From 20f586486b87dcfe10b8c79398e24e720885588a Mon Sep 17 00:00:00 2001 From: Raghavendra K T Date: Wed, 1 Mar 2023 17:49:02 +0530 Subject: [PATCH] sched/numa: implement access PID reset logic This helps to ensure that only recently accessed PIDs scan the VMAs. Current implementation: (idea supported by PeterZ) 1. Accessing PID information is maintained in two windows. access_pids[1] being newest. 2. Reset old access PID info i.e. access_pid[0] every (4 * sysctl_numa_balancing_scan_delay) interval after initial scan delay period expires. The above interval seemed to be experimentally optimum since it avoids frequent reset of access info as well as helps clearing the old access info regularly. The reset logic is implemented in scan path. Link: https://lkml.kernel.org/r/f7a675f66d1442d048b4216b2baf94515012c405.1677672277.git.raghavendra.kt@amd.com Signed-off-by: Raghavendra K T Suggested-by: Mel Gorman Cc: Bharata B Rao Cc: David Hildenbrand Cc: Disha Talreja Cc: Ingo Molnar Cc: Mike Rapoport Cc: Peter Zijlstra Signed-off-by: Andrew Morton --- include/linux/mm.h | 4 ++-- include/linux/mm_types.h | 3 ++- kernel/sched/fair.c | 23 +++++++++++++++++++++-- 3 files changed, 25 insertions(+), 5 deletions(-) diff --git a/include/linux/mm.h b/include/linux/mm.h index 215327daffae..e05a878e186e 100644 --- a/include/linux/mm.h +++ b/include/linux/mm.h @@ -1692,8 +1692,8 @@ static inline void vma_set_access_pid_bit(struct vm_area_struct *vma) unsigned int pid_bit; pid_bit = current->pid % BITS_PER_LONG; - if (vma->numab_state && !test_bit(pid_bit, &vma->numab_state->access_pids)) { - __set_bit(pid_bit, &vma->numab_state->access_pids); + if (vma->numab_state && !test_bit(pid_bit, &vma->numab_state->access_pids[1])) { + __set_bit(pid_bit, &vma->numab_state->access_pids[1]); } } #else /* !CONFIG_NUMA_BALANCING */ diff --git a/include/linux/mm_types.h b/include/linux/mm_types.h index f8cbd8efc7cb..092f842a854f 100644 --- a/include/linux/mm_types.h +++ b/include/linux/mm_types.h @@ -477,7 +477,8 @@ struct vma_lock { struct vma_numab_state { unsigned long next_scan; - unsigned long access_pids; + unsigned long next_pid_reset; + unsigned long access_pids[2]; }; /* diff --git a/kernel/sched/fair.c b/kernel/sched/fair.c index ef27b5931480..a962d4b60cd7 100644 --- a/kernel/sched/fair.c +++ b/kernel/sched/fair.c @@ -2930,6 +2930,7 @@ static void reset_ptenuma_scan(struct task_struct *p) static bool vma_is_accessed(struct vm_area_struct *vma) { + unsigned long pids; /* * Allow unconditional access first two times, so that all the (pages) * of VMAs get prot_none fault introduced irrespective of accesses. @@ -2939,10 +2940,12 @@ static bool vma_is_accessed(struct vm_area_struct *vma) if (READ_ONCE(current->mm->numa_scan_seq) < 2) return true; - return test_bit(current->pid % BITS_PER_LONG, - &vma->numab_state->access_pids); + pids = vma->numab_state->access_pids[0] | vma->numab_state->access_pids[1]; + return test_bit(current->pid % BITS_PER_LONG, &pids); } +#define VMA_PID_RESET_PERIOD (4 * sysctl_numa_balancing_scan_delay) + /* * The expensive part of numa migration is done from task_work context. * Triggered from task_tick_numa(). @@ -3051,6 +3054,10 @@ static void task_numa_work(struct callback_head *work) vma->numab_state->next_scan = now + msecs_to_jiffies(sysctl_numa_balancing_scan_delay); + + /* Reset happens after 4 times scan delay of scan start */ + vma->numab_state->next_pid_reset = vma->numab_state->next_scan + + msecs_to_jiffies(VMA_PID_RESET_PERIOD); } /* @@ -3065,6 +3072,18 @@ static void task_numa_work(struct callback_head *work) if (!vma_is_accessed(vma)) continue; + /* + * RESET access PIDs regularly for old VMAs. Resetting after checking + * vma for recent access to avoid clearing PID info before access.. + */ + if (mm->numa_scan_seq && + time_after(jiffies, vma->numab_state->next_pid_reset)) { + vma->numab_state->next_pid_reset = vma->numab_state->next_pid_reset + + msecs_to_jiffies(VMA_PID_RESET_PERIOD); + vma->numab_state->access_pids[0] = READ_ONCE(vma->numab_state->access_pids[1]); + vma->numab_state->access_pids[1] = 0; + } + do { start = max(start, vma->vm_start); end = ALIGN(start + (pages << PAGE_SHIFT), HPAGE_SIZE);