On Fri, 2012-09-07 at 09:00 +0200, Peter Zijlstra wrote:
> On Thu, 2012-09-06 at 15:22 -0700, Paul E. McKenney wrote:
> > Ah!
> >
> > It is perfectly legal to avoid -starting- an RCU grace period for a
> > minute, or even longer. If RCU has nothing to do, in other words, if no
> > one registers
On Thu, 2012-09-06 at 15:22 -0700, Paul E. McKenney wrote:
> Ah!
>
> It is perfectly legal to avoid -starting- an RCU grace period for a
> minute, or even longer. If RCU has nothing to do, in other words, if no
> one registers any RCU callbacks, then RCU need not start a grace period.
>
> Of
On Thu, 2012-09-06 at 15:22 -0700, Paul E. McKenney wrote:
Ah!
It is perfectly legal to avoid -starting- an RCU grace period for a
minute, or even longer. If RCU has nothing to do, in other words, if no
one registers any RCU callbacks, then RCU need not start a grace period.
Of course,
On Fri, 2012-09-07 at 09:00 +0200, Peter Zijlstra wrote:
On Thu, 2012-09-06 at 15:22 -0700, Paul E. McKenney wrote:
Ah!
It is perfectly legal to avoid -starting- an RCU grace period for a
minute, or even longer. If RCU has nothing to do, in other words, if no
one registers any RCU
On Thu, Sep 06, 2012 at 06:05:53PM -0400, Steven Rostedt wrote:
> On Thu, 2012-09-06 at 14:58 -0700, Paul E. McKenney wrote:
>
> > > All these cases deserve a warning.
> >
> > Agreed, and that is the whole purpose of the stall warnings.
>
> Then let me ask the question again. According to the
On Thu, 2012-09-06 at 14:58 -0700, Paul E. McKenney wrote:
> > All these cases deserve a warning.
>
> Agreed, and that is the whole purpose of the stall warnings.
Then let me ask the question again. According to the change log:
> If a given CPU avoids the idle loop but also avoids starting a
On Thu, Sep 06, 2012 at 05:41:01PM -0400, Steven Rostedt wrote:
> On Thu, 2012-09-06 at 14:03 -0700, Paul E. McKenney wrote:
>
> > Here are a few other ways that stalls can happen:
> >
> > o A CPU looping in an RCU read-side critical section.
>
> For a minute? That's a bug.
>
> >
> > o
On Thu, 2012-09-06 at 14:03 -0700, Paul E. McKenney wrote:
> Here are a few other ways that stalls can happen:
>
> o A CPU looping in an RCU read-side critical section.
For a minute? That's a bug.
>
> o A CPU looping with interrupts disabled. This condition can
> result
On Thu, Sep 06, 2012 at 05:19:18PM +0200, Peter Zijlstra wrote:
> On Thu, 2012-09-06 at 11:07 -0400, Steven Rostedt wrote:
> > On Thu, 2012-09-06 at 16:56 +0200, Peter Zijlstra wrote:
> > > On Thu, 2012-08-30 at 11:56 -0700, Paul E. McKenney wrote:
> > > >
> > > > If a given CPU avoids the idle
On Thu, 2012-09-06 at 11:07 -0400, Steven Rostedt wrote:
> On Thu, 2012-09-06 at 16:56 +0200, Peter Zijlstra wrote:
> > On Thu, 2012-08-30 at 11:56 -0700, Paul E. McKenney wrote:
> > >
> > > If a given CPU avoids the idle loop but also avoids starting a new
> > > RCU grace period for a full
On Thu, 2012-09-06 at 16:56 +0200, Peter Zijlstra wrote:
> On Thu, 2012-08-30 at 11:56 -0700, Paul E. McKenney wrote:
> >
> > If a given CPU avoids the idle loop but also avoids starting a new
> > RCU grace period for a full minute, RCU can issue spurious RCU CPU
> > stall warnings. This commit
On Thu, 2012-08-30 at 11:56 -0700, Paul E. McKenney wrote:
>
> If a given CPU avoids the idle loop but also avoids starting a new
> RCU grace period for a full minute, RCU can issue spurious RCU CPU
> stall warnings. This commit fixes this issue by adding a check for
> ongoing grace period to
On Thu, 2012-08-30 at 11:56 -0700, Paul E. McKenney wrote:
If a given CPU avoids the idle loop but also avoids starting a new
RCU grace period for a full minute, RCU can issue spurious RCU CPU
stall warnings. This commit fixes this issue by adding a check for
ongoing grace period to avoid
On Thu, 2012-09-06 at 16:56 +0200, Peter Zijlstra wrote:
On Thu, 2012-08-30 at 11:56 -0700, Paul E. McKenney wrote:
If a given CPU avoids the idle loop but also avoids starting a new
RCU grace period for a full minute, RCU can issue spurious RCU CPU
stall warnings. This commit fixes
On Thu, 2012-09-06 at 11:07 -0400, Steven Rostedt wrote:
On Thu, 2012-09-06 at 16:56 +0200, Peter Zijlstra wrote:
On Thu, 2012-08-30 at 11:56 -0700, Paul E. McKenney wrote:
If a given CPU avoids the idle loop but also avoids starting a new
RCU grace period for a full minute, RCU can
On Thu, Sep 06, 2012 at 05:19:18PM +0200, Peter Zijlstra wrote:
On Thu, 2012-09-06 at 11:07 -0400, Steven Rostedt wrote:
On Thu, 2012-09-06 at 16:56 +0200, Peter Zijlstra wrote:
On Thu, 2012-08-30 at 11:56 -0700, Paul E. McKenney wrote:
If a given CPU avoids the idle loop but also
On Thu, 2012-09-06 at 14:03 -0700, Paul E. McKenney wrote:
Here are a few other ways that stalls can happen:
o A CPU looping in an RCU read-side critical section.
For a minute? That's a bug.
o A CPU looping with interrupts disabled. This condition can
result in
On Thu, Sep 06, 2012 at 05:41:01PM -0400, Steven Rostedt wrote:
On Thu, 2012-09-06 at 14:03 -0700, Paul E. McKenney wrote:
Here are a few other ways that stalls can happen:
o A CPU looping in an RCU read-side critical section.
For a minute? That's a bug.
o A CPU looping
On Thu, 2012-09-06 at 14:58 -0700, Paul E. McKenney wrote:
All these cases deserve a warning.
Agreed, and that is the whole purpose of the stall warnings.
Then let me ask the question again. According to the change log:
If a given CPU avoids the idle loop but also avoids starting a new
On Thu, Sep 06, 2012 at 06:05:53PM -0400, Steven Rostedt wrote:
On Thu, 2012-09-06 at 14:58 -0700, Paul E. McKenney wrote:
All these cases deserve a warning.
Agreed, and that is the whole purpose of the stall warnings.
Then let me ask the question again. According to the change log:
On Thu, Aug 30, 2012 at 11:56:24AM -0700, Paul E. McKenney wrote:
> From: "Paul E. McKenney"
>
> If a given CPU avoids the idle loop but also avoids starting a new
> RCU grace period for a full minute, RCU can issue spurious RCU CPU
> stall warnings. This commit fixes this issue by adding a
On Thu, Aug 30, 2012 at 11:56:24AM -0700, Paul E. McKenney wrote:
From: Paul E. McKenney paul.mcken...@linaro.org
If a given CPU avoids the idle loop but also avoids starting a new
RCU grace period for a full minute, RCU can issue spurious RCU CPU
stall warnings. This commit fixes this
From: "Paul E. McKenney"
If a given CPU avoids the idle loop but also avoids starting a new
RCU grace period for a full minute, RCU can issue spurious RCU CPU
stall warnings. This commit fixes this issue by adding a check for
ongoing grace period to avoid these spurious stall warnings.
From: Paul E. McKenney paul.mcken...@linaro.org
If a given CPU avoids the idle loop but also avoids starting a new
RCU grace period for a full minute, RCU can issue spurious RCU CPU
stall warnings. This commit fixes this issue by adding a check for
ongoing grace period to avoid these spurious
24 matches
Mail list logo