From mboxrd@z Thu Jan  1 00:00:00 1970
Return-Path: <linux-fsdevel-owner@vger.kernel.org>
Received: from mail-oi1-f195.google.com ([209.85.167.195]:42361 "EHLO
        mail-oi1-f195.google.com" rhost-flags-OK-OK-OK-OK) by vger.kernel.org
        with ESMTP id S1726724AbfAGWlk (ORCPT
        <rfc822;linux-fsdevel@vger.kernel.org>);
        Mon, 7 Jan 2019 17:41:40 -0500
Received: by mail-oi1-f195.google.com with SMTP id w13so1739390oiw.9
        for <linux-fsdevel@vger.kernel.org>; Mon, 07 Jan 2019 14:41:39 -0800 (PST)
MIME-Version: 1.0
References: <1546873978-27797-1-git-send-email-longman@redhat.com> <20190107223214.GZ6311@dastard>
In-Reply-To: <20190107223214.GZ6311@dastard>
From: Daniel Colascione <dancol@google.com>
Date: Mon, 7 Jan 2019 17:41:28 -0500
Message-ID: <CAKOZueuHGg=F8se1AQqswZWCEco=ScmudWq5X5s1qS4+LCtgWw@mail.gmail.com>
Subject: Re: [PATCH 0/2] /proc/stat: Reduce irqs counting performance overhead
To: Dave Chinner <david@fromorbit.com>
Cc: Waiman Long <longman@redhat.com>,
        Andrew Morton <akpm@linux-foundation.org>,
        Alexey Dobriyan <adobriyan@gmail.com>,
        Luis Chamberlain <mcgrof@kernel.org>,
        Kees Cook <keescook@chromium.org>,
        Jonathan Corbet <corbet@lwn.net>,
        linux-kernel <linux-kernel@vger.kernel.org>,
        "open list:DOCUMENTATION" <linux-doc@vger.kernel.org>,
        Linux FS Devel <linux-fsdevel@vger.kernel.org>,
        Davidlohr Bueso <dave@stgolabs.net>,
        Miklos Szeredi <miklos@szeredi.hu>,
        Randy Dunlap <rdunlap@infradead.org>
Content-Type: text/plain; charset="UTF-8"
Sender: linux-fsdevel-owner@vger.kernel.org
List-ID: <linux-fsdevel.vger.kernel.org>

On Mon, Jan 7, 2019 at 5:32 PM Dave Chinner <david@fromorbit.com> wrote:
>
> On Mon, Jan 07, 2019 at 10:12:56AM -0500, Waiman Long wrote:
> > As newer systems have more and more IRQs and CPUs available in their
> > system, the performance of reading /proc/stat frequently is getting
> > worse and worse.
>
> Because the "roll-your-own" per-cpu counter implementaiton has been
> optimised for low possible addition overhead on the premise that
> summing the counters is rare and isn't a performance issue. This
> patchset is a direct indication that this "summing is rare and can
> be slow" premise is now invalid.

Focusing on counter performance is, IMHO, missing the mark. Even if
interrupt count collection were made fast, there's *something* in any
particular /proc file that a particular reader doesn't need and that,
by being uselessly collected, needlessly slows that reader. There
should be a general-purpose way for /proc file readers to tell the
kernel which bits of information interest them on a particular read
syscall sequence or particular open(2) or something. Creating a new
proc file for every useful combination of attributes doesn't scale
either.