From mboxrd@z Thu Jan 1 00:00:00 1970 Return-Path: Received: from smtprelay0069.hostedemail.com ([216.40.44.69]:57599 "EHLO smtprelay.hostedemail.com" rhost-flags-OK-OK-OK-FAIL) by vger.kernel.org with ESMTP id S964833AbaFSViM (ORCPT ); Thu, 19 Jun 2014 17:38:12 -0400 Message-ID: <53A3584D.1080708@nellans.org> Date: Thu, 19 Jun 2014 16:38:21 -0500 From: David Nellans MIME-Version: 1.0 Subject: Re: fio execution issue on Android device with MediaTek References: <53A3505F.1000809@nellans.org> <53A3527A.1000800@nellans.org> In-Reply-To: Content-Type: text/plain; charset=UTF-8; format=flowed Content-Transfer-Encoding: 7bit Sender: fio-owner@vger.kernel.org List-Id: fio@vger.kernel.org To: David N Cc: fio@vger.kernel.org what -march are you actually compiling for and under what distro? On 06/19/2014 04:25 PM, David N wrote: > Hi David, > > Yes, it's mt6572 with armv7 rev 3. I didn't do any changes to fio. > Just pulled the latest version, compiled, and pushed the binary to the > device. I tried the same binary on Samsung S4 with qualcomm, and it > worked fine. > > Thanks, > -David Nguyen > > On Thu, Jun 19, 2014 at 2:13 PM, David Nellans wrote: >> I may have actually spoken prematurely - if the krait version is running v7a >> and compiles for armeabi-v7a >> but the mt6572 is only supports armeabi you could run into ABI issues. >> either way, still very unlikely its a fio issue. >> >> >> On 06/19/2014 04:04 PM, David Nellans wrote: >>> generally speaking taking a pre-compiled binary from one machine to >>> another is a dicey proposition >>> but in this case you're moving from a krait 400? which runs armv7 to the >>> MT6572 which is a cortex A-7 >>> which are the same ISA rev. are you running the exact same distro and/or >>> set of libs on them too? >>> changes there in glibc, will cause issues. cross compiling for x86 >>> certainly isn't going to fix your problems! >>> >>> just for good measure I did just compile and run fio tip on a tegra k1 >>> running ubuntu 13.04 (3.10.33 kern) >>> and it seems to be working just fine. have you managed to get anything at >>> all to work via this method? >>> i doubt its an issue specific to fio. >>> >>> - the real David N >>> >>> On 06/19/2014 03:39 PM, David N wrote: >>>> Hi all, >>>> >>>> I got fio working fine on a device with Qualcomm Snapdragon but >>>> executing that same compiled binary gave me "sh: ./fio: not >>>> executable: magic 7F45" on a MediaTek (MT6572) device. >>>> >>>> I tried to recompile both for ARM and x86 but still the same issue. >>>> The binary is executable (did chmod it), so I'm not sure what is >>>> causing this. I'd very much appreciate any input. >>>> >>>> Thanks much! >>>> David >>>> -- >>>> To unsubscribe from this list: send the line "unsubscribe fio" in >>>> the body of a message to majordomo@vger.kernel.org >>>> More majordomo info at http://vger.kernel.org/majordomo-info.html >>>