Trending the h1iopsusauxh2 cpu meter (attached) shows that the system crashed at  08:53 UTC (01:53 PDT) and was restored 09:40 UTC (02:40 PDT). I've rounded this up to a 1 hour downtime for the FRS accounting.

While getting these stats I've noticed a problem with h1edc's trending of its own channel-connection counters. I've opened FRS12776.