Skip site navigation (1)Skip section navigation (2)
Date:      Fri, 4 Feb 2011 23:07:49 +0100
From:      Michael Tuexen <tuexen@fh-muenster.de>
To:        "Robert N. M. Watson" <rwatson@freebsd.org>
Cc:        svn-src-head@freebsd.org, Randall Stewart <rrs@FreeBSD.org>, svn-src-all@freebsd.org, src-committers@freebsd.org
Subject:   Re: svn commit: r218211 - in head/sys: conf netinet
Message-ID:  <37716196-EE55-4D94-82BB-4DE19AAF34F2@fh-muenster.de>
In-Reply-To: <1F9E5E6D-ADCA-4F43-B04D-54CCBD5AC2A8@freebsd.org>
References:  <201102031005.p13A5Vwi040803@svn.freebsd.org> <alpine.BSF.2.00.1102040639440.18938@fledge.watson.org> <FC0EBA69-26C9-450D-9B18-F2B4461364F7@fh-muenster.de> <1F9E5E6D-ADCA-4F43-B04D-54CCBD5AC2A8@freebsd.org>

next in thread | previous in thread | raw e-mail | index | archive | help
On Feb 4, 2011, at 11:00 PM, Robert N. M. Watson wrote:
>=20
> On 4 Feb 2011, at 13:30, Michael Tuexen wrote:
>=20
>>> Hmm.  It might be better to add a new NETISR_SCTP and use netisr's =
support for multithreading?
>> That sounds really good.
>>=20
>> Is it possible that different network cards put packets in the same =
queue?
>> That would be helpful in the case of SCTP.
>>>=20
>>> (I'm preparing a patch for review that enhances that a bit so that =
protocols can be a bit more expressive in terms of specifying dispatch =
policy, etc, currently).
>> Great!
>=20
> You get a spectrum of possibilities -- protocols can request source =
ordering (i.e., ifnet), flow ordering (in which they expose ordering =
information but not CPU affinity), or a full CPU affinity. How work is =
distributed and what queue it ends up in depends on the model, but yes, =
you can request that interfaces distribute packets to various queues, =
and that multiple interfaces use consistent distribution models. I =
implement this for RSS, where there's a global RSS setup that is =
propagated to supporting device drivers so that they can align their =
distribution with the network stack's affinity model for connection =
groups.
That sounds great. Let us know when the code is ready for testing...

Best regards
Michael
>=20
> Robert
>=20
>=20




Want to link to this message? Use this URL: <https://mail-archive.FreeBSD.org/cgi/mid.cgi?37716196-EE55-4D94-82BB-4DE19AAF34F2>