From owner-freebsd-mobile@FreeBSD.ORG Sun May 3 15:41:34 2009 Return-Path: Delivered-To: freebsd-mobile@freebsd.org Received: from mx1.freebsd.org (mx1.freebsd.org [IPv6:2001:4f8:fff6::34]) by hub.freebsd.org (Postfix) with ESMTP id D29E2106566C for ; Sun, 3 May 2009 15:41:34 +0000 (UTC) (envelope-from ivakras1@gmail.com) Received: from mail-bw0-f213.google.com (mail-bw0-f213.google.com [209.85.218.213]) by mx1.freebsd.org (Postfix) with ESMTP id 095B08FC0A for ; Sun, 3 May 2009 15:41:32 +0000 (UTC) (envelope-from ivakras1@gmail.com) Received: by bwz9 with SMTP id 9so3115825bwz.43 for ; Sun, 03 May 2009 08:41:32 -0700 (PDT) DKIM-Signature: v=1; a=rsa-sha256; c=relaxed/relaxed; d=gmail.com; s=gamma; h=domainkey-signature:received:received:from:reply-to:organization:to :subject:date:user-agent:references:in-reply-to:mime-version :content-type:content-transfer-encoding:content-disposition :message-id; bh=yY3RvrGSieuU4A+C0vvkAtP970FlULbcypk0v9+pm6I=; b=mhOITiUQuu9v5oa0pfTjvefi43GcSRLt5f6cJH8H7YU3rCIfgo6FZI0Knjxpy2r0Kf TfjknNpJe4ZVu/MPYYYm9/zVWa3PQVRQJ6V6+zEkhPUYHhC7+TGJcIM4WerczL3aydi9 vyV09SRzKTNYzcXEUOPDyOy0cZPyNrRLexV8g= DomainKey-Signature: a=rsa-sha1; c=nofws; d=gmail.com; s=gamma; h=from:reply-to:organization:to:subject:date:user-agent:references :in-reply-to:mime-version:content-type:content-transfer-encoding :content-disposition:message-id; b=xjcbdmiMflB6iQE1CJ5DyfYudg0n02Yr2wmjvGzBKnAXJ3uCYWVLCY1q+OxJ2I6A9s 6XoBJQr2yF5/a+BgZRQYBxt9jjWQPBcw6JdABx0fxgCnnrnOPWFnOpAfvp90Q7VhswN3 hfPSFug6E2FhZa6BmiUAwSlx5FHwim5mqeFOs= Received: by 10.204.102.15 with SMTP id e15mr4727247bko.196.1241365291984; Sun, 03 May 2009 08:41:31 -0700 (PDT) Received: from onyx_hp.dhcp.loc ([92.50.244.68]) by mx.google.com with ESMTPS id g28sm7602661fkg.5.2009.05.03.08.41.30 (version=TLSv1/SSLv3 cipher=RC4-MD5); Sun, 03 May 2009 08:41:31 -0700 (PDT) From: Dmitry Kolosov Organization: Home To: freebsd-mobile@freebsd.org Date: Sun, 3 May 2009 19:39:15 +0400 User-Agent: KMail/1.11.2 (FreeBSD/7.2-PRERELEASE; KDE/4.2.2; i386; ; ) References: In-Reply-To: MIME-Version: 1.0 Content-Type: Text/Plain; charset="koi8-r" Content-Transfer-Encoding: quoted-printable Content-Disposition: inline Message-Id: <200905031939.16089.ivakras1@gmail.com> Subject: Re: Hard drive for Dell Inspiron 5000e - place to buy X-BeenThere: freebsd-mobile@freebsd.org X-Mailman-Version: 2.1.5 Precedence: list Reply-To: ivakras1@gmail.com List-Id: Mobile computing with FreeBSD List-Unsubscribe: , List-Archive: List-Post: List-Help: List-Subscribe: , X-List-Received-Date: Sun, 03 May 2009 15:41:35 -0000 On =F0=D1=D4=CE=C9=C3=C1 01 =CD=C1=D1 2009 22:03:47 Missmolly1944@aol.com w= rote: > Hi, how much for the hard drive? Lou > **************Access 350+ FREE radio stations anytime from anywhere on th= e=20 > web. Get the Radio Toolbar!=20 > (http://toolbar.aol.com/aolradio/download.html?ncid=3Demlcntusdown0000000= 3) > _______________________________________________ > freebsd-mobile@freebsd.org mailing list > http://lists.freebsd.org/mailman/listinfo/freebsd-mobile > To unsubscribe, send any mail to "freebsd-mobile-unsubscribe@freebsd.org" >=20 That is subject for me. My WDC-WD2500BEVS hdd is about 56-60C in idle, i ca= n't handle laptop on laps. Power consumption is very high, less than 1 hou= r on battery. Thinking about SSD. From owner-freebsd-mobile@FreeBSD.ORG Sun May 3 22:18:25 2009 Return-Path: Delivered-To: freebsd-mobile@freebsd.org Received: from mx1.freebsd.org (mx1.freebsd.org [IPv6:2001:4f8:fff6::34]) by hub.freebsd.org (Postfix) with ESMTP id 0B2E8106564A; Sun, 3 May 2009 22:18:25 +0000 (UTC) (envelope-from mav@FreeBSD.org) Received: from cmail.optima.ua (cmail.optima.ua [195.248.191.121]) by mx1.freebsd.org (Postfix) with ESMTP id BAE548FC17; Sun, 3 May 2009 22:18:23 +0000 (UTC) (envelope-from mav@FreeBSD.org) X-Spam-Flag: SKIP X-Spam-Yversion: Spamooborona-2.1.0 Received: from [212.86.226.226] (account mav@alkar.net HELO mavbook.mavhome.dp.ua) by cmail.optima.ua (CommuniGate Pro SMTP 5.2.9) with ESMTPSA id 241853410; Mon, 04 May 2009 01:18:22 +0300 Message-ID: <49FE1826.4060000@FreeBSD.org> Date: Mon, 04 May 2009 01:18:14 +0300 From: Alexander Motin User-Agent: Thunderbird 2.0.0.21 (X11/20090405) MIME-Version: 1.0 To: FreeBSD-Current , freebsd-mobile@freebsd.org, FreeBSD acpi Content-Type: text/plain; charset=KOI8-R; format=flowed Content-Transfer-Encoding: 7bit Cc: Subject: Fighting for the power. X-BeenThere: freebsd-mobile@freebsd.org X-Mailman-Version: 2.1.5 Precedence: list List-Id: Mobile computing with FreeBSD List-Unsubscribe: , List-Archive: List-Post: List-Help: List-Subscribe: , X-List-Received-Date: Sun, 03 May 2009 22:18:25 -0000 I would like to summarize some of my knowledge on reducing FreeBSD power consumption and describe some new things I have recently implemented in 8-CURRENT. The main character of this story is my 12" Acer TravelMate 6292 laptop with C2D T7700 2.4GHz CPU, 965GM chipset and SATA HDD, under amd64 8-CURRENT. Modern systems, especially laptops, are implementing big number of power-saving technologies. Some of them are working automatically, other have significant requirements and need special system tuning or trade-offs to be effectively used. So here is the steps: 1. CPU CPU is the most consuming part of the system. Under the full load it alone may consume more then 40W of power, but for real laptop usage the most important is idle consumption. Core2Duo T7700 CPU has 2 cores, runs on 2.4GHz frequency, supports EIST technology with P-states at 2400, 2000, 1600, 1200 and 800MHz levels, supports C1, C2 and C3 idle C-states, plus throttling. So how can we use it: P-states and throttling Enabling powerd allows to effectively control CPU frequency/voltage depending on CPU load. powerd on recent system can handle it quite transparently. By default, frequency controlled via mix of EIST and throttling technologies. First one controls both core frequency and voltage, second - only core frequency. Both technologies give positive power-saving effect. But effect of throttling is small and can be completely hidden by using C2 state, that's why I recommend to disable throttling control by adding to /boot/loader.conf: hint.p4tcc.0.disabled=1 hint.acpi_throttle.0.disabled=1 In my case frequency/voltage control saves about 5W of idle power. C-states - C1 stops clock on some parts of CPU core during inactivity. It is safe, cheap and supported by CPUs for ages. System uses C1 state by default. - C2 state allows CPU to turn off all core clocks on idle. It is also cheap, but requires correct ACPI-chipset-CPU interoperation to be used. Use of C2 state can be enabled by adding to /etc/rc.conf: performance_cx_lowest="C2" economy_cx_lowest="C2" Effect from this state is not so big when powerd is used, but still noticeable, - C3 state allows CPU completely stop all internal clocks, reduce voltage and disconnect from system bus. This state gives additional power saving effect, but it is not cheap and require trade-offs. As soon as CPU is completely stopped in C3 state, local APIC timers in each CPU core, used by FreeBSD as event sources on SMP, are not functioning. It stops system time, breaks scheduling that makes system close to dead. The only solution for this problem is to use some external timers. Originally, before SMP era, FreeBSD used i8254 (for HZ) and RTC (for stats) chipset timers. I have made changes to 8-CURRENT to resurrect them for SMP systems. To use them, you can disable local APIC timers by adding to /boot/loader.conf: hint.apic.0.clock=0 Also, to drop/rise voltage on C3, CPU needs time (57us for my system). It means that C3 state can't be effectively used when system is waking up often. To increase inactivity periods we should reduce interrupt rate as much as possible by adding to loader.conf: kern.hz=100 It may increase system response time a bit, but it is not significant for laptop. Also we may avoid additional 128 interrupts per second per core, by the cost of scheduling precision, with using i8254 timer also for statistic collection purposes instead of RTC clock, by using another newly added option: hint.atrtc.0.clock=0 As result, system has only 100 interrupts per core and CPUs are using C3 with high efficiency: %sysctl dev.cpu |grep cx dev.cpu.0.cx_supported: C1/1 C2/1 C3/57 dev.cpu.0.cx_lowest: C3 dev.cpu.0.cx_usage: 0.00% 0.00% 100.00% last 7150us dev.cpu.1.cx_supported: C1/1 C2/1 C3/57 dev.cpu.1.cx_lowest: C3 dev.cpu.1.cx_usage: 0.00% 0.00% 100.00% last 2235us Result of effective C3 state usage, comparing to C2+powerd, is about 2W. 2. PCI devices PCI bus provides method to control device power. For example, I have completely no use for my FireWire controller and most of time - EHCI USB controller. Disabling them allows me to save about 3W of power. To disable all unneeded PCI devices you should build kernel without their drivers and add to loader.conf: hw.pci.do_power_nodriver=3 To enable devices back all you need to do is just load their drivers as modules. 3. Radios WiFi and Bluetooth adapters can consume significant power when used (up to 2W when my iwn WiFi is connected) or just enabled (0.5W). Disabling them with mechanical switch on laptop case saves energy even when they are not connected. 4. HDA modem I was surprised, but integrated HDA modem consumed about 1W of power even when not used. I have used the most radical solution - removed it mechanically from socket. Case surface in that area become much cooler. 5. HDA sound To reduce number of sound generated interrupts I have added to the loader.conf: hint.pcm.0.buffersize=65536 hint.pcm.1.buffersize=65536 hw.snd.feeder_buffersize=65536 hw.snd.latency=7 6. HDD First common recommendation is use tmpfs for temporary files. RAM is cheap, fast and anyway with you. Also you may try to setup automatic idle drive spin-down, but if it is the only system drive you should be careful, as every spin-up reduces drive's life time. For several months (until I have bought SATA SSD) I have successfully used SDHC card in built-in PCI sdhci card reader as main filesystem. On random read requests it is much faster then HDD, but it is very slow on random write. Same time it consumes almost nothing. USB drives could also be used, but effect is much less as EHCI USB controller consumes much power. Spinning-down my 2.5" Hitachi SATA HDD saves about 1W of power. Removing it completely saves 2W. 7. SATA Comparing to PATA, SATA interface uses differential signaling for data transfer. To work properly it has to transmit pseudo-random scrambled sequence even when idle. As you understand, that requires power. But SATA implements two power saving modes: PARTIAL and SLUMBER. These modes could be activated by either host or device if both sides support them. PARTIAL mode just stops scrambling, but keeps neutral link state, resume time is 50-100us. SLUMBER mode powers down interface completely, but respective resume time is 3-10ms. I have added minimal SATA power management to AHCI driver. There are hint.ata.X.pm_level loader tunables can be used to control it now. Setting it to 1 allows drive itself to initiate power saving, when it wish. Values 2 and 3 make AHCI controller to initiate PARTIAL and SLUMBER transitions after every command completion. Note that SATA power saving is not compatible with drive hot-swap, as controller unable to detect drive presence when link is powered-down. In my case PARTIAL mode saves 0.5W and SLUMBER - 0.8W of power. So what have I got? To monitor real system power consumption I am using information provided by ACPI battery via `acpiconf -i0` command: Original system: Design capacity: 4800 mAh Last full capacity: 4190 mAh Technology: secondary (rechargeable) Design voltage: 11100 mV Capacity (warn): 300 mAh Capacity (low): 167 mAh Low/warn granularity: 32 mAh Warn/full granularity: 32 mAh Model number: Victoria Serial number: 292 Type: LION OEM info: SIMPLO State: discharging Remaining capacity: 93% Remaining time: 2:24 Present rate: 1621 mA Voltage: 12033 mV Tuned system: %acpiconf -i0 Design capacity: 4800 mAh Last full capacity: 4190 mAh Technology: secondary (rechargeable) Design voltage: 11100 mV Capacity (warn): 300 mAh Capacity (low): 167 mAh Low/warn granularity: 32 mAh Warn/full granularity: 32 mAh Model number: Victoria Serial number: 292 Type: LION OEM info: SIMPLO State: discharging Remaining capacity: 94% Remaining time: 4:47 Present rate: 826 mA Voltage: 12231 mV So I have really doubled my on-battery time by this tuning - 4:47 hours instead of 2:24 with default settings. Preinstalled vendor-tuned Windows XP on the same system, provides maximum 3:20 hours. -- Alexander Motin From owner-freebsd-mobile@FreeBSD.ORG Sun May 3 23:44:31 2009 Return-Path: Delivered-To: freebsd-mobile@freebsd.org Received: from mx1.freebsd.org (mx1.freebsd.org [IPv6:2001:4f8:fff6::34]) by hub.freebsd.org (Postfix) with ESMTP id 3BAB21065673; Sun, 3 May 2009 23:44:31 +0000 (UTC) (envelope-from nate@root.org) Received: from nlpi053.prodigy.net (nlpi053.sbcis.sbc.com [207.115.36.82]) by mx1.freebsd.org (Postfix) with ESMTP id 10D328FC14; Sun, 3 May 2009 23:44:30 +0000 (UTC) (envelope-from nate@root.org) Received: from [10.0.5.18] (ppp-71-139-5-28.dsl.snfc21.pacbell.net [71.139.5.28]) (authenticated bits=0) by nlpi053.prodigy.net (8.13.8 smtpauth/dk/map_regex/8.13.8) with ESMTP id n43NWpPQ009414; Sun, 3 May 2009 18:32:51 -0500 Message-ID: <49FE29A4.30507@root.org> Date: Sun, 03 May 2009 16:32:52 -0700 From: Nate Lawson User-Agent: Thunderbird 2.0.0.21 (Windows/20090302) MIME-Version: 1.0 To: Alexander Motin References: <49FE1826.4060000@FreeBSD.org> In-Reply-To: <49FE1826.4060000@FreeBSD.org> X-Enigmail-Version: 0.95.7 Content-Type: text/plain; charset=KOI8-R Content-Transfer-Encoding: 7bit Cc: FreeBSD acpi , FreeBSD-Current , freebsd-mobile@freebsd.org Subject: Re: Fighting for the power. X-BeenThere: freebsd-mobile@freebsd.org X-Mailman-Version: 2.1.5 Precedence: list List-Id: Mobile computing with FreeBSD List-Unsubscribe: , List-Archive: List-Post: List-Help: List-Subscribe: , X-List-Received-Date: Sun, 03 May 2009 23:44:31 -0000 Alexander Motin wrote: > I would like to summarize some of my knowledge on reducing FreeBSD power > consumption and describe some new things I have recently implemented in > 8-CURRENT. The main character of this story is my 12" Acer TravelMate > 6292 laptop with C2D T7700 2.4GHz CPU, 965GM chipset and SATA HDD, under > amd64 8-CURRENT. Very nice summary. Thanks for doing the research. > P-states and throttling > Enabling powerd allows to effectively control CPU frequency/voltage > depending on CPU load. powerd on recent system can handle it quite > transparently. By default, frequency controlled via mix of EIST and > throttling technologies. First one controls both core frequency and > voltage, second - only core frequency. Both technologies give positive > power-saving effect. But effect of throttling is small and can be > completely hidden by using C2 state, that's why I recommend to disable > throttling control by adding to /boot/loader.conf: > hint.p4tcc.0.disabled=1 > hint.acpi_throttle.0.disabled=1 When I first wrote cpufreq, there was some question if vendors (even non-Intel) might use throttling for more than just cutting the duty cycle. It turns out they haven't, and have focused more on dropping the voltage with P-state transitions (EIST, PowerNow) and are treating throttling as a legacy feature. The time may have come to disable p4tcc and throttling by default, as long as it's easy for a user to enable them again. Perhaps just a change to boot/default/device.hints? > In my case frequency/voltage control saves about 5W of idle power. > C-states > - C1 stops clock on some parts of CPU core during inactivity. It is > safe, cheap and supported by CPUs for ages. System uses C1 state by > default. > - C2 state allows CPU to turn off all core clocks on idle. It is also > cheap, but requires correct ACPI-chipset-CPU interoperation to be used. > Use of C2 state can be enabled by adding to /etc/rc.conf: > performance_cx_lowest="C2" > economy_cx_lowest="C2" The default settings in rc.conf should allow the lowest Cx setting available to be used. Perhaps that changed? Really, we want C3+ to be enabled by default without the user doing anything. > - C3 state allows CPU completely stop all internal clocks, reduce > voltage and disconnect from system bus. This state gives additional > power saving effect, but it is not cheap and require trade-offs. > As soon as CPU is completely stopped in C3 state, local APIC timers in > each CPU core, used by FreeBSD as event sources on SMP, are not > functioning. It stops system time, breaks scheduling that makes system > close to dead. The only solution for this problem is to use some > external timers. Originally, before SMP era, FreeBSD used i8254 (for HZ) > and RTC (for stats) chipset timers. I have made changes to 8-CURRENT to > resurrect them for SMP systems. To use them, you can disable local APIC > timers by adding to /boot/loader.conf: > hint.apic.0.clock=0 > Also, to drop/rise voltage on C3, CPU needs time (57us for my system). > It means that C3 state can't be effectively used when system is waking > up often. To increase inactivity periods we should reduce interrupt rate > as much as possible by adding to loader.conf: > kern.hz=100 Yeah, hz=1000 doesn't make sense for laptops and I use hz=100 everywhere. > It may increase system response time a bit, but it is not significant > for laptop. Also we may avoid additional 128 interrupts per second per > core, by the cost of scheduling precision, with using i8254 timer also > for statistic collection purposes instead of RTC clock, by using another > newly added option: > hint.atrtc.0.clock=0 The real solution for C3 (and C4, etc.) is to implement tickless scheduling and to fix the current dependence on LAPIC for timer interrupts. Hopefully someone will do that soon. With that change, this change isn't needed. > 4. HDA modem > I was surprised, but integrated HDA modem consumed about 1W of power > even when not used. I have used the most radical solution - removed it > mechanically from socket. Case surface in that area become much cooler. Most modems support the ACPI Dx states, where D3 = device powered off. I'd think the PCI "power no driver option" would disable the soft modem since it's unlikely you have a driver for it. > 6. HDD > First common recommendation is use tmpfs for temporary files. RAM is > cheap, fast and anyway with you. > Also you may try to setup automatic idle drive spin-down, but if it is > the only system drive you should be careful, as every spin-up reduces > drive's life time. Did you increase the fsflush delay also? > So I have really doubled my on-battery time by this tuning - 4:47 hours > instead of 2:24 with default settings. Preinstalled vendor-tuned Windows > XP on the same system, provides maximum 3:20 hours. Very nice. I think tickless scheduling is the single largest win for power mgmt we could get. Second best would be S4 (suspend to disk). -- Nate From owner-freebsd-mobile@FreeBSD.ORG Mon May 4 01:30:56 2009 Return-Path: Delivered-To: freebsd-mobile@freebsd.org Received: from mx1.freebsd.org (mx1.freebsd.org [IPv6:2001:4f8:fff6::34]) by hub.freebsd.org (Postfix) with ESMTP id 40F6D106566B; Mon, 4 May 2009 01:30:56 +0000 (UTC) (envelope-from mcdouga9@egr.msu.edu) Received: from mx.egr.msu.edu (surfnturf.egr.msu.edu [35.9.37.164]) by mx1.freebsd.org (Postfix) with ESMTP id 179228FC14; Mon, 4 May 2009 01:30:55 +0000 (UTC) (envelope-from mcdouga9@egr.msu.edu) Received: from localhost (localhost [127.0.0.1]) by mx.egr.msu.edu (Postfix) with ESMTP id A600771EFEB; Sun, 3 May 2009 21:14:21 -0400 (EDT) X-Virus-Scanned: amavisd-new at egr.msu.edu Received: from mx.egr.msu.edu ([127.0.0.1]) by localhost (surfnturf.egr.msu.edu [127.0.0.1]) (amavisd-new, port 10024) with ESMTP id nNISy7un-t4T; Sun, 3 May 2009 21:14:21 -0400 (EDT) Received: from localhost (daemon.egr.msu.edu [35.9.44.65]) by mx.egr.msu.edu (Postfix) with ESMTP id 839B871EFE4; Sun, 3 May 2009 21:14:21 -0400 (EDT) Received: by localhost (Postfix, from userid 21281) id 80A0E68D; Sun, 3 May 2009 21:14:21 -0400 (EDT) Date: Sun, 3 May 2009 21:14:21 -0400 From: Adam McDougall To: Alexander Motin Message-ID: <20090504011421.GI6901@egr.msu.edu> References: <49FE1826.4060000@FreeBSD.org> MIME-Version: 1.0 Content-Type: text/plain; charset=us-ascii Content-Disposition: inline In-Reply-To: <49FE1826.4060000@FreeBSD.org> User-Agent: Mutt/1.5.19 (2009-01-05) Cc: FreeBSD acpi , FreeBSD-Current , freebsd-mobile@freebsd.org Subject: Re: Fighting for the power. X-BeenThere: freebsd-mobile@freebsd.org X-Mailman-Version: 2.1.5 Precedence: list List-Id: Mobile computing with FreeBSD List-Unsubscribe: , List-Archive: List-Post: List-Help: List-Subscribe: , X-List-Received-Date: Mon, 04 May 2009 01:30:56 -0000 On Mon, May 04, 2009 at 01:18:14AM +0300, Alexander Motin wrote: I would like to summarize some of my knowledge on reducing FreeBSD power consumption and describe some new things I have recently implemented in 8-CURRENT. The main character of this story is my 12" Acer TravelMate 6292 laptop with C2D T7700 2.4GHz CPU, 965GM chipset and SATA HDD, under amd64 8-CURRENT. Great list! May I suggest screen brightness and DPMS as another tool to save power, I've measured a 5W difference from the screen draw. Keeping the brightness as low as tolerable helps considerably, but also using 'xset dpms 120 120 120' (modify to taste) in .xinitrc to turn off the screen after 2 minutes helps when the laptop isn't being used every second. May need this in xorg.conf: Option "dpms" From owner-freebsd-mobile@FreeBSD.ORG Mon May 4 03:19:41 2009 Return-Path: Delivered-To: freebsd-mobile@freebsd.org Received: from mx1.freebsd.org (mx1.freebsd.org [IPv6:2001:4f8:fff6::34]) by hub.freebsd.org (Postfix) with ESMTP id C9A5E106564A; Mon, 4 May 2009 03:19:41 +0000 (UTC) (envelope-from mav@FreeBSD.org) Received: from cmail.optima.ua (cmail.optima.ua [195.248.191.121]) by mx1.freebsd.org (Postfix) with ESMTP id DB9868FC13; Mon, 4 May 2009 03:19:40 +0000 (UTC) (envelope-from mav@FreeBSD.org) X-Spam-Flag: SKIP X-Spam-Yversion: Spamooborona-2.1.0 Received: from [212.86.226.226] (account mav@alkar.net HELO mavbook.mavhome.dp.ua) by cmail.optima.ua (CommuniGate Pro SMTP 5.2.9) with ESMTPSA id 241860680; Mon, 04 May 2009 06:19:39 +0300 Message-ID: <49FE5EC8.3040205@FreeBSD.org> Date: Mon, 04 May 2009 06:19:36 +0300 From: Alexander Motin User-Agent: Thunderbird 2.0.0.21 (X11/20090405) MIME-Version: 1.0 To: Nate Lawson References: <49FE1826.4060000@FreeBSD.org> <49FE29A4.30507@root.org> In-Reply-To: <49FE29A4.30507@root.org> Content-Type: text/plain; charset=KOI8-R; format=flowed Content-Transfer-Encoding: 7bit Cc: FreeBSD acpi , FreeBSD-Current , freebsd-mobile@FreeBSD.org Subject: Re: Fighting for the power. X-BeenThere: freebsd-mobile@freebsd.org X-Mailman-Version: 2.1.5 Precedence: list List-Id: Mobile computing with FreeBSD List-Unsubscribe: , List-Archive: List-Post: List-Help: List-Subscribe: , X-List-Received-Date: Mon, 04 May 2009 03:19:42 -0000 Nate Lawson wrote: > The time may have come to disable p4tcc and throttling by default, as > long as it's easy for a user to enable them again. Perhaps just a change > to boot/default/device.hints? They still could be effective for old P4 series which had no C1E/C2 idle states support yet. But probably their power consumption is not so interesting area now. > The default settings in rc.conf should allow the lowest Cx setting > available to be used. Perhaps that changed? Really, we want C3+ to be > enabled by default without the user doing anything. Present defaults are to use C1. Probably we can allow C2 use more or less safely. Due to default LAPIC timer problems, enabling C3+ by default will make system dead by default. > Yeah, hz=1000 doesn't make sense for laptops and I use hz=100 everywhere. Without using C3+ it is not so important. I haven't seen any power difference. C1/C2 have practically zero exit latency, while power consumed by interrupt handler itself is miserable. > The real solution for C3 (and C4, etc.) is to implement tickless > scheduling and to fix the current dependence on LAPIC for timer > interrupts. Hopefully someone will do that soon. With that change, this > change isn't needed. System will always have tons of waiting callouts and timeouts to be handled. So timer will be always needed. Working timer. >> 4. HDA modem >> I was surprised, but integrated HDA modem consumed about 1W of power >> even when not used. I have used the most radical solution - removed it >> mechanically from socket. Case surface in that area become much cooler. > > Most modems support the ACPI Dx states, where D3 = device powered off. > I'd think the PCI "power no driver option" would disable the soft modem > since it's unlikely you have a driver for it. Modem share HDA bus/controller with sound. So PCI D3 will kill sound also, that is not an option. snd_hda driver itself puts all non-audio codecs into the HDA D3 state, but in my case it was not effective. >> 6. HDD >> First common recommendation is use tmpfs for temporary files. RAM is >> cheap, fast and anyway with you. >> Also you may try to setup automatic idle drive spin-down, but if it is >> the only system drive you should be careful, as every spin-up reduces >> drive's life time. > > Did you increase the fsflush delay also? I don't, but how long can it delay requests? Several minutes? Hour? Then there is high probability of data loss. Actually I have tried to reduce number of idle disk write activity, but I haven't very succeeded. Even in my quite simple icewm X environment something was persistently writing something every several minutes. I have found and disabled some activity sources, but it was not enough. What would happen in some complicated KDE/Gnome environment I am just afraid to think. -- Alexander Motin From owner-freebsd-mobile@FreeBSD.ORG Mon May 4 03:45:14 2009 Return-Path: Delivered-To: freebsd-mobile@freebsd.org Received: from mx1.freebsd.org (mx1.freebsd.org [IPv6:2001:4f8:fff6::34]) by hub.freebsd.org (Postfix) with ESMTP id EE595106566B; Mon, 4 May 2009 03:45:14 +0000 (UTC) (envelope-from mav@FreeBSD.org) Received: from cmail.optima.ua (cmail.optima.ua [195.248.191.121]) by mx1.freebsd.org (Postfix) with ESMTP id 0B5428FC15; Mon, 4 May 2009 03:45:13 +0000 (UTC) (envelope-from mav@FreeBSD.org) X-Spam-Flag: SKIP X-Spam-Yversion: Spamooborona-2.1.0 Received: from [212.86.226.226] (account mav@alkar.net HELO mavbook.mavhome.dp.ua) by cmail.optima.ua (CommuniGate Pro SMTP 5.2.9) with ESMTPSA id 241861314; Mon, 04 May 2009 06:45:12 +0300 Message-ID: <49FE64C5.2020507@FreeBSD.org> Date: Mon, 04 May 2009 06:45:09 +0300 From: Alexander Motin User-Agent: Thunderbird 2.0.0.21 (X11/20090405) MIME-Version: 1.0 To: Adam McDougall References: <49FE1826.4060000@FreeBSD.org> <20090504011421.GI6901@egr.msu.edu> In-Reply-To: <20090504011421.GI6901@egr.msu.edu> Content-Type: text/plain; charset=ISO-8859-1; format=flowed Content-Transfer-Encoding: 7bit Cc: FreeBSD acpi , FreeBSD-Current , freebsd-mobile@freebsd.org Subject: Re: Fighting for the power. X-BeenThere: freebsd-mobile@freebsd.org X-Mailman-Version: 2.1.5 Precedence: list List-Id: Mobile computing with FreeBSD List-Unsubscribe: , List-Archive: List-Post: List-Help: List-Subscribe: , X-List-Received-Date: Mon, 04 May 2009 03:45:15 -0000 Adam McDougall wrote: > On Mon, May 04, 2009 at 01:18:14AM +0300, Alexander Motin wrote: > > I would like to summarize some of my knowledge on reducing FreeBSD power > consumption and describe some new things I have recently implemented in > 8-CURRENT. The main character of this story is my 12" Acer TravelMate > 6292 laptop with C2D T7700 2.4GHz CPU, 965GM chipset and SATA HDD, under > amd64 8-CURRENT. > > Great list! May I suggest screen brightness and DPMS as another tool > to save power, I've measured a 5W difference from the screen draw. > Keeping the brightness as low as tolerable helps considerably, but > also using 'xset dpms 120 120 120' (modify to taste) in .xinitrc to > turn off the screen after 2 minutes helps when the laptop isn't being > used every second. May need this in xorg.conf: > Option "dpms" Yes, backlight is also important. But there is not so much things could be done. When I am leaving system for some time, I can just close the lid, if not put system into S3 state, which require very small power (at least I was unable to really measure it without all-day-long testing). Thanks to jkim@ we have more or less working S3 state for amd64 now. -- Alexander Motin From owner-freebsd-mobile@FreeBSD.ORG Mon May 4 07:50:24 2009 Return-Path: Delivered-To: freebsd-mobile@freebsd.org Received: from mx1.freebsd.org (mx1.freebsd.org [IPv6:2001:4f8:fff6::34]) by hub.freebsd.org (Postfix) with ESMTP id 91BB91065676; Mon, 4 May 2009 07:50:24 +0000 (UTC) (envelope-from mav@FreeBSD.org) Received: from cmail.optima.ua (cmail.optima.ua [195.248.191.121]) by mx1.freebsd.org (Postfix) with ESMTP id 9E7858FC14; Mon, 4 May 2009 07:50:23 +0000 (UTC) (envelope-from mav@FreeBSD.org) X-Spam-Flag: SKIP X-Spam-Yversion: Spamooborona-2.1.0 Received: from [212.86.226.226] (account mav@alkar.net HELO mavbook.mavhome.dp.ua) by cmail.optima.ua (CommuniGate Pro SMTP 5.2.9) with ESMTPSA id 241870610; Mon, 04 May 2009 10:50:22 +0300 Message-ID: <49FE9E3B.1050509@FreeBSD.org> Date: Mon, 04 May 2009 10:50:19 +0300 From: Alexander Motin User-Agent: Thunderbird 2.0.0.21 (X11/20090405) MIME-Version: 1.0 To: Hans Petter Selasky References: <49FE1826.4060000@FreeBSD.org> <200905040926.38337.hselasky@c2i.net> In-Reply-To: <200905040926.38337.hselasky@c2i.net> Content-Type: text/plain; charset=KOI8-R; format=flowed Content-Transfer-Encoding: 7bit Cc: FreeBSD acpi , freebsd-current@freebsd.org, freebsd-mobile@freebsd.org Subject: Re: Fighting for the power. X-BeenThere: freebsd-mobile@freebsd.org X-Mailman-Version: 2.1.5 Precedence: list List-Id: Mobile computing with FreeBSD List-Unsubscribe: , List-Archive: List-Post: List-Help: List-Subscribe: , X-List-Received-Date: Mon, 04 May 2009 07:50:25 -0000 Hans Petter Selasky wrote: >> 2. PCI devices >> PCI bus provides method to control device power. For example, I have >> completely no use for my FireWire controller and most of time - EHCI USB >> controller. Disabling them allows me to save about 3W of power. To >> disable all unneeded PCI devices you should build kernel without their >> drivers and add to loader.conf: >> hw.pci.do_power_nodriver=3 >> To enable devices back all you need to do is just load their drivers as >> modules. > > The new USB stack should turn off USB HC's automatically when not in use. At > least the schedules will get disabled. Did you do any research on this? Sorry, I really was testing it only with previous USB stack. Now I can acknowledge, that new ehci module loading adds only 0.2W for me by default and almost nothing if I power down built-in USB2 web cam connected to it using `usbconfig -u 5 -a 2 power_off`. Great! Thanks! -- Alexander Motin From owner-freebsd-mobile@FreeBSD.ORG Mon May 4 08:24:07 2009 Return-Path: Delivered-To: freebsd-mobile@freebsd.org Received: from mx1.freebsd.org (mx1.freebsd.org [IPv6:2001:4f8:fff6::34]) by hub.freebsd.org (Postfix) with ESMTP id 33C6C106566C; Mon, 4 May 2009 08:24:07 +0000 (UTC) (envelope-from hselasky@c2i.net) Received: from swip.net (mailfe09.tele2.se [212.247.155.1]) by mx1.freebsd.org (Postfix) with ESMTP id 937118FC0A; Mon, 4 May 2009 08:24:06 +0000 (UTC) (envelope-from hselasky@c2i.net) X-Cloudmark-Score: 0.000000 [] X-Cloudmark-Analysis: v=1.0 c=1 a=z_VEKX-DvsiYp74B3mQA:9 a=JUA1JGd_aKKhrkhcxeqo9KW786QA:4 Received: from [81.191.55.181] (account mc467741@c2i.net HELO [10.36.2.183]) by mailfe09.swip.net (CommuniGate Pro SMTP 5.2.13) with ESMTPA id 894745855; Mon, 04 May 2009 09:24:03 +0200 From: Hans Petter Selasky To: freebsd-current@freebsd.org Date: Mon, 4 May 2009 09:26:37 +0200 User-Agent: KMail/1.9.7 References: <49FE1826.4060000@FreeBSD.org> In-Reply-To: <49FE1826.4060000@FreeBSD.org> MIME-Version: 1.0 Content-Type: text/plain; charset="koi8-r" Content-Transfer-Encoding: 7bit Content-Disposition: inline Message-Id: <200905040926.38337.hselasky@c2i.net> Cc: Alexander Motin , FreeBSD acpi , freebsd-mobile@freebsd.org Subject: Re: Fighting for the power. X-BeenThere: freebsd-mobile@freebsd.org X-Mailman-Version: 2.1.5 Precedence: list List-Id: Mobile computing with FreeBSD List-Unsubscribe: , List-Archive: List-Post: List-Help: List-Subscribe: , X-List-Received-Date: Mon, 04 May 2009 08:24:07 -0000 > 2. PCI devices > PCI bus provides method to control device power. For example, I have > completely no use for my FireWire controller and most of time - EHCI USB > controller. Disabling them allows me to save about 3W of power. To > disable all unneeded PCI devices you should build kernel without their > drivers and add to loader.conf: > hw.pci.do_power_nodriver=3 > To enable devices back all you need to do is just load their drivers as > modules. The new USB stack should turn off USB HC's automatically when not in use. At least the schedules will get disabled. Did you do any research on this? --HPS From owner-freebsd-mobile@FreeBSD.ORG Mon May 4 09:40:42 2009 Return-Path: Delivered-To: freebsd-mobile@freebsd.org Received: from mx1.freebsd.org (mx1.freebsd.org [IPv6:2001:4f8:fff6::34]) by hub.freebsd.org (Postfix) with ESMTP id 5FEC01065673; Mon, 4 May 2009 09:40:42 +0000 (UTC) (envelope-from onemda@gmail.com) Received: from fk-out-0910.google.com (fk-out-0910.google.com [209.85.128.186]) by mx1.freebsd.org (Postfix) with ESMTP id 615A08FC26; Mon, 4 May 2009 09:40:36 +0000 (UTC) (envelope-from onemda@gmail.com) Received: by fk-out-0910.google.com with SMTP id f33so1839206fkf.11 for ; Mon, 04 May 2009 02:40:35 -0700 (PDT) DKIM-Signature: v=1; a=rsa-sha256; c=relaxed/relaxed; d=gmail.com; s=gamma; h=domainkey-signature:mime-version:received:in-reply-to:references :date:message-id:subject:from:to:cc:content-type :content-transfer-encoding; bh=lkelNI0vwYVPkC3u2T27PnQyiTOKSBwvH2qmXEgihx8=; b=hoAL8tMPe2D79pmmAmzJU2vu8w1o9UXfSWtsbwQIJnPGhvDER7eNxR9+ThYXMgM/yv PFlqbp2hf7AN/rpWjY64GC5d1p9Ij/nSbkN936jczDLe39dt1FqsiAQo+zg0XuXbfz7L YeANJkYozvZDJNvOXq2dAQKNJzJHePwr4xLdY= DomainKey-Signature: a=rsa-sha1; c=nofws; d=gmail.com; s=gamma; h=mime-version:in-reply-to:references:date:message-id:subject:from:to :cc:content-type:content-transfer-encoding; b=Lweg7IHS4jYPrURiL+GtHK5erc8z6oX5Qs4bQvZZsetMOYVZ93IgCP91A8Uh7qTXLW 7bkzDzVfjsULAFCfduq9twPLca9VUoFykyKgtR0feZW2I0ACoD27YF3MEvZ5t7ixJtGS zg1SRzU5nhTeL1E0Y21AHG7FRguJpdDzC8zSo= MIME-Version: 1.0 Received: by 10.239.132.134 with SMTP id 6mr291132hbr.157.1241430035330; Mon, 04 May 2009 02:40:35 -0700 (PDT) In-Reply-To: <49FE1826.4060000@FreeBSD.org> References: <49FE1826.4060000@FreeBSD.org> Date: Mon, 4 May 2009 11:40:35 +0200 Message-ID: <3a142e750905040240g58152e69p6fcb797a5e026426@mail.gmail.com> From: "Paul B. Mahol" To: Alexander Motin Content-Type: text/plain; charset=ISO-8859-1 Content-Transfer-Encoding: 7bit Cc: FreeBSD acpi , FreeBSD-Current , freebsd-mobile@freebsd.org Subject: Re: Fighting for the power. X-BeenThere: freebsd-mobile@freebsd.org X-Mailman-Version: 2.1.5 Precedence: list List-Id: Mobile computing with FreeBSD List-Unsubscribe: , List-Archive: List-Post: List-Help: List-Subscribe: , X-List-Received-Date: Mon, 04 May 2009 09:40:43 -0000 On 5/4/09, Alexander Motin wrote: > 2. PCI devices > PCI bus provides method to control device power. For example, I have > completely no use for my FireWire controller and most of time - EHCI USB > controller. Disabling them allows me to save about 3W of power. To > disable all unneeded PCI devices you should build kernel without their > drivers and add to loader.conf: > hw.pci.do_power_nodriver=3 > To enable devices back all you need to do is just load their drivers as > modules. Unloading modules doesnt put them back into into D3 state. You are forced to load some another module again to put wanted device into D3 state. -- Paul From owner-freebsd-mobile@FreeBSD.ORG Mon May 4 09:51:10 2009 Return-Path: Delivered-To: freebsd-mobile@freebsd.org Received: from mx1.freebsd.org (mx1.freebsd.org [IPv6:2001:4f8:fff6::34]) by hub.freebsd.org (Postfix) with ESMTP id A9C91106567F; Mon, 4 May 2009 09:51:10 +0000 (UTC) (envelope-from mav@FreeBSD.org) Received: from cmail.optima.ua (cmail.optima.ua [195.248.191.121]) by mx1.freebsd.org (Postfix) with ESMTP id B7F5F8FC14; Mon, 4 May 2009 09:51:09 +0000 (UTC) (envelope-from mav@FreeBSD.org) X-Spam-Flag: SKIP X-Spam-Yversion: Spamooborona-2.1.0 Received: from [212.86.226.226] (account mav@alkar.net HELO mavbook.mavhome.dp.ua) by cmail.optima.ua (CommuniGate Pro SMTP 5.2.9) with ESMTPSA id 241877347; Mon, 04 May 2009 12:51:08 +0300 Message-ID: <49FEBA89.4040609@FreeBSD.org> Date: Mon, 04 May 2009 12:51:05 +0300 From: Alexander Motin User-Agent: Thunderbird 2.0.0.21 (X11/20090405) MIME-Version: 1.0 To: "Paul B. Mahol" References: <49FE1826.4060000@FreeBSD.org> <3a142e750905040240g58152e69p6fcb797a5e026426@mail.gmail.com> In-Reply-To: <3a142e750905040240g58152e69p6fcb797a5e026426@mail.gmail.com> Content-Type: text/plain; charset=ISO-8859-1; format=flowed Content-Transfer-Encoding: 7bit Cc: FreeBSD acpi , FreeBSD-Current , freebsd-mobile@freebsd.org Subject: Re: Fighting for the power. X-BeenThere: freebsd-mobile@freebsd.org X-Mailman-Version: 2.1.5 Precedence: list List-Id: Mobile computing with FreeBSD List-Unsubscribe: , List-Archive: List-Post: List-Help: List-Subscribe: , X-List-Received-Date: Mon, 04 May 2009 09:51:11 -0000 Paul B. Mahol wrote: > On 5/4/09, Alexander Motin wrote: >> 2. PCI devices >> PCI bus provides method to control device power. For example, I have >> completely no use for my FireWire controller and most of time - EHCI USB >> controller. Disabling them allows me to save about 3W of power. To >> disable all unneeded PCI devices you should build kernel without their >> drivers and add to loader.conf: >> hw.pci.do_power_nodriver=3 >> To enable devices back all you need to do is just load their drivers as >> modules. > > Unloading modules doesnt put them back into into D3 state. > You are forced to load some another module again to put wanted device > into D3 state. Yes. Resume also does not powers down unowned devices. Would be good to fix that also. -- Alexander Motin From owner-freebsd-mobile@FreeBSD.ORG Mon May 4 12:24:32 2009 Return-Path: Delivered-To: freebsd-mobile@freebsd.org Received: from mx1.freebsd.org (mx1.freebsd.org [IPv6:2001:4f8:fff6::34]) by hub.freebsd.org (Postfix) with ESMTP id 515741065673; Mon, 4 May 2009 12:24:32 +0000 (UTC) (envelope-from mav@FreeBSD.org) Received: from cmail.optima.ua (cmail.optima.ua [195.248.191.121]) by mx1.freebsd.org (Postfix) with ESMTP id 4C2E88FC14; Mon, 4 May 2009 12:24:31 +0000 (UTC) (envelope-from mav@FreeBSD.org) X-Spam-Flag: SKIP X-Spam-Yversion: Spamooborona-2.1.0 Received: from [212.86.226.226] (account mav@alkar.net HELO mavbook.mavhome.dp.ua) by cmail.optima.ua (CommuniGate Pro SMTP 5.2.9) with ESMTPSA id 241886311; Mon, 04 May 2009 15:24:30 +0300 Message-ID: <49FEDE7B.30804@FreeBSD.org> Date: Mon, 04 May 2009 15:24:27 +0300 From: Alexander Motin User-Agent: Thunderbird 2.0.0.21 (X11/20090405) MIME-Version: 1.0 To: "Alexandre \"Sunny\" Kovalenko" References: <49FE1826.4060000@FreeBSD.org> <1241438990.1280.6.camel@RabbitsDen> In-Reply-To: <1241438990.1280.6.camel@RabbitsDen> Content-Type: text/plain; charset=UTF-8; format=flowed Content-Transfer-Encoding: 7bit Cc: FreeBSD acpi , FreeBSD-Current , freebsd-mobile@freebsd.org Subject: Re: Fighting for the power. X-BeenThere: freebsd-mobile@freebsd.org X-Mailman-Version: 2.1.5 Precedence: list List-Id: Mobile computing with FreeBSD List-Unsubscribe: , List-Archive: List-Post: List-Help: List-Subscribe: , X-List-Received-Date: Mon, 04 May 2009 12:24:33 -0000 Alexandre "Sunny" Kovalenko wrote: > On Mon, 2009-05-04 at 01:18 +0300, Alexander Motin wrote: >> - C3 state allows CPU completely stop all internal clocks, reduce >> voltage and disconnect from system bus. This state gives additional >> power saving effect, but it is not cheap and require trade-offs. >> As soon as CPU is completely stopped in C3 state, local APIC timers in >> each CPU core, used by FreeBSD as event sources on SMP, are not >> functioning. It stops system time, breaks scheduling that makes system >> close to dead. > Did you try to see whether putting one of the cores in C3 state by doing > something like > > dev.cpu.1.cx_lowest=C3 > > makes any difference? > > # sysctl dev.cpu | grep cx_usage > dev.cpu.0.cx_usage: 0.00% 100.00% 0.00% > dev.cpu.1.cx_usage: 0.00% 5.18% 94.81% I did. As soon as first CPU core is not in C3 state, second core unable to enter C3 completely and disconnect from the bus, as cores are sharing common resources. Such technique allows to avoid LAPIC timer problems, but I haven't noticed any effect from this on CPU idle power. The only difference I have noticed was in the case, when first core is busy. C3 on second idle core then somehow reduces summary consumption a bit. In other words, C3 state should be active on both cores simultaneously to give real effect. -- Alexander Motin From owner-freebsd-mobile@FreeBSD.ORG Mon May 4 13:12:26 2009 Return-Path: Delivered-To: freebsd-mobile@freebsd.org Received: from mx1.freebsd.org (mx1.freebsd.org [IPv6:2001:4f8:fff6::34]) by hub.freebsd.org (Postfix) with ESMTP id CD8221065670; Mon, 4 May 2009 13:12:26 +0000 (UTC) (envelope-from gaijin.k@gmail.com) Received: from qw-out-2122.google.com (qw-out-2122.google.com [74.125.92.25]) by mx1.freebsd.org (Postfix) with ESMTP id 5916C8FC27; Mon, 4 May 2009 13:12:25 +0000 (UTC) (envelope-from gaijin.k@gmail.com) Received: by qw-out-2122.google.com with SMTP id 3so2893389qwe.7 for ; Mon, 04 May 2009 06:12:25 -0700 (PDT) DKIM-Signature: v=1; a=rsa-sha256; c=relaxed/relaxed; d=gmail.com; s=gamma; h=domainkey-signature:received:received:subject:from:to:cc :in-reply-to:references:content-type:date:message-id:mime-version :x-mailer:content-transfer-encoding; bh=iypo7b7zlz3AwW7Rii0IuyDmz0y5EAe4AmcmAFjM5yg=; b=IKTbdOeNRmOyTLwZjzkrxA45DSu53hM9yAT9k3MbJEvJ0V+U+Y0AlY14kUGzHSCVsG 3TyNMC97zZdf/2wBETeoAx5XG0Wxc68ctlR1xBVV1aLcNMkk6vHkX95vYjo4hGG4sgvq 8oigwhjRc5DWaZz8yiqgDjzZIa6b4kLYbu4Dk= DomainKey-Signature: a=rsa-sha1; c=nofws; d=gmail.com; s=gamma; h=subject:from:to:cc:in-reply-to:references:content-type:date :message-id:mime-version:x-mailer:content-transfer-encoding; b=riT3LkSGTUGTQOffl9OMoXGA8Uhry9jVlN963nhGmG41saIETpuGzlJJHQpsILItY5 ZcPgIviH80RrG9onXJmFD4tmotXu+jPDHPG16lc7dOKyx03r8Jbw8ccOYWcptXr3ORtW Ee3pl/G2xuM2m7wQHNGNSBpDqxDS6mGG7u0K8= Received: by 10.224.80.134 with SMTP id t6mr5686248qak.173.1241439011846; Mon, 04 May 2009 05:10:11 -0700 (PDT) Received: from ?10.0.3.231? (pool-70-111-23-127.nwrk.east.verizon.net [70.111.23.127]) by mx.google.com with ESMTPS id 7sm9754803qwf.55.2009.05.04.05.10.10 (version=SSLv3 cipher=RC4-MD5); Mon, 04 May 2009 05:10:11 -0700 (PDT) From: "Alexandre \"Sunny\" Kovalenko" To: Alexander Motin In-Reply-To: <49FE1826.4060000@FreeBSD.org> References: <49FE1826.4060000@FreeBSD.org> Content-Type: text/plain; charset="UTF-8" Date: Mon, 04 May 2009 08:09:50 -0400 Message-Id: <1241438990.1280.6.camel@RabbitsDen> Mime-Version: 1.0 X-Mailer: Evolution 2.26.1.1 FreeBSD GNOME Team Port Content-Transfer-Encoding: 8bit Cc: FreeBSD acpi , FreeBSD-Current , freebsd-mobile@freebsd.org Subject: Re: Fighting for the power. X-BeenThere: freebsd-mobile@freebsd.org X-Mailman-Version: 2.1.5 Precedence: list List-Id: Mobile computing with FreeBSD List-Unsubscribe: , List-Archive: List-Post: List-Help: List-Subscribe: , X-List-Received-Date: Mon, 04 May 2009 13:12:27 -0000 On Mon, 2009-05-04 at 01:18 +0300, Alexander Motin wrote: > I would like to summarize some of my knowledge on reducing FreeBSD power > consumption and describe some new things I have recently implemented in > 8-CURRENT. The main character of this story is my 12" Acer TravelMate > 6292 laptop with C2D T7700 2.4GHz CPU, 965GM chipset and SATA HDD, under > amd64 8-CURRENT. > > Modern systems, especially laptops, are implementing big number of > power-saving technologies. Some of them are working automatically, other > have significant requirements and need special system tuning or > trade-offs to be effectively used. > > So here is the steps: > > 1. CPU > CPU is the most consuming part of the system. Under the full load it > alone may consume more then 40W of power, but for real laptop usage the > most important is idle consumption. > Core2Duo T7700 CPU has 2 cores, runs on 2.4GHz frequency, supports EIST > technology with P-states at 2400, 2000, 1600, 1200 and 800MHz levels, > supports C1, C2 and C3 idle C-states, plus throttling. So how can we use it: > P-states and throttling > Enabling powerd allows to effectively control CPU frequency/voltage > depending on CPU load. powerd on recent system can handle it quite > transparently. By default, frequency controlled via mix of EIST and > throttling technologies. First one controls both core frequency and > voltage, second - only core frequency. Both technologies give positive > power-saving effect. But effect of throttling is small and can be > completely hidden by using C2 state, that's why I recommend to disable > throttling control by adding to /boot/loader.conf: > hint.p4tcc.0.disabled=1 > hint.acpi_throttle.0.disabled=1 > In my case frequency/voltage control saves about 5W of idle power. > C-states > - C1 stops clock on some parts of CPU core during inactivity. It is > safe, cheap and supported by CPUs for ages. System uses C1 state by default. > - C2 state allows CPU to turn off all core clocks on idle. It is also > cheap, but requires correct ACPI-chipset-CPU interoperation to be used. > Use of C2 state can be enabled by adding to /etc/rc.conf: > performance_cx_lowest="C2" > economy_cx_lowest="C2" > Effect from this state is not so big when powerd is used, but still > noticeable, > - C3 state allows CPU completely stop all internal clocks, reduce > voltage and disconnect from system bus. This state gives additional > power saving effect, but it is not cheap and require trade-offs. > As soon as CPU is completely stopped in C3 state, local APIC timers in > each CPU core, used by FreeBSD as event sources on SMP, are not > functioning. It stops system time, breaks scheduling that makes system > close to dead. Did you try to see whether putting one of the cores in C3 state by doing something like dev.cpu.1.cx_lowest=C3 makes any difference? # sysctl dev.cpu | grep cx_usage dev.cpu.0.cx_usage: 0.00% 100.00% 0.00% dev.cpu.1.cx_usage: 0.00% 5.18% 94.81% -- Alexandre Kovalenko (Олександр Коваленко) From owner-freebsd-mobile@FreeBSD.ORG Mon May 4 15:10:01 2009 Return-Path: Delivered-To: freebsd-mobile@freebsd.org Received: from mx1.freebsd.org (mx1.freebsd.org [IPv6:2001:4f8:fff6::34]) by hub.freebsd.org (Postfix) with ESMTP id 4F9FE106566C; Mon, 4 May 2009 15:10:01 +0000 (UTC) (envelope-from oberman@es.net) Received: from mailgw.es.net (mail3.es.net [IPv6:2001:400:4c01::2]) by mx1.freebsd.org (Postfix) with ESMTP id 1F5418FC1C; Mon, 4 May 2009 15:10:01 +0000 (UTC) (envelope-from oberman@es.net) Received: from ptavv.es.net (ptavv.es.net [IPv6:2001:400:910::29]) by mailgw.es.net (8.14.3/8.14.3) with ESMTP id n44F9xYd027247 (version=TLSv1/SSLv3 cipher=DHE-RSA-AES256-SHA bits=256 verify=NOT); Mon, 4 May 2009 08:10:00 -0700 Received: from ptavv.es.net (ptavv.es.net [127.0.0.1]) by ptavv.es.net (Tachyon Server) with ESMTP id 67BE91CC50; Mon, 4 May 2009 08:09:59 -0700 (PDT) To: Alexander Motin In-reply-to: Your message of "Mon, 04 May 2009 15:24:27 +0300." <49FEDE7B.30804@FreeBSD.org> Date: Mon, 04 May 2009 08:09:59 -0700 From: "Kevin Oberman" Message-Id: <20090504150959.67BE91CC50@ptavv.es.net> Cc: FreeBSD acpi , FreeBSD-Current , "Alexandre \"Sunny\" Kovalenko" , freebsd-mobile@freebsd.org Subject: Re: Fighting for the power. X-BeenThere: freebsd-mobile@freebsd.org X-Mailman-Version: 2.1.5 Precedence: list List-Id: Mobile computing with FreeBSD List-Unsubscribe: , List-Archive: List-Post: List-Help: List-Subscribe: , X-List-Received-Date: Mon, 04 May 2009 15:10:02 -0000 > Date: Mon, 04 May 2009 15:24:27 +0300 > From: Alexander Motin > Sender: owner-freebsd-mobile@freebsd.org > > Alexandre "Sunny" Kovalenko wrote: > > On Mon, 2009-05-04 at 01:18 +0300, Alexander Motin wrote: > >> - C3 state allows CPU completely stop all internal clocks, reduce > >> voltage and disconnect from system bus. This state gives additional > >> power saving effect, but it is not cheap and require trade-offs. > >> As soon as CPU is completely stopped in C3 state, local APIC timers in > >> each CPU core, used by FreeBSD as event sources on SMP, are not > >> functioning. It stops system time, breaks scheduling that makes system > >> close to dead. > > Did you try to see whether putting one of the cores in C3 state by doing > > something like > > > > dev.cpu.1.cx_lowest=C3 > > > > makes any difference? > > > > # sysctl dev.cpu | grep cx_usage > > dev.cpu.0.cx_usage: 0.00% 100.00% 0.00% > > dev.cpu.1.cx_usage: 0.00% 5.18% 94.81% > > I did. As soon as first CPU core is not in C3 state, second core unable > to enter C3 completely and disconnect from the bus, as cores are sharing > common resources. Such technique allows to avoid LAPIC timer problems, > but I haven't noticed any effect from this on CPU idle power. The only > difference I have noticed was in the case, when first core is busy. C3 > on second idle core then somehow reduces summary consumption a bit. > > In other words, C3 state should be active on both cores simultaneously > to give real effect. It is important to be aware that the presence of USB will keep a system from entering C3. Either build a kernel without USB and load it only whan needed or run 8-CURRENT with the USB2 stack which is purported to fix this problem. (I have no systems running CURRENT, so I can't confirm that USB2 fixes the problem.) -- R. Kevin Oberman, Network Engineer Energy Sciences Network (ESnet) Ernest O. Lawrence Berkeley National Laboratory (Berkeley Lab) E-mail: oberman@es.net Phone: +1 510 486-8634 Key fingerprint:059B 2DDF 031C 9BA3 14A4 EADA 927D EBB3 987B 3751 From owner-freebsd-mobile@FreeBSD.ORG Mon May 4 18:40:41 2009 Return-Path: Delivered-To: freebsd-mobile@freebsd.org Received: from mx1.freebsd.org (mx1.freebsd.org [IPv6:2001:4f8:fff6::34]) by hub.freebsd.org (Postfix) with ESMTP id 714FF1065708; Mon, 4 May 2009 18:40:41 +0000 (UTC) (envelope-from lwindschuh@googlemail.com) Received: from yx-out-2324.google.com (yx-out-2324.google.com [74.125.44.29]) by mx1.freebsd.org (Postfix) with ESMTP id 13BAF8FC0C; Mon, 4 May 2009 18:40:40 +0000 (UTC) (envelope-from lwindschuh@googlemail.com) Received: by yx-out-2324.google.com with SMTP id 8so2476384yxb.13 for ; Mon, 04 May 2009 11:40:40 -0700 (PDT) DKIM-Signature: v=1; a=rsa-sha256; c=relaxed/relaxed; d=googlemail.com; s=gamma; h=domainkey-signature:mime-version:received:in-reply-to:references :date:message-id:subject:from:to:cc:content-type :content-transfer-encoding; bh=pVHndkLoel/dDf3T7QhRgr0F+FW0JewyPjQJXOv+qAk=; b=dqFTBCu/S235gSWzohtF25MZuLELY+lmvrcMo3ndRSqXzyd1z/uRSYDA9VZwEgSJ3j Mt7G1wsdONmS8X7Dld/9z/KJBsuuM2YmQDNxxxyVcIZEfWRxuoPVYNfBw6vwZ+a8/QIt ZIKV8O7ZM6XUQlt8Hgj71mdYb6wC/f+1DXICg= DomainKey-Signature: a=rsa-sha1; c=nofws; d=googlemail.com; s=gamma; h=mime-version:in-reply-to:references:date:message-id:subject:from:to :cc:content-type:content-transfer-encoding; b=i0r/ZX4mJVU/gIIVt0c6+yUN1DnlN+3T+R/MCZ32ESmsZ1tE/oV1nSfcQJ9YRU+Jal 9KbZWDcYvQLIDIH6MSjyAzhNp91np8xgyo3JOegh2gSjPUrXAE3V8hZZIzpaMOrJF4XL efg4CM4b+inmZHJpjBZWnpLOqxtHO6I50o5/k= MIME-Version: 1.0 Received: by 10.150.138.8 with SMTP id l8mr12588155ybd.63.1241461141253; Mon, 04 May 2009 11:19:01 -0700 (PDT) In-Reply-To: <49FE1826.4060000@FreeBSD.org> References: <49FE1826.4060000@FreeBSD.org> Date: Mon, 4 May 2009 20:19:01 +0200 Message-ID: <90a5caac0905041119h70101d12i56863e57b27d2e55@mail.gmail.com> From: Lucius Windschuh To: Alexander Motin Content-Type: text/plain; charset=ISO-8859-1 Content-Transfer-Encoding: quoted-printable Cc: freebsd-current@freebsd.org, freebsd-mobile@freebsd.org Subject: Re: Fighting for the power. X-BeenThere: freebsd-mobile@freebsd.org X-Mailman-Version: 2.1.5 Precedence: list List-Id: Mobile computing with FreeBSD List-Unsubscribe: , List-Archive: List-Post: List-Help: List-Subscribe: , X-List-Received-Date: Mon, 04 May 2009 18:40:42 -0000 2009/5/4 Alexander Motin : > I would like to summarize some of my knowledge on reducing FreeBSD power > consumption and describe some new things I have recently implemented in > 8-CURRENT. The main character of this story is my 12" Acer TravelMate > 6292 laptop with C2D T7700 2.4GHz CPU, 965GM chipset and SATA HDD, under > amd64 8-CURRENT. First, thank you for your report about power saving on current laptops. :-) > 1. CPU > [...] > =A0- C3 state allows CPU completely stop all internal clocks, reduce > voltage and disconnect from system bus. This state gives additional > power saving effect, but it is not cheap and require trade-offs. > As soon as CPU is completely stopped in C3 state, local APIC timers in > each CPU core, used by FreeBSD as event sources on SMP, are not > functioning. It stops system time, breaks scheduling that makes system > close to dead. The only solution for this problem is to use some > external timers. Originally, before SMP era, FreeBSD used i8254 (for HZ) > and RTC (for stats) chipset timers. I have made changes to 8-CURRENT to > resurrect them for SMP systems. To use them, you can disable local APIC > timers by adding to /boot/loader.conf: > hint.apic.0.clock=3D0 I tried this on CURRENT@r191784 (i386) on a Thinkpad T400 (Intel(R) Core(TM)2 Duo CPU T9400) with INVARIANTS, etc. enabled. The result was a panic shortly before /sbin/init is called: panic: lapic1: zero divisor So, the KASSERT in sys/i386/local_apic.c:325 fired: KASSERT(lapic_timer_period !=3D 0, ("lapic%u: zero divisor", lapic_id())); Did I forget something? My /boot/loader.conf: hint.p4tcc.0.disabled=3D1 hint.acpi_throttle.0.disabled=3D1 kern.hz=3D100 hint.atrtc.0.clock=3D0 hint.apic.0.clock=3D0 hint.ata.2.pm_level=3D2 hint.ata.3.pm_level=3D3 vm.pmap.pg_ps_enabled=3D1 dmesg: http://sites.google.com/site/lwfreebsd/Home/files/dmesg-T400-FreeBSD= -CURRENT.txt kernel config: http://sites.google.com/site/lwfreebsd/Home/files/kernel-CUR= RENT.txt Regards Lucius From owner-freebsd-mobile@FreeBSD.ORG Mon May 4 22:28:52 2009 Return-Path: Delivered-To: freebsd-mobile@freebsd.org Received: from mx1.freebsd.org (mx1.freebsd.org [IPv6:2001:4f8:fff6::34]) by hub.freebsd.org (Postfix) with ESMTP id A3128106567D; Mon, 4 May 2009 22:28:52 +0000 (UTC) (envelope-from mav@FreeBSD.org) Received: from cmail.optima.ua (cmail.optima.ua [195.248.191.121]) by mx1.freebsd.org (Postfix) with ESMTP id DF52A8FC1F; Mon, 4 May 2009 22:28:51 +0000 (UTC) (envelope-from mav@FreeBSD.org) X-Spam-Flag: SKIP X-Spam-Yversion: Spamooborona-2.1.0 Received: from [77.52.120.34] (account mav@alkar.net HELO mavbook.mavhome.dp.ua) by cmail.optima.ua (CommuniGate Pro SMTP 5.2.9) with ESMTPSA id 241908524; Tue, 05 May 2009 01:28:45 +0300 Message-ID: <49FF6C11.5030607@FreeBSD.org> Date: Tue, 05 May 2009 01:28:33 +0300 From: Alexander Motin User-Agent: Thunderbird 2.0.0.21 (X11/20090405) MIME-Version: 1.0 To: Lucius Windschuh References: <49FE1826.4060000@FreeBSD.org> <90a5caac0905041119h70101d12i56863e57b27d2e55@mail.gmail.com> In-Reply-To: <90a5caac0905041119h70101d12i56863e57b27d2e55@mail.gmail.com> Content-Type: multipart/mixed; boundary="------------080307030500090208040209" Cc: freebsd-current@freebsd.org, freebsd-mobile@freebsd.org Subject: Re: Fighting for the power. X-BeenThere: freebsd-mobile@freebsd.org X-Mailman-Version: 2.1.5 Precedence: list List-Id: Mobile computing with FreeBSD List-Unsubscribe: , List-Archive: List-Post: List-Help: List-Subscribe: , X-List-Received-Date: Mon, 04 May 2009 22:28:53 -0000 This is a multi-part message in MIME format. --------------080307030500090208040209 Content-Type: text/plain; charset=ISO-8859-1; format=flowed Content-Transfer-Encoding: 7bit Lucius Windschuh wrote: > I tried this on CURRENT@r191784 (i386) on a Thinkpad T400 (Intel(R) > Core(TM)2 Duo CPU T9400) with INVARIANTS, etc. enabled. > The result was a panic shortly before /sbin/init is called: > > panic: lapic1: zero divisor > > So, the KASSERT in sys/i386/local_apic.c:325 fired: > KASSERT(lapic_timer_period != 0, ("lapic%u: zero divisor", > lapic_id())); > > Did I forget something? > > My /boot/loader.conf: > hint.p4tcc.0.disabled=1 > hint.acpi_throttle.0.disabled=1 > kern.hz=100 > hint.atrtc.0.clock=0 > hint.apic.0.clock=0 > hint.ata.2.pm_level=2 > hint.ata.3.pm_level=3 > vm.pmap.pg_ps_enabled=1 > > dmesg: http://sites.google.com/site/lwfreebsd/Home/files/dmesg-T400-FreeBSD-CURRENT.txt > kernel config: http://sites.google.com/site/lwfreebsd/Home/files/kernel-CURRENT.txt Sorry, my fault. Try attached patch. -- Alexander Motin --------------080307030500090208040209 Content-Type: text/plain; name="local_apic.nohz.patch" Content-Transfer-Encoding: 7bit Content-Disposition: inline; filename="local_apic.nohz.patch" --- local_apic.c.prev 2009-05-01 23:53:37.000000000 +0300 +++ local_apic.c 2009-05-05 01:10:04.000000000 +0300 @@ -319,7 +319,7 @@ lapic_setup(int boot) } /* We don't setup the timer during boot on the BSP until later. */ - if (!(boot && PCPU_GET(cpuid) == 0)) { + if (!(boot && PCPU_GET(cpuid) == 0) && lapic_timer_hz != 0) { KASSERT(lapic_timer_period != 0, ("lapic%u: zero divisor", lapic_id())); lapic_timer_set_divisor(lapic_timer_divisor); --------------080307030500090208040209-- From owner-freebsd-mobile@FreeBSD.ORG Mon May 4 23:22:14 2009 Return-Path: Delivered-To: freebsd-mobile@freebsd.org Received: from mx1.freebsd.org (mx1.freebsd.org [IPv6:2001:4f8:fff6::34]) by hub.freebsd.org (Postfix) with ESMTP id 73C261065670; Mon, 4 May 2009 23:22:14 +0000 (UTC) (envelope-from lwindschuh@googlemail.com) Received: from yw-out-2324.google.com (yw-out-2324.google.com [74.125.46.28]) by mx1.freebsd.org (Postfix) with ESMTP id 021FF8FC0A; Mon, 4 May 2009 23:22:13 +0000 (UTC) (envelope-from lwindschuh@googlemail.com) Received: by yw-out-2324.google.com with SMTP id 9so2565429ywe.13 for ; Mon, 04 May 2009 16:22:13 -0700 (PDT) DKIM-Signature: v=1; a=rsa-sha256; c=relaxed/relaxed; d=googlemail.com; s=gamma; h=domainkey-signature:mime-version:received:in-reply-to:references :date:message-id:subject:from:to:cc:content-type :content-transfer-encoding; bh=/+7aw/hSDt4QIlNIrJ+kZflW/Puzna+vtSKkbc1k8Jo=; b=TU+0DRkQAbftx1t01/C8xbFf/jlKPVPhIRo5DJXS4tD3/rRFnhqiuj7GXghghKC+VK c4GYdWMxBXhM+pKc/NZWJepIYxT/KQPootSMH8taOEUO503rayEVv2LX1i0SsuM4hZcN oB3xTFj4DYfK6DNtx8hfTNJevqg0NiBuOEQx8= DomainKey-Signature: a=rsa-sha1; c=nofws; d=googlemail.com; s=gamma; h=mime-version:in-reply-to:references:date:message-id:subject:from:to :cc:content-type:content-transfer-encoding; b=WyVkCZUvcWWnr8nk98F1u1fCVuUfzH0NpZsLcMDIC0DUA71+i3cUL+0HzoZ2EBVogM ymt5pbOiRELLFo/mEQgiYZAcoS6jTFnZqTl2bRHRMyAI30H3/pWgk3ZDcBw769+weQFN hOEe5Oqx9VR2jGTMjdqu8C681aitf5KhUreZE= MIME-Version: 1.0 Received: by 10.151.101.20 with SMTP id d20mr13084900ybm.14.1241479333020; Mon, 04 May 2009 16:22:13 -0700 (PDT) In-Reply-To: <49FF6C11.5030607@FreeBSD.org> References: <49FE1826.4060000@FreeBSD.org> <90a5caac0905041119h70101d12i56863e57b27d2e55@mail.gmail.com> <49FF6C11.5030607@FreeBSD.org> Date: Tue, 5 May 2009 01:22:12 +0200 Message-ID: <90a5caac0905041622oaddd7cek52f28a9b018b3ea7@mail.gmail.com> From: Lucius Windschuh To: Alexander Motin Content-Type: text/plain; charset=ISO-8859-1 Content-Transfer-Encoding: quoted-printable Cc: freebsd-current@freebsd.org, freebsd-mobile@freebsd.org Subject: Re: Fighting for the power. X-BeenThere: freebsd-mobile@freebsd.org X-Mailman-Version: 2.1.5 Precedence: list List-Id: Mobile computing with FreeBSD List-Unsubscribe: , List-Archive: List-Post: List-Help: List-Subscribe: , X-List-Received-Date: Mon, 04 May 2009 23:22:14 -0000 2009/5/5 Alexander Motin : > Lucius Windschuh wrote: >> [...] >> panic: lapic1: zero divisor > [...] > --- local_apic.c.prev =A0 2009-05-01 23:53:37.000000000 +0300 > +++ local_apic.c =A0 =A0 =A0 =A02009-05-05 01:10:04.000000000 +0300 > @@ -319,7 +319,7 @@ lapic_setup(int boot) > =A0 =A0 =A0 =A0} > > =A0 =A0 =A0 =A0/* We don't setup the timer during boot on the BSP until l= ater. */ > - =A0 =A0 =A0 if (!(boot && PCPU_GET(cpuid) =3D=3D 0)) { > + =A0 =A0 =A0 if (!(boot && PCPU_GET(cpuid) =3D=3D 0) && lapic_timer_hz != =3D 0) { > =A0 =A0 =A0 =A0 =A0 =A0 =A0 =A0KASSERT(lapic_timer_period !=3D 0, ("lapic= %u: zero divisor", > =A0 =A0 =A0 =A0 =A0 =A0 =A0 =A0 =A0 =A0lapic_id())); > =A0 =A0 =A0 =A0 =A0 =A0 =A0 =A0lapic_timer_set_divisor(lapic_timer_diviso= r); This patch solves the panic. C3 instead of C2 saves between 0.5 and 1.5 Watt here with some quick measurements. Thanks. Lucius From owner-freebsd-mobile@FreeBSD.ORG Tue May 5 09:30:36 2009 Return-Path: Delivered-To: freebsd-mobile@freebsd.org Received: from mx1.freebsd.org (mx1.freebsd.org [IPv6:2001:4f8:fff6::34]) by hub.freebsd.org (Postfix) with ESMTP id 385B3106564A; Tue, 5 May 2009 09:30:36 +0000 (UTC) (envelope-from peterjeremy@optushome.com.au) Received: from fallbackmx07.syd.optusnet.com.au (fallbackmx07.syd.optusnet.com.au [211.29.132.9]) by mx1.freebsd.org (Postfix) with ESMTP id B9B898FC0A; Tue, 5 May 2009 09:30:35 +0000 (UTC) (envelope-from peterjeremy@optushome.com.au) Received: from mail36.syd.optusnet.com.au (mail36.syd.optusnet.com.au [211.29.133.76]) by fallbackmx07.syd.optusnet.com.au (8.13.1/8.13.1) with ESMTP id n459JJBj029564; Tue, 5 May 2009 19:19:19 +1000 Received: from server.vk2pj.dyndns.org (c122-106-216-167.belrs3.nsw.optusnet.com.au [122.106.216.167]) by mail36.syd.optusnet.com.au (8.13.1/8.13.1) with ESMTP id n459JFEW001664 (version=TLSv1/SSLv3 cipher=DHE-RSA-AES256-SHA bits=256 verify=NO); Tue, 5 May 2009 19:19:16 +1000 X-Bogosity: Ham, spamicity=0.000000 Received: from server.vk2pj.dyndns.org (localhost.vk2pj.dyndns.org [127.0.0.1]) by server.vk2pj.dyndns.org (8.14.3/8.14.3) with ESMTP id n459JF5F094733; Tue, 5 May 2009 19:19:15 +1000 (EST) (envelope-from peter@server.vk2pj.dyndns.org) Received: (from peter@localhost) by server.vk2pj.dyndns.org (8.14.3/8.14.3/Submit) id n459JFr9094732; Tue, 5 May 2009 19:19:15 +1000 (EST) (envelope-from peter) Date: Tue, 5 May 2009 19:19:14 +1000 From: Peter Jeremy To: Alexander Motin Message-ID: <20090505091914.GA94521@server.vk2pj.dyndns.org> References: <49FE1826.4060000@FreeBSD.org> <49FE29A4.30507@root.org> <49FE5EC8.3040205@FreeBSD.org> MIME-Version: 1.0 Content-Type: multipart/signed; micalg=pgp-sha1; protocol="application/pgp-signature"; boundary="cWoXeonUoKmBZSoM" Content-Disposition: inline In-Reply-To: <49FE5EC8.3040205@FreeBSD.org> X-PGP-Key: http://members.optusnet.com.au/peterjeremy/pubkey.asc User-Agent: Mutt/1.5.19 (2009-01-05) Cc: FreeBSD acpi , FreeBSD-Current , freebsd-mobile@freebsd.org Subject: Re: Fighting for the power. X-BeenThere: freebsd-mobile@freebsd.org X-Mailman-Version: 2.1.5 Precedence: list List-Id: Mobile computing with FreeBSD List-Unsubscribe: , List-Archive: List-Post: List-Help: List-Subscribe: , X-List-Received-Date: Tue, 05 May 2009 09:30:36 -0000 --cWoXeonUoKmBZSoM Content-Type: text/plain; charset=us-ascii Content-Disposition: inline Content-Transfer-Encoding: quoted-printable On 2009-May-04 06:19:36 +0300, Alexander Motin wrote: >System will always have tons of waiting callouts and timeouts to be=20 >handled. So timer will be always needed. Working timer. Yes, but a tickless kernel will let the CPU stay asleep for longer since it doesn't need to wake up just to discover there's nothing to do. >number of idle disk write activity, but I haven't very succeeded. Even=20 >in my quite simple icewm X environment something was persistently=20 >writing something every several minutes. I have found and disabled some=20 >activity sources, but it was not enough. I've recently (in the last few days) worked through minimising the write activity on the SSD in my laptop (I wrote a tool that monitors write transfers via devstat(3) and it would be possible to track down the actual modified files via kqueue(2) if necessary). I'm now down to about two chunks of about 13 transfers each per hour (due to entopy saving and ntp.drift updating). The changes I made were: 1) Mount the SSD filesystems as noatime 2) Turn off all local syslogging (syslog is directed to another system when my laptop is at home, lost otherwise). 3) Change maillog rotation to size instead of daily 4) Run save-entropy once per hour instead of every 11 minutes. 5) Patch the save-entropy script to reduce the write load when it's run (see PR bin/134225). 6) Use a swap-back /tmp By default, ntpd updates ntp.drift every hour. I might do some monitoring and see if the drift changes significantly over time. If it doesn't, hard-wiring the ntp.drift file will save some writes. (The other option would be to tweak the relevant timecounter until the actual drift is 0 and then stop ntpd and just run something like ntpdate regularly to compensate for the remaining drift). Experimentation shows that firefox3 generates a fairly heavy write load - continuously updating several internal databases whilst it is in use. Turning off the "Block reported attack sites" and "Block reported web forgeries" options under 'Security' stops it updating urlclassifier3.sqlite. Note that when you update a file, you implicitly update the associated inode and the filesystem superbock. > What would happen in some=20 >complicated KDE/Gnome environment I am just afraid to think. I'd recommend avoiding a heavyweight window manager and using something like fwvm or vtwm. --=20 Peter Jeremy --cWoXeonUoKmBZSoM Content-Type: application/pgp-signature Content-Disposition: inline -----BEGIN PGP SIGNATURE----- Version: GnuPG v2.0.11 (FreeBSD) iEYEARECAAYFAkoABJIACgkQ/opHv/APuIfq8wCdH8DXPq3Vv0V1hzLBO1KOmnG8 67AAnjuB8SS3/vaNaSu5WP+7b7xHQ6Xj =ZLjp -----END PGP SIGNATURE----- --cWoXeonUoKmBZSoM-- From owner-freebsd-mobile@FreeBSD.ORG Tue May 5 21:55:56 2009 Return-Path: Delivered-To: freebsd-mobile@freebsd.org Received: from mx1.freebsd.org (mx1.freebsd.org [IPv6:2001:4f8:fff6::34]) by hub.freebsd.org (Postfix) with ESMTP id 356991065689; Tue, 5 May 2009 21:55:56 +0000 (UTC) (envelope-from eitanadlerlist@gmail.com) Received: from qw-out-2122.google.com (qw-out-2122.google.com [74.125.92.27]) by mx1.freebsd.org (Postfix) with ESMTP id 45C168FC16; Tue, 5 May 2009 21:55:53 +0000 (UTC) (envelope-from eitanadlerlist@gmail.com) Received: by qw-out-2122.google.com with SMTP id 3so3651095qwe.7 for ; Tue, 05 May 2009 14:55:52 -0700 (PDT) DKIM-Signature: v=1; a=rsa-sha256; c=relaxed/relaxed; d=gmail.com; s=gamma; h=domainkey-signature:received:received:message-id:date:from :user-agent:mime-version:to:cc:subject:references:in-reply-to :x-enigmail-version:openpgp:content-type:content-transfer-encoding; bh=yx4brSKUDTB09SWwDxfsK92rS6enO9dX9V+R0m4vPbE=; b=mulAXzgx9iNdfP+/pDOJPwzP+t8pKWKvGpwlODTw2xEGJPBNUYNzjPsriXrgu+Wzol cKD1lXuBuVZkceodPf8w6KZ1LvkLgM7HLUyB3Ae4KGIn4SPntTikEEu/9UaVwfvG0qyl IrmChSUkjMRfI6KD42K0zaoktmVtToj7O3Z4E= DomainKey-Signature: a=rsa-sha1; c=nofws; d=gmail.com; s=gamma; h=message-id:date:from:user-agent:mime-version:to:cc:subject :references:in-reply-to:x-enigmail-version:openpgp:content-type :content-transfer-encoding; b=t2K1RwcYwUcWXGOd9xNhXuUyDAydBj8jbShBo7K/o/i4RV86qR6fB4K1i1sGgGFycS 1QN9YNOAydqGLsLuU4RAgJGt5yeHmBhRlJSSzaG2FTZagoOETQUWvPlcrS33urtNcXOF gQCpE+GoJG6+cA4TOHapREW+VONtCanh1aL6U= Received: by 10.224.2.202 with SMTP id 10mr723225qak.336.1241558952496; Tue, 05 May 2009 14:29:12 -0700 (PDT) Received: from aargh.lan (ool-182fcc8b.dyn.optonline.net [24.47.204.139]) by mx.google.com with ESMTPS id 5sm3549213ywl.22.2009.05.05.14.29.11 (version=TLSv1/SSLv3 cipher=RC4-MD5); Tue, 05 May 2009 14:29:12 -0700 (PDT) Message-ID: <4A00AFEB.7010001@gmail.com> Date: Tue, 05 May 2009 17:30:19 -0400 From: Eitan Adler User-Agent: Mozilla (X11; U; FreeBSD i386; en-US; ) Gecko Thunderbird Mnenhy/0.7.6.666 MIME-Version: 1.0 To: mcdouga9@egr.msu.edu References: <49FE1826.4060000@FreeBSD.org> <20090504011421.GI6901@egr.msu.edu> In-Reply-To: <20090504011421.GI6901@egr.msu.edu> X-Enigmail-Version: 0.95.7 OpenPGP: id=E9C2CCD1; url=pgp.mit.edu Content-Type: text/plain; charset=ISO-8859-1 Content-Transfer-Encoding: 7bit Cc: mav@FreeBSD.org, freebsd-current@freebsd.org, freebsd-acpi@freebsd.org, freebsd-mobile@freebsd.org Subject: Re: Fighting for the power. X-BeenThere: freebsd-mobile@freebsd.org X-Mailman-Version: 2.1.5 Precedence: list List-Id: Mobile computing with FreeBSD List-Unsubscribe: , List-Archive: List-Post: List-Help: List-Subscribe: , X-List-Received-Date: Tue, 05 May 2009 21:55:56 -0000 Adam McDougall wrote: > On Mon, May 04, 2009 at 01:18:14AM +0300, Alexander Motin wrote: > > I would like to summarize some of my knowledge on reducing FreeBSD power > consumption and describe some new things I have recently implemented in > 8-CURRENT. The main character of this story is my 12" Acer TravelMate > 6292 laptop with C2D T7700 2.4GHz CPU, 965GM chipset and SATA HDD, under > amd64 8-CURRENT. > Could some of these tips get added to 11.15 Power and Resource Management? I'm sure many people who don't regularly read the mailing lists would like to use these tips. -- Eitan Adler "Security is increased by designing for the way humans actually behave." -Jakob Nielsen From owner-freebsd-mobile@FreeBSD.ORG Thu May 7 00:50:38 2009 Return-Path: Delivered-To: mobile@freebsd.org Received: from mx1.freebsd.org (mx1.freebsd.org [IPv6:2001:4f8:fff6::34]) by hub.freebsd.org (Postfix) with ESMTP id DE89D106566C for ; Thu, 7 May 2009 00:50:38 +0000 (UTC) (envelope-from phpmail@the-gurus.de) Received: from mx01.d-labs.de (ist.d-labs.de [213.239.218.44]) by mx1.freebsd.org (Postfix) with ESMTP id A8BC48FC1A for ; Thu, 7 May 2009 00:50:38 +0000 (UTC) (envelope-from phpmail@the-gurus.de) Received: by mx01.d-labs.de (Postfix, from userid 2039) id 42396841BD; Thu, 7 May 2009 02:28:10 +0200 (CEST) To: mobile@freebsd.org From: password@dengo.the-gurus.de Message-Id: <20090507002810.42396841BD@mx01.d-labs.de> Date: Thu, 7 May 2009 02:28:10 +0200 (CEST) Cc: Subject: New -[ dengo's page ]- Password X-BeenThere: freebsd-mobile@freebsd.org X-Mailman-Version: 2.1.5 Precedence: list List-Id: Mobile computing with FreeBSD List-Unsubscribe: , List-Archive: List-Post: List-Help: List-Subscribe: , X-List-Received-Date: Thu, 07 May 2009 00:50:39 -0000 Name: jonnik1 Password: 1agojad5 http://dengo.the-gurus.de/index.php?section=login From owner-freebsd-mobile@FreeBSD.ORG Thu May 7 06:14:20 2009 Return-Path: Delivered-To: freebsd-mobile@freebsd.org Received: from mx1.freebsd.org (mx1.freebsd.org [IPv6:2001:4f8:fff6::34]) by hub.freebsd.org (Postfix) with ESMTP id 09333106566B; Thu, 7 May 2009 06:14:20 +0000 (UTC) (envelope-from imp@bsdimp.com) Received: from harmony.bsdimp.com (bsdimp.com [199.45.160.85]) by mx1.freebsd.org (Postfix) with ESMTP id BDDD58FC1F; Thu, 7 May 2009 06:14:19 +0000 (UTC) (envelope-from imp@bsdimp.com) Received: from localhost (localhost [127.0.0.1]) by harmony.bsdimp.com (8.14.3/8.14.1) with ESMTP id n476Ax9N066591; Thu, 7 May 2009 00:11:00 -0600 (MDT) (envelope-from imp@bsdimp.com) Date: Thu, 07 May 2009 00:10:59 -0600 (MDT) Message-Id: <20090507.001059.-1558772981.imp@bsdimp.com> To: onemda@gmail.com From: "M. Warner Losh" In-Reply-To: <3a142e750905040240g58152e69p6fcb797a5e026426@mail.gmail.com> References: <49FE1826.4060000@FreeBSD.org> <3a142e750905040240g58152e69p6fcb797a5e026426@mail.gmail.com> X-Mailer: Mew version 5.2 on Emacs 21.3 / Mule 5.0 (SAKAKI) Mime-Version: 1.0 Content-Type: Text/Plain; charset=us-ascii Content-Transfer-Encoding: 7bit Cc: mav@freebsd.org, freebsd-current@freebsd.org, freebsd-acpi@freebsd.org, freebsd-mobile@freebsd.org Subject: Re: Fighting for the power. X-BeenThere: freebsd-mobile@freebsd.org X-Mailman-Version: 2.1.5 Precedence: list List-Id: Mobile computing with FreeBSD List-Unsubscribe: , List-Archive: List-Post: List-Help: List-Subscribe: , X-List-Received-Date: Thu, 07 May 2009 06:14:20 -0000 In message: <3a142e750905040240g58152e69p6fcb797a5e026426@mail.gmail.com> "Paul B. Mahol" writes: : On 5/4/09, Alexander Motin wrote: : > 2. PCI devices : > PCI bus provides method to control device power. For example, I have : > completely no use for my FireWire controller and most of time - EHCI USB : > controller. Disabling them allows me to save about 3W of power. To : > disable all unneeded PCI devices you should build kernel without their : > drivers and add to loader.conf: : > hw.pci.do_power_nodriver=3 : > To enable devices back all you need to do is just load their drivers as : > modules. : : Unloading modules doesnt put them back into into D3 state. : You are forced to load some another module again to put wanted device : into D3 state. It should. If it isn't, that's a bug. Warner From owner-freebsd-mobile@FreeBSD.ORG Fri May 8 10:34:54 2009 Return-Path: Delivered-To: freebsd-mobile@freebsd.org Received: from mx1.freebsd.org (mx1.freebsd.org [IPv6:2001:4f8:fff6::34]) by hub.freebsd.org (Postfix) with ESMTP id 85CC0106566B; Fri, 8 May 2009 10:34:54 +0000 (UTC) (envelope-from onemda@gmail.com) Received: from mail-bw0-f165.google.com (mail-bw0-f165.google.com [209.85.218.165]) by mx1.freebsd.org (Postfix) with ESMTP id 7F48B8FC0C; Fri, 8 May 2009 10:34:53 +0000 (UTC) (envelope-from onemda@gmail.com) Received: by bwz9 with SMTP id 9so1285555bwz.43 for ; Fri, 08 May 2009 03:34:52 -0700 (PDT) DKIM-Signature: v=1; a=rsa-sha256; c=relaxed/relaxed; d=gmail.com; s=gamma; h=domainkey-signature:mime-version:received:in-reply-to:references :date:message-id:subject:from:to:cc:content-type :content-transfer-encoding; bh=p2cItQSo7NSeVItexvTC4atsaRofqEwF9mh9nWatND8=; b=KdBo0A80m64jlcGk70IH/13IzI12ys138mpqzwvvVsHxCGsxnOq8hMgUjD6Cr+KjZ3 kywEIm9Lt9dngtOh8ga5yxQXLl8Wl6P259L/dofE7ORFuhnvLqA/oMt0bv/PrdF802lc Wi8nuT7QT+UrSaTBTx2nJ5Y6I/xNsKgmJ6E8A= DomainKey-Signature: a=rsa-sha1; c=nofws; d=gmail.com; s=gamma; h=mime-version:in-reply-to:references:date:message-id:subject:from:to :cc:content-type:content-transfer-encoding; b=Cn3iRY7MelgofEeezLYWo+6ckjLqPH15X0Us402zeC3yqlhRhi+SslGMTARtb8ARhC uRm9pxToIoqYOvVVXTlrNyzsJZvBH9yWc6mOcKfy6WaNDtWLb/Q9N8HfHSpKgHGW1tl4 +AUGmvNTr8eT6PQEtOGgu8Htz2FPB3jnIYiuA= MIME-Version: 1.0 Received: by 10.239.154.83 with SMTP id d19mr206468hbc.33.1241778892413; Fri, 08 May 2009 03:34:52 -0700 (PDT) In-Reply-To: <20090507.001059.-1558772981.imp@bsdimp.com> References: <49FE1826.4060000@FreeBSD.org> <3a142e750905040240g58152e69p6fcb797a5e026426@mail.gmail.com> <20090507.001059.-1558772981.imp@bsdimp.com> Date: Fri, 8 May 2009 10:34:52 +0000 Message-ID: <3a142e750905080334qb62dcb5hcd07ce028a4ff035@mail.gmail.com> From: "Paul B. Mahol" To: "M. Warner Losh" Content-Type: text/plain; charset=ISO-8859-1 Content-Transfer-Encoding: 7bit Cc: mav@freebsd.org, freebsd-current@freebsd.org, freebsd-acpi@freebsd.org, freebsd-mobile@freebsd.org Subject: Re: Fighting for the power. X-BeenThere: freebsd-mobile@freebsd.org X-Mailman-Version: 2.1.5 Precedence: list List-Id: Mobile computing with FreeBSD List-Unsubscribe: , List-Archive: List-Post: List-Help: List-Subscribe: , X-List-Received-Date: Fri, 08 May 2009 10:34:55 -0000 On 5/7/09, M. Warner Losh wrote: > In message: <3a142e750905040240g58152e69p6fcb797a5e026426@mail.gmail.com> > "Paul B. Mahol" writes: > : On 5/4/09, Alexander Motin wrote: > : > 2. PCI devices > : > PCI bus provides method to control device power. For example, I have > : > completely no use for my FireWire controller and most of time - EHCI USB > : > controller. Disabling them allows me to save about 3W of power. To > : > disable all unneeded PCI devices you should build kernel without their > : > drivers and add to loader.conf: > : > hw.pci.do_power_nodriver=3 > : > To enable devices back all you need to do is just load their drivers as > : > modules. > : > : Unloading modules doesnt put them back into into D3 state. > : You are forced to load some another module again to put wanted device > : into D3 state. > > It should. If it isn't, that's a bug. It's a bug. On machine resume(pci_resume), pci_cfg_restore() is called causing D3 -> D0 for all devices(including not attached ones). Unloading module/detaching device doesn't call pci_cfg_save. Should device_detach routine be used or new one like pci_driver_removed() implemented? -- Paul From owner-freebsd-mobile@FreeBSD.ORG Fri May 8 13:10:39 2009 Return-Path: Delivered-To: freebsd-mobile@freebsd.org Received: from mx1.freebsd.org (mx1.freebsd.org [IPv6:2001:4f8:fff6::34]) by hub.freebsd.org (Postfix) with ESMTP id 0A3D01065673; Fri, 8 May 2009 13:10:39 +0000 (UTC) (envelope-from imp@bsdimp.com) Received: from harmony.bsdimp.com (bsdimp.com [199.45.160.85]) by mx1.freebsd.org (Postfix) with ESMTP id BBFEA8FC12; Fri, 8 May 2009 13:10:38 +0000 (UTC) (envelope-from imp@bsdimp.com) Received: from localhost (localhost [127.0.0.1]) by harmony.bsdimp.com (8.14.3/8.14.1) with ESMTP id n48D70nR089707; Fri, 8 May 2009 07:07:01 -0600 (MDT) (envelope-from imp@bsdimp.com) Date: Fri, 08 May 2009 07:06:59 -0600 (MDT) Message-Id: <20090508.070659.1622573996.imp@bsdimp.com> To: onemda@gmail.com From: "M. Warner Losh" In-Reply-To: <3a142e750905080334qb62dcb5hcd07ce028a4ff035@mail.gmail.com> References: <3a142e750905040240g58152e69p6fcb797a5e026426@mail.gmail.com> <20090507.001059.-1558772981.imp@bsdimp.com> <3a142e750905080334qb62dcb5hcd07ce028a4ff035@mail.gmail.com> X-Mailer: Mew version 5.2 on Emacs 21.3 / Mule 5.0 (SAKAKI) Mime-Version: 1.0 Content-Type: Text/Plain; charset=us-ascii Content-Transfer-Encoding: 7bit Cc: mav@freebsd.org, freebsd-current@freebsd.org, freebsd-acpi@freebsd.org, freebsd-mobile@freebsd.org Subject: Re: Fighting for the power. X-BeenThere: freebsd-mobile@freebsd.org X-Mailman-Version: 2.1.5 Precedence: list List-Id: Mobile computing with FreeBSD List-Unsubscribe: , List-Archive: List-Post: List-Help: List-Subscribe: , X-List-Received-Date: Fri, 08 May 2009 13:10:39 -0000 In message: <3a142e750905080334qb62dcb5hcd07ce028a4ff035@mail.gmail.com> "Paul B. Mahol" writes: : On 5/7/09, M. Warner Losh wrote: : > In message: <3a142e750905040240g58152e69p6fcb797a5e026426@mail.gmail.com> : > "Paul B. Mahol" writes: : > : On 5/4/09, Alexander Motin wrote: : > : > 2. PCI devices : > : > PCI bus provides method to control device power. For example, I have : > : > completely no use for my FireWire controller and most of time - EHCI USB : > : > controller. Disabling them allows me to save about 3W of power. To : > : > disable all unneeded PCI devices you should build kernel without their : > : > drivers and add to loader.conf: : > : > hw.pci.do_power_nodriver=3 : > : > To enable devices back all you need to do is just load their drivers as : > : > modules. : > : : > : Unloading modules doesnt put them back into into D3 state. : > : You are forced to load some another module again to put wanted device : > : into D3 state. : > : > It should. If it isn't, that's a bug. : : It's a bug. : : On machine resume(pci_resume), pci_cfg_restore() is called causing D3 -> D0 for : all devices(including not attached ones). : Unloading module/detaching device doesn't call pci_cfg_save. : : Should device_detach routine be used or new one like : pci_driver_removed() implemented? No. device_detach shouldn't be used for this. This should happen all in the PCI bus code when do_power_nodriver is > 0. Warner From owner-freebsd-mobile@FreeBSD.ORG Fri May 8 14:44:04 2009 Return-Path: Delivered-To: freebsd-mobile@freebsd.org Received: from mx1.freebsd.org (mx1.freebsd.org [IPv6:2001:4f8:fff6::34]) by hub.freebsd.org (Postfix) with ESMTP id A83CF106566C for ; Fri, 8 May 2009 14:44:04 +0000 (UTC) (envelope-from guru@unixarea.de) Received: from dd12710.kasserver.com (dd12710.kasserver.com [85.13.134.233]) by mx1.freebsd.org (Postfix) with ESMTP id 645258FC1E for ; Fri, 8 May 2009 14:44:04 +0000 (UTC) (envelope-from guru@unixarea.de) Received: from rebelion.Sisis.de (cazador.sisis.de [193.31.11.193]) by dd12710.kasserver.com (Postfix) with ESMTP id CCCB018516EC9; Fri, 8 May 2009 16:17:59 +0200 (CEST) Received: (from guru@localhost) by rebelion.Sisis.de (8.14.2/8.13.8/Submit) id n48EHt6u013667; Fri, 8 May 2009 16:17:55 +0200 (CEST) (envelope-from guru@unixarea.de) X-Authentication-Warning: rebelion.Sisis.de: guru set sender to guru@unixarea.de using -f Date: Fri, 8 May 2009 16:17:55 +0200 From: Matthias Apitz To: freebsd-mobile@freebsd.org Message-ID: <20090508141755.GB13584@rebelion.Sisis.de> References: <20090428083627.GA3621@rebelion.Sisis.de> Mime-Version: 1.0 Content-Type: text/plain; charset=iso-8859-1 Content-Disposition: inline Content-Transfer-Encoding: 8bit In-Reply-To: <20090428083627.GA3621@rebelion.Sisis.de> User-Agent: Mutt/1.4.2.3i X-Operating-System: FreeBSD 7.0-STABLE (i386) Cc: freebsd-current@freebsd.org Subject: Re: laptop Dell M4400 with -CURRENT? X-BeenThere: freebsd-mobile@freebsd.org X-Mailman-Version: 2.1.5 Precedence: list Reply-To: Matthias Apitz List-Id: Mobile computing with FreeBSD List-Unsubscribe: , List-Archive: List-Post: List-Help: List-Subscribe: , X-List-Received-Date: Fri, 08 May 2009 14:44:04 -0000 El da Tuesday, April 28, 2009 a las 10:36:27AM +0200, Matthias Apitz escribi: > > Hello, > > I'm planning to order a new laptop and got an offer for a Dell M4400 > with the following main details: > > Precision M4400 : Intel Core 2 Extreme X9100 (3.06GHz,1066MHz,6MB) > Base Option : 512MB Discrete nVidia FX770M Graphics Card (with 512MB dedicated memory) > Palmrest : UPEK Swipe Fingerprint Reader Biometric > Display : 15.4in Widescreen WUXGA (1920X1200) with Dual CCFL > Camera : Integrated 0.3 Mega Pixel Camera with Microphone for 2CCFL LCD Panel > LCD Back Cover : 2CCFL > Memory : 4096MB (2x2048) 800MHz DDR2 Dual Channel > disk : 250GB Serial ATA (7200 1/min) Festplatte (Free-Fall-Sensor) > Optical Drive : Roxio Creator 9.0 Software and Media Included > Optisches Laufwerk : 8x DVD+/-RW Laufwerk ohne Software > Battery : Primary 9-cell 85 W/HR LI-ION 451-10589 > Battery : Additional 6-Cell 56 W/HR LI-ION 451-10590 > Wireless : EMEA Dell Wireless 1510 (802.11a/b/g/n 2X3) MiniCard for Core 2 Extreme ONLY > Wireless : EMEA Dell Wireless 370 Bluetooth 2.1 MiniCard > Keyboard : Internal German Qwertz Keyboard I have now installed CURRENT in that Precision M4400; shrinked the Vista partition to 50 GByte and installed in the remaining 170 GByte FreeBSD CURRENT from a prepared USB key. It seems that the Quadro FX 770M Graphics Card is not supported by the NVIDIA driver in Xorg 1.6. -- any idea how to solve this? Thx in advance matthias -- Matthias Apitz t +49-89-61308 351 - f +49-89-61308 399 - m +49-170-4527211 e - w http://www.unixarea.de/ People who hate Microsoft Windows use Linux but people who love UNIX use FreeBSD. From owner-freebsd-mobile@FreeBSD.ORG Fri May 8 16:04:00 2009 Return-Path: Delivered-To: freebsd-mobile@freebsd.org Received: from mx1.freebsd.org (mx1.freebsd.org [IPv6:2001:4f8:fff6::34]) by hub.freebsd.org (Postfix) with ESMTP id 22B001065673 for ; Fri, 8 May 2009 16:04:00 +0000 (UTC) (envelope-from rnoland@FreeBSD.org) Received: from gizmo.2hip.net (gizmo.2hip.net [64.74.207.195]) by mx1.freebsd.org (Postfix) with ESMTP id D6CC18FC2A for ; Fri, 8 May 2009 16:03:59 +0000 (UTC) (envelope-from rnoland@FreeBSD.org) Received: from [192.168.1.4] (adsl-154-182-184.bna.bellsouth.net [68.154.182.184]) (authenticated bits=0) by gizmo.2hip.net (8.14.3/8.14.3) with ESMTP id n48FSXLi091668 (version=TLSv1/SSLv3 cipher=DHE-RSA-AES256-SHA bits=256 verify=NO); Fri, 8 May 2009 11:28:33 -0400 (EDT) (envelope-from rnoland@FreeBSD.org) From: Robert Noland To: Matthias Apitz In-Reply-To: <20090508141755.GB13584@rebelion.Sisis.de> References: <20090428083627.GA3621@rebelion.Sisis.de> <20090508141755.GB13584@rebelion.Sisis.de> Content-Type: multipart/signed; micalg="pgp-sha1"; protocol="application/pgp-signature"; boundary="=-/MGbhDqCNVtlOmgASu1X" Organization: FreeBSD Date: Fri, 08 May 2009 10:28:09 -0500 Message-Id: <1241796489.1733.25.camel@balrog.2hip.net> Mime-Version: 1.0 X-Mailer: Evolution 2.26.1.1 FreeBSD GNOME Team Port X-Spam-Status: No, score=-1.7 required=5.0 tests=AWL,BAYES_00,RCVD_IN_PBL, RCVD_IN_SORBS_DUL,RDNS_DYNAMIC autolearn=no version=3.2.5 X-Spam-Checker-Version: SpamAssassin 3.2.5 (2008-06-10) on gizmo.2hip.net Cc: freebsd-current@freebsd.org, freebsd-mobile@freebsd.org Subject: Re: laptop Dell M4400 with -CURRENT? X-BeenThere: freebsd-mobile@freebsd.org X-Mailman-Version: 2.1.5 Precedence: list List-Id: Mobile computing with FreeBSD List-Unsubscribe: , List-Archive: List-Post: List-Help: List-Subscribe: , X-List-Received-Date: Fri, 08 May 2009 16:04:00 -0000 --=-/MGbhDqCNVtlOmgASu1X Content-Type: text/plain; charset="ISO-8859-1" Content-Transfer-Encoding: quoted-printable On Fri, 2009-05-08 at 16:17 +0200, Matthias Apitz wrote: > El d=EDa Tuesday, April 28, 2009 a las 10:36:27AM +0200, Matthias Apitz e= scribi=F3: >=20 > >=20 > > Hello, > >=20 > > I'm planning to order a new laptop and got an offer for a Dell M4400 > > with the following main details: > >=20 > > Precision M4400 : Intel Core 2 Extreme X9100 (3.06GHz,1066MHz,6MB) > > Base Option : 512MB Discrete nVidia FX770M Graphics Card (with 512MB= dedicated memory) > > Palmrest : UPEK Swipe Fingerprint Reader Biometric > > Display : 15.4in Widescreen WUXGA (1920X1200) with Dual CCFL > > Camera : Integrated 0.3 Mega Pixel Camera with Microphone for 2CCFL = LCD Panel > > LCD Back Cover : 2CCFL > > Memory : 4096MB (2x2048) 800MHz DDR2 Dual Channel > > disk : 250GB Serial ATA (7200 1/min) Festplatte (Free-Fall-Sensor) > > Optical Drive : Roxio Creator 9.0 Software and Media Included > > Optisches Laufwerk : 8x DVD+/-RW Laufwerk ohne Software > > Battery : Primary 9-cell 85 W/HR LI-ION 451-10589 > > Battery : Additional 6-Cell 56 W/HR LI-ION 451-10590 > > Wireless : EMEA Dell Wireless 1510 (802.11a/b/g/n 2X3) MiniCard for = Core 2 Extreme ONLY > > Wireless : EMEA Dell Wireless 370 Bluetooth 2.1 MiniCard=20 > > Keyboard : Internal German Qwertz Keyboard >=20 > I have now installed CURRENT in that Precision M4400; shrinked the Vista > partition to 50 GByte and installed in the remaining 170 GByte FreeBSD > CURRENT from a prepared USB key. >=20 > It seems that the Quadro FX 770M Graphics Card is not supported by the > NVIDIA driver in Xorg 1.6. -- any idea how to solve this? I have ported the nouveau drm driver. http://people.freebsd.org/~rnoland/drm-nouveau-043009.patch It is working on NV50 cards, NV40 was working, but with WITNESS enabled I seem to be getting a panic on NV40. My NV40 card seems to be having memory issues so I haven't been able to get and/or see the backtrace. I think it is just a locking issue which should be pretty easily solved if I can get a clear backtrace. You will need current libdrm and xf86-video-nouveau from ports. This won't get you 3d right now, but should get you EXA + Xv. robert. > Thx in advance >=20 > matthias --=20 Robert Noland FreeBSD --=-/MGbhDqCNVtlOmgASu1X Content-Type: application/pgp-signature; name="signature.asc" Content-Description: This is a digitally signed message part -----BEGIN PGP SIGNATURE----- Version: GnuPG v2.0.11 (FreeBSD) iEYEABECAAYFAkoET4kACgkQM4TrQ4qfROPexACcC3rFSNW0pw/X5whWgraMrvDA wXwAoIoR20hoaepPUyUzFUfwEUDZ82PJ =tHbM -----END PGP SIGNATURE----- --=-/MGbhDqCNVtlOmgASu1X--