Google Cloud Outage History

The Google Cloud us-east1 region experienced elevated error rates and degraded performance beginning at 2:06 PM UTC, impacting a broad set of services across the region. Users saw slower responses and partial outages across products including Compute Engine, Cloud Storage, Cloud SQL, BigQuery, Dataflow, Pub/Sub, Cloud Run, and App Engine. The impact was most pronounced in us-east1-a, with us-east1-b partially affected, while other zones showed intermittent normal operation as engineers investigated.

Google Cloud communications indicated a hardware infrastructure failure as the likely cause and said engineers would provide more details as the investigation progressed. Engineers recovered the failed hardware and began restoring the network control plane across affected zones. By around 6:00 PM UTC, many services had recovered and teams were validating the remaining workloads. The incident lasted roughly 3 hours and 54 minutes and was localized to the us-east1 region, with no global impact reported.

Google Cloud experienced a major outage tied to Identity and Access Management (IAM) services, affecting a broad set of products and regions. The disruption began at 5:51 PM UTC (10:51 PDT) on Thursday, June 12, and Google Cloud acknowledged the incident shortly after. Users reported widespread failures and degraded performance across numerous services, including Cloud Storage, BigQuery, Cloud Spanner, Cloud Run, Pub/Sub, Dataflow, Data Fusion, Dataproc, Dataplex, Vertex AI, and more on a global scale.

Google Compute Engine (GCE) and a broad set of dependent Google Cloud services experienced a region-wide issue, causing degraded performance and partial service interruptions across zones in the Americas and Europe. Affected components included Google Compute Engine, Google Kubernetes Engine, Cloud Dataflow, Cloud SQL, AlloyDB for PostgreSQL, Cloud Composer, Cloud Build, Cloud Dataproc, Cloud Filestore, Google App Engine, and more. The outage began on May 20, 2025 11:10 AM UTC and was resolved by May 20, 2025 12:20 PM UTC, lasting about 1 hour and 10 minutes. The status page listed dozens of components with degraded status during the incident.

An outage began at 1:36 AM UTC in Google Cloud zone us-east5-c after a power event, leading to widespread connectivity issues across a broad set of services. Users reported disruptions and degraded performance across multiple Google Cloud components, including Cloud Interconnect, Google Compute Engine, Virtual Private Cloud (VPC), Persistent Disk, AlloyDB, Cloud Dataproc, Cloud Dataflow, Cloud Filestore, Identity and Access Management, Cloud SQL, Google Kubernetes Engine, Cloud Composer, BigQuery, Cloud Bigtable, and more. The issue was centered in the us-east5 region and affected related components and services in the Americas. Initial guidance indicated full recovery would take several hours.

An incident caused temporary degradation of Apigee and Apigee Hybrid components across numerous Google Cloud regions, affecting API management operations for a brief period. The outage began at 9:38 PM UTC and was resolved by 9:45 PM UTC, lasting approximately 7 minutes.

The provider issued two status updates during the incident, describing the degraded performance and subsequent restoration as services came back online.

Google Cloud Asset Inventory experienced an outage where queries could return empty results. The incident began at 9:14 AM UTC (01:14 US/Pacific) and lasted about 22 hours 46 minutes, ending at Feb 20, 2025 8:00 AM UTC. This affected the Global Cloud Asset Inventory component and degraded query reliability for customers.

The provider issued 2 official status updates during the incident, with the issue recorded as a degraded Cloud Asset Inventory service. The outage was resolved and Cloud Asset Inventory returned to normal by Feb 20, 2025 8:00 AM UTC.

Google Cloud experienced an outage affecting SIEM Dashboards and SOAR Advanced Dashboards for Google Security Operations (SecOps), rendering dashboards unavailable and causing errors loading data visualizations. The issue impacted dozens of Chronicle Security and Chronicle SOAR components across global regions, limiting visibility into security trends. The outage began at 10:42 PM UTC and was resolved by 2:45 AM UTC, lasting roughly 4 hours.

The Google Cloud team issued three updates during the incident, communicating ongoing investigation and current details as engineers worked to restore dashboards. Affected regions spanned Americas, Europe, Asia Pacific, and other areas, with multiple Chronicle Security and Chronicle SOAR components impacted.

Google Cloud Vertex AI Search for commerce customers experienced a partial outage, with a subset of IPs reporting a 100% error rate. The incident began on 12:48 PM UTC and persisted for roughly 3 hours, affecting Global/Recommendation AI and Vertex AI Search across multiple regions (eu and us) as well as the global Vertex AI Search component. The status page captured the issue with ongoing investigation and several updates as engineers worked to restore service. Three official updates were issued at Feb 16, 2025 3:35 PM UTC, Feb 16, 2025 3:50 PM UTC, and Feb 16, 2025 3:55 PM UTC, with all listed components listed back to normal by 3:55 PM UTC.

Google Cloud Chronicle Security feed-based ingestion experienced issues affecting Europe regions, including europe-west2. Users relying on feed-based ingestion may have seen delays in detection and data ingestion, impacting visibility of security events. The incident began on Feb 13, 2025 8:13 PM UTC and progressed to a degraded state for European Chronicle Security components, including Europe (regions) and europe-west2. The outage lasted roughly 9 hours and 32 minutes, with service returning to normal after Feb 14, 2025 5:45 AM UTC.

The Chronicle Security service within Google Cloud experienced an outage affecting the Risk Analytics Dashboard in the US multi-regions. Users observed that dashboard details were not up-to-date, reducing visibility into risk. The issue began at Feb 3, 2025 2:00 AM UTC and affected two Chronicle Security components (us / Chronicle Security and Multi-regions / Chronicle Security). Google Cloud issued three status updates as the incident progressed, and the components returned to normal by Feb 3, 2025 9:55 AM UTC. The outage lasted about 7 hours 55 minutes.