From: Stephen Hemminger <shemminger@osdl.org>
To: "Michael S. Tsirkin" <mst@mellanox.co.il>
Cc: Linux Kernel Mailing List <linux-kernel@vger.kernel.org>,
netdev@vger.kernel.org, openib-general@openib.org,
Roland Dreier <rolandd@cisco.com>
Subject: Re: Dropping NETIF_F_SG since no checksum feature.
Date: Tue, 10 Oct 2006 10:43:15 -0700 [thread overview]
Message-ID: <20061010104315.61540986@freekitty> (raw)
In-Reply-To: <20061010144330.GA28175@mellanox.co.il>
On Tue, 10 Oct 2006 16:43:30 +0200
"Michael S. Tsirkin" <mst@mellanox.co.il> wrote:
> Quoting r. Stephen Hemminger <shemminger@osdl.org>:
> > Subject: Re: Dropping NETIF_F_SG since no checksum feature.
> >
> > On Mon, 9 Oct 2006 19:47:05 +0200
> > "Michael S. Tsirkin" <mst@mellanox.co.il> wrote:
> >
> > > Hi!
> > > I'm trying to build a network device driver supporting a very large MTU (around 64K)
> > > on top of an infiniband connection, and I've hit a couple of issues I'd
> > > appreciate some feedback on:
> > >
> > > 1. On the send side,
> > > I've set NETIF_F_SG, but hardware does not support checksum offloading,
> > > and I see "dropping NETIF_F_SG since no checksum feature" warning,
> > > and I seem to be getting large packets all in one chunk.
> > > The reason I've set NETIF_F_SG, is because I'm concerned that under real life
> > > stress Linux won't be able to allocate 64K of continuous memory.
> > >
> > > Is this concern of mine valid? I saw in-tree drivers allocating at least 8K.
> > > What's the best way to enable S/G on send side?
> > > Is checksum offloading really required for S/G?
> >
> > Yes, in the current implementation, Linux needs checksum offload. But there
> > is no reason, your driver can't compute the checksum in software.
>
> Are there drivers that do this already? Couldn't find any such beast ...
dev_queue_xmit() does it, all you need to do in your driver is:
/* If packet is not checksummed and device does not support
* checksumming for this protocol, complete checksumming here.
*/
if (skb->ip_summed == CHECKSUM_PARTIAL) {
if (skb_checksum_help(skb))
goto error_recovery
}
> I'm worried whether an extra pass over data won't eat up all of
> the performance gains I get from the large MTU ...
Yup, the cost is in touching the data, not in the copy.
> > > What are the helpers legal for fragmented skb?
>
> BTW, I found skb_put_frags in sky2 which seems generic enough - I even wander
> why isn't this in net/core.
>
Only because I just wrote it for my needs. If you need it, then it
can be moved to skbuff.c
--
Stephen Hemminger <shemminger@osdl.org>
next prev parent reply other threads:[~2006-10-10 17:46 UTC|newest]
Thread overview: 54+ messages / expand[flat|nested] mbox.gz Atom feed top
2006-10-09 17:47 Dropping NETIF_F_SG since no checksum feature Michael S. Tsirkin
2006-10-09 16:50 ` Stephen Hemminger
2006-10-09 16:50 ` Stephen Hemminger
2006-10-10 14:43 ` Michael S. Tsirkin
2006-10-10 17:43 ` Stephen Hemminger [this message]
2006-10-11 0:13 ` Michael S. Tsirkin
2006-10-11 0:15 ` Roland Dreier
2006-10-11 0:26 ` Michael S. Tsirkin
2006-10-11 3:33 ` Roland Dreier
2006-10-11 3:36 ` David Miller
2006-10-11 3:42 ` Roland Dreier
2006-10-11 3:45 ` David Miller
2006-10-11 3:49 ` Roland Dreier
2006-10-11 3:50 ` David Miller
2006-10-11 2:15 ` David Miller
2006-10-11 9:05 ` Michael S. Tsirkin
2006-10-11 9:05 ` Michael S. Tsirkin
2006-10-11 9:09 ` Steven Whitehouse
2006-10-11 15:01 ` Michael S. Tsirkin
2006-10-11 20:11 ` Steven Whitehouse
2006-10-11 20:52 ` Michael S. Tsirkin
2006-10-11 20:57 ` Stephen Hemminger
2006-10-11 21:23 ` Michael S. Tsirkin
2006-10-11 21:23 ` Michael S. Tsirkin
2006-10-11 21:29 ` Stephen Hemminger
2006-10-11 21:42 ` Michael S. Tsirkin
2006-10-11 21:41 ` David Miller
2006-10-12 19:12 ` Michael S. Tsirkin
2006-10-12 19:12 ` Michael S. Tsirkin
2006-10-13 4:22 ` David Miller
2006-10-13 6:17 ` Michael S. Tsirkin
2006-10-11 20:52 ` David Miller
2006-10-11 20:52 ` David Miller
2006-10-11 21:11 ` Michael S. Tsirkin
2006-10-11 21:11 ` Michael S. Tsirkin
2006-10-11 9:20 ` David Miller
2006-10-11 9:46 ` Michael S. Tsirkin
2006-10-11 18:21 ` [openib-general] " Michael Krause
2006-10-11 13:11 ` [RFC] Question about potential problem in net/ipv4/route.c Eric Dumazet
2006-10-12 5:05 ` David Miller
2006-10-12 5:31 ` Patrick McHardy
2006-10-12 5:54 ` David Miller
2006-10-12 5:48 ` Eric Dumazet
2006-10-12 6:02 ` David Miller
2006-10-12 6:10 ` Patrick McHardy
2006-10-12 6:25 ` David Miller
2006-10-12 6:35 ` Eric Dumazet
2006-10-12 7:48 ` David Miller
2006-10-16 9:00 ` [PATCH] NET : Suspicious locking in reqsk_queue_hash_req() Eric Dumazet
2006-10-16 9:07 ` Eric Dumazet
2006-10-16 16:16 ` Arnaldo Carvalho de Melo
2006-10-16 16:56 ` Eric Dumazet
2006-10-16 17:39 ` Eric Dumazet
2006-10-16 20:41 ` 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=20061010104315.61540986@freekitty \
--to=shemminger@osdl.org \
--cc=linux-kernel@vger.kernel.org \
--cc=mst@mellanox.co.il \
--cc=netdev@vger.kernel.org \
--cc=openib-general@openib.org \
--cc=rolandd@cisco.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 an external index of several public inboxes,
see mirroring instructions on how to clone and mirror
all data and code used by this external index.