All of lore.kernel.org
 help / color / mirror / Atom feed
From: Peter Zijlstra <peterz@infradead.org>
To: Yuyang Du <yuyang.du@intel.com>
Cc: mingo@redhat.com, linux-kernel@vger.kernel.org, pjt@google.com,
	bsegall@google.com, arjan.van.de.ven@intel.com,
	len.brown@intel.com, rafael.j.wysocki@intel.com,
	alan.cox@intel.com, mark.gross@intel.com, fengguang.wu@intel.com
Subject: Re: [PATCH 2/2 v4] sched: Rewrite per entity runnable load average tracking
Date: Mon, 28 Jul 2014 12:48:37 +0200	[thread overview]
Message-ID: <20140728104837.GQ6758@twins.programming.kicks-ass.net> (raw)
In-Reply-To: <1405639567-21445-3-git-send-email-yuyang.du@intel.com>

[-- Attachment #1: Type: text/plain, Size: 2049 bytes --]

On Fri, Jul 18, 2014 at 07:26:06AM +0800, Yuyang Du wrote:
> @@ -665,20 +660,27 @@ static u64 sched_vslice(struct cfs_rq *cfs_rq, struct sched_entity *se)
>  }
>  
>  #ifdef CONFIG_SMP
> -static unsigned long task_h_load(struct task_struct *p);
>  
> -static inline void __update_task_entity_contrib(struct sched_entity *se);
> +/* dependent on LOAD_AVG_PERIOD, see below */
> +#define LOAD_AVG_MAX 47742 /* maximum possible load avg */

Please don't separate this from the rest of the values it belongs to. If
you really have to, move the entire block.

> @@ -2071,13 +2073,9 @@ static inline long calc_tg_weight(struct task_group *tg, struct cfs_rq *cfs_rq)
>  	long tg_weight;
>  
>  	/*
> -	 * Use this CPU's actual weight instead of the last load_contribution
> -	 * to gain a more accurate current total weight. See
> -	 * update_cfs_rq_load_contribution().
> +	 * Use this CPU's load average instead of actual weight
>  	 */
>  	tg_weight = atomic_long_read(&tg->load_avg);
> -	tg_weight -= cfs_rq->tg_load_contrib;
> -	tg_weight += cfs_rq->load.weight;

I don't think that comment makes any sense after this. The comment was
there to explain the -=, += things, but that's all gone so its pretty
trivial now, and i++ /* inc by one */ comments are not useful.

> @@ -2181,7 +2178,7 @@ static const u32 runnable_avg_yN_sum[] = {
>   * Approximate:
>   *   val * y^n,    where y^32 ~= 0.5 (~1 scheduling period)
>   */
> -static __always_inline u64 decay_load(u64 val, u64 n)
> +static __always_inline u64 decay_load32(u64 val, u64 n)
>  {
>  	unsigned int local_n;
>  
> @@ -2210,6 +2207,18 @@ static __always_inline u64 decay_load(u64 val, u64 n)
>  	return val >> 32;
>  }
>  
> +static __always_inline u64 decay_load(u64 val, u64 n)
> +{
> +	if (likely(val <= UINT_MAX))
> +		val = decay_load32(val, n);
> +	else {
> +		val *= (u32)decay_load32(1 << 15, n);
> +		val >>= 15;
> +	}
> +
> +	return val;
> +}

Please just use mul_u64_u32_shr().

/me continues reading the rest of it..

[-- Attachment #2: Type: application/pgp-signature, Size: 836 bytes --]

  parent reply	other threads:[~2014-07-28 10:48 UTC|newest]

Thread overview: 47+ messages / expand[flat|nested]  mbox.gz  Atom feed  top
2014-07-17 23:26 [PATCH 0/2 v4] sched: Rewrite per entity runnable load average tracking Yuyang Du
2014-07-17 23:26 ` [PATCH 1/2 v4] sched: Remove update_rq_runnable_avg Yuyang Du
2014-07-17 23:26 ` [PATCH 2/2 v4] sched: Rewrite per entity runnable load average tracking Yuyang Du
2014-07-18  9:43   ` Vincent Guittot
2014-07-27 17:36     ` Yuyang Du
2014-07-29  9:12       ` Vincent Guittot
2014-07-29  1:43         ` Yuyang Du
2014-07-29 13:17           ` Vincent Guittot
2014-07-29 22:27             ` Yuyang Du
2014-07-30  8:30               ` Peter Zijlstra
2014-07-30  0:40                 ` Yuyang Du
2014-07-29  9:39         ` Peter Zijlstra
2014-07-29  1:53           ` Yuyang Du
2014-07-29 13:35             ` Peter Zijlstra
2014-07-29 15:55               ` Peter Zijlstra
2014-07-29 23:08               ` Yuyang Du
2014-07-31  9:40             ` Vincent Guittot
2014-07-31  9:56             ` [PATCH 2/2 v4] sched: Rewrite per entity runnable load average Vincent Guittot
2014-07-31 19:16               ` Yuyang Du
2014-08-01  9:28                 ` Vincent Guittot
2014-07-28 10:48   ` Peter Zijlstra [this message]
2014-07-29  0:56     ` [PATCH 2/2 v4] sched: Rewrite per entity runnable load average tracking Yuyang Du
2014-07-29 13:15       ` Peter Zijlstra
2014-07-28 11:39   ` Peter Zijlstra
2014-07-29  1:09     ` Yuyang Du
2014-07-29 13:19       ` Peter Zijlstra
2014-07-28 12:01   ` Peter Zijlstra
2014-07-28 13:51   ` Peter Zijlstra
2014-07-28 16:58     ` bsegall
2014-07-28 17:19       ` Peter Zijlstra
2014-07-29  1:13         ` Yuyang Du
2014-07-18 15:39 ` [PATCH 0/2 " Morten Rasmussen
2014-07-27 19:02   ` Yuyang Du
2014-07-28 10:38     ` Peter Zijlstra
2014-07-29  1:17       ` Yuyang Du
2014-07-29 13:06         ` Peter Zijlstra
2014-07-30 10:13     ` Morten Rasmussen
2014-07-30 10:21       ` Peter Zijlstra
2014-07-30 10:57         ` Morten Rasmussen
2014-07-30 19:17       ` Yuyang Du
2014-07-31  8:54         ` Morten Rasmussen
2014-07-31  2:15           ` Yuyang Du
2014-07-20  5:46 ` Mike Galbraith
2014-07-27 19:34   ` Yuyang Du
2014-07-28  7:49     ` Mike Galbraith
2014-07-28  0:01       ` Yuyang Du
2014-07-28  8:55     ` Peter Zijlstra

Reply instructions:

You may reply publicly to this message via plain-text email
using any one of the following methods:

* Save the following mbox file, import it into your mail client,
  and reply-to-all from there: mbox

  Avoid top-posting and favor interleaved quoting:
  https://en.wikipedia.org/wiki/Posting_style#Interleaved_style

* Reply using the --to, --cc, and --in-reply-to
  switches of git-send-email(1):

  git send-email \
    --in-reply-to=20140728104837.GQ6758@twins.programming.kicks-ass.net \
    --to=peterz@infradead.org \
    --cc=alan.cox@intel.com \
    --cc=arjan.van.de.ven@intel.com \
    --cc=bsegall@google.com \
    --cc=fengguang.wu@intel.com \
    --cc=len.brown@intel.com \
    --cc=linux-kernel@vger.kernel.org \
    --cc=mark.gross@intel.com \
    --cc=mingo@redhat.com \
    --cc=pjt@google.com \
    --cc=rafael.j.wysocki@intel.com \
    --cc=yuyang.du@intel.com \
    /path/to/YOUR_REPLY

  https://kernel.org/pub/software/scm/git/docs/git-send-email.html

* If your mail client supports setting the In-Reply-To header
  via mailto: links, try the mailto: link
Be sure your reply has a Subject: header at the top and a blank line before the message body.
This is an external index of several public inboxes,
see mirroring instructions on how to clone and mirror
all data and code used by this external index.