netdev
[Top] [All Lists]

Re: [RFC] TCP congestion schedulers

To: John Heffner <jheffner@xxxxxxx>
Subject: Re: [RFC] TCP congestion schedulers
From: "David S. Miller" <davem@xxxxxxxxxxxxx>
Date: Tue, 29 Mar 2005 12:03:06 -0800
Cc: netdev@xxxxxxxxxxx, shemminger@xxxxxxxx, ak@xxxxxx, baruch@xxxxxxxxx
In-reply-to: <Pine.LNX.4.58.0503291422100.3256@xxxxxxxxxxxxxx>
References: <421D30FA.1060900@xxxxxxxxx> <20050225120814.5fa77b13@xxxxxxxxxxxxxxxxx> <20050309210442.3e9786a6.davem@xxxxxxxxxxxxx> <4230288F.1030202@xxxxxxxxx> <20050310182629.1eab09ec.davem@xxxxxxxxxxxxx> <20050311120054.4bbf675a@xxxxxxxxxxxxxxxxx> <20050311201011.360c00da.davem@xxxxxxxxxxxxx> <20050314151726.532af90d@xxxxxxxxxxxxxxxxx> <m13bur5qyo.fsf@xxxxxx> <Pine.LNX.4.58.0503211605300.6729@xxxxxxxxxxxxxx> <20050322074122.GA64595@xxxxxx> <Pine.LNX.4.58.0503291422100.3256@xxxxxxxxxxxxxx>
Sender: netdev-bounce@xxxxxxxxxxx
On Tue, 29 Mar 2005 14:32:33 -0500 (EST)
John Heffner <jheffner@xxxxxxx> wrote:

> The motivation for my question is that I get very unpredictable
> performance over loopback with UP for all architectures, often varying by
> more than a factor of two.  I haven't really tried to track down the
> cause, but an important characteristic seems to be that the greater the
> differential between the CPU utilization of the sender and the receiver,
> the slower the throughput.  (But I'm not sure if there's a causal relation
> here.)  Maybe this is simply scheduler strangeness, since it doesn't seem
> to be an issue that I've noticed on SMP.  Has anyone seen this or know
> offhand what's going on?

It could be L2 cache-coloring effects as well.  Try to keep the working
set size smaller than the L2 cache size of the cpu you are on.

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