On Tue, Jan 21, 2014 at 05:20:06PM -0500, [email protected] wrote:
> From: Rik van Riel <[email protected]>
>
> 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.
>
> Cc: Peter Zijlstra <[email protected]>
> Cc: Mel Gorman <[email protected]>
> Cc: Ingo Molnar <[email protected]>
> Cc: Chegu Vinod <[email protected]>
> Signed-off-by: Rik van Riel <[email protected]>
> ---
> kernel/sched/fair.c | 51 +++++++++++++++++++++++++++++++++++++++++++++++++++
> 1 file changed, 51 insertions(+)
>
> diff --git a/kernel/sched/fair.c b/kernel/sched/fair.c
> index b98ed61..d4f6df5 100644
> --- a/kernel/sched/fair.c
> +++ b/kernel/sched/fair.c
> @@ -885,6 +885,7 @@ struct numa_group {
> struct list_head task_list;
>
> struct rcu_head rcu;
> + nodemask_t active_nodes;
> unsigned long total_faults;
> unsigned long *faults_cpu;
> 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)];
> }
>
> +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
> * task group, on a particular numa node. The group weight is given a
> @@ -1275,6 +1282,40 @@ static void numa_migrate_preferred(struct task_struct
> *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 = numa_group->faults_cpu[task_faults_idx(nid, 0)] +
> + numa_group->faults_cpu[task_faults_idx(nid, 1)];
faults = group_faults_cpu(numa_group, nid)
?
> + if (faults > max_faults)
> + max_faults = faults;
> + }
> +
> + for_each_online_node(nid) {
> + faults = numa_group->faults_cpu[task_faults_idx(nid, 0)] +
> + numa_group->faults_cpu[task_faults_idx(nid, 1)];
Same?
> + 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
> * increments. The more local the fault statistics are, the higher the scan
> * period will be for the next scan window. If local/remote ratio is below
> @@ -1416,6 +1457,7 @@ static void task_numa_placement(struct task_struct *p)
> update_task_scan_period(p, fault_types[0], fault_types[1]);
>
> if (p->numa_group) {
> + update_numa_active_node_mask(p->numa_group);
> /*
> * If the preferred task and group nids are different,
> * iterate over the nodes again to find the best place.
> @@ -1478,6 +1520,8 @@ static void task_numa_group(struct task_struct *p, int
> cpupid, int flags,
> /* Second half of the array tracks nids where faults happen */
> 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++)
> grp->faults[i] = p->numa_faults_memory[i];
>
> @@ -1547,6 +1591,13 @@ static void task_numa_group(struct task_struct *p, int
> cpupid, int flags,
> my_grp->nr_tasks--;
> grp->nr_tasks++;
>
> + /*
> + * We just joined a new group, the set of active nodes may have
> + * changed. Do not update the nodemask of the old group, since
> + * the tasks in that group will probably join the new group soon.
> + */
> + update_numa_active_node_mask(grp);
> +
> spin_unlock(&my_grp->lock);
> spin_unlock(&grp->lock);
>
Ok, I guess this stops the old group making very different migration
decisions just because one task left the group. That has difficult to
predict consequences so assuming the new group_faults_cpu helper gets used
Acked-by: Mel Gorman <[email protected]>
--
Mel Gorman
SUSE Labs
--
To unsubscribe from this list: send the line "unsubscribe linux-kernel" in
the body of a message to [email protected]
More majordomo info at http://vger.kernel.org/majordomo-info.html
Please read the FAQ at http://www.tux.org/lkml/
