recent FreeBSD 13.0-CURRENT has fans screaming again on PowerMac quad
Justin Hibbits
chmeeedalf at gmail.com
Fri Jun 19 16:10:59 UTC 2020
On Fri, 19 Jun 2020 15:57:43 +0000
Dennis Clarke <dclarke at blastwave.org> wrote:
> On 6/19/20 3:22 PM, Michael Tuexen wrote:
> >> On 19. Jun 2020, at 16:34, Justin Hibbits <chmeeedalf at gmail.com>
> >> wrote:
> >>
> >> On Fri, 19 Jun 2020 15:55:30 +0200
> >> Michael Tuexen <tuexen at freebsd.org> wrote:
> >>
> >>>> On 19. Jun 2020, at 14:22, Dennis Clarke via freebsd-ppc
> >>>> <freebsd-ppc at freebsd.org> wrote:
> >>>>
> >>>>
> >>>> Dear ppc64 big endian types:
> >>>>
> >>>> Sort of the same problem we had before. Except now the screaming
> >>>> fans seem to mysteriously die down for about thirty seconds
> >>>> before they start up again and run full blast for five minutes.
> >>>> It makes the machine a nasty blower fan thing to put down the
> >>>> hallway and run a 30 meter CAT6 ethernet to it just to deal with
> >>>> it at all.
> >>>>
> >>>> Anyone else seeing this ? It is really quite horrible to listen
> >>>> to.
> >>>>
> >>>> At the moment there is nothing running at all with the exception
> >>>> of a svnlite checkout of http://svn.freebsd.org/base/head and the
> >>>> machine is screaming as if its life may end at any moment.
> >>>> Thankfully I have spare parts for when these fans blow up :
> >>>>
> >>>>
> >>>> dclarke at enceladus:~ $ uptime
> >>>> 12:21PM up 33 mins, 2 users, load averages: 0.97, 0.84, 0.48
> >>>>
> >>>> dclarke at enceladus:~ $ uname -apKU
> >>>> FreeBSD enceladus 13.0-CURRENT FreeBSD 13.0-CURRENT #0 r362037:
> >>>> Thu Jun 11 06:09:20 UTC 2020
> >>>> root at releng1.nyi.freebsd.org:/usr/obj/usr/src/powerpc.powerpc64/sys/GENERIC64
> >>>> powerpc powerpc64 1300097 1300097
> >>>>
> >>>> dclarke at enceladus:~ $ cat /etc/rc.conf
> >>>> clear_tmp_enable="YES"
> >>>> syslogd_flags="-ss"
> >>>> hostname="enceladus"
> >>>> ifconfig_bge0="inet 172.16.35.8 netmask 255.255.255.192"
> >>>> defaultrouter="172.16.35.1"
> >>>> sshd_enable="YES"
> >>>> ntpd_enable="YES"
> >>>> # Set dumpdev to "AUTO" to enable crash dumps, "NO" to disable
> >>>> dumpdev="AUTO"
> >>>> powerd_enable="YES"
> >>>> dclarke at enceladus:~ $
> >>>> dclarke at enceladus:~ $
> >>>>
> >>>> top -CSP shows :
> >>>>
> >>>> last pid: 1113; load averages: 1.00, 0.70, 0.35
> >>>> up 0+00:29:42 12:17:57 55 processes: 3
> >>>> running, 51 sleeping, 1 waiting CPU 0: 8.6% user, 0.0% nice,
> >>>> 44.7% system, 0.3% interrupt, 46.3% idle CPU 1: 0.3% user,
> >>>> 0.0% nice, 2.8% system, 0.6% interrupt, 96.4% idle CPU 2:
> >>>> 0.0% user, 0.0% nice, 0.0% system, 0.0% interrupt, 0.0% idle
> >>>> CPU 3: 0.0% user, 0.0% nice, 0.0% system, 0.0% interrupt,
> >>>> 0.0% idle Mem: 28M Active, 696M Inact, 626M Wired, 344M Buf,
> >>>> 6406M Free Swap: 3615M Total, 3615M Free
> >>>>
> >>>> PID USERNAME THR PRI NICE SIZE RES STATE C TIME
> >>>> CPU COMMAND 11 root 4 155 ki31 0B 192K RUN 0
> >>>> 112:42 307.44% idle 1104 root 1 103 0 32M 19M
> >>>> CPU3 3 4:57 87.60% svnlite 12 root 22 -52 -
> >>>> 0B 1056K WAIT 1 0:12 2.65% intr 7 root 2 -16
> >>>> - 0B 96K - 0 0:04 1.17% cam 19 root 6 20
> >>>> - 0B 288K psleep 2 0:02 0.50% bufdaemon 1050
> >>>> dclarke 1 20 0 23M 5252K select 0 0:01 0.23% sshd
> >>>> 1113 dclarke 1 20 0 16M 4408K CPU0 0 0:00
> >>>> 0.01% top 931 root 1 20 0 23M 4676K select 2
> >>>> 0:00 0.01% ntpd 1109 dclarke 1 20 0 23M 5260K
> >>>> select 2 0:00 0.00% sshd 15 root 15 -68 - 0B
> >>>> 720K - 0 0:00 0.00% usb 971 root 1 20 0 19M
> >>>> 5696K select 3 0:00 0.00% sendmail 761 root 1
> >>>> 20 0 14M 2384K select 2 0:00 0.00% syslogd 0 root
> >>>> 21 -16
> >>>> - 0B 1008K swapin 3 0:00 0.00% kernel 1062 root
> >>>> 1 20 0 15M 4944K pause 2 0:00 0.00% csh 1107
> >>>> root 1 20 0 23M 11M select 1 0:00 0.00% sshd
> >>>> 1048 root 1 39 0 23M 11M select 2 0:00
> >>>> 0.00% sshd 940 root 1 20 0 14M 1260K select 3
> >>>> 0:00 0.00% powerd 1057 dclarke 1 20 0 15M 3848K
> >>>> wait 1 0:00 0.00% su 1058 dante 1 20 0 15M
> >>>> 3988K wait 3 0:00 0.00% sh 1051 dclarke 1 20 0
> >>>> 15M 3988K wait 3 0:00 0.00% sh 1 root 1 20
> >>>> 0 13M 1228K wait 3 0:00 0.00% init 1061 dante 1
> >>>> 20 0 15M 3848K wait 1 0:00 0.00% su 13 root
> >>>> 3 -8 - 0B 144K - 3 0:00 0.00% geom 978 root
> >>>> 1 20 0 14M 2400K nanslp 3 0:00 0.00% cron
> >>>> 1110 dclarke 1 20 0 15M 4028K wait 1 0:00
> >>>> 0.00% sh 23 root 1 -16 - 0B 48K pmac_t 3
> >>>> 0:00 0.00% pmac_thermal 1037 root 1 52 0 14M
> >>>> 2808K ttyin 2 0:00 0.00% getty 1035 root 1 52
> >>>> 0 14M 2808K ttyin 0 0:00 0.00% getty 1033 root
> >>>> 1 52 0 14M 2808K ttyin 1 0:00 0.00% getty 1032
> >>>> root 1 52 0 14M 2808K ttyin 3 0:00 0.00%
> >>>> getty 968 root 1 20 0 22M 4108K select 2 0:00
> >>>> 0.00% sshd 1036 root 1 52 0 14M 2808K ttyin 3 0:00
> >>>> 0.00% getty
> >>>>
> >>>> There must be a trivial fix to all this as we had it all working
> >>>> pretty darn well some few months ago.
> >>> Disable SMP?
> >>>
> >>> Best regards
> >>> Michael
> >>>>
> >>>> --
> >>>> Dennis Clarke
> >>>> RISC-V/SPARC/PPC/ARM/CISC
> >>>> UNIX and Linux spoken
> >>>> GreyBeard and suspenders optional
> >>>> _______________________________________________
> >>>> freebsd-ppc at freebsd.org mailing list
> >>>> https://lists.freebsd.org/mailman/listinfo/freebsd-ppc
> >>>> To unsubscribe, send any mail to
> >>>> "freebsd-ppc-unsubscribe at freebsd.org"
> >>>
> >>> _______________________________________________
> >>> freebsd-ppc at freebsd.org mailing list
> >>> https://lists.freebsd.org/mailman/listinfo/freebsd-ppc
> >>> To unsubscribe, send any mail to
> >>> "freebsd-ppc-unsubscribe at freebsd.org"
> >>
> >> If it's SMP timebase sync related, the problem actually looks
> >> relatively easy to solve, at least for G4 and PowerMac11,2 G5's
> >> (PowerMac7,3 looks trickier), from examining the Linux source and
> >> the OFW device tree. The PowerMac11,2 (which the Quad is), and
> >> the G4s, use a GPIO to disable and enable the timebase, so a very
> >> similar thing can be done with the powermac platform driver as is
> >> done with the mpc85xx platform driver, which effectively is:
> >>
> >> All CPUs rendezvous in the smp_timebase_sync() function
> >> BSP disables timebase, sets the timebase sync to non-zero
> >> APs check for non-zero timebase, set their timebases to it
> >> All CPUs rendezvous at the end
> >> BSP re-enables timebase, and unleashes CPUs
> >>
> >> A couple hours of work for someone with the hardware, I'd say. I
> >> can probably provide a patch to be tested by someone in the next
> >> few days, if someone else doesn't get around to it first.
> > I would be happy to test. Need to check what kind of PowerMac I
> > have in my lab...
> >
> > Best regards
> > Michael
> >>
> >> - Justin
>
>
> Would love to test also !!
>
> I was going to, brace yourself, try to buildworld/buildkernel etc but
> the noise is just silly. So yes I did drag out a 30m CAT6 cable and
> hauled it down a hallway and stuffed it into another room to annoy
> other people.
>
> Now then, how do I get you the details you need about hardware?
>
> This is the top of the line unit that had the dual socket IBM970 cpu
> things which are dual core. There is 8G of ECC memory and dual disks
> inside. Would be great to get more memory for it but such is life.
>
> Dennis Clarke
Providing the output of 'ofwdump -ap' will suffice. The 'model'
property listed at the top will tell you what the type is. The rest
will help for figuring out what is needed. However, I know already
that since you have a Quad, it's a PowerMac11,2 so I don't need more
details.
All I gleaned so far from the Linux source was that PowerMac11,2 and
PowerMac (G4 family) use GPIOs for timebase enable, while PowerMac7,3
uses i2c twiddling, which looks more complicated. Given the age of
that hardware, I'm inclined to punt on that one, and get the
low-hanging fruit, which should satisfy most users.
- Justin
More information about the freebsd-ppc
mailing list