All of lore.kernel.org
 help / color / mirror / Atom feed
From: Martin Schwidefsky <schwidefsky@de.ibm.com>
To: Frederic Weisbecker <fweisbec@gmail.com>
Cc: LKML <linux-kernel@vger.kernel.org>,
	Tony Luck <tony.luck@intel.com>,
	Peter Zijlstra <peterz@infradead.org>,
	Heiko Carstens <heiko.carstens@de.ibm.com>,
	Benjamin Herrenschmidt <benh@kernel.crashing.org>,
	Thomas Gleixner <tglx@linutronix.de>,
	Oleg Nesterov <oleg@redhat.com>,
	Paul Mackerras <paulus@samba.org>,
	Wu Fengguang <fengguang.wu@intel.com>,
	Ingo Molnar <mingo@kernel.org>, Rik van Riel <riel@redhat.com>
Subject: Re: [RFC PATCH 07/30] cputime: Convert kcpustat to nsecs
Date: Mon, 1 Dec 2014 15:14:02 +0100	[thread overview]
Message-ID: <20141201151402.31a6cc9a@mschwide> (raw)
In-Reply-To: <1417199040-21044-8-git-send-email-fweisbec@gmail.com>

On Fri, 28 Nov 2014 19:23:37 +0100
Frederic Weisbecker <fweisbec@gmail.com> wrote:

> Kernel cpu stats are stored in cputime_t which is an architecture
> defined type, and hence a bit opaque and requiring accessors and mutators
> for any operation.
> 
> Converting them to nsecs simplifies the code a little bit.

Quite honestly I do not see much of an improvement here, on set of
functions (cputime_to_xxx) gets replaced by another (nsecs_to_xxx).

On the contrary for s390 I see a degradation, consider a hunk like
this:

> @@ -128,9 +128,9 @@ static inline u64 get_cpu_idle_time_jiffy(unsigned int cpu, u64 *wall)
> 
>  	idle_time = cur_wall_time - busy_time;
>  	if (wall)
> -		*wall = cputime_to_usecs(cur_wall_time);
> +		*wall = div_u64(cur_wall_time, NSEC_PER_USEC);
> 
> -	return cputime_to_usecs(idle_time);
> +	return div_u64(idle_time, NSEC_PER_USEC);
>  }
> 
>  u64 get_cpu_idle_time(unsigned int cpu, u64 *wall, int io_busy)

For s390 cputime_to_usecs is a shift, with the new code we now have a division.
Fortunately this is in a piece of code that s390 does not use..

-- 
blue skies,
   Martin.

"Reality continues to ruin my life." - Calvin.


  reply	other threads:[~2014-12-01 14:14 UTC|newest]

Thread overview: 49+ messages / expand[flat|nested]  mbox.gz  Atom feed  top
2014-11-28 18:23 [RFC PATCH 00/30] cputime: Convert task/cpu cputime accounting to nsecs Frederic Weisbecker
2014-11-28 18:23 ` [RFC PATCH 01/30] jiffies: Remove HZ > USEC_PER_SEC special case Frederic Weisbecker
2014-11-28 18:23 ` [RFC PATCH 02/30] time: Introduce jiffies64_to_nsecs() Frederic Weisbecker
2014-11-28 18:23 ` [RFC PATCH 03/30] cputime: Introduce nsecs_to_cputime64() Frederic Weisbecker
2014-12-01 14:05   ` Martin Schwidefsky
2014-11-28 18:23 ` [RFC PATCH 04/30] s390: Convert open coded idle time seqcount Frederic Weisbecker
2014-12-01 13:46   ` Heiko Carstens
2014-11-28 18:23 ` [RFC PATCH 05/30] s390: Translate cputime magic constants to macros Frederic Weisbecker
2014-12-01 13:47   ` Heiko Carstens
2014-12-01 16:23     ` Frederic Weisbecker
2014-11-28 18:23 ` [RFC PATCH 06/30] s390: Introduce cputime64_to_nsecs() Frederic Weisbecker
2014-12-01 12:24   ` Heiko Carstens
2014-12-01 13:58     ` Martin Schwidefsky
2014-12-01 16:23     ` Frederic Weisbecker
2014-11-28 18:23 ` [RFC PATCH 07/30] cputime: Convert kcpustat to nsecs Frederic Weisbecker
2014-12-01 14:14   ` Martin Schwidefsky [this message]
2014-12-01 16:10     ` Frederic Weisbecker
2014-12-01 16:48       ` Martin Schwidefsky
2014-12-01 17:15         ` Thomas Gleixner
2014-12-01 17:27           ` Martin Schwidefsky
2014-12-01 19:59             ` Frederic Weisbecker
2014-12-01 20:14           ` Christian Borntraeger
2014-12-01 20:21             ` Thomas Gleixner
2014-11-28 18:23 ` [RFC PATCH 08/30] apm32: Fix cputime == jiffies assumption Frederic Weisbecker
2014-11-28 18:23 ` [RFC PATCH 09/30] alpha: Fix jiffies based cputime assumption Frederic Weisbecker
2014-11-28 18:23 ` [RFC PATCH 10/30] cputime: Convert guest time accounting to nsecs Frederic Weisbecker
2014-11-28 18:23 ` [RFC PATCH 11/30] cputime: Special API to return old-typed cputime Frederic Weisbecker
2014-11-28 18:23 ` [RFC PATCH 12/30] cputime: Convert task/group cputime to nsecs Frederic Weisbecker
2014-11-28 18:23 ` [RFC PATCH 13/30] alpha: Convert obsolete cputime_t " Frederic Weisbecker
2014-11-28 18:23 ` [RFC PATCH 14/30] x86: Convert obsolete cputime type " Frederic Weisbecker
2014-11-28 18:23 ` [RFC PATCH 15/30] isdn: " Frederic Weisbecker
2014-11-28 18:23 ` [RFC PATCH 16/30] binfmt: " Frederic Weisbecker
2014-11-28 18:23 ` [RFC PATCH 17/30] acct: " Frederic Weisbecker
2014-11-28 18:23 ` [RFC PATCH 18/30] delaycct: " Frederic Weisbecker
2014-11-28 18:23 ` [RFC PATCH 19/30] tsacct: " Frederic Weisbecker
2014-11-28 18:23 ` [RFC PATCH 20/30] signal: " Frederic Weisbecker
2014-11-28 18:23 ` [RFC PATCH 21/30] cputime: Remove task_cputime_t_scaled Frederic Weisbecker
2014-11-28 18:23 ` [RFC PATCH 22/30] u64_stats_sync: Introduce preempt-unsafe readers Frederic Weisbecker
2014-11-28 18:23 ` [RFC PATCH 23/30] cputime: Convert irq_time_accounting to use u64_stats_sync Frederic Weisbecker
2014-11-28 18:23 ` [RFC PATCH 24/30] cputime: Increment kcpustat directly on irqtime account Frederic Weisbecker
2014-12-01 14:41   ` Martin Schwidefsky
2014-12-01 16:15     ` Frederic Weisbecker
2014-12-01 16:50       ` Martin Schwidefsky
2014-11-28 18:23 ` [RFC PATCH 25/30] cputime: Remove temporary irqtime states Frederic Weisbecker
2014-11-28 18:23 ` [RFC PATCH 26/30] cputime: Push time to account_user_time() in nanosecs Frederic Weisbecker
2014-11-28 18:23 ` [RFC PATCH 27/30] cputime: Push time to account_steal_time() " Frederic Weisbecker
2014-11-28 18:23 ` [RFC PATCH 28/30] cputime: Push time to account_idle_time() " Frederic Weisbecker
2014-11-28 18:23 ` [RFC PATCH 29/30] cputime: Push time to account_guest_time() " Frederic Weisbecker
2014-11-28 18:24 ` [RFC PATCH 30/30] cputime: Push time to account_system_time() " Frederic Weisbecker

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=20141201151402.31a6cc9a@mschwide \
    --to=schwidefsky@de.ibm.com \
    --cc=benh@kernel.crashing.org \
    --cc=fengguang.wu@intel.com \
    --cc=fweisbec@gmail.com \
    --cc=heiko.carstens@de.ibm.com \
    --cc=linux-kernel@vger.kernel.org \
    --cc=mingo@kernel.org \
    --cc=oleg@redhat.com \
    --cc=paulus@samba.org \
    --cc=peterz@infradead.org \
    --cc=riel@redhat.com \
    --cc=tglx@linutronix.de \
    --cc=tony.luck@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.