lkml.org 
[lkml]   [2009]   [Mar]   [19]   [last100]   RSS Feed
Views: [wrap][no wrap]   [headers]  [forward] 
 
Messages in this thread
/
Date
From
SubjectRe: [PATCH 20/35] Use a pre-calculated value for num_online_nodes()
On Thu, Mar 19, 2009 at 06:22:38PM -0400, Christoph Lameter wrote:
> On Thu, 19 Mar 2009, Mel Gorman wrote:
>
> > This patch actually alters the API. node_set_online() called when
> > MAX_NUMNODES == 1 will now fail to compile. That situation wouldn't make
> > any sense anyway but is it intentional?
>
> Yes MAX_NUMNODES means that this is not a NUMA configuration. Setting an
> ode online would make no sense. Node 0 is always online.
>

Right.

> > For reference here is the patch I had for a similar goal which kept the
> > API as it was. I'll drop it if you prefer your own version.
>
> Lets look through it and get the best pieces from both.
>

I posted an amalgamation. Sorry for the cross-over mails but I wanted to
get tests going before I fell asleep. They take a few hours to complete.

> > static inline void node_set_state(int node, enum node_states state)
> > {
> > __node_set(node, &node_states[state]);
> > + if (state == N_ONLINE)
> > + nr_online_nodes = num_node_state(N_ONLINE);
> > }
>
> That assumes uses of node_set_state N_ONLINE. Are there such users or are
> all using node_set_online()?
>

node_set_online() calls node_set_state(node, N_ONLINE) so it should have
worked out.

> > @@ -449,7 +457,8 @@ static inline int num_node_state(enum node_states state)
> > node; \
> > })
> >
> > -#define num_online_nodes() num_node_state(N_ONLINE)
> > +
> > +#define num_online_nodes() (nr_online_nodes)
> > #define num_possible_nodes() num_node_state(N_POSSIBLE)
> > #define node_online(node) node_state((node), N_ONLINE)
> > #define node_possible(node) node_state((node), N_POSSIBLE)
>
> Hmmmm... Yes we could get rid of those.
>
> I'd also like to see nr_possible_nodes(). nr_possible_nodes is important
> if you want to check if the system could ever bring up a second node
> (which would make the current optimization not viable) whereas
> nr_online_nodes is the check for how many nodes are currently online.
>

I redid your patch to drop the nr_possible_nodes() because I couldn't convince
myself it was correct in all cases and it isn't as important as avoiding
num_online_nodes() in fast paths.

--
Mel Gorman
Part-time Phd Student Linux Technology Center
University of Limerick IBM Dublin Software Lab


\
 
 \ /
  Last update: 2009-03-19 23:37    [W:0.082 / U:2.488 seconds]
©2003-2020 Jasper Spaans|hosted at Digital Ocean and TransIP|Read the blog|Advertise on this site