Live / Snowflake / Incident
Snowflake: INC20000237
Snowflake · snowflake.comCritical outageResolved2026-09-26 00:20 UTC
Public — what happened
Summary
Snowflake reported a critical incident in which customers in certain regions may have lost access to several core services, including signing in, running queries, managing data, connecting through private links such as AWS PrivateLink, and streaming data with Snowpipe Streaming, while scheduled and serverless tasks may have run late. The company said the problem began at 22:35 UTC on September 25, 2026, and that most of the impact had eased by 22:59 UTC, with the leftover task backlog cleared by 23:43 UTC. Snowflake said its preliminary finding was that an internal metadata database in the affected region went offline, causing connection failures across services. It said a fix was in place, service was confirmed restored, and a fuller root cause summary would follow within 5 business days.
Timeline
- Started — 2026-09-25 23:00 UTC
- Resolved — 2026-09-26 00:20 UTC · 1h 20m after it started
With SquidGrid — where it starts on the route
Independent path health
The status page is the symptom. SquidGrid measures the paths that reach Snowflake against their own baselines — whether the routes carrying your traffic degraded, at which handoff, and who owns that stretch.
🔒 Sign in to seeCustomers get the live Provider Assessment Report for Snowflake: its full incident track record, what tends to break, and recent public reports of problems.
Included with any paid plan.
Open the Snowflake report →
More from Snowflake
Covered in The Squid’s Ink, Week 40, 2026, our weekly internet health report.