On Wed, Feb 02, 2022 at 03:30:32PM -0500, Waiman Long wrote: > v4: > - Take rcu_read_lock() when memcg is being accessed as suggested by > Michal. > - Make print_page_owner_memcg() return the new offset into the buffer > and put CONFIG_MEMCG block inside as suggested by Mike. > - Directly use TASK_COMM_LEN as length of name buffer as suggested by > Roman. > > v3: > - Add unlikely() to patch 1 and clarify that -1 will not be returned. > - Use a helper function to print out memcg information in patch 3. > - Add a new patch 4 to store task command name in page_owner > structure. > > v2: > - Remove the SNPRINTF() macro as suggested by Ira and use scnprintf() > instead to remove some buffer overrun checks. > - Add a patch to optimize vscnprintf with a size parameter of 0. > > While debugging the constant increase in percpu memory consumption on > a system that spawned large number of containers, it was found that a > lot of offline mem_cgroup structures remained in place without being > freed. Further investigation indicated that those mem_cgroup structures > were pinned by some pages. > > In order to find out what those pages are, the existing page_owner > debugging tool is extended to show memory cgroup information and whether > those memcgs are offline or not. With the enhanced page_owner tool, > the following is a typical page that pinned the mem_cgroup structure > in my test case: > > Page allocated via order 0, mask 0x1100cca(GFP_HIGHUSER_MOVABLE), pid 162970 (podman), ts 1097761405537 ns, free_ts 1097760838089 ns > PFN 1925700 type Movable Block 3761 type Movable Flags 0x17ffffc00c001c(uptodate|dirty|lru|reclaim|swapbacked|node=0|zone=2|lastcpupid=0x1fffff) > prep_new_page+0xac/0xe0 > get_page_from_freelist+0x1327/0x14d0 > __alloc_pages+0x191/0x340 > alloc_pages_vma+0x84/0x250 > shmem_alloc_page+0x3f/0x90 > shmem_alloc_and_acct_page+0x76/0x1c0 > shmem_getpage_gfp+0x281/0x940 > shmem_write_begin+0x36/0xe0 > generic_perform_write+0xed/0x1d0 > __generic_file_write_iter+0xdc/0x1b0 > generic_file_write_iter+0x5d/0xb0 > new_sync_write+0x11f/0x1b0 > vfs_write+0x1ba/0x2a0 > ksys_write+0x59/0xd0 > do_syscall_64+0x37/0x80 > entry_SYSCALL_64_after_hwframe+0x44/0xae > Charged to offline memcg libpod-conmon-15e4f9c758422306b73b2dd99f9d50a5ea53cbb16b4a13a2c2308a4253cc0ec8. > > So the page was not freed because it was part of a shmem segment. That > is useful information that can help users to diagnose similar problems. > > With cgroup v1, /proc/cgroups can be read to find out the total number > of memory cgroups (online + offline). With cgroup v2, the cgroup.stat of > the root cgroup can be read to find the number of dying cgroups (most > likely pinned by dying memcgs). > > The page_owner feature is not supposed to be enabled for production > system due to its memory overhead. However, if it is suspected that > dying memcgs are increasing over time, a test environment with page_owner > enabled can then be set up with appropriate workload for further analysis > on what may be causing the increasing number of dying memcgs. > > Waiman Long (4): > lib/vsprintf: Avoid redundant work with 0 size > mm/page_owner: Use scnprintf() to avoid excessive buffer overrun check > mm/page_owner: Print memcg information > mm/page_owner: Record task command name > > lib/vsprintf.c | 8 +++--- > mm/page_owner.c | 70 ++++++++++++++++++++++++++++++++++++++----------- > 2 files changed, 60 insertions(+), 18 deletions(-) > > -- > 2.27.0 > Thank you, Waiman. Acked-by: Rafael Aquini <aquini@xxxxxxxxxx>
