I just wanted to mention that despite of the sudden spike on DB reads, our databases kept up just fine in general. We did have timeouts on some enwiki (s1) replicas, but it was mostly well handled.

I think https://gerrit.wikimedia.org/r/c/operations/puppet/+/892570 would have smoothed this out, at least in part -- we just didn't get it reviewed in time for the switchover. We'll have to try it out on the next one instead. (Unless we stage a depool and cache wipe just to test the warmup script, but that's probably not necessary.)

892570 is merged now, and I think we'll be in better shape for the next one. @Clement_Goubert I'm tempted to resolve this, and reopen if we find we still have a problem the next time we have to do a warmup -- but your call.