On Wed, May 11, 2022 at 10:52:55AM +0900, Yuichiro NAITO wrote: > Hi, Scott. > > Recently I started running OpenBSD on ESXi. > I'm facing monotonic time going back problem as same as Yasuoka-san's report. > > https://marc.info/?l=openbsd-tech&m=161657532610882&w=2 > > I've tried your v2 patch. It seems the problem has been solved in my > enviroment. > But I'm a little bit confused about the patch. May I ask you goal of the > patch?
The primary goal of the patch is to eliminate false positives when testing for TSC skew. NUMA lag seems to sometimes fool the current test. It would be nice to be able to use the TSC in userland on multisocket machines. > Is it indented to fix the problem or is it for collecting test cases and the > results? The intention of the patch was not to fix the problem Yasuoka is describing. If it fixes that problem it is unintentional. > Here is the dmesg shown in my patched environment. > > [...]
