Re: RCU CPU stall console spews leads to soft lockup disabled is reasonable ?

2015-01-21 Thread Paul E. McKenney
On Thu, Jan 22, 2015 at 11:08:11AM +0800, Zhang Zhen wrote: > On 2015/1/22 4:06, Paul E. McKenney wrote: > > On Wed, Jan 21, 2015 at 10:10:51AM -0500, Don Zickus wrote: > >> On Wed, Jan 21, 2015 at 10:26:27AM +0800, Zhang Zhen wrote: > This may not cause other problems but what happens if you

Re: RCU CPU stall console spews leads to soft lockup disabled is reasonable ?

2015-01-21 Thread Zhang Zhen
On 2015/1/22 4:06, Paul E. McKenney wrote: > On Wed, Jan 21, 2015 at 10:10:51AM -0500, Don Zickus wrote: >> On Wed, Jan 21, 2015 at 10:26:27AM +0800, Zhang Zhen wrote: This may not cause other problems but what happens if you comment out the 'touch_softlockup_watchdog' from the

Re: RCU CPU stall console spews leads to soft lockup disabled is reasonable ?

2015-01-21 Thread Paul E. McKenney
On Wed, Jan 21, 2015 at 10:10:51AM -0500, Don Zickus wrote: > On Wed, Jan 21, 2015 at 10:26:27AM +0800, Zhang Zhen wrote: > > > This may not cause other problems but what happens if you comment out the > > > 'touch_softlockup_watchdog' from the touch_nmi_watchdog function like > > > below (based

Re: RCU CPU stall console spews leads to soft lockup disabled is reasonable ?

2015-01-21 Thread Paul E. McKenney
On Wed, Jan 21, 2015 at 07:11:51PM +0800, Zhang Zhen wrote: > On 2015/1/21 18:16, Paul E. McKenney wrote: > > On Wed, Jan 21, 2015 at 05:05:50PM +0800, Zhang Zhen wrote: > >> On 2015/1/21 15:02, Paul E. McKenney wrote: > >>> On Wed, Jan 21, 2015 at 02:54:05PM +0800, Zhang Zhen wrote: > On

Re: RCU CPU stall console spews leads to soft lockup disabled is reasonable ?

2015-01-21 Thread Don Zickus
On Wed, Jan 21, 2015 at 10:26:27AM +0800, Zhang Zhen wrote: > > This may not cause other problems but what happens if you comment out the > > 'touch_softlockup_watchdog' from the touch_nmi_watchdog function like > > below (based on latest upstream cb59670870)? > > > > The idea is that console

Re: RCU CPU stall console spews leads to soft lockup disabled is reasonable ?

2015-01-21 Thread Zhang Zhen
On 2015/1/21 18:16, Paul E. McKenney wrote: > On Wed, Jan 21, 2015 at 05:05:50PM +0800, Zhang Zhen wrote: >> On 2015/1/21 15:02, Paul E. McKenney wrote: >>> On Wed, Jan 21, 2015 at 02:54:05PM +0800, Zhang Zhen wrote: On 2015/1/21 11:13, Zhang Zhen wrote: > On 2015/1/21 10:26, Zhang Zhen

Re: RCU CPU stall console spews leads to soft lockup disabled is reasonable ?

2015-01-21 Thread Paul E. McKenney
On Wed, Jan 21, 2015 at 05:05:50PM +0800, Zhang Zhen wrote: > On 2015/1/21 15:02, Paul E. McKenney wrote: > > On Wed, Jan 21, 2015 at 02:54:05PM +0800, Zhang Zhen wrote: > >> On 2015/1/21 11:13, Zhang Zhen wrote: > >>> On 2015/1/21 10:26, Zhang Zhen wrote: > On 2015/1/20 23:25, Don Zickus

Re: RCU CPU stall console spews leads to soft lockup disabled is reasonable ?

2015-01-21 Thread Zhang Zhen
On 2015/1/21 15:02, Paul E. McKenney wrote: > On Wed, Jan 21, 2015 at 02:54:05PM +0800, Zhang Zhen wrote: >> On 2015/1/21 11:13, Zhang Zhen wrote: >>> On 2015/1/21 10:26, Zhang Zhen wrote: On 2015/1/20 23:25, Don Zickus wrote: > > [ . . . ] > >>> Sorry, i made a mistake, the log above is

Re: RCU CPU stall console spews leads to soft lockup disabled is reasonable ?

2015-01-21 Thread Paul E. McKenney
On Wed, Jan 21, 2015 at 07:11:51PM +0800, Zhang Zhen wrote: On 2015/1/21 18:16, Paul E. McKenney wrote: On Wed, Jan 21, 2015 at 05:05:50PM +0800, Zhang Zhen wrote: On 2015/1/21 15:02, Paul E. McKenney wrote: On Wed, Jan 21, 2015 at 02:54:05PM +0800, Zhang Zhen wrote: On 2015/1/21 11:13,

Re: RCU CPU stall console spews leads to soft lockup disabled is reasonable ?

2015-01-21 Thread Paul E. McKenney
On Wed, Jan 21, 2015 at 10:10:51AM -0500, Don Zickus wrote: On Wed, Jan 21, 2015 at 10:26:27AM +0800, Zhang Zhen wrote: This may not cause other problems but what happens if you comment out the 'touch_softlockup_watchdog' from the touch_nmi_watchdog function like below (based on latest

Re: RCU CPU stall console spews leads to soft lockup disabled is reasonable ?

2015-01-21 Thread Paul E. McKenney
On Thu, Jan 22, 2015 at 11:08:11AM +0800, Zhang Zhen wrote: On 2015/1/22 4:06, Paul E. McKenney wrote: On Wed, Jan 21, 2015 at 10:10:51AM -0500, Don Zickus wrote: On Wed, Jan 21, 2015 at 10:26:27AM +0800, Zhang Zhen wrote: This may not cause other problems but what happens if you comment

Re: RCU CPU stall console spews leads to soft lockup disabled is reasonable ?

2015-01-21 Thread Zhang Zhen
On 2015/1/22 4:06, Paul E. McKenney wrote: On Wed, Jan 21, 2015 at 10:10:51AM -0500, Don Zickus wrote: On Wed, Jan 21, 2015 at 10:26:27AM +0800, Zhang Zhen wrote: This may not cause other problems but what happens if you comment out the 'touch_softlockup_watchdog' from the touch_nmi_watchdog

Re: RCU CPU stall console spews leads to soft lockup disabled is reasonable ?

2015-01-21 Thread Zhang Zhen
On 2015/1/21 18:16, Paul E. McKenney wrote: On Wed, Jan 21, 2015 at 05:05:50PM +0800, Zhang Zhen wrote: On 2015/1/21 15:02, Paul E. McKenney wrote: On Wed, Jan 21, 2015 at 02:54:05PM +0800, Zhang Zhen wrote: On 2015/1/21 11:13, Zhang Zhen wrote: On 2015/1/21 10:26, Zhang Zhen wrote: On

Re: RCU CPU stall console spews leads to soft lockup disabled is reasonable ?

2015-01-21 Thread Paul E. McKenney
On Wed, Jan 21, 2015 at 05:05:50PM +0800, Zhang Zhen wrote: On 2015/1/21 15:02, Paul E. McKenney wrote: On Wed, Jan 21, 2015 at 02:54:05PM +0800, Zhang Zhen wrote: On 2015/1/21 11:13, Zhang Zhen wrote: On 2015/1/21 10:26, Zhang Zhen wrote: On 2015/1/20 23:25, Don Zickus wrote: [ . .

Re: RCU CPU stall console spews leads to soft lockup disabled is reasonable ?

2015-01-21 Thread Zhang Zhen
On 2015/1/21 15:02, Paul E. McKenney wrote: On Wed, Jan 21, 2015 at 02:54:05PM +0800, Zhang Zhen wrote: On 2015/1/21 11:13, Zhang Zhen wrote: On 2015/1/21 10:26, Zhang Zhen wrote: On 2015/1/20 23:25, Don Zickus wrote: [ . . . ] Sorry, i made a mistake, the log above is based on v3.10.63.

Re: RCU CPU stall console spews leads to soft lockup disabled is reasonable ?

2015-01-21 Thread Don Zickus
On Wed, Jan 21, 2015 at 10:26:27AM +0800, Zhang Zhen wrote: This may not cause other problems but what happens if you comment out the 'touch_softlockup_watchdog' from the touch_nmi_watchdog function like below (based on latest upstream cb59670870)? The idea is that console printing for

Re: RCU CPU stall console spews leads to soft lockup disabled is reasonable ?

2015-01-20 Thread Zhang Zhen
On 2015/1/21 15:02, Paul E. McKenney wrote: > On Wed, Jan 21, 2015 at 02:54:05PM +0800, Zhang Zhen wrote: >> On 2015/1/21 11:13, Zhang Zhen wrote: >>> On 2015/1/21 10:26, Zhang Zhen wrote: On 2015/1/20 23:25, Don Zickus wrote: > > [ . . . ] > >>> Sorry, i made a mistake, the log above is

Re: RCU CPU stall console spews leads to soft lockup disabled is reasonable ?

2015-01-20 Thread Paul E. McKenney
On Wed, Jan 21, 2015 at 02:54:05PM +0800, Zhang Zhen wrote: > On 2015/1/21 11:13, Zhang Zhen wrote: > > On 2015/1/21 10:26, Zhang Zhen wrote: > >> On 2015/1/20 23:25, Don Zickus wrote: [ . . . ] > > Sorry, i made a mistake, the log above is based on v3.10.63. > > I have tested the latest

Re: RCU CPU stall console spews leads to soft lockup disabled is reasonable ?

2015-01-20 Thread Zhang Zhen
On 2015/1/21 11:13, Zhang Zhen wrote: > On 2015/1/21 10:26, Zhang Zhen wrote: >> On 2015/1/20 23:25, Don Zickus wrote: >>> On Tue, Jan 20, 2015 at 11:09:19AM +0800, Zhang Zhen wrote: > Of course back then, touch_nmi_watchdog touched all cpus. So a problem > like this was masked. I

Re: RCU CPU stall console spews leads to soft lockup disabled is reasonable ?

2015-01-20 Thread Zhang Zhen
On 2015/1/21 10:26, Zhang Zhen wrote: > On 2015/1/20 23:25, Don Zickus wrote: >> On Tue, Jan 20, 2015 at 11:09:19AM +0800, Zhang Zhen wrote: >>> Of course back then, touch_nmi_watchdog touched all cpus. So a problem like this was masked. I believe this upstream commit 62572e29bc53,

Re: RCU CPU stall console spews leads to soft lockup disabled is reasonable ?

2015-01-20 Thread Zhang Zhen
On 2015/1/20 23:25, Don Zickus wrote: > On Tue, Jan 20, 2015 at 11:09:19AM +0800, Zhang Zhen wrote: >> >>> Of course back then, touch_nmi_watchdog touched all cpus. So a problem >>> like this was masked. I believe this upstream commit 62572e29bc53, solved >>> the problem. >> >> Thanks for your

Re: RCU CPU stall console spews leads to soft lockup disabled is reasonable ?

2015-01-20 Thread Don Zickus
On Tue, Jan 20, 2015 at 11:09:19AM +0800, Zhang Zhen wrote: > > > Of course back then, touch_nmi_watchdog touched all cpus. So a problem > > like this was masked. I believe this upstream commit 62572e29bc53, solved > > the problem. > > Thanks for your suggestion. > > Commit 62572e29bc53

Re: RCU CPU stall console spews leads to soft lockup disabled is reasonable ?

2015-01-20 Thread Don Zickus
On Tue, Jan 20, 2015 at 11:09:19AM +0800, Zhang Zhen wrote: Of course back then, touch_nmi_watchdog touched all cpus. So a problem like this was masked. I believe this upstream commit 62572e29bc53, solved the problem. Thanks for your suggestion. Commit 62572e29bc53 changed the

Re: RCU CPU stall console spews leads to soft lockup disabled is reasonable ?

2015-01-20 Thread Zhang Zhen
On 2015/1/20 23:25, Don Zickus wrote: On Tue, Jan 20, 2015 at 11:09:19AM +0800, Zhang Zhen wrote: Of course back then, touch_nmi_watchdog touched all cpus. So a problem like this was masked. I believe this upstream commit 62572e29bc53, solved the problem. Thanks for your suggestion.

Re: RCU CPU stall console spews leads to soft lockup disabled is reasonable ?

2015-01-20 Thread Zhang Zhen
On 2015/1/21 10:26, Zhang Zhen wrote: On 2015/1/20 23:25, Don Zickus wrote: On Tue, Jan 20, 2015 at 11:09:19AM +0800, Zhang Zhen wrote: Of course back then, touch_nmi_watchdog touched all cpus. So a problem like this was masked. I believe this upstream commit 62572e29bc53, solved the

Re: RCU CPU stall console spews leads to soft lockup disabled is reasonable ?

2015-01-20 Thread Paul E. McKenney
On Wed, Jan 21, 2015 at 02:54:05PM +0800, Zhang Zhen wrote: On 2015/1/21 11:13, Zhang Zhen wrote: On 2015/1/21 10:26, Zhang Zhen wrote: On 2015/1/20 23:25, Don Zickus wrote: [ . . . ] Sorry, i made a mistake, the log above is based on v3.10.63. I have tested the latest upstream kernel

Re: RCU CPU stall console spews leads to soft lockup disabled is reasonable ?

2015-01-20 Thread Zhang Zhen
On 2015/1/21 11:13, Zhang Zhen wrote: On 2015/1/21 10:26, Zhang Zhen wrote: On 2015/1/20 23:25, Don Zickus wrote: On Tue, Jan 20, 2015 at 11:09:19AM +0800, Zhang Zhen wrote: Of course back then, touch_nmi_watchdog touched all cpus. So a problem like this was masked. I believe this upstream

Re: RCU CPU stall console spews leads to soft lockup disabled is reasonable ?

2015-01-20 Thread Zhang Zhen
On 2015/1/21 15:02, Paul E. McKenney wrote: On Wed, Jan 21, 2015 at 02:54:05PM +0800, Zhang Zhen wrote: On 2015/1/21 11:13, Zhang Zhen wrote: On 2015/1/21 10:26, Zhang Zhen wrote: On 2015/1/20 23:25, Don Zickus wrote: [ . . . ] Sorry, i made a mistake, the log above is based on v3.10.63.

Re: RCU CPU stall console spews leads to soft lockup disabled is reasonable ?

2015-01-19 Thread Paul E. McKenney
On Tue, Jan 20, 2015 at 11:17:01AM +0800, Zhang Zhen wrote: > On 2015/1/19 19:09, Paul E. McKenney wrote: > > On Mon, Jan 19, 2015 at 05:04:29PM +0800, Zhang Zhen wrote: > >> On 2015/1/19 16:42, Paul E. McKenney wrote: > >>> On Mon, Jan 19, 2015 at 04:07:15PM +0800, Zhang Zhen wrote: > Hi, >

Re: RCU CPU stall console spews leads to soft lockup disabled is reasonable ?

2015-01-19 Thread Zhang Zhen
On 2015/1/19 19:09, Paul E. McKenney wrote: > On Mon, Jan 19, 2015 at 05:04:29PM +0800, Zhang Zhen wrote: >> On 2015/1/19 16:42, Paul E. McKenney wrote: >>> On Mon, Jan 19, 2015 at 04:07:15PM +0800, Zhang Zhen wrote: Hi, On my x86_64 qemu virtual machine, RCU CPU stall console spews

Re: RCU CPU stall console spews leads to soft lockup disabled is reasonable ?

2015-01-19 Thread Zhang Zhen
On 2015/1/19 22:06, Don Zickus wrote: > On Mon, Jan 19, 2015 at 05:04:29PM +0800, Zhang Zhen wrote: >>> >>> Did you really intend to acquire the same spinlock twice in a row, >>> forcing a self-deadlock? If not, I of course suggest changing the second >>> "spin_lock()" to "spin_unlock()". >>> >>

Re: RCU CPU stall console spews leads to soft lockup disabled is reasonable ?

2015-01-19 Thread Don Zickus
On Mon, Jan 19, 2015 at 05:04:29PM +0800, Zhang Zhen wrote: > > > > Did you really intend to acquire the same spinlock twice in a row, > > forcing a self-deadlock? If not, I of course suggest changing the second > > "spin_lock()" to "spin_unlock()". > > > > Yes, i acquire the same spinlock

Re: RCU CPU stall console spews leads to soft lockup disabled is reasonable ?

2015-01-19 Thread Paul E. McKenney
On Mon, Jan 19, 2015 at 05:04:29PM +0800, Zhang Zhen wrote: > On 2015/1/19 16:42, Paul E. McKenney wrote: > > On Mon, Jan 19, 2015 at 04:07:15PM +0800, Zhang Zhen wrote: > >> Hi, > >> > >> On my x86_64 qemu virtual machine, RCU CPU stall console spews may > >> lead to soft lockup disabled. > >> >

Re: RCU CPU stall console spews leads to soft lockup disabled is reasonable ?

2015-01-19 Thread Zhang Zhen
On 2015/1/19 16:42, Paul E. McKenney wrote: > On Mon, Jan 19, 2015 at 04:07:15PM +0800, Zhang Zhen wrote: >> Hi, >> >> On my x86_64 qemu virtual machine, RCU CPU stall console spews may >> lead to soft lockup disabled. >> >> If softlockup_thresh > rcu_cpu_stall_timeout (softlockup_thresh = 2 * >>

Re: RCU CPU stall console spews leads to soft lockup disabled is reasonable ?

2015-01-19 Thread Paul E. McKenney
On Mon, Jan 19, 2015 at 04:07:15PM +0800, Zhang Zhen wrote: > Hi, > > On my x86_64 qemu virtual machine, RCU CPU stall console spews may > lead to soft lockup disabled. > > If softlockup_thresh > rcu_cpu_stall_timeout (softlockup_thresh = 2 * > watchdog_thresh): > > / # > / # busybox cat

RCU CPU stall console spews leads to soft lockup disabled is reasonable ?

2015-01-19 Thread Zhang Zhen
Hi, On my x86_64 qemu virtual machine, RCU CPU stall console spews may lead to soft lockup disabled. If softlockup_thresh > rcu_cpu_stall_timeout (softlockup_thresh = 2 * watchdog_thresh): / # / # busybox cat /sys/module/rcupdate/parameters/rcu_cpu_stall_timeout 21 / # echo 60 >

Re: RCU CPU stall console spews leads to soft lockup disabled is reasonable ?

2015-01-19 Thread Zhang Zhen
On 2015/1/19 19:09, Paul E. McKenney wrote: On Mon, Jan 19, 2015 at 05:04:29PM +0800, Zhang Zhen wrote: On 2015/1/19 16:42, Paul E. McKenney wrote: On Mon, Jan 19, 2015 at 04:07:15PM +0800, Zhang Zhen wrote: Hi, On my x86_64 qemu virtual machine, RCU CPU stall console spews may lead to soft

Re: RCU CPU stall console spews leads to soft lockup disabled is reasonable ?

2015-01-19 Thread Zhang Zhen
On 2015/1/19 22:06, Don Zickus wrote: On Mon, Jan 19, 2015 at 05:04:29PM +0800, Zhang Zhen wrote: Did you really intend to acquire the same spinlock twice in a row, forcing a self-deadlock? If not, I of course suggest changing the second spin_lock() to spin_unlock(). Yes, i acquire the

Re: RCU CPU stall console spews leads to soft lockup disabled is reasonable ?

2015-01-19 Thread Paul E. McKenney
On Tue, Jan 20, 2015 at 11:17:01AM +0800, Zhang Zhen wrote: On 2015/1/19 19:09, Paul E. McKenney wrote: On Mon, Jan 19, 2015 at 05:04:29PM +0800, Zhang Zhen wrote: On 2015/1/19 16:42, Paul E. McKenney wrote: On Mon, Jan 19, 2015 at 04:07:15PM +0800, Zhang Zhen wrote: Hi, On my x86_64

RCU CPU stall console spews leads to soft lockup disabled is reasonable ?

2015-01-19 Thread Zhang Zhen
Hi, On my x86_64 qemu virtual machine, RCU CPU stall console spews may lead to soft lockup disabled. If softlockup_thresh rcu_cpu_stall_timeout (softlockup_thresh = 2 * watchdog_thresh): / # / # busybox cat /sys/module/rcupdate/parameters/rcu_cpu_stall_timeout 21 / # echo 60

Re: RCU CPU stall console spews leads to soft lockup disabled is reasonable ?

2015-01-19 Thread Paul E. McKenney
On Mon, Jan 19, 2015 at 04:07:15PM +0800, Zhang Zhen wrote: Hi, On my x86_64 qemu virtual machine, RCU CPU stall console spews may lead to soft lockup disabled. If softlockup_thresh rcu_cpu_stall_timeout (softlockup_thresh = 2 * watchdog_thresh): / # / # busybox cat

Re: RCU CPU stall console spews leads to soft lockup disabled is reasonable ?

2015-01-19 Thread Paul E. McKenney
On Mon, Jan 19, 2015 at 05:04:29PM +0800, Zhang Zhen wrote: On 2015/1/19 16:42, Paul E. McKenney wrote: On Mon, Jan 19, 2015 at 04:07:15PM +0800, Zhang Zhen wrote: Hi, On my x86_64 qemu virtual machine, RCU CPU stall console spews may lead to soft lockup disabled. If

Re: RCU CPU stall console spews leads to soft lockup disabled is reasonable ?

2015-01-19 Thread Don Zickus
On Mon, Jan 19, 2015 at 05:04:29PM +0800, Zhang Zhen wrote: Did you really intend to acquire the same spinlock twice in a row, forcing a self-deadlock? If not, I of course suggest changing the second spin_lock() to spin_unlock(). Yes, i acquire the same spinlock twice in order to

Re: RCU CPU stall console spews leads to soft lockup disabled is reasonable ?

2015-01-19 Thread Zhang Zhen
On 2015/1/19 16:42, Paul E. McKenney wrote: On Mon, Jan 19, 2015 at 04:07:15PM +0800, Zhang Zhen wrote: Hi, On my x86_64 qemu virtual machine, RCU CPU stall console spews may lead to soft lockup disabled. If softlockup_thresh rcu_cpu_stall_timeout (softlockup_thresh = 2 *