Skip to contentSkip to conversation

scheduler fixes

GIT PULL Ingo Molnar 2 participants 2 messages Oct 5, 2018

Subsystems (7)
Memory management MM core Tracing Scheduler +3 more subsystems
lore
Share & tools
lore

Ingo Molnar

author
#0 lore raw

Greg,

Please pull the latest sched-urgent-for-linus git tree from:

git://git.kernel.org/pub/scm/linux/kernel/git/tip/tip.git sched-urgent-for-linus

# HEAD: 37355bdc5a129899f6b245900a8eb944a092f7fd sched/numa: Migrate pages to local nodes quicker early in the lifetime of a task

These fixes address a rather involved performance regression between v4.17->v4.19 in the sched/numa auto-balancing code. Since distros really need this fix we accelerated it to sched/urgent for a faster upstream merge.

NUMA scheduling and balancing performance is now largely back to v4.17 levels, without reintroducing the NUMA placement bugs that v4.18 and v4.19 fixed.

Many thanks to Srikar Dronamraju, Mel Gorman and Jirka Hladky, for reporting, testing, re-testing and solving this rather complex set of bugs.

Thanks,

Ingo

------------------>
Mel Gorman (3):
sched/numa: Limit the conditions where scan period is reset
mm, sched/numa: Remove rate-limiting of automatic NUMA balancing migration sched/numa: Migrate pages to local nodes quicker early in the lifetime of a task

Srikar Dronamraju (5):
sched/numa: Stop multiple tasks from moving to the CPU at the same time sched/numa: Pass destination CPU as a parameter to migrate_task_rq sched/numa: Reset scan rate whenever task moves across nodes mm/migrate: Use spin_trylock() while resetting rate limit sched/numa: Avoid task migration for small NUMA improvement

 include/linux/mmzone.h         |   6 ---
 include/trace/events/migrate.h |  27 -----------
 kernel/sched/core.c            |   2 +-
 kernel/sched/deadline.c        |   2 +-
 kernel/sched/fair.c            | 104 +++++++++++++++++++++++++++++++++++------
 kernel/sched/sched.h           |   3 +-
 mm/migrate.c                   |  57 ----------------------
 mm/page_alloc.c                |   2 -
 8 files changed, 95 insertions(+), 108 deletions(-)
include/linux/mmzone.h +0 -6
index 1e22d96734e0..3f4c0b167333 100644
@@ -671,12 +671,6 @@ typedef struct pglist_data {
 #ifdef CONFIG_NUMA_BALANCING
 	/* Lock serializing the migrate rate limiting window */
 	spinlock_t numabalancing_migrate_lock;
-
-	/* Rate limiting time interval */
-	unsigned long numabalancing_migrate_next_window;
-
-	/* Number of pages migrated during the rate limiting time interval */
-	unsigned long numabalancing_migrate_nr_pages;
 #endif
 	/*
 	 * This is a per-node reserve of pages that are not available
include/trace/events/migrate.h +0 -27
index 711372845945..705b33d1e395 100644
@@ -70,33 +70,6 @@ TRACE_EVENT(mm_migrate_pages,
 		__print_symbolic(__entry->mode, MIGRATE_MODE),
 		__print_symbolic(__entry->reason, MIGRATE_REASON))
 );
-
-TRACE_EVENT(mm_numa_migrate_ratelimit,
-
-	TP_PROTO(struct task_struct *p, int dst_nid, unsigned long nr_pages),
-
-	TP_ARGS(p, dst_nid, nr_pages),
-
-	TP_STRUCT__entry(
-		__array(	char,		comm,	TASK_COMM_LEN)
-		__field(	pid_t,		pid)
-		__field(	int,		dst_nid)
-		__field(	unsigned long,	nr_pages)
-	),
-
-	TP_fast_assign(
-		memcpy(__entry->comm, p->comm, TASK_COMM_LEN);
-		__entry->pid		= p->pid;
-		__entry->dst_nid	= dst_nid;
-		__entry->nr_pages	= nr_pages;
-	),
-
-	TP_printk("comm=%s pid=%d dst_nid=%d nr_pages=%lu",
-		__entry->comm,
-		__entry->pid,
-		__entry->dst_nid,
-		__entry->nr_pages)
-);
 #endif /* _TRACE_MIGRATE_H */
 
 /* This part must be outside protection */
kernel/sched/core.c +1 -1
index 625bc9897f62..ad97f3ba5ec5 100644
@@ -1167,7 +1167,7 @@ void set_task_cpu(struct task_struct *p, unsigned int new_cpu)
 
 	if (task_cpu(p) != new_cpu) {
 		if (p->sched_class->migrate_task_rq)
-			p->sched_class->migrate_task_rq(p);
+			p->sched_class->migrate_task_rq(p, new_cpu);
 		p->se.nr_migrations++;
 		rseq_migrate(p);
 		perf_event_task_migrate(p);
kernel/sched/deadline.c +1 -1
index 997ea7b839fa..91e4202b0634 100644
@@ -1607,7 +1607,7 @@ select_task_rq_dl(struct task_struct *p, int cpu, int sd_flag, int flags)
 	return cpu;
 }
 
-static void migrate_task_rq_dl(struct task_struct *p)
+static void migrate_task_rq_dl(struct task_struct *p, int new_cpu __maybe_unused)
 {
 	struct rq *rq;
kernel/sched/fair.c +91 -13

195 lines not on this page · raw message

kernel/sched/sched.h +2 -1
index 4a2e8cae63c4..455fa330de04 100644
@@ -783,6 +783,7 @@ struct rq {
 #ifdef CONFIG_NUMA_BALANCING
 	unsigned int		nr_numa_running;
 	unsigned int		nr_preferred_running;
+	unsigned int		numa_migrate_on;
 #endif
 	#define CPU_LOAD_IDX_MAX 5
 	unsigned long		cpu_load[CPU_LOAD_IDX_MAX];

@@ -1523,7 +1524,7 @@ struct sched_class {
 
 #ifdef CONFIG_SMP
 	int  (*select_task_rq)(struct task_struct *p, int task_cpu, int sd_flag, int flags);
-	void (*migrate_task_rq)(struct task_struct *p);
+	void (*migrate_task_rq)(struct task_struct *p, int new_cpu);
 
 	void (*task_woken)(struct rq *this_rq, struct task_struct *task);
mm/migrate.c +0 -57

81 lines not on this page · raw message

mm/page_alloc.c +0 -2
index 89d2a2ab3fe6..706a738c0aee 100644
@@ -6197,8 +6197,6 @@ static unsigned long __init calc_memmap_size(unsigned long spanned_pages,
 static void pgdat_init_numabalancing(struct pglist_data *pgdat)
 {
 	spin_lock_init(&pgdat->numabalancing_migrate_lock);
-	pgdat->numabalancing_migrate_nr_pages = 0;
-	pgdat->numabalancing_migrate_next_window = jiffies;
 }
 #else
 static void pgdat_init_numabalancing(struct pglist_data *pgdat) {}
#1 lore raw
Quoted 5 lines · Ingo Molnar

Greg,

Please pull the latest sched-urgent-for-linus git tree from:

git://git.kernel.org/pub/scm/linux/kernel/git/tip/tip.git sched-urgent-for-linus

Now merged, thanks.

greg k-h