2023-06-16 08:02:02

by Zqiang

[permalink] [raw]
Subject: [PATCH] rcuscale: Move schedule_timeout _uninterruptible to _idle in rcu_scale_writer()

The rcuscale.holdoff can be used to delay the start of rcu_scale_writer
kthread, however, if the rcuscale.holdoff is set and the timeout is greater
than the hung_task_timeout_secs, can trigger the hung-task timeout:

runqemu kvm nographic slirp qemuparams="-smp 4 -m 2048M"
bootparams="rcuscale.shutdown=0 rcuscale.holdoff=300"

[ 247.071753] INFO: task rcu_scale_write:59 blocked for more than 122 seconds.
[ 247.072529] Not tainted 6.4.0-rc1-00134-gb9ed6de8d4ff #7
[ 247.073400] "echo 0 > /proc/sys/kernel/hung_task_timeout_secs" disables this message.
[ 247.074331] task:rcu_scale_write state:D stack:30144 pid:59 ppid:2 flags:0x00004000
[ 247.075346] Call Trace:
[ 247.075660] <TASK>
[ 247.075965] __schedule+0x635/0x1280
[ 247.076448] ? __pfx___schedule+0x10/0x10
[ 247.076967] ? schedule_timeout+0x2dc/0x4d0
[ 247.077471] ? __pfx_lock_release+0x10/0x10
[ 247.078018] ? enqueue_timer+0xe2/0x220
[ 247.078522] schedule+0x84/0x120
[ 247.078957] schedule_timeout+0x2e1/0x4d0
[ 247.079447] ? __pfx_schedule_timeout+0x10/0x10
[ 247.080032] ? __pfx_rcu_scale_writer+0x10/0x10
[ 247.080591] ? __pfx_process_timeout+0x10/0x10
[ 247.081163] ? __pfx_sched_set_fifo_low+0x10/0x10
[ 247.081760] ? __pfx_rcu_scale_writer+0x10/0x10
[ 247.082287] rcu_scale_writer+0x6b1/0x7f0
[ 247.082773] ? mark_held_locks+0x29/0xa0
[ 247.083252] ? __pfx_rcu_scale_writer+0x10/0x10
[ 247.083865] ? __pfx_rcu_scale_writer+0x10/0x10
[ 247.084412] kthread+0x179/0x1c0
[ 247.084759] ? __pfx_kthread+0x10/0x10
[ 247.085098] ret_from_fork+0x2c/0x50
[ 247.085433] </TASK>

This commit therefore replaces schedule_timeout_uninterruptible() with
schedule_timeout_idle().

Signed-off-by: Zqiang <[email protected]>
---
kernel/rcu/rcuscale.c | 2 +-
1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/kernel/rcu/rcuscale.c b/kernel/rcu/rcuscale.c
index a0eae1900708..ffdb30495e3c 100644
--- a/kernel/rcu/rcuscale.c
+++ b/kernel/rcu/rcuscale.c
@@ -469,7 +469,7 @@ rcu_scale_writer(void *arg)
sched_set_fifo_low(current);

if (holdoff)
- schedule_timeout_uninterruptible(holdoff * HZ);
+ schedule_timeout_idle(holdoff * HZ);

/*
* Wait until rcu_end_inkernel_boot() is called for normal GP tests
--
2.17.1



2023-06-16 16:57:06

by Paul E. McKenney

[permalink] [raw]
Subject: Re: [PATCH] rcuscale: Move schedule_timeout _uninterruptible to _idle in rcu_scale_writer()

On Fri, Jun 16, 2023 at 03:39:26PM +0800, Zqiang wrote:
> The rcuscale.holdoff can be used to delay the start of rcu_scale_writer
> kthread, however, if the rcuscale.holdoff is set and the timeout is greater
> than the hung_task_timeout_secs, can trigger the hung-task timeout:
>
> runqemu kvm nographic slirp qemuparams="-smp 4 -m 2048M"
> bootparams="rcuscale.shutdown=0 rcuscale.holdoff=300"
>
> [ 247.071753] INFO: task rcu_scale_write:59 blocked for more than 122 seconds.
> [ 247.072529] Not tainted 6.4.0-rc1-00134-gb9ed6de8d4ff #7
> [ 247.073400] "echo 0 > /proc/sys/kernel/hung_task_timeout_secs" disables this message.
> [ 247.074331] task:rcu_scale_write state:D stack:30144 pid:59 ppid:2 flags:0x00004000
> [ 247.075346] Call Trace:
> [ 247.075660] <TASK>
> [ 247.075965] __schedule+0x635/0x1280
> [ 247.076448] ? __pfx___schedule+0x10/0x10
> [ 247.076967] ? schedule_timeout+0x2dc/0x4d0
> [ 247.077471] ? __pfx_lock_release+0x10/0x10
> [ 247.078018] ? enqueue_timer+0xe2/0x220
> [ 247.078522] schedule+0x84/0x120
> [ 247.078957] schedule_timeout+0x2e1/0x4d0
> [ 247.079447] ? __pfx_schedule_timeout+0x10/0x10
> [ 247.080032] ? __pfx_rcu_scale_writer+0x10/0x10
> [ 247.080591] ? __pfx_process_timeout+0x10/0x10
> [ 247.081163] ? __pfx_sched_set_fifo_low+0x10/0x10
> [ 247.081760] ? __pfx_rcu_scale_writer+0x10/0x10
> [ 247.082287] rcu_scale_writer+0x6b1/0x7f0
> [ 247.082773] ? mark_held_locks+0x29/0xa0
> [ 247.083252] ? __pfx_rcu_scale_writer+0x10/0x10
> [ 247.083865] ? __pfx_rcu_scale_writer+0x10/0x10
> [ 247.084412] kthread+0x179/0x1c0
> [ 247.084759] ? __pfx_kthread+0x10/0x10
> [ 247.085098] ret_from_fork+0x2c/0x50
> [ 247.085433] </TASK>
>
> This commit therefore replaces schedule_timeout_uninterruptible() with
> schedule_timeout_idle().
>
> Signed-off-by: Zqiang <[email protected]>

Good catch, queued, thank you!

Thanx, Paul

> ---
> kernel/rcu/rcuscale.c | 2 +-
> 1 file changed, 1 insertion(+), 1 deletion(-)
>
> diff --git a/kernel/rcu/rcuscale.c b/kernel/rcu/rcuscale.c
> index a0eae1900708..ffdb30495e3c 100644
> --- a/kernel/rcu/rcuscale.c
> +++ b/kernel/rcu/rcuscale.c
> @@ -469,7 +469,7 @@ rcu_scale_writer(void *arg)
> sched_set_fifo_low(current);
>
> if (holdoff)
> - schedule_timeout_uninterruptible(holdoff * HZ);
> + schedule_timeout_idle(holdoff * HZ);
>
> /*
> * Wait until rcu_end_inkernel_boot() is called for normal GP tests
> --
> 2.17.1
>