Messages in this thread | | | Date | Wed, 25 Nov 1998 21:30:33 +0000 | From | Stephen Donnelly <> | Subject | Re: kernel time *UNSAFE* during interrupts |
| |
Michael Krause wrote: > The page says you printk()'ed the time from both get_fast_time() and > do_gettimeofday() -- however, on a Pentium system with TSC enabled, > get_fast_time() also ends up in do_gettimeofday() [do_get_fast_time > gets overwritten at the bottom of arch/i386/kernel/time.c] so I don't > quite see how you can get different results.
Ah, but I don't! do_gettimeofday and get_fast_time produce the same results at interrupt time, both of them show the -10ms jump. It is only from user space (or non-interrupt time?) that gettimeofday is safe.
> What a machine do you have, and is CONFIG_CPU_IS_SLOW enabled?
I have tried this on a PII 266MHz with 196MB of ram, and an old P75. Both of these will have TSC.
I could not find the CONFIG_CPU_IS_SLOW option anywhere, where does it get set or cleared?
I would very much like it if you could try the tcpdump experiment, so that I can say that its not only me that sees this bug!
> Hmm. I was sure it's only a matter of time until someone finds a bug > in the new time.c code :)
Ah well, this is the nature of things. :)
Stephen. -- ----------------------------------------------------------------------- Stephen Donnelly (BCMS) email: sfd@cs.waikato.ac.nz Waikato ATM Group Lab G1.31 phone +64 7 838 4466 x6728 Computer Science Department, University of Waikato, New Zealand -----------------------------------------------------------------------
- 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/
| |