On Thu, Feb 04, 2021 at 09:07:06PM +0000, Jaromir Dolecek wrote: > Module Name: src > Committed By: jdolecek > Date: Thu Feb 4 21:07:06 UTC 2021 > > Modified Files: > src/sys/kern: vfs_init.c vfs_subr.c > src/sys/sys: mount.h > > Log Message: > introduce vfs.generic.timestamp_precision sysctl to control precision > of the timer used for vfs_timestamp(); default stays the same > to use nanotime(9), but option is there to use the faster, albeit > less precise methods
Most of this seems to be misguided at best. I mean it makes sense to have a variant of getnanotime vs nanotime to avoid touching the timecounter hardware. But the rest is just begging for hard to debug bug reports for little to no gain. Especially limiting it to microseconds doesn't buy anything on this level really. Joerg
