From: Hans Westgaard Ry <hans.westgaard.ry@oracle.com>
To: David Laight <David.Laight@ACULAB.COM>,
"David S. Miller" <davem@davemloft.net>
Cc: Alexey Kuznetsov <kuznet@ms2.inr.ac.ru>,
James Morris <jmorris@namei.org>,
Hideaki YOSHIFUJI <yoshfuji@linux-ipv6.org>,
Patrick McHardy <kaber@trash.net>,
Alexei Starovoitov <ast@plumgrid.com>,
Jiri Pirko <jiri@mellanox.com>,
Eric Dumazet <edumazet@google.com>,
Daniel Borkmann <daniel@iogearbox.net>,
Nicolas Dichtel <nicolas.dichtel@6wind.com>,
"Eric W. Biederman " <ebiederm@xmission.com>,
Salam Noureddine <noureddine@arista.com>,
Jarod Wilson <jarod@redhat.com>,
Toshiaki Makita <makita.toshiaki@lab.ntt.co.jp>,
Julian Anastasov <ja@ssi.bg>, Ying Xue <ying.xue@windriver.com>,
Craig Gallek <kraig@google.com>,
Mel Gorman <mgorman@techsingularity.net>,
"\" hannes\"@stressinduktion.org " <hannes@stressinduktion.org>,
Edward Jee <edjee@google.com>,
Julia Lawall <julia.lawall@lip6.fr>,
"netdev@vger.kernel.org" <netdev@vger.kernel.org>,
"linux-kernel@vger.kernel.org" <linux-kernel@vger.kernel.org>,
Haakon Bugge <haakon.bugge@oracle.com>,
Knut Omang <knut.omang@oracle.com>,
Wei Lin Guay <wei.lin.guay@oracle.com>,
Santosh Shilimkar <santosh.shilimkar@oracle.com>,
Yuval Shaia <yuval.shaia@oracle.com>
Subject: Re: [PATCH] net: add per device sg_max_frags for skb
Date: Fri, 8 Jan 2016 10:55:56 +0100 [thread overview]
Message-ID: <568F87AC.60405@oracle.com> (raw)
In-Reply-To: <063D6719AE5E284EB5DD2968C1650D6D1CCBE5AA@AcuExch.aculab.com>
On 01/06/2016 02:59 PM, David Laight wrote:
> From: Hans Westgaard Ry
>> Sent: 06 January 2016 13:16
>> Devices may have limits on the number of fragments in an skb they
>> support. Current codebase uses a constant as maximum for number of
>> fragments (MAX_SKB_FRAGS) one skb can hold and use.
>>
>> When enabling scatter/gather and running traffic with many small
>> messages the codebase uses the maximum number of fragments and thereby
>> violates the max for certain devices.
>>
>> An example of such a violation is when running IPoIB on a HCA
>> supporting 16 SGE on an architecture with 4K pagesize. The
>> MAX_SKB_FRAGS will be 17 (64K/4K+1) and because IPoIB adds yet another
>> segment we end up with send_requests with 18 SGE resulting in
>> kernel-panic.
>>
>> The patch allows the device to limit the maximum number fragments used
>> in one skb.
> This doesn't seem to me to be the correct way to fix this.
> Anything that adds an extra fragment (in this case IPoIB) should allow
> for the skb already having the maximum number of fragments.
> Fully linearising the skb is overkill, but I think the first fragment
> can be added to the linear part of the skb.
>
> David
>
>
When IpoIB handles a skb-request it converts fragments to SGEs to
be handled by a HCA.
The problem arises when the HCA have a limited number of SGEs less than
MAX_SKB_FRAGS.
(it gets a little worse since IPoIB need to yet another segment)
I have not found any easy way of fixing this with currenct codebase.
Hans
next prev parent reply other threads:[~2016-01-08 9:57 UTC|newest]
Thread overview: 34+ messages / expand[flat|nested] mbox.gz Atom feed top
2016-01-06 13:16 [PATCH] net: add per device sg_max_frags for skb Hans Westgaard Ry
2016-01-06 13:59 ` David Laight
2016-01-08 9:55 ` Hans Westgaard Ry [this message]
2016-01-08 10:33 ` David Laight
2016-01-08 11:47 ` Hannes Frederic Sowa
2016-01-13 13:57 ` Hans Westgaard Ry
2016-01-13 14:19 ` Eric Dumazet
2016-01-13 14:20 ` Eric Dumazet
2016-01-13 15:07 ` Hannes Frederic Sowa
2016-01-13 15:38 ` David Miller
2016-01-13 15:44 ` Eric Dumazet
2016-01-13 21:07 ` Eric W. Biederman
2016-01-27 13:20 ` [PATCH v2] net:Add sysctl_tcp_sg_max_skb_frags Hans Westgaard Ry
2016-01-27 15:15 ` Eric Dumazet
2016-01-27 18:12 ` Hannes Frederic Sowa
2016-02-01 13:12 ` Hans Westgaard Ry
2016-01-27 20:13 ` David Miller
2016-02-03 8:26 ` [PATCH v3] net:Add sysctl_max_skb_frags Hans Westgaard Ry
2016-02-03 11:25 ` Herbert Xu
2016-02-03 11:36 ` Hannes Frederic Sowa
2016-02-03 12:20 ` Herbert Xu
2016-02-03 14:03 ` Hannes Frederic Sowa
2016-02-03 14:30 ` Eric Dumazet
2016-02-03 17:36 ` David Laight
2016-02-03 15:58 ` Alexander Duyck
2016-02-03 16:07 ` Eric Dumazet
2016-02-03 17:43 ` Alexander Duyck
2016-02-03 17:54 ` Eric Dumazet
2016-02-03 18:24 ` Alexander Duyck
2016-02-03 19:23 ` Eric Dumazet
2016-02-03 21:03 ` Alexander Duyck
2016-02-09 9:30 ` David Miller
2016-01-06 14:05 ` [PATCH] net: add per device sg_max_frags for skb Eric Dumazet
2016-01-08 10:01 ` Hans Westgaard Ry
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=568F87AC.60405@oracle.com \
--to=hans.westgaard.ry@oracle.com \
--cc=David.Laight@ACULAB.COM \
--cc=ast@plumgrid.com \
--cc=daniel@iogearbox.net \
--cc=davem@davemloft.net \
--cc=ebiederm@xmission.com \
--cc=edjee@google.com \
--cc=edumazet@google.com \
--cc=haakon.bugge@oracle.com \
--cc=hannes@stressinduktion.org \
--cc=ja@ssi.bg \
--cc=jarod@redhat.com \
--cc=jiri@mellanox.com \
--cc=jmorris@namei.org \
--cc=julia.lawall@lip6.fr \
--cc=kaber@trash.net \
--cc=knut.omang@oracle.com \
--cc=kraig@google.com \
--cc=kuznet@ms2.inr.ac.ru \
--cc=linux-kernel@vger.kernel.org \
--cc=makita.toshiaki@lab.ntt.co.jp \
--cc=mgorman@techsingularity.net \
--cc=netdev@vger.kernel.org \
--cc=nicolas.dichtel@6wind.com \
--cc=noureddine@arista.com \
--cc=santosh.shilimkar@oracle.com \
--cc=wei.lin.guay@oracle.com \
--cc=ying.xue@windriver.com \
--cc=yoshfuji@linux-ipv6.org \
--cc=yuval.shaia@oracle.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;
as well as URLs for NNTP newsgroup(s).