Thanks, that helped a lot. Did a bit of research online and came up with
this article that answered my question:
"There are two types of CPU affinity. The first, soft affinity, also
called natural affinity, is the tendency of a scheduler to try to keep
processes on the same CPU as long as possible. It is merely an attempt;
if it is ever infeasible, the processes certainly will migrate to
another processor. The new O(1) scheduler in 2.5 exhibits excellent
natural affinity. On the opposite end, however, is the 2.4 scheduler,
which has poor CPU affinity. This behavior results in the ping-pong
effect. The scheduler bounces processes between multiple processors each
time they are scheduled and rescheduled. Table 1 is an example of poor
natural affinity; Table 2 shows what good natural affinity looks like.
Hard affinity, on the other hand, is what a CPU affinity system call
provides. It is a requirement, and processes must adhere to a specified
hard affinity. If a processor is bound to CPU zero, for example, then it
can run only on CPU zero."
Carlo
Ian Wienand wrote:
On Mon, Jun 26, 2006 at 01:55:16PM +1000, Carlo Sogono wrote:
I would like to find out how Linux distributes processes in an
SMP-enabled box with n CPUs. Will the kernel "move" a process from one
CPU to another if another CPU is idle?
It may do. Keeping processes close to where they last run is called
CPU affinity, and is obviously better for the cache. See the man
pages for sched_[set|get]affinity for the Linux interface for binding
to CPUs.
On a larger machine you also need to control node locality, for that
you can use libnuma and numactl, which should come with your
distribution.
-i
--
SLUG - Sydney Linux User's Group Mailing List - http://slug.org.au/
Subscription info and FAQs: http://slug.org.au/faq/mailinglists.html
