Skip site navigation (1)Skip section navigation (2)
Date:      Wed, 9 Apr 2003 15:47:28 +0200
From:      Bernd Walter <ticso@cicely9.cicely.de>
To:        Harti Brandt <brandt@fokus.fraunhofer.de>
Cc:        ticso@cicely.de
Subject:   Re: realtime problem
Message-ID:  <20030409134727.GB95434@cicely9.cicely.de>
In-Reply-To: <20030409144042.B901@beagle.fokus.fraunhofer.de>
References:  <20030409114957.GN83126@cicely9.cicely.de> <20030409144042.B901@beagle.fokus.fraunhofer.de>

next in thread | previous in thread | raw e-mail | index | archive | help
On Wed, Apr 09, 2003 at 02:45:07PM +0200, Harti Brandt wrote:
> On Wed, 9 Apr 2003, Bernd Walter wrote:
> BW>I need a realtime behavour in the (-current) kernel with 1ms
> BW>resolution and a presision of 500us.
> BW>I thought about these two ways:
> BW>- use timeout(9), but it seems that on i386 we only have a
> BW>  resolution of 10ms.
> BW>  And I don't know of what presision quality I can expect.
> BW>  Can the resolution changed to 1ms as we have on alpha?
> BW>- attach to the clock service routine.
> BW>  I asume the presision will be good enough.
> BW>  But how can I find out the resolution on a given hardware?
> BW>
> BW>What is the best way to solve the problem?
> 
> You must change HZ by putting
> 
> options	HZ=2000
> 
> or whatever you want in your config file.
> 
> You should also ensure, that you have no miibus ethernet cards in your
> system, or comment out the relevant sections in dev/mii that periodically
> call the status update stuff.
> 
> I fact I have used a HZ=10000 machine to simulate a 120000 packets/sec
> satellite link with good success (jitters are in the order of 300usecs).

That's a hopefully information.
Did you use a hardclock, timeout(9) or something else?

> If you really mean 'real-time' with bounded times for interrupts and so
> on, that will be much harder :-) See Terry's mail.

Well it's wishfull to have non failures on my requirements, but if it
does fail once it is detectable and it only costs a small amount of
money - noone will die because of it.
If I would need garantied 100% acuracy, then I would spend the money
into a microcontroller to do the job.
In fact I need it for the programming impulse on writing EPROMs and
GALs.
GALs are the devices which may need a 1ms programming impulse, but I
don't know if there are really devices on the maket which use 1ms.
EPROMS are not very sensible on the programming length.
I really hate that available burners need DOS or Windows.

-- 
B.Walter                   BWCT                http://www.bwct.de
ticso@bwct.de                                  info@bwct.de



Want to link to this message? Use this URL: <https://mail-archive.FreeBSD.org/cgi/mid.cgi?20030409134727.GB95434>