From 879c6000e191b61b97e17bce44c4564ee42eb612 Mon Sep 17 00:00:00 2001 From: Lance Yang Date: Mon, 29 Jan 2024 13:45:51 +0800 Subject: [PATCH] mm/khugepaged: bypassing unnecessary scans with MMF_DISABLE_THP check khugepaged scans the entire address space in the background for each given mm, looking for opportunities to merge sequences of basic pages into huge pages. However, when an mm is inserted to the mm_slots list, and the MMF_DISABLE_THP flag is set later, this scanning process becomes unnecessary for that mm and can be skipped to avoid redundant operations, especially in scenarios with a large address space. On an Intel Core i5 CPU, the time taken by khugepaged to scan the address space of the process, which has been set with the MMF_DISABLE_THP flag after being added to the mm_slots list, is as follows (shorter is better): VMA Count | Old | New | Change --------------------------------------- 50 | 23us | 9us | -60.9% 100 | 32us | 9us | -71.9% 200 | 44us | 9us | -79.5% 400 | 75us | 9us | -88.0% 800 | 98us | 9us | -90.8% Once the count of VMAs for the process exceeds page_to_scan, khugepaged needs to wait for scan_sleep_millisecs ms before scanning the next process. IMO, unnecessary scans could actually be skipped with a very inexpensive mm->flags check in this case. This commit introduces a check before each scanning process to test the MMF_DISABLE_THP flag for the given mm; if the flag is set, the scanning process is bypassed, thereby improving the efficiency of khugepaged. This optimization is not a correctness issue but rather an enhancement to save expensive checks on each VMA when userspace cannot prctl itself before spawning into the new process. On some servers within our company, we deploy a daemon responsible for monitoring and updating local applications. Some applications prefer not to use THP, so the daemon calls prctl to disable THP before fork/exec. Conversely, for other applications, the daemon calls prctl to enable THP before fork/exec. Ideally, the daemon should invoke prctl after the fork, but its current implementation follows the described approach. In the Go standard library, there is no direct encapsulation of the fork system call; instead, fork and execve are combined into one through syscall.ForkExec. Link: https://lkml.kernel.org/r/20240129054551.57728-1-ioworker0@gmail.com Signed-off-by: Lance Yang Acked-by: David Hildenbrand Cc: Michal Hocko Cc: Minchan Kim Cc: Muchun Song Cc: Peter Xu Cc: Zach O'Keefe Signed-off-by: Andrew Morton --- mm/khugepaged.c | 18 ++++++++++++------ 1 file changed, 12 insertions(+), 6 deletions(-) diff --git a/mm/khugepaged.c b/mm/khugepaged.c index fe43fbc44525..2771fc043b3b 100644 --- a/mm/khugepaged.c +++ b/mm/khugepaged.c @@ -410,6 +410,12 @@ static inline int hpage_collapse_test_exit(struct mm_struct *mm) return atomic_read(&mm->mm_users) == 0; } +static inline int hpage_collapse_test_exit_or_disable(struct mm_struct *mm) +{ + return hpage_collapse_test_exit(mm) || + test_bit(MMF_DISABLE_THP, &mm->flags); +} + void __khugepaged_enter(struct mm_struct *mm) { struct khugepaged_mm_slot *mm_slot; @@ -1422,7 +1428,7 @@ static void collect_mm_slot(struct khugepaged_mm_slot *mm_slot) lockdep_assert_held(&khugepaged_mm_lock); - if (hpage_collapse_test_exit(mm)) { + if (hpage_collapse_test_exit_or_disable(mm)) { /* free mm_slot */ hash_del(&slot->hash); list_del(&slot->mm_node); @@ -2360,7 +2366,7 @@ static unsigned int khugepaged_scan_mm_slot(unsigned int pages, int *result, goto breakouterloop_mmap_lock; progress++; - if (unlikely(hpage_collapse_test_exit(mm))) + if (unlikely(hpage_collapse_test_exit_or_disable(mm))) goto breakouterloop; vma_iter_init(&vmi, mm, khugepaged_scan.address); @@ -2368,7 +2374,7 @@ static unsigned int khugepaged_scan_mm_slot(unsigned int pages, int *result, unsigned long hstart, hend; cond_resched(); - if (unlikely(hpage_collapse_test_exit(mm))) { + if (unlikely(hpage_collapse_test_exit_or_disable(mm))) { progress++; break; } @@ -2390,7 +2396,7 @@ skip: bool mmap_locked = true; cond_resched(); - if (unlikely(hpage_collapse_test_exit(mm))) + if (unlikely(hpage_collapse_test_exit_or_disable(mm))) goto breakouterloop; VM_BUG_ON(khugepaged_scan.address < hstart || @@ -2408,7 +2414,7 @@ skip: fput(file); if (*result == SCAN_PTE_MAPPED_HUGEPAGE) { mmap_read_lock(mm); - if (hpage_collapse_test_exit(mm)) + if (hpage_collapse_test_exit_or_disable(mm)) goto breakouterloop; *result = collapse_pte_mapped_thp(mm, khugepaged_scan.address, false); @@ -2450,7 +2456,7 @@ breakouterloop_mmap_lock: * Release the current mm_slot if this mm is about to die, or * if we scanned all vmas of this mm. */ - if (hpage_collapse_test_exit(mm) || !vma) { + if (hpage_collapse_test_exit_or_disable(mm) || !vma) { /* * Make sure that if mm_users is reaching zero while * khugepaged runs here, khugepaged_exit will find