Intermittent DNS probe timeouts
Resolver probes from two regions timed out at a higher rate. Cached records continued to serve slammed.st. Hub and API were reachable by IP throughout.
- Affected
- DNS / Anycast Edge
- Started
- Oct 4, 2026, 3:06 AM UTC
- Resolved
- Oct 4, 2026, 4:18 AM UTC
- Duration
- 1.2 h
Response time
Peak 210 ms
{"labels":["0m","2m","3m","5m","6m","8m","9m","11m","12m","14m","15m","17m","18m","20m","21m","23m","25m","26m","28m","29m","31m","32m","34m","35m","37m","38m","40m","41m","43m","44m","46m","47m","49m","51m","52m","54m","55m","57m","58m","60m","61m","63m","64m","66m","67m","69m","70m","72m"],"series":[{"name":"Response time","color":"#ff4ecd","values":[21.4,22,22,21,20.3,21.7,21.5,20,21.1,21,21.5,21.6,21,53.8,85.6,115.5,142.5,165.8,184.7,198.6,207.1,210,207.1,198.6,184.7,165.8,142.5,115.5,85.6,53.8,21,20.6,21.8,21,20.1,21.8,20.5,20.7,21.9,20.9,20.8,20.8,20.8,21.4,21.4,20.7,20.6,20.2],"unit":"ms"}]}
Error rate
Peak 3.9 %
{"labels":["0m","2m","3m","5m","6m","8m","9m","11m","12m","14m","15m","17m","18m","20m","21m","23m","25m","26m","28m","29m","31m","32m","34m","35m","37m","38m","40m","41m","43m","44m","46m","47m","49m","51m","52m","54m","55m","57m","58m","60m","61m","63m","64m","66m","67m","69m","70m","72m"],"series":[{"name":"Error rate","color":"#3dd6f5","values":[0.1,0.1,0.1,0.1,0.1,0.1,0.1,0.1,0.1,0.1,0.1,0.1,0.1,0.8,1.4,2,2.5,3,3.4,3.7,3.8,3.9,3.8,3.7,3.4,3,2.5,2,1.4,0.8,0.1,0.1,0.1,0.1,0.1,0.1,0.1,0.1,0.1,0.1,0.1,0.1,0.1,0.1,0.1,0.1,0.1,0.1],"unit":"%"}]}
Forwarded capacity
Peak 9 Gbps
{"labels":["0m","2m","3m","5m","6m","8m","9m","11m","12m","14m","15m","17m","18m","20m","21m","23m","25m","26m","28m","29m","31m","32m","34m","35m","37m","38m","40m","41m","43m","44m","46m","47m","49m","51m","52m","54m","55m","57m","58m","60m","61m","63m","64m","66m","67m","69m","70m","72m"],"series":[{"name":"Forwarded capacity","color":"#8b6cff","values":[9.4,9.3,9.4,8.7,8.7,9.3,8.8,9,8.9,8.7,8.9,8.6,9,8.3,7.6,7,6.4,5.9,5.5,5.2,5.1,5,5.1,5.2,5.5,5.9,6.4,7,7.6,8.3,9,9.3,9,9.2,9.1,9,9.2,8.7,9.1,9,8.7,9.1,9.2,9.4,9,8.7,9.4,9.4],"unit":"Gbps"}]}
Timeline
-
Investigating
Anycast health from SG and FRA showed elevated SERVFAIL on probes.
-
Identified
A prefix withdrawal left two PoPs catching extra catch-all traffic.
-
Mitigating
Announcement restored. Recursors recovered as caches expired.
-
Resolved
Probe success returned to 99.9%+.