LKML Archive on lore.kernel.org
help / color / mirror / Atom feed
From: Lai Jiangshan <laijs@cn.fujitsu.com>
To: Ingo Molnar <mingo@elte.hu>
Cc: Mathieu Desnoyers <compudj@krystal.dyndns.org>,
	Linux Kernel Mailing List <linux-kernel@vger.kernel.org>
Subject: Re: [PATCH tip/tracing/markers] new probes manager
Date: Tue, 28 Oct 2008 09:17:52 +0800	[thread overview]
Message-ID: <49066840.2070408@cn.fujitsu.com> (raw)
In-Reply-To: <20081027182655.GA11494@elte.hu>

Ingo Molnar wrote:
> * Mathieu Desnoyers <compudj@krystal.dyndns.org> wrote:
>>> Do you have performance measurements for this ? On x86 it's a nop,
>>> AFAIK.
>> My statement above is inexact : x86_64 uses lfence for rmb(). But
>> numbers would still be welcome.
> 
> yes, the statement that rmb() is very expensive looks dubious. It is 
> absolutely cheap everywhere.
> 
> 	Ingo
> 
> 
> 

On x86 it's _NOT_ a nop.

i386
#define rmb() alternative("lock; addl $0,0(%%esp)", "lfence", X86_FEATURE_XMM2)

uses the "lock" prefix.

x86_64
#define rmb()	asm volatile("lfence":::"memory")

uses the "lfence"

these two are harm for cache. rmb is exactly a expensive operator.

rmb() is indeed cheaper than any other atomic-operator(atomic, spin_lock .. etc)
everywhere. but In a fast path, avoiding rmb() is worthy.


		Thanx, Lai


      parent reply	other threads:[~2008-10-28  1:21 UTC|newest]

Thread overview: 6+ messages / expand[flat|nested]  mbox.gz  Atom feed  top
2008-10-23  2:47 Lai Jiangshan
2008-10-27 15:58 ` Mathieu Desnoyers
2008-10-27 16:30   ` Mathieu Desnoyers
2008-10-27 18:26     ` Ingo Molnar
2008-10-27 23:13       ` Paul Mackerras
2008-10-28  1:17       ` Lai Jiangshan [this message]

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=49066840.2070408@cn.fujitsu.com \
    --to=laijs@cn.fujitsu.com \
    --cc=compudj@krystal.dyndns.org \
    --cc=linux-kernel@vger.kernel.org \
    --cc=mingo@elte.hu \
    --subject='Re: [PATCH tip/tracing/markers] new probes manager' \
    /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

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).