Elastic Cloud: Degraded availability for some Elastic Cloud Hosted and Serverless deployments in GCP europe-west2 (London)

MajorStatus: resolvededitedStarted 2026-10-20 06:51 UTCResolved 2026-10-20 21:54 UTC (15 h)8 updatesstspg.io

Summary

Elastic reported major degraded availability or connectivity for some Elastic Cloud Hosted and Serverless deployments in one GCP europe-west2 (London) availability zone, with possible regional monitoring/logging delays. The incident started at 2026-10-20 06:51 UTC (effects reported from approximately 06:15 UTC) and remained open when archived, open for 0 min at the last update.

Machine-written from the archived incident (Sol). Check the timeline before relying on it.

Part of an outage event

Google Cloud europe-west2 outage, Oct 20, 2026 · 19 vendors, 19 incidents

Elastic Cloud’s incident blames Google Cloud as the cause. (hop 1, posted +43 min vs Google Cloud’s own post)

“…Degraded availability for some Elastic Cloud Hosted and Serverless deployments in GCP europe-west2 (London) The infrastructure incident at our cloud provider affecting availability zone europe-west2-b…”

Swipe sideways to see the whole diagram.

Elastic Cloud is outlined in red. Groups show up to a few vendors each; the event page lists every incident.

Mermaid source

flowchart LR
  root["Google Cloud europe-west2<br/>posted 06:08 UTC"]:::root
  before["Posted before Google Cloud did<br/>1 vendor, 1 blamed Google Cloud<br/>JFrog"]:::blames
  root --> before
  h1["Within an hour<br/>4 vendors, 4 blamed Google Cloud<br/>Aiven, Northflank, Elastic Cloud, dbt Labs"]:::blames
  root --> h1
  h4["1 to 4 hours later<br/>4 vendors, 4 blamed Google Cloud<br/>MongoDB Atlas, Sourcegraph, CockroachDB, ClickHouse Cloud"]:::blames
  root --> h4
  later["Later<br/>2 vendors, 1 blamed Google Cloud<br/>Grafana Cloud, Confluent"]:::blames
  root --> later
  me["Elastic Cloud (this incident)<br/>posted +43 min"]:::me
  h1 --- me

Full event: timeline, evidence and all vendors →

Detected automatically from incidents that started together and named the same provider. A link means one vendor’s incident named another, not a confirmed cause.

Timeline of updates

investigating2026-10-20 06:51 UTC
We are investigating an issue affecting one availability zone in the GCP europe-west2 (London) region. Starting at approximately 06:15 UTC, some Elastic Cloud Hosted and Serverless deployments with capacity in this zone may experience degraded availability or connectivity. Monitoring and logging for deployments in the region may also be delayed.
Deployments in other zones and regions are not affected. Our engineers are actively working on the issue, and we are in contact with our cloud provider.
identified2026-10-20 07:56 UTC
Our cloud provider has confirmed an infrastructure incident affecting a single availability zone (europe-west2-b) in the GCP europe-west2 (London) region, causing network connectivity loss and resource unavailability in that zone. Elastic Cloud Hosted deployments and Elastic Serverless projects with resources in the affected zone may be unavailable or experience degraded performance.
We have taken steps to avoid placing new Serverless projects in the affected zone, and we are working to restore services that depend on it. Reduced capacity in the region may delay scaling and the creation of new resources.
We do not yet have an estimated time for recovery from our cloud provider. We are working closely with them and will provide the next update within an hour.
identified2026-10-20 09:15 UTC
The infrastructure incident at our cloud provider affecting availability zone europe-west2-b in the GCP europe-west2 (London) region is ongoing.
Elastic Cloud Hosted: Most deployments with resources in the affected zone remain unavailable or degraded. We are seeing early, limited signs of recovery, and a small number of the initially affected deployments are recovering. We are continuing our mitigation work and will share more as recovery progresses.
Elastic Serverless: We have taken steps to avoid placing new projects in the affected zone, and we are now rebalancing existing projects to other availability zones. We are seeing signs of recovery - some projects remain unavailable or degraded in the meantime.
Reduced capacity in the region may delay scaling and the creation of new resources. We do not yet have an estimated time for full recovery from our cloud provider. We are working closely with them and will provide the next update by 10:15am UTC.
identified2026-10-20 10:32 UTC
The infrastructure incident at our cloud provider affecting availability zone europe-west2-b in the GCP europe-west2 (London) region is ongoing. Elastic Cloud Hosted deployments and Elastic Serverless projects with resources in the affected zone may remain unavailable or degraded.
Our teams are continuing to work on mitigation and recovery, and we are working closely with our cloud provider. We do not yet have an estimated time for full recovery.
We will provide the next update by 12:00 UTC, or sooner if there is a significant change.
identified2026-10-20 12:24 UTC
The infrastructure incident at our cloud provider affecting availability zone europe-west2-b in the GCP europe-west2 (London) region is ongoing. We are seeing slight signs of recovery, both from our cloud provider and from our own mitigation work.
Elastic Cloud Hosted: Some of the affected deployments are recovering. Customers whose plan changes or other operations failed during the incident are advised to retry them from the Elastic Cloud console. Operations that depend on the affected zone may take longer than usual, or fail again, until recovery progresses further. Some deployments may remain unavailable or degraded.
Elastic Serverless: Some projects may remain unavailable or degraded.
identified2026-10-20 14:15 UTC
The infrastructure incident at our cloud provider affecting availability zone europe-west2-b in the GCP europe-west2 (London) region is recovering. Our cloud provider reports recovery of services for most workloads in the region, and we are seeing progress on our side as the affected zone comes back.
Elastic Cloud Hosted: An increasing number of affected deployments are recovering. Customers whose plan changes or other operations failed during the incident are advised to retry them from the Elastic Cloud console. Some deployments may still be unavailable or degraded, and some may need additional recovery steps that our Support team will work through case by case. If your deployment is still unhealthy, please contact Support.
Operations may take longer than usual while capacity is restored.
identified2026-10-20 17:27 UTC
The infrastructure incident at our cloud provider affecting availability zone europe-west2-b in the GCP europe-west2 (London) region has been resolved. We are continuing to work towards full recovery of our services.
Elastic Cloud Hosted: An increasing number of affected deployments are recovering. Customers whose plan changes or other operations failed during the incident are advised to retry them from the Elastic Cloud console. Some deployments may still be unavailable or degraded, and some may need additional recovery steps that our Support team will work through case by case. If your deployment is still unhealthy, please contact Support.
Operations may take longer than usual while capacity is restored.
resolved2026-10-20 21:54 UTC
The infrastructure incident at our cloud provider affecting availability zone europe-west2-b in the GCP europe-west2 (London) region has been resolved. Engineering has completed recovery of infrastructure running in the affected availability zone.
Elastic Cloud Hosted: Customers whose plan changes or other operations failed during the incident are advised to retry them from the Elastic Cloud console. Some deployments may still be unavailable or degraded, and may need additional recovery steps that our Support team will work through case by case. If your deployment is still unhealthy, please contact Support.

Changes Rewindex caught on this incident

Archive proof

Rewindex commits each version of an incident it captures to a daily checkpoint, chains it to the day before, and has the checkpoint timestamped by FreeTSA and DigiCert.

How the archive is checked, and what it cannot prove.

Rewindex captured this after the last checkpoint; the next run (00:41 UTC) commits it.

Impact, status and times are the vendor’s own, as last archived. View on stspg.io (opens in new tab).

Elastic Cloud profile Recent Elastic Cloud incidents Markdown JSON