Thank you Sitsofe. On 9/18/08, Sitsofe Wheeler <sitsofe@xxxxxxxxx> wrote: > Peter Teoh wrote: > > Thank you for your reply Sitsofe. I hope you will allow me to share > > with the Kernelnewbies team as well. > > > > Of course. > > > To rephrase my question: > > > > In a standard x86 hardware system, we have hardware clock source from > > APIC timer, ACPI timer, and then old 8253 PIT timer. So my question > > the different API listed above uses which hardware as the source of > > clocking? Then there is another HPET timer - is it synonymous to one > > of the above timer? > > > > Just after start up the kernel decides which hardware clock source it deems > to be the best after tests (the order on x86 from most to least prefered is > roughly HPET, ACPI, TSC, PIT) and goes on to only use that (after I am curious to know - where is this in the source code? > calibrating various bits). All timer events will then be generated from this > one source (unless the kernel suspects it has gone bad at which point it > will switch). There are several interfaces creating events to fire off at > points in the future but underneath they are running off the same source > that was decided at boot. > > HPET hardware is "new" and is not synonymous to the APIC/ACPI, PIT or TSC > hardware. > > There seems to be a good treatment of timers in the Understanding the Linux > Kernel, Third Edition book (see the chapter on Timing Measurements). > Yes, I just saw that as well, even in 2nd edition several of these are being discussed. And the book is classic.....seemingly covering a lot of topics, and lots of knowledge is in between the lines. Hm.... -- Regards, Peter Teoh -- To unsubscribe from this list: send an email with "unsubscribe kernelnewbies" to ecartis@xxxxxxxxxxxx Please read the FAQ at http://kernelnewbies.org/FAQ
