netdev.vger.kernel.org archive mirror
 help / color / mirror / Atom feed
From: Ben Hutchings <bhutchings@solarflare.com>
To: Tom Herbert <therbert@google.com>
Cc: Zhi Yong Wu <zwu.kernel@gmail.com>,
	Stefan Hajnoczi <stefanha@redhat.com>,
	Linux Netdev List <netdev@vger.kernel.org>,
	Eric Dumazet <edumazet@google.com>,
	"David S. Miller" <davem@davemloft.net>,
	Zhi Yong Wu <wuzhy@linux.vnet.ibm.com>
Subject: Re: [RFC PATCH net-next 3/3] virtio-net: Add accelerated RFS support
Date: Sat, 18 Jan 2014 14:19:30 +0000	[thread overview]
Message-ID: <1390054770.16433.20.camel@deadeye.wl.decadent.org.uk> (raw)
In-Reply-To: <CA+mtBx8eRuWpYkYoPbuCaO1h0Y+g96zJB96zP17ZixOwZ1_gmQ@mail.gmail.com>

On Fri, 2014-01-17 at 20:59 -0800, Tom Herbert wrote:
> Ben,
> 
> I've never quite understood why flow management in aRFS has to be done
> with separate messages, and if I recall this seems to mitigate
> performance gains to a large extent. It seems like we should be able
> to piggyback on a TX descriptor for a connection information about the
> RX side for that connection, namely the rxhash and queue mapping.
> State creation should be implicit by just seeing a new rxhash value,
> tear down might be accomplished with a separate flag on the final TX
> packet on the connection (this would need some additional logic in the
> stack). Is this method not feasible in either NICs or virtio-net?

Well that's roughly how Flow Director works, isn't it?  So it is
feasible on at least one NIC!  It might be possible to implement
something like that in firmware on the SFC9100 (with the filter based on
the following packet headers, not a hash), but I don't know.  As for
other vendors - I have no idea.

Inserting filters from the receive path seemed like a natural extension
of the software RFS implementation.  And it means that the hardware
filters are inserted a little earlier (no need to transmit another
packet), but maybe that doesn't matter much.

Ben.

-- 
Ben Hutchings, Staff Engineer, Solarflare
Not speaking for my employer; that's the marketing department's job.
They asked us to note that Solarflare product names are trademarked.

  reply	other threads:[~2014-01-18 14:19 UTC|newest]

Thread overview: 32+ messages / expand[flat|nested]  mbox.gz  Atom feed  top
2014-01-15 14:20 [RFC PATCH net-next 0/3] virtio_net: add aRFS support Zhi Yong Wu
2014-01-15 14:20 ` [RFC PATCH net-next 1/3] virtio_pci: Introduce one new config api vp_get_vq_irq() Zhi Yong Wu
2014-01-15 14:20 ` [RFC PATCH net-next 2/3] virtio_net: Introduce one dummy function virtnet_filter_rfs() Zhi Yong Wu
2014-01-15 17:54   ` Tom Herbert
2014-01-16  2:45     ` Zhi Yong Wu
2014-01-15 14:20 ` [RFC PATCH net-next 3/3] virtio-net: Add accelerated RFS support Zhi Yong Wu
2014-01-16 21:31   ` Ben Hutchings
2014-01-16 22:00     ` Zhi Yong Wu
2014-01-16 23:16       ` Ben Hutchings
2014-01-17 16:54         ` Zhi Yong Wu
2014-01-17 17:20           ` Ben Hutchings
2014-01-18  4:59             ` Tom Herbert
2014-01-18 14:19               ` Ben Hutchings [this message]
2014-01-16  4:23 ` [RFC PATCH net-next 0/3] virtio_net: add aRFS support Jason Wang
2014-01-16  8:34   ` Fwd: " Zhi Yong Wu
2014-01-16  8:52     ` Stefan Hajnoczi
2014-01-16 17:12       ` Tom Herbert
2014-01-17  3:26         ` Jason Wang
2014-01-17  5:08           ` Tom Herbert
2014-01-17  6:36             ` Jason Wang
2014-01-17 16:03               ` Tom Herbert
2014-01-17  5:22         ` Stefan Hajnoczi
2014-01-17  6:45           ` Jason Wang
2014-01-20 14:36           ` Ben Hutchings
2014-01-22 13:27         ` Zhi Yong Wu
2014-01-22 18:00           ` Tom Herbert
2014-01-23  0:40             ` Zhi Yong Wu
2014-01-23 14:23             ` Michael S. Tsirkin
2014-01-17  3:04       ` Jason Wang
2014-01-20 16:49         ` Stefan Hajnoczi
2014-01-16  8:48   ` Zhi Yong Wu
2014-01-23 14:26     ` Michael S. Tsirkin

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=1390054770.16433.20.camel@deadeye.wl.decadent.org.uk \
    --to=bhutchings@solarflare.com \
    --cc=davem@davemloft.net \
    --cc=edumazet@google.com \
    --cc=netdev@vger.kernel.org \
    --cc=stefanha@redhat.com \
    --cc=therbert@google.com \
    --cc=wuzhy@linux.vnet.ibm.com \
    --cc=zwu.kernel@gmail.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).