From owner-FreeBSD-users-jp@jp.FreeBSD.org Sun Mar  8 14:37:24 2009
Received: (from daemon@localhost)
	by castle.jp.FreeBSD.org (8.11.6p2+3.4W/8.11.3) id n285bOG78079;
	Sun, 8 Mar 2009 14:37:24 +0900 (JST)
	(envelope-from owner-FreeBSD-users-jp@jp.FreeBSD.org)
Received: from sakura.ninth-nine.com ([2001:2f0:104:80a0:230:48ff:fe41:2455])
	by castle.jp.FreeBSD.org (8.11.6p2+3.4W/8.11.3) with ESMTP/inet6 id n285bOt78074
	for <FreeBSD-users-jp@jp.FreeBSD.org>; Sun, 8 Mar 2009 14:37:24 +0900 (JST)
	(envelope-from nork@ninth-nine.com)
Received: from nadesico.ninth-nine.com (nadesico.ninth-nine.com [219.127.74.122]) by sakura.ninth-nine.com (8.14.1/8.14.1/NinthNine) with ESMTP id n285bIPP038687 for <FreeBSD-users-jp@jp.FreeBSD.org>; Sun, 8 Mar 2009 14:37:18 +0900 (JST) (envelope-from nork@ninth-nine.com)
From: Norikatsu Shigemura <nork@ninth-nine.com>
To: FreeBSD-users-jp@jp.FreeBSD.org
Message-Id: <20090308143717.c69f2c5b.nork@ninth-nine.com>
In-Reply-To: <200903070636.n276apxc008723@softbank219001162114.bbtec.net>
References: <200811022251.mA2MpLwh001847@localhost>
	<20090228170231.234ec102.nork@ninth-nine.com>
	<20090228173619.cbaf83a7.nork@ninth-nine.com>
	<200903010909.n21990Qb002967@localhost>
	<20090301184041.596a5acd.nork@ninth-nine.com>
	<20090301185737.296751b0.nork@ninth-nine.com>
	<200903021056.n22AuoPu001805@softbank219001162114.bbtec.net>
	<200903021334.n22DYSWI002113@softbank219001162114.bbtec.net>
	<200903070636.n276apxc008723@softbank219001162114.bbtec.net>
X-Mailer: Sylpheed 2.6.0 (GTK+ 2.14.7; i386-portbld-freebsd8.0)
Mime-Version: 1.0
Content-Type: text/plain; charset=ISO-2022-JP
Content-Transfer-Encoding: 7bit
X-Greylist: Sender IP whitelisted, not delayed by milter-greylist-2.0.2 (sakura.ninth-nine.com [219.127.74.121]); Sun, 08 Mar 2009 14:37:18 +0900 (JST)
Reply-To: FreeBSD-users-jp@jp.FreeBSD.org
Precedence: list
Date: Sun, 8 Mar 2009 14:37:17 +0900
X-Sequence: FreeBSD-users-jp 92174
Subject: [FreeBSD-users-jp 92174] Re: Phenom
 =?ISO-2022-JP?B?GyRCJEokSSROGyhC?= cpufreq
Sender: owner-FreeBSD-users-jp@jp.FreeBSD.org
X-Originator: nork@ninth-nine.com
X-Distribute: distribute version 2.1 (Alpha) patchlevel 24e+060209

$B=EB<K!9n$G$9!#(B

On Sat, 07 Mar 2009 15:36:51 +0900
"G .Otsuji" <annona2@gmail.com> wrote:
> $B$=$7$F$@$a$b$H$G%j%V!<%H$7$^$7$?!#(B
> $B$=$&$9$k$H(Bacpi_throttle0$B$,G'<1$5$l$k$G$O$J$$$G$9$+(B!

	$B0l1~(B, $B8x<0$K$O(B cpufreq(4) $B$O5/F0;~$7$+G'<1$7(B/$BAH$_9~$a$^$;$s(B:-)$B!#(B

> $B$U$?$D$N(Bcpufreq$B$,G'<1$5$l$F$^$9!#(B
> $B$3$l$i$,:.$6$C$?7k2L!"(B
>  % sysctl dev.cpu.0.freq_levels       
>  dev.cpu.0.freq_levels: 2500/96000 1875/72000 1250/29000 937/21750 625/14500 312/7250
> $B$3$&$J$j$^$7$?!#(B

	$B4pK\E*$K$=$&$$$&F0$-$GLdBj$"$j$^$;$s!#J#?t$N%a%+%K%:%`$,$"$k;~$O(B, $BJ#?t(B
	$B$N%a%+%K%:%`$GO"F0$7$FF0$-$^$9!#(B

> (2)$B%U%j!<%:$9$k$+$I$&$+!#(B
> $B$=$3$G!"$@$a$b$H$G(B,freq=312$B$H$7$F$_$^$9!#(B
>  # sysctl dev.cpu.0.freq=312
>  dev.cpu.0.freq: 2500
>  sysctl: dev.cpu.0.freq: Invalid argument
>  # sysctl dev.cpu.0.freq
>  dev.cpu.0.freq: 312
> Invalid argument$B$,$J$<JV$k$N$+$o$+$j$^$;$s$,!"(B
> $BK\Mh$J$iLp0u$,$D$$$F(B
> dev.cpu.0.freq: 2500 -> 312
> $B$H$J$k$O$:$G$9!#$7$+$7$=$N8e(Bdev.cpu.freq: 312$B$H$J$C$F$k$N$G(B
> $B<B:]$KJQ$o$C$F$O$$$k$h$&$G$9!#(B

	powerd $B$@$H0l5s$K%U%j!<%:$7$F$7$^$&$N$G(B, 1 $B8D(B 1 $B8D%Q%i%a!<%?%A%'%C%/(B
	$B$7$F$_$k$H(B 900MHz $B$H(B 500MHz, 400MHz, 300MHz, 200MHz, 100MHz
	$B$G%U%j!<%:$9$k$3$H$,$o$+$j$^$7$?!#(Bdebug.cpufreq.lowest=800 $B$@$H(B
	900MHz $B@_Dj$r5_$($J$$!#!#(B

	$B$_$F$k$H(B Invalid argument $B$,=P$F(B cpu 1 $B8DJ,$7$+(B P-state $B$,JQ$o(B
	$B$i$J$$;~$@$1(B($B;D$j$O$h$j>e0L$N(B state), $B%U%j!<%:$9$k$h$&$G$9!#(B

	cpufreq(4)$BE*$K$OA4BN$H$7$F$G$7$+(B(1 $B%Q%i%a!<%?$7$+$J$$(B)$B<~GH?t$rJQ99(B
	$B$G$-$J$$$?$a(B, $B8D!9$N%5%V%7%9%F%`$G(B CPU $B<~GH?t$,JQ$o$C$?>l9g$N<h$j07$$(B
	$B$,$I$&$J$k$+$O$o$+$j$^$;$s$,(B, $B$3$N$"$?$j$K860x$,$"$j$=$&$J5$$,$7$^$9!#(B

	$BAH$_9g$o$;3NG'$GF,$,DK$/$J$C$?$N$G(B, Invalid argument $B$N@5BN$^$GD4(B
	$B$Y$F$^$;$s!#(Borz

> (3)acpi_throttle
> acpi_throttle$B$O(BSTPCLK#$B?.9f$G%/%m%C%/$r2<$2$k$h$&$G$9!#(B
> acpi_throttle$B$O!"(BAMD$B$N(BBKDG$B$G$O$I$&$J$C$F$k$N$@$m$&$H;W$C$?$i(B
> AMD BKDG(bios kernel developer guide)$B$N(B
> Table 57: ACPI Power State Control Register SMAF Settings$B$N=j$K(B
> >  Occurs based upon SMC hardware-initiated throttling. AMD recommends
> > using PROCHOT_L for thermal throttling and not implementing
> > stop clock based throttling.
> $B$H$$$&$3$H$G(Bstop clock$B$r;H$C$?%9%m%C%H%j%s%0$O$"$^$j$*$9$9$a$G$O$J$$$h$&$G$9!#(B
> [$B7kO@$J$I(B]
> 1) acpi_throttle$B$rL5M}$d$jG'<1$5$;$F$bF0$/>l9g$,$"$k$1$IB?J,Nc30$G$9!#(B
> 2) acpi_throttle$B$N9b<~GH2;$,7k9=5$$K$J$j$^$7$?!#(B
> 3) acpi_throttle$B$O$"$^$j$*$9$9$a$G$O$J$$$h$&$G$9!#(B
> 4) $B%U%j!<%:$,:F8=$G$-$::$$j$^$7$?!#(B
> 5) acpi_throttle$B$HAH$_9g$o$;$F$&$^$/$$$/%^%6%\$b$"$k$N$+$b$H;W$o$l$^$9!#(B

	acpi_throttle$B$N%3!<%I(B(/usr/src/sys/dev/acpica/acpi_throttle.c)
	$B$r8+$F$_$^$7$?$,(B, p4tcc(4) $B$G$bF1$8$_$?$$$G$9$M!#$3$l$KDI2C$7$F$7$^(B
	$B$&$N$,@52r$H;W$o$l$^$9!#(B

        /*
         * On i386 platforms at least, ACPI throttling is accomplished by
         * the chipset modulating the STPCLK# pin based on the duty cycle.
         * Since p4tcc uses the same mechanism (but internal to the CPU),
         * we disable acpi_throttle when p4tcc is also present.
         */
        if (device_find_child(device_get_parent(dev), "p4tcc", -1) &&
            !resource_disabled("p4tcc", 0))
                return (ENXIO);

	$B0J>e$h$m$7$/$*4j$$$$$?$7$^$9!#(B
