Google Cloud experienced outages today that led to disruptions for many online services. Reports of issues for Google products and others began around 2 PM ET. The company was able to restore function to its own apps, but several other businesses have continued to experience problems for some users.
In an update at 4:16PM ET, Google said, “We have identified the root cause and applied appropriate mitigations. Our infrastructure has recovered in all regions except us-central1. Google Cloud products that rely on the affected infrastructure are seeing recovery in multiple locations. Our engineers are aware of the customers still experiencing issues on us-central1 and multi-region/us and are actively working on full recovery. We do not have an ETA for full recovery.”
Spotify, Discord, Snapchat, Etsy, UPS and OpenAI all experienced a high volume of reports on DownDetector, with some informing users of disruptions. Even the Pokemon Trading Card Game and Pokemon Go weren’t spared issues. Snapchat acknowledged the ongoing issues on its support page. OpenAI has posted that users may have trouble logging in due to “issues affecting multiple external internet providers.” AWS also experienced a higher-than-usual volume of reports on DownDetector during the outage, but Amazon clarified in a statement to Engadget that it has no broad service issues and noted that its AWS Health Dashboard is a better indicator of its current status than DownDetector.
Almost all services have now returned to normal operation. By 5PM ET, Spotify’s main page loaded for our editors and reports of outages on DownDetector had fallen back to close to their baseline. Other platforms like Snapchat and Discord also seemed to be functioning normally for us. Google said at the time that its products were coming back online across multiple regions and that it expected the recovery to be complete “in less than an hour.” However, as of 7:13PM ET, the company noted that several Google Cloud components were still experiencing “residual impact.” Google Cloud Dataflow, Vertex AI Online Prediction and Personalized Service Health are all still somewhat affected, and the company has not provided a timeline for when everything will be back to normal.