linux-kernel - Re: [tip:tracing/printk] tracing: optimize trace

lists.openwall.net		lists / announce owl-users owl-dev john-users john-dev passwdqc-users yescrypt popa3d-users / oss-security kernel-hardening musl sabotage tlsify passwords / crypt-dev xvendor / Bugtraq Full-Disclosure linux-kernel linux-netdev linux-ext4 linux-hardening linux-cve-announce PHC
Open Source and information security mailing list archives

Hash Suite for Android: free password hash cracker in your pocket

[<prev] [next>] [<thread-prev] [thread-next>] [day] [month] [year] [list]

Message-ID: <alpine.DEB.2.00.0903091322050.2203@gandalf.stny.rr.com>
Date:	Mon, 9 Mar 2009 13:23:12 -0400 (EDT)
From:	Steven Rostedt <rostedt@...dmis.org>
To:	mingo@...hat.com, hpa@...or.com, linux-kernel@...r.kernel.org,
	fweisbec@...il.com, peterz@...radead.org, tglx@...utronix.de,
	mingo@...e.hu
cc:	linux-tip-commits@...r.kernel.org
Subject: Re: [tip:tracing/printk] tracing: optimize trace_printk()


On Mon, 9 Mar 2009, Ingo Molnar wrote:
> 
> tracing: optimize trace_printk()
> 
> Impact: micro-optimization
> 
> trace_printk() does this unconditionally:
> 
> 	trace_printk_fmt = fmt;
> 
> Where trace_printk_fmt is an entry into a global array. This is
> very SMP-unfriendly.
> 
> So only write it once per bootup.
> 
> Cc: Frederic Weisbecker <fweisbec@...il.com>
> Cc: Steven Rostedt <rostedt@...dmis.org>
> Cc: Peter Zijlstra <peterz@...radead.org>
> LKML-Reference: <1236356510-8381-5-git-send-email-fweisbec@...il.com>
> Signed-off-by: Ingo Molnar <mingo@...e.hu>
> 
> 
> ---
>  include/linux/kernel.h |   10 ++++++++--
>  1 files changed, 8 insertions(+), 2 deletions(-)
> 
> diff --git a/include/linux/kernel.h b/include/linux/kernel.h
> index 4e726b9..7742798 100644
> --- a/include/linux/kernel.h
> +++ b/include/linux/kernel.h
> @@ -454,7 +454,10 @@ do {									\
>  do {									\
>  	static const char *trace_printk_fmt				\
>  	__attribute__((section("__trace_printk_fmt")));			\
> -	trace_printk_fmt = fmt;					\
> +									\
> +	if (!trace_printk_fmt)						\
> +		trace_printk_fmt = fmt;					\
> +									\

But this is a static init. That is, it is done at initialization and not
every time.

The change actually slows down the system.

>  	__trace_printk_check_format(fmt, ##args);			\
>  	__trace_printk(_THIS_IP_, trace_printk_fmt, ##args);		\
>  } while (0)
> @@ -467,7 +470,10 @@ __trace_printk(unsigned long ip, const char *fmt, ...)
>  do {									\
>  	static const char *trace_printk_fmt				\
>  	__attribute__((section("__trace_printk_fmt")));			\
> -	trace_printk_fmt = fmt;					\
> +									\
> +	if (!trace_printk_fmt)						\
> +		trace_printk_fmt = fmt;					\
> +									\

Same here.

-- Steve

>  	__ftrace_vprintk(_THIS_IP_, trace_printk_fmt, vargs);		\
>  } while (0)
>  
> 
--
To unsubscribe from this list: send the line "unsubscribe linux-kernel" in
the body of a message to majordomo@...r.kernel.org
More majordomo info at  http://vger.kernel.org/majordomo-info.html
Please read the FAQ at  http://www.tux.org/lkml/