From: Eric Dumazet <eric.dumazet@gmail.com>
To: Eliezer Tamir <eliezer.tamir@linux.intel.com>
Cc: Shawn Bohrer <sbohrer@rgmadvisors.com>,
davem@davemloft.net, netdev@vger.kernel.org,
Amir Vadai <amirv@mellanox.com>,
tomk@rgmadvisors.com
Subject: Re: [PATCH v2 net-next] net: Add low-latency/polling support for UDP multicast
Date: Thu, 08 Aug 2013 16:55:14 -0700 [thread overview]
Message-ID: <1376006114.4004.141.camel@edumazet-glaptop> (raw)
In-Reply-To: <52035AD9.30703@linux.intel.com>
On Thu, 2013-08-08 at 11:46 +0300, Eliezer Tamir wrote:
> On 07/08/2013 23:22, Eric Dumazet wrote:
> > On Tue, 2013-08-06 at 14:51 -0500, Shawn Bohrer wrote:
> >> Set the napi id for each socket in the multicast path to enable
> >> low-latency/polling support.
> >>
> >> Signed-off-by: Shawn Bohrer <sbohrer@rgmadvisors.com>
> >> ---
> >> v2 include ipv6 support
> >
> > This might help your workload, but I doubt it is generic enough.
> >
> > One UDP socket is supposed to receive traffic from many endpoints,
> > so we have no guarantee all the received traffic will end on a single RX
> > queue on the NIC.
> >
> > That's the same logic than RFS here.
> >
> > sk_mark_napi_id() in UDP are wrong IMHO.
> >
> > It should be guarded by the following test in
> > __udp_queue_rcv_skb()
> >
> > if (inet_sk(sk)->inet_daddr) {
> > sock_rps_save_rxhash(sk, skb);
> > sk_mark_napi_id(sk, skb);
> > }
> >
> > (To occur only for connected UDP sockets, where we are 100% sure all
> > packets will use this same rxhash/rx queue)
>
> This would also be safe if there is only one NIC and said NIC was
> programmed to always place this socket's data on the same queue.
>
> I don't have a good suggestion on how to detect this.
Well, this stuff relies on flows being correctly steered.
TCP stack performs much better if we avoid reorders ;)
next prev parent reply other threads:[~2013-08-08 23:55 UTC|newest]
Thread overview: 17+ messages / expand[flat|nested] mbox.gz Atom feed top
2013-08-05 21:22 low latency/busy poll feedback and bugs Shawn Bohrer
2013-08-05 22:16 ` [PATCH net-next] net: Add low-latency/polling support for UDP multicast Shawn Bohrer
2013-08-06 7:13 ` Eliezer Tamir
2013-08-06 19:51 ` [PATCH v2 " Shawn Bohrer
2013-08-07 20:22 ` Eric Dumazet
2013-08-08 8:46 ` Eliezer Tamir
2013-08-08 23:55 ` Eric Dumazet [this message]
2013-08-11 7:59 ` Eliezer Tamir
2013-08-06 7:41 ` low latency/busy poll feedback and bugs Eliezer Tamir
2013-08-06 18:08 ` Shawn Bohrer
2013-08-06 18:25 ` Eliezer Tamir
2013-08-07 20:05 ` Ben Hutchings
2013-08-07 20:23 ` Eric Dumazet
2013-08-07 23:41 ` David Miller
2013-08-06 20:39 ` Or Gerlitz
2013-08-06 21:02 ` Eric Dumazet
2013-08-06 12:15 ` Amir Vadai
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=1376006114.4004.141.camel@edumazet-glaptop \
--to=eric.dumazet@gmail.com \
--cc=amirv@mellanox.com \
--cc=davem@davemloft.net \
--cc=eliezer.tamir@linux.intel.com \
--cc=netdev@vger.kernel.org \
--cc=sbohrer@rgmadvisors.com \
--cc=tomk@rgmadvisors.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).