Messages in this thread | | | Subject | Re: [patch] x86: unify/rewrite SMP TSC sync code | From | Arjan van de Ven <> | Date | Sat, 25 Nov 2006 09:30:23 +0100 |
| |
On Fri, 2006-11-24 at 18:56 -0800, Wink Saville wrote: > Ingo Molnar wrote: > > * Andi Kleen <ak@suse.de> wrote: > > > > a new CPU is added. If the TSC isnt sync on SMP then it quickly gets > > pretty messy, and we should rather take a look at /why/ these apps are > > using RDTSC. > > > > Ingo > > - > > I use RDTSC in get a cheap method of measuring time. What other choices are > there for a low overhead high frequency time source? > > By low overhead a kernel call is way to expensive, I want to minimally impact > the code and have many of these calls through out the code. One of the > ways I use it is to instrument multi-threaded applications and then use > the TSC to compare when actions occur between threads. i.e. I use it as a > time stamp counter and neither precision or accuracy is too important. > On the other hand the more precise and accurate the better:)
so you can live with an occasional jump of seconds/minutes between threads? Or when a thread moves to another cpu? (yes on many PCs you won't see minutes, but on others you will)
-- if you want to mail me at work (you don't), use arjan (at) linux.intel.com Test the interaction between Linux and your BIOS via http://www.linuxfirmwarekit.org
- To unsubscribe from this list: send the line "unsubscribe linux-kernel" in the body of a message to majordomo@vger.kernel.org More majordomo info at http://vger.kernel.org/majordomo-info.html Please read the FAQ at http://www.tux.org/lkml/
| |