Re: AW: Re[2]: [uml-user] timer resolution in UML kernel

2005-10-24 Thread Blaisorblade
On Monday 24 October 2005 19:45, Serge Goodenko wrote: > > I don't now if this also works in UML, but we use rdtsc for quite > > something similar. > > rdtsc is a C function which read a processor register (twice 32 bit) > > which counts processor ticks (meaning on a 1 GHz processor you get a > >

Re[2]: [uml-user] timer resolution in UML kernel

2005-10-24 Thread Jim Carter
On Mon, 24 Oct 2005, Serge Goodenko wrote: > > Also, HZ (i.e. the timer interrupt) is implemented using signals (i.e. > > alarm()), which are both slow and not precise (no more than host > > jiffies). > hm.. this suggests that maybe it would be really better not to use > jiffies in UML (in my

Re: AW: Re[2]: [uml-user] timer resolution in UML kernel

2005-10-24 Thread Serge Goodenko
> I don't now if this also works in UML, but we use rdtsc for quite something > similar. > > rdtsc is a C function which read a processor register (twice 32 bit) which > counts processor ticks (meaning on a 1 GHz processor you get a resolution of > nano seconds). well, I suppose UML is the keywor

Re[2]: [uml-user] timer resolution in UML kernel

2005-10-24 Thread Serge Goodenko
> > On Friday 21 October 2005 13:47, Serge Goodenko wrote: > > How can I increase the resolution of UML kernel timer? > Elaborate on what you mean. You show being a kernel hacker, and I need to > know > if you want to increase the resolution for jiffies (i.e. you must surely > increase HZ in UM