From 86e6919e3c65a709ffaf12d8af4f1082991d961f Mon Sep 17 00:00:00 2001 From: Bibo Mao Date: Thu, 14 Apr 2022 12:16:43 -0700 Subject: [PATCH] mm/khugepaged: sched to numa node when collapse huge page Collapsing a huge page will copy huge page from general small pages, dest node is calculated from most one of source pages, however THP daemon is not scheduled on dest node. The performance may be poor since huge page copying across nodes, also cache is not used for target node. With this patch, khugepaged daemon switches to the same numa node with huge page. It saves copying time and makes use of local cache better. With this patch, specint 2006 base performance is improved with 6% on Loongson 3C5000L platform with 32 cores and 8 numa nodes. Link: https://lkml.kernel.org/r/20220317065024.2635069-1-maobibo@loongson.cn Signed-off-by: Bibo Mao Cc: David Hildenbrand Cc: Yang Shi Cc: Mike Kravetz Signed-off-by: Andrew Morton --- mm/khugepaged.c | 8 ++++++++ 1 file changed, 8 insertions(+) diff --git a/mm/khugepaged.c b/mm/khugepaged.c index edd643de2347..4688a6df035b 100644 --- a/mm/khugepaged.c +++ b/mm/khugepaged.c @@ -1055,6 +1055,7 @@ static void collapse_huge_page(struct mm_struct *mm, struct vm_area_struct *vma; struct mmu_notifier_range range; gfp_t gfp; + const struct cpumask *cpumask; VM_BUG_ON(address & ~HPAGE_PMD_MASK); @@ -1068,6 +1069,13 @@ static void collapse_huge_page(struct mm_struct *mm, * that. We will recheck the vma after taking it again in write mode. */ mmap_read_unlock(mm); + + /* sched to specified node before huage page memory copy */ + if (task_node(current) != node) { + cpumask = cpumask_of_node(node); + if (!cpumask_empty(cpumask)) + set_cpus_allowed_ptr(current, cpumask); + } new_page = khugepaged_alloc_page(hpage, gfp, node); if (!new_page) { result = SCAN_ALLOC_HUGE_PAGE_FAIL; -- 2.49.0