mirror of
https://git.kernel.org/pub/scm/linux/kernel/git/stable/linux.git
synced 2024-10-02 07:04:24 +00:00
97b27821b4
There's an inherent mismatch between memcg and writeback. The former trackes ownership per-page while the latter per-inode. This was a deliberate design decision because honoring per-page ownership in the writeback path is complicated, may lead to higher CPU and IO overheads and deemed unnecessary given that write-sharing an inode across different cgroups isn't a common use-case. Combined with inode majority-writer ownership switching, this works well enough in most cases but there are some pathological cases. For example, let's say there are two cgroups A and B which keep writing to different but confined parts of the same inode. B owns the inode and A's memory is limited far below B's. A's dirty ratio can rise enough to trigger balance_dirty_pages() sleeps but B's can be low enough to avoid triggering background writeback. A will be slowed down without a way to make writeback of the dirty pages happen. This patch implements foreign dirty recording and foreign mechanism so that when a memcg encounters a condition as above it can trigger flushes on bdi_writebacks which can clean its pages. Please see the comment on top of mem_cgroup_track_foreign_dirty_slowpath() for details. A reproducer follows. write-range.c:: #include <stdio.h> #include <stdlib.h> #include <unistd.h> #include <fcntl.h> #include <sys/types.h> static const char *usage = "write-range FILE START SIZE\n"; int main(int argc, char **argv) { int fd; unsigned long start, size, end, pos; char *endp; char buf[4096]; if (argc < 4) { fprintf(stderr, usage); return 1; } fd = open(argv[1], O_WRONLY); if (fd < 0) { perror("open"); return 1; } start = strtoul(argv[2], &endp, 0); if (*endp != '\0') { fprintf(stderr, usage); return 1; } size = strtoul(argv[3], &endp, 0); if (*endp != '\0') { fprintf(stderr, usage); return 1; } end = start + size; while (1) { for (pos = start; pos < end; ) { long bread, bwritten = 0; if (lseek(fd, pos, SEEK_SET) < 0) { perror("lseek"); return 1; } bread = read(0, buf, sizeof(buf) < end - pos ? sizeof(buf) : end - pos); if (bread < 0) { perror("read"); return 1; } if (bread == 0) return 0; while (bwritten < bread) { long this; this = write(fd, buf + bwritten, bread - bwritten); if (this < 0) { perror("write"); return 1; } bwritten += this; pos += bwritten; } } } } repro.sh:: #!/bin/bash set -e set -x sysctl -w vm.dirty_expire_centisecs=300000 sysctl -w vm.dirty_writeback_centisecs=300000 sysctl -w vm.dirtytime_expire_seconds=300000 echo 3 > /proc/sys/vm/drop_caches TEST=/sys/fs/cgroup/test A=$TEST/A B=$TEST/B mkdir -p $A $B echo "+memory +io" > $TEST/cgroup.subtree_control echo $((1<<30)) > $A/memory.high echo $((32<<30)) > $B/memory.high rm -f testfile touch testfile fallocate -l 4G testfile echo "Starting B" (echo $BASHPID > $B/cgroup.procs pv -q --rate-limit 70M < /dev/urandom | ./write-range testfile $((2<<30)) $((2<<30))) & echo "Waiting 10s to ensure B claims the testfile inode" sleep 5 sync sleep 5 sync echo "Starting A" (echo $BASHPID > $A/cgroup.procs pv < /dev/urandom | ./write-range testfile 0 $((2<<30))) v2: Added comments explaining why the specific intervals are being used. v3: Use 0 @nr when calling cgroup_writeback_by_id() to use best-effort flushing while avoding possible livelocks. v4: Use get_jiffies_64() and time_before/after64() instead of raw jiffies_64 and arthimetic comparisons as suggested by Jan. Reviewed-by: Jan Kara <jack@suse.cz> Signed-off-by: Tejun Heo <tj@kernel.org> Signed-off-by: Jens Axboe <axboe@kernel.dk> |
||
---|---|---|
.. | ||
kasan | ||
backing-dev.c | ||
balloon_compaction.c | ||
cleancache.c | ||
cma.c | ||
cma.h | ||
cma_debug.c | ||
compaction.c | ||
debug.c | ||
debug_page_ref.c | ||
dmapool.c | ||
early_ioremap.c | ||
fadvise.c | ||
failslab.c | ||
filemap.c | ||
frame_vector.c | ||
frontswap.c | ||
gup.c | ||
gup_benchmark.c | ||
highmem.c | ||
hmm.c | ||
huge_memory.c | ||
hugetlb.c | ||
hugetlb_cgroup.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 | ||
memfd.c | ||
memory-failure.c | ||
memory.c | ||
memory_hotplug.c | ||
mempolicy.c | ||
mempool.c | ||
memremap.c | ||
memtest.c | ||
migrate.c | ||
mincore.c | ||
mlock.c | ||
mm_init.c | ||
mmap.c | ||
mmu_context.c | ||
mmu_gather.c | ||
mmu_notifier.c | ||
mmzone.c | ||
mprotect.c | ||
mremap.c | ||
msync.c | ||
nommu.c | ||
oom_kill.c | ||
page-writeback.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 | ||
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 | ||
shuffle.c | ||
shuffle.h | ||
slab.c | ||
slab.h | ||
slab_common.c | ||
slob.c | ||
slub.c | ||
sparse-vmemmap.c | ||
sparse.c | ||
swap.c | ||
swap_cgroup.c | ||
swap_slots.c | ||
swap_state.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 |