Messages in this thread | | | Date | Wed, 02 Sep 1998 01:35:28 -0500 | From | Manoj Apte <> | Subject | 2us Interrupt latency's for Linux 2.0.xx |
| |
Hello,
I was doing some test on interrupt latency (time from raising an interrupt to reading timestamp in a handler). I created my own fast handler registered at IRQ32 ( interrupt is generated by the APIC timer on a Ppro 200) that gives me a latency of approx 2300 nanoseconds
However, approx every 30 seconds this latency shoots up to 15000ns or so and shows 4 instances of that and then goes back to 2000ns.. I was wondering if anyone knows what this could be due to. I applied the RT-Linux patch, and I still see it (rt-linux should disable all the cli()'s in the kernel source) so.. i am quite perplexed as to where this is coming from. The most interesting thing it is perfectly periodic.
If anyone wants to see a plot (over 500secs).. I could send it to you with an FFT :)
Would greatly appreciate any hints :)
Thanks Manoj Apte
===========================================================================
MANOJ APTE Computer Science email: manoj@erc.msstate.edu phone: (601)-325-2476 (off) ENGINEERING RESEARCH CENTER. (601)-323-8160 (res) Mississippi State University.
- To unsubscribe from this list: send the line "unsubscribe linux-kernel" in the body of a message to majordomo@vger.rutgers.edu Please read the FAQ at http://www.altern.org/andrebalsa/doc/lkml-faq.html
| |