Re: [rtl] 20 microsecond jitter using 9G with an IRQ driven task...

[Donald Gaffney <gaffney@salus.med.uvm.edu>]

On Mon, 9 Nov 1998 yodaiken@chelm.cs.nmt.edu wrote:

> > The downside is that there is a very large amount of jitter, about
> > 20 microseconds on either side of the scheduled time. This only
> > occurs around every 5-15 seconds, but it does happen. (If folks
> > want to look at the traces then let me know and I'll put them up,
> > but they don't look different than the periodic task in terms of jitter).
> 
> What's the mother board, chipset, and devices?
> Are you sure the delay is not in the device timer?
> 

Hardware:

	Toshiba Equium 6200M (from a closeout sale at insight.com)
	 - Intel Dual PPro 200 MHz (PR440FX) motherboard
	 - 64 MB ECC RAM
	 - Adaptec 78XX SCSI controller with Quantum 4.5 GB disk
	 - IDE CDROM
	 - ATI 2 MB Rage II+ video
	 - Netgear FA310TX (tulip) fast ethernet

	The box is headless, it is currently accessed over the
	network for control purposes.

I can't answer whether the delay is in the device timer. I suppose I
could test this by triggering interrupts externally - that is, I could
pump a square wave into the card from an external pin and check to see
whether the jitter changes. This would nail down whether it is originating
from the 82C53 on the board itself or if it is something in the interrupt
handling.

I was just wondering if the jitter was the best case, as far as what other
people have been seeing.

I'll be sure to report back any progress I make.

-Don

--- [rtl] ---
To unsubscribe:
echo "unsubscribe rtl" | mail majordomo@rtlinux.cs.nmt.edu OR
echo "unsubscribe rtl <Your_email>" | mail majordomo@rtlinux.cs.nmt.edu
----
For more information on Real-Time Linux see:
http://www.rtlinux.org/~rtlinux/