[ntp:questions] Re: IEEE 1588 support in NTP?

Hal Murray hmurray at suespammers.org
Wed Nov 2 21:12:40 UTC 2005


>I'd like to object: Some long time ago someone (I can't remember) made a test
>over an extended period of time showing that Linux did not loose a single
>interrupt. However depending on the drivers and crappy hardware (not to talk
>about CPU frequency scaling and ACPI's various power saving modes), the system
>may loose interrupts. For any hardware there is a rate of interrupts that
>cannot be handled. For my 16MHz 386SX that rate was quite low.

It may depend upon which version/distributino of Linux you are talking
about.

I have an old RH 7.2 system.  After a reasonably vanilla install,
it was using PIO for disk accesses.  Any big burst of disk activity
would cause missed interrupts.  I have a test hack for measuring
disk bandwidth.  It would totally trash the clock.

After poking around a bit I found some simple way to activate the
DMA mechanism.  That solved the problem for me.

I forget the details.  If anybody is still having troubles with
lost interrupts on Linux I'll try to track it down and contribute
it to a FAQ or such.

There may be similar problems with some network adapters.

-- 
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