Re: [PATCH] powerpc: mitigate impact of decrementer reset
On Tue, Nov 18, 2014 at 12:46:56PM +1100, Michael Ellerman wrote: > On Mon, 2014-11-17 at 11:18 -0800, Paul E. McKenney wrote: > > On Thu, Nov 13, 2014 at 01:42:12PM +1100, Michael Ellerman wrote: > > > On Mon, 2014-11-10 at 14:58 -0600, Paul Clarke wrote: > > > > On 11/10/2014 04:08 AM, Benjamin Herrenschmidt wrote: > > > > > On Tue, 2014-10-07 at 14:13 -0500, Paul Clarke wrote: > > > > >> This patch short-circuits the reset of the decrementer, exiting after > > > > >> the decrementer reset, but before the housekeeping tasks if the only > > > > >> need for the interrupt is simply to reset it. After this patch, > > > > >> the latency spike was measured at about 150 nanoseconds. > > > > > > > > > > Doesn't this break the irq_work stuff ? We trigger it with a > > > > > set_dec(1); > > > > > and your patch will probably cause it to be skipped... > > > > > > > > You're right. > > > > > > Yeah, thanks Ben, that would have been bad. > > > > > > So we'll need to come up with a different approach. > > > > If I am understanding this correctly, it underscores the need for more > > bits in the decrementer register. :-/ > > Yes that is the root cause of the problem :) Sigh!!! I was hoping! ;-) Thanx, Paul ___ Linuxppc-dev mailing list Linuxppc-dev@lists.ozlabs.org https://lists.ozlabs.org/listinfo/linuxppc-dev
Re: [PATCH] powerpc: mitigate impact of decrementer reset
On Mon, 2014-11-17 at 11:18 -0800, Paul E. McKenney wrote: > On Thu, Nov 13, 2014 at 01:42:12PM +1100, Michael Ellerman wrote: > > On Mon, 2014-11-10 at 14:58 -0600, Paul Clarke wrote: > > > On 11/10/2014 04:08 AM, Benjamin Herrenschmidt wrote: > > > > On Tue, 2014-10-07 at 14:13 -0500, Paul Clarke wrote: > > > >> This patch short-circuits the reset of the decrementer, exiting after > > > >> the decrementer reset, but before the housekeeping tasks if the only > > > >> need for the interrupt is simply to reset it. After this patch, > > > >> the latency spike was measured at about 150 nanoseconds. > > > > > > > > Doesn't this break the irq_work stuff ? We trigger it with a set_dec(1); > > > > and your patch will probably cause it to be skipped... > > > > > > You're right. > > > > Yeah, thanks Ben, that would have been bad. > > > > So we'll need to come up with a different approach. > > If I am understanding this correctly, it underscores the need for more > bits in the decrementer register. :-/ Yes that is the root cause of the problem :) cheers ___ Linuxppc-dev mailing list Linuxppc-dev@lists.ozlabs.org https://lists.ozlabs.org/listinfo/linuxppc-dev
Re: [PATCH] powerpc: mitigate impact of decrementer reset
On Thu, Nov 13, 2014 at 01:42:12PM +1100, Michael Ellerman wrote: > On Mon, 2014-11-10 at 14:58 -0600, Paul Clarke wrote: > > On 11/10/2014 04:08 AM, Benjamin Herrenschmidt wrote: > > > On Tue, 2014-10-07 at 14:13 -0500, Paul Clarke wrote: > > >> This patch short-circuits the reset of the decrementer, exiting after > > >> the decrementer reset, but before the housekeeping tasks if the only > > >> need for the interrupt is simply to reset it. After this patch, > > >> the latency spike was measured at about 150 nanoseconds. > > > > > > Doesn't this break the irq_work stuff ? We trigger it with a set_dec(1); > > > and your patch will probably cause it to be skipped... > > > > You're right. > > Yeah, thanks Ben, that would have been bad. > > So we'll need to come up with a different approach. > > > I'm confused by the division between timer_interrupt() and > > __timer_interrupt(). The former is called with interrupts disabled (and > > enables them), but also calls irq_enter()/irq_exit(). Why are those > > calls not in __timer_interrupt()? (If they were, the short-circuit > > logic might be a bit easier to put directly in __timer_interrupt(), > > which would eliminate any duplicate code.) > > > > It looks like __timer_interrupt is only called directly by the broadcast > > timer IPI handler. (Why is __timer_interrupt not static?) Does this > > path not need irq_enter/irq_exit? > > I think I answered most of this in the other mail I just sent, but let me know > if not. > > And __timer_interrupt() is static, if you have a new enough kernel :) If I am understanding this correctly, it underscores the need for more bits in the decrementer register. :-/ Thanx, Paul ___ Linuxppc-dev mailing list Linuxppc-dev@lists.ozlabs.org https://lists.ozlabs.org/listinfo/linuxppc-dev
Re: [PATCH] powerpc: mitigate impact of decrementer reset
On Mon, 2014-11-10 at 14:58 -0600, Paul Clarke wrote: > On 11/10/2014 04:08 AM, Benjamin Herrenschmidt wrote: > > On Tue, 2014-10-07 at 14:13 -0500, Paul Clarke wrote: > >> This patch short-circuits the reset of the decrementer, exiting after > >> the decrementer reset, but before the housekeeping tasks if the only > >> need for the interrupt is simply to reset it. After this patch, > >> the latency spike was measured at about 150 nanoseconds. > > > > Doesn't this break the irq_work stuff ? We trigger it with a set_dec(1); > > and your patch will probably cause it to be skipped... > > You're right. Yeah, thanks Ben, that would have been bad. So we'll need to come up with a different approach. > I'm confused by the division between timer_interrupt() and > __timer_interrupt(). The former is called with interrupts disabled (and > enables them), but also calls irq_enter()/irq_exit(). Why are those > calls not in __timer_interrupt()? (If they were, the short-circuit > logic might be a bit easier to put directly in __timer_interrupt(), > which would eliminate any duplicate code.) > > It looks like __timer_interrupt is only called directly by the broadcast > timer IPI handler. (Why is __timer_interrupt not static?) Does this > path not need irq_enter/irq_exit? I think I answered most of this in the other mail I just sent, but let me know if not. And __timer_interrupt() is static, if you have a new enough kernel :) cheers ___ Linuxppc-dev mailing list Linuxppc-dev@lists.ozlabs.org https://lists.ozlabs.org/listinfo/linuxppc-dev
Re: [PATCH] powerpc: mitigate impact of decrementer reset
On 11/10/2014 04:08 AM, Benjamin Herrenschmidt wrote:
On Tue, 2014-10-07 at 14:13 -0500, Paul Clarke wrote:
The POWER ISA defines an always-running decrementer which can be used
to schedule interrupts after a certain time interval has elapsed.
The decrementer counts down at the same frequency as the Time Base,
which is 512 MHz. The maximum value of the decrementer is 0x7fff.
This works out to a maximum interval of about 4.19 seconds.
If a larger interval is desired, the kernel will set the decrementer
to its maximum value and reset it after it expires (underflows)
a sufficient number of times until the desired interval has elapsed.
The negative effect of this is that an unwanted latency spike will
impact normal processing at most every 4.19 seconds. On an IBM
POWER8-based system, this spike was measured at about 25-30
microseconds, much of which was basic, opportunistic housekeeping
tasks that could otherwise have waited.
This patch short-circuits the reset of the decrementer, exiting after
the decrementer reset, but before the housekeeping tasks if the only
need for the interrupt is simply to reset it. After this patch,
the latency spike was measured at about 150 nanoseconds.
Doesn't this break the irq_work stuff ? We trigger it with a set_dec(1);
and your patch will probably cause it to be skipped...
You're right.
I'm confused by the division between timer_interrupt() and
__timer_interrupt(). The former is called with interrupts disabled (and
enables them), but also calls irq_enter()/irq_exit(). Why are those
calls not in __timer_interrupt()? (If they were, the short-circuit
logic might be a bit easier to put directly in __timer_interrupt(),
which would eliminate any duplicate code.)
It looks like __timer_interrupt is only called directly by the broadcast
timer IPI handler. (Why is __timer_interrupt not static?) Does this
path not need irq_enter/irq_exit?
Signed-off-by: Paul A. Clarke
---
arch/powerpc/kernel/time.c | 13 +
1 file changed, 13 insertions(+)
diff --git a/arch/powerpc/kernel/time.c b/arch/powerpc/kernel/time.c
index 368ab37..962a06b 100644
--- a/arch/powerpc/kernel/time.c
+++ b/arch/powerpc/kernel/time.c
@@ -528,6 +528,7 @@ void timer_interrupt(struct pt_regs * regs)
{
struct pt_regs *old_regs;
u64 *next_tb = &__get_cpu_var(decrementers_next_tb);
+ u64 now;
/* Ensure a positive value is written to the decrementer, or else
* some CPUs will continue to take decrementer exceptions.
@@ -550,6 +551,18 @@ void timer_interrupt(struct pt_regs * regs)
*/
may_hard_irq_enable();
+ /* If this is simply the decrementer expiring (underflow) due to
+* the limited size of the decrementer, and not a set timer,
+* reset (if needed) and return
+*/
+ now = get_tb_or_rtc();
+ if (now < *next_tb) {
+ now = *next_tb - now;
+ if (now <= DECREMENTER_MAX)
+ set_dec((int)now);
+ __get_cpu_var(irq_stat).timer_irqs_others++;
+ return;
+ }
#if defined(CONFIG_PPC32) && defined(CONFIG_PPC_PMAC)
if (atomic_read(&ppc_n_lost_interrupts) != 0)
Regards,
PC
___
Linuxppc-dev mailing list
Linuxppc-dev@lists.ozlabs.org
https://lists.ozlabs.org/listinfo/linuxppc-dev
Re: [PATCH] powerpc: mitigate impact of decrementer reset
On Tue, 2014-10-07 at 14:13 -0500, Paul Clarke wrote:
> The POWER ISA defines an always-running decrementer which can be used
> to schedule interrupts after a certain time interval has elapsed.
> The decrementer counts down at the same frequency as the Time Base,
> which is 512 MHz. The maximum value of the decrementer is 0x7fff.
> This works out to a maximum interval of about 4.19 seconds.
>
> If a larger interval is desired, the kernel will set the decrementer
> to its maximum value and reset it after it expires (underflows)
> a sufficient number of times until the desired interval has elapsed.
>
> The negative effect of this is that an unwanted latency spike will
> impact normal processing at most every 4.19 seconds. On an IBM
> POWER8-based system, this spike was measured at about 25-30
> microseconds, much of which was basic, opportunistic housekeeping
> tasks that could otherwise have waited.
>
> This patch short-circuits the reset of the decrementer, exiting after
> the decrementer reset, but before the housekeeping tasks if the only
> need for the interrupt is simply to reset it. After this patch,
> the latency spike was measured at about 150 nanoseconds.
Doesn't this break the irq_work stuff ? We trigger it with a set_dec(1);
and your patch will probably cause it to be skipped...
Cheers,
Ben.
> Signed-off-by: Paul A. Clarke
> ---
> arch/powerpc/kernel/time.c | 13 +
> 1 file changed, 13 insertions(+)
>
> diff --git a/arch/powerpc/kernel/time.c b/arch/powerpc/kernel/time.c
> index 368ab37..962a06b 100644
> --- a/arch/powerpc/kernel/time.c
> +++ b/arch/powerpc/kernel/time.c
> @@ -528,6 +528,7 @@ void timer_interrupt(struct pt_regs * regs)
> {
> struct pt_regs *old_regs;
> u64 *next_tb = &__get_cpu_var(decrementers_next_tb);
> + u64 now;
>
> /* Ensure a positive value is written to the decrementer, or else
>* some CPUs will continue to take decrementer exceptions.
> @@ -550,6 +551,18 @@ void timer_interrupt(struct pt_regs * regs)
>*/
> may_hard_irq_enable();
>
> + /* If this is simply the decrementer expiring (underflow) due to
> + * the limited size of the decrementer, and not a set timer,
> + * reset (if needed) and return
> + */
> + now = get_tb_or_rtc();
> + if (now < *next_tb) {
> + now = *next_tb - now;
> + if (now <= DECREMENTER_MAX)
> + set_dec((int)now);
> + __get_cpu_var(irq_stat).timer_irqs_others++;
> + return;
> + }
>
> #if defined(CONFIG_PPC32) && defined(CONFIG_PPC_PMAC)
> if (atomic_read(&ppc_n_lost_interrupts) != 0)
___
Linuxppc-dev mailing list
Linuxppc-dev@lists.ozlabs.org
https://lists.ozlabs.org/listinfo/linuxppc-dev
Re: [PATCH] powerpc: mitigate impact of decrementer reset
On 10/08/2014 12:37 AM, Heinz Wrobel wrote: what if your tb wraps during the test? Per the Power ISA, Time Base is 64 bits, monotonically increasing, and is writable only in hypervisor state. To my understanding, it is set to zero at boot (although this is not prescribed). Also, as noted by others, the logic is roughly duplicated (with some differences) from the analogous code in __timer_interrupt just above it. I don't see wrapping as a concern. PC ___ Linuxppc-dev mailing list Linuxppc-dev@lists.ozlabs.org https://lists.ozlabs.org/listinfo/linuxppc-dev
RE: [PATCH] powerpc: mitigate impact of decrementer reset
Paul,
what if your tb wraps during the test?
> -Original Message-
> From: Linuxppc-dev [mailto:linuxppc-dev-
> bounces+heinz.wrobel=freescale@lists.ozlabs.org] On Behalf Of Paul
> Clarke
> Sent: Tuesday, October 07, 2014 21:13
> To: linuxppc-dev@lists.ozlabs.org
> Subject: [PATCH] powerpc: mitigate impact of decrementer reset
>
> The POWER ISA defines an always-running decrementer which can be used to
> schedule interrupts after a certain time interval has elapsed.
> The decrementer counts down at the same frequency as the Time Base, which
> is 512 MHz. The maximum value of the decrementer is 0x7fff.
> This works out to a maximum interval of about 4.19 seconds.
>
> If a larger interval is desired, the kernel will set the decrementer to its
> maximum value and reset it after it expires (underflows) a sufficient number
> of
> times until the desired interval has elapsed.
>
> The negative effect of this is that an unwanted latency spike will impact
> normal
> processing at most every 4.19 seconds. On an IBM POWER8-based system, this
> spike was measured at about 25-30 microseconds, much of which was basic,
> opportunistic housekeeping tasks that could otherwise have waited.
>
> This patch short-circuits the reset of the decrementer, exiting after the
> decrementer reset, but before the housekeeping tasks if the only need for the
> interrupt is simply to reset it. After this patch, the latency spike was
> measured
> at about 150 nanoseconds.
>
> Signed-off-by: Paul A. Clarke
> ---
> arch/powerpc/kernel/time.c | 13 +
> 1 file changed, 13 insertions(+)
>
> diff --git a/arch/powerpc/kernel/time.c b/arch/powerpc/kernel/time.c index
> 368ab37..962a06b 100644
> --- a/arch/powerpc/kernel/time.c
> +++ b/arch/powerpc/kernel/time.c
> @@ -528,6 +528,7 @@ void timer_interrupt(struct pt_regs * regs)
> {
> struct pt_regs *old_regs;
> u64 *next_tb = &__get_cpu_var(decrementers_next_tb);
> + u64 now;
>
> /* Ensure a positive value is written to the decrementer, or else
>* some CPUs will continue to take decrementer exceptions.
> @@ -550,6 +551,18 @@ void timer_interrupt(struct pt_regs * regs)
>*/
> may_hard_irq_enable();
>
> + /* If this is simply the decrementer expiring (underflow) due to
> + * the limited size of the decrementer, and not a set timer,
> + * reset (if needed) and return
> + */
> + now = get_tb_or_rtc();
> + if (now < *next_tb) {
What if "now" and *next_tb are not on the same wrap count? They are both modulo
values AFACS.
Shouldn't this be right here more like a "if ((*next_tb - now) < 2^63)" style
test to check for deltas within the range instead of absolute values?
> + now = *next_tb - now;
> + if (now <= DECREMENTER_MAX)
> + set_dec((int)now);
> + __get_cpu_var(irq_stat).timer_irqs_others++;
> + return;
> + }
>
> #if defined(CONFIG_PPC32) && defined(CONFIG_PPC_PMAC)
> if (atomic_read(&ppc_n_lost_interrupts) != 0)
> --
> 2.1.2.330.g565301e
BR,
Heinz
___
Linuxppc-dev mailing list
Linuxppc-dev@lists.ozlabs.org
https://lists.ozlabs.org/listinfo/linuxppc-dev
