Date: Mon, 18 Sep 2006 08:25:27 -0400
From: "Frank Ch. Eigler" <fche@redhat.com>
To: Ingo Molnar <mingo@elte.hu>
Cc: Karim Yaghmour <karim@opersys.com>,
       Mathieu Desnoyers <mathieu.desnoyers@polymtl.ca>,
       Paul Mundt <lethal@linux-sh.org>,
       linux-kernel <linux-kernel@vger.kernel.org>,
       Ingo Molnar <mingo@redhat.com>, Jes Sorensen <jes@sgi.com>,
       Andrew Morton <akpm@osdl.org>, Roman Zippel <zippel@linux-m68k.org>,
       Tom Zanussi <zanussi@us.ibm.com>,
       Richard J Moore <richardj_moore@uk.ibm.com>,
       "Frank Ch. Eigler" <fche@redhat.com>,
       Michel Dagenais <michel.dagenais@polymtl.ca>,
       Christoph Hellwig <hch@infradead.org>,
       Greg Kroah-Hartman <gregkh@suse.de>,
       Thomas Gleixner <tglx@linutronix.de>, William Cohen <wcohen@redhat.com>,
       "Martin J. Bligh" <mbligh@mbligh.org>
Subject: Re: tracepoint maintainance models
Message-ID: <20060918122527.GC3951@redhat.com>
References: <450D182B.9060300@opersys.com> <20060917112128.GA3170@localhost.usen.ad.jp> <20060917143623.GB15534@elte.hu> <20060917153633.GA29987@Krystal> <20060918000703.GA22752@elte.hu> <450DF28E.3050101@opersys.com> <20060918011352.GB30835@elte.hu>
Mime-Version: 1.0
Content-Type: text/plain; charset=us-ascii
Content-Disposition: inline
In-Reply-To: <20060918011352.GB30835@elte.hu>
User-Agent: Mutt/1.4.1i
Sender: linux-kernel-owner@vger.kernel.org
Content-Length: 1365
Lines: 36

Hi -

mingo wrote:

> [...]
>   static int x;
>   void func(int a)
>        MARK(event, a);
>
> if a dynamic tracer installs a probe into that MARK() spot, it will
> have access to 'a', but it can also have access to 'x'. While a
> static in-source markup for _static tracers_, if it also wanted to
> have the 'x' information, would also have to add 'x' as a parameter:
> [...]

Without heroic measures taken by by a static tracer type of tool, this
is correct.

> For dynamic tracers no such 'parameter preparation' instructions
> would need to be generated by gcc.  (thus for example the runtime
> overhead would be lower for inactive tracepoints)

Any such additional code would be small, plus if properly marked up
with unlikely() and compiled with -freorder-blocks, it would all be
out-of-line.  This small cost could be worth the added benefit of
systemtap being able to probe that point without debugging information
present, and avoiding its slow & deliberate way of accessing
target-side variables like $x.  (The slow & deliberate part comes in
from the need to check any pointer dereferences involved.)

- FChE
-
To unsubscribe from this list: send the line "unsubscribe linux-kernel" in
the body of a message to majordomo@vger.kernel.org
More majordomo info at  http://vger.kernel.org/majordomo-info.html
Please read the FAQ at  http://www.tux.org/lkml/