On Wed, Jan 15, 2014 at 12:33:55PM -0800, Josh Triplett wrote:
> On Tue, Jan 14, 2014 at 09:20:46PM -0800, Paul E. McKenney wrote:
> > From: "Paul E. McKenney"
> >
> > The __run_timers() function currently steps through the list one jiffy at
> > a time in order to update the timer wheel.
On Wed, Jan 15, 2014 at 03:47:10PM -0500, Steven Rostedt wrote:
> On Wed, 15 Jan 2014 12:32:45 -0800
> Josh Triplett wrote:
>
> > On Wed, Jan 15, 2014 at 06:38:58PM +0100, Oleg Nesterov wrote:
> > > forgot to mention...
> > >
> > > On 01/14, Paul E. McKenney wrote:
> > > >
> > > > +static bool
On Wed, Jan 15, 2014 at 06:03:10PM +0100, Oleg Nesterov wrote:
> On 01/14, Paul E. McKenney wrote:
> >
> > The __run_timers() function currently steps through the list one jiffy at
> > a time
>
> And this is very suboptimal if jiffies - timer_jiffies is huge. Looks
> like, we should rework
On Wed, 15 Jan 2014 12:32:45 -0800
Josh Triplett wrote:
> On Wed, Jan 15, 2014 at 06:38:58PM +0100, Oleg Nesterov wrote:
> > forgot to mention...
> >
> > On 01/14, Paul E. McKenney wrote:
> > >
> > > +static bool catchup_timer_jiffies(struct tvec_base *base)
> > > +{
> > > +#ifdef
On Tue, Jan 14, 2014 at 09:20:46PM -0800, Paul E. McKenney wrote:
> From: "Paul E. McKenney"
>
> The __run_timers() function currently steps through the list one jiffy at
> a time in order to update the timer wheel. However, if the timer wheel
> is empty, no adjustment is needed other than
On Wed, Jan 15, 2014 at 06:38:58PM +0100, Oleg Nesterov wrote:
> forgot to mention...
>
> On 01/14, Paul E. McKenney wrote:
> >
> > +static bool catchup_timer_jiffies(struct tvec_base *base)
> > +{
> > +#ifdef CONFIG_NO_HZ_FULL
> > + if (!base->all_timers) {
> > + base->timer_jiffies
forgot to mention...
On 01/14, Paul E. McKenney wrote:
>
> +static bool catchup_timer_jiffies(struct tvec_base *base)
> +{
> +#ifdef CONFIG_NO_HZ_FULL
> + if (!base->all_timers) {
> + base->timer_jiffies = jiffies;
> + return 1;
> + }
> +#endif /* #ifdef
On Wed, Jan 15, 2014 at 06:03:10PM +0100, Oleg Nesterov wrote:
> On 01/14, Paul E. McKenney wrote:
> >
> > The __run_timers() function currently steps through the list one jiffy at
> > a time
>
> And this is very suboptimal if jiffies - timer_jiffies is huge. Looks
> like, we should rework
On 01/14, Paul E. McKenney wrote:
>
> The __run_timers() function currently steps through the list one jiffy at
> a time
And this is very suboptimal if jiffies - timer_jiffies is huge. Looks
like, we should rework base->tv* structures, or (perhaps) optimize
the "cascade" logic so that
On 01/14, Paul E. McKenney wrote:
The __run_timers() function currently steps through the list one jiffy at
a time
And this is very suboptimal if jiffies - timer_jiffies is huge. Looks
like, we should rework base-tv* structures, or (perhaps) optimize
the cascade logic so that __run_timers()
On Wed, Jan 15, 2014 at 06:03:10PM +0100, Oleg Nesterov wrote:
On 01/14, Paul E. McKenney wrote:
The __run_timers() function currently steps through the list one jiffy at
a time
And this is very suboptimal if jiffies - timer_jiffies is huge. Looks
like, we should rework base-tv*
forgot to mention...
On 01/14, Paul E. McKenney wrote:
+static bool catchup_timer_jiffies(struct tvec_base *base)
+{
+#ifdef CONFIG_NO_HZ_FULL
+ if (!base-all_timers) {
+ base-timer_jiffies = jiffies;
+ return 1;
+ }
+#endif /* #ifdef CONFIG_NO_HZ_FULL */
On Wed, Jan 15, 2014 at 06:38:58PM +0100, Oleg Nesterov wrote:
forgot to mention...
On 01/14, Paul E. McKenney wrote:
+static bool catchup_timer_jiffies(struct tvec_base *base)
+{
+#ifdef CONFIG_NO_HZ_FULL
+ if (!base-all_timers) {
+ base-timer_jiffies = jiffies;
+
On Tue, Jan 14, 2014 at 09:20:46PM -0800, Paul E. McKenney wrote:
From: Paul E. McKenney paul...@linux.vnet.ibm.com
The __run_timers() function currently steps through the list one jiffy at
a time in order to update the timer wheel. However, if the timer wheel
is empty, no adjustment is
On Wed, 15 Jan 2014 12:32:45 -0800
Josh Triplett j...@joshtriplett.org wrote:
On Wed, Jan 15, 2014 at 06:38:58PM +0100, Oleg Nesterov wrote:
forgot to mention...
On 01/14, Paul E. McKenney wrote:
+static bool catchup_timer_jiffies(struct tvec_base *base)
+{
+#ifdef
On Wed, Jan 15, 2014 at 06:03:10PM +0100, Oleg Nesterov wrote:
On 01/14, Paul E. McKenney wrote:
The __run_timers() function currently steps through the list one jiffy at
a time
And this is very suboptimal if jiffies - timer_jiffies is huge. Looks
like, we should rework base-tv*
On Wed, Jan 15, 2014 at 03:47:10PM -0500, Steven Rostedt wrote:
On Wed, 15 Jan 2014 12:32:45 -0800
Josh Triplett j...@joshtriplett.org wrote:
On Wed, Jan 15, 2014 at 06:38:58PM +0100, Oleg Nesterov wrote:
forgot to mention...
On 01/14, Paul E. McKenney wrote:
+static bool
On Wed, Jan 15, 2014 at 12:33:55PM -0800, Josh Triplett wrote:
On Tue, Jan 14, 2014 at 09:20:46PM -0800, Paul E. McKenney wrote:
From: Paul E. McKenney paul...@linux.vnet.ibm.com
The __run_timers() function currently steps through the list one jiffy at
a time in order to update the timer
From: "Paul E. McKenney"
The __run_timers() function currently steps through the list one jiffy at
a time in order to update the timer wheel. However, if the timer wheel
is empty, no adjustment is needed other than updating ->timer_jiffies.
In this case, which is likely to be common for
From: Paul E. McKenney paul...@linux.vnet.ibm.com
The __run_timers() function currently steps through the list one jiffy at
a time in order to update the timer wheel. However, if the timer wheel
is empty, no adjustment is needed other than updating -timer_jiffies.
In this case, which is likely
20 matches
Mail list logo