netdev
[Top] [All Lists]

Re: [PATCH] "lockless loopback" patch for 2.6.6

To: Arthur Kepner <akepner@xxxxxxx>
Subject: Re: [PATCH] "lockless loopback" patch for 2.6.6
From: Andi Kleen <ak@xxxxxxx>
Date: Sat, 22 May 2004 14:20:55 +0200
Cc: netdev@xxxxxxxxxxx
In-reply-to: <Pine.SGI.4.56.0405211356440.8333289@xxxxxxxxxxxxxxxxxxx>
References: <Pine.SGI.4.56.0405111251080.7038576@xxxxxxxxxxxxxxxxxxx> <20040512120810.464aaee6.davem@xxxxxxxxxx> <Pine.SGI.4.56.0405121256510.7328714@xxxxxxxxxxxxxxxxxxx> <Pine.SGI.4.56.0405211356440.8333289@xxxxxxxxxxxxxxxxxxx>
Sender: netdev-bounce@xxxxxxxxxxx
On Fri, May 21, 2004 at 02:04:09PM -0700, Arthur Kepner wrote:
> 
> Lock contention on the loopback device can lead to poor
> performance, even an essentially hung system, on systems
> with many processors.
> 
> For the loopback device, the only purpose that locking serves
> is to protect the device statistics. The attached patch
> keeps per-cpu statistics for the loopback device and removes
> all locking. The patch is against 2.6.6.

[...]

It looks quite ugly. How about you just create multiple loopback devices
and use these preferably from specific CPUs ? 

One loopback device per CPU would be probably overkill, but maybe one
per 8 CPUs.

-Andi

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