From mboxrd@z Thu Jan 1 00:00:00 1970 Return-Path: Received: (majordomo@vger.kernel.org) by vger.kernel.org via listexpand id S1754159AbbFITII (ORCPT ); Tue, 9 Jun 2015 15:08:08 -0400 Received: from mail.draxit.de ([78.47.242.75]:38844 "EHLO mail.draxit.de" rhost-flags-OK-OK-OK-OK) by vger.kernel.org with ESMTP id S1753519AbbFITIC (ORCPT ); Tue, 9 Jun 2015 15:08:02 -0400 X-Greylist: delayed 324 seconds by postgrey-1.27 at vger.kernel.org; Tue, 09 Jun 2015 15:08:02 EDT Message-ID: <5577384A.6000709@draxit.de> Date: Tue, 09 Jun 2015 21:02:34 +0200 From: Wolfgang Draxinger User-Agent: Mozilla/5.0 (X11; Linux x86_64; rv:31.0) Gecko/20100101 Icedove/31.6.0 MIME-Version: 1.0 To: linux-kernel@vger.kernel.org Subject: mmap vs. read/write performance/overhead revisited Content-Type: text/plain; charset=utf-8; format=flowed Content-Transfer-Encoding: 7bit Sender: linux-kernel-owner@vger.kernel.org List-ID: X-Mailing-List: linux-kernel@vger.kernel.org Hi! So how is it _today_ with the current 4.x kernels when it comes to mmap vs read(2)/write(2)? Either it's my Google-foo lacking or the most recent comment on the topic really dates back 15 years, but this is the only substancial background information relevant for Linux I did find: http://marc.info/?l=linux-kernel&m=95496636207616&w=2 ... that was 15 years ago, the beaver was not even conceived, not to speak going into detox, or even its predecessor. So I'm wondering, how relevant are the deliberations of back then today? I've got a very practical application for which this deliberation is relevant, but I don't want to spam the list with a technical lecture on ultra high speed OCT imaging. Cheers, Wolfgang