netdev - RE: [PATCH 2.6.25 2/4]S2io: Multiqueue network device support

lists.openwall.net		lists / announce owl-users owl-dev john-users john-dev passwdqc-users yescrypt popa3d-users / oss-security kernel-hardening musl sabotage tlsify passwords / crypt-dev xvendor / Bugtraq Full-Disclosure linux-kernel linux-netdev linux-ext4 linux-hardening linux-cve-announce PHC
Open Source and information security mailing list archives

Hash Suite for Android: free password hash cracker in your pocket

[<prev] [next>] [<thread-prev] [thread-next>] [day] [month] [year] [list]

Date:	Wed, 20 Feb 2008 18:49:41 -0500
From:	"Ramkrishna Vepa" <Ramkrishna.Vepa@...erion.com>
To:	"Patrick McHardy" <kaber@...sh.net>,
	"David Miller" <davem@...emloft.net>
Cc:	"Sreenivasa Honnur" <Sreenivasa.Honnur@...erion.com>,
	<netdev@...r.kernel.org>, <jeff@...zik.org>,
	"support" <support@...erion.com>
Subject: RE: [PATCH 2.6.25 2/4]S2io: Multiqueue network device support - FIFO selection based on L4 ports

> From: Patrick McHardy [mailto:kaber@...sh.net]
> Sent: Wednesday, February 20, 2008 3:22 PM
> To: David Miller
> Cc: Ramkrishna Vepa; Sreenivasa Honnur; netdev@...r.kernel.org;
> jeff@...zik.org; support
> Subject: Re: [PATCH 2.6.25 2/4]S2io: Multiqueue network device support
-
> FIFO selection based on L4 ports
> 
> David Miller wrote:
> > From: Patrick McHardy <kaber@...sh.net>
> > Date: Thu, 21 Feb 2008 00:15:13 +0100
> >
> >
> >> I missed those discussions, but this has already been agreed on,
> >> fine by me. It would still be preferable to use queue_mapping
> >> instead of priority IMO, even if its activated by a module
> >> parameter, since that leaves the option to use classifiers.
> >>
> >
> > I think the driver should compute the value in it's transmit
> > routine and keep the value local.  It shouldn't be setting
> > skb->foo values at all, they don't belong to the driver
> > and this could confuse other code.
> >
> 
> Yes, I didn't meant it should set anything, but on of the options
> this patch introduces is to _use_ skb->priority for classification,
> so the classification is already external, in which case it might
> as well offer the full flexibility (as one option) to use qdisc
> classifiers.
[Ram] Yes, this should be possible. We can add an additional option to
use qdisc classifiers and submit it as a patch later on.

Ram
--
To unsubscribe from this list: send the line "unsubscribe netdev" in
the body of a message to majordomo@...r.kernel.org
More majordomo info at  http://vger.kernel.org/majordomo-info.html