[PATCH] sched: loadavg 0.00, 0.01, 0.05 on idle, 1.00, 0.99, 0.95 on full load

[PATCH] sched: loadavg 0.00, 0.01, 0.05 on idle, 1.00, 0.99, 0.95 on full load

[Vik Heyndrickx]

Hi Peter,

Systems show a minimal load average of 0.00, 0.01, 0.05 even when they 
have no load at all.

Uptime and /proc/loadavg on all systems with kernels released during the 
last five years up until kernel version 4.6-rc5, show a 5- and 15-minute 
minimum loadavg of 0.01 and 0.05 respectively. This should be 0.00 on 
idle systems, but the way the kernel calculates this value prevents it 
from getting lower than the mentioned values.

Likewise but not as obviously noticeable, a fully loaded system with no 
processes waiting, shows a maximum 1/5/15 loadavg of 1.00, 0.99, 0.95 
(multiplied by number of cores).

Once the (old) load becomes 93 or higher, it mathematically can never
get lower than 93, even when the active (load) remains 0 forever.
This results in the strange 0.00, 0.01, 0.05 uptime values on idle
systems.  Note: 93/2048 = 0.0454..., which rounds up to 0.05.

It is not correct to add a 0.5 rounding (=1024/2048) here, since the
result from this function is fed back into the next iteration again,
so the result of that +0.5 rounding value then gets multiplied by
(2048-2037), and then rounded again, so there is a virtual "ghost"
load created, next to the old and active load terms.

By changing the way the internally kept value is rounded, that internal 
value equivalent now can reach 0.00 on idle, and 1.00 on full load. Upon 
increasing load, the internally kept load value is rounded up, when the 
load is decreasing, the load value is rounded down.

The modified code was tested on nohz=off and nohz kernels. It was tested 
on vanilla kernel 4.6-rc5 and on centos 7.1 kernel 3.10.0-327. It was 
tested on single, dual, and octal cores system. It was tested on virtual 
hosts and bare hardware. No unwanted effects have been observed, and the 
problems that the patch intended to fix were indeed gone.

Fixes: 0f004f5a696a ("sched: Cure more NO_HZ load average woes")
Cc: Doug Smythies <dsmythies@telus.net>
Tested-by: Damien Wyart <damien.wyart@free.fr>
Signed-off-by: Vik Heyndrickx <vik.heyndrickx@veribox.net>

--- kernel/sched/loadavg.c.orig	2016-04-25 01:17:05.000000000 +0200
+++ kernel/sched/loadavg.c	2016-04-28 16:47:47.754266136 +0200
@@ -99,10 +99,12 @@ long calc_load_fold_active(struct rq *th
  static unsigned long
  calc_load(unsigned long load, unsigned long exp, unsigned long active)
  {
-	load *= exp;
-	load += active * (FIXED_1 - exp);
-	load += 1UL << (FSHIFT - 1);
-	return load >> FSHIFT;
+	long unsigned newload;
+	
+	newload = load * exp + active * (FIXED_1 - exp);
+	if (active >= load)
+		newload += FIXED_1-1;
+	return newload / FIXED_1;	
  }

  #ifdef CONFIG_NO_HZ_COMMON

RE: [PATCH] sched: loadavg 0.00, 0.01, 0.05 on idle, 1.00, 0.99, 0.95 on full load

[Doug Smythies]

On 2016.04.28 11:46 Vik Heyndrickx wrote:

> Hi Peter,
>
>Systems show a minimal load average of 0.00, 0.01, 0.05 even when they 
> have no load at all.
>
> Uptime and /proc/loadavg on all systems with kernels released during the 
> last five years up until kernel version 4.6-rc5, show a 5- and 15-minute 
> minimum loadavg of 0.01 and 0.05 respectively. This should be 0.00 on 
> idle systems, but the way the kernel calculates this value prevents it 
> from getting lower than the mentioned values.
>
> Likewise but not as obviously noticeable, a fully loaded system with no 
> processes waiting, shows a maximum 1/5/15 loadavg of 1.00, 0.99, 0.95 
> (multiplied by number of cores).
>
> Once the (old) load becomes 93 or higher, it mathematically can never
> get lower than 93, even when the active (load) remains 0 forever.
> This results in the strange 0.00, 0.01, 0.05 uptime values on idle
> systems.  Note: 93/2048 = 0.0454..., which rounds up to 0.05.
>
> It is not correct to add a 0.5 rounding (=1024/2048) here, since the
> result from this function is fed back into the next iteration again,
> so the result of that +0.5 rounding value then gets multiplied by
> (2048-2037), and then rounded again, so there is a virtual "ghost"
> load created, next to the old and active load terms.
>
> By changing the way the internally kept value is rounded, that internal 
> value equivalent now can reach 0.00 on idle, and 1.00 on full load. Upon 
> increasing load, the internally kept load value is rounded up, when the 
> load is decreasing, the load value is rounded down.
>
> The modified code was tested on nohz=off and nohz kernels. It was tested 
> on vanilla kernel 4.6-rc5 and on centos 7.1 kernel 3.10.0-327. It was 
> tested on single, dual, and octal cores system. It was tested on virtual 
> hosts and bare hardware. No unwanted effects have been observed, and the 
> problems that the patch intended to fix were indeed gone.
>
> Fixes: 0f004f5a696a ("sched: Cure more NO_HZ load average woes")
> Cc: Doug Smythies <dsmythies@telus.net>
> Tested-by: Damien Wyart <damien.wyart@free.fr>
> Signed-off-by: Vik Heyndrickx <vik.heyndrickx@veribox.net>
>
> --- kernel/sched/loadavg.c.orig	2016-04-25 01:17:05.000000000 +0200
> +++ kernel/sched/loadavg.c	2016-04-28 16:47:47.754266136 +0200
> @@ -99,10 +99,12 @@ long calc_load_fold_active(struct rq *th
>   static unsigned long
>   calc_load(unsigned long load, unsigned long exp, unsigned long active)
>   {
> -	load *= exp;
> -	load += active * (FIXED_1 - exp);
> -	load += 1UL << (FSHIFT - 1);
> -	return load >> FSHIFT;
> +	long unsigned newload;
> +	
> +	newload = load * exp + active * (FIXED_1 - exp);
> +	if (active >= load)
> +		newload += FIXED_1-1;
> +	return newload / FIXED_1;	
>   }
>
>  #ifdef CONFIG_NO_HZ_COMMON

See also: https://bugzilla.kernel.org/show_bug.cgi?id=45001
I also tested this patch on 2016.01.22. It works fine.

[tip:sched/core] sched/loadavg: Fix loadavg artifacts on fully idle and on fully loaded systems

[tip-bot for Vik Heyndrickx]

Commit-ID:  20878232c52329f92423d27a60e48b6a6389e0dd
Gitweb:     http://git.kernel.org/tip/20878232c52329f92423d27a60e48b6a6389e0dd
Author:     Vik Heyndrickx <vik.heyndrickx@veribox.net>
AuthorDate: Thu, 28 Apr 2016 20:46:28 +0200
Committer:  Ingo Molnar <mingo@kernel.org>
CommitDate: Thu, 12 May 2016 09:55:34 +0200

sched/loadavg: Fix loadavg artifacts on fully idle and on fully loaded systems

Systems show a minimal load average of 0.00, 0.01, 0.05 even when they
have no load at all.

Uptime and /proc/loadavg on all systems with kernels released during the
last five years up until kernel version 4.6-rc5, show a 5- and 15-minute
minimum loadavg of 0.01 and 0.05 respectively. This should be 0.00 on
idle systems, but the way the kernel calculates this value prevents it
from getting lower than the mentioned values.

Likewise but not as obviously noticeable, a fully loaded system with no
processes waiting, shows a maximum 1/5/15 loadavg of 1.00, 0.99, 0.95
(multiplied by number of cores).

Once the (old) load becomes 93 or higher, it mathematically can never
get lower than 93, even when the active (load) remains 0 forever.
This results in the strange 0.00, 0.01, 0.05 uptime values on idle
systems.  Note: 93/2048 = 0.0454..., which rounds up to 0.05.

It is not correct to add a 0.5 rounding (=1024/2048) here, since the
result from this function is fed back into the next iteration again,
so the result of that +0.5 rounding value then gets multiplied by
(2048-2037), and then rounded again, so there is a virtual "ghost"
load created, next to the old and active load terms.

By changing the way the internally kept value is rounded, that internal
value equivalent now can reach 0.00 on idle, and 1.00 on full load. Upon
increasing load, the internally kept load value is rounded up, when the
load is decreasing, the load value is rounded down.

The modified code was tested on nohz=off and nohz kernels. It was tested
on vanilla kernel 4.6-rc5 and on centos 7.1 kernel 3.10.0-327. It was
tested on single, dual, and octal cores system. It was tested on virtual
hosts and bare hardware. No unwanted effects have been observed, and the
problems that the patch intended to fix were indeed gone.

Tested-by: Damien Wyart <damien.wyart@free.fr>
Signed-off-by: Vik Heyndrickx <vik.heyndrickx@veribox.net>
Signed-off-by: Peter Zijlstra (Intel) <peterz@infradead.org>
Cc: <stable@vger.kernel.org>
Cc: Doug Smythies <dsmythies@telus.net>
Cc: Linus Torvalds <torvalds@linux-foundation.org>
Cc: Mike Galbraith <efault@gmx.de>
Cc: Peter Zijlstra <peterz@infradead.org>
Cc: Thomas Gleixner <tglx@linutronix.de>
Fixes: 0f004f5a696a ("sched: Cure more NO_HZ load average woes")
Link: http://lkml.kernel.org/r/e8d32bff-d544-7748-72b5-3c86cc71f09f@veribox.net
Signed-off-by: Ingo Molnar <mingo@kernel.org>
---
 kernel/sched/loadavg.c | 11 +++++++----
 1 file changed, 7 insertions(+), 4 deletions(-)

diff --git a/kernel/sched/loadavg.c b/kernel/sched/loadavg.c
index ef71590..b0b93fd 100644
--- a/kernel/sched/loadavg.c
+++ b/kernel/sched/loadavg.c
@@ -99,10 +99,13 @@ long calc_load_fold_active(struct rq *this_rq)
 static unsigned long
 calc_load(unsigned long load, unsigned long exp, unsigned long active)
 {
-	load *= exp;
-	load += active * (FIXED_1 - exp);
-	load += 1UL << (FSHIFT - 1);
-	return load >> FSHIFT;
+	unsigned long newload;
+
+	newload = load * exp + active * (FIXED_1 - exp);
+	if (active >= load)
+		newload += FIXED_1-1;
+
+	return newload / FIXED_1;
 }
 
 #ifdef CONFIG_NO_HZ_COMMON