Udo van den Heuvel via devel writes: > On 13-04-19 15:29, Achim Gratz via devel wrote: >> Udo van den Heuvel via devel writes: >>> Fedora 29, kernel.org 4.19.30. (my compile) >> >> Is this a "tickless" kernel perhaps? If so, try "nohz=off" on the >> kernel command line in the boot manager and see if that helps. > > # grep HZ .config|grep -v ^# > CONFIG_NO_HZ_COMMON=y > CONFIG_NO_HZ_IDLE=y > CONFIG_HZ_250=y > CONFIG_HZ=250 > > tickless does not go with PPS support...
How about you boot with "nohz=off"? > My kernel is from kernel.org and compiled by me. What keeps you from using a newer one, then? > I need faster memory for later BIOS. Perhaps later this year. That's the first time I ever hear about a BIOS update requiring a higher memory speed (earlier BIOS versions not supporting _hugher_ memory speeds, yes -- but not the other way around). > !? > What /was/ the problem in that case? The same that you still see: the system clock gets stopped and two consecutive reads of the clock read the same (or maybe time even goes backwards when looked at with higher resolution). > With tsc there was no real sync to pps. > With hpet we do have sync to pps. The only thing switching to HPET does is reducing clock resolution _a lot_, so if your clock is funky with TSC, it still is with HPET. It has more chance of averaging out over the longer interval between clock ticks, that's all. Regards, Achim. -- +<[Q+ Matrix-12 WAVE#46+305 Neuron microQkb Andromeda XTk Blofeld]>+ SD adaptation for Waldorf rackAttack V1.04R1: http://Synth.Stromeko.net/Downloads.html#WaldorfSDada _______________________________________________ devel mailing list devel@ntpsec.org http://lists.ntpsec.org/mailman/listinfo/devel