**Summary** The issue causing timeouts, degradations, errors, and latencies across multiple us-west1 products has been mitigated. **Description** We have mitigated the issue impacting multiple products in our us-west1 region as of Thursday, 2026-08-20 10:22 PDT. Our engineering teams have restored capacity on a planned optical maintenance that caused unexpected congestion in Dalles, Oregon metro /us-west1 region. Our systems stabilized and services have recovered once capacity was restored. Our teams are continuing to monitor for any residual impact. We will publish an analysis of this incident once we have completed our internal investigation. We thank you for your patience while we worked on resolving the issue. **Diagnosis / Customer Symptoms** Customers in us-west1 may have experienced timeouts, service degradations, errors, and elevated latencies across multiple products. **Workaround** This issue is now mitigated.

**Title** Google SecOps customers may have experienced elevated latencies in SecOps Dashboards & Reports in the US region. **Description** The issue Google SecOps has been mitigated for all regions as of Wednesday, 2026-08-19 18:33 PDT. The issue was a temporary surge in data processing. We thank you for your patience while we resolved the issue. **Symptoms** Impacted customers may have experienced elevated latencies in SecOps Dashboards & Reports. Dashboards for UDM Events were not impacted. **Workaround** None, as the issue is resolved.

# Preliminary Incident Report We sincerely apologize for the disruption this incident caused to your business. We know how much you rely on Google Workspace, and we regret the impact on your productivity. We are working to address the root cause and prevent this from occurring in the future.  Please note, this information is based on our best knowledge at the time of posting and is subject to change as our investigation continues. A final Incident Report with preventative actions will be posted once our investigation is complete.  If you have experienced impact outside of what is listed below, please reach out to Google Workspace Support using the help article [**https://support.google.com/a/answer/1047213**](https://support.google.com/a/answer/1047213). ## Date/Time of the Issue (All time US/Pacific) Incident Start: 18 August 2026 16:58 Incident End: 19 August 2026 05:40 Duration: 12 hours, 42 minutes  ## Summary On August 18, 2026 from 16:58 to August 19, 2026 05:40 US/Pacific, Drive customers in Australia, Philippines and New Zealand experienced degraded performance and slowness. During this period users also experienced 502 errors. Other Google Workspace services were not affected.  ## Preliminary Root Cause Google utilizes a multi-tiered global load balancing and network routing architecture to serve traffic efficiently. To ensure fair use and prevent congestion, bandwidth allocation is managed by attributing traffic to specific downstream services. A misconfiguration in the attribution of traffic caused the bandwidth usage to be incorrectly attributed to the frontend network load balancing tier itself, rather than to the Drive service. The sequence of events leading to customer impact was as follows: * Traffic from the regional load balancing tier was incorrectly attributed to the load balancing infrastructure rather than the Drive service. * Unrelated traffic caused network bandwidth usage attributed to the load balancing infrastructure in this region to exceed its quota. * Network bandwidth management systems applied throttling to this traffic to enforce quotas, causing severe network congestion affecting Drive traffic in this region. * This congestion led to increased latency, slowness, and error rates for users accessing Drive in the affected regions. ## Remediation  Google engineers were alerted to the issue via automated monitoring and an influx of customer support cases, with initial incident response teams engaged by 17:21 US/Pacific on August 18, 2026\. Engineers initially attempted to alleviate the congestion by draining regional frontend traffic to an alternate geographic location, but this proved ineffective and was reverted. The team then mitigated the issue by migrating regional traffic to an upgraded internal network routing architecture, which correctly set the traffic attribution for Drive. Normal operations were fully restored once 100% of the regional traffic was migrated to the upgraded network architecture. ## Description of Impact Between August 18, 2026, at 16:58 US/Pacific and August 19, 2026, at 05:40 US/Pacific, Google Drive users in Australia, Philippines and New Zealand experienced severe latency, degraded performance and 502 errors. During this roughly 12-hour and 42-minute window, affected customers may have observed significant slowness or errors when attempting to access Google Drive or listing files through Editors (e.g. [docs.google.com](http://docs.google.com)), with initial load times significantly delayed. The issue was fully mitigated as of August 19, 2026, at 05:40 US/Pacific, and normal service has been restored.

**Summary** [Mitigated] Access issues for Workspace Admins with Classroom’s web homepage. **Description** The issue with Classroom has been resolved for all affected users as of Tuesday, 2026-08-18 15:30 PDT. From preliminary analysis, the issue was triggered due to a recent change which caused the permission mismatch, our Engineering team has rolled out the fix to mitigate the impact. We thank you for your patience while we worked on resolving the issue. **Symptoms** Workspace Admins may have experienced permission errors when accessing Classroom’s web homepage. Remaining Classroom functionality remained unaffected. The Classroom Mobile App and the Classroom API were unaffected by the issue. **Workaround** None as the issue is resolved

**Summary** [MITIGATED] Google SecOps customers in the me-west1 region may have seen elevated latencies, and errors in Search queries, Dashboards and Rule execution. **Description** The issue affecting increased Search query latency and error rates for Google SecOps in me-west1 has been mitigated as of Sunday, 2026-08-16 18:00 PDT. Our engineers mitigated the issue by load shedding SecOps Curated Rules. Custom rules are not impacted. We will backfill all impacted curated rules through the remainder of the week. We thank you for your patience while we worked to mitigate the issue. **Diagnosis / Customer Symptoms** Impacted customers in the me-west1 region may have seen elevated latencies in Search queries and Dashboard visualization, and errors in Rule execution. **Workaround** This issue is mitigated.

**Description:** We were experiencing an issue with Google SecOps beginning on Friday, 2026-08-14 05:04 PDT. This has been confirmed due to an upstream (3rd party) Proofpoint Service outage. https://proofpoint.my.site.com/community/s/proofpoint-current-incidents The issue has been mitigated as of Friday, 2026-08-14 7:25 PDT once the upstream service has recovered. Google SecOps will backfill any missing data for the impacted duration. We apologize to all who were affected by the disruption. **Symptoms:** Google SecOps customers were experiencing ingestion failure with the 3P Proofpoint API in all regions. **Workaround:** None as the issue has been mitigated.

**Title** Some Google SecOps customers may have experienced missing data for UEBA metrics. **Description** The issue with Google Google SecOps has been mitigated for all affected customers as of Friday, 2026-08-14 09:34 US/Pacific. From preliminary analysis, the issue was triggered by elevated data processing volumes and localized infrastructure resource constraints that led to processing delays in the analytics pipeline. Our engineers mitigated the issue by scaling up the system resource capacity, optimizing pipeline data processing, and segmenting workloads to prevent processing bottlenecks. We thank you for your patience while we worked on mitigating the issue. **Symptoms** Affected US customers may have had metrics-based rules failing to return detections and missing data for UEBA metrics. Automatic reprocessing may result in new detections dating back to the start of the incident. **Workaround** None as the issue is now mitigated.