diff --git a/include/linux/sched.h b/include/linux/sched.h index 37841958d234c42af49ce9f709f7382d5e33c3f2..7d95a232b5b963b538f5079a542597904942ea73 100644 --- a/include/linux/sched.h +++ b/include/linux/sched.h @@ -2006,6 +2006,7 @@ enum sched_tunable_scaling { }; 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_size; diff --git a/kernel/sched/core.c b/kernel/sched/core.c index cad0d092ce3b02d1e118d0e165072ab65e7dccbf..fbfc4843063ff17140a18d82e59229499aa7f755 100644 --- a/kernel/sched/core.c +++ b/kernel/sched/core.c @@ -1543,7 +1543,7 @@ static void __sched_fork(struct task_struct *p) p->node_stamp = 0ULL; p->numa_scan_seq = p->mm ? p->mm->numa_scan_seq : 0; p->numa_migrate_seq = p->mm ? p->mm->numa_scan_seq - 1 : 0; - p->numa_scan_period = sysctl_numa_balancing_scan_period_min; + p->numa_scan_period = sysctl_numa_balancing_scan_delay; p->numa_work.next = &p->numa_work; #endif /* CONFIG_NUMA_BALANCING */ } diff --git a/kernel/sched/fair.c b/kernel/sched/fair.c index f6e1f25ed2bd6b6c30aa80d93280664d8bfd06ac..7727b01615795b9209641de693f40e5429f541ec 100644 --- a/kernel/sched/fair.c +++ b/kernel/sched/fair.c @@ -788,6 +788,9 @@ unsigned int sysctl_numa_balancing_scan_period_max = 100*16; /* Portion of address space to scan in MB */ unsigned int sysctl_numa_balancing_scan_size = 256; +/* Scan @scan_size MB every @scan_period after an initial @scan_delay in ms */ +unsigned int sysctl_numa_balancing_scan_delay = 1000; + static void task_numa_placement(struct task_struct *p) { int seq = ACCESS_ONCE(p->mm->numa_scan_seq); @@ -929,6 +932,8 @@ void task_tick_numa(struct rq *rq, struct task_struct *curr) period = (u64)curr->numa_scan_period * NSEC_PER_MSEC; if (now - curr->node_stamp > period) { + if (!curr->node_stamp) + curr->numa_scan_period = sysctl_numa_balancing_scan_period_min; curr->node_stamp = now; if (!time_before(jiffies, curr->mm->numa_next_scan)) { diff --git a/kernel/sysctl.c b/kernel/sysctl.c index 7d3a2e0475e51f29dac7a9674eb08b5b0e1b75db..48a68cc258c12fdbffe6912810fe22c21bfcc1db 100644 --- a/kernel/sysctl.c +++ b/kernel/sysctl.c @@ -352,6 +352,13 @@ static struct ctl_table kern_table[] = { }, #endif /* CONFIG_SMP */ #ifdef CONFIG_NUMA_BALANCING + { + .procname = "numa_balancing_scan_delay_ms", + .data = &sysctl_numa_balancing_scan_delay, + .maxlen = sizeof(unsigned int), + .mode = 0644, + .proc_handler = proc_dointvec, + }, { .procname = "numa_balancing_scan_period_min_ms", .data = &sysctl_numa_balancing_scan_period_min,