At 10:31 UTC on 07 July 2021, we observed elevated latencies and errors in our Tokyo point of presence which affected History. This issue occurred because of an atypical combination of usage patterns causing CPU over-utilization in that region, ultimately resulting in the latencies and errors we observed. The incident was fully resolved at 11:07 UTC.
We added additional checks to prevent this from reoccurring in the short term. Still, in the coming weeks, we will be analyzing the causal usage patterns and working to separate the affected services with the goal of mitigating the possible recurrence of these multiple process failures.