On 10/7/08, James Mills [EMAIL PROTECTED] wrote:
I shall do some latency benchmarks ok :)
Out of curiosity I modifed my bench marking tool
for my event/component library (pymills) and here
are the results:
~/pymills/examples/event
$ ./bench.py -m latency -t 10
Setting up latency Test...
James Mills wrote:
$ ./bench.py -m latency -t 10 -f 100
Setting up latency Test...
Latency: 1.52 ms
Latency: 0.78 ms
Latency: 0.76 ms
Latency: 0.76 ms
Latency: 0.77 ms
Latency: 0.77 ms
Latency: 0.76 ms
Latency: 0.76 ms
Latency: 0.76 ms
Latency: 0.77 ms
Interesting. Can you do something to
On 7 Ott, 01:25, Blubaugh, David A. [EMAIL PROTECTED] wrote:
To All,
I have done some additional research into the possibility of utilizing
Python for hard real time development. I have seen on various websites
where this has been discussed before on the internet. However, I was
wondering
Am 07.10.2008 um 11:44 schrieb Diez B. Roggisch:
Kurt Mueller wrote:
David,
As others mentioned before, python is not the right tool for HARD
REAL TIME.
But: Maybe you can isolate the part of your application that needs
HARD REAL TIME.
Then implement this part in an approriate Environment
I've done this using RTAI + ctypes. Of course the hard realtime
tasks are
written in C - but only the absolutely minimal core.
Works like a charm.
(Btw, what is this application like)
It's for a robot with 8 motors, with a industrial PIII-based PC on board,
running RTAI Linux 2.6. The core
Kurt Mueller wrote:
David,
Am 07.10.2008 um 01:25 schrieb Blubaugh, David A.:
I have done some additional research into the possibility of utilizing
Python for hard real time development. I have seen on various
websites
where this has been discussed before on the internet. However, I
David,
Am 07.10.2008 um 01:25 schrieb Blubaugh, David A.:
I have done some additional research into the possibility of utilizing
Python for hard real time development. I have seen on various
websites
where this has been discussed before on the internet. However, I was
wondering as to how
Blubaugh, David A. dblubelcan.com wrote:
I have done some additional research into the possibility of utilizing
Python for hard real time development. I have seen on various websites
where this has been discussed before on the internet. However, I was
wondering as to how successful anyone
On Tue, Oct 7, 2008 at 6:42 PM, [EMAIL PROTECTED] wrote:
AFAIK, the requirement for hard real time, is that response time have
to be predictable, rather than
generally 'fast'.
Very high level languages like python use many features which are by
their nature unpredictable or
difficult to
On Tue, Oct 7, 2008 at 7:27 PM, Kurt Mueller [EMAIL PROTECTED] wrote:
To be more helpful, we should know what you mean by HARD REAL TIME.
Do you mean:
- Handle at least 70 interrupt per second(SPEED)
- If one fails, this is catastrophic for the application (HARD)
- Deliver
Am 08.10.2008 um 06:59 schrieb Hendrik van Rooyen:
Blubaugh, David A. dblubelcan.com wrote:
I have done some additional research into the possibility of
utilizing
Python for hard real time development. I have seen on various
websites
where this has been discussed before on the
On Tue, Oct 7, 2008 at 9:25 AM, Blubaugh, David A. [EMAIL PROTECTED] wrote:
close to real time constraints? For example is it possible to develop a
python program that can address an interrupt or execute an operation
within 70 Hz or less?? Are there any additional considerations that I
should
On Tue, 7 Oct 2008 09:32:37 +1000, James Mills [EMAIL PROTECTED] wrote:
On Tue, Oct 7, 2008 at 9:25 AM, Blubaugh, David A. [EMAIL PROTECTED] wrote:
close to real time constraints? For example is it possible to develop a
python program that can address an interrupt or execute an operation
within
On Tue, Oct 7, 2008 at 11:48 AM, Jean-Paul Calderone [EMAIL PROTECTED] wrote:
Indeed, this looks wrong - or at least inconclusive. The benchmark
above demonstrates throughput, not minimum (or maximum, or average,
or any other statistic) response latency, which is what the OP was
really asking
On Tue, 7 Oct 2008 12:10:44 +1000, James Mills [EMAIL PROTECTED] wrote:
On Tue, Oct 7, 2008 at 11:48 AM, Jean-Paul Calderone [EMAIL PROTECTED] wrote:
Indeed, this looks wrong - or at least inconclusive. The benchmark
above demonstrates throughput, not minimum (or maximum, or average,
or any
15 matches
Mail list logo
