From mboxrd@z Thu Jan 1 00:00:00 1970 Return-Path: Received: (majordomo@vger.kernel.org) by vger.kernel.org via listexpand id S1752802AbZKHOv7 (ORCPT ); Sun, 8 Nov 2009 09:51:59 -0500 Received: (majordomo@vger.kernel.org) by vger.kernel.org id S1752561AbZKHOv7 (ORCPT ); Sun, 8 Nov 2009 09:51:59 -0500 Received: from lucidpixels.com ([75.144.35.66]:50480 "EHLO lucidpixels.com" rhost-flags-OK-OK-OK-OK) by vger.kernel.org with ESMTP id S1751896AbZKHOv6 (ORCPT ); Sun, 8 Nov 2009 09:51:58 -0500 Date: Sun, 8 Nov 2009 09:52:03 -0500 (EST) From: Justin Piszcz To: linux-kernel@vger.kernel.org Subject: 2.6.31.4+Benchmarks: Core i5/7 - No turbo boost, maximum speed is always 2.93 GHz? Message-ID: User-Agent: Alpine 2.00 (DEB 1167 2008-08-23) MIME-Version: 1.0 Content-Type: TEXT/PLAIN; format=flowed; charset=US-ASCII Sender: linux-kernel-owner@vger.kernel.org List-ID: X-Mailing-List: linux-kernel@vger.kernel.org Hello, It looks like turbo boost is never activated... [ 23.322132] freq-table: target is 0 (2927000 kHz, 0) [ 23.322133] cpufreq-core: governor: change or update limits [ 23.322135] cpufreq-core: __cpufreq_governor for CPU 7, event 3 [ 23.322137] cpufreq-core: target for CPU 7: 2927000 kHz, relation 1 [ 23.322138] freq-table: request for target 2927000 kHz (relation: 1) for cpu 7 [ 23.322140] freq-table: target is 0 (2927000 kHz, 0) I tried setting it manually as well: cpufreq-set -g ondemand -d 1100000 -u 3600000 # cat /sys/devices/system/cpu/cpu*/cpufreq/*max* 2927000 2927000 2927000 2927000 2927000 2927000 2927000 2927000 2927000 2927000 2927000 2927000 2927000 2927000 2927000 2927000 -- Using the latest Intel BIOS on a DP55KG, I have run multiple tests and all seem to be within the noise: Q6600: 71.37user 0.56system 1:11.97elapsed 99%CPU (0avgtext+0avgdata 0maxresident)k 0inputs+0outputs (1major+2002minor)pagefaults 0swaps i870: - SpeedStep Tech: ON - C States: ON 50.14user 0.11system 0:50.27elapsed 99%CPU (0avgtext+0avgdata 0maxresident)k 0inputs+0outputs (0major+2022minor)pagefaults 0swaps 50.14user 0.11system 0:50.27elapsed 99%CPU (0avgtext+0avgdata 0maxresident)k 0inputs+0outputs (0major+2653minor)pagefaults 0swaps - SpeedStep Tech: OFF - C States: ON 49.63user 0.13system 0:49.81elapsed 99%CPU (0avgtext+0avgdata 0maxresident)k 0inputs+0outputs (1major+2021minor)pagefaults 0swaps 49.95user 0.07system 0:50.03elapsed 99%CPU (0avgtext+0avgdata 0maxresident)k 0inputs+0outputs (0major+2022minor)pagefaults 0swaps - SpeedStep Tech: OFF - C States: OFF 49.62user 0.11system 0:49.79elapsed 99%CPU (0avgtext+0avgdata 0maxresident)k 0inputs+0outputs (1major+2021minor)pagefaults 0swaps 50.12user 0.07system 0:50.20elapsed 99%CPU (0avgtext+0avgdata 0maxresident)k 0inputs+0outputs (0major+2022minor)pagefaults 0swaps - SpeedStep Tech: ON - C States: ON - ACPI_FREQ/KERNEL OPTIONS COMPILED IN - Set to: PERFORMANCE 44.50user 0.12system 0:44.69elapsed 99%CPU (0avgtext+0avgdata 0maxresident)k 0inputs+0outputs (1major+2022minor)pagefaults 0swaps 47.13user 0.09system 0:47.27elapsed 99%CPU (0avgtext+0avgdata 0maxresident)k 0inputs+0outputs (0major+2023minor)pagefaults 0swaps Still though, something does not seem right, 2.93 GHz -- if the CPU speed was really increasing to 3.60 GHz this would be much faster? File: linux-2.6.31.tar Benchmark: /usr/bin/time bzip2 -c -9 *tar > /dev/null