Re: hash table sizes

[Jes Sorensen <jes@wildopensource.com>]

>>>>> "Andrew" == Andrew Morton <akpm@osdl.org> writes:

Andrew> jbarnes@sgi.com (Jesse Barnes) wrote:
>> Something like that might be ok, but on our system, all memory is
>> in ZONE_DMA...

Andrew> Well yes, we'd want

Andrew> 	vfs_caches_init(min(num_physpages,
Andrew> some_platform_limit()));

Andrew> which on ia32 would evaluate to nr_free_buffer_pages() and on
Andrew> ia64 would evaluate to the size of one of those zones.

What about something like this? I believe node_present_pages should be
the same as nym_physpages on a non-NUMA machine. If not we can make it
min(num_physpages, NODE_DATA(0)->node_present_pages).

Of course this might not work perfectly if one has multiple nodes and
node 0 has no or very little memory. It would also be nice if one
could spread the various caches onto various nodes, but we can leave
that for stage 2 ;-)

Cheers,
Jes

--- orig/linux-2.6.0-test10/init/main.c	Sun Nov 23 17:31:14 2003
+++ linux-2.6.0-test10/init/main.c	Fri Nov 28 07:06:45 2003
@@ -447,7 +447,7 @@
 	proc_caches_init();
 	buffer_init();
 	security_scaffolding_startup();
-	vfs_caches_init(num_physpages);
+	vfs_caches_init(NODE_DATA(0)->node_present_pages);
 	radix_tree_init();
 	signals_init();
 	/* rootfs populating might need page-writeback */