Re: GCE: significant clock drift - the solution

2017-01-18 Thread Leif Pedersen
I wanna say it was i8254 that I had the weird trouble with, but I can't remember for sure. It's my experience as well that much of this seems to vary over time and with different VMs. -Leif On Jan 18, 2017 8:26 PM, "Dmitri Goutnik" wrote: Hi Bruce, Thanks for posting this, setting machdep.di

Re: GCE: significant clock drift - the solution

2017-01-18 Thread Dmitri Goutnik
Hi Bruce, Thanks for posting this, setting machdep.disable_tsc_calibration=1 indeed makes TSC-low available and fixes the clock drift. The confusing thing is that timecounter choices vary with GCE hardware and the only common choice seems to be low "quality" i8254. On Wed, Jan 18, 2017 at 8:10 P

Re: GCE: significant clock drift - the solution

2017-01-18 Thread Leif Pedersen
Just for others to learn from my head-pounding, heh: On 10.3, I've been using kern.timecounter.hardware=ACPI-safe I set it with sysctl after booting, then recorded it in sysctl.conf. No loader tweaking was necessary. Besides speculating from experience, I don't know which is best or why. I arrive

GCE: significant clock drift - the solution

2017-01-18 Thread Bruce Walker
Hi gang, first message. I am developing on Google Cloud Engine, I'm using the FreeBSD community image, and so far it's been pretty painless. Thank you! But I noticed that the system clock on one of my two instances was drifting fast over time, and I mean really fast. I estimate about 1 second ahea