On Mon, Sep 28, 2015 at 11:48:16AM -0700, Yunhong Jiang wrote:
> Currently, when a new timer added to timer wheel for a nohz_active CPU,
> the target CPU will always be waked up.
>
> In fact, if the new added timer is after the base->next_timer, we don't
> need wake up the target CPU since it
On Mon, Sep 28, 2015 at 11:48:16AM -0700, Yunhong Jiang wrote:
> Currently, when a new timer added to timer wheel for a nohz_active CPU,
> the target CPU will always be waked up.
>
> In fact, if the new added timer is after the base->next_timer, we don't
> need wake up the target CPU since it
On Wed, Oct 21, 2015 at 04:16:31PM +0530, Viresh Kumar wrote:
> Cc'ing Frederic.
>
> On 20-10-15, 15:47, Yunhong Jiang wrote:
> > On Sun, Oct 11, 2015 at 08:12:39PM +0200, Thomas Gleixner wrote:
> > > On Mon, 28 Sep 2015, Yunhong Jiang wrote:
> > > > static void internal_add_timer(struct
On Wed, Oct 21, 2015 at 04:16:31PM +0530, Viresh Kumar wrote:
> Cc'ing Frederic.
>
> On 20-10-15, 15:47, Yunhong Jiang wrote:
> > On Sun, Oct 11, 2015 at 08:12:39PM +0200, Thomas Gleixner wrote:
> > > On Mon, 28 Sep 2015, Yunhong Jiang wrote:
> > > > static void internal_add_timer(struct
On Sat, Oct 24, 2015 at 08:50:54AM +0530, Viresh Kumar wrote:
> On 23-10-15, 15:10, Yunhong Jiang wrote:
> > I got this impression from Frederic's comments on
> > http://marc.info/?l=linux-kernel=139048415303210=2, "So you simply rely
> > on the next tick to see the new timer. This should work
On Sat, Oct 24, 2015 at 08:50:54AM +0530, Viresh Kumar wrote:
> On 23-10-15, 15:10, Yunhong Jiang wrote:
> > I got this impression from Frederic's comments on
> > http://marc.info/?l=linux-kernel=139048415303210=2, "So you simply rely
> > on the next tick to see the new timer. This should work
On 23-10-15, 15:10, Yunhong Jiang wrote:
> I got this impression from Frederic's comments on
> http://marc.info/?l=linux-kernel=139048415303210=2, "So you simply rely
> on the next tick to see the new timer. This should work with
> CONFIG_NO_HZ_IDLE but not with CONFIG_NO_HZ_FULL since the
On Fri, Oct 23, 2015 at 07:49:51AM +0530, Viresh Kumar wrote:
> On 22-10-15, 14:40, Yunhong Jiang wrote:
> > A naive question is, why it's sure a tick will happen when the tickless
> > processor is in idle?
>
> How do you get this impression? I don't think anyone has said that.
Viresh, thanks
On 23-10-15, 15:10, Yunhong Jiang wrote:
> I got this impression from Frederic's comments on
> http://marc.info/?l=linux-kernel=139048415303210=2, "So you simply rely
> on the next tick to see the new timer. This should work with
> CONFIG_NO_HZ_IDLE but not with CONFIG_NO_HZ_FULL since the
On Fri, Oct 23, 2015 at 07:49:51AM +0530, Viresh Kumar wrote:
> On 22-10-15, 14:40, Yunhong Jiang wrote:
> > A naive question is, why it's sure a tick will happen when the tickless
> > processor is in idle?
>
> How do you get this impression? I don't think anyone has said that.
Viresh, thanks
On 22-10-15, 14:40, Yunhong Jiang wrote:
> A naive question is, why it's sure a tick will happen when the tickless
> processor is in idle?
How do you get this impression? I don't think anyone has said that.
We are talking about deferrable timers, which by design are only
required if the target
On Wed, Oct 21, 2015 at 04:16:31PM +0530, Viresh Kumar wrote:
> Cc'ing Frederic.
>
> On 20-10-15, 15:47, Yunhong Jiang wrote:
> > On Sun, Oct 11, 2015 at 08:12:39PM +0200, Thomas Gleixner wrote:
> > > On Mon, 28 Sep 2015, Yunhong Jiang wrote:
> > > > static void internal_add_timer(struct
On Wed, Oct 21, 2015 at 04:16:31PM +0530, Viresh Kumar wrote:
> Cc'ing Frederic.
>
> On 20-10-15, 15:47, Yunhong Jiang wrote:
> > On Sun, Oct 11, 2015 at 08:12:39PM +0200, Thomas Gleixner wrote:
> > > On Mon, 28 Sep 2015, Yunhong Jiang wrote:
> > > > static void internal_add_timer(struct
On 22-10-15, 14:40, Yunhong Jiang wrote:
> A naive question is, why it's sure a tick will happen when the tickless
> processor is in idle?
How do you get this impression? I don't think anyone has said that.
We are talking about deferrable timers, which by design are only
required if the target
Cc'ing Frederic.
On 20-10-15, 15:47, Yunhong Jiang wrote:
> On Sun, Oct 11, 2015 at 08:12:39PM +0200, Thomas Gleixner wrote:
> > On Mon, 28 Sep 2015, Yunhong Jiang wrote:
> > > static void internal_add_timer(struct tvec_base *base, struct timer_list
> > > *timer)
> > > {
> > > + bool kick_nohz
Cc'ing Frederic.
On 20-10-15, 15:47, Yunhong Jiang wrote:
> On Sun, Oct 11, 2015 at 08:12:39PM +0200, Thomas Gleixner wrote:
> > On Mon, 28 Sep 2015, Yunhong Jiang wrote:
> > > static void internal_add_timer(struct tvec_base *base, struct timer_list
> > > *timer)
> > > {
> > > + bool kick_nohz
On Sun, Oct 11, 2015 at 08:12:39PM +0200, Thomas Gleixner wrote:
> On Mon, 28 Sep 2015, Yunhong Jiang wrote:
> > static void internal_add_timer(struct tvec_base *base, struct timer_list
> > *timer)
> > {
> > + bool kick_nohz = false;
> > +
> > /* Advance base->jiffies, if the base is
On Sun, Oct 11, 2015 at 08:12:39PM +0200, Thomas Gleixner wrote:
> On Mon, 28 Sep 2015, Yunhong Jiang wrote:
> > static void internal_add_timer(struct tvec_base *base, struct timer_list
> > *timer)
> > {
> > + bool kick_nohz = false;
> > +
> > /* Advance base->jiffies, if the base is
On Mon, 28 Sep 2015, Yunhong Jiang wrote:
> static void internal_add_timer(struct tvec_base *base, struct timer_list
> *timer)
> {
> + bool kick_nohz = false;
> +
> /* Advance base->jiffies, if the base is empty */
> if (!base->all_timers++)
> base->timer_jiffies =
On Mon, 28 Sep 2015, Yunhong Jiang wrote:
> static void internal_add_timer(struct tvec_base *base, struct timer_list
> *timer)
> {
> + bool kick_nohz = false;
> +
> /* Advance base->jiffies, if the base is empty */
> if (!base->all_timers++)
> base->timer_jiffies =
Ping for any response.
Thanks
--jyh
On Mon, Sep 28, 2015 at 11:48:16AM -0700, Yunhong Jiang wrote:
> Currently, when a new timer added to timer wheel for a nohz_active CPU,
> the target CPU will always be waked up.
>
> In fact, if the new added timer is after the base->next_timer, we don't
>
Ping for any response.
Thanks
--jyh
On Mon, Sep 28, 2015 at 11:48:16AM -0700, Yunhong Jiang wrote:
> Currently, when a new timer added to timer wheel for a nohz_active CPU,
> the target CPU will always be waked up.
>
> In fact, if the new added timer is after the base->next_timer, we don't
>
Currently, when a new timer added to timer wheel for a nohz_active CPU,
the target CPU will always be waked up.
In fact, if the new added timer is after the base->next_timer, we don't
need wake up the target CPU since it will not change the sleep time. A
lazy wake up is better in such scenario.
Currently, when a new timer added to timer wheel for a nohz_active CPU,
the target CPU will always be waked up.
In fact, if the new added timer is after the base->next_timer, we don't
need wake up the target CPU since it will not change the sleep time. A
lazy wake up is better in such scenario.
24 matches
Mail list logo