[01:11:10] <Krinkle>	 We may want to oversample navtiming in those regions for a little while and get some before/after numbers
[01:15:02] <Krinkle>	 https://diff.wikimedia.org/2018/04/24/new-data-center-singapore/
[01:16:25] <Krinkle>	 Hmm it seems the last Grafana 8 upgrade killed compat for the redirects for symbolic dashboard URLs
[01:16:30] <Krinkle>	 https://grafana.wikimedia.org/dashboard/db/performance-singapore-caching-center
[01:16:53] <Krinkle>	 https://grafana.wikimedia.org/dashboard/db/navigation-timing
[14:33:55] <elukey>	 folks I just roll restarted blazegraph on wdqs-public-codfw, the metrics https://grafana.wikimedia.org/d/000000489/wikidata-query-service?orgId=1&refresh=1m&from=now-3h&to=now looks better now but I have not a complete idea about what caused blazegraph to stall in this way. The page look resolved/acked in vops' dashboard, so I am inclined to keep going with my Sunday
[14:34:12] <elukey>	 Cc: gehel, dcausse, ryankemper --^
[14:35:04] <gehel>	 elukey: thanks !
[14:36:24] <gehel>	 We have a few ideas of what can cause Blazegraph to crash, but none of them actionable in the short term
[14:36:48] <gehel>	 It seems to have recovered, so we should be good for now
[14:37:32] <gehel>	 ryankemper, inflatador : can you write an incident report tomorrow and share with the team ? (I'll be on the plane)