Received-SPF: pass (google.com: domain of linux-kernel-owner@vger.kernel.org designates 23.128.96.18 as permitted sender) client-ip=23.128.96.18;
Date:   Sat, 11 Sep 2021 16:33:52 +0200
From:   Peter Zijlstra <peterz@infradead.org>
To:     Yinan Liu <yinan@linux.alibaba.com>
Cc:     rostedt@goodmis.org, mark-pk.tsai@mediatek.com, mingo@redhat.com,
        linux-kernel@vger.kernel.org
Subject: Re: [PATCH 2/2] scripts: ftrace - move the nop-processing in
 ftrace_init to compile time
Message-ID: <20210911143352.GA4323@worktop.programming.kicks-ass.net>
References: <20210911135043.16014-1-yinan@linux.alibaba.com>
 <20210911135043.16014-3-yinan@linux.alibaba.com>
MIME-Version: 1.0
Content-Type: text/plain; charset=us-ascii
Content-Disposition: inline
In-Reply-To: <20210911135043.16014-3-yinan@linux.alibaba.com>
Precedence: bulk

On Sat, Sep 11, 2021 at 09:50:43PM +0800, Yinan Liu wrote:
> When ftrace is enabled, ftrace_init will consume a period of
> time, usually around 15~20ms. Approximately 60% of the time is
> consumed by nop-processing. Moving the nop-processing to the
> compile time can speed up the kernel boot process.
> 
> performance test:
>         env:    Intel(R) Xeon(R) CPU E5-2682 v4 @ 2.50GHz

If you use objtool's -M argument instead of recordmcount, you already
get this and you can avoid running recordmcount entirely.