35 ` Eric Dumazet
2016-05-03 15:37 ` Agarwal, Anil
2016-05-03 17:37 ` Dave Taht
2016-05-03 17:54 ` Eric Dumazet
2016-05-03 18:11 ` Dave Taht
2016-05-01 18:26 ` Dave Taht
2016-05-01 22:30 ` Eric Dumazet
2016-05-02 14:09 ` Roman Yeryomin
2016-05-02 15:04 ` Eric Dumazet
2016-05-02 15:42 ` Roman Yeryomin
2016-05-02 13:47 ` [Make-wifi-fast] " Roman Yeryomin
2016-05-02 15:01 ` Eric Dumazet
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/make-wifi-fast.lists.bufferbloat.net/
* Reply using the --to, --cc, and --in-reply-to
switches of git-send-email(1):
git send-email \
--in-reply-to=572DBC21.10209@darbyshire-bryant.me.uk \
--to=kevin@darbyshire-bryant.me.uk \
--cc=ath10k@lists.infradead.org \
--cc=brouer@redhat.com \
--cc=chromatix99@gmail.com \
--cc=codel@lists.bufferbloat.net \
--cc=dave.taht@gmail.com \
--cc=eric.dumazet@gmail.com \
--cc=leroi.lists@gmail.com \
--cc=make-wifi-fast@lists.bufferbloat.net \
--cc=nbd@openwrt.org \
--cc=netdev@vger.kernel.org \
--cc=zajec5@gmail.com \
/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