[PATCH] powerpc/64: Use tick accounting by default

[PATCH] powerpc/64: Use tick accounting by default

[Anton Blanchard]

From: Anton Blanchard <anton@samba.org>

ppc64 is the only architecture that turns on VIRT_CPU_ACCOUNTING_NATIVE
by default. The overhead of this option is extremely high - a context
switch microbenchmark using sched_yield() is almost 20% slower.

To get finer grained user/hardirq/softirq statitics, the
IRQ_TIME_ACCOUNTING option can be used instead, which has much lower
overhead.

As such, disable this option by default. If a user really wants it,
they can still enable it manually.

Signed-off-by: Anton Blanchard <anton@samba.org>
---
 init/Kconfig | 3 +--
 1 file changed, 1 insertion(+), 2 deletions(-)

diff --git a/init/Kconfig b/init/Kconfig
index 1d3475fc9496..a5c30acc1ede 100644
--- a/init/Kconfig
+++ b/init/Kconfig
@@ -342,8 +342,7 @@ config VIRT_CPU_ACCOUNTING
 
 choice
 	prompt "Cputime accounting"
-	default TICK_CPU_ACCOUNTING if !PPC64
-	default VIRT_CPU_ACCOUNTING_NATIVE if PPC64
+	default TICK_CPU_ACCOUNTING
 
 # Kind of a stub config for the pure tick based cputime accounting
 config TICK_CPU_ACCOUNTING
-- 
2.11.0

Re: [PATCH] powerpc/64: Use tick accounting by default

[Michael Ellerman]

Anton Blanchard <anton@ozlabs.org> writes:

> From: Anton Blanchard <anton@samba.org>
>
> ppc64 is the only architecture that turns on VIRT_CPU_ACCOUNTING_NATIVE
> by default. The overhead of this option is extremely high - a context
> switch microbenchmark using sched_yield() is almost 20% slower.

Running on what? It should all be nop'ed out unless you're on a platform
that needs it (SPLPAR).

> To get finer grained user/hardirq/softirq statitics, the
> IRQ_TIME_ACCOUNTING option can be used instead, which has much lower
> overhead.

Can it? We don't select HAVE_IRQ_TIME_ACCOUNTING, so AFAICS it can't be
enabled.

Doesn't dropping this mean we never count stolen time?

cheers

Re: [PATCH] powerpc/64: Use tick accounting by default

[Nicholas Piggin]

On Mon, 22 May 2017 14:15:57 +1000
Michael Ellerman <mpe@ellerman.id.au> wrote:

> Anton Blanchard <anton@ozlabs.org> writes:
> 
> > From: Anton Blanchard <anton@samba.org>
> >
> > ppc64 is the only architecture that turns on VIRT_CPU_ACCOUNTING_NATIVE
> > by default. The overhead of this option is extremely high - a context
> > switch microbenchmark using sched_yield() is almost 20% slower.  
> 
> Running on what? It should all be nop'ed out unless you're on a platform
> that needs it (SPLPAR).

Not ACCOUNT_CPU_USER_ENTRY/EXIT, which adds a fair cost to kernel
entry/exit (my notes say ~70 cycles on getppid() out of 3-4 hundred).

> 
> > To get finer grained user/hardirq/softirq statitics, the
> > IRQ_TIME_ACCOUNTING option can be used instead, which has much lower
> > overhead.  
> 
> Can it? We don't select HAVE_IRQ_TIME_ACCOUNTING, so AFAICS it can't be
> enabled.
> 
> Doesn't dropping this mean we never count stolen time?
> 
> cheers

Re: [PATCH] powerpc/64: Use tick accounting by default

[Anton Blanchard]

Hi Michael,

> > ppc64 is the only architecture that turns on
> > VIRT_CPU_ACCOUNTING_NATIVE by default. The overhead of this option
> > is extremely high - a context switch microbenchmark using
> > sched_yield() is almost 20% slower.  
> 
> Running on what? It should all be nop'ed out unless you're on a
> platform that needs it (SPLPAR).

POWERNV native. We don't nop out all the vtime_account_* gunk do we? It
is all those functions that are a large part of the problem.

> > To get finer grained user/hardirq/softirq statitics, the
> > IRQ_TIME_ACCOUNTING option can be used instead, which has much lower
> > overhead.  
> 
> Can it? We don't select HAVE_IRQ_TIME_ACCOUNTING, so AFAICS it can't
> be enabled.

I have a separate patch to enable it.

> Doesn't dropping this mean we never count stolen time?

Perhaps. Do we have any applications left that care?

Anton

Re: [PATCH] powerpc/64: Use tick accounting by default

[Christophe LEROY]

Le 19/05/2017 à 16:41, Anton Blanchard a écrit :
> From: Anton Blanchard <anton@samba.org>
>
> ppc64 is the only architecture that turns on VIRT_CPU_ACCOUNTING_NATIVE
> by default. The overhead of this option is extremely high - a context
> switch microbenchmark using sched_yield() is almost 20% slower.
>
> To get finer grained user/hardirq/softirq statitics, the
> IRQ_TIME_ACCOUNTING option can be used instead, which has much lower
> overhead.

Does IRQ_TIME_ACCOUNTING allow the same granularity as 
VIRT_CPU_ACCOUNTING_NATIVE ?
I've quickly looked into the source, it seems that this option still 
accounts based on time ticks.
On a hardware doing mainly VoIP handling, the processes run a few ms 
every 20 ms. With TICK_CPU_ACCOUNTING and a 10ms tick, the processes 
either appear with 50% CPU or almost 0%.
Would it be more precise with IRQ_TIME_ACCOUNTING ?

Christophe

>
> As such, disable this option by default. If a user really wants it,
> they can still enable it manually.
>
> Signed-off-by: Anton Blanchard <anton@samba.org>
> ---
>  init/Kconfig | 3 +--
>  1 file changed, 1 insertion(+), 2 deletions(-)
>
> diff --git a/init/Kconfig b/init/Kconfig
> index 1d3475fc9496..a5c30acc1ede 100644
> --- a/init/Kconfig
> +++ b/init/Kconfig
> @@ -342,8 +342,7 @@ config VIRT_CPU_ACCOUNTING
>
>  choice
>  	prompt "Cputime accounting"
> -	default TICK_CPU_ACCOUNTING if !PPC64
> -	default VIRT_CPU_ACCOUNTING_NATIVE if PPC64
> +	default TICK_CPU_ACCOUNTING
>
>  # Kind of a stub config for the pure tick based cputime accounting
>  config TICK_CPU_ACCOUNTING
>

Re: [PATCH] powerpc/64: Use tick accounting by default

[Christophe Leroy]

Le 22/05/2017 à 07:13, Anton Blanchard a écrit :
> Hi Michael,
> 
>>> ppc64 is the only architecture that turns on
>>> VIRT_CPU_ACCOUNTING_NATIVE by default. The overhead of this option
>>> is extremely high - a context switch microbenchmark using
>>> sched_yield() is almost 20% slower.
>>
>> Running on what? It should all be nop'ed out unless you're on a
>> platform that needs it (SPLPAR).
> 
> POWERNV native. We don't nop out all the vtime_account_* gunk do we? It
> is all those functions that are a large part of the problem.
> 
>>> To get finer grained user/hardirq/softirq statitics, the
>>> IRQ_TIME_ACCOUNTING option can be used instead, which has much lower
>>> overhead.
>>
>> Can it? We don't select HAVE_IRQ_TIME_ACCOUNTING, so AFAICS it can't
>> be enabled.
> 
> I have a separate patch to enable it.
> 
>> Doesn't dropping this mean we never count stolen time?
> 
> Perhaps. Do we have any applications left that care?
> 

This patch has been superseded by Nick's patch 
https://patchwork.ozlabs.org/project/linuxppc-dev/patch/20220525081346.871535-1-npiggin@gmail.com/

Christophe