...@lists.ntp.org
> [mailto:questions-bounces+elliott.ch=verizon@lists.ntp.org] On
> Behalf Of james machado
> Sent: Friday, January 11, 2013 2:15 AM
> To: Charles Swiger
> Cc: david-tay...@blueyonder.co.uk; questions@lists.ntp.org
> Subject: Re: [ntp:questions] Loopstats jit
On 2013-01-11, james machado wrote:
>> http://www.jhauser.us/arithmetic/TestFloat.html
>> http://www.netlib.org/fp/ (see UCBTEST)
>
> i've spent the last two days trying to get the UCBTEST to compile on
> the RPi with no luck. there are some defines the ieee.c file wants
> that I just don't grok
On 2013-01-11, james machado wrote:
> i've spent the last two days trying to get the UCBTEST to compile on
> the RPi with no luck. there are some defines the ieee.c file wants
> that I just don't grok. As far as TestFloat it requires SoftFloat
> which has fallen off the interwebs. If you have
On Tue, Jan 8, 2013 at 6:01 AM, Charles Swiger wrote:
> Hi--
>
> On Jan 8, 2013, at 2:16 AM, David Taylor
> wrote:
>> Thanks, Harlan. I see that a function SQRT() is used, and that this
>> function is defined as sqrt() in ntp.h:
>>
>> #define SQRT(x) (sqrt(x))
>>
>> I recall seeing /something
On Tue, Jan 8, 2013 at 8:24 AM, John Hasler wrote:
>
> The cpu in the Pi has hardware floating point but it does not support
> all the instructions supported by the hardware floating point in newer
> ARM cpu designs. Consequently software must be compiled specifically
> for the Pi cpu or else use
David Taylor writes:
> I recall seeing /something/ about hardware and software floating point
> support in the Raspberry Pi, that some hardware/firmware/software had
> it and some not.
The cpu in the Pi has hardware floating point but it does not support
all the instructions supported by the hardw
On 08/01/2013 14:01, Charles Swiger wrote:
Hi--
On Jan 8, 2013, at 2:16 AM, David Taylor
wrote:
Thanks, Harlan. I see that a function SQRT() is used, and that this function
is defined as sqrt() in ntp.h:
#define SQRT(x) (sqrt(x))
I recall seeing /something/ about hardware and software f
Hi--
On Jan 8, 2013, at 2:16 AM, David Taylor
wrote:
> Thanks, Harlan. I see that a function SQRT() is used, and that this function
> is defined as sqrt() in ntp.h:
>
> #define SQRT(x) (sqrt(x))
>
> I recall seeing /something/ about hardware and software floating point
> support in the Ras
On 08/01/2013 05:17, Mischanko, Edward T wrote:
The question may be what is unique about the raspberry pi and the version of
Linux that you are running? I don't see this symptom on my Soekris Net4501
with FreeBSD 8.2. Can you run FreeBSD on a raspberry pi?
Regards,
Ed
Ed, I don't know abou
On 07/01/2013 22:32, Harlan Stenn wrote:
David Taylor writes:
On 14/12/2012 08:17, David Taylor wrote:
Reported as bug 2314:
http://bugs.ntp.org/show_bug.cgi?id=2314
There's been no at all progress with this bug report. ...
My focus is on bugs that are blocking the 4.2.8 release.
The
-
> bounces+edward.mischanko=arcelormittal@lists.ntp.org
> [mailto:questions-
> bounces+edward.mischanko=arcelormittal@lists.ntp.org] On
> Behalf Of Harlan Stenn
> Sent: Monday, January 07, 2013 4:32 PM
> To: david-tay...@blueyonder.co.uk
> Cc: questions@lists.ntp.org
> Subject: R
David Taylor writes:
> On 14/12/2012 08:17, David Taylor wrote:
> > Reported as bug 2314:
> >
> >http://bugs.ntp.org/show_bug.cgi?id=2314
>
> There's been no at all progress with this bug report. ...
My focus is on bugs that are blocking the 4.2.8 release.
The logged value looks like clock_
On 14/12/2012 08:17, David Taylor wrote:
Reported as bug 2314:
http://bugs.ntp.org/show_bug.cgi?id=2314
There's been no at all progress with this bug report. I don't know
either C or the NTP internal architecture well enough to even start to
help with this. I saw that others were gettin
On 24/11/2012 19:56, David Taylor wrote:
I've just started the statistics collection on my Linux/RPi NTP server,
and when plotting the jitter results I found that most of the values
were zero. I don't see that on my Windows stratum-1 systems. Is there
a limit in the calculation of the jitter va
On 27/11/2012 07:05, james machado wrote:
[]
on my RPi running as at stratum 1
# ntpq -c "rv 0 version" 127.0.0.1
version="ntpd 4.2.6p3@1.2290 Thu Oct 25 04:18:47 UTC 2012 (1)"
# uname -a
Linux pisces 3.6.1+ #1 Fri Nov 2 02:10:35 PDT 2012 armv6l GNU/Linux
# ntpq -c lpeers
remote
On Wednesday, November 28, 2012 6:54:17 AM UTC+8, unruh wrote:
>
> What kind of platform is that?
>
TP-LINK TL-WR841N (Atheros ar71xx), see
http://code.google.com/p/openwrt-stratum1
___
questions mailing list
questions@lists.ntp.org
http://lists.ntp.
On 2012-11-27, gabs wrote:
> On Sunday, November 25, 2012 3:56:28 AM UTC+8, David Taylor wrote:
>> I've just started the statistics collection on my Linux/RPi NTP server,
>> and when plotting the jitter results I found that most of the values
>> were zero. I don't see that on my Windows stratum
On 27/11/2012 16:24, gabs wrote:
[]
The displayed jitter in loopstats or the peer list can be different from the
actual jitter of the source. This case is the reverse: low actual jitter,
15 us displayed jitter.
root@OpenWrt:/tmp# tail /tmp/ntp/loops
56257 76888.554 -0.00080 6.553 0.15259
On Sunday, November 25, 2012 3:56:28 AM UTC+8, David Taylor wrote:
> I've just started the statistics collection on my Linux/RPi NTP server,
> and when plotting the jitter results I found that most of the values
> were zero. I don't see that on my Windows stratum-1 systems. Is there
> a limit
David Taylor wrote:
> BTW: I would like to get step-by-step instructions for recompiling the
> kernel with the gpio-pps added, as I'm using someone else's kernel and I
> may need to make my own when upgrading in the future.
I did it with
http://elinux.org/RPi_Kernel_Compilation
After zcat /pr
On 26/11/2012 21:27, Dave Morgan wrote:
[]
My Pi ntp server ... syncing to other ntp pool servers only
(not stratum 1 yet)
56257 943.692 0.000152844 -4.041 0.000616901 0.028755 10
56257 2672.693 0.000354418 -4.038 0.000581443 0.026910 10
56257 3558.700 -0.000495198 -4.040 0.000621327 0.025178 10
On 27/11/2012 07:05, james machado wrote:
[]
on my RPi running as at stratum 1
[]
i checked my loopstats for the last 47,000 odd lines of loopstats I
have had 7 lines where the jitter has not been zero.
james
Thanks, James! Good to know I am not alone!
BTW: I would like to get step-by-step
On Mon, Nov 26, 2012 at 1:27 PM, Dave Morgan wrote:
> Dave Hart wrote:
>> I'd appreciate others taking a look at their loopstats on Linux
>> systems and especially non-x86 Linux to see if 0.0 shows up in
>> the jitter (fifth column). I think we need more information to
>> understand the p
Dave Hart wrote:
> I'd appreciate others taking a look at their loopstats on Linux
> systems and especially non-x86 Linux to see if 0.0 shows up in
> the jitter (fifth column). I think we need more information to
> understand the problem.
>
My Pi ntp server ... syncing to other ntp pool
On 25/11/2012 21:37, Dave Hart wrote:
[]
Jitter is a measure of the variability of the phase offset across up
to eight entries in the clock filter register of the selected peer,
the "best" sample of which ends up as the third column of loopstats.
For a LAN peer best is lowest delay. For PPS, it'
On Sun, Nov 25, 2012 at 06:25 UTC, David Taylor wrote:
> On 24/11/2012 20:26, Dave Hart wrote:
>>
>> On Sat, Nov 24, 2012 at 7:56 PM, David Taylor
>> wrote:
[...]
>>> I really can't imagine that such a low-powered server is /that/ good -
>>> better than a nanosecond.
>>
>> What version of ntpd is
On 24/11/2012 20:26, Dave Hart wrote:
On Sat, Nov 24, 2012 at 7:56 PM, David Taylor
wrote:
I've just started the statistics collection on my Linux/RPi NTP server, and
when plotting the jitter results I found that most of the values were zero.
I don't see that on my Windows stratum-1 systems. I
On Sat, Nov 24, 2012 at 7:56 PM, David Taylor
wrote:
> I've just started the statistics collection on my Linux/RPi NTP server, and
> when plotting the jitter results I found that most of the values were zero.
> I don't see that on my Windows stratum-1 systems. Is there a limit in the
> calculatio
I've just started the statistics collection on my Linux/RPi NTP server,
and when plotting the jitter results I found that most of the values
were zero. I don't see that on my Windows stratum-1 systems. Is there
a limit in the calculation of the jitter value recorded (to 9 decimal
places) in t
29 matches
Mail list logo