On 2/3/22 11:03, Mel Gorman wrote:
> A soft lockup bug in kcompactd was reported in a private bugzilla with
> the following visible in dmesg;
>
> [15980.045209][ C33] watchdog: BUG: soft lockup - CPU#33 stuck for 26s! [kcompactd0:479]
> [16008.044989][ C33] watchdog: BUG: soft lockup - CPU#33 stuck for 52s! [kcompactd0:479]
> [16036.044768][ C33] watchdog: BUG: soft lockup - CPU#33 stuck for 78s! [kcompactd0:479]
> [16064.044548][ C33] watchdog: BUG: soft lockup - CPU#33 stuck for 104s! [kcompactd0:479]
>
> The machine had 256G of RAM with no swap and an earlier failed allocation
> indicated that node 0 where kcompactd was run was potentially
> unreclaimable;
>
> Node 0 active_anon:29355112kB inactive_anon:2913528kB active_file:0kB
> inactive_file:0kB unevictable:64kB isolated(anon):0kB isolated(file):0kB
> mapped:8kB dirty:0kB writeback:0kB shmem:26780kB shmem_thp:
> 0kB shmem_pmdmapped: 0kB anon_thp: 23480320kB writeback_tmp:0kB
> kernel_stack:2272kB pagetables:24500kB all_unreclaimable? yes
>
> Vlastimil Babka investigated a crash dump and found that a task migrating pages
> was trying to drain PCP lists;
>
> PID: 52922 TASK: ffff969f820e5000 CPU: 19 COMMAND: "kworker/u128:3"
> #0 [ffffaf4e4f4c3848] __schedule at ffffffffb840116d
> #1 [ffffaf4e4f4c3908] schedule at ffffffffb8401e81
> #2 [ffffaf4e4f4c3918] schedule_timeout at ffffffffb84066e8
> #3 [ffffaf4e4f4c3990] wait_for_completion at ffffffffb8403072
> #4 [ffffaf4e4f4c39d0] __flush_work at ffffffffb7ac3e4d
> #5 [ffffaf4e4f4c3a48] __drain_all_pages at ffffffffb7cb707c
> #6 [ffffaf4e4f4c3a80] __alloc_pages_slowpath.constprop.114 at ffffffffb7cbd9dd
> #7 [ffffaf4e4f4c3b60] __alloc_pages at ffffffffb7cbe4f5
> #8 [ffffaf4e4f4c3bc0] alloc_migration_target at ffffffffb7cf329c
> #9 [ffffaf4e4f4c3bf0] migrate_pages at ffffffffb7cf6d15
> 10 [ffffaf4e4f4c3cb0] migrate_to_node at ffffffffb7cdb5aa
> 11 [ffffaf4e4f4c3da8] do_migrate_pages at ffffffffb7cdcf26
> 12 [ffffaf4e4f4c3e88] cpuset_migrate_mm_workfn at ffffffffb7b859d2
> 13 [ffffaf4e4f4c3e98] process_one_work at ffffffffb7ac45f3
> 14 [ffffaf4e4f4c3ed8] worker_thread at ffffffffb7ac47fd
> 15 [ffffaf4e4f4c3f10] kthread at ffffffffb7acbdc6
> 16 [ffffaf4e4f4c3f50] ret_from_fork at ffffffffb7a047e2
>
> The root of the problem is that kcompact0 is not rescheduling on a CPU
> while a task that has isolated a large number of the pages from the
> LRU is waiting on kcompact0 to reschedule so the pages can be released.
> While shrink_inactive_list() only loops once around too_many_isolated,
> reclaim can continue without rescheduling if sc->skipped_deactivate ==
> 1 which could happen if there was no file LRU and the inactive anon list
> was not low.
>
> Debugged-by: Vlastimil Babka <vbabka@xxxxxxx>
> Signed-off-by: Mel Gorman <mgorman@xxxxxxx>
Fixes: d818fca1cac3 ("mm/vmscan: throttle reclaim and compaction when too
may pages are isolated")
Reviewed-by: Vlastimil Babka <vbabka@xxxxxxx>
> ---
> mm/vmscan.c | 4 +++-
> 1 file changed, 3 insertions(+), 1 deletion(-)
>
> diff --git a/mm/vmscan.c b/mm/vmscan.c
> index 090bfb605ecf..59b14e0d696c 100644
> --- a/mm/vmscan.c
> +++ b/mm/vmscan.c
> @@ -1066,8 +1066,10 @@ void reclaim_throttle(pg_data_t *pgdat, enum vmscan_throttle_state reason)
> * forward progress (e.g. journalling workqueues or kthreads).
> */
> if (!current_is_kswapd() &&
> - current->flags & (PF_IO_WORKER|PF_KTHREAD))
> + current->flags & (PF_IO_WORKER|PF_KTHREAD)) {
> + cond_resched();
> return;
> + }
>
> /*
> * These figures are pulled out of thin air.
>
