859d4adc34
Workloads consisting of a large number of processes running the same program with a very large shared data segment may experience performance problems when numa balancing attempts to migrate the shared cow pages. This manifests itself with many processes or tasks in TASK_UNINTERRUPTIBLE state waiting for the shared pages to be migrated. The program listed below simulates the conditions with these results when run with 288 processes on a 144 core/8 socket machine. Average throughput Average throughput Average throughput with numa_balancing=0 with numa_balancing=1 with numa_balancing=1 without the patch with the patch --------------------- --------------------- --------------------- 2118782 2021534 2107979 Complex production environments show less variability and fewer poorly performing outliers accompanied with a smaller number of processes waiting on NUMA page migration with this patch applied. In some cases, %iowait drops from 16%-26% to 0. // SPDX-License-Identifier: GPL-2.0 /* * Copyright (c) 2017 Oracle and/or its affiliates. All rights reserved. */ #include <sys/time.h> #include <stdio.h> #include <wait.h> #include <sys/mman.h> int a[1000000] = {13}; int main(int argc, const char **argv) { int n = 0; int i; pid_t pid; int stat; int *count_array; int cpu_count = 288; long total = 0; struct timeval t1, t2 = {(argc > 1 ? atoi(argv[1]) : 10), 0}; if (argc > 2) cpu_count = atoi(argv[2]); count_array = mmap(NULL, cpu_count * sizeof(int), (PROT_READ|PROT_WRITE), (MAP_SHARED|MAP_ANONYMOUS), 0, 0); if (count_array == MAP_FAILED) { perror("mmap:"); return 0; } for (i = 0; i < cpu_count; ++i) { pid = fork(); if (pid <= 0) break; if ((i & 0xf) == 0) usleep(2); } if (pid != 0) { if (i == 0) { perror("fork:"); return 0; } for (;;) { pid = wait(&stat); if (pid < 0) break; } for (i = 0; i < cpu_count; ++i) total += count_array[i]; printf("Total %ld\n", total); munmap(count_array, cpu_count * sizeof(int)); return 0; } gettimeofday(&t1, 0); timeradd(&t1, &t2, &t1); while (timercmp(&t2, &t1, <)) { int b = 0; int j; for (j = 0; j < 1000000; j++) b += a[j]; gettimeofday(&t2, 0); n++; } count_array[i] = n; return 0; } This patch changes change_pte_range() to skip shared copy-on-write pages when called from change_prot_numa(). NOTE: change_prot_numa() is nominally called from task_numa_work() and queue_pages_test_walk(). task_numa_work() is the auto NUMA balancing path, and queue_pages_test_walk() is part of explicit NUMA policy management. However, queue_pages_test_walk() only calls change_prot_numa() when MPOL_MF_LAZY is specified and currently that is not allowed, so change_prot_numa() is only called from auto NUMA balancing. In the case of explicit NUMA policy management, shared pages are not migrated unless MPOL_MF_MOVE_ALL is specified, and MPOL_MF_MOVE_ALL depends on CAP_SYS_NICE. Currently, there is no way to pass information about MPOL_MF_MOVE_ALL to change_pte_range. This will have to be fixed if MPOL_MF_LAZY is enabled and MPOL_MF_MOVE_ALL is to be honored in lazy migration mode. task_numa_work() skips the read-only VMAs of programs and shared libraries. Link: http://lkml.kernel.org/r/1516751617-7369-1-git-send-email-henry.willard@oracle.com Signed-off-by: Henry Willard <henry.willard@oracle.com> Reviewed-by: Håkon Bugge <haakon.bugge@oracle.com> Reviewed-by: Steve Sistare <steven.sistare@oracle.com> Acked-by: Mel Gorman <mgorman@suse.de> Cc: Kate Stewart <kstewart@linuxfoundation.org> Cc: Zi Yan <zi.yan@cs.rutgers.edu> Cc: Philippe Ombredanne <pombredanne@nexb.com> Cc: Andrea Arcangeli <aarcange@redhat.com> Cc: Greg Kroah-Hartman <gregkh@linuxfoundation.org> Cc: Aneesh Kumar K.V <aneesh.kumar@linux.vnet.ibm.com> Cc: Kirill A. Shutemov <kirill.shutemov@linux.intel.com> Cc: "Jérôme Glisse" <jglisse@redhat.com> Signed-off-by: Andrew Morton <akpm@linux-foundation.org> Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org> |
||
---|---|---|
.. | ||
kasan | ||
backing-dev.c | ||
balloon_compaction.c | ||
bootmem.c | ||
cleancache.c | ||
cma_debug.c | ||
cma.c | ||
cma.h | ||
compaction.c | ||
debug_page_ref.c | ||
debug.c | ||
dmapool.c | ||
early_ioremap.c | ||
fadvise.c | ||
failslab.c | ||
filemap.c | ||
frame_vector.c | ||
frontswap.c | ||
gup_benchmark.c | ||
gup.c | ||
highmem.c | ||
hmm.c | ||
huge_memory.c | ||
hugetlb_cgroup.c | ||
hugetlb.c | ||
hwpoison-inject.c | ||
init-mm.c | ||
internal.h | ||
interval_tree.c | ||
Kconfig | ||
Kconfig.debug | ||
khugepaged.c | ||
kmemleak-test.c | ||
kmemleak.c | ||
ksm.c | ||
list_lru.c | ||
maccess.c | ||
madvise.c | ||
Makefile | ||
memblock.c | ||
memcontrol.c | ||
memory_hotplug.c | ||
memory-failure.c | ||
memory.c | ||
mempolicy.c | ||
mempool.c | ||
memtest.c | ||
migrate.c | ||
mincore.c | ||
mlock.c | ||
mm_init.c | ||
mmap.c | ||
mmu_context.c | ||
mmu_notifier.c | ||
mmzone.c | ||
mprotect.c | ||
mremap.c | ||
msync.c | ||
nobootmem.c | ||
nommu.c | ||
oom_kill.c | ||
page_alloc.c | ||
page_counter.c | ||
page_ext.c | ||
page_idle.c | ||
page_io.c | ||
page_isolation.c | ||
page_owner.c | ||
page_poison.c | ||
page_vma_mapped.c | ||
page-writeback.c | ||
pagewalk.c | ||
percpu-internal.h | ||
percpu-km.c | ||
percpu-stats.c | ||
percpu-vm.c | ||
percpu.c | ||
pgtable-generic.c | ||
process_vm_access.c | ||
quicklist.c | ||
readahead.c | ||
rmap.c | ||
rodata_test.c | ||
shmem.c | ||
slab_common.c | ||
slab.c | ||
slab.h | ||
slob.c | ||
slub.c | ||
sparse-vmemmap.c | ||
sparse.c | ||
swap_cgroup.c | ||
swap_slots.c | ||
swap_state.c | ||
swap.c | ||
swapfile.c | ||
truncate.c | ||
usercopy.c | ||
userfaultfd.c | ||
util.c | ||
vmacache.c | ||
vmalloc.c | ||
vmpressure.c | ||
vmscan.c | ||
vmstat.c | ||
workingset.c | ||
z3fold.c | ||
zbud.c | ||
zpool.c | ||
zsmalloc.c | ||
zswap.c |