netdev
[Top] [All Lists]

Re: [announce] [patch] limiting IRQ load, irq-rewrite-2.4.11-B5

To: kuznet@xxxxxxxxxxxxx
Subject: Re: [announce] [patch] limiting IRQ load, irq-rewrite-2.4.11-B5
From: Benjamin LaHaise <bcrl@xxxxxxxxxx>
Date: Wed, 3 Oct 2001 15:03:55 -0400
Cc: mingo@xxxxxxx, hadi@xxxxxxxxxx, linux-kernel@xxxxxxxxxxxxxxx, Robert.Olsson@xxxxxxxxxxx, netdev@xxxxxxxxxxx, torvalds@xxxxxxxxxxxxx, alan@xxxxxxxxxxxxxxxxxxx
In-reply-to: <200110031653.UAA13938@xxxxxxxxxxxxx>; from kuznet@xxxxxxxxxxxxx on Wed, Oct 03, 2001 at 08:53:58PM +0400
References: <Pine.LNX.4.33.0110031702280.7221-100000@xxxxxxxxxxxxxxxxxxxxx> <200110031653.UAA13938@xxxxxxxxxxxxx>
Sender: owner-netdev@xxxxxxxxxxx
User-agent: Mutt/1.2.5i
On Wed, Oct 03, 2001 at 08:53:58PM +0400, kuznet@xxxxxxxxxxxxx wrote:
> Citing my old explanation:
> 
> >"Polling" is not a real polling in fact, it just accepts irqs as
> >events waking rx softirq with blocking subsequent irqs.
> >Actual receive happens at softirq.
> >
> >Seems, this approach solves the worst half of livelock problem completely:
> >irqs are throttled and tuned to load automatically.
> >Well, and drivers become cleaner.

Well, this sounds like a 2.5 patch.  When do we get to merge it?

                -ben

<Prev in Thread] Current Thread [Next in Thread>