Christian Weisgerber <na...@mips.inka.de> wrote: > Scott Cheloha: > > > > kern.timecounter.tick=1 > > > kern.timecounter.timestepwarnings=0 > > > kern.timecounter.hardware=i8254 > > > kern.timecounter.choice=i8254(0) tsc(-1000) acpihpet0(1000) > > > acpitimer0(1000) > > > > This is expected behavior with the patch. > > > > cpu0's TSC is way out of sync with every > > other CPU's TSC, so the TSC is marked > > as a bad timecounter and a different one is > > chosen. > > Shouldn't it pick acpihpet0 then?
Let's keep in mind the goal: When it works well, the TSC is a better timer than all the others, so if the TSC problems can be diagnosed & resolved by various measurements and mitigations, then we will want the TSC to be chosen. So the long term roadmap probably does NOT include acpihpet0 being chosen. Long term, that hopefully is a falacy.
