Groups | Search | Server Info | Keyboard shortcuts | Login | Register [http] [https] [nntp] [nntps]
Groups > linux.kernel > #1681383 > unrolled thread
| Started by | Ganesh Mahendran <opensource.ganesh@gmail.com> |
|---|---|
| First post | 2017-07-05 10:50 +0200 |
| Last post | 2017-07-06 03:50 +0200 |
| Articles | 3 — 2 participants |
Back to article view | Back to linux.kernel
[PATCH] sched/fair: fix contribution calculation Ganesh Mahendran <opensource.ganesh@gmail.com> - 2017-07-05 10:50 +0200
Re: [PATCH] sched/fair: fix contribution calculation Peter Zijlstra <peterz@infradead.org> - 2017-07-05 14:00 +0200
Re: [PATCH] sched/fair: fix contribution calculation Ganesh Mahendran <opensource.ganesh@gmail.com> - 2017-07-06 03:50 +0200
| From | Ganesh Mahendran <opensource.ganesh@gmail.com> |
|---|---|
| Date | 2017-07-05 10:50 +0200 |
| Subject | [PATCH] sched/fair: fix contribution calculation |
| Message-ID | <tZOau-3Wl-27@gated-at.bofh.it> |
Function __compute_runnable_contrib() is to calculate:
\Sum 1024*y^n {for (1..n_period)}
But LOAD_AVG_MAX returns sum of 1024*y^n (0..n_period).
So we need to subtract 1024*y^0.
Cc: stable@vger.kernel.org
Signed-off-by: Ganesh Mahendran <opensource.ganesh@gmail.com>
---
kernel/sched/fair.c | 2 +-
1 file changed, 1 insertion(+), 1 deletion(-)
diff --git a/kernel/sched/fair.c b/kernel/sched/fair.c
index 90e26b1..777ad49 100644
--- a/kernel/sched/fair.c
+++ b/kernel/sched/fair.c
@@ -2508,7 +2508,7 @@ static u32 __compute_runnable_contrib(u64 n)
if (likely(n <= LOAD_AVG_PERIOD))
return runnable_avg_yN_sum[n];
else if (unlikely(n >= LOAD_AVG_MAX_N))
- return LOAD_AVG_MAX;
+ return LOAD_AVG_MAX - 1024;
/* Compute \Sum k^n combining precomputed values for k^i, \Sum k^j */
do {
--
1.9.1
[toc] | [next] | [standalone]
| From | Peter Zijlstra <peterz@infradead.org> |
|---|---|
| Date | 2017-07-05 14:00 +0200 |
| Message-ID | <tZR8m-5K7-23@gated-at.bofh.it> |
| In reply to | #1681383 |
On Wed, Jul 05, 2017 at 04:46:30PM +0800, Ganesh Mahendran wrote:
> Function __compute_runnable_contrib() is to calculate:
> \Sum 1024*y^n {for (1..n_period)}
> But LOAD_AVG_MAX returns sum of 1024*y^n (0..n_period).
> So we need to subtract 1024*y^0.
>
> Cc: stable@vger.kernel.org
> Signed-off-by: Ganesh Mahendran <opensource.ganesh@gmail.com>
> ---
> kernel/sched/fair.c | 2 +-
> 1 file changed, 1 insertion(+), 1 deletion(-)
>
> diff --git a/kernel/sched/fair.c b/kernel/sched/fair.c
> index 90e26b1..777ad49 100644
> --- a/kernel/sched/fair.c
> +++ b/kernel/sched/fair.c
> @@ -2508,7 +2508,7 @@ static u32 __compute_runnable_contrib(u64 n)
> if (likely(n <= LOAD_AVG_PERIOD))
> return runnable_avg_yN_sum[n];
> else if (unlikely(n >= LOAD_AVG_MAX_N))
> - return LOAD_AVG_MAX;
> + return LOAD_AVG_MAX - 1024;
>
> /* Compute \Sum k^n combining precomputed values for k^i, \Sum k^j */
> do {
This code no longer exists...
[toc] | [prev] | [next] | [standalone]
| From | Ganesh Mahendran <opensource.ganesh@gmail.com> |
|---|---|
| Date | 2017-07-06 03:50 +0200 |
| Message-ID | <u045B-5Wp-37@gated-at.bofh.it> |
| In reply to | #1681488 |
Hello, Peter:
2017-07-05 19:59 GMT+08:00 Peter Zijlstra <peterz@infradead.org>:
> On Wed, Jul 05, 2017 at 04:46:30PM +0800, Ganesh Mahendran wrote:
>> Function __compute_runnable_contrib() is to calculate:
>> \Sum 1024*y^n {for (1..n_period)}
>> But LOAD_AVG_MAX returns sum of 1024*y^n (0..n_period).
>> So we need to subtract 1024*y^0.
>>
>> Cc: stable@vger.kernel.org
>> Signed-off-by: Ganesh Mahendran <opensource.ganesh@gmail.com>
>> ---
>> kernel/sched/fair.c | 2 +-
>> 1 file changed, 1 insertion(+), 1 deletion(-)
>>
>> diff --git a/kernel/sched/fair.c b/kernel/sched/fair.c
>> index 90e26b1..777ad49 100644
>> --- a/kernel/sched/fair.c
>> +++ b/kernel/sched/fair.c
>> @@ -2508,7 +2508,7 @@ static u32 __compute_runnable_contrib(u64 n)
>> if (likely(n <= LOAD_AVG_PERIOD))
>> return runnable_avg_yN_sum[n];
>> else if (unlikely(n >= LOAD_AVG_MAX_N))
>> - return LOAD_AVG_MAX;
>> + return LOAD_AVG_MAX - 1024;
>>
>> /* Compute \Sum k^n combining precomputed values for k^i, \Sum k^j */
>> do {
>
>
> This code no longer exists...
Yes, you are right. The latest kernel has fix this.
Do we need to fix this in LTS 4.1, 4.4?
Thanks.
[toc] | [prev] | [standalone]
Back to top | Article view | linux.kernel
csiph-web