From mboxrd@z Thu Jan  1 00:00:00 1970
Return-Path: <linux-kernel-owner@vger.kernel.org>
Received: (majordomo@vger.kernel.org) by vger.kernel.org via listexpand
	id S1752205AbbEQHaU (ORCPT <rfc822;w@1wt.eu>);
	Sun, 17 May 2015 03:30:20 -0400
Received: from mail-wi0-f176.google.com ([209.85.212.176]:38622 "EHLO
	mail-wi0-f176.google.com" rhost-flags-OK-OK-OK-OK) by vger.kernel.org
	with ESMTP id S1751208AbbEQHaO (ORCPT
	<rfc822;linux-kernel@vger.kernel.org>);
	Sun, 17 May 2015 03:30:14 -0400
Date: Sun, 17 May 2015 09:30:08 +0200
From: Ingo Molnar <mingo@kernel.org>
To: Linus Torvalds <torvalds@linux-foundation.org>
Cc: Andy Lutomirski <luto@amacapital.net>, Davidlohr Bueso <dave@stgolabs.net>,
        Peter Anvin <hpa@zytor.com>, Denys Vlasenko <dvlasenk@redhat.com>,
        Linux Kernel Mailing List <linux-kernel@vger.kernel.org>,
        Tim Chen <tim.c.chen@linux.intel.com>, Borislav Petkov <bp@alien8.de>,
        Peter Zijlstra <peterz@infradead.org>,
        "Chandramouleeswaran, Aswin" <aswin@hp.com>,
        Peter Zijlstra <a.p.zijlstra@chello.nl>,
        Brian Gerst <brgerst@gmail.com>,
        Paul McKenney <paulmck@linux.vnet.ibm.com>,
        Thomas Gleixner <tglx@linutronix.de>, Jason Low <jason.low2@hp.com>,
        "linux-tip-commits@vger.kernel.org" 
	<linux-tip-commits@vger.kernel.org>
Subject: Re: [tip:x86/asm] x86: Pack function addresses tightly as well
Message-ID: <20150517073008.GA6571@gmail.com>
References: <20150410121808.GA19918@gmail.com>
 <tip-4874fe1eeb40b403a8c9d0ddeb4d166cab3f37ba@git.kernel.org>
 <CA+55aFywCXk083w78cQGbRKh-ERLtE8v9PZhqxaHcyHJxSNsFQ@mail.gmail.com>
 <20150517055551.GB17002@gmail.com>
 <20150517070929.GA23344@gmail.com>
MIME-Version: 1.0
Content-Type: text/plain; charset=us-ascii
Content-Disposition: inline
In-Reply-To: <20150517070929.GA23344@gmail.com>
User-Agent: Mutt/1.5.23 (2014-03-12)
Sender: linux-kernel-owner@vger.kernel.org
List-ID: <linux-kernel.vger.kernel.org>
X-Mailing-List: linux-kernel@vger.kernel.org


* Ingo Molnar <mingo@kernel.org> wrote:

> The median function size is around 1 cacheline (64-byte one), ~80% 
> fitting into two cachelines, with a big peak for very small 
> functions that make up something like 20% of all functions [...]

Correction:

   32% of kernel functions fit into a single cacheline,
   55% fit into two cachelines,
   70% into three cachelines,
   76% into four cachelines

so the tail is longer than my quick read of the graph suggested.

OTOH, probability of use is biased towards smaller functions: we tend 
to use smaller, facility functions more frequently.

Thanks,

	Ingo