Google Cloud·29 Mar 2025 · 12:53 PDTResolved

Google Cloud us-east5-c power and UPS failure

A utility power loss followed by a battery failure in the zone’s UPS system caused virtual machines to lose power and disrupted multiple Google Cloud services.

Reported duration6h 10m
Impact scopeRegional
Incident categoryData center / power

Google’s summary describes 6h 10m, while the incident header lists 12:53–19:15 PDT (6h 22m). This archive preserves the provider summary duration and retains the published incident window in the timeline.

WHAT HAPPENED

Incident summary

A utility power loss followed by a battery failure in the zone’s UPS system caused virtual machines to lose power and disrupted multiple Google Cloud services.

Multiple Google Cloud services in the us-east5-c zone experienced degraded service or unavailability for 6 hours and 10 minutes. Some services recovered later than the initial power restoration because manual recovery steps were required.

ROOT CAUSE

What the provider reported

Google Cloud reported that a utility power outage triggered a cascading UPS failure after a critical battery malfunction. Some network and storage components in the zone were also affected.

Editorial note: This is a concise summary of the provider’s public explanation, not an independent technical investigation.

AFFECTED SURFACE

Services and systems

Compute EngineCloud SQLCloud FirestoreBigQueryGKEVPCIAMPersistent Disk

Reported scope: Columbus, Ohio · us-east5-c

EVENT TIMELINE

Latest source updates

Showing up to the 3 latest updates available in the source record. UTC is fixed; local time is converted in this browser (your local timezone).

  1. 12:53 PDT Local conversion unavailable: source time is not normalized

    Incident begins

    Customers begin experiencing connectivity issues in the us-east5-c zone.

  2. 14:49 PDT Local conversion unavailable: source time is not normalized

    Power restored

    Engineers bypass the failed UPS and restore power via generator.

  3. 19:15 PDT Local conversion unavailable: source time is not normalized

    Incident ends

    The provider records the incident as ended after 6 hours and 10 minutes.

COMMUNITY SIGNAL

What did this incident feel like?

React anonymously. Counts are shared across visitors and are not a measure of the number of customers affected.

Community signal
Shared anonymous reactions