From: "Maciej W. Rozycki" <macro@linux-mips.org>
To: Wu Zhangjin <wuzhangjin@gmail.com>
Cc: David Daney <ddaney@caviumnetworks.com>,
linux-mips@linux-mips.org, linux-kernel@vger.kernel.org,
zhangfx@lemote.com, zhouqg@gmail.com,
Ralf Baechle <ralf@linux-mips.org>,
rostedt@goodmis.org, Frederic Weisbecker <fweisbec@gmail.com>,
Ingo Molnar <mingo@elte.hu>, Nicholas Mc Guire <der.herr@hofr.at>,
Richard Sandiford <rdsandiford@googlemail.com>,
Patrik Kluba <kpajko79@gmail.com>,
Thomas Gleixner <tglx@linutronix.de>,
Michal Simek <monstr@monstr.eu>
Subject: Re: [PATCH v7 04/17] tracing: add static function tracer support for MIPS
Date: Wed, 11 Nov 2009 13:15:02 +0000 (GMT) [thread overview]
Message-ID: <alpine.LFD.2.00.0911111309170.10184@eddie.linux-mips.org> (raw)
In-Reply-To: <1257907351.2922.37.camel@falcon.domain.org>
On Wed, 11 Nov 2009, Wu Zhangjin wrote:
> > -mlong-calls really degrades performance. I have seen things like 6%
> > drop in network packet forwarding rates with -mlong-calls.
> >
>
> so much drop? seems only two instructions added for it: lui, addi. from
> this view point, I think the -fno-omit-frame-pointer(add, sd, move...)
> will also bring with much drop.
No, register jumps cannot be predicted -- this is where the performance
goes on any serious processor -- the two extra instructions are nothing
compared to that. OTOH frame pointer calculations are pure arithmetic, so
you only lose time incurred by the instructions themselves.
Maciej
next prev parent reply other threads:[~2009-11-11 13:15 UTC|newest]
Thread overview: 36+ messages / expand[flat|nested] mbox.gz Atom feed top
2009-11-09 15:29 [PATCH v7 00/17] ftrace " Wu Zhangjin
2009-11-09 15:31 ` [PATCH v7 01/17] tracing: convert trace_clock_local() as weak function Wu Zhangjin
2009-11-09 15:31 ` [PATCH v7 02/17] tracing: add mips_timecounter_read() for MIPS Wu Zhangjin
2009-11-09 15:31 ` [PATCH v7 03/17] tracing: add MIPS specific trace_clock_local() Wu Zhangjin
2009-11-10 17:48 ` David Daney
2009-11-11 2:47 ` Wu Zhangjin
2009-11-09 15:31 ` [PATCH v7 04/17] tracing: add static function tracer support for MIPS Wu Zhangjin
2009-11-10 0:26 ` David Daney
2009-11-10 1:00 ` Wu Zhangjin
2009-11-10 16:43 ` David Daney
2009-11-11 2:42 ` Wu Zhangjin
2009-11-11 3:13 ` Ralf Baechle
2009-11-11 13:30 ` Maciej W. Rozycki
2009-11-12 21:16 ` Ralf Baechle
2009-11-11 14:13 ` Maciej W. Rozycki
2009-11-13 16:50 ` Ralf Baechle
2009-11-11 13:15 ` Maciej W. Rozycki [this message]
2009-11-11 13:51 ` Wu Zhangjin
2009-11-11 14:18 ` Maciej W. Rozycki
2009-11-11 14:27 ` Wu Zhangjin
2009-11-12 11:06 ` Wu Zhangjin
2009-11-09 15:31 ` [PATCH v7 05/17] tracing: enable HAVE_FUNCTION_TRACE_MCOUNT_TEST " Wu Zhangjin
2009-11-09 15:31 ` [PATCH v7 06/17] tracing: add an endian argument to scripts/recordmcount.pl Wu Zhangjin
2009-11-09 15:31 ` [PATCH v7 07/17] tracing: add dynamic function tracer support for MIPS Wu Zhangjin
2009-11-09 15:31 ` [PATCH v7 08/17] tracing: add IRQENTRY_EXIT section " Wu Zhangjin
2009-11-09 15:31 ` [PATCH v7 09/17] tracing: define a new __time_notrace annotation flag Wu Zhangjin
2009-11-09 15:31 ` [PATCH v7 10/17] tracing: not trace the timecounter_read* in kernel/time/clocksource.c Wu Zhangjin
2009-11-09 15:31 ` [PATCH v7 11/17] tracing: not trace mips_timecounter_read() for MIPS Wu Zhangjin
2009-11-09 15:31 ` [PATCH v7 12/17] tracing: add function graph tracer support " Wu Zhangjin
2009-11-09 15:31 ` [PATCH v7 13/17] tracing: add dynamic function graph tracer " Wu Zhangjin
2009-11-09 15:31 ` [PATCH v7 14/17] tracing: make ftrace for MIPS work without -fno-omit-frame-pointer Wu Zhangjin
2009-11-09 15:31 ` [PATCH v7 15/17] tracing: make ftrace for MIPS more robust Wu Zhangjin
2009-11-09 15:31 ` [PATCH v7 16/17] tracing: reserve $12(t0) for mcount-ra-address of gcc 4.5 Wu Zhangjin
2009-11-09 15:31 ` [PATCH v7 17/17] tracing: make function graph tracer work with -mmcount-ra-address Wu Zhangjin
2009-11-09 22:34 ` David Daney
2009-11-10 2:42 ` Wu Zhangjin
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=alpine.LFD.2.00.0911111309170.10184@eddie.linux-mips.org \
--to=macro@linux-mips.org \
--cc=ddaney@caviumnetworks.com \
--cc=der.herr@hofr.at \
--cc=fweisbec@gmail.com \
--cc=kpajko79@gmail.com \
--cc=linux-kernel@vger.kernel.org \
--cc=linux-mips@linux-mips.org \
--cc=mingo@elte.hu \
--cc=monstr@monstr.eu \
--cc=ralf@linux-mips.org \
--cc=rdsandiford@googlemail.com \
--cc=rostedt@goodmis.org \
--cc=tglx@linutronix.de \
--cc=wuzhangjin@gmail.com \
--cc=zhangfx@lemote.com \
--cc=zhouqg@gmail.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
Powered by JetHome