0ac0c0d0f8
Some workloads that create a large number of small files tend to assign too many pages to node 0 (multi-node systems). Part of the reason is that the rotor (in cpuset_mem_spread_node()) used to assign nodes starts at node 0 for newly created tasks. This patch changes the rotor to be initialized to a random node number of the cpuset. [akpm@linux-foundation.org: fix layout] [Lee.Schermerhorn@hp.com: Define stub numa_random() for !NUMA configuration] Signed-off-by: Jack Steiner <steiner@sgi.com> Signed-off-by: Lee Schermerhorn <lee.schermerhorn@hp.com> Cc: Christoph Lameter <cl@linux-foundation.org> Cc: Pekka Enberg <penberg@cs.helsinki.fi> Cc: Paul Menage <menage@google.com> Cc: Jack Steiner <steiner@sgi.com> Cc: Robin Holt <holt@sgi.com> Signed-off-by: Andrew Morton <akpm@linux-foundation.org> Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
85 lines
1.9 KiB
C
85 lines
1.9 KiB
C
/* Common code for 32 and 64-bit NUMA */
|
|
#include <linux/topology.h>
|
|
#include <linux/module.h>
|
|
#include <linux/bootmem.h>
|
|
#include <linux/random.h>
|
|
|
|
#ifdef CONFIG_DEBUG_PER_CPU_MAPS
|
|
# define DBG(x...) printk(KERN_DEBUG x)
|
|
#else
|
|
# define DBG(x...)
|
|
#endif
|
|
|
|
/*
|
|
* Which logical CPUs are on which nodes
|
|
*/
|
|
cpumask_var_t node_to_cpumask_map[MAX_NUMNODES];
|
|
EXPORT_SYMBOL(node_to_cpumask_map);
|
|
|
|
/*
|
|
* Allocate node_to_cpumask_map based on number of available nodes
|
|
* Requires node_possible_map to be valid.
|
|
*
|
|
* Note: node_to_cpumask() is not valid until after this is done.
|
|
* (Use CONFIG_DEBUG_PER_CPU_MAPS to check this.)
|
|
*/
|
|
void __init setup_node_to_cpumask_map(void)
|
|
{
|
|
unsigned int node, num = 0;
|
|
|
|
/* setup nr_node_ids if not done yet */
|
|
if (nr_node_ids == MAX_NUMNODES) {
|
|
for_each_node_mask(node, node_possible_map)
|
|
num = node;
|
|
nr_node_ids = num + 1;
|
|
}
|
|
|
|
/* allocate the map */
|
|
for (node = 0; node < nr_node_ids; node++)
|
|
alloc_bootmem_cpumask_var(&node_to_cpumask_map[node]);
|
|
|
|
/* cpumask_of_node() will now work */
|
|
pr_debug("Node to cpumask map for %d nodes\n", nr_node_ids);
|
|
}
|
|
|
|
#ifdef CONFIG_DEBUG_PER_CPU_MAPS
|
|
/*
|
|
* Returns a pointer to the bitmask of CPUs on Node 'node'.
|
|
*/
|
|
const struct cpumask *cpumask_of_node(int node)
|
|
{
|
|
if (node >= nr_node_ids) {
|
|
printk(KERN_WARNING
|
|
"cpumask_of_node(%d): node > nr_node_ids(%d)\n",
|
|
node, nr_node_ids);
|
|
dump_stack();
|
|
return cpu_none_mask;
|
|
}
|
|
if (node_to_cpumask_map[node] == NULL) {
|
|
printk(KERN_WARNING
|
|
"cpumask_of_node(%d): no node_to_cpumask_map!\n",
|
|
node);
|
|
dump_stack();
|
|
return cpu_online_mask;
|
|
}
|
|
return node_to_cpumask_map[node];
|
|
}
|
|
EXPORT_SYMBOL(cpumask_of_node);
|
|
#endif
|
|
|
|
/*
|
|
* Return the bit number of a random bit set in the nodemask.
|
|
* (returns -1 if nodemask is empty)
|
|
*/
|
|
int __node_random(const nodemask_t *maskp)
|
|
{
|
|
int w, bit = -1;
|
|
|
|
w = nodes_weight(*maskp);
|
|
if (w)
|
|
bit = bitmap_ord_to_pos(maskp->bits,
|
|
get_random_int() % w, MAX_NUMNODES);
|
|
return bit;
|
|
}
|
|
EXPORT_SYMBOL(__node_random);
|