On Wed, Oct 02, 2024 at 05:14:42PM GMT, Markus Armbruster wrote: > >> Are we confident we'll never need less than a full second? > > > > Hmm, recent "[PATCH v2] chardev: introduce 'reconnect-ms' and deprecate > > 'reconnect'" shows that at least sometimes second is not enough precision. > > > > Maybe, using milliseconds consistently for all relatively short time > > intervals in QAPI would be a good rule? > > Ideally, we'd use a single unit for time: nanoseconds. But we missed > that chance long ago, and now are stuck with a mix of seconds, > milliseconds, microseconds, and nanoseconds. > > I think a good rule is to pick the first from this list that will surely > provide all the precision we'll ever need. > > In this case, milliseconds should do.
I'll use milliseconds in the next revision. -- Eric Blake, Principal Software Engineer Red Hat, Inc. Virtualization: qemu.org | libguestfs.org
