adelorenzo at dinossauro.com
Mon Oct 15 16:30:06 PDT 2001
I haven't noticed any significant degradations to be quite honest on any
other area of the system. One of my intial fears with a low latency patched
kernel was stability, which after a 92 day uptime was over (I had to boot
the machine in order to install a new kernel,patched by the way.... :) ).
I suggest care when implementing a low latency patched kernel and suggest
you go for Anderw Morton's patches. And yes, compiling a kernel can be
achieved in less time with the patch. Finally, unless there you really need
to set up a heavy duty box (databaes, three digit users web server, etc...),
there is no real need to patch your kernel.
Below a very interesting O'Reilly article on the subject with links to the
----- Original Message -----
From: "Gerard Beekmans" <gerard at linuxfromscratch.org>
To: <blfs-support at linuxfromscratch.org>
Sent: Monday, October 15, 2001 8:55 PM
Subject: Re: low latency
> On Mon, Oct 15, 2001 at 07:57:39PM -0300, Adolfo Delorenzo wrote:
> > Yup. Actually I've been patching my 2.4 kernels since 2.4.0
> > A LFS box with a low latency patched kernel can render VERY interesting
> > performance results, specially with databases or I/O intensive apps.
> I'm guessing compiling LFS systems almost all day long falls under I/O
> intensive apps.
> Are there downsides from the low latency patch? It improves I/O handling
> and some other things i've heard on linux kernel list, but it was never
> clear to me if there are performance degradations in other areas.
> And, I can't seem to find the low latency patches. URL please
> Gerard Beekmans
> -*- If Linux doesn't have the solution, you have the wrong problem -*-
> Unsubscribe: send email to listar at linuxfromscratch.org
> and put 'unsubscribe blfs-support' in the subject header of the message
Unsubscribe: send email to listar at linuxfromscratch.org
and put 'unsubscribe blfs-support' in the subject header of the message
More information about the blfs-support