[<prev] [next>] [<thread-prev] [thread-next>] [day] [month] [year] [list]
Message-ID: <CAGdX0WGK+U1gg5YYALeviJSsPGF_5S3CjTNzNqVxSGeqDHfeqg@mail.gmail.com>
Date: Sat, 29 Mar 2014 15:38:38 +0800
From: Jovi Zhangwei <jovi.zhangwei@...il.com>
To: Andi Kleen <andi@...stfloor.org>
Cc: Ingo Molnar <mingo@...hat.com>,
Steven Rostedt <rostedt@...dmis.org>,
LKML <linux-kernel@...r.kernel.org>,
Masami Hiramatsu <masami.hiramatsu.pt@...achi.com>,
Greg Kroah-Hartman <gregkh@...uxfoundation.org>,
Frederic Weisbecker <fweisbec@...il.com>
Subject: Re: [PATCH 16/28] ktap: add runtime/amalg.c
Hi,
On Sat, Mar 29, 2014 at 2:52 AM, Andi Kleen <andi@...stfloor.org> wrote:
> Jovi Zhangwei <jovi.zhangwei@...il.com> writes:
>
>> Use amalgamation build make ktapvm.ko much smaller.
>>
>> No amalgamation build in x86_64:
>> ktapvm.ko: 2.4M
>>
>> amalgamation build in x86_64:
>> ktapvm.ko: 1.1M
>>
>> User can set use amalgamation build or not in Makefile.
>
> This seems dubious. Is that due to debug information?
>
> [if yes new enough toolchain can fix that]
>
> If it's due to code something is seriously wrong,
> perhaps in your inlines.
>
Change: The kernel module size without amalgamation build is: 3.1M
I guess it's not because of debug info.
Amalgamation build is a kind of simple 'LTO', it compiles the ktapvm as
one huge C file and allows GCC to generate faster and shorter code.
But I also surprised by the size gap, will spend some time to investigate it.
Thanks.
Jovi
--
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