From: Wanpeng Li <[email protected]>
I use several dd processes to write a slow SD card
dd if=/dev/sda1 of=/dev/sdc4 bs=1M count=4000
and several sync commands(maybe > 10),dmesg show this:
[ 366.888741] INFO: task sync:3518 blocked for more than 120 seconds.
[ 366.888742] "echo 0 > /proc/sys/kernel/hung_task_timeout_secs" disables this message.
[ 366.888746] sync D 00000201 0 3518 3462 0x00000000
[ 366.888752] dcde5e54 00000082 00000000 00000201 00000000 c180d220 c1933d00 c1933d00
[ 366.888758] 614a7ae7 00000023 f6bc0d00 ebecb280 c180d220 f6bc0d6c f04acbfc 00000000
[ 366.888786] f6bc0d6c dcde5e2c 00000023 f6bc0d44 00000000 00000000 ebd8b2b4 dcde5e6c
[ 366.888788] Call Trace:
[ 366.888792] [<c107a0ee>] ? enqueue_entity+0xee/0x5a0
[ 366.888795] [<c15abc83>] schedule+0x23/0x60
[ 366.888798] [<c15aa5ad>] schedule_timeout+0x22d/0x2a0
[ 366.888801] [<c1071ce2>] ? check_preempt_curr+0x72/0x90
[ 366.888804] [<c1071d28>] ? ttwu_do_wakeup+0x28/0x130
[ 366.888807] [<c1037f28>] ? default_spin_lock_flags+0x8/0x10
[ 366.888810] [<c15acaad>] ? _raw_spin_lock_irqsave+0x2d/0x40
[ 366.888813] [<c15abb17>] wait_for_common+0xa7/0x110
[ 366.888816] [<c1074690>] ? try_to_wake_up+0x220/0x220
[ 366.888819] [<c15abc57>] wait_for_completion+0x17/0x20
[ 366.888822] [<c116ad80>] writeback_inodes_sb_nr+0x70/0x90
[ 366.888825] [<c116af75>] writeback_inodes_sb+0x25/0x30
[ 366.888828] [<c117159f>] __sync_filesystem+0x4f/0x90
[ 366.888831] [<c11715f7>] sync_one_sb+0x17/0x20
[ 366.888834] [<c114c430>] iterate_supers+0xc0/0xd0
[ 366.888837] [<c11715e0>] ? __sync_filesystem+0x90/0x90
[ 366.888840] [<c117167b>] sys_sync+0x2b/0x60
[ 366.888842] [<c15b385f>] sysenter_do_call+0x12/0x28
Too many similar messages flood the logs. So I use a present method to
fix this issue.
------------------------------------------
Author: Mark Lord <[email protected]>
Date: Fri Sep 24 09:51:13 2010 -0400
block: Prevent hang_check firing during long I/O
------------------------------------------
Signed-off-by: Wanpeng Li <[email protected]>
---
fs/fs-writeback.c | 8 +++++++-
1 file changed, 7 insertions(+), 1 deletion(-)
diff --git a/fs/fs-writeback.c b/fs/fs-writeback.c
index f2d0109..5d403a1 100644
--- a/fs/fs-writeback.c
+++ b/fs/fs-writeback.c
@@ -1300,6 +1300,7 @@ void writeback_inodes_sb_nr(struct super_block *sb,
enum wb_reason reason)
{
DECLARE_COMPLETION_ONSTACK(done);
+ unsigned long hangcheck;
struct wb_writeback_work work = {
.sb = sb,
.sync_mode = WB_SYNC_NONE,
@@ -1311,7 +1312,12 @@ void writeback_inodes_sb_nr(struct super_block *sb,
WARN_ON(!rwsem_is_locked(&sb->s_umount));
bdi_queue_work(sb->s_bdi, &work);
- wait_for_completion(&done);
+ hangcheck = sysctl_hung_task_timeout_secs;
+ if (hangcheck)
+ while (!wait_for_completion_timeout(&done, HZ/2))
+ ;
+ else
+ wait_for_completion(&done);
}
EXPORT_SYMBOL(writeback_inodes_sb_nr);
--
1.7.9.5
On Wed, Jun 13, 2012 at 08:52:53AM +0800, Wanpeng Li wrote:
> From: Wanpeng Li <[email protected]>
>
> I use several dd processes to write a slow SD card
> dd if=/dev/sda1 of=/dev/sdc4 bs=1M count=4000
> and several sync commands(maybe > 10),dmesg show this:
>
> [ 366.888741] INFO: task sync:3518 blocked for more than 120 seconds.
> [ 366.888742] "echo 0 > /proc/sys/kernel/hung_task_timeout_secs" disables this message.
> [ 366.888746] sync D 00000201 0 3518 3462 0x00000000
> Too many similar messages flood the logs. So I use a present method to
> fix this issue.
> ------------------------------------------
> Author: Mark Lord <[email protected]>
> Date: Fri Sep 24 09:51:13 2010 -0400
>
> block: Prevent hang_check firing during long I/O
> ------------------------------------------
>
> Signed-off-by: Wanpeng Li <[email protected]>
Yeah that's also what I'd like to do. So you've tested it?
> ---
> fs/fs-writeback.c | 8 +++++++-
> 1 file changed, 7 insertions(+), 1 deletion(-)
>
> diff --git a/fs/fs-writeback.c b/fs/fs-writeback.c
> index f2d0109..5d403a1 100644
> --- a/fs/fs-writeback.c
> +++ b/fs/fs-writeback.c
> @@ -1300,6 +1300,7 @@ void writeback_inodes_sb_nr(struct super_block *sb,
> enum wb_reason reason)
> {
> DECLARE_COMPLETION_ONSTACK(done);
> + unsigned long hangcheck;
> struct wb_writeback_work work = {
> .sb = sb,
> .sync_mode = WB_SYNC_NONE,
> @@ -1311,7 +1312,12 @@ void writeback_inodes_sb_nr(struct super_block *sb,
>
> WARN_ON(!rwsem_is_locked(&sb->s_umount));
> bdi_queue_work(sb->s_bdi, &work);
> - wait_for_completion(&done);
> + hangcheck = sysctl_hung_task_timeout_secs;
> + if (hangcheck)
The hangcheck variable looks redundant.
> + while (!wait_for_completion_timeout(&done, HZ/2))
> + ;
> + else
> + wait_for_completion(&done);
> }
> EXPORT_SYMBOL(writeback_inodes_sb_nr);
>
> --
> 1.7.9.5
On Wed, Jun 13, 2012 at 08:59:46AM +0800, Fengguang Wu wrote:
>On Wed, Jun 13, 2012 at 08:52:53AM +0800, Wanpeng Li wrote:
>> From: Wanpeng Li <[email protected]>
>>
>> I use several dd processes to write a slow SD card
>> dd if=/dev/sda1 of=/dev/sdc4 bs=1M count=4000
>> and several sync commands(maybe > 10),dmesg show this:
>>
>> [ 366.888741] INFO: task sync:3518 blocked for more than 120 seconds.
>> [ 366.888742] "echo 0 > /proc/sys/kernel/hung_task_timeout_secs" disables this message.
>> [ 366.888746] sync D 00000201 0 3518 3462 0x00000000
>
>> Too many similar messages flood the logs. So I use a present method to
>> fix this issue.
>> ------------------------------------------
>> Author: Mark Lord <[email protected]>
>> Date: Fri Sep 24 09:51:13 2010 -0400
>>
>> block: Prevent hang_check firing during long I/O
>> ------------------------------------------
>>
>> Signed-off-by: Wanpeng Li <[email protected]>
>
>Yeah that's also what I'd like to do. So you've tested it?
Not yet, I will test it today.
>
>> ---
>> fs/fs-writeback.c | 8 +++++++-
>> 1 file changed, 7 insertions(+), 1 deletion(-)
>>
>> diff --git a/fs/fs-writeback.c b/fs/fs-writeback.c
>> index f2d0109..5d403a1 100644
>> --- a/fs/fs-writeback.c
>> +++ b/fs/fs-writeback.c
>> @@ -1300,6 +1300,7 @@ void writeback_inodes_sb_nr(struct super_block *sb,
>> enum wb_reason reason)
>> {
>> DECLARE_COMPLETION_ONSTACK(done);
>> + unsigned long hangcheck;
>> struct wb_writeback_work work = {
>> .sb = sb,
>> .sync_mode = WB_SYNC_NONE,
>> @@ -1311,7 +1312,12 @@ void writeback_inodes_sb_nr(struct super_block *sb,
>>
>> WARN_ON(!rwsem_is_locked(&sb->s_umount));
>> bdi_queue_work(sb->s_bdi, &work);
>> - wait_for_completion(&done);
>> + hangcheck = sysctl_hung_task_timeout_secs;
>> + if (hangcheck)
>
>The hangcheck variable looks redundant.
if sysctl_hung_task_timeout_secs is equal to ZERO, it means infinite
timeout -- no checking done. So I think wait_for_completion_timeout
makes no sense this time.
Regards,
Wanpeng Li
>
>> + while (!wait_for_completion_timeout(&done, HZ/2))
>> + ;
>> + else
>> + wait_for_completion(&done);
>> }
>> EXPORT_SYMBOL(writeback_inodes_sb_nr);
>>
>> --
>> 1.7.9.5
> >> @@ -1311,7 +1312,12 @@ void writeback_inodes_sb_nr(struct super_block *sb,
> >>
> >> WARN_ON(!rwsem_is_locked(&sb->s_umount));
> >> bdi_queue_work(sb->s_bdi, &work);
> >> - wait_for_completion(&done);
> >> + hangcheck = sysctl_hung_task_timeout_secs;
> >> + if (hangcheck)
> >
> >The hangcheck variable looks redundant.
>
> if sysctl_hung_task_timeout_secs is equal to ZERO, it means infinite
> timeout -- no checking done. So I think wait_for_completion_timeout
> makes no sense this time.
I mean, you can test sysctl_hung_task_timeout_secs directly?
It's a one shot test anyway.
> >> + while (!wait_for_completion_timeout(&done, HZ/2))
> >> + ;
> >> + else
> >> + wait_for_completion(&done);
> >> }
> >> EXPORT_SYMBOL(writeback_inodes_sb_nr);
> >>
> >> --
> >> 1.7.9.5
On Wed, Jun 13, 2012 at 09:18:17AM +0800, Fengguang Wu wrote:
>> >> @@ -1311,7 +1312,12 @@ void writeback_inodes_sb_nr(struct super_block *sb,
>> >>
>> >> WARN_ON(!rwsem_is_locked(&sb->s_umount));
>> >> bdi_queue_work(sb->s_bdi, &work);
>> >> - wait_for_completion(&done);
>> >> + hangcheck = sysctl_hung_task_timeout_secs;
>> >> + if (hangcheck)
>> >
>> >The hangcheck variable looks redundant.
>>
>> if sysctl_hung_task_timeout_secs is equal to ZERO, it means
>> timeout -- no checking done. So I think wait_for_completion_timeout
>> makes no sense this time.
>
>I mean, you can test sysctl_hung_task_timeout_secs directly?
>It's a one shot test anyway.
/*
* Zero means infinite timeout - no checking done:
*/
unsigned long __read_mostly sysctl_hung_task_timeout_secs = CONFIG_DEFAULT_HUNG_TASK_TIMEOUT;
The comment in kernel/hung_task.c says "Zero means infinite timeout - no
cheking done". Maybe I can just test if this time alarm doesn't flood my
logs. Do you have more suggestion. :-)
Regards,
Wanpeng Li
>
>> >> + while (!wait_for_completion_timeout(&done, HZ/2))
>> >> + ;
>> >> + else
>> >> + wait_for_completion(&done);
>> >> }
>> >> EXPORT_SYMBOL(writeback_inodes_sb_nr);
>> >>
>> >> --
>> >> 1.7.9.5