From: David Miller <davem@davemloft.net>
To: eric.dumazet@gmail.com
Cc: jim_baxter@mentor.com, linux-usb@vger.kernel.org,
linux-kernel@vger.kernel.org, netdev@vger.kernel.org,
kamal@canonical.com, bhutchings@solarflare.com,
edumazet@google.com, mszeredi@suse.cz, fw@strlen.de,
bjorn@mork.no
Subject: Re: skbuff truesize incorrect.
Date: Thu, 22 May 2014 17:10:33 -0400 (EDT) [thread overview]
Message-ID: <20140522.171033.1040508444998374401.davem@davemloft.net> (raw)
In-Reply-To: <1400792601.5367.176.camel@edumazet-glaptop2.roam.corp.google.com>
From: Eric Dumazet <eric.dumazet@gmail.com>
Date: Thu, 22 May 2014 14:03:21 -0700
> On Thu, 2014-05-22 at 13:58 -0700, Eric Dumazet wrote:
>
>> I would set rx_max (rx_urb_size) to SKB_MAX_HEAD(0) so that you do not
>> use high order allocations.
>
> Correction, that would need SKB_MAX_HEAD(NET_SKB_PAD + NET_IP_ALIGN),
> because drivers/net/usb/usbnet.c calls __netdev_alloc_skb_ip_align().
I seem to recall that this driver has a lot of strange buffering
restrictions and that Bjorn Mork was talking a lot about this
recently.
Bjorn people are getting really burnt because the driver ends up
having a skb->truesize of 32K for the buffers it allocates on receive
and this chokes up TCP and SCTP because the socket memory limits
are hitting earlier than they should.
We've just in the past few postings been discussing whether the just
copy every packet into a more appropriately sized buffer, and it isn't
clear if that's a good idea of the data rates handled here.
next prev parent reply other threads:[~2014-05-22 21:10 UTC|newest]
Thread overview: 32+ messages / expand[flat|nested] mbox.gz Atom feed top
2014-05-22 19:07 skbuff truesize incorrect Jim Baxter
2014-05-22 19:21 ` David Miller
2014-05-22 20:21 ` Jim Baxter
[not found] ` <537E5C63.7080607-nmGgyN9QBj3QT0dZR+AlfA@public.gmane.org>
2014-05-22 20:30 ` Eric Dumazet
2014-05-22 20:58 ` David Miller
2014-05-23 9:21 ` Jim Baxter
2014-05-23 9:27 ` David Laight
2014-05-23 16:46 ` David Miller
2014-05-22 19:25 ` Vlad Yasevich
2014-05-22 19:39 ` Jim Baxter
2014-05-22 19:59 ` Eric Dumazet
2014-05-22 20:21 ` Jim Baxter
2014-05-22 20:58 ` Eric Dumazet
2014-05-22 21:03 ` Eric Dumazet
2014-05-22 21:10 ` David Miller [this message]
2014-05-23 7:07 ` Bjørn Mork
2014-05-23 8:58 ` Jim Baxter
2014-05-23 9:33 ` Bjørn Mork
2014-05-23 14:00 ` Eric Dumazet
2014-05-23 15:44 ` Rick Jones
2014-05-23 16:00 ` Eric Dumazet
2014-05-23 8:52 ` David Laight
2014-05-23 9:48 ` Bjørn Mork
2014-05-23 10:45 ` David Laight
2014-05-23 11:13 ` Jim Baxter
2014-05-23 13:47 ` Eric Dumazet
2014-05-23 15:00 ` Jim Baxter
2014-05-23 15:30 ` David Laight
2014-05-23 15:41 ` Eric Dumazet
2014-05-23 20:18 ` David Miller
2014-05-27 15:23 ` David Laight
[not found] ` <063D6719AE5E284EB5DD2968C1650D6D1724E565-VkEWCZq2GCInGFn1LkZF6NBPR1lH4CV8@public.gmane.org>
2014-05-27 15:52 ` David Miller
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
* Reply using the --to, --cc, and --in-reply-to
switches of git-send-email(1):
git send-email \
--in-reply-to=20140522.171033.1040508444998374401.davem@davemloft.net \
--to=davem@davemloft.net \
--cc=bhutchings@solarflare.com \
--cc=bjorn@mork.no \
--cc=edumazet@google.com \
--cc=eric.dumazet@gmail.com \
--cc=fw@strlen.de \
--cc=jim_baxter@mentor.com \
--cc=kamal@canonical.com \
--cc=linux-kernel@vger.kernel.org \
--cc=linux-usb@vger.kernel.org \
--cc=mszeredi@suse.cz \
--cc=netdev@vger.kernel.org \
/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;
as well as URLs for NNTP newsgroup(s).