From: Stanislaw Gruszka <sgruszka@redhat.com>
To: Frederic Weisbecker <fweisbec@gmail.com>
Cc: Ingo Molnar <mingo@kernel.org>,
LKML <linux-kernel@vger.kernel.org>,
Tony Luck <tony.luck@intel.com>,
Wanpeng Li <wanpeng.li@hotmail.com>,
Peter Zijlstra <peterz@infradead.org>,
Michael Ellerman <mpe@ellerman.id.au>,
Heiko Carstens <heiko.carstens@de.ibm.com>,
Benjamin Herrenschmidt <benh@kernel.crashing.org>,
Thomas Gleixner <tglx@linutronix.de>,
Paul Mackerras <paulus@samba.org>,
Fenghua Yu <fenghua.yu@intel.com>, Rik van Riel <riel@redhat.com>,
Martin Schwidefsky <schwidefsky@de.ibm.com>
Subject: Re: [GIT PULL] cputime: Convert core use of cputime_t to nsecs
Date: Mon, 30 Jan 2017 16:29:29 +0100 [thread overview]
Message-ID: <20170130152928.GD2669@redhat.com> (raw)
In-Reply-To: <20170130145648.GA16945@lerouge>
On Mon, Jan 30, 2017 at 03:56:49PM +0100, Frederic Weisbecker wrote:
> On Mon, Jan 30, 2017 at 03:32:24PM +0100, Stanislaw Gruszka wrote:
> > On Mon, Jan 30, 2017 at 05:46:43AM +0100, Frederic Weisbecker wrote:
> > > Now lets admit one drawback: s390 and powerpc with
> > > CONFIG_VIRT_CPU_ACCOUNTING_NATIVE have new cputime_t to nsecs conversion
> > > on cputime accounting path. But this should be leveraged by the recent
> > > changes which delay the cputime accounting to tick and context switch.
> >
> > I think it would be worth to mention that there are other drawbacks on
> > 32bit architectures that use cputime-jiffies currently, like:
> > - cache utilization will be worse
>
> Due to utime and stime becoming 64 bits? Yeah indeed.
:-) Well, it is possible that something that use to fit into one cache
line, now will be consuming 2 cache lines and results more cache misses.
In general, this patchset seems to be nice cleanup of code, but how it
affect runtime efficiency is not clear and might depend on .config
and architecture. However seems 32bit embedded users will be affected
negatively.
Stanislaw
next prev parent reply other threads:[~2017-01-30 15:58 UTC|newest]
Thread overview: 82+ messages / expand[flat|nested] mbox.gz Atom feed top
2017-01-30 4:46 [GIT PULL] cputime: Convert core use of cputime_t to nsecs Frederic Weisbecker
2017-01-30 14:32 ` Stanislaw Gruszka
2017-01-30 14:56 ` Frederic Weisbecker
2017-01-30 15:29 ` Stanislaw Gruszka [this message]
2017-01-31 3:09 ` [PATCH RESEND 01/36] jiffies: Reuse TICK_NSEC instead of NSEC_PER_JIFFY Frederic Weisbecker
2017-02-01 9:49 ` [tip:sched/core] " tip-bot for Frederic Weisbecker
2017-01-31 3:09 ` [PATCH RESEND 02/36] time: Introduce jiffies64_to_nsecs() Frederic Weisbecker
2017-02-01 9:50 ` [tip:sched/core] " tip-bot for Frederic Weisbecker
2017-01-31 3:09 ` [PATCH RESEND 03/36] sched: Remove unused INIT_CPUTIME macro Frederic Weisbecker
2017-02-01 9:50 ` [tip:sched/core] sched/cputime: Remove the " tip-bot for Frederic Weisbecker
2017-01-31 3:09 ` [PATCH RESEND 04/36] cputime: Convert kcpustat to nsecs Frederic Weisbecker
2017-02-01 9:51 ` [tip:sched/core] sched/cputime: " tip-bot for Frederic Weisbecker
2017-01-31 3:09 ` [PATCH RESEND 05/36] macintosh/rack-meter: Remove cputime_t internal use Frederic Weisbecker
2017-02-01 9:51 ` [tip:sched/core] macintosh/rack-meter: Convert cputime64_t use to u64 tip-bot for Frederic Weisbecker
2017-01-31 3:09 ` [PATCH RESEND 06/36] cputime: Convert guest time accounting to nsecs Frederic Weisbecker
2017-02-01 9:52 ` [tip:sched/core] sched/cputime: Convert guest time accounting to nsecs (u64) tip-bot for Frederic Weisbecker
2017-01-31 3:09 ` [PATCH RESEND 07/36] cputime: Special API to return old-typed cputime Frederic Weisbecker
2017-02-01 9:52 ` [tip:sched/core] sched/cputime: Introduce special task_cputime_t() " tip-bot for Frederic Weisbecker
2017-01-31 3:09 ` [PATCH RESEND 08/36] cputime: Convert task/group cputime to nsecs Frederic Weisbecker
2017-02-01 9:53 ` [tip:sched/core] sched/cputime: " tip-bot for Frederic Weisbecker
2017-01-31 3:09 ` [PATCH RESEND 09/36] alpha: Convert obsolete cputime_t " Frederic Weisbecker
2017-02-01 9:53 ` [tip:sched/core] " tip-bot for Frederic Weisbecker
2017-01-31 3:09 ` [PATCH RESEND 10/36] x86: Convert obsolete cputime type " Frederic Weisbecker
2017-02-01 9:54 ` [tip:sched/core] " tip-bot for Frederic Weisbecker
2017-01-31 3:09 ` [PATCH RESEND 11/36] isdn: " Frederic Weisbecker
2017-02-01 9:54 ` [tip:sched/core] " tip-bot for Frederic Weisbecker
2017-01-31 3:09 ` [PATCH RESEND 12/36] binfmt: " Frederic Weisbecker
2017-02-01 9:55 ` [tip:sched/core] fs/binfmt: " tip-bot for Frederic Weisbecker
2017-01-31 3:09 ` [PATCH RESEND 13/36] acct: " Frederic Weisbecker
2017-02-01 9:55 ` [tip:sched/core] " tip-bot for Frederic Weisbecker
2017-01-31 3:09 ` [PATCH RESEND 14/36] delaycct: " Frederic Weisbecker
2017-02-01 9:56 ` [tip:sched/core] " tip-bot for Frederic Weisbecker
2017-01-31 3:09 ` [PATCH RESEND 15/36] tsacct: " Frederic Weisbecker
2017-02-01 9:56 ` [tip:sched/core] " tip-bot for Frederic Weisbecker
2017-01-31 3:09 ` [PATCH RESEND 16/36] signal: " Frederic Weisbecker
2017-02-01 9:57 ` [tip:sched/core] " tip-bot for Frederic Weisbecker
2017-01-31 3:09 ` [PATCH RESEND 17/36] cputime: Increment kcpustat directly on irqtime account Frederic Weisbecker
2017-02-01 9:58 ` [tip:sched/core] sched/cputime: " tip-bot for Frederic Weisbecker
2017-01-31 3:09 ` [PATCH RESEND 18/36] posix-timers: Use TICK_NSEC instead of a dynamically ad-hoc calculated version Frederic Weisbecker
2017-02-01 9:58 ` [tip:sched/core] timers/posix-timers: " tip-bot for Frederic Weisbecker
2017-01-31 3:09 ` [PATCH RESEND 19/36] posix-timers: Convert internals to use nsecs Frederic Weisbecker
2017-02-01 9:59 ` [tip:sched/core] timers/posix-timers: " tip-bot for Frederic Weisbecker
2017-01-31 3:09 ` [PATCH RESEND 20/36] itimer: Convert internal cputime_t units to nsec Frederic Weisbecker
2017-02-01 9:59 ` [tip:sched/core] timers/itimer: " tip-bot for Frederic Weisbecker
2017-01-31 3:09 ` [PATCH RESEND 21/36] sched: Remove temporary cputime_t accessors Frederic Weisbecker
2017-02-01 10:00 ` [tip:sched/core] sched/cputime: " tip-bot for Frederic Weisbecker
2017-01-31 3:09 ` [PATCH RESEND 22/36] cputime: Push time to account_user_time() in nsecs Frederic Weisbecker
2017-02-01 10:00 ` [tip:sched/core] sched/cputime: " tip-bot for Frederic Weisbecker
2017-01-31 3:09 ` [PATCH RESEND 23/36] cputime: Push time to account_steal_time() " Frederic Weisbecker
2017-02-01 10:01 ` [tip:sched/core] sched/cputime: " tip-bot for Frederic Weisbecker
2017-01-31 3:09 ` [PATCH RESEND 24/36] cputime: Push time to account_idle_time() " Frederic Weisbecker
2017-02-01 10:01 ` [tip:sched/core] sched/cputime: " tip-bot for Frederic Weisbecker
2017-01-31 3:09 ` [PATCH RESEND 25/36] cputime: Push time to account_system_time() " Frederic Weisbecker
2017-02-01 10:02 ` [tip:sched/core] sched/cputime: " tip-bot for Frederic Weisbecker
2017-01-31 3:09 ` [PATCH RESEND 26/36] cputime: Complete nsec conversion of tick based accounting Frederic Weisbecker
2017-02-01 10:02 ` [tip:sched/core] sched/cputime: " tip-bot for Frederic Weisbecker
2017-01-31 3:09 ` [PATCH RESEND 27/36] vtime: Return nsecs instead of cputime_t to account Frederic Weisbecker
2017-02-01 10:03 ` [tip:sched/core] sched/cputime, " tip-bot for Frederic Weisbecker
2017-01-31 3:09 ` [PATCH RESEND 28/36] cputime: Remove jiffies based cputime Frederic Weisbecker
2017-02-01 10:03 ` [tip:sched/core] sched/cputime: " tip-bot for Frederic Weisbecker
2017-01-31 3:09 ` [PATCH RESEND 29/36] ia64: Move nsecs based cputime headers to the last arch using it Frederic Weisbecker
2017-02-01 10:04 ` [tip:sched/core] ia64, sched/cputime: Move the " tip-bot for Frederic Weisbecker
2017-01-31 3:09 ` [PATCH RESEND 30/36] ia64: Convert vtime to use nsec units directly Frederic Weisbecker
2017-02-01 10:04 ` [tip:sched/core] " tip-bot for Frederic Weisbecker
2017-01-31 3:09 ` [PATCH RESEND 31/36] ia64: Remove unused cputime definitions Frederic Weisbecker
2017-02-01 10:05 ` [tip:sched/core] ia64, sched/cputime: " tip-bot for Frederic Weisbecker
2017-01-31 3:09 ` [PATCH RESEND 32/36] s390: Make arch_cpu_idle_time() to return nsecs Frederic Weisbecker
2017-02-01 10:05 ` [tip:sched/core] s390, sched/cputime: " tip-bot for Frederic Weisbecker
2017-01-31 3:09 ` [PATCH RESEND 33/36] powerpc: Remove unused cputime definitions Frederic Weisbecker
2017-02-01 10:06 ` [tip:sched/core] powerpc, sched/cputime: " tip-bot for Frederic Weisbecker
2017-01-31 3:09 ` [PATCH RESEND 34/36] s390: " Frederic Weisbecker
2017-02-01 10:06 ` [tip:sched/core] s390, sched/cputime: " tip-bot for Frederic Weisbecker
2017-01-31 3:09 ` [PATCH RESEND 35/36] cputime: Remove unused nsec_to_cputime Frederic Weisbecker
2017-02-01 10:07 ` [tip:sched/core] sched/cputime: Remove unused nsec_to_cputime() tip-bot for Frederic Weisbecker
2017-01-31 3:09 ` [PATCH RESEND 36/36] cputime: Remove asm generic headers Frederic Weisbecker
2017-02-01 10:07 ` [tip:sched/core] sched/cputime: Remove generic asm headers tip-bot for Frederic Weisbecker
2017-02-06 13:49 ` [GIT PULL] cputime: Convert core use of cputime_t to nsecs Frederic Weisbecker
2017-02-07 8:08 ` Ingo Molnar
2017-02-07 14:06 ` Frederic Weisbecker
2017-02-07 18:41 ` Ingo Molnar
2017-02-21 5:08 ` hejianet
2017-02-22 14:30 ` 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=20170130152928.GD2669@redhat.com \
--to=sgruszka@redhat.com \
--cc=benh@kernel.crashing.org \
--cc=fenghua.yu@intel.com \
--cc=fweisbec@gmail.com \
--cc=heiko.carstens@de.ibm.com \
--cc=linux-kernel@vger.kernel.org \
--cc=mingo@kernel.org \
--cc=mpe@ellerman.id.au \
--cc=paulus@samba.org \
--cc=peterz@infradead.org \
--cc=riel@redhat.com \
--cc=schwidefsky@de.ibm.com \
--cc=tglx@linutronix.de \
--cc=tony.luck@intel.com \
--cc=wanpeng.li@hotmail.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 a public inbox, see mirroring instructions
for how to clone and mirror all data and code used for this inbox;
as well as URLs for NNTP newsgroup(s).