lkml.org 
[lkml]   [1999]   [May]   [27]   [last100]   RSS Feed
Views: [wrap][no wrap]   [headers]  [forward] 
 
Messages in this thread
/
Date
From
SubjectRe: andrea buffer code (2.2.9-C.gz)
On 23 May 1999, Stefan Monnier wrote:

> >>>>> "Andrea" == Andrea Arcangeli <andrea@suse.de> writes:
> > Impacting runtime performances to SMP scale better, is going to lose
> > according to me. I think that if you want to SMP scale better it worth to
> > pay _only_ with memory wastage and _not_ with wasted CPU cycles.
>
> The rule generally goes in the other directions for fairly obvious reasons:
> the amount of memory-resources per CPU is usually lower on an SMP so you
> want to save memory more than you want to save CPU.

Hmm, I probably have NO clue what I'm talking about, but it would seem
to me that in general, SMP machines have more memory than uni-processor
machines because in general they play a different role. A uni-processor machine
is going to have 32M or 64M probably, whereas a dual-proc machine is going
to have 128M+ most likely. Why? Because if you're going dual-proc there is
usually a reason, perhaps it's for a server, or a high-end workstation or
something, but there is usually a reason, and that reason usually follows that
the machine will have more memory.
Also, memory is (relatively) inexpensive compared to processors.
Which also makes me think that dual processor machines are going to have more
memory than uni-processor machines.
How much memory are we talking here, anyway? And how many processor
cycles? :)

Stephen


-
To unsubscribe from this list: send the line "unsubscribe linux-kernel" in
the body of a message to majordomo@vger.rutgers.edu
Please read the FAQ at http://www.tux.org/lkml/

\
 
 \ /
  Last update: 2005-03-22 13:51    [W:0.036 / U:0.028 seconds]
©2003-2020 Jasper Spaans|hosted at Digital Ocean and TransIP|Read the blog|Advertise on this site