[<prev] [next>] [<thread-prev] [thread-next>] [day] [month] [year] [list]
Message-ID: <20081022170517.051d766f@extreme>
Date: Wed, 22 Oct 2008 17:05:17 -0700
From: Stephen Hemminger <shemminger@...tta.com>
To: Rick Jones <rick.jones2@...com>
Cc: Eric Dumazet <dada1@...mosbay.com>,
David Miller <davem@...emloft.net>, jgarzik@...ox.com,
netdev@...r.kernel.org
Subject: Re: [PATCH] sky2: skb recycling
On Wed, 22 Oct 2008 16:58:17 -0700
Rick Jones <rick.jones2@...com> wrote:
> Stephen Hemminger wrote:
> > On Tue, 21 Oct 2008 22:15:43 +0200
> > Eric Dumazet <dada1@...mosbay.com> wrote:
> >
> >
> >>Rick Jones a écrit :
> >>> I've not had a good emily litella moment all day so I'll ask - is
> >>> there really that much in the way of suitable skb's which are
> >>> completely free after transmit completion?
> >>
> >> Or, if we take another way, say a VOIP RTP machine sends and
> >> receive 20.000 packets per second, each being 200 bytes long, are
> >> transmited packets correctly sized at sendto() time to be
> >> candidates for recycling ?
> >
> > No. Most locally generate packets aren't going to be right size
> > because they will be too small, cloned or fragmented. It really only
> > helps when forwarding.
>
> So we have a bit of "tension" between the desires of an end host vs
> those of a router right?
>
> rick jones
Not tension, just means on end host this optimization does nothing.
--
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
Powered by blists - more mailing lists