netdev
[Top] [All Lists]

Re: Route cache performance under stress

To: "David S. Miller" <davem@xxxxxxxxxx>
Subject: Re: Route cache performance under stress
From: Andi Kleen <ak@xxxxxxx>
Date: Wed, 11 Jun 2003 09:28:32 +0200
Cc: ralph+d@xxxxxxxxx, ralph@xxxxxxxxx, greearb@xxxxxxxxxxxxxxx, Robert.Olsson@xxxxxxxxxxx, hadi@xxxxxxxxxxxxxxxx, xerox@xxxxxxxxxx, sim@xxxxxxxxxxxxx, fw@xxxxxxxxxxxxx, netdev@xxxxxxxxxxx, linux-net@xxxxxxxxxxxxxxx
In-reply-to: <20030610.182338.41657455.davem@xxxxxxxxxx>
References: <3EE67D2D.80608@xxxxxxxxxxxxxxx> <20030610.180120.71112140.davem@xxxxxxxxxx> <Pine.LNX.4.51.0306102115210.18076@xxxxxxxxxxxx> <20030610.182338.41657455.davem@xxxxxxxxxx>
Sender: netdev-bounce@xxxxxxxxxxx
On Tue, Jun 10, 2003 at 06:23:38PM -0700, David S. Miller wrote:
>    From: Ralph Doncaster <ralph@xxxxxxxxx>
>    Date: Tue, 10 Jun 2003 21:17:28 -0400 (EDT)
> 
>    Aren't the read_lock_irqsave and restore expensive?
> 
> If x86 has an inefficient implementation, well... :-)

sti/cli is normally fast on x86, a bit slower on P3 core (a few cycles or so)
read_lock_irqsave does a pushfl though, that's rather slow on P4,
but still not that bad. read_lock_irq would be faster, but too risky 
here.

> 
> This can be done without locks, nobody has done the x86 implementation
> of that that's all.  I think the x86_64 folks did a lockless version,
> I know I did for sparc64 :)

2.5 i386 gettimeofday is lockless. But on UP it should not make any difference
anyways.

-Andi

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