[<prev] [next>] [<thread-prev] [thread-next>] [day] [month] [year] [list]
Message-ID: <20100127232936.GI12567@ghostprotocols.net>
Date: Wed, 27 Jan 2010 21:29:36 -0200
From: Arnaldo Carvalho de Melo <acme@...radead.org>
To: Masami Hiramatsu <mhiramat@...hat.com>
Cc: Ingo Molnar <mingo@...e.hu>, linux-kernel@...r.kernel.org,
Frédéric Weisbecker <fweisbec@...il.com>,
Mike Galbraith <efault@....de>,
Peter Zijlstra <a.p.zijlstra@...llo.nl>,
Paul Mackerras <paulus@...ba.org>
Subject: Re: [PATCH 4/9] perf session: Create kernel maps in the constructor
Em Wed, Jan 27, 2010 at 06:17:58PM -0500, Masami Hiramatsu escreveu:
> Arnaldo Carvalho de Melo wrote:
> > From: Arnaldo Carvalho de Melo <acme@...hat.com>
> >
> > Removing one extra step needed in the tools that need this, fixing a bug
> > in 'perf probe' where this was not being done.
>
> Thanks,
> BTW, when O_WRONLY should be used? I guess I might misunderstand something
> in builtin-probe.c, and it should use O_RDONLY ...
O_RDONLY only when you have a perf.data file, O_WRONLY was thought for
'perf record', then for tools that want only to do symbol lookup it was
reused...
I think we should have a proper enum and more clearly specify these
semantics, as well as adding a MMAP mode so that we can lift the code
now in perf top somehow.
But for now using O_WRONLY provides what 'perf probe' needs, I guess :-)
- Arnaldo
--
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/
Powered by blists - more mailing lists