Hosting / Cloud / DigitalOcean
DigitalOcean
OPERATIONALSince Apr 2026 · 50 incidents · status.digitalocean.com · checked just now
GradeFLast 90 days
FPRODBSHIP
Admitted uptime
Time not covered by a Sev 1 the provider posted itself. A best case.Incidents
Everything posted on the status page except scheduled maintenance.Sev 1 downtime
Total minutes of Sev 1 incidents, as posted.Median fix
Median time to resolve. Half of incidents were fixed faster.Longest
Longest single incident, start to resolved.Since last
Time since the last counted incident was resolved.By area
AProduction2INCIDENTS1h 27mAFFECTED
2INCIDENTS
1h 27mAFFECTED
Your users are hit: apps, APIs, databases, inference
Worst, 30d
Most hit
Worse. 36 in the last 6 months, 2 in the 6 before.Global1
Kubernetes - Global1
Bangalore1
BLR11
A+Shipping3INCIDENTS1h 35mAFFECTED
3INCIDENTS
1h 35mAFFECTED
You can't deploy, build or manage: CI, CLI, dashboard, auth, billing
Worst, 30d
Most hit
Worse. 18 in the last 6 months, 0 in the 6 before.Global2
App Platform - Global1
VPC - Global1
Bangalore1
CleanSev 3–4Sev 1–2No data
What it costs
One small production web app, per month
512 MB app on all month, 1M requests, 100 GB out, commercial use, one seat. Cheapest plan that runs it.App Platform, shared 512 MB2 of 8 cheaper · Cloudflare: cheaper, same grade
$6/mo
apps-s-1vcpu-0.5gb (includes 50 GiB transfer)$5
50 GiB extra transfer at $0.02/GiB$1
docs.digitalocean.com · checked Oct 22, 2026 · Wrong price?
Trend, last 12 months
Worse. 48 in the last 6 months, 2 in the 6 before.
Severity mix
Sev 1 · Lights outProd site, API or database down, or data loss0
Sev 2 · BleedingProd degraded or partly down2
Sev 3 · Can't shipCan't deploy, build or manage it2
Sev 4 · PapercutDocs, status page, slow dashboard0
When it breaks
Start times, last 12 months, UTC.
Mon
Tue
Wed
Thu
Fri
Sat
Sun
0006121823
What breaks
Global15 incidents
Managed Databases - Global7 incidents
Agent Runtime6 incidents
Inference6 incidents
Agentic Inference Cloud - Inference6 incidents
App Platform - Global5 incidents
Communication
Updates each
Status page updates per incident, on average.Update gap
Median time between status page updates during an incident.Postmortems
Sev 1–2 incidents with a published write-up.Incident history
Show all 50Oct 13, 20260mSEV 3
App Platform DeploymentsFrom 04:34 to 12:15 UTC, DigitalOcean App Platform customers could not reliably deploy new apps or scale existing ones because a software update stopped containers starting on newly provisioned nodes. Running applications were unaffected. Engineering rolled back the update and restored the nodes, and operations have recovered.AI-graded · Global +1
Why this grade
- RULES · SEV 2
Sev 2 because App Platform - Global had degraded performance - CLAUDE · SEV 3 · UNCLEAR · MEDIUM CONFIDENCE
App Platform deployments and scaling failed for about 7.7 hours; already-running apps were unaffected. - Claude Haiku 5.5 · prompt v5 · Oct 22, 2026 · Raw record
1 update
- 17:09 UTC · resolved
Between 04:34 and 12:15 UTC, customers experienced service interruptions affecting App Platform deployment operations. During this window, customers may have been unable to deploy new applications or scale existing deployments. Applications already running prior to the incident were unaffected and continued to operate normally. The disruption was caused by a software update that prevented application containers from starting on newly provisioned infrastructure nodes. Our Engineering team rolled back the update and restored the affected nodes. App Platform deployment and scaling operations have recovered and are operating normally. We sincerely apologize for any inconvenience this caused. If you continue to experience any issues, please open a support ticket and our team will be happy to assist you.
Oct 11, 20261h 27mSEV 2
DNS Resolution for Managed KubernetesManaged Kubernetes clusters in multiple regions intermittently failed to resolve external domain names from 22:01 to 23:29 UTC on October 11. Applications on affected clusters were impacted. DigitalOcean's engineering team implemented a fix and resolved the issue; no cause was given in the updates.AI-graded · regional · Global +1
Why this grade
- RULES · SEV 2
Sev 2 from the incident title (no components listed) - CLAUDE · SEV 2 · REGIONAL · MEDIUM CONFIDENCE
Intermittent external DNS lookup failures hit apps on Managed Kubernetes clusters in multiple regions for about 90 minutes; not a full outage. - Claude Haiku 5.5 · prompt v5 · Oct 22, 2026 · Raw record
3 updates
- 22:01 UTC · investigating
Our Engineering team is investigating an issue causing intermittent external DNS lookup failures for Managed Kubernetes clusters in multiple regions. Applications running on affected clusters may intermittently fail to resolve external domain names. We apologize for the inconvenience and will provide further updates as more information becomes available. - 22:54 UTC · monitoring
Our Engineering team has implemented a fix to address the intermittent external DNS lookup failures affecting Managed Kubernetes clusters in multiple regions. We are currently monitoring the results to ensure the issue is fully resolved. We will provide another update as soon as the issue is confirmed to be resolved. - 23:29 UTC · resolved
Our Engineering team has resolved the external DNS resolution failures affecting Managed Kubernetes across multiple regions. Applications running on Managed Kubernetes can now resolve external domain names. We sincerely apologize for any inconvenience this disruption may have caused to your operations. If you continue to experience problems, please open a ticket with our Support team: https://cloudsupport.digitalocean.com/s/
Oct 5, 20261h 35mSEV 3
VPC Networking AvailabilityDigitalOcean VPC networking operations failed or were delayed from about 08:48 to 10:29 UTC on October 5, 2026. Creating or deleting VPC peerings, VPC-native DOKS clusters, Private Network Connections, routes and subnets was affected, and adding cluster members too. Existing VPC resources and connectivity stayed unaffected. A fix cleared pending operations and the incident was resolved.AI-graded · Global +1
Why this grade
- RULES · SEV 2
Sev 2 because VPC - Global had degraded performance - CLAUDE · SEV 3 · GLOBAL · MEDIUM CONFIDENCE
Creating and deleting VPC peerings, DOKS clusters, PNCs, routes and subnets failed or was delayed for about two hours; existing networking stayed up. - Claude Haiku 5.5 · prompt v5 · Oct 22, 2026 · Raw record
3 updates
- 10:38 UTC · identified
Our Engineering team identified a disruption affecting VPC Networking operations that began at approximately 08:48 UTC. During this time, customers may have experienced delays or failures when creating or deleting VPC peerings, VPC Native DOKS clusters, or Private Network Connections (PNCs), as well as when adding cluster members. Creating routes and subnets may also have been affected. Operations are now returning to normal, and our Engineering team is monitoring the affected systems to ensure continued stability. Existing VPC resources and network connectivity remain unaffected. We will provide another update as soon as more information becomes available. - 11:02 UTC · monitoring
Our Engineering team has implemented a fix for the VPC Networking disruption. Customers should now be able to create and delete VPC peering connections, subnets, and routes as expected. Previously pending operations have been cleared, and VPC Networking operations are returning to normal. Our Engineering team is monitoring the affected systems to ensure continued stability and verify that operations remain healthy. We appreciate your patience and will provide another update once normal operation has been fully confirmed. - 12:13 UTC · resolved
Our Engineering team fully resolved the VPC Networking disruption as of 10:29 UTC. Customers can now create and delete VPC peering connections, subnets, and routes as expected. Following the recovery, we monitored the affected systems and confirmed that VPC Networking operations remain stable. We apologize for any inconvenience this disruption may have caused. If you continue to experience unexpected behavior, please open a ticket with our Support team for further assistance.
Oct 3, 20260mSEV 2
A Network Disruption in BLR1 Region Impacted Multiple Products (Resolved)A networking disruption in DigitalOcean's BLR1 region, caused by failed upstream connectivity paths and resulting link saturation, degraded connectivity, latency and intermittent errors across multiple products from 11:59 to 13:02 UTC on October 3, 2026. Services returned to normal after routing was restored with upstream providers. Users still seeing issues were asked to open a support ticket.AI-graded · regional · Bangalore +9
Why this grade
- RULES · SEV 2
Sev 2 because App Platform - Bangalore had degraded performance - CLAUDE · SEV 2 · REGIONAL · HIGH CONFIDENCE
Networking disruption in BLR1 caused degraded connectivity, latency and intermittent errors for apps, databases and control panel for about 71 minutes. - Claude Haiku 5.5 · prompt v5 · Oct 22, 2026 · Raw record
1 update
- 14:51 UTC · resolved
From 11:59 UTC to 13:02 UTC on October 3, 2026, a networking disruption in our BLR1 region affected multiple products, including Monitoring, App Platform, Managed Databases, Functions, Load Balancers, Spaces, and the Cloud Control Panel. During this period, some users experienced degraded connectivity, increased latency, or intermittent errors when accessing resources in the region. Multiple network paths operated by our upstream connectivity providers were unavailable, including redundant paths intended to maintain connectivity during a disruption. Traffic shifted to a remaining link with insufficient capacity to handle the full load, resulting in network saturation and the connectivity issues described above. Our Engineering and Network teams worked closely with our upstream providers to restore normal routing and connectivity. All affected services have since returned to normal operation. We apologize for the disruption and its impact on your work. If you continue to experience unexpected behavior, please open a support ticket so our team can investigate and assist you.
Sep 16, 202611h 21mSEV 4
Support Portal Service DisruptionDigitalOcean's Support Portal was inaccessible and customers could not create or review support tickets from about 08:06 to 13:41 UTC on September 16, 2026, caused by an upstream third-party disruption. Customers were directed to a contact form as a workaround. Support responses were also delayed. The issue was resolved after the upstream provider applied a fix.AI-graded · Support Center
Why this grade
- RULES · SEV 4
Sev 4 because Support Center had degraded performance - CLAUDE · SEV 4 · UNCLEAR · HIGH CONFIDENCE
Support Portal and ticket creation were inaccessible for hours due to a third-party disruption; core product and apps were not described as affected. - Claude Haiku 5.5 · prompt v5 · Oct 22, 2026 · Raw record
3 updates
- 09:48 UTC · investigating
Our Support Portal is currently experiencing issues due to a third-party service disruption impacting our systems. During this time, customers may be unable to access the Support Portal or create new support tickets for their concerns. Existing support requests may also experience delayed responses from our Support team. As a workaround if you're unable to access the Support Portal or need to create a new support ticket, please submit your request via Support Contact form: https://www.digitalocean.com/company/contact/support. We apologize for the inconvenience and appreciate your patience while we work to resolve the issue. We'll provide another update as soon as we have more information. - 14:07 UTC · monitoring
The Support Portal and ticket creation are now accessible. Our upstream provider has applied a fix, and we've verified ticket creation and review are working as expected. We'll continue monitoring for the next 2 hours to confirm full stability and will post a final update once the incident is closed. If you're still unable to access the portal, please use our Support Contact form as a backup: https://www.digitalocean.com/company/contact/support We apologize for the disruption and appreciate your patience. - 21:09 UTC · resolved
From 08:06 UTC to 13:41 UTC, users may have experienced issues accessing the Support Portal, creating new support tickets, or reviewing existing support requests. Our Engineering team has confirmed the full resolution of the issue affecting the Support Portal following a fix from our upstream provider. We have verified that the Support Portal, ticket creation, and ticket review are now operating normally. If you continue to experience problems, please open a ticket with our support team. We apologize for any inconvenience and appreciate your patience.
Sep 9, 20261h 38mSEV 2
Power Degradation impacting GPU Performance in ATL1Part of DigitalOcean's ATL1 datacenter lost power redundancy, reducing available capacity. GPU Droplet workloads may have degraded during high utilization. No server outages were observed. Power redundancy was restored and the incident resolved about 1.5 hours after it started.AI-graded · one location · ATL1 +1
Why this grade
- RULES · SEV 2
Sev 2 from the incident title (no components listed) - CLAUDE · SEV 2 · LOCAL · MEDIUM CONFIDENCE
Reduced power capacity in part of ATL1 may have degraded some GPU workloads for about 1.5 hours; no server outages were observed. - Claude Haiku 5.5 · prompt v5 · Oct 22, 2026 · Raw record
3 updates
- 10:47 UTC · investigating
We are investigating a power issue affecting part of our ATL1 datacenter. Redundant power systems are keeping servers online, and we have not observed any server outages. However, available power capacity is reduced, which may cause degraded performance for some GPU workloads, particularly during periods of high utilization. Our datacenter and infrastructure teams are working to restore full power redundancy. We will provide an update as more information becomes available. We apologize for the inconvenience and appreciate your patience. - 11:32 UTC · monitoring
The power issue affecting part of our ATL1 datacenter has been fully resolved. Power redundancy has been restored, and any potential customer impact has been mitigated. We will continue monitoring the environment to ensure continued stability. - 12:25 UTC · resolved
This incident is now resolved. Power redundancy has been fully restored, and we have confirmed that customer impact has been mitigated. We are closing this incident.
Aug 24, 202625h 50mSEV 2
Cloud Control Panel and APIAn auth database migration slowed an authorization query, causing retry storms and cascading timeouts. Control panel and API requests failed in two windows over about 3.5 hours on August 24-25, 2026. Under 2% of accounts were hit, with about 10% average failures. Droplets, networking and volumes were unaffected. Engineers restored service by consolidating traffic and disabling hedging. No data loss occurred.AI-graded · some customers · API +1
Why this grade
- RULES · SEV 1
Sev 1 because the provider reported data loss or exposure - CLAUDE · SEV 2 · SUBSET · HIGH CONFIDENCE
Control panel and public API requests failed for under 2% of active accounts, peaking near 25% errors; Droplets and volumes stayed up. - Claude Haiku 5.5 · prompt v5 · Oct 22, 2026 · Raw record
8 updates
- 17:14 UTC · investigating
Our Engineering team is investigating an issue impacting the DigitalOcean public API and Cloud Control Panel. At this time, users will see elevated 5xx errors for all API requests, including things like creates for various products. Users may also be unable to access cloud.digitalocean.com. We are actively investigating the root cause and will provide updates as soon as more information becomes available. We apologize for the inconvenience and appreciate your patience. - 18:33 UTC · investigating
We are continuing to investigate the issue impacting the DigitalOcean public API and Cloud Control Panel. At this time, we are seeing some improvement in latency/error rates and some users may now be able to access the Cloud Control Panel. Serverless Inference users may currently experience 403 and 503 errors when making API requests or accessing affected services. We will continue to provide updates as more information becomes available. We apologize for the inconvenience and appreciate your patience. - 19:14 UTC · monitoring
Our Engineering team has implemented mitigation measures to address the issue affecting the DigitalOcean public API and Cloud Control Panel. We are seeing requests succeed, and users should now be able to access the Cloud Control Panel and issue/receive API requests normally. We are currently monitoring the situation to ensure that the service has returned to normal operation and remains stable. We appreciate your patience and will provide an update once the issue is fully confirmed as resolved. - 22:27 UTC · investigating
Our Engineering team is investigating a recurrence of the issue impacting the DigitalOcean public API and Cloud Control Panel. This issue does not impact our data plane (i.e. running droplets). Users may experience difficulties accessing the Cloud Control Panel, along with elevated latency and intermittent errors when accessing the public API or Cloud Control Plane. We are actively investigating the issue and working to restore normal service. We will continue to provide updates as more information becomes available. We apologize for the inconvenience and appreciate your patience. - 00:54 UTC · monitoring
Our Engineering team has implemented mitigation measures to address the issue impacting the DigitalOcean public API and Cloud Control Panel. We are seeing improvements, and users should now be able to access the Cloud Control Panel and use the public API normally. We are continuing to monitor the service to ensure it remains stable and will provide further updates as more information becomes available. We appreciate your patience and understanding. - 16:30 UTC · monitoring
Our Engineering team has continued to monitor the health of all services and has observed no recurrence of impact over the past 12+ hours. We will continue to monitor services for a short period to confirm stability before we mark this incident resolved. We understand the impact this incident had for DigitalOcean users and we will publish a postmortem on the status page to provide further details on root cause and mitigation. - 19:04 UTC · resolved
Our Engineering team has confirmed all services remain stable and we will now resolve this incident. Further details on root cause and mitigation will be provided in a postmortem via this status page for users interested in learning more. Thank you for your patience throughout this incident. If you continue to experience any issues, please reach out to Support from within your account - 18:44 UTC · postmortem
## 1. What happened Between 16:56 UTC and 23:09 UTC on August 24, 2026, customers using DigitalOcean’s Cloud Control Panel, Public API, and dependent product management systems experienced elevated request error rates, peaking at 25%, in two distinct windows totaling 3.5 hours of active degradation within a 6-hour span. Running Droplets, network routing, and block storage \(Volumes\) remained fully functional and unaffected throughout the event. No customer data loss occurred. The event was initiated during a planned infrastructure migration of the database layer supporting identity, authentication, and authorization services. The migration introduced increased execution latency for a critical authorization query. In response to the elevated query latency, multiple upstream services initiated automated hedged retries. This secondary request amplification led to queue buildup in excess of the authentication service pool's processing throughput, resulting in cascading request timeouts across the authorization path. To mitigate the initial degradation, engineering teams rerouted authorization traffic onto a single healthy processing path and temporarily disabled hedging for primary callers, successfully restoring service availability. However, upon returning traffic to the standard multipath routing configuration, lingering query latency combined with retry behavior from unhedged callers caused recurrent queue saturation, leading to the second window of degradation. ## 2. Impact * Active customer accounts \(<2%\) experienced one or more API or Control Panel request failures during the event windows. * Aggregate failure rates across both impact windows averaged approximately 10% of authenticated requests, with a peak error rate of 25% during the second window. * Affected management control planes included the Cloud Control Panel, Public API, Kubernetes cluster authentication, Container Registry, and Serverless / AI Inference endpoints. * Data plane components—including active Droplets, network routing, and block storage volumes—maintained 100% availability, as established connections do not depend on the affected authorization control path. There was zero data loss. ## 3. Current state All impacted control plane services have been restored to nominal operational capacity. The database infrastructure migration has been completed. Remediation controls have been validated to ensure system stability against similar query latency scenarios. ## 4. Preventing recurrence To prevent future occurrences and enhance systemic resilience, DigitalOcean has implemented the following technical enhancements: 1. Automated Request Throttling and Circuit Breaking: Deployed automated circuit breakers across upstream services to detect downstream dependency degradation and automatically suppress hedged/retry amplification. Completed a broad architecture audit to ensure retry suppression and circuit breaking are uniformly enforced across all control plane services. 1. Queue Management and Load Shedding: Implemented fast-fail load-shedding mechanisms to prevent request queue saturation during dependency slowness, accompanied by proactive telemetry alerts to identify queue backing prior to customer impact. 1. Graceful Service Degradation: Configured critical authorization components to operate in degraded execution modes utilizing asynchronous, eventually-consistent data replicas during primary database latency events. ## 5. Timeline | **Time UTC** | **Event** | | --- | --- | | 16:56 | A specific authorization query began running significantly slower than its historical baseline. | | 16:58 | Automated monitoring detected abnormal error rates and latency; detected within 5 minutes of impact starting. | | 17:05–18:52 | Operators tuned retry configuration and consolidated requests to a healthy service instance \(first unavailability window closed\). | | 21:30 | Shifting traffic back to the production pattern caused the same saturation problem \(second unavailability window begins\). | | 21:30–23:09 | Teams disabled the retry/amplification behavior across the remaining affected services and added additional read capacity for the slow query. Service was restored to a stable state. |
Aug 23, 20269h 22mSEV 3
Managed Databases CreationUsers could not create Managed Database clusters in NYC1 and NYC3 via the control panel or API from about 05:11 to 14:33 UTC on 23 August. Engineering implemented fixes and monitored stability before resolving. Existing clusters were not described as affected.AI-graded · regional · NYC1 +4
Why this grade
- RULES · SEV 2
Sev 2 because Managed Databases - NYC1 had degraded performance - CLAUDE · SEV 3 · REGIONAL · HIGH CONFIDENCE
Creating Managed Database clusters failed in NYC1 and NYC3 for about nine hours; existing clusters were not described as affected. - Claude Haiku 5.5 · prompt v5 · Oct 22, 2026 · Raw record
4 updates
- 05:11 UTC · investigating
Our Engineering team is investigating an issue with our Managed Database product. At this time, users may experience errors while creating clusters, both via Cloud Control Panel and API requests. We apologize for the inconvenience and will share an update once we have more information. - 07:06 UTC · investigating
We continue to investigate an issue affecting DigitalOcean Managed Databases cluster creation across multiple regions. During this time, users may experience errors when creating Managed Database clusters via the Cloud Control Panel or API. Our engineering team is implementing a mitigation and working to restore normal provisioning. We will provide another update as soon as more information is available. - 11:30 UTC · monitoring
Our Engineering team has implemented the necessary fixes affecting Managed Database cluster creation in the NYC3 and NYC1 regions. Users should now be able to create new Managed Database clusters. We are currently monitoring the situation to ensure that the service has returned to normal operation and remains stable. We appreciate your patience and will provide an update once the issue is fully confirmed as resolved. - 14:33 UTC · resolved
Our Engineering team has resolved the issue preventing cluster creation on Managed Databases in the NYC3 and NYC1 regions. Customers can now create new Managed Databases Clusters normally. Our Engineering team has monitored the environment to ensure stability. We sincerely apologize for any inconvenience this disruption may have caused to your operations. If you continue to experience issues, please open a ticket with our Support team: https://cloudsupport.digitalocean.com/s/
Aug 21, 20261h 53mSEV 2
Container Registry and Spaces AccessibilityDigitalOcean reported that Container Registry image push and pull failed in some regions, and Spaces buckets were hard to reach via the Cloud Control Panel, starting 12:59 UTC on 21 August 2026. A fix was applied around 13:06 UTC and the incident was resolved by 14:52 UTC. The text does not give a root cause.AI-graded · regional · Global +2
Why this grade
- RULES · SEV 3
Sev 3 because Container Registry - Global had degraded performance - CLAUDE · SEV 2 · REGIONAL · MEDIUM CONFIDENCE
Container Registry pushes and pulls failed and Spaces control panel access broke in some regions for about two hours. - Claude Haiku 5.5 · prompt v5 · Oct 22, 2026 · Raw record
3 updates
- 12:59 UTC · investigating
Our Engineering team is currently investigating reports of an issue affecting Container Registry and Spaces buckets in some regions. During this time, customers may experience failures when pushing or pulling container images. Additionally, customers may experience issues accessing Spaces via the Cloud Control Panel, where the page may display "Looks like something went wrong…" Our Engineering team is actively investigating the issue and treating it with priority. We will provide another update as soon as more information becomes available. - 13:06 UTC · monitoring
Our Engineering team has identified the issue affecting Container Registry and Spaces buckets, and a fix has been applied. Spaces accessibility via the Cloud Control Panel should now be restored, and pushing and pulling container images should be back to normal. We are continuing to monitor the results to ensure the issue has been fully resolved and will provide another update once we've confirmed normal service has been restored. - 14:52 UTC · resolved
Our Engineering team has confirmed that the issue impacting Container Registry and Spaces accessibility has been resolved. Spaces accessibility via the Cloud Control Panel is now restored, and pushing and pulling container images is succeeding as expected. Customers who previously encountered these issues should now be able to access Spaces and deploy their container images without further issues. If you continue to experience any problems, please open a ticket with our support team. Thank you for your patience, and we apologize for any inconvenience.
Aug 19, 20268h 25mSEV 2
Major Service Interruption in MKC1An MKC1 region incident affected multiple racks and nodes from about 11:10 to 19:34 UTC on 19 August. GPU Droplets and GPU inference endpoints stayed offline or unreachable, and some DOKS GPU nodes stayed NotReady. Control plane, CPU Droplets, databases and storage were restored by 18:59. The cause was a facility equipment issue; full GPU recovery was still pending at resolution.AI-graded · one location · MKC1 +2
Why this grade
- RULES · SEV 1
Sev 1 from the incident title (no components listed) - CLAUDE · SEV 2 · LOCAL · MEDIUM CONFIDENCE
GPU Droplets and GPU-backed inference in MKC1 went offline across multiple racks for about eight hours; CPU services and the control plane recovered. - Claude Haiku 5.5 · prompt v5 · Oct 22, 2026 · Raw record
5 updates
- 11:10 UTC · investigating
Our Engineering team is currently investigating an issue in the MKC1 region affecting multiple racks and nodes. During this time, customers may experience disruptions to GPU workloads, and Kubernetes (DOKS) worker nodes may enter a NotReady state. Our team is actively working to restore connectivity and bring impacted nodes back online. If you continue to experience issues, please open a support ticket from within your account. - 12:22 UTC · identified
We have identified the root cause of the issue in the MKC1 region affecting multiple racks and nodes. Our Engineering team is actively implementing remediation steps to restore connectivity and bring the impacted nodes back online. During this time, customers may continue to experience disruptions to GPU workloads and Serverless Inference. Kubernetes (DOKS) worker nodes may also remain in a NotReady state, and customers may be unable to reach Kubernetes API endpoints or perform cluster-management operations in affected clusters. We will provide another update as soon as we have more information. - 15:28 UTC · identified
Our Engineering team continues to work on the issue affecting the MKC1 region. We are actively working to restore connectivity and bring the impacted nodes back online. We will provide another update as soon as we have more information. - 18:59 UTC · monitoring
At this time, the regional control plane is fully healthy. CPU Droplets, Managed databases, Load balancers, Block storage and Spaces are operating normally. Droplet create, resize and other management operations are working. Kubernetes (DOKS) control planes are reachable. Our teams are continuing to work with the facility to restore all equipment. GPU Droplets in MKC1 remain offline or unreachable. DOKS GPU worker nodes may remain NotReady, and GPU-backed inference endpoints in this region may be unavailable. We will monitor the regional control plane for a short time and then resolve this incident. GPU customers will receive personalized updates with more information in lieu of this status page. If you have questions about your affected resources, contact support and reference this incident. - 19:34 UTC · resolved
Our Engineering team has confirmed the regional control plane is healthy and CPU Droplets, Managed databases, Load balancers, Block storage, Kubernetes (DOKS) and Spaces are operating normally. GPU Droplets continue to be impacted and our teams are working to restore all nodes. We will communicate with GPU Droplet customers separately via Slack and email with more information and regular updates. Thank you for your patience throughout this incident. If you continue to experience any issues, please open a support ticket from within your account.
Aug 13, 20260mSEV 2
Volume Attach/Detach events in FRA1From 09:50 to 14:30 UTC on Aug 13, FRA1 customers had delays or failures attaching and detaching Block Storage Volumes on Droplets and Managed Kubernetes clusters. Operations were restored, though some residual cleanup of Kubernetes volume attachments is still in progress.AI-graded · regional · FRA1 +1
Why this grade
- RULES · SEV 2
Sev 2 because Volumes - FRA1 had degraded performance - CLAUDE · SEV 2 · REGIONAL · MEDIUM CONFIDENCE
Volume attach and detach operations failed or were delayed in FRA1 for about five hours; other regions were not reported affected. - Claude Haiku 5.5 · prompt v5 · Oct 22, 2026 · Raw record
1 update
- 14:59 UTC · resolved
Between Aug 13, 09:50 UTC and 14:30 UTC, customers in the FRA1 region experienced an issue affecting Block Storage Volumes attachment and detachment operations on Droplets and Managed Kubernetes clusters. During this window, customers may have encountered delays or been unable to attach and detach Block Storage Volumes from their resources. Block Storage Volumes attachment and detachment operations now appear to be functioning normally, and customers should no longer experience issues with these operations. For Managed Kubernetes clusters specifically, some residual cleanup of affected volume attachments may still be needed, and our team is actively working through this. We apologize for any inconvenience this may have caused. If you continue to experience issues with Block Storage Volumes operations, please don't hesitate to open a support ticket for further investigation. Our team will be happy to assist you.
Aug 8, 20266h 03mSEV 2
Account Registration, Droplets, and Related ServicesAcross multiple regions for about six hours, new account registration, Droplet creation, Reserved IPs, snapshots and backups, DOKS cluster operations, autoscaling, and the Droplet console failed. GenAI services were affected, and database clusters got stuck in Creating. The provider fixed the issue and resolved it after monitoring.AI-graded · regional · Global +4
Why this grade
- RULES · SEV 2
Sev 2 because Managed Databases - Global had degraded performance - CLAUDE · SEV 2 · REGIONAL · MEDIUM CONFIDENCE
Account signup, Droplet creation, snapshots and DOKS operations failed across multiple regions for about 6 hours; running workloads were not described as down. - Claude Haiku 5.5 · prompt v5 · Oct 22, 2026 · Raw record
6 updates
- 18:57 UTC · investigating
Our Engineering team is currently investigating reports of an issue affecting new account registration, Reserved IPs, Snapshots, Droplets and Droplet-based services across multiple regions. During this time, customers may be unable to create new accounts, create Droplets, allocate Reserved IPs, or perform Automated Backups and Snapshots operations. Droplet Autoscale scaling operations and DOKS cluster operations are also affected. Our Engineering team is actively investigating the issue and we will provide another update as soon as more information becomes available. - 19:38 UTC · investigating
Our Engineering team is continuing to investigate reports of an issue affecting new account registration, Reserved IPs, Snapshots, Droplets and Droplet-based services across multiple regions. During this time, customers may be unable to create new accounts, create Droplets, allocate Reserved IPs, or perform Automated Backups and Snapshots operations. Droplet Autoscale scaling operations and DOKS cluster operations are also affected. Further investigation has found that GenAI services are also affected due to this issue, customers may also be unable to access the Droplet console, and Database clusters may be stuck in a "Creating" state. Our Engineering team is actively investigating the issue and we will provide another update as soon as more information becomes available. - 20:02 UTC · identified
Our Engineering team has identified the root cause of the issue affecting new account registration, Droplets, Reserved IPs, Snapshots, and DOKS clusters across multiple regions. Customers may experience the following: Unable to create new accounts Unable to create Droplets Unable to allocate Reserved IPs Failures with Automated Backups and Snapshots operations Droplet Autoscale scaling operations not working as expected DOKS cluster operations failing GenAI services impacted Unable to access the Droplet console Database clusters stuck in a "Creating" state Our Engineering team is working on implementing a fix and we will provide another update as soon as more information becomes available. - 22:02 UTC · identified
Our Engineering team continues to work on implementing and rolling out a fix for the issue affecting multiple services across multiple regions, including new account registration, Droplets, Reserved IPs, Automated Backups and Snapshots, Droplet Autoscale, DOKS clusters, GenAI services, the Droplet console, and Database cluster creation. Customers may continue to experience the previously reported service disruptions while remediation efforts remain in progress. We will provide another update as soon as more information becomes available. - 00:31 UTC · monitoring
Our Engineering team has implemented a fix for the issue affecting new account registration, Droplets, Reserved IPs, Snapshots, and DOKS clusters across multiple regions, and is currently monitoring the situation. At this time, customers should no longer experience errors with: New account registration Droplet creation Reserved IP allocation Automated Backups and Snapshots operations Droplet Autoscale scaling operations DOKS cluster operations GenAI services Access to the Droplet console Database cluster creation We will continue to monitor the situation to ensure that all services are stable and functioning as expected. We will post an update as soon as the issue is fully resolved. - 01:01 UTC · resolved
Our Engineering team confirms the full resolution of the issue affecting all impacted services, including new account registration, Droplet Creation, Reserved IPs, Automated Backups and Snapshots, Droplet Autoscale, DOKS clusters, GenAI services, the Droplet Console, and Database cluster creation. We apologize for the inconvenience. If you continue to experience any issues, please open a support ticket from within your account.
Aug 6, 20262h 04mSEV 2
Functions on App PlatformFunctions on App Platform hit an SSL error when App Platform forwarded requests to Functions, causing 504 errors on Functions endpoints and build/deploy failures. Starting 19:01 UTC on 2026-08-06, a fix was deployed around 20:02 and the incident was resolved at 21:05 UTC.AI-graded · some customers · Global +2
Why this grade
- RULES · SEV 2
Sev 2 because App Platform - Global had degraded performance - CLAUDE · SEV 2 · SUBSET · HIGH CONFIDENCE
Functions on App Platform returned 504 errors from an SSL forwarding fault and builds/deploys failed for about two hours; isolated to App Platform Functions. - Claude Haiku 5.5 · prompt v5 · Oct 22, 2026 · Raw record
3 updates
- 19:01 UTC · investigating
Our Engineering team is investigating an issue impacting Functions on App Platform. During this time, users may experience build/deploy failures for Functions components, and requests to Functions endpoints may fail with a 504 error, caused by an SSL error when App Platform attempts to forward requests to Functions. This issue currently appears to be isolated to Functions deployed within App Platform. We apologize for the inconvenience and will share an update once we have more information. - 20:02 UTC · monitoring
Our Engineering team has implemented a fix for the issue affecting Functions on App Platform. Functions builds/deploys and requests to Functions endpoints should now be completing successfully. We are currently monitoring the situation to ensure the service has returned to normal operation and remains stable. We apologize for the inconvenience and will provide a further update once the incident is confirmed resolved. - 21:05 UTC · resolved
Our Engineering team has confirmed that the issue affecting Functions on App Platform has been fully resolved. Functions builds, deploys, and requests to Functions endpoints are all working as expected. The fix implemented earlier was successful, and we are no longer seeing any problems affecting Functions. However, if you continue to experience any issues, please don't hesitate to raise a support ticket for further investigation.
Aug 6, 20260mSEV 2
Multiple Services AvailabilityFrom about 06:42 to 09:08 UTC on Aug 6, write operations failed across DigitalOcean services including Managed Databases, DOKS, Cloud Firewalls, DNS, Spaces, Volumes, and event processing. Customers could not change configuration or provision or scale resources, and event processing was delayed or failed. Services recovered, and the provider gave no cause in the update.AI-graded · Global +7
Why this grade
- RULES · SEV 2
Sev 2 because DNS had degraded performance - CLAUDE · SEV 2 · GLOBAL · MEDIUM CONFIDENCE
Write operations failed across several DigitalOcean services for about two and a half hours; reads and running workloads were not described as affected. - Claude Haiku 5.5 · prompt v5 · Oct 22, 2026 · Raw record
1 update
- 16:33 UTC · resolved
Between Aug 6, 06:42 UTC and 09:08 UTC, customers experienced failures with write operations across multiple DigitalOcean services, including Managed Databases, DOKS, Cloud Firewalls, DNS, Spaces, Block Storage Volumes, and event processing. Customers attempting to update Cloud Firewall rules, modify DNS records, manage object storage operations, provision or scale DOKS clusters and node pools, and make other infrastructure configuration changes experienced failures. These operations returned errors, preventing customers from managing their resources. Additionally, event processing was delayed or failed during this window, which may have impacted the timeliness of resource status updates and notifications. The services have recovered and are now operating normally. Customers should no longer experience issues with write operations, configuration changes, or event processing. We apologize for any inconvenience this may have caused. If you continue to experience issues with any of these services, please don't hesitate to open a support ticket. Our team will be happy to assist you.
Aug 4, 20265h 29mSEV 4
Spaces Cold Storage BillingSpaces Cold Storage customers saw incorrect daily usage and current invoice values from about 16:13 to 21:42 UTC on August 4, 2026. A billing data sync error caused it. The team fixed the sync and reported accurate usage reporting restored. Storage operations were not described as affected.AI-graded · some customers · Global +2
Why this grade
- RULES · SEV 4
Sev 4 because Billing had degraded performance - CLAUDE · SEV 4 · SUBSET · MEDIUM CONFIDENCE
Cold storage customers saw incorrect daily usage and invoice values for about five hours; storage itself was not reported affected. - Claude Haiku 5.5 · prompt v5 · Oct 22, 2026 · Raw record
4 updates
- 16:13 UTC · investigating
Our Engineering team is investigating an issue affecting Spaces Cold Storage billing. During this time, customers with cold storage buckets may see incorrect values reflected in their daily usage and current invoices. We apologize for the inconvenience and are actively working to resolve the issue. We will provide an update as soon as more information becomes available. - 18:52 UTC · identified
Our Engineering team has identified the issue affecting Spaces Cold Storage billing. The team is actively working on a fix to resolve the issue. We apologize for the inconvenience and will provide another update as soon as more information becomes available. - 20:44 UTC · monitoring
Our Engineering team has implemented a fix for the issue affecting Spaces Cold Storage billing and is currently monitoring the situation. Customers with cold storage buckets should no longer see incorrect values reflected in their daily usage and current invoices. We will post an update as soon as the issue is fully resolved. - 21:42 UTC · resolved
As of 21:06 UTC, our Engineering team has resolved the issue affecting Spaces Cold Storage billing. An error in our billing processing system caused incorrect values to be reflected in daily usage and current invoices for customers with cold storage buckets. Our team identified and corrected an issue with the billing data sync, ensuring accurate usage reporting. If you continue to experience any issues, please open a ticket with our Support team. We apologize for any inconvenience this may have caused.
Aug 3, 20264h 02mSEV 3
Cloud Control Panel AccessSome customers saw intermittent errors and 'mTLS verification failed' messages when accessing the Cloud Control Panel from 09:36 to 13:30 UTC on August 3. Expired internal certificates were renewed and access was restored. Customer apps were not reported affected.AI-graded · some customers · Cloud Control Panel
Why this grade
- RULES · SEV 2
Sev 2 from the incident title (no components listed) - CLAUDE · SEV 3 · SUBSET · HIGH CONFIDENCE
Some customers got intermittent errors and mTLS failures in the Cloud Control Panel for about four hours; apps and APIs were not reported affected. - Claude Haiku 5.5 · prompt v5 · Oct 22, 2026 · Raw record
3 updates
- 13:58 UTC · investigating
Beginning at 09:36 UTC on August 3, some customers may experience intermittent errors when accessing the DigitalOcean Cloud Control Panel, including an "mTLS verification failed" message. Our engineering team is actively investigating. We apologise for the inconvenience this may have caused. We will provide another update as soon as more information is available. If you have any questions related to this issue, please send us a ticket from your cloud support page. https://cloudsupport.digitalocean.com/s/createticket - 16:39 UTC · monitoring
We have implemented mitigation for the issue causing some customers to experience intermittent errors when accessing the DigitalOcean Cloud Control Panel. We are seeing recovery and are monitoring the service closely. We will provide another update once we have confirmed the issue is fully resolved - 17:59 UTC · resolved
Between 09:36 and 13:30 UTC on August 3, some customers experienced intermittent errors while accessing the DigitalOcean Cloud Control Panel. We renewed the affected internal certificates and restored access. The issue is resolved, and the Cloud Control Panel is operating normally. We apologize for the disruption.
Jul 29, 202612h 19mSEV 2
Response Degradation Impacting Kimi-K3Kimi-K3 on DigitalOcean's Agentic Inference Cloud returned empty or broken responses, including repeated characters, from July 29 17:56 UTC until resolved July 30 06:15 UTC. Engineering identified and fixed the issue; the update gives no further cause detail.AI-graded · some customers · Model Services +1
Why this grade
- RULES · SEV 2
Sev 2 because Model Services had degraded performance - CLAUDE · SEV 2 · SUBSET · MEDIUM CONFIDENCE
Kimi-K3 model responses were empty or broken, including repeated characters, for about 12 hours; other services were not described as affected. - Claude Haiku 5.5 · prompt v5 · Oct 22, 2026 · Raw record
3 updates
- 17:56 UTC · investigating
We are currently investigating this issue. - 21:41 UTC · investigating
Our Engineering team is investigating reports of empty or broken responses impacting Kimi-K3. At this point, users may experience degraded response quality, specifically empty or broken outputs (including repeated characters), when querying the Kimi-K3 service. We apologize for the inconvenience and will share an update once we have more information. - 06:15 UTC · resolved
Our Engineering team has resolved the issue causing empty or broken responses from Kimi-K3. If you continue to experience any problems, please open a ticket with our Support team. We apologize for any inconvenience this may have caused.
Jul 27, 202620h 53mSEV 2
Agent Platform Requests Returning HTTP 500 ErrorsAgent Platform requests returned HTTP 500 errors for about 21 hours; the update text does not say how many customers were hit.AI-graded · Agent Runtime +1
Why this grade
- RULES · SEV 1
Sev 1 because Agent Runtime had a partial outage - CLAUDE · SEV 2 · UNCLEAR · MEDIUM CONFIDENCE
Agent Platform requests returned HTTP 500 errors for about 21 hours; the update text does not say how many customers were hit. - Claude Haiku 5.5 · prompt v5 · Oct 22, 2026 · Raw record
3 updates
- 18:31 UTC · investigating
We are currently investigating this issue. - 19:44 UTC · identified
The issue has been identified and a fix is being implemented. - 15:24 UTC · resolved
This incident has been resolved.
Jul 24, 20262h 06mSEV 3
Network Connectivity from India to NYCUsers in India on Airtel and BSNL reported latency, packet loss, and intermittent connectivity to DigitalOcean NYC resources. The provider later said impact was limited to Airtel users, from about 07:46 to 10:24 UTC, and that the cause was an internal Airtel network issue, not DigitalOcean's. The issue is resolved.AI-graded · some customers · NYC1 +1
Why this grade
- RULES · SEV 2
Sev 2 because Networking - NYC1 had degraded performance - CLAUDE · SEV 3 · SUBSET · MEDIUM CONFIDENCE
Some users in India on Airtel saw latency and packet loss reaching NYC resources; the provider attributes the cause to Airtel's network. - Claude Haiku 5.5 · prompt v5 · Oct 22, 2026 · Raw record
3 updates
- 10:36 UTC · identified
We have noticed network connectivity issues affecting some users connecting from India to resources in the NYC region. Based on our current investigation, users on Airtel and BSNL have reported increased latency, packet loss, or intermittent connectivity. We apologize for the inconvenience and will provide an update as soon as more information becomes available. - 11:45 UTC · monitoring
We are observing improvements in network connectivity for users in India accessing resources in our NYC region. Our team is monitoring the situation to ensure that the service has returned to normal operation and remain stable. We appreciate your patience and will provide an update once the issue is fully confirmed as resolved. - 12:42 UTC · resolved
Between 07:46 UTC & 10:24 UTC today, some users in India accessing resources in the NYC region may have experienced connectivity issues. The impact was limited to users using Airtel as their ISP. Our investigation determined that the issue was caused by an internal network issue within Airtel and was not related to DigitalOcean network. The connectivity issue now appears to be resolved, and users should no longer experience problems accessing their resources. We apologize for any inconvenience this may have caused. However, if you continue to experience any connectivity issues, please don't hesitate to open a support ticket for further investigation; we'll be happy to assist you further.
Jul 23, 20261h 20mSEV 2
Llama-4-Maverick Model AvailabilityThe llama-4-maverick model returned HTTP 500 errors on Serverless Inference for about 80 minutes; other models were not described as affected.AI-graded · some customers · Inference +1
Why this grade
- RULES · SEV 2
Sev 2 because Inference had degraded performance - CLAUDE · SEV 2 · SUBSET · MEDIUM CONFIDENCE
The llama-4-maverick model returned HTTP 500 errors on Serverless Inference for about 80 minutes; other models were not described as affected. - Claude Haiku 5.5 · prompt v5 · Oct 22, 2026 · Raw record
2 updates
- 11:16 UTC · investigating
Our Engineering team is currently investigating an issue where the llama-4-maverick model is unavailable. Users may experience HTTP 500 errors while using this model with Serverless Inference. We apologize for the inconvenience. Our Engineering team is working with high priority to resolve the issue. Thank you for your patience and understanding. - 12:37 UTC · resolved
This incident has been resolved.
Peers, 90 days
CompareHerokuGrade A+100.00% up0 incidentsMTTR –$7/moNetlifyGrade B100.00% up17 incidentsMTTR 34m~$20/moRenderGrade C100.00% up13 incidentsMTTR 1h 35m$21.25/moVercelGrade C100.00% up23 incidentsMTTR 47m~$20/moDigitalOceanGrade F100.00% up18 incidentsMTTR 4h 02m$6/moFly.ioGrade F99.38% up26 incidentsMTTR 44m$5.69/moCloudflareGrade F100.00% up54 incidentsMTTR 1h 13m~$5/moRailwayGrade F98.31% up27 incidentsMTTR 55m~$12/mo
README badge
DigitalOcean's live grade, for your README.
[](https://downagain.dev/p/digitalocean)