On Thu, 2004-02-12 at 23:09, David Mosberger wrote: > >>>>> On Thu, 12 Feb 2004 18:29:35 -0800, john stultz <johnstul@us.ibm.com> said: > > John> I'm not sure I see how gettimeofday will use ITC based > John> interpolation if the ITCdrift is off. Sure, the ITC will > John> register a timesource, but init_cyclone_clock runs after > John> time_init and has a negative drift value, so on the x450/x455 > John> the cyclone interpolator will be used. > > John> Am I missing something? > > Yes: it's the _lightweight_ gettimeofday() handler that will get > you. See arch/ia64/kernel/fsys.S:fsys_gettimeofday(). > > To date no distribution ships with light-weight syscall supported > enabled, but the support is in the current glibc, so it's only a > matter of time before this would start to bite. Ah! Thanks for the pointer! I wouldn't have caught that otherwise. So, as it seems the hardware currently doesn't set the ITCdrift flag, should I then set it in my init code? Or is there some other way of disabling fsys support, possibly on a per-syscall basis? thanks -john - To unsubscribe from this list: send the line "unsubscribe linux-ia64" in the body of a message to majordomo@vger.kernel.org More majordomo info at http://vger.kernel.org/majordomo-info.htmlReceived on Mon Feb 16 21:51:10 2004
This archive was generated by hypermail 2.1.8 : 2005-08-02 09:20:22 EST