sched/numa: Build per numa_group active node mask from numa_faults_cpu statistics
The numa_faults_cpu statistics are used to maintain an active_nodes nodemask per numa_group. This allows us to be smarter about when to do numa migrations. Signed-off-by: Rik van Riel <riel@redhat.com> Acked-by: Mel Gorman <mgorman@suse.de> Signed-off-by: Peter Zijlstra <peterz@infradead.org> Cc: Chegu Vinod <chegu_vinod@hp.com> Link: http://lkml.kernel.org/r/1390860228-21539-5-git-send-email-riel@redhat.com Signed-off-by: Ingo Molnar <mingo@kernel.org>
This commit is contained in:
parent
50ec8a401f
commit
20e07dea28
|
@ -885,6 +885,7 @@ struct numa_group {
|
||||||
struct list_head task_list;
|
struct list_head task_list;
|
||||||
|
|
||||||
struct rcu_head rcu;
|
struct rcu_head rcu;
|
||||||
|
nodemask_t active_nodes;
|
||||||
unsigned long total_faults;
|
unsigned long total_faults;
|
||||||
unsigned long *faults_cpu;
|
unsigned long *faults_cpu;
|
||||||
unsigned long faults[0];
|
unsigned long faults[0];
|
||||||
|
@ -918,6 +919,12 @@ static inline unsigned long group_faults(struct task_struct *p, int nid)
|
||||||
p->numa_group->faults[task_faults_idx(nid, 1)];
|
p->numa_group->faults[task_faults_idx(nid, 1)];
|
||||||
}
|
}
|
||||||
|
|
||||||
|
static inline unsigned long group_faults_cpu(struct numa_group *group, int nid)
|
||||||
|
{
|
||||||
|
return group->faults_cpu[task_faults_idx(nid, 0)] +
|
||||||
|
group->faults_cpu[task_faults_idx(nid, 1)];
|
||||||
|
}
|
||||||
|
|
||||||
/*
|
/*
|
||||||
* These return the fraction of accesses done by a particular task, or
|
* These return the fraction of accesses done by a particular task, or
|
||||||
* task group, on a particular numa node. The group weight is given a
|
* task group, on a particular numa node. The group weight is given a
|
||||||
|
@ -1270,6 +1277,38 @@ static void numa_migrate_preferred(struct task_struct *p)
|
||||||
task_numa_migrate(p);
|
task_numa_migrate(p);
|
||||||
}
|
}
|
||||||
|
|
||||||
|
/*
|
||||||
|
* Find the nodes on which the workload is actively running. We do this by
|
||||||
|
* tracking the nodes from which NUMA hinting faults are triggered. This can
|
||||||
|
* be different from the set of nodes where the workload's memory is currently
|
||||||
|
* located.
|
||||||
|
*
|
||||||
|
* The bitmask is used to make smarter decisions on when to do NUMA page
|
||||||
|
* migrations, To prevent flip-flopping, and excessive page migrations, nodes
|
||||||
|
* are added when they cause over 6/16 of the maximum number of faults, but
|
||||||
|
* only removed when they drop below 3/16.
|
||||||
|
*/
|
||||||
|
static void update_numa_active_node_mask(struct numa_group *numa_group)
|
||||||
|
{
|
||||||
|
unsigned long faults, max_faults = 0;
|
||||||
|
int nid;
|
||||||
|
|
||||||
|
for_each_online_node(nid) {
|
||||||
|
faults = group_faults_cpu(numa_group, nid);
|
||||||
|
if (faults > max_faults)
|
||||||
|
max_faults = faults;
|
||||||
|
}
|
||||||
|
|
||||||
|
for_each_online_node(nid) {
|
||||||
|
faults = group_faults_cpu(numa_group, nid);
|
||||||
|
if (!node_isset(nid, numa_group->active_nodes)) {
|
||||||
|
if (faults > max_faults * 6 / 16)
|
||||||
|
node_set(nid, numa_group->active_nodes);
|
||||||
|
} else if (faults < max_faults * 3 / 16)
|
||||||
|
node_clear(nid, numa_group->active_nodes);
|
||||||
|
}
|
||||||
|
}
|
||||||
|
|
||||||
/*
|
/*
|
||||||
* When adapting the scan rate, the period is divided into NUMA_PERIOD_SLOTS
|
* When adapting the scan rate, the period is divided into NUMA_PERIOD_SLOTS
|
||||||
* increments. The more local the fault statistics are, the higher the scan
|
* increments. The more local the fault statistics are, the higher the scan
|
||||||
|
@ -1412,6 +1451,7 @@ static void task_numa_placement(struct task_struct *p)
|
||||||
update_task_scan_period(p, fault_types[0], fault_types[1]);
|
update_task_scan_period(p, fault_types[0], fault_types[1]);
|
||||||
|
|
||||||
if (p->numa_group) {
|
if (p->numa_group) {
|
||||||
|
update_numa_active_node_mask(p->numa_group);
|
||||||
/*
|
/*
|
||||||
* If the preferred task and group nids are different,
|
* If the preferred task and group nids are different,
|
||||||
* iterate over the nodes again to find the best place.
|
* iterate over the nodes again to find the best place.
|
||||||
|
@ -1474,6 +1514,8 @@ static void task_numa_group(struct task_struct *p, int cpupid, int flags,
|
||||||
/* Second half of the array tracks nids where faults happen */
|
/* Second half of the array tracks nids where faults happen */
|
||||||
grp->faults_cpu = grp->faults + 2 * nr_node_ids;
|
grp->faults_cpu = grp->faults + 2 * nr_node_ids;
|
||||||
|
|
||||||
|
node_set(task_node(current), grp->active_nodes);
|
||||||
|
|
||||||
for (i = 0; i < 4*nr_node_ids; i++)
|
for (i = 0; i < 4*nr_node_ids; i++)
|
||||||
grp->faults[i] = p->numa_faults_memory[i];
|
grp->faults[i] = p->numa_faults_memory[i];
|
||||||
|
|
||||||
|
|
Loading…
Reference in New Issue