Re: [time-nuts] Comparing the BeagleBone Black & Raspberry Pi as NTP servers
The other key key key item is make sure you hand build yourself a 3.14 or .16 kernel. NS On Mon, Mar 23, 2015 at 2:30 AM, Attila Kinali wrote: > On Sun, 22 Mar 2015 16:41:56 -0400 > Paul wrote: > > > 1) Did you start out using the attached patch antenna? D Drown implies > > successfully using the patch on the Adafruit until it was soldered in > > place. He fixed that by switching to an external antenna. I've never > had > > any success with attached patch antennas but my receivers are inside. > > > The BBB is known to have a bad EMI behaviour. You should not put > any sensitive RF components near it, without proper shielding. > > Attila kinali > -- > It is upon moral qualities that a society is ultimately founded. All > the prosperity and technological sophistication in the world is of no > use without that foundation. > -- Miss Matheson, The Diamond Age, Neil Stephenson > ___ > time-nuts mailing list -- time-nuts@febo.com > To unsubscribe, go to > https://www.febo.com/cgi-bin/mailman/listinfo/time-nuts > and follow the instructions there. > ___ time-nuts mailing list -- time-nuts@febo.com To unsubscribe, go to https://www.febo.com/cgi-bin/mailman/listinfo/time-nuts and follow the instructions there.
Re: [time-nuts] Comparing the BeagleBone Black & Raspberry Pi as NTP servers
On Sun, 22 Mar 2015 16:41:56 -0400 Paul wrote: > 1) Did you start out using the attached patch antenna? D Drown implies > successfully using the patch on the Adafruit until it was soldered in > place. He fixed that by switching to an external antenna. I've never had > any success with attached patch antennas but my receivers are inside. The BBB is known to have a bad EMI behaviour. You should not put any sensitive RF components near it, without proper shielding. Attila kinali -- It is upon moral qualities that a society is ultimately founded. All the prosperity and technological sophistication in the world is of no use without that foundation. -- Miss Matheson, The Diamond Age, Neil Stephenson ___ time-nuts mailing list -- time-nuts@febo.com To unsubscribe, go to https://www.febo.com/cgi-bin/mailman/listinfo/time-nuts and follow the instructions there.
Re: [time-nuts] Comparing the BeagleBone Black & Raspberry Pi as NTP servers
On Sat, Mar 21, 2015 at 12:23 PM, David J Taylor <
david-tay...@blueyonder.co.uk> wrote:
> I've just put up my first draft of a comparison of these two popular
> devices as NTP servers:
>
> Comments welcomed - I know it's an imperfect test!
> ...
Perhaps there are some services or background tasks I can disable to reduce
> the CPU steady load from its present 16% average level?
>
There's not enough background to offer good advice but here's some "okay"
points:
1) Did you start out using the attached patch antenna? D Drown implies
successfully using the patch on the Adafruit until it was soldered in
place. He fixed that by switching to an external antenna. I've never had
any success with attached patch antennas but my receivers are inside.
2) I've attached the output of pstree for my NTP BBB. That machine is
typically 97% idle (load average 0 to .005) unless I run the PPS blinker
which is written in Python. It is running the heartbeat blinker that
sleeps almost all the time.
3) I run R. C. Nelson's builds of Ubuntu (Server) which do start Apache by
default but it's easy to turn off.
4) I don't understand the section labelled "The view from afar". You say
you're measuring two machines but there are many lines of output. Perhaps
you could discard the data that's not related to the machines under test.
Compared to my primary clock via peerstats:
BBB mean offset 7.8e-6, mean jitter 7.0e-6
RPi mean offset 7.1e-5, mean jitter 5.3e-5
init-+-acpid
|-avahi-daemon---avahi-daemon
|-cron
|-dbus-daemon
|-dhclient
|-7*[getty]
|-hb.py
|-ntpd-428p1
|-rpc.idmapd
|-rpc.statd
|-rpcbind
|-rsyslogd---3*[{rsyslogd}]
|-sshd-+-sshd---bash
| `-sshd---bash---pstree
|-systemd-logind
|-systemd-udevd---6*[systemd-udevd]
|-udhcpd
|-upstart-file-br
|-upstart-socket-
`-upstart-udev-br
___
time-nuts mailing list -- time-nuts@febo.com
To unsubscribe, go to https://www.febo.com/cgi-bin/mailman/listinfo/time-nuts
and follow the instructions there.
Re: [time-nuts] Comparing the BeagleBone Black & Raspberry Pi as NTP servers
On Sun, 22 Mar 2015 14:14:01 - "David J Taylor" wrote: > Yes, my posting was at least in part for help with resolving the much higher > CPU load seen on a default BBB installation than on an RPi setup. If you > could provide a list of services and cron jobs to be disabled, and a brief > guide to doing so (as I'm a beginner with Linux) that would be appreciated. Sorry, I cannot. I don't have a BBB to test the image and tell you what it runs. But i can at least guide you trough the steps to figure out what's going on. If you run `ps aux` you will get a list of what processes are active. This is the low level view. The high level view is aquired using `systemctl list-units` You can stop the units you don't need using `systemctl stop ` You can find more information on how to deal with systemd on https://wiki.archlinux.org/index.php/systemd Do not get confused by this being an Arch Linux wiki, it applies to Debian as well. BTW: As Graham wrote Debian is in kind of a transition, though nobody has really decided where it will be going (there are too many people who opose the systemd switch). But unlike what he wrote, there is no mix of init systems. It's either systemd, or it isn't. You cannot have both at the same time. The default image of BBB runs systemd. The second place where to look at are your cron jobs. They can be found in: /etc/crontab /etc/cron.d /etc/cron.hourly /var/spool/cron/crontabs/ The first one (/etc/crontab) is the system wide, old school table that contains all jobs. On a regular debian system, you should have only 4 entries, the monthly, weekly, daily and hourly job scripts. If you have only these, don't touch it. They are necessary. The second one (/etc/cron.d/) is a directory that contains files of the same format as /etc/crontab for specific installed packages. Edit them as you whish (but know what you are doing ;-). The third (/etc/cron.hourly) contains shell scripts that are run once per hour. They are most likely necessary, but might not be. If you don't want/need them, it's best to uninstall the package that they came with. The last one is one (/var/spool/cron/crontabs/) is one you shouldn't touch by hand. These are the files stored by the crontab command, for the respective user. If you need to disable/edit those, use the crontab command. BTW: i reccomend you getting a book on linux. Dealing with embedded devices you will need a good understanding of the inner workings of linux to effectively deal with them. I have heard good things about "linux for dummies" but i have never read it myself. > I had looked at [1] but I'm not using his special timer setup, just GPIO > pins. Unfortunately he doesn't quote any of the usual NTP parameters with > which to compare. Yes. But it gives an idea how stable the oscillator is. You have large deviations of over 10us, which contradict the number Dan Drown is getting. HTH Attila Kinali -- < _av500_> phd is easy < _av500_> getting dsl is hard ___ time-nuts mailing list -- time-nuts@febo.com To unsubscribe, go to https://www.febo.com/cgi-bin/mailman/listinfo/time-nuts and follow the instructions there.
Re: [time-nuts] Comparing the BeagleBone Black & Raspberry Pi as NTP servers
I'm surprised you did not kill off those other tasks. Looks like you might be running a web server, building an index or something. Were the /etc/ntp.conf files the same on Pi and BBB? Test is not valid unless both computers are running the same things. On Sat, Mar 21, 2015 at 12:38 PM, Graham / KE9H wrote: > David: > On the BBB, were you running the fully loaded release, or the minimum > "console" version of the OS? > Which specific version of the OS? > > Thanks, > --- Graham > > == > > > On Sat, Mar 21, 2015 at 11:23 AM, David J Taylor < > david-tay...@blueyonder.co.uk> wrote: > > > Folks, > > > > I've just put up my first draft of a comparison of these two popular > > devices as NTP servers: > > > > http://www.satsignal.eu/ntp/BBB-vs-RPi.html > > > > Comments welcomed - I know it's an imperfect test! > > > > Cheers, > > David > > -- > > SatSignal Software - Quality software written to your requirements > > Web: http://www.satsignal.eu > > Email: david-tay...@blueyonder.co.uk > > ___ > > time-nuts mailing list -- time-nuts@febo.com > > To unsubscribe, go to https://www.febo.com/cgi-bin/ > > mailman/listinfo/time-nuts > > and follow the instructions there. > > > ___ > time-nuts mailing list -- time-nuts@febo.com > To unsubscribe, go to > https://www.febo.com/cgi-bin/mailman/listinfo/time-nuts > and follow the instructions there. > -- Chris Albertson Redondo Beach, California ___ time-nuts mailing list -- time-nuts@febo.com To unsubscribe, go to https://www.febo.com/cgi-bin/mailman/listinfo/time-nuts and follow the instructions there.
Re: [time-nuts] Comparing the BeagleBone Black & Raspberry Pi as NTP servers
One of those services is likely the full blown web server that runs on the BBB to allow you to view the help pages. -Chuck Harris Attila Kinali wrote: On Sat, 21 Mar 2015 16:23:30 - "David J Taylor" wrote: I've just put up my first draft of a comparison of these two popular devices as NTP servers: http://www.satsignal.eu/ntp/BBB-vs-RPi.html Comments welcomed - I know it's an imperfect test! Something is wrong here. I would expect the BBB to perform at least as well as the rpi (after all, the BBB has an ethernet MAC with IEEE1588 support, while the rpi is basically a glorified USB controller with attached graphics card). You are most likely running services on the BBB (network services, local services, cron jobs,...) that cause the high, and spikey cpu load, which in turn destroys your ntp performance. Also, compare your results to [1], where Dan Drown uses the capture/compare unit of the AM3359 to timestamp the PPS and use this for ntp. In [2] he tries to measure the temperature dependence of the BBB oscillator (not be best way, but...). Attila Kinali [1] http://blog.dan.drown.org/beaglebone-black-timer-capture-driver/ [2] http://blog.dan.drown.org/tcxo-beaglebone-black/ ___ time-nuts mailing list -- time-nuts@febo.com To unsubscribe, go to https://www.febo.com/cgi-bin/mailman/listinfo/time-nuts and follow the instructions there.
Re: [time-nuts] Comparing the BeagleBone Black & Raspberry Pi as NTP servers
From: Attila Kinali Something is wrong here. I would expect the BBB to perform at least as well as the rpi (after all, the BBB has an ethernet MAC with IEEE1588 support, while the rpi is basically a glorified USB controller with attached graphics card). You are most likely running services on the BBB (network services, local services, cron jobs,...) that cause the high, and spikey cpu load, which in turn destroys your ntp performance. Also, compare your results to [1], where Dan Drown uses the capture/compare unit of the AM3359 to timestamp the PPS and use this for ntp. In [2] he tries to measure the temperature dependence of the BBB oscillator (not be best way, but...). Attila Kinali [1] http://blog.dan.drown.org/beaglebone-black-timer-capture-driver/ [2] http://blog.dan.drown.org/tcxo-beaglebone-black/ Attila, Yes, my posting was at least in part for help with resolving the much higher CPU load seen on a default BBB installation than on an RPi setup. If you could provide a list of services and cron jobs to be disabled, and a brief guide to doing so (as I'm a beginner with Linux) that would be appreciated. I had looked at [1] but I'm not using his special timer setup, just GPIO pins. Unfortunately he doesn't quote any of the usual NTP parameters with which to compare. I'm also measuring thing differently, in that I'm measuring from a remote rather than a local system, as that is what would happen when using the device as an NTP server. Thanks, David -- SatSignal Software - Quality software written to your requirements Web: http://www.satsignal.eu Email: david-tay...@blueyonder.co.uk ___ time-nuts mailing list -- time-nuts@febo.com To unsubscribe, go to https://www.febo.com/cgi-bin/mailman/listinfo/time-nuts and follow the instructions there.
Re: [time-nuts] Comparing the BeagleBone Black & Raspberry Pi as NTP servers
On Sat, 21 Mar 2015 16:23:30 - "David J Taylor" wrote: > I've just put up my first draft of a comparison of these two popular devices > as NTP servers: > > http://www.satsignal.eu/ntp/BBB-vs-RPi.html > > Comments welcomed - I know it's an imperfect test! Something is wrong here. I would expect the BBB to perform at least as well as the rpi (after all, the BBB has an ethernet MAC with IEEE1588 support, while the rpi is basically a glorified USB controller with attached graphics card). You are most likely running services on the BBB (network services, local services, cron jobs,...) that cause the high, and spikey cpu load, which in turn destroys your ntp performance. Also, compare your results to [1], where Dan Drown uses the capture/compare unit of the AM3359 to timestamp the PPS and use this for ntp. In [2] he tries to measure the temperature dependence of the BBB oscillator (not be best way, but...). Attila Kinali [1] http://blog.dan.drown.org/beaglebone-black-timer-capture-driver/ [2] http://blog.dan.drown.org/tcxo-beaglebone-black/ -- < _av500_> phd is easy < _av500_> getting dsl is hard ___ time-nuts mailing list -- time-nuts@febo.com To unsubscribe, go to https://www.febo.com/cgi-bin/mailman/listinfo/time-nuts and follow the instructions there.
Re: [time-nuts] Comparing the BeagleBone Black & Raspberry Pi as NTP servers
David: On the BBB, were you running the fully loaded release, or the minimum "console" version of the OS? Which specific version of the OS? Thanks, --- Graham == On Sat, Mar 21, 2015 at 11:23 AM, David J Taylor < david-tay...@blueyonder.co.uk> wrote: > Folks, > > I've just put up my first draft of a comparison of these two popular > devices as NTP servers: > > http://www.satsignal.eu/ntp/BBB-vs-RPi.html > > Comments welcomed - I know it's an imperfect test! > > Cheers, > David > -- > SatSignal Software - Quality software written to your requirements > Web: http://www.satsignal.eu > Email: david-tay...@blueyonder.co.uk > ___ > time-nuts mailing list -- time-nuts@febo.com > To unsubscribe, go to https://www.febo.com/cgi-bin/ > mailman/listinfo/time-nuts > and follow the instructions there. > ___ time-nuts mailing list -- time-nuts@febo.com To unsubscribe, go to https://www.febo.com/cgi-bin/mailman/listinfo/time-nuts and follow the instructions there.
