LVS
lvs-users
Google
 
Web LinuxVirtualServer.org

Re: dual CPU balancer

To: <mike@xxxxxxxxxx>
Subject: Re: dual CPU balancer
Cc: Michael E Brown <michael_e_brown@xxxxxxxxxxxxxxxxx>, <lvs-users@xxxxxxxxxxxxxxxxxxxxxx>
From: Michael E Brown <michael_e_brown@xxxxxxxx>
Date: Tue, 26 Dec 2000 19:13:31 -0600 (CST)
On Tue, 26 Dec 2000 mike@xxxxxxxxxx wrote:

>
> On Tue, 26 Dec 2000, Michael E Brown wrote:
>
> > On Tue, 26 Dec 2000, Horms wrote:
> >
> > > On Tue, Dec 26, 2000 at 10:58:34AM -0800, Florin Andrei wrote:
> > > > Is there any advantage in using a dual-CPU balancer
> > > > over a single-CPU?
> > > >
> > > > (...and i guess this question too is a nice FAQ entry
> > > > ;-) )
> > >
> > > The _theory_ is that under 2.2.x no and uder 2.4.x yes.
> > >
> >
> > Make that _reality_. In some tests I've done with FTP, I have seen
> > *significant* improvements using dual and quad processors using 2.4. Under
> > 2.2, there are improvements, but not astonishing ones.
> >
> > Things like 90% saturation of a Gig link using quad processors, 70% using
> > dual processors and 55% using a single processor under 2.4.0test. Really
> > amazing improvements.
>
> What are the percentage differences on each processor configuration
> between 2.2 and 2.4?  How does a 2.2 system compare to a 2.4 system on the
> same hardware?

I haven't had much of a chance to do a full comparison of 2.2 vs 2.4, but
most of the evidence on tests that I have run points to a > 100%
improvement for *network intensive* tasks.

--
Michael Brown




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