lkml.org 
[lkml]   [2013]   [Jul]   [30]   [last100]   RSS Feed
Views: [wrap][no wrap]   [headers]  [forward] 
 
Messages in this thread
Patch in this message
/
From
Subject[RFC PATCH 01/10] sched: Introduce per node numa weights
Date
Load balancer spreads the load evenly for fairness and for maintaining
balance across different domains. However where possible related tasks
could be scheduled in the same domain (esp at node domains) to allow tasks
to have more local accesses. This consolidation can be done without
affecting fairness and leaving the domains balanced

To better consolidate the loads, account weights per-mm per-node. These
stats are used in later patches to select more appropriate tasks during
load balance.

TODO: Modify to capture and use the actual task weights rather than task
counts

Signed-off-by: Srikar Dronamraju <srikar@linux.vnet.ibm.com>
---
fs/exec.c | 5 +++++
include/linux/mm_types.h | 1 +
kernel/fork.c | 10 +++++++---
kernel/sched/fair.c | 34 ++++++++++++++++++++++++++++++++++
4 files changed, 47 insertions(+), 3 deletions(-)

diff --git a/fs/exec.c b/fs/exec.c
index a96a488..b086e9e 100644
--- a/fs/exec.c
+++ b/fs/exec.c
@@ -833,6 +833,11 @@ static int exec_mmap(struct mm_struct *mm)
activate_mm(active_mm, mm);
task_unlock(tsk);
arch_pick_mmap_layout(mm);
+#ifdef CONFIG_NUMA_BALANCING
+ mm->numa_weights = kzalloc(sizeof(atomic_t) * (nr_node_ids + 1), GFP_KERNEL);
+ atomic_inc(&mm->numa_weights[cpu_to_node(task_cpu(tsk))]);
+ atomic_inc(&mm->numa_weights[nr_node_ids]);
+#endif
if (old_mm) {
up_read(&old_mm->mmap_sem);
BUG_ON(active_mm != old_mm);
diff --git a/include/linux/mm_types.h b/include/linux/mm_types.h
index ace9a5f..45d02df 100644
--- a/include/linux/mm_types.h
+++ b/include/linux/mm_types.h
@@ -435,6 +435,7 @@ struct mm_struct {
* a different node than Make PTE Scan Go Now.
*/
int first_nid;
+ atomic_t *numa_weights;
#endif
struct uprobes_state uprobes_state;
};
diff --git a/kernel/fork.c b/kernel/fork.c
index 1766d32..21421bd 100644
--- a/kernel/fork.c
+++ b/kernel/fork.c
@@ -617,6 +617,9 @@ void mmput(struct mm_struct *mm)
khugepaged_exit(mm); /* must run before exit_mmap */
exit_mmap(mm);
set_mm_exe_file(mm, NULL);
+#ifdef CONFIG_NUMA_BALANCING
+ kfree(mm->numa_weights);
+#endif
if (!list_empty(&mm->mmlist)) {
spin_lock(&mmlist_lock);
list_del(&mm->mmlist);
@@ -823,9 +826,6 @@ struct mm_struct *dup_mm(struct task_struct *tsk)
#ifdef CONFIG_TRANSPARENT_HUGEPAGE
mm->pmd_huge_pte = NULL;
#endif
-#ifdef CONFIG_NUMA_BALANCING
- mm->first_nid = NUMA_PTE_SCAN_INIT;
-#endif
if (!mm_init(mm, tsk))
goto fail_nomem;

@@ -844,6 +844,10 @@ struct mm_struct *dup_mm(struct task_struct *tsk)
if (mm->binfmt && !try_module_get(mm->binfmt->module))
goto free_pt;

+#ifdef CONFIG_NUMA_BALANCING
+ mm->first_nid = NUMA_PTE_SCAN_INIT;
+ mm->numa_weights = kzalloc(sizeof(atomic_t) * (nr_node_ids + 1), GFP_KERNEL);
+#endif
return mm;

free_pt:
diff --git a/kernel/sched/fair.c b/kernel/sched/fair.c
index 7a33e59..8a2b5aa 100644
--- a/kernel/sched/fair.c
+++ b/kernel/sched/fair.c
@@ -995,10 +995,40 @@ void task_tick_numa(struct rq *rq, struct task_struct *curr)
}
}
}
+
+static void account_numa_enqueue(struct cfs_rq *cfs_rq, struct task_struct *p)
+{
+ struct mm_struct *mm = p->mm;
+ struct rq *rq = rq_of(cfs_rq);
+ int curnode = cpu_to_node(cpu_of(rq));
+
+ if (mm && mm->numa_weights) {
+ atomic_read(&mm->numa_weights[curnode]);
+ atomic_read(&mm->numa_weights[nr_node_ids]);
+ }
+}
+
+static void account_numa_dequeue(struct cfs_rq *cfs_rq, struct task_struct *p)
+{
+ struct mm_struct *mm = p->mm;
+ struct rq *rq = rq_of(cfs_rq);
+ int curnode = cpu_to_node(cpu_of(rq));
+
+ if (mm && mm->numa_weights) {
+ atomic_dec(&mm->numa_weights[curnode]);
+ atomic_dec(&mm->numa_weights[nr_node_ids]);
+ }
+}
#else
static void task_tick_numa(struct rq *rq, struct task_struct *curr)
{
}
+static void account_numa_enqueue(struct cfs_rq *cfs_rq, struct task_struct *p)
+{
+}
+static void account_numa_dequeue(struct cfs_rq *cfs_rq, struct task_struct *p)
+{
+}
#endif /* CONFIG_NUMA_BALANCING */

static void
@@ -1713,6 +1743,8 @@ enqueue_entity(struct cfs_rq *cfs_rq, struct sched_entity *se, int flags)
if (se != cfs_rq->curr)
__enqueue_entity(cfs_rq, se);
se->on_rq = 1;
+ if (entity_is_task(se))
+ account_numa_enqueue(cfs_rq, task_of(se));

if (cfs_rq->nr_running == 1) {
list_add_leaf_cfs_rq(cfs_rq);
@@ -1810,6 +1842,8 @@ dequeue_entity(struct cfs_rq *cfs_rq, struct sched_entity *se, int flags)

update_min_vruntime(cfs_rq);
update_cfs_shares(cfs_rq);
+ if (entity_is_task(se))
+ account_numa_dequeue(cfs_rq, task_of(se));
}

/*
--
1.7.1


\
 
 \ /
  Last update: 2013-07-30 10:01    [W:0.485 / U:0.656 seconds]
©2003-2020 Jasper Spaans|hosted at Digital Ocean and TransIP|Read the blog|Advertise on this site