Fly.io outage: Partial outage in AMS

1. resolvedOct 3, 2026, 08:57 UTC

   All impacted services are operational now.

2. monitoringOct 3, 2026, 08:35 UTC

   All MPG clusters have recovered. We are monitoring for additional impact.

3. monitoringOct 3, 2026, 08:19 UTC

   All hosts are back online. MPGv2 control plane is fully operational now. Some MPGv1 clusters in AMS might be degraded while MPGv1's control plane recovers.

4. identifiedOct 3, 2026, 08:08 UTC

   Those hosts are coming back online after a brief interruption. We are assessing the impact on MPG.

5. identifiedOct 3, 2026, 08:01 UTC

   Some of our hosts are offline in AMS. Control plane for Managed Postgres v1 and v2 in AMS is unavailable as a result of this. MPG clusters should remain online but any control plane ops will fail. Some machines in AMS are also unavailable.

What APIStatus.watch saw

• Oct 3, 2026, 08:05 UTCoperational → major outage
• Oct 3, 2026, 08:10 UTCmajor outage → degraded
• Oct 3, 2026, 08:40 UTCdegraded → operational

Other services with incidents at the same time

Overlapping incidents aren't necessarily related.

• OVHcloud: [GRA][Storage] - Object Storage S3 incident notificationMajor · Oct 3, 2026, 03:06 UTC
• Akamai: Origin Server Connectivity Issues with Elevated Errors in APAC RegionMinor · Sep 22, 2026, 14:28 UTC
• Cloudflare: Cloudflare One Clients are incorrectly challenged on some sitesMinor · Sep 22, 2026, 19:23 UTC
• Zoom: Service Degradation Affecting Customer Using Polycom Devices Going OfflineMinor · Sep 25, 2026, 17:45 UTC
• Twilio: MMS Delivery Delays from a Subset of Twilio Long Codes to GCI United StatesMinor · Sep 26, 2026, 03:16 UTC
• Clerk: Development instances only - Apple rejecting emailsMinor · Sep 28, 2026, 15:23 UTC
• Supabase: Intermittent latency in Eastern USMinor · Sep 29, 2026, 16:26 UTC
• LaunchDarkly: Elevated error rates in the LaunchDarkly applicationMinor · Oct 2, 2026, 14:10 UTC
• Twilio: SMS Delivery Delays and Failures from Twilio to Hi3G ItalyMinor · Oct 2, 2026, 21:48 UTC
• Shippo: DPD Germany service degradationMinor · Oct 3, 2026, 05:41 UTC

How often does Fly.io have incidents?

Fly.io reported 19 incidents in the last 90 days, 11 of them major or critical. A typical incident lasted 57 min. See Fly.io's uptime and incident history