On Fri, 10 Aug 2012 08:12:19 +0100, Dave Caroline wrote:
> I had a look at the source of the comp that latency-test uses
>
> and I feel it is buggy
>
> It measures the difference in time delay one tick to the next
> not actual jitter from the system time
>
> __s64 now = rtapi_get_time();
> 18 __s
I had a look at the source of the comp that latency-test uses
and I feel it is buggy
It measures the difference in time delay one tick to the next
not actual jitter from the system time
__s64 now = rtapi_get_time();
18 __s64 del = (now - last); //only check period of last tick
19 out = del;
On Thu, 2012-08-09 at 13:06 -0700, Peter C. Wallace wrote:
> On Thu, 9 Aug 2012, Andrew wrote:
>
> > Date: Thu, 9 Aug 2012 22:56:36 +0300
> > From: Andrew
> > Reply-To: EMC developers
> > To: EMC developers
> > Subject: Re: [Emc-developers] Latency a
On Thu, 9 Aug 2012, Andrew wrote:
> Date: Thu, 9 Aug 2012 22:56:36 +0300
> From: Andrew
> Reply-To: EMC developers
> To: EMC developers
> Subject: Re: [Emc-developers] Latency and latency
>
> 2012/8/9 Peter C. Wallace
>
>>>> It gets
>>>> notic
2012/8/9 Peter C. Wallace
>
> > I do not know why the latency
> > test does not "see" this.
> >
>
Latency test isn't foolproof. I have never been motivated enough to figure
out why, but I have seen many systems that will pass the latency test with
flying colors even under stress and then get a r
2012/8/9 Peter C. Wallace
> >> It gets
> >> noticable worse when the screen is re-drawn. I do not know why the
> latency
> >> test does not "see" this.
> >>
> >
> > Have you tried it with AXIS only?
> > I also noticed strange RT errors with D525MW but did not know the reason.
>
>
> This was with
On Thu, 9 Aug 2012, Andrew wrote:
> Date: Thu, 9 Aug 2012 21:45:23 +0300
> From: Andrew
> Reply-To: EMC developers
> To: EMC developers
> Subject: Re: [Emc-developers] Latency and latency
>
> 2012/8/9 Peter C. Wallace
>
>> It gets
>> noticable worse w
2012/8/9 Peter C. Wallace
> It gets
> noticable worse when the screen is re-drawn. I do not know why the latency
> test does not "see" this.
>
Have you tried it with AXIS only?
I also noticed strange RT errors with D525MW but did not know the reason.
Andrew
2012/8/9 Peter C. Wallace :
>
> While testing our maximum SSerial update rates, (linuxCNC 2.5.1 Ubuntu 10.4) I
> noticed something somewhat interesting/disturbing about latency test on the
> servo thread on my Atom 330 based motherboard (Jetway). After disabling
> hyperthreading in the BIOS and add
Peter C. Wallace wrote:
> To check what was going on I toggled an I/O bit at the servo thread rate and
> looked at it on the oscilloscope, and the latency on the servo thread is much
> worse than 6 usec, occasionally getting above 100 usec! . It gets
> noticable worse when the screen is re-drawn
While testing our maximum SSerial update rates, (linuxCNC 2.5.1 Ubuntu 10.4) I
noticed something somewhat interesting/disturbing about latency test on the
servo thread on my Atom 330 based motherboard (Jetway). After disabling
hyperthreading in the BIOS and adding the isolcpus=1 line to grub.cf
11 matches
Mail list logo
