From: David Miller <davem@davemloft.net>
To: eric.dumazet@gmail.com
Cc: kaber@trash.net, herbert@gondor.apana.org.au, hkchu@google.com,
mwdalton@google.com, netdev@vger.kernel.org
Subject: Re: [RFC] csum experts, csum_replace2() is too expensive
Date: Fri, 21 Mar 2014 14:07:30 -0400 (EDT) [thread overview]
Message-ID: <20140321.140730.1007660405690890605.davem@davemloft.net> (raw)
In-Reply-To: <1395341341.9114.93.camel@edumazet-glaptop2.roam.corp.google.com>
From: Eric Dumazet <eric.dumazet@gmail.com>
Date: Thu, 20 Mar 2014 11:49:01 -0700
> csum_replace2() uses about 29 cycles, while a plain ip_send_check() is
> way faster (16 cycles)
>
> csum_partial() is not really meant for doing checksums over 8 bytes !
>
> Any idea how to make the thing really fast as intended ?
>
> I saw csum_partial() consuming 1% of cpu cycles in a GRO workload, that
> is insane...
>
> Following patch might be the fastest thing ?
>
> (At this point we already have validated IP checksum)
...
> @@ -1434,8 +1434,8 @@ static int inet_gro_complete(struct sk_buff *skb, int nhoff)
> int proto = iph->protocol;
> int err = -ENOSYS;
>
> - csum_replace2(&iph->check, iph->tot_len, newlen);
> iph->tot_len = newlen;
> + ip_send_check(&iph);
Yeah the csum_replace*() are extremely suboptimal.
We should be able to cons up something cheap like the trick that
ip_decrease_ttl() uses.
https://tools.ietf.org/html/rfc1624
https://tools.ietf.org/html/rfc1141
next prev parent reply other threads:[~2014-03-21 18:07 UTC|newest]
Thread overview: 26+ messages / expand[flat|nested] mbox.gz Atom feed top
2014-03-20 18:49 [RFC] csum experts, csum_replace2() is too expensive Eric Dumazet
2014-03-21 0:13 ` Herbert Xu
2014-03-21 0:54 ` Eric Dumazet
2014-03-21 12:50 ` Herbert Xu
2014-03-21 1:56 ` Andi Kleen
2014-03-21 2:51 ` Eric Dumazet
2014-03-21 12:50 ` Eric Dumazet
2014-03-21 13:28 ` Andi Kleen
2014-03-21 13:32 ` Eric Dumazet
2014-03-21 13:47 ` Eric Dumazet
2014-03-21 13:56 ` Eric Dumazet
2014-03-21 14:14 ` David Laight
2014-03-21 18:52 ` David Miller
2014-03-24 2:50 ` Eric Dumazet
2014-03-24 10:30 ` David Laight
2014-03-24 13:17 ` Eric Dumazet
2014-03-24 14:13 ` Eric Dumazet
2014-03-21 18:07 ` David Miller [this message]
2014-03-21 18:30 ` Eric Dumazet
2014-03-24 2:51 ` [PATCH net-next] net: optimize csum_replace2() Eric Dumazet
2014-03-24 4:20 ` David Miller
2014-03-24 10:22 ` David Laight
2014-03-24 13:25 ` Eric Dumazet
2014-03-24 14:38 ` David Laight
2014-03-24 15:14 ` Eric Dumazet
2014-03-24 15:52 ` David Laight
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=20140321.140730.1007660405690890605.davem@davemloft.net \
--to=davem@davemloft.net \
--cc=eric.dumazet@gmail.com \
--cc=herbert@gondor.apana.org.au \
--cc=hkchu@google.com \
--cc=kaber@trash.net \
--cc=mwdalton@google.com \
--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).