* tracing "lost_ticks" in 2.2.9 on a slow machine
@ 1999-06-17 8:29 Ulrich Windl
0 siblings, 0 replies; only message in thread
From: Ulrich Windl @ 1999-06-17 8:29 UTC (permalink / raw
To: linux-kernel
Hello,
I'm seeking for some advice: I run my old PC (a 16MHz 386/SX,
possibly the absolute low-end until I disable the "turbo") with Linux
2.2.9 as a time server (my boss won't donate a machine). With ntpd-
4.0.92 and a DCF77 reference clock the machine can keep time within
2ms (in the last two weeks).
Unfortunately some debugging code from PPSkit-0.7.0 indicates that
``ticks'' in update_wall_time() is 2 quite frequently, even if the
machine is idle. Running one program I saw a value of "4"...
This is not very encouraging. I'd like to find out what parts of the
kernel disable interrupt processing for that long, but I'm not good
enough with the assembler facts:
I'd like to modify the interrupt enabling code (restore_flags) to
check the value of the lost_ticks, and if it's high, it should
display the address where the instruction pointer is.
Can anybody tell me how to do that?
(I'm not subscribed to the list, so please CC: any replies, please)
Regards,
Ulrich
-
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.tux.org/lkml/
^ permalink raw reply [flat|nested] only message in thread
only message in thread, other threads:[~1999-06-17 8:30 UTC | newest]
Thread overview: (only message) (download: mbox.gz follow: Atom feed
-- links below jump to the message on this page --
1999-06-17 8:29 tracing "lost_ticks" in 2.2.9 on a slow machine Ulrich Windl
This is an external index of several public inboxes,
see mirroring instructions on how to clone and mirror
all data and code used by this external index.