Re: [ntp:questions] Seeing large jitter and delay in recent ntpd and recent Solaris

2011-11-09 Thread Dave Hart
On Wed, Nov 9, 2011 at 23:44, Chuck Swiger wrote: > On Nov 9, 2011, at 2:47 PM, Chris Albertson wrote: >> That will do little good and maybe some harm.  ntpd reads time stamped >> input.  Even if this sits in a buffer unprocessed it's OK because the >> critical work, the stamping is done inside an

Re: [ntp:questions] Seeing large jitter and delay in recent ntpd and recent Solaris

2011-11-09 Thread Chuck Swiger
On Nov 9, 2011, at 2:47 PM, Chris Albertson wrote: >> We have other real time processing occuring on the system and are sensitive >> to offset errors, so we want ntpd to run at the highest real time priority. > > That will do little good and maybe some harm. ntpd reads time stamped > input. Eve

Re: [ntp:questions] Seeing large jitter and delay in recent ntpd and recent Solaris

2011-11-09 Thread Chris Albertson
On Wed, Nov 9, 2011 at 1:28 PM, Fran wrote: > Thanks Chuck, > > We have other real time processing occuring on the system and are sensitive > to offset errors, so we want ntpd to run at the highest real time priority. That will do little good and maybe some harm. ntpd reads time stamped input.

Re: [ntp:questions] Seeing large jitter and delay in recent ntpd and recent Solaris

2011-11-09 Thread Fran
Thanks Chuck, We have other real time processing occuring on the system and are sensitive to offset errors, so we want ntpd to run at the highest real time priority. Irregardless of the priority levels, don't you think that if SIGPOLL is sent to the ntpd process then select() called in that SIG

Re: [ntp:questions] Seeing large jitter and delay in recent ntpd and recent Solaris

2011-11-08 Thread Dave Hart
On Tue, Nov 8, 2011 at 23:26, Chuck Swiger wrote: > If you've set ntpd's priority above 100 via realtime scheduling class, > then it has priority over the system kernel threads which service > network interrupts.  select() might be legitimately returning zero > because ntpd is running before the N

Re: [ntp:questions] Seeing large jitter and delay in recent ntpd and recent Solaris

2011-11-08 Thread Chuck Swiger
Hi-- On Nov 8, 2011, at 12:29 PM, Fran wrote: > My ‘high performance’ configuration is running ntpd bound to processor 0 on > an SMP, and at highest priority. My poll rate is 16 sec. And I’m running ntpq > locally so ntpq is communicating with ntpd over the loopback interface. Most > of these c

[ntp:questions] Seeing large jitter and delay in recent ntpd and recent Solaris

2011-11-08 Thread Fran
When running recent versions of ntpd and with a recent Solaris patch, I see large delay and jitter in ntpq based output, and in the stats files. I am running in a high performance configuration where I'm trying to minimize offset. I think it is a Solaris problem in asynchronous i/o processing, w