[LinuxPPS] Re: strange readings...

[James Boddington]

Martin wrote:
> 
> Maybe it is the switch to 2.6.21...
> 
> I know almost nothing about kernel internals, but I just
> read somewhere that:
> 
> "As of Linux kernel version 2.6.21, the kernel no longer has
> a fixed 1000Hz timer tick."
> 
> Maybe this has implications for ntp? Anyone have any thoughts?
> 

These my HZ settings. I am trying NO_HZ using the master branch from linuxpps.

CONFIG_NO_HZ=y
CONFIG_HZ_100=y
# CONFIG_HZ_250 is not set
# CONFIG_HZ_300 is not set
# CONFIG_HZ_1000 is not set
CONFIG_HZ=100

I am happy enough with results.

http://aiken.dnsalias.org/cgi-bin/ntp has offset and drift graphs for my ntp 
server and 2 of the client machines. The bad bits in the graphs for sunday and 
monday are because I changed from freebsd back to linux for ntp and it took a 
couple of days before I was happy with it.

2.6.21 still can not follow the 1pps from the garmin as well as 2.6.17 and 
earlier or freebsd can but it is still doing better than 2.6.18 - 2.6.20.

I use the SHM driver as the preferred peer. I read 16 offsets, drop the 
outliers and average the rest then use the shm driver to feed the time to ntp. 
My hardware has a nasty habit of generating large offsets. Had a 100ms and a 
129ms offset last night on the pps. The worst has been 1.3 seconds. This 
happens under both linux and freebsd.

The reason for minpoll 4 maxpoll 4 for pebbles is ntp makes a useful 
thermometer. http://aiken.dnsalias.org/cgi-bin/ambient

-- 
    James