[ntp:questions] Re: is there a way to "lock" the drift frequency

Hal Murray hmurray at suespammers.org
Wed Nov 19 02:41:41 UTC 2003


>Well yes of course this would be ideal, but is simply impractical.  I
>run many types of machines, with many types of processors, running
>many types of OS's. They *all* exhibit this behavior (missed
>interrupts).

I'll take your word for it, but I don't see lost interrupts
discussed here very often.  Do you also have problems with
lost characters on serial ports?  (and similar things)

What sort of IO gear are you using?

My experience is that I rarely see lost interrupts.  I used to
have a recipe to provoke them.  I forget what system that was.
I think it involved a lot of disk activity with DMA turned off.


I wonder if it would be reasonable to hack together a lost
interrupt fixer-upper.  The idea is to have some code (could
be user level) that compares the cycle counter with the time of
day, and calls the kernel to generate a fake/extra timer interrupt
when it notices one got lost.

-- 
The suespammers.org mail server is located in California.  So are all my
other mailboxes.  Please do not send unsolicited bulk e-mail or unsolicited
commercial e-mail to my suespammers.org address or any of my other addresses.
These are my opinions, not necessarily my employer's.  I hate spam.




More information about the questions mailing list