dm-io: don't warn if flush takes too long time
Subsystems (3)
Mikulas Patocka
maintainerPATCH v4 1/1 dm-io: don't warn if flush takes too long time
There was reported hang warning when using dm-integrity on the top of loop device on XFS on a rotational disk. The warning was triggered because flush on the loop device was too slow.
There's no easy way to reduce the latency, so I made a patch that shuts the warning up.
There's already a function blk_wait_io that avoids the hung task warning. This commit moves this function from block/blk.h to kernel/sched/completion.c, renames it to wait_for_completion_long_io (because it is not dependent on the block layer at all) and uses it in dm-io instead of wait_for_completion_io.
[ 1352.586981] INFO: task kworker/1:2:14820 blocked for more than 120 seconds. [ 1352.593951] Not tainted 4.18.0-552.el8_10.x86_64 #1 [ 1352.599358] "echo 0 > /proc/sys/kernel/hung_task_timeout_secs" disables this message. [ 1352.607202] Call Trace: [ 1352.609670] __schedule+0x2d1/0x870 [ 1352.613173] ? update_load_avg+0x7e/0x710 [ 1352.617193] ? update_load_avg+0x7e/0x710 [ 1352.621214] schedule+0x55/0xf0 [ 1352.624371] schedule_timeout+0x281/0x320 [ 1352.628393] ? __schedule+0x2d9/0x870 [ 1352.632065] io_schedule_timeout+0x19/0x40 [ 1352.636176] wait_for_completion_io+0x96/0x100 [ 1352.640639] sync_io+0xcc/0x120 [dm_mod] [ 1352.644592] dm_io+0x209/0x230 [dm_mod] [ 1352.648436] ? bit_wait_timeout+0xa0/0xa0 [ 1352.652461] ? vm_next_page+0x20/0x20 [dm_mod] [ 1352.656924] ? km_get_page+0x60/0x60 [dm_mod] [ 1352.661298] dm_bufio_issue_flush+0xa0/0xd0 [dm_bufio] [ 1352.666448] dm_bufio_write_dirty_buffers+0x1a0/0x1e0 [dm_bufio] [ 1352.672462] dm_integrity_flush_buffers+0x32/0x140 [dm_integrity] [ 1352.678567] ? lock_timer_base+0x67/0x90 [ 1352.682505] ? __timer_delete.part.36+0x5c/0x90 [ 1352.687050] integrity_commit+0x31a/0x330 [dm_integrity] [ 1352.692368] ? __switch_to+0x10c/0x430 [ 1352.696131] process_one_work+0x1d3/0x390 [ 1352.700152] ? process_one_work+0x390/0x390 [ 1352.704348] worker_thread+0x30/0x390 [ 1352.708019] ? process_one_work+0x390/0x390 [ 1352.712214] kthread+0x134/0x150 [ 1352.715459] ? set_kthread_struct+0x50/0x50 [ 1352.719659] ret_from_fork+0x1f/0x40
--- block/bio.c | 2 +- block/blk-mq.c | 2 +- block/blk.h | 12 ------------ drivers/md/dm-io.c | 2 +- include/linux/completion.h | 1 + kernel/sched/completion.c | 20 ++++++++++++++++++++ 6 files changed, 24 insertions(+), 15 deletions(-)
block/blk.h +0 -12
@@ -72,18 +72,6 @@ static inline int bio_queue_enter(structreturn __bio_queue_enter (q, bio); } -static inline void blk_wait_io (struct completion *done) -{ -/* Prevent hang_check timer from firing at us during very long I/O */ -unsigned long timeout = sysctl_hung_task_timeout_secs *HZ /2 ; - -if (timeout) -while (!wait_for_completion_io_timeout (done, timeout)) - ; -else -wait_for_completion_io (done); -} -#define BIO_INLINE_VECS 4struct bio_vec *bvec_alloc (mempool_t *pool,unsigned short *nr_vecs,gfp_t gfp_mask);
drivers/md/dm-io.c +1 -1
@@ -450,7 +450,7 @@ static int sync_io(struct dm_io_client *dispatch_io (opf, num_regions, where, dp, io,1 , ioprio); -wait_for_completion_io (&sio.wait); +wait_for_completion_long_io (&sio.wait);if (error_bits) *error_bits = sio.error_bits;
include/linux/completion.h +1 -0
@@ -112,6 +112,7 @@ extern long wait_for_completion_interrup struct completion *x, unsigned long timeout);extern long wait_for_completion_killable_timeout (struct completion *x,unsigned long timeout); +extern void wait_for_completion_long_io (struct completion *x);extern bool try_wait_for_completion (struct completion *x);extern bool completion_done (struct completion *x);
block/bio.c +1 -1
@@ -1378,7 +1378,7 @@ int submit_bio_wait(struct bio *bio) bio->bi_end_io = submit_bio_wait_endio; bio->bi_opf |=REQ_SYNC ;submit_bio (bio); -blk_wait_io (&done); +wait_for_completion_long_io (&done);return blk_status_to_errno (bio->bi_status); }
block/blk-mq.c +1 -1
@@ -1407,7 +1407,7 @@ blk_status_t blk_execute_rq(struct requeif (blk_rq_is_poll (rq))blk_rq_poll_completion (rq, &wait.done);else -blk_wait_io (&wait.done); +wait_for_completion_long_io (&wait.done);return wait.ret; }
kernel/sched/completion.c +20 -0
@@ -290,6 +290,26 @@ wait_for_completion_killable_timeout(strEXPORT_SYMBOL (wait_for_completion_killable_timeout);/** +* wait_for_completion_long_io - waits for completion of a task +* @x: holds the state of this particular completion +* +* This is like wait_for_completion_io, but it doesn't warn if the wait takes +* too long. +*/ +void wait_for_completion_long_io (struct completion *x) +{ +/* Prevent hang_check timer from firing at us during very long I/O */ +unsigned long timeout = sysctl_hung_task_timeout_secs *HZ /2 ; + +if (timeout) +while (!wait_for_completion_io_timeout (x, timeout)) + ; +else +wait_for_completion_io (x); +} +EXPORT_SYMBOL (wait_for_completion_long_io); + +/** * try_wait_for_completion - try to decrement a completion without blocking * @x: completion structure *
Jens Axboe
maintainerQuoted 4 lines · Mikulas Patocka
There was reported hang warning when using dm-integrity on the top of loop device on XFS on a rotational disk. The warning was triggered because flush on the loop device was too slow.
Quoted 8 lines
There's no easy way to reduce the latency, so I made a patch that shuts the warning up.
There's already a function
blk_wait_iothat avoids the hung task warning. This commit moves this function fromblock/blk.htokernel/sched/completion.c, renames it towait_for_completion_long_io(because it is not dependent on the block layer at all) and uses it in dm-io instead ofwait_for_completion_io.
Looks good to me, though I'd probably split out that dm change as it's a new addition where the other parts are strictly mechanical (moving the helper to where it belongs, and using it where we already do it).
Signature · 1 line
Jens Axboe