diff mbox series

dm-io: don't warn if flush takes too long time

Message ID c183dd5c-da91-c71-dccc-c923977bc77@redhat.com (mailing list archive)
State Superseded, archived
Delegated to: Mike Snitzer
Headers show
Series dm-io: don't warn if flush takes too long time | expand

Commit Message

Mikulas Patocka April 12, 2024, 12:46 p.m. UTC
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
include/linux/completion.h 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 

Signed-off-by: Mikulas Patocka <mpatocka@redhat.com>

---
 block/blk.h                |   12 ------------
 drivers/md/dm-io.c         |    2 +-
 include/linux/completion.h |   13 +++++++++++++
 3 files changed, 14 insertions(+), 13 deletions(-)

Comments

Damien Le Moal April 13, 2024, 12:51 a.m. UTC | #1
On 4/12/24 21:46, Mikulas Patocka wrote:
> 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
> include/linux/completion.h 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 
> 
> Signed-off-by: Mikulas Patocka <mpatocka@redhat.com>
> 
> ---
>  block/blk.h                |   12 ------------
>  drivers/md/dm-io.c         |    2 +-
>  include/linux/completion.h |   13 +++++++++++++
>  3 files changed, 14 insertions(+), 13 deletions(-)
> 
> Index: linux-2.6/block/blk.h
> ===================================================================
> --- linux-2.6.orig/block/blk.h	2024-03-30 20:07:03.000000000 +0100
> +++ linux-2.6/block/blk.h	2024-04-12 12:45:13.000000000 +0200
> @@ -72,18 +72,6 @@ static inline int bio_queue_enter(struct
>  	return __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 4
>  struct bio_vec *bvec_alloc(mempool_t *pool, unsigned short *nr_vecs,
>  		gfp_t gfp_mask);
> Index: linux-2.6/drivers/md/dm-io.c
> ===================================================================
> --- linux-2.6.orig/drivers/md/dm-io.c	2024-03-30 20:07:03.000000000 +0100
> +++ linux-2.6/drivers/md/dm-io.c	2024-04-12 12:42:17.000000000 +0200
> @@ -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);
> +	blk_wait_io(&sio.wait);
>  
>  	if (error_bits)
>  		*error_bits = sio.error_bits;
> Index: linux-2.6/include/linux/completion.h
> ===================================================================
> --- linux-2.6.orig/include/linux/completion.h	2023-10-31 15:31:42.000000000 +0100
> +++ linux-2.6/include/linux/completion.h	2024-04-12 12:46:08.000000000 +0200
> @@ -10,6 +10,7 @@
>   */
>  
>  #include <linux/swait.h>
> +#include <linux/sched/sysctl.h>
>  
>  /*
>   * struct completion - structure used to maintain state for a "completion"
> @@ -119,4 +120,16 @@ extern void complete(struct completion *
>  extern void complete_on_current_cpu(struct completion *x);
>  extern void complete_all(struct completion *);
>  
> +static inline void blk_wait_io(struct completion *done)

Since you move this function outside of the block layer, the "blk_" prefix seems
out of place. What about renaming this to something like
"wait_for_completion_blk_io()", or to make it clear that it is not the same as
wait_for_completion_io(), may be "wait_for_completion_long_io()" ?

> +{
> +	/* 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);
> +}
> +
>  #endif
> 
>
diff mbox series

Patch

Index: linux-2.6/block/blk.h
===================================================================
--- linux-2.6.orig/block/blk.h	2024-03-30 20:07:03.000000000 +0100
+++ linux-2.6/block/blk.h	2024-04-12 12:45:13.000000000 +0200
@@ -72,18 +72,6 @@  static inline int bio_queue_enter(struct
 	return __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 4
 struct bio_vec *bvec_alloc(mempool_t *pool, unsigned short *nr_vecs,
 		gfp_t gfp_mask);
Index: linux-2.6/drivers/md/dm-io.c
===================================================================
--- linux-2.6.orig/drivers/md/dm-io.c	2024-03-30 20:07:03.000000000 +0100
+++ linux-2.6/drivers/md/dm-io.c	2024-04-12 12:42:17.000000000 +0200
@@ -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);
+	blk_wait_io(&sio.wait);
 
 	if (error_bits)
 		*error_bits = sio.error_bits;
Index: linux-2.6/include/linux/completion.h
===================================================================
--- linux-2.6.orig/include/linux/completion.h	2023-10-31 15:31:42.000000000 +0100
+++ linux-2.6/include/linux/completion.h	2024-04-12 12:46:08.000000000 +0200
@@ -10,6 +10,7 @@ 
  */
 
 #include <linux/swait.h>
+#include <linux/sched/sysctl.h>
 
 /*
  * struct completion - structure used to maintain state for a "completion"
@@ -119,4 +120,16 @@  extern void complete(struct completion *
 extern void complete_on_current_cpu(struct completion *x);
 extern void complete_all(struct completion *);
 
+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);
+}
+
 #endif