Skip site navigation (1)Skip section navigation (2)
Date:      Tue, 16 Mar 2004 22:04:32 -0500
From:      Don Bowman <don@sandvine.com>
To:        "'current@freebsd.org'" <current@freebsd.org>
Subject:   equivalent of kern.timecounter.method?
Message-ID:  <FE045D4D9F7AED4CBFF1B3B813C85337045D85C7@mail.sandvine.com>

next in thread | raw e-mail | index | archive | help

in 4.x there is a sysctl kern.timecounter.method.
If this isn't set to '1', the system doesn't work
correctly (at least with SMP), you get microuptime()
backwards, and problems with processes hanging
while time catches up, etc.

What is the equivalent of this sysctl in 5.x?

kern.timecounter.nbinuptime: 6810682
kern.timecounter.nnanouptime: 4
kern.timecounter.nmicrouptime: 2218
kern.timecounter.nbintime: 7091
kern.timecounter.nnanotime: 172
kern.timecounter.nmicrotime: 6919
kern.timecounter.ngetbinuptime: 0
kern.timecounter.ngetnanouptime: 490
kern.timecounter.ngetmicrouptime: 30909
kern.timecounter.ngetbintime: 0
kern.timecounter.ngetnanotime: 0
kern.timecounter.ngetmicrotime: 187117
kern.timecounter.nsetclock: 4
kern.timecounter.hardware: ACPI-fast
kern.timecounter.choice: TSC(-100) ACPI-fast(1000) i8254(0) dummy(-1000000)
kern.timecounter.tick: 1
kern.timecounter.smp_tsc: 0

is what i have.

I'm having a problem with this machine sometimes hanging...
sometimes for 5-10s, sometimes permanently (?). When hung,
everything (serial console, etc) is locked. This includes
the key-sequence to drop to db on the serial.

I'm not sure the time and the hang are related, but there's
a suspicious ntpd message just before the hang,
kernel time discipline status [2041, 2040, etc]

5.2.1-RELEASE-p1 (RELENG_5_2) is what its running, with the (absolutely
critical ufs_vnops.c fix of 1.235).

The only thing the machine runs is postgresql.

Suggestions on how to debug this lockup?



Want to link to this message? Use this URL: <https://mail-archive.FreeBSD.org/cgi/mid.cgi?FE045D4D9F7AED4CBFF1B3B813C85337045D85C7>