netdev
[Top] [All Lists]

Re: Info: NAPI performance at "low" loads

To: "Eric W. Biederman" <ebiederm@xxxxxxxxxxxx>
Subject: Re: Info: NAPI performance at "low" loads
From: Alan Cox <alan@xxxxxxxxxxxxxxxxxxx>
Date: 19 Sep 2002 16:53:02 +0100
Cc: "David S. Miller" <davem@xxxxxxxxxx>, hadi@xxxxxxxxxx, akpm@xxxxxxxxx, manfred@xxxxxxxxxxxxxxxx, netdev@xxxxxxxxxxx, linux-kernel@xxxxxxxxxxxxxxx
In-reply-to: <m18z1ykoms.fsf@frodo.biederman.org>
References: <1032381789.20498.151.camel@irongate.swansea.linux.org.uk> <20020918.134630.127509858.davem@redhat.com> <1032383727.20463.155.camel@irongate.swansea.linux.org.uk> <20020918.142250.130847722.davem@redhat.com> <m18z1ykoms.fsf@frodo.biederman.org>
Sender: netdev-bounce@xxxxxxxxxxx
On Thu, 2002-09-19 at 16:03, Eric W. Biederman wrote:
> If I do an inb to a PCI-X device running at 133Mhz it should come back
> much faster than an inb from my serial port on the ISA port.  What
> is the reason for the fixed minimum timing?

As far as I can tell the minimum time for the inb/outb is simply the
time it takes the bus to respond. The only difference there is that for
writel rather than outl you won't wait for the write to complete on the
PCI bus just dump it into the fifo if its empty


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