Yandex Cloud experienced a major incident on June 23, 2025 affecting Compute Cloud and ru-central1-b, lasting 10h 29m. The incident has been resolved; the full update timeline is below.
Affected components
Update timeline
- investigating Jun 23, 2025, 09:03 PM UTC
We noticed a partial unavailability of Compute services in Yandex Cloud. Currently, there are problems with creating, deleting, and mounting disks. Previously created virtual machines continue to work normally. The developers are already aware of it and are fixing it.
- identified Jun 24, 2025, 04:17 AM UTC
• Current Status: Most of the existing disks are operating normally (only a few disks have been affected; developers have taken measures to minimize the risk of this list growing). In the zones ru-central1-a and ru-central1-d, all services are functioning normally. • Current Impact on Services: Compute: Currently, it is not possible to perform any operations with VMs, instance groups, or network disks located in zone ru-central1-b. MDB: Currently, it is not possible to perform any operations with clusters that have network disks in zone ru-central1-b, including adding new hosts. MDB maintenance operations have been paused. K8S: Currently, it is not possible to perform any operations with node groups in zone ru-central1-b. Autoscaling in zone ru-central1-b is unavailable. • What We Are Doing Now: The NBS service team is working on restoring functionality for disk-related operations. • Our Recommendations: Compute: If virtual machines were affected, we recommend restoring them from a snapshot in another zone, provided there is a backup created via Snapshot or Cloud Backup. MDB: Avoid performing any modifying operations on hosts within clusters in zone ru-central1-b. If nodes in zone ru-central1-b have been affected, consider creating additional replicas in other zones. K8S: If you have node groups in zone ru-central1-b and are concerned about insufficient capacity during peak load, we recommend proactively switching to fixed zonal node groups in other zones without editing the node group in zone ru-central1-b. • ETA for Resolution: At this time, we cannot provide a clear estimate — however, it will certainly take no less than 2 hours. • Next Update: At 09:00 MSK.
- identified Jun 24, 2025, 06:23 AM UTC
• Current status : We are stabilizing the recovery of previously affected disks, VMs, and MDB hosts. Limited compute operations have been enabled. • Current impact on services : Possible delays in completing certain operations in the ru-central1-b zone. • ETA : 1 hour.
- resolved Jun 24, 2025, 07:12 AM UTC
At 10:00 Moscow time, the problem was completely fixed, and the Cloud services are now operating normally. We will tell you about the reasons for the incident later.