Commit 930aa174 authored by Mel Gorman's avatar Mel Gorman Committed by Ingo Molnar
Browse files

sched/numa: Remove the numa_balancing_scan_period_reset sysctl 



With scan rate adaptions based on whether the workload has properly
converged or not there should be no need for the scan period reset
hammer. Get rid of it.

Signed-off-by: default avatarMel Gorman <mgorman@suse.de>
Reviewed-by: default avatarRik van Riel <riel@redhat.com>
Cc: Andrea Arcangeli <aarcange@redhat.com>
Cc: Johannes Weiner <hannes@cmpxchg.org>
Cc: Srikar Dronamraju <srikar@linux.vnet.ibm.com>
Signed-off-by: default avatarPeter Zijlstra <peterz@infradead.org>
Link: http://lkml.kernel.org/r/1381141781-10992-60-git-send-email-mgorman@suse.de


Signed-off-by: default avatarIngo Molnar <mingo@kernel.org>
parent 04bb2f94

Documentation/sysctl/kernel.txt

+3 −8
Original line number Diff line number Diff line
@@ -374,15 +374,13 @@ guarantee. If the target workload is already bound to NUMA nodes then this 
feature should be disabled. Otherwise, if the system overhead from the

feature is too high then the rate the kernel samples for NUMA hinting

faults may be controlled by the numa_balancing_scan_period_min_ms,

numa_balancing_scan_delay_ms, numa_balancing_scan_period_reset,

numa_balancing_scan_period_max_ms, numa_balancing_scan_size_mb and

numa_balancing_settle_count sysctls.

numa_balancing_scan_delay_ms, numa_balancing_scan_period_max_ms,

numa_balancing_scan_size_mb and numa_balancing_settle_count sysctls.



==============================================================



numa_balancing_scan_period_min_ms, numa_balancing_scan_delay_ms,

numa_balancing_scan_period_max_ms, numa_balancing_scan_period_reset,

numa_balancing_scan_size_mb

numa_balancing_scan_period_max_ms, numa_balancing_scan_size_mb



Automatic NUMA balancing scans tasks address space and unmaps pages to

detect if pages are properly placed or if the data should be migrated to a
@@ -418,9 +416,6 @@ rate for each task. 
numa_balancing_scan_size_mb is how many megabytes worth of pages are

scanned for a given scan.



numa_balancing_scan_period_reset is a blunt instrument that controls how

often a tasks scan delay is reset to detect sudden changes in task behaviour.



numa_balancing_settle_count is how many scan periods must complete before

the schedule balancer stops pushing the task towards a preferred node. This

gives the scheduler a chance to place the task on an alternative node if the

include/linux/mm_types.h

+0 −3
Original line number Diff line number Diff line
@@ -420,9 +420,6 @@ struct mm_struct { 
	 */

	unsigned long numa_next_scan;



	/* numa_next_reset is when the PTE scanner period will be reset */

	unsigned long numa_next_reset;



	/* Restart point for scanning and setting pte_numa */

	unsigned long numa_scan_offset;

include/linux/sched/sysctl.h

+0 −1
Original line number Diff line number Diff line
@@ -47,7 +47,6 @@ extern enum sched_tunable_scaling sysctl_sched_tunable_scaling; 
extern unsigned int sysctl_numa_balancing_scan_delay;

extern unsigned int sysctl_numa_balancing_scan_period_min;

extern unsigned int sysctl_numa_balancing_scan_period_max;

extern unsigned int sysctl_numa_balancing_scan_period_reset;

extern unsigned int sysctl_numa_balancing_scan_size;

extern unsigned int sysctl_numa_balancing_settle_count;

kernel/sched/core.c

+0 −1
Original line number Diff line number Diff line
@@ -1721,7 +1721,6 @@ static void __sched_fork(unsigned long clone_flags, struct task_struct *p) 
#ifdef CONFIG_NUMA_BALANCING

	if (p->mm && atomic_read(&p->mm->mm_users) == 1) {

		p->mm->numa_next_scan = jiffies + msecs_to_jiffies(sysctl_numa_balancing_scan_delay);

		p->mm->numa_next_reset = jiffies + msecs_to_jiffies(sysctl_numa_balancing_scan_period_reset);

		p->mm->numa_scan_seq = 0;

	}

kernel/sched/fair.c

+1 −17
Original line number Diff line number Diff line
@@ -826,7 +826,6 @@ update_stats_curr_start(struct cfs_rq *cfs_rq, struct sched_entity *se) 
 */

unsigned int sysctl_numa_balancing_scan_period_min = 1000;

unsigned int sysctl_numa_balancing_scan_period_max = 60000;

unsigned int sysctl_numa_balancing_scan_period_reset = 60000;



/* Portion of address space to scan in MB */

unsigned int sysctl_numa_balancing_scan_size = 256;
@@ -1685,24 +1684,9 @@ void task_numa_work(struct callback_head *work) 
	if (p->flags & PF_EXITING)

		return;



	if (!mm->numa_next_reset || !mm->numa_next_scan) {

	if (!mm->numa_next_scan) {

		mm->numa_next_scan = now +

			msecs_to_jiffies(sysctl_numa_balancing_scan_delay);

		mm->numa_next_reset = now +

			msecs_to_jiffies(sysctl_numa_balancing_scan_period_reset);

	}



	/*

	 * Reset the scan period if enough time has gone by. Objective is that

	 * scanning will be reduced if pages are properly placed. As tasks

	 * can enter different phases this needs to be re-examined. Lacking

	 * proper tracking of reference behaviour, this blunt hammer is used.

	 */

	migrate = mm->numa_next_reset;

	if (time_after(now, migrate)) {

		p->numa_scan_period = task_scan_min(p);

		next_scan = now + msecs_to_jiffies(sysctl_numa_balancing_scan_period_reset);

		xchg(&mm->numa_next_reset, next_scan);

	}



	/*

CRA Git | Maintained and supported by SUSTech CRA and CCSE