Notice history

Console

99.90% uptime

Mar 2024100.0% uptime

Apr 202499.70% uptime

May 2024100.0% uptime

Infrastructure

99.72% uptime

Mar 2024100.0% uptime

Apr 202499.15% uptime

May 2024100.0% uptime

Zones

100.0% uptime

dev.aws-us-east-1c

100.0% uptime

Mar 2024100.0% uptime

Apr 2024100.0% uptime

May 2024100.0% uptime

dev.gcp-us-central1-f

100.0% uptime

Mar 2024100.0% uptime

Apr 2024100.0% uptime

May 2024100.0% uptime

perf.aws-us-east-1c

100.0% uptime

Mar 2024100.0% uptime

Apr 2024100.0% uptime

May 2024100.0% uptime

test.aws-us-east-1c

100.0% uptime

Mar 2024100.0% uptime

Apr 2024100.0% uptime

May 2024100.0% uptime

test.gcp-us-central1-f

100.0% uptime

Mar 2024100.0% uptime

Apr 2024100.0% uptime

May 2024100.0% uptime

staging.aws-us-east-1c

100.0% uptime

Mar 2024100.0% uptime

Apr 2024100.0% uptime

May 2024100.0% uptime

staging.gcp-us-central1-f

100.0% uptime

Mar 2024100.0% uptime

Apr 2024100.0% uptime

May 2024100.0% uptime

prod.aws-us-east-1c

100.0% uptime

Mar 2024100.0% uptime

Apr 2024100.0% uptime

May 2024100.0% uptime

prod.aws-us-west-2a

100.0% uptime

Mar 2024100.0% uptime

Apr 2024100.0% uptime

May 2024100.0% uptime

prod.aws-eu-west-1a

100.0% uptime

Mar 2024100.0% uptime

Apr 2024100.0% uptime

May 2024100.0% uptime

prod.ap-northeast-1a

100.0% uptime

Mar 2024100.0% uptime

Apr 2024100.0% uptime

May 2024100.0% uptime

prod.gcp-europe-west3-b

100.0% uptime

Mar 2024100.0% uptime

Apr 2024100.0% uptime

May 2024100.0% uptime

prod.gcp-us-central1-f

100.0% uptime

Mar 2024100.0% uptime

Apr 2024100.0% uptime

May 2024100.0% uptime

Enclave

100.0% uptime

AWS

100.0% uptime

Mar 2024100.0% uptime

Apr 2024100.0% uptime

May 2024100.0% uptime

GCP

100.0% uptime

Mar 2024100.0% uptime

Apr 2024100.0% uptime

May 2024100.0% uptime

May 2024

No notices reported this month

Apr 2024

Resolved
April 26, 2024 at 14:07
Resolved
April 26, 2024 at 14:07
This incident has been resolved.
Monitoring
April 26, 2024 at 13:09
Monitoring
April 26, 2024 at 13:09
A problem related to Google login was identified and has been remedied. Users will be asked to approve Google login when logging in the first time. Currently monitoring issue resolution.

Resolved
April 25, 2024 at 11:52
Resolved
April 25, 2024 at 11:52
The metrics issue is fixed in vespa-8.336.22 that released today.
Identified
April 24, 2024 at 14:17
Identified
April 24, 2024 at 14:17
We have detected a bug in the vespa-8.334.22 release that is preventing metrics to be retrieved using the /prometheus/v1 API.
Please reach out to us if you have been upgraded and are using this API.

Resolved
April 23, 2024 at 07:43
Resolved
April 23, 2024 at 07:43
We tested new deployments and it is working correctly.
Investigating
April 23, 2024 at 07:26
Investigating
April 23, 2024 at 07:26
We are investigating deployment related issues for applications using model url where the url points to Huggingface model hub.

Resolved
April 02, 2024 at 12:33
Resolved
April 02, 2024 at 12:33
This incident has been resolved.
Identified
April 02, 2024 at 12:22
Update
April 02, 2024 at 12:22
This affects all tenants which have an invoice created at August 2023 or earlier.
Identified
April 02, 2024 at 06:16
Identified
April 02, 2024 at 06:16
We are continuing to work on a fix for this incident.

Users will see "Unexpected error occurred"

Mar 2024

Resolved
March 02, 2024 at 01:45
Resolved
March 02, 2024 at 01:45
This incident has been resolved.
Monitoring
March 02, 2024 at 01:28
Monitoring
March 02, 2024 at 01:28
The fix has been pushed out to production, and the system stabilizes. We will continue to monitor for some time to ensure everything is working as expected.
Identified
March 02, 2024 at 00:47
Update
March 02, 2024 at 00:47
Fully rolling out the fix to production is ongoing, but it is taking longer than anticipated. We will report back within the hour with another update.
Identified
March 01, 2024 at 23:36
Update
March 01, 2024 at 23:36
We are currently rolling out a fix that is expected to resolve this issue. The rollout is estimated to take 1 hour.
Identified
March 01, 2024 at 22:40
Update
March 01, 2024 at 22:40
We are continuing to implement a fix. We will provide another update within 1 hour.
Identified
March 01, 2024 at 17:55
Identified
March 01, 2024 at 17:55
We have identified the underlying cause of the issue and are currently implementing a fix.

Mar 2024 to May 2024