quick question on numa

Discussions on more advanced topics such as monolithic vs micro-kernels, transactional memory models, and paging vs segmentation should go here. Use this forum to expand and improve the wiki!
Post Reply
cxzuk
Member
Member
Posts: 164
Joined: Mon Dec 21, 2009 6:03 pm

quick question on numa

Post by cxzuk »

hi all,

just a quick question. when dealing with ram in numa domains, how are they addressed in the cpu?

does a cpu have access to all ram in the normal access process, or do i only get to see a small portion of the total ram and talk to other cpus for access to other areas? or are both possible?

Merry Christmas
Top
User avatar
Brendan
Member
Member
Posts: 8561
Joined: Sat Jan 15, 2005 12:00 am
Location: At his keyboard!
Contact:
Contact Brendan

Re: quick question on numa

Post by Brendan »

Hi,
cxzuk wrote:just a quick question. when dealing with ram in numa domains, how are they addressed in the cpu?

does a cpu have access to all ram in the normal access process, or do i only get to see a small portion of the total ram and talk to other cpus for access to other areas? or are both possible?
For all 80x86 machines (and cache coherent NUMA in general), all CPUs can access all RAM. In this case supporting NUMA is a performance optimisation (and an OS could do no optimisation for NUMA at all and treat it as plain SMP and still access everything, just with some extra performance penalties).


Cheers,

Brendan
For all things; perfection is, and will always remain, impossible to achieve in practice. However; by striving for perfection we create things that are as perfect as practically possible. Let the pursuit of perfection be our guide.
Top
Post Reply

Return to “OS Design & Theory”