Snowflake: Incident updated: INC20000294

Incident updateNormal progress (rule, 100%)Changed 2026-10-20 07:23 UTCstspg.io

Summary

Summary pending. The diff below shows exactly what changed.

Incident page: the full timeline of updates

Part of an outage event

Google Cloud europe-west2 outage, Oct 20, 2026 · 19 vendors, 19 incidents

Snowflake’s incident started in the same window without naming Google Cloud (timing only, not evidence of a link). (timing only, posted +26 min vs Google Cloud’s own post)

See the cascade chart and every vendor →

Detected automatically from incidents that started together and named the same provider. A link means one vendor’s incident named another, not a confirmed cause.

What changed

~~Struck in red~~ is what Snowflake removed; blue is what they added. Muted text is unchanged context.

ChangedStatus#1

~~investigating~~

identified

AddedUpdateidentified2026-10-20 07:22 UTC#2

not present

Current status: We've identified an issue with a third-party cloud platform that's affecting part of the infrastructure in the specified region, and we're coordinating with the provider to develop and implement a fix to restore service. We have identified and issue with one of the availability zones in the region. Workloads have automatically moved away from the affected infrastructure. We'll provide another update within 30 minutes. Customer experience: We're seeing recovery of the affected services as of 6:40 UTC. Customers hosted in the specified region may have been unable to access or use multiple Snowflake services and features, including Snowflake Postgres. Affected users may experience errors or failures when connecting to Snowflake Postgres instances, managing data, loading data, or using applications. ETA: An ETA isn't available yet. We'll provide one as soon as possible. Workaround: There are currently no available workarounds for this issue. Incident start time: 06:01 UTC October 20, 2026

Compared with the previous archived version of this incident (10 to 30-minute polling). View the live incident (opens in new tab).

Archive proof

Rewindex commits each version of an incident it captures to a daily checkpoint, chains it to the day before, and has the checkpoint timestamped by FreeTSA and DigiCert.

How the archive is checked, and what it cannot prove.

Rewindex captured this after the last checkpoint; the next run (00:41 UTC) commits it.

History of this incident

TodayTuesday, October 20Tue, Oct 20

2 rewrites, 7 incident changes

Incident update
15:43Incident
Incident updateINC20000294
Incident update
14:43Incident
Incident updateINC20000294
Incident update
12:43Incident
Incident updateINC20000294
Normal progress
09:53Incident
Incident updateINC20000294
Wording only
09:13Edited by the vendor
INC20000294
The incident update shows no visible wording change. Snowflake continued to report healthy service since 06:40 UTC October 20, 2026, while a third-party provider availability zone remained unavailable; new workloads were blocked from that zone and routine regional software updates remained paused.
Normal progress
08:03Incident
Incident updateINC20000294
Wording only
07:33Edited by the vendor
INC20000294
Snowflake edited its 10-20 07:22 UTC incident update to correct “and issue” to “an issue” and adjust a truncated closing sentence. The edit was wording-only; it did not change the reported availability-zone issue, automatic workload relocation, or coordination with the third-party cloud provider on a fix.
Normal progress
07:23Incident
Incident updateINC20000294this change
Outage
06:34Critical incident
INC20000294
Snowflake reported a critical outage in GCP - Europe West 2 (London) starting 2026-10-20 06:34 UTC: customers may be unable to access multiple services, including Snowflake Postgres, with connection, data management and loading failures. Investigation was ongoing; it was still open when archived, with 0 min elapsed at the last update.

All Snowflake changes Snowflake profile Markdown JSON