lkml.org 
[lkml]   [2018]   [Mar]   [25]   [last100]   RSS Feed
Views: [wrap][no wrap]   [headers]  [forward] 
 
Messages in this thread
Patch in this message
/
From
SubjectRe: [PATCH v3] cpuidle: poll_state: Add time limit to poll_idle()
Date
On Sunday, March 25, 2018 10:15:52 PM CEST Rik van Riel wrote:
>
> --=-e8yLbs0aoH4SrxOskwwl
> Content-Type: text/plain; charset="UTF-8"
> Content-Transfer-Encoding: quoted-printable
>
> On Thu, 2018-03-22 at 18:09 +0100, Rafael J. Wysocki wrote:
> >=20
> > +++ linux-pm/drivers/cpuidle/poll_state.c
> > @@ -10,6 +10,7 @@
> > #include <linux/sched/idle.h>
> > =20
> > #define POLL_IDLE_TIME_LIMIT (TICK_NSEC / 16)
> > +#define POLL_IDLE_COUNT 1000
> > =20
> > static int __cpuidle poll_idle(struct cpuidle_device *dev,
> > struct cpuidle_driver *drv, int
> > index)
> > @@ -18,9 +19,14 @@ static int __cpuidle poll_idle(struct cp
> > =20
> > local_irq_enable();
> > if (!current_set_polling_and_test()) {
> > + unsigned int loop_count =3D 0;
> > +
> > while (!need_resched()) {
> > cpu_relax();
> > + if (loop_count++ < POLL_IDLE_COUNT)
> > + continue;
> > =20
> > + loop_count =3D 0;
> > if (local_clock() - time_start >
> > POLL_IDLE_TIME_LIMIT)
> > break;
> > }
>
> OK, I am still seeing a performance
> degradation with the above, though
> not throughout the entire workload.
>
> It appears that making the idle loop
> do anything besides cpu_relax() for
> a significant amount of time slows
> things down.

I see.

> I plan to try two more things:
>
> 1) Disable polling on SMT systems, with
> the idea that putting one thread to
> sleep with monitor/mwait in C1 will
> allow the other thread to run faster.

Sounds plausible.

> 2) Insert more cpu_relax() calls into the
> main loop, so the CPU core spends more
> of its time in cpu_relax() and less
> time doing other things:

Well, maybe it's a matter of doing cpu_relax() between any other bits of
significant computation in there:


---
drivers/cpuidle/poll_state.c | 13 ++++++++++++-
1 file changed, 12 insertions(+), 1 deletion(-)

Index: linux-pm/drivers/cpuidle/poll_state.c
===================================================================
--- linux-pm.orig/drivers/cpuidle/poll_state.c
+++ linux-pm/drivers/cpuidle/poll_state.c
@@ -10,6 +10,7 @@
#include <linux/sched/idle.h>

#define POLL_IDLE_TIME_LIMIT (TICK_NSEC / 16)
+#define POLL_IDLE_COUNT 200

static int __cpuidle poll_idle(struct cpuidle_device *dev,
struct cpuidle_driver *drv, int index)
@@ -18,11 +19,21 @@ static int __cpuidle poll_idle(struct cp

local_irq_enable();
if (!current_set_polling_and_test()) {
+ unsigned int loop_count = 0;
+
while (!need_resched()) {
cpu_relax();
-
+ if (loop_count++ < POLL_IDLE_COUNT) {
+ cpu_relax();
+ continue;
+ }
+ cpu_relax();
+ loop_count = 0;
+ cpu_relax();
if (local_clock() - time_start > POLL_IDLE_TIME_LIMIT)
break;
+
+ cpu_relax();
}
}
current_clr_polling();
\
 
 \ /
  Last update: 2018-03-25 23:34    [W:0.147 / U:0.104 seconds]
©2003-2020 Jasper Spaans|hosted at Digital Ocean and TransIP|Read the blog|Advertise on this site