[PATCH] node local per-cpu-pages

This patch modifies the way pagesets in struct zone are managed.

Each zone has a per-cpu array of pagesets.  So any particular CPU has some
memory in each zone structure which belongs to itself.  Even if that CPU is
not local to that zone.

So the patch relocates the pagesets for each cpu to the node that is nearest
to the cpu instead of allocating the pagesets in the (possibly remote) target
zone.  This means that the operations to manage pages on remote zone can be
done with information available locally.

We play a macro trick so that non-NUMA pmachines avoid the additional
pointer chase on the page allocator fastpath.

AIM7 benchmark on a 32 CPU SGI Altix

w/o patches:
Tasks    jobs/min  jti  jobs/min/task      real       cpu
    1      484.68  100       484.6769     12.01      1.97   Fri Mar 25 11:01:42 2005
  100    27140.46   89       271.4046     21.44    148.71   Fri Mar 25 11:02:04 2005
  200    30792.02   82       153.9601     37.80    296.72   Fri Mar 25 11:02:42 2005
  300    32209.27   81       107.3642     54.21    451.34   Fri Mar 25 11:03:37 2005
  400    34962.83   78        87.4071     66.59    588.97   Fri Mar 25 11:04:44 2005
  500    31676.92   75        63.3538     91.87    742.71   Fri Mar 25 11:06:16 2005
  600    36032.69   73        60.0545     96.91    885.44   Fri Mar 25 11:07:54 2005
  700    35540.43   77        50.7720    114.63   1024.28   Fri Mar 25 11:09:49 2005
  800    33906.70   74        42.3834    137.32   1181.65   Fri Mar 25 11:12:06 2005
  900    34120.67   73        37.9119    153.51   1325.26   Fri Mar 25 11:14:41 2005
 1000    34802.37   74        34.8024    167.23   1465.26   Fri Mar 25 11:17:28 2005

with slab API changes and pageset patch:

Tasks    jobs/min  jti  jobs/min/task      real       cpu
    1      485.00  100       485.0000     12.00      1.96   Fri Mar 25 11:46:18 2005
  100    28000.96   89       280.0096     20.79    150.45   Fri Mar 25 11:46:39 2005
  200    32285.80   79       161.4290     36.05    293.37   Fri Mar 25 11:47:16 2005
  300    40424.15   84       134.7472     43.19    438.42   Fri Mar 25 11:47:59 2005
  400    39155.01   79        97.8875     59.46    590.05   Fri Mar 25 11:48:59 2005
  500    37881.25   82        75.7625     76.82    730.19   Fri Mar 25 11:50:16 2005
  600    39083.14   78        65.1386     89.35    872.79   Fri Mar 25 11:51:46 2005
  700    38627.83   77        55.1826    105.47   1022.46   Fri Mar 25 11:53:32 2005
  800    39631.94   78        49.5399    117.48   1169.94   Fri Mar 25 11:55:30 2005
  900    36903.70   79        41.0041    141.94   1310.78   Fri Mar 25 11:57:53 2005
 1000    36201.23   77        36.2012    160.77   1458.31   Fri Mar 25 12:00:34 2005

Signed-off-by: Christoph Lameter <clameter@sgi.com>
Signed-off-by: Shobhit Dayal <shobhit@calsoftinc.com>
Signed-off-by: Shai Fultheim <Shai@Scalex86.org>
Signed-off-by: Andrew Morton <akpm@osdl.org>
Signed-off-by: Linus Torvalds <torvalds@osdl.org>

2 files changed, 16 insertions, 1 deletions

diff --git a/include/linux/mm.h b/include/linux/mm.h
index 17518fe0b311..1813b162b0a8 100644
--- a/include/linux/mm.h
+++ b/include/linux/mm.h
@@ -691,6 +691,12 @@ extern void show_mem(void);
 extern void si_meminfo(struct sysinfo * val);
 extern void si_meminfo_node(struct sysinfo *val, int nid);
 
+#ifdef CONFIG_NUMA
+extern void setup_per_cpu_pageset(void);
+#else
+static inline void setup_per_cpu_pageset(void) {}
+#endif
+
 /* prio_tree.c */
 void vma_prio_tree_add(struct vm_area_struct *, struct vm_area_struct *old);
 void vma_prio_tree_insert(struct vm_area_struct *, struct prio_tree_root *);
diff --git a/include/linux/mmzone.h b/include/linux/mmzone.h
index 18fed8b67943..4733d35d8223 100644
--- a/include/linux/mmzone.h
+++ b/include/linux/mmzone.h
@@ -63,6 +63,12 @@ struct per_cpu_pageset {
 #endif
 } ____cacheline_aligned_in_smp;
 
+#ifdef CONFIG_NUMA
+#define zone_pcp(__z, __cpu) ((__z)->pageset[(__cpu)])
+#else
+#define zone_pcp(__z, __cpu) (&(__z)->pageset[(__cpu)])
+#endif
+
 #define ZONE_DMA                0
 #define ZONE_NORMAL             1
 #define ZONE_HIGHMEM            2
@@ -122,8 +128,11 @@ struct zone {
          */
         unsigned long           lowmem_reserve[MAX_NR_ZONES];
 
+#ifdef CONFIG_NUMA
+        struct per_cpu_pageset  *pageset[NR_CPUS];
+#else
         struct per_cpu_pageset  pageset[NR_CPUS];
-
+#endif
         /*
          * free areas of different sizes
          */