Return-Path: Received: (majordomo@vger.kernel.org) by vger.kernel.org via listexpand id S1758158Ab2FOWJo (ORCPT ); Fri, 15 Jun 2012 18:09:44 -0400 Received: from mail-yx0-f174.google.com ([209.85.213.174]:55408 "EHLO mail-yx0-f174.google.com" rhost-flags-OK-OK-OK-OK) by vger.kernel.org with ESMTP id S1757954Ab2FOWJm (ORCPT ); Fri, 15 Jun 2012 18:09:42 -0400 MIME-Version: 1.0 In-Reply-To: <3908561D78D1C84285E8C5FCA982C28F1931FC85@ORSMSX104.amr.corp.intel.com> References: <20120615170659.GA4060@lizard> <1339780111-12075-3-git-send-email-anton.vorontsov@linaro.org> <3908561D78D1C84285E8C5FCA982C28F1931FC30@ORSMSX104.amr.corp.intel.com> <1339797308.25903.8.camel@gandalf.stny.rr.com> <3908561D78D1C84285E8C5FCA982C28F1931FC85@ORSMSX104.amr.corp.intel.com> Date: Fri, 15 Jun 2012 15:09:41 -0700 X-Google-Sender-Auth: HeWEHPWaysCAg3kssBwpcJKgpMY Message-ID: Subject: Re: [PATCH 3/6] pstore: Add persistent function tracing From: Colin Cross To: "Luck, Tony" Cc: Steven Rostedt , Anton Vorontsov , Greg Kroah-Hartman , Kees Cook , Frederic Weisbecker , Ingo Molnar , Arnd Bergmann , John Stultz , Shuah Khan , "arve@android.com" , Rebecca Schultz Zavin , Jesper Juhl , Randy Dunlap , Stephen Boyd , Thomas Meyer , Andrew Morton , Marco Stornelli , WANG Cong , "linux-kernel@vger.kernel.org" , "devel@driverdev.osuosl.org" , "linaro-kernel@lists.linaro.org" , "patches@linaro.org" , "kernel-team@android.com" Content-Type: text/plain; charset=ISO-8859-1 X-System-Of-Record: true Sender: linux-kernel-owner@vger.kernel.org List-ID: X-Mailing-List: linux-kernel@vger.kernel.org Content-Length: 1028 Lines: 20 On Fri, Jun 15, 2012 at 3:00 PM, Luck, Tony wrote: >> With function tracing the impact to performance is tremendous. Just >> recording two long words is a 130% hit to performance. Now multiply that >> to recording strings. > > If pstore is writing to a flash based backend - then there will be many > milli-seconds of delay. I think the time taken to convert from binary to > ascii would be insignificant. Function tracing into flash would be silly, adding milliseconds of overhead to every function call is enormous. The normal use case for this is tracing to persistent ram, and even the difference between 2 and 3 words in the binary format was noticeable. Converting to ascii would expand 2 words to at least 20 words, making the entire feature useless. -- To unsubscribe from this list: send the line "unsubscribe linux-kernel" in the body of a message to majordomo@vger.kernel.org More majordomo info at http://vger.kernel.org/majordomo-info.html Please read the FAQ at http://www.tux.org/lkml/