Re: Timekeeping hosed by factor 3, high lapic[01] interrupt rates
From: Jens Schweikhardt (schweikh_at_schweikhardt.net)
Date: 06/28/05
- Previous message: Pawel Jakub Dawidek: "VFS panic (bp 0xd6523fdc wrong b_bufobj 0 should be 0xc27d2940)."
- In reply to: John Baldwin: "Re: Timekeeping hosed by factor 3, high lapic[01] interrupt rates"
- Next in thread: John Baldwin: "Re: Timekeeping hosed by factor 3, high lapic[01] interrupt rates"
- Reply: John Baldwin: "Re: Timekeeping hosed by factor 3, high lapic[01] interrupt rates"
- Messages sorted by: [ date ] [ thread ] [ subject ] [ author ]
Date: Tue, 28 Jun 2005 23:07:49 +0200 To: John Baldwin <jhb@FreeBSD.org>
John et al,
# Forget SMP and go back to UP for now. Turn off ntpd if you are using it, then
# do something like this:
#
# # ntpdate ntp.xxxx ; sleep 10 ; ntpdate ntp.xxxx
#
# And try it both with the timecounter set to TSC and with the timecounter set
# to i8254.
Here we go, kernel with your second patch, boot with kern.smp.disabled=1.
Script started on Tue Jun 28 22:53:10 2005
# /etc/rc.d/ntpd stop
Stopping ntpd.
# sysctl kern.smp.disabled
kern.smp.disabled: 1
# sysctl -a|grep timec
kern.timecounter.stepwarnings: 0
kern.timecounter.nbinuptime: 116095
kern.timecounter.nnanouptime: 0
kern.timecounter.nmicrouptime: 670
kern.timecounter.nbintime: 902
kern.timecounter.nnanotime: 24
kern.timecounter.nmicrotime: 880
kern.timecounter.ngetbinuptime: 410
kern.timecounter.ngetnanouptime: 24
kern.timecounter.ngetmicrouptime: 2337
kern.timecounter.ngetbintime: 0
kern.timecounter.ngetnanotime: 0
kern.timecounter.ngetmicrotime: 5
kern.timecounter.nsetclock: 2
kern.timecounter.hardware: TSC
kern.timecounter.choice: TSC(800) i8254(0) dummy(-1000000)
kern.timecounter.tick: 1
kern.timecounter.smp_tsc: 0
# ntpdate 192.53.103.103; sleep 10; ntpdate 192.53.103.103
28 Jun 22:54:31 ntpdate[606]: adjust time server 192.53.103.103 offset 0.275702 sec
28 Jun 22:54:41 ntpdate[608]: adjust time server 192.53.103.103 offset 0.267708 sec
# sysctl kern.timecounter.hardware=i8254
kern.timecounter.hardware: TSC -> i8254
# ntpdate 192.53.103.103; sleep 10; ntpdate 192.53.103.103
28 Jun 22:55:16 ntpdate[621]: step time server 192.53.103.103 offset 8.265734 sec
28 Jun 22:56:16 ntpdate[623]: step time server 192.53.103.103 offset 49.488049 sec
# ntpdate 192.53.103.103; sleep 10; ntpdate 192.53.103.103
28 Jun 22:56:50 ntpdate[624]: step time server 192.53.103.103 offset 27.732229 sec
28 Jun 22:57:49 ntpdate[626]: step time server 192.53.103.103 offset 48.679758 sec
# sysctl kern.timecounter.hardware=TSC
kern.timecounter.hardware: i8254 -> TSC
# ntpdate 192.53.103.103; sleep 10; ntpdate 192.53.103.103
28 Jun 22:57:59 ntpdate[628]: step time server 192.53.103.103 offset 2.417985 sec
28 Jun 22:58:10 ntpdate[630]: adjust time server 192.53.103.103 offset -0.008257 sec
# ntpdate 192.53.103.103; sleep 10; ntpdate 192.53.103.103
28 Jun 22:58:23 ntpdate[631]: adjust time server 192.53.103.103 offset -0.005786 sec
28 Jun 22:58:33 ntpdate[633]: adjust time server 192.53.103.103 offset -0.004015 sec
#
Script done on Tue Jun 28 22:58:38 2005
Regards,
Jens
-- Jens Schweikhardt http://www.schweikhardt.net/ SIGSIG -- signature too long (core dumped) _______________________________________________ freebsd-current@freebsd.org mailing list http://lists.freebsd.org/mailman/listinfo/freebsd-current To unsubscribe, send any mail to "freebsd-current-unsubscribe@freebsd.org"
- Previous message: Pawel Jakub Dawidek: "VFS panic (bp 0xd6523fdc wrong b_bufobj 0 should be 0xc27d2940)."
- In reply to: John Baldwin: "Re: Timekeeping hosed by factor 3, high lapic[01] interrupt rates"
- Next in thread: John Baldwin: "Re: Timekeeping hosed by factor 3, high lapic[01] interrupt rates"
- Reply: John Baldwin: "Re: Timekeeping hosed by factor 3, high lapic[01] interrupt rates"
- Messages sorted by: [ date ] [ thread ] [ subject ] [ author ]
Relevant Pages
|
|