Date: Tue, 25 Jul 2006 07:54:54 -0400 From: "Michael Scheidell" <scheidell@secnap.net> To: "Peter Jeremy" <peterjeremy@optushome.com.au> Cc: freebsd-hackers@freebsd.org Subject: RE: FBSD 5.5 and software timers Message-ID: <B3BCAF4246A8A84983A80DAB50FE72424C6970@secnap2.secnap.com>
next in thread | raw e-mail | index | archive | help
> -----Original Message----- > From: Peter Jeremy [mailto:peterjeremy@optushome.com.au]=20 > Sent: Tuesday, July 25, 2006 4:00 AM > To: Michael Scheidell > Cc: freebsd-hackers@freebsd.org > Subject: Re: FBSD 5.5 and software timers >=20 >=20 > Basically, when you ask for a 200msec delay, the kernel=20 > sleeps until an absolute time. It looks like the handling of=20 > absolute time sleeps across time steps was changed. =20 > Unfortunately, both approaches are equally valid in different=20 > circumstances. I agree >=20 > >It fails within 1 second of getting these types of log=20 > entries: Jul 23=20 > >15:03:42 audit18 ntpd[473]: time reset -2.497234 s Jul 23 16:03:56=20 > >audit18 ntpd[473]: time reset +1.532401 s >=20 > Rather than focussing on the changed sleep handling, I=20 > suggest you concentrate on fixing your clock: Your system=20 > clock should not be stepping. >=20 Except: 20 different machines. Some IBM 300's with 2.0Ghz P4,s, 305 and 306's with 2.8P4, some DELL 750's and 850's with 2.8p4 with HTT enabled. Even the 5.4 machines shows the bifurcating -1, +2, -2, +1 time resets, but timers work more like I want them to. > I presume the servers are all stable (ie not stepping) and=20 > have a reasonably low delay. If so, I suspect your ntpd PLL=20 > has locked up. I've seen problems with some versions of ntpd=20 20 different machines?
Want to link to this message? Use this URL: <https://mail-archive.FreeBSD.org/cgi/mid.cgi?B3BCAF4246A8A84983A80DAB50FE72424C6970>