* Question on build_sched_domains
@ 2006-03-24 2:58 Srivatsa Vaddagiri
2006-03-24 7:12 ` Srivatsa Vaddagiri
0 siblings, 1 reply; 6+ messages in thread
From: Srivatsa Vaddagiri @ 2006-03-24 2:58 UTC (permalink / raw)
To: nickpiggin; +Cc: linux-kernel, Ingo Molnar
Nick,
I was going thr' build_sched_domains and had a question
regarding formation of sched_groups for NUMA nodes. There are two 'for'
loops, each loop possibly allocating memory (sched_group) for one or more nodes.
My question is: in the outer loop, don't we need to skip allocating for
nodes for whom the inner loop has allocated in an earlier pass?
Taking the example of 4 node system which are in the same
sched_domain_node_span(), I see that we end up allocating 16
times (when 4 would have sufficed?).
What am I missing here?
--
Regards,
vatsa
^ permalink raw reply [flat|nested] 6+ messages in thread
* Re: Question on build_sched_domains
2006-03-24 2:58 Question on build_sched_domains Srivatsa Vaddagiri
@ 2006-03-24 7:12 ` Srivatsa Vaddagiri
2006-03-24 7:45 ` Nick Piggin
0 siblings, 1 reply; 6+ messages in thread
From: Srivatsa Vaddagiri @ 2006-03-24 7:12 UTC (permalink / raw)
To: nickpiggin; +Cc: linux-kernel, Ingo Molnar
On Fri, Mar 24, 2006 at 08:28:34AM +0530, Srivatsa Vaddagiri wrote:
> Taking the example of 4 node system which are in the same
> sched_domain_node_span(), I see that we end up allocating 16
> times (when 4 would have sufficed?).
Maybe this is it to avoid touching same memory from different nodes?
--
Regards,
vatsa
^ permalink raw reply [flat|nested] 6+ messages in thread
* Re: Question on build_sched_domains
2006-03-24 7:12 ` Srivatsa Vaddagiri
@ 2006-03-24 7:45 ` Nick Piggin
2006-03-25 8:36 ` Srivatsa Vaddagiri
0 siblings, 1 reply; 6+ messages in thread
From: Nick Piggin @ 2006-03-24 7:45 UTC (permalink / raw)
To: vatsa; +Cc: linux-kernel, Ingo Molnar
Srivatsa Vaddagiri wrote:
> On Fri, Mar 24, 2006 at 08:28:34AM +0530, Srivatsa Vaddagiri wrote:
>
>>Taking the example of 4 node system which are in the same
>>sched_domain_node_span(), I see that we end up allocating 16
>>times (when 4 would have sufficed?).
>
>
> Maybe this is it to avoid touching same memory from different nodes?
>
Yeah I think what's happening is that the sched groups structures
are not shared between nodes. (It's been a while since I looked at
this code, and it is a bit tricky to follow).
Aside, it should be using kmalloc_node now...
--
SUSE Labs, Novell Inc.
Send instant messages to your online friends http://au.messenger.yahoo.com
^ permalink raw reply [flat|nested] 6+ messages in thread
* Re: Question on build_sched_domains
2006-03-24 7:45 ` Nick Piggin
@ 2006-03-25 8:36 ` Srivatsa Vaddagiri
2006-03-26 2:21 ` Nick Piggin
0 siblings, 1 reply; 6+ messages in thread
From: Srivatsa Vaddagiri @ 2006-03-25 8:36 UTC (permalink / raw)
To: Nick Piggin; +Cc: linux-kernel, Ingo Molnar
On Fri, Mar 24, 2006 at 06:45:21PM +1100, Nick Piggin wrote:
> Yeah I think what's happening is that the sched groups structures
> are not shared between nodes. (It's been a while since I looked at
> this code, and it is a bit tricky to follow).
Its really odd that sched group structure aren't shared between nodes in some
case (sched_group_nodes) and are shared in other cases (sched_group_cpus,
sched_group_core, sched_group_phys).
Also is the GFP_ATOMIC allocation really required (for
sched_group_nodes) in build_sched_domains()?
--
Regards,
vatsa
^ permalink raw reply [flat|nested] 6+ messages in thread
* Re: Question on build_sched_domains
2006-03-25 8:36 ` Srivatsa Vaddagiri
@ 2006-03-26 2:21 ` Nick Piggin
2006-03-26 2:41 ` Srivatsa Vaddagiri
0 siblings, 1 reply; 6+ messages in thread
From: Nick Piggin @ 2006-03-26 2:21 UTC (permalink / raw)
To: vatsa; +Cc: linux-kernel, Ingo Molnar
Srivatsa Vaddagiri wrote:
> On Fri, Mar 24, 2006 at 06:45:21PM +1100, Nick Piggin wrote:
>
>>Yeah I think what's happening is that the sched groups structures
>>are not shared between nodes. (It's been a while since I looked at
>>this code, and it is a bit tricky to follow).
>
>
> Its really odd that sched group structure aren't shared between nodes in some
> case (sched_group_nodes) and are shared in other cases (sched_group_cpus,
> sched_group_core, sched_group_phys).
>
> Also is the GFP_ATOMIC allocation really required (for
> sched_group_nodes) in build_sched_domains()?
>
I don't see why. It should be changed to GFP_KERNEL.
--
SUSE Labs, Novell Inc.
Send instant messages to your online friends http://au.messenger.yahoo.com
^ permalink raw reply [flat|nested] 6+ messages in thread
end of thread, other threads:[~2006-03-26 2:41 UTC | newest]
Thread overview: 6+ messages (download: mbox.gz follow: Atom feed
-- links below jump to the message on this page --
2006-03-24 2:58 Question on build_sched_domains Srivatsa Vaddagiri
2006-03-24 7:12 ` Srivatsa Vaddagiri
2006-03-24 7:45 ` Nick Piggin
2006-03-25 8:36 ` Srivatsa Vaddagiri
2006-03-26 2:21 ` Nick Piggin
2006-03-26 2:41 ` Srivatsa Vaddagiri
This is a public inbox, see mirroring instructions
for how to clone and mirror all data and code used for this inbox