What Microsoft, GitHub, Cloudflare, Ubiquiti, Cisco Meraki, Palo Alto Networks, GitLab, OpenAI, Anthropic, and Google post on their public status pages, read every 5 minutes while something is open. Each incident shows what else was happening and what changed in the same products just before.
CloudflareNetwork Performance Issues in Washington, DC datacenter (IAD)resolved 07:44 UTC11 h 8 min
Started 20 Nov 20:35 UTCUpdated 10 h 17 min ago
Network
This incident has been resolved.
2 earlier updates
20 Nov 20:36 UTCMonitoringA fix has been implemented and we are monitoring the results.
20 Nov 20:35 UTCInvestigatingCloudflare is investigating issues with network performance in Washington, DC datacenter (IAD). We are working to analyze and mitigate this problem. More updates to follow shortly.
Around it3 other incidents at the same time · 5 earlier incidents
CloudflareCache Purging Delays in Milanresolved 22:25 UTC1 h 33 min
Started 20 Nov 20:51 UTCUpdated 19 h 36 min ago
CDN Cache Purge
This incident is now resolved.
3 earlier updates
20 Nov 22:03 UTCMonitoringA fix has been implemented and we are currently monitoring the results.
20 Nov 20:55 UTCIdentifiedThe issue has been identified and a fix is being implemented.
20 Nov 20:51 UTCInvestigatingCloudflare single-file cache purging (purge by URL) called via the Dashboard/API is delayed in Milan. We are working to resolve this issue as soon as possible. Until then you may use the Purge Everything feature but do be aware it may cause a surge in traffic to your origin server(s). More updates to follow.
Around it2 other incidents at the same time · 5 earlier incidents
CloudflareCache Purging Delays in Amsterdamresolved 19:41 UTC1 h 41 min
Started 20 Nov 18:00 UTCUpdated 22 h 19 min ago
CDN Cache Purge
This incident has been resolved.
3 earlier updates
20 Nov 19:40 UTCMonitoringA fix has been implemented and we are monitoring the results.
20 Nov 19:40 UTCIdentifiedThe issue has been identified and a fix is being implemented.
20 Nov 18:00 UTCInvestigatingCloudflare single-file cache purging (purge by URL) called via the Dashboard/API is delayed in Amsterdam. We are working to resolve this issue as soon as possible. Until then you may use the Purge Everything feature but do be aware it may cause a surge in traffic to your origin server(s). More updates to follow.
Around it2 other incidents at the same time · 5 earlier incidents
Cloudflare has resolved API and dashboard issues in the EU region.
2 earlier updates
20 Nov 18:38 UTCMonitoringA fix has been implemented and we are monitoring the results.
20 Nov 18:24 UTCInvestigatingCloudflare is investigating issues with Cloudflare Dashboard and related APIs in EU region. These issues do not affect the serving of cached files via the Cloudflare CDN or other security features at the Cloudflare Edge. Customers using the Dashboard / Cloudflare APIs are impacted as requests might fail and/or errors may be displayed.
Around it2 other incidents at the same time · 5 earlier incidents
20 Nov 05:10 UTCIdentifiedThe issue has been identified and a fix is being implemented.
20 Nov 05:00 UTCInvestigatingCloudflare has identified issues with Network Performance in Miami. We are working to analyze and mitigate this problem. More updates to follow shortly.
Around it2 other incidents at the same time · 5 earlier incidents
CloudflareR2 and Durable Objects availability issuesresolved 04:35 UTC1 h 42 min
Started 20 Nov 02:52 UTCUpdated 37 h 26 min ago
Durable ObjectsR2
This incident has been resolved.
2 earlier updates
20 Nov 04:02 UTCMonitoringA fix has been implemented and we are monitoring the results.
20 Nov 02:52 UTCInvestigatingCustomers using R2 and Durable Objects in Eastern North America may be experiencing intermittent errors and failed requests. We are investigating the cause and working to confirm that service availability has stabilized. We will provide updates as more information becomes available.
Around it1 other incident at the same time · 5 earlier incidents
CloudflareObservability ingestion delay and query failuresresolved 21:55 UTC5 h 25 min
Started 19 Nov 16:30 UTCUpdated 44 h 5 min ago
WorkersWorkers Observability
This incident has been resolved.
2 earlier updates
19 Nov 21:23 UTCMonitoringA fix has been implemented and we are monitoring the results.
19 Nov 16:30 UTCIdentifiedCloudflare has identified an issue impacting Observability ingestion and querying. Customers may be seeing delays in new data coming in and increased error rates querying Workers Observability and Cloudflare Traces data. We are working to analyze and mitigate this problem. More updates to follow shortly.
Around it4 other incidents at the same time · 5 earlier incidents
Between November 5, 2026, at 18:02 UTC and November 19, 2026, at 18:05 UTC, GitHub users experienced unexpected expiration of their web browser sessions despite continued activity, requiring them to login. An authentication change introduced an issue that caused web requests to bypass the session activity updates and cookie renewal that normally extend session lifetime. Affected sessions consequently expired when they reached their initial expiration time.We mitigated the incident by deploying a fix to ensure that continued web activity renews session expiration and browser cookies.We are adding monitoring to detect unexpected drops in session renewal activity, helping us catch similar issues sooner and reduce their impact on users.
4 earlier updates
19 Nov 18:17 UTCResolvedThis incident has been resolved. Thank you for your patience and understanding as we addressed this issue. A detailed root cause analysis will be shared as soon as it is available.
19 Nov 18:05 UTCUpdateThe degradation has been mitigated. We are monitoring to ensure stability.
19 Nov 17:43 UTCMonitoringStarting around 18:02 UTC on November 5, GitHub web sessions stopped being renewed based on recent activity, so users were signed out when their sessions expired due to inactivity. These sign-outs were caused by a bug in session renewal, not due to a security incident.We believe we fixed the bug at 05:23 UTC on November 19, and sessions created since then should renew as usual. We’re continuing to monitor the situation.If you had an inactive session from that period, you may still find that you’re signed out when you return to GitHub. If that happens, all you need to do is sign back in.
19 Nov 17:06 UTCInvestigatingWe are investigating reports of impacted performance for some GitHub services.
Around it4 other incidents at the same time · 4 earlier incidents · 1 change in the 14 days before
GitHubDegraded availability for GPT-6 Luna in Copilotlast seen 16:37 UTCunknown
Posted 19 Nov 15:56 UTCUpdated 2d ago
CopilotCopilot AI Model Providers
This incident has been resolved. Thank you for your patience and understanding as we addressed this issue. A detailed root cause analysis will be shared as soon as it is available.
3 earlier updates
19 Nov 16:28 UTCMonitoringThe degradation affecting Copilot AI Model Providers has been mitigated. We are monitoring to ensure stability.
19 Nov 15:57 UTCUpdateWe are experiencing degraded availability for the GPT-6 Luna model in Copilot products and IDE surfaces. This is due to an issue with an upstream model provider. While we work with them to resolve the issue, we recommend choosing another model or selecting 'Fusion' to continue using Copilot.
19 Nov 15:56 UTCInvestigatingWe are investigating reports of degraded performance for Copilot AI Model Providers
Around it2 other incidents at the same time · 4 earlier incidents · 1 change in the 14 days before
CloudflareDurable Objects and D1 – Increased Errorsresolved 13:37 UTC31 min
Started 19 Nov 13:05 UTCUpdated 2d ago
Durable ObjectsD1
This incident has been resolved.
2 earlier updates
19 Nov 13:26 UTCIdentifiedThe issue has been identified and a fix is being implemented.
19 Nov 13:05 UTCInvestigatingCloudflare is investigating an increased level of errors and latency affecting a subset of Durable Objects and D1 customers. Affected customers may see storage operations fail or take longer than usual to complete. Workers that don't use Durable Objects or D1 are not affected. We are working to analyse and mitigate this problem. More updates to follow shortly.
Around it1 other incident at the same time · 5 earlier incidents
The issue affecting claude.ai, the Claude API, Claude Code, and Claude Cowork has been resolved. Impact occurred from 00:56 PT / 08:56 UTC to 01:11 PT / 09:11 UTC.
2 earlier updates
19 Nov 09:22 UTCMonitoringA fix has been deployed for other Claude models and we are monitoring for recovery.
19 Nov 09:10 UTCInvestigatingWe are investigating elevated errors on requests to Claude Mythos 5.2 and Claude Fable 5.2. We will provide an update as soon as possible.
Around it2 other incidents at the same time · 5 earlier incidents
CloudflareCloudflare Access Issueresolved 08:56 UTC2 h 8 min
Started 19 Nov 06:48 UTCUpdated 2d ago
Access
This incident has been resolved.
2 earlier updates
19 Nov 08:32 UTCMonitoringA fix has been implemented and we are monitoring the results.
19 Nov 06:48 UTCIdentifiedCloudflare is investigating an issue with Cloudflare Access. A recent Cloudflare Access release removed the sub claim from service token JWTs, which can cause authentication failures for applications that strictly validate token claims. The change has been reverted and the fix is rolling out globally.
Around it1 other incident at the same time · 5 earlier incidents
CloudflareDegraded connectivity between Europe and Asia Pacificresolved 03:19 UTC4 h 52 min
Started 18 Nov 22:26 UTCUpdated 2d ago
Cache ReserveD1R2
This incident has been resolved.
5 earlier updates and 2 changes ChangeIntel noticed
19 Nov 00:36 UTCMonitoringA fix has been implemented and we are monitoring the results.
18 Nov 23:48 UTCIdentifiedThe issue has been identified and a fix is being implemented.
18 Nov 22:26 UTCInvestigatingCloudflare is investigating degraded connectivity between Europe and the Asia Pacific region. Customers may experience increased errors and latency for requests traversing this path, including requests involving R2, D1, and Cache Reserve. Other Cloudflare services that rely on Europe-to-Asia Pacific connectivity may also be affected. Network teams are working to mitigate the issue and restore normal connectivity. Further updates will be provided as more information becomes available.
18 Nov 22:26 UTCInvestigatingRequests to R2 and D1 from the EU and Asia Pacific regions may experience elevated error rates. We are investigating the issue and working to identify the cause. Further updates will be provided as more information becomes available.
18 Nov 22:26 UTCInvestigatingRequests to R2 from EU and APAC region may experience elevated error rates.
18 Nov 23:51 UTC ChangeIntel noticed a new title; it was "Elevated R2 and D1 error rates in EU and Asia Pacific region"
18 Nov 23:00 UTC ChangeIntel noticed a new title; it was "Elevated R2 error rates in EU and Asia Pacific region"
Around it4 other incidents at the same time · 5 earlier incidents
Claude Meetings (beta) is joining calls normally. Enterprise and Team customers can add Claude to calls. Auto-join is available for all Enterprise customers and some Team customers. We'll continue rolling out auto-join to additional Team customers in the coming days.
8 earlier updates and 1 change ChangeIntel noticed
17 Nov 23:39 UTCUpdateClaude Meetings (beta) is joining calls more reliably, and we are monitoring it. It remains enabled for all Enterprise customers. Team customers can again add Claude to new calls manually, and Auto-join is being restored gradually for Team customers.
17 Nov 02:02 UTCIdentifiedClaude Meetings (beta) saw higher than expected demand today, and Claude was unable to join many calls. We have put mitigations in place and are continuing to monitor and improve join reliability.Claude Meetings is now re-enabled for all Enterprise customers, though Claude may take a little longer than usual to join. Adding Claude to new calls and Auto-join remain paused for Team customers. We will share more updates as we expand capacity and begin restoring the feature for Team customers.
16 Nov 18:10 UTCUpdateClaude may still be unable to join some calls in Claude Meetings (beta), and Auto-join remains paused. Calls already in progress and other Claude features are not affected. We expect this to take some time to fully resolve and will post an update when the status changes.
16 Nov 16:27 UTCUpdateWe have temporarily paused Auto-join while we work on this. Adding Claude to a call by hand is also affected. Calls already in progress are not affected. We will provide another update as soon as possible.
16 Nov 15:12 UTCUpdateWe are continuing to investigate an issue preventing Claude from joining new calls in Claude Meetings (beta).
16 Nov 15:12 UTCUpdateWe are continuing to investigate an issue preventing Claude from joining new calls in Claude Meetings (beta). We have temporarily paused Auto-join while we work on this. Adding Claude to a call by hand is also affected. Calls already in progress are not affected. We will provide another update as soon as possible.
16 Nov 15:12 UTCUpdateWe are investigating reports of degraded performance affecting claude.ai. We will provide an update as soon as possible.
16 Nov 15:10 UTCInvestigatingWe are investigating an issue preventing Claude from joining new calls in Claude Meetings (beta). Calls already in progress are not affected, and core functionality is not impacted. We will provide an update as soon as possible.
19 Nov 02:18 UTC ChangeIntel noticed a new title; it was "Claude unable to join meetings"
Around it6 other incidents at the same time · 5 earlier incidents
Elsewhere at the same time · within 12 hours of its start
18 Nov 20:40 UTCMonitoringA fix has been implemented and we are monitoring the results.
18 Nov 20:35 UTCIdentifiedCloudflare has identified an issue where some customers may experience latency querying the GraphQL API. We are working to analyze and mitigate this problem. More updates to follow shortly.
Around it3 other incidents at the same time · 5 earlier incidents
CloudflareR2 Downloads Stalling in Japanresolved 15:03 UTC1 h 17 min
Started 18 Nov 13:45 UTCUpdated 3d ago
R2
This incident has been resolved.
2 earlier updates
18 Nov 14:40 UTCMonitoringA fix has been implemented and we are monitoring the results.
18 Nov 13:45 UTCInvestigatingCloudflare is aware of, and investigating an issue where R2 Downloads are stalling for users connecting via datacenters in Japan. Further detail will be provided as more information becomes available.
Around it3 other incidents at the same time · 5 earlier incidents
GitHubDegraded Availability for MAI Code 2 Flash in Copilotlast seen 09:34 UTCunknown
Posted 18 Nov 09:00 UTCUpdated 3d ago
CopilotCopilot AI Model Providers
This incident has been resolved. Thank you for your patience and understanding as we addressed this issue. A detailed root cause analysis will be shared as soon as it is available.
5 earlier updates
18 Nov 09:34 UTCUpdateThe issues with our upstream model provider have been resolved, and MAI Code 2 Flash is once again available in Copilot products and IDE surfaces.We will continue monitoring to ensure stability, but mitigation is complete.
18 Nov 09:13 UTCMonitoringThe degradation affecting Copilot AI Model Providers has been mitigated. We are monitoring to ensure stability.
18 Nov 09:13 UTCUpdateWe have been working with the upstream provider and applying mitigations, and are seeing widespread improvement in availability for MAI Code 2 Flash across Copilot products and IDE surfaces.We will continue monitoring.
18 Nov 09:00 UTCUpdateWe are experiencing degraded availability for the MAI Code 2 Flash model in Copilot products and IDE surfaces. This is due to an issue with an upstream model provider. While we work with them to resolve the issue, we recommend choosing another model or selecting ‘Copilot Fusion’ to continue using Copilot.
18 Nov 09:00 UTCInvestigatingWe are investigating reports of degraded performance for Copilot AI Model Providers
Around it4 other incidents at the same time · 4 earlier incidents · 1 change in the 14 days before
18 Nov 08:38 UTCMonitoringA fix has been implemented and we are monitoring the results.
18 Nov 08:22 UTCIdentifiedThe issue has been identified and a fix is being implemented.
18 Nov 08:04 UTCInvestigatingCloudflare is investigating a network disruption across multiple datacenters in India, impacting some Cloudflare services in region. We are working to analyse and mitigate this problem. More updates to follow shortly.
Around it3 other incidents at the same time · 5 earlier incidents
CloudflareNetwork Performance Issues in Parisresolved 04:51 UTC1 h 12 min
Started 18 Nov 03:39 UTCUpdated 3d ago
EuropeNetworkCloud Network Interconnect (CNI)
This incident has been resolved.
4 earlier updates
18 Nov 03:57 UTCMonitoringA fix has been implemented and we are monitoring the results. This incident impacted Cloudflare Network Interconnect (CNI) only.
18 Nov 03:49 UTCIdentifiedWe are continuing to work on a fix for the issue.
18 Nov 03:43 UTCIdentifiedThe issue has been identified and a fix is being implemented.
18 Nov 03:39 UTCInvestigatingCloudflare is investigating issues with Network Performance in Paris, FR. We are working to analyze and mitigate this problem. More updates to follow shortly.
Around it5 other incidents at the same time · 5 earlier incidents
CloudflareErrors and stalled predictions on some modelsresolved 03:23 UTC12 h 20 min
Started 17 Nov 15:02 UTCUpdated 3d ago
Replicate
This incident has been resolved.
4 earlier updates
18 Nov 02:56 UTCMonitoringA fix has been implemented and we are monitoring the results.
17 Nov 21:53 UTCIdentifiedThe issue has been identified and a fix is being implemented. Current impact: predictions on OpenAI models are back to normal. Predictions on other models may still return HTTP 500 errors or stay in a processing state while we continue to work on a fix.
17 Nov 16:32 UTCIdentifiedThe issue has been identified and a fix is being implemented. Current impact: prediction requests for some models may return HTTP 500 errors, and some predictions may stay in a processing state. Customers using the API may also see validation errors on responses.
17 Nov 15:02 UTCInvestigatingWe are currently investigating this issue. Cloudflare is aware of, and investigating, an issue affecting predictions for some models on Replicate. Customers may see prediction requests return HTTP 500 errors, and some predictions may remain in a processing state without completing. Some API responses are also missing version information, which can cause validation errors in client libraries. We are working to understand the full impact and mitigate this problem.
Around it6 other incidents at the same time · 5 earlier incidents
Elsewhere at the same time · within 12 hours of its start
Between 02:31-03:04 UTC on November 18, a subset of customers reaching Mumbai, IN, may have experienced an elevated number of 5xx errors and increased latency. This has been resolved.
Around it5 other incidents at the same time · 5 earlier incidents
CloudflareCloudflare Access Issueresolved 02:39 UTC1 h 29 min
Started 18 Nov 01:10 UTCUpdated 3d ago
Access
This incident has been resolved.
3 earlier updates
18 Nov 02:11 UTCMonitoringA fix has been implemented and we are monitoring the results.
18 Nov 01:22 UTCIdentifiedThe issue has been identified and a fix is being implemented.
18 Nov 01:10 UTCInvestigatingCloudflare is investigating issues with Cloudflare Access. Customers may experience a delay making configuration changes to Access. We are working to understand the full impact and mitigate this problem. More updates to follow shortly.
Around it6 other incidents at the same time · 5 earlier incidents
The issue affecting editing documents with the Google Docs connector on claude.ai, Claude Code, and Claude Cowork has been resolved. Impact occurred from 16:19 PT on November 17 / 00:19 UTC on November 18 to 17:33 PT on November 17 / 01:33 UTC on November 18.
2 earlier updates
18 Nov 01:40 UTCMonitoringA fix has been deployed for the issue affecting editing documents with the Google Docs connector on claude.ai, Claude Code, and Claude Cowork, and we are monitoring for recovery.
18 Nov 01:13 UTCInvestigatingWe are investigating elevated errors when editing documents with the Google Docs connector on claude.ai, Claude Code, and Claude Cowork. Reading documents is not affected. We will provide an update as soon as possible.
Around it5 other incidents at the same time · 5 earlier incidents
CloudflareIssues with Durable Objects and Dependent Servicesresolved 00:17 UTC2 h 21 min
Started 17 Nov 21:56 UTCUpdated 3d ago
Durable ObjectsStreamContainers
This incident has been resolved.
1 earlier update
17 Nov 21:56 UTCInvestigatingWe are investigating reports of elevated timeout rates and performance degradation affecting Durable Objects. This may impact dependent services, including Stream and Containers. Our team is actively investigating, and further updates will be provided shortly.
Around it5 other incidents at the same time · 5 earlier incidents
CloudflareR2 elevated errors and timeouts for requests from South Americaresolved 22:08 UTC2 h 3 min
Started 17 Nov 20:05 UTCUpdated 3d ago
R2
This incident has been resolved.
3 earlier updates
17 Nov 20:53 UTCMonitoringA fix has been implemented and we are monitoring the results.
17 Nov 20:13 UTCIdentifiedThe issue has been identified and a fix is being implemented.
17 Nov 20:05 UTCInvestigatingWe are investigating elevated errors and read timeouts affecting R2 requests originating from South America (impacting datacenters such as GRU, GIG, EZE, and SCL). Our team is actively working to identify and resolve the issue.
Around it5 other incidents at the same time · 5 earlier incidents
The issue affecting Sign in with Apple on claude.ai and the Claude iOS app has been resolved. Impact occurred from 08:40 PT / 16:40 UTC to 12:20 PT / 20:20 UTC.
2 earlier updates
17 Nov 18:56 UTCUpdateWe have identified the cause of the issue affecting claude.ai and are working on a fix. We will provide an update as soon as possible.
17 Nov 18:55 UTCIdentifiedWe are investigating an issue with Sign in with Apple on claude.ai and the Claude iOS app. Sign in with Google and email are not affected. We will provide an update as soon as possible.
Around it6 other incidents at the same time · 5 earlier incidents
CloudflareNetwork performance issues in Los Angeles (LAX) and Frankfurt (FRA) datacentersresolved 18:00 UTC47 min
Started 17 Nov 17:12 UTCUpdated 4d ago
Network
This incident has been resolved.
4 earlier updates and 1 change ChangeIntel noticed
17 Nov 17:56 UTCMonitoringA fix has been implemented and we are monitoring the results.
17 Nov 17:14 UTCIdentifiedThe issue has been identified and a fix is being implemented.
17 Nov 17:12 UTCInvestigatingCloudflare is investigating issues with network performance in Los Angeles (LAX), United States and Frankfurt (FRA), Germany datacenters. We are working to analyse and mitigate this problem. More updates to follow shortly.
17 Nov 17:12 UTCInvestigatingCloudflare is investigating issues with network performance in Los Angeles (LAX) datacenter. We are working to analyse and mitigate this problem. More updates to follow shortly.
17 Nov 17:28 UTC ChangeIntel noticed a new title; it was "Network performance issues in Los Angeles (LAX) datacenter"
Around it6 other incidents at the same time · 5 earlier incidents
CloudflareTurnstile verification failuresresolved 16:37 UTC6 h 12 min
Started 17 Nov 10:24 UTCUpdated 4d ago
Turnstile
This incident has been resolved.
2 earlier updates
17 Nov 10:42 UTCIdentifiedThe issue has been identified and a fix is being implemented.
17 Nov 10:24 UTCInvestigatingWe are investigating reports of Turnstile verification failures affecting some users with browser fingerprinting protection enabled, including Helium. We are assessing the impact and potential mitigations.
Around it6 other incidents at the same time · 5 earlier incidents
17 Nov 14:43 UTCMonitoringA fix has been implemented and we are monitoring the results.
17 Nov 13:54 UTCIdentifiedWe are investigating reports of connection drops and TCP resets affecting requests routed through Cloudflare WARP and Gateway that aims for Cloudflare Regional Services hostnames and domains. Engineering has identified the root cause and is preparing a fix for release
Around it4 other incidents at the same time · 5 earlier incidents
Between 04:50 - 05:50 UTC 17th November, customers in Seoul may have experienced an elevated number of 52x origin connectivity errors. This is now resolved.
Around it2 other incidents at the same time · 5 earlier incidents
17 Nov 00:52 UTCMonitoringA fix has been implemented and we are monitoring the results.
17 Nov 00:41 UTCIdentifiedThe issue has been identified and a fix is being implemented.
17 Nov 00:41 UTCInvestigatingCloudflare is investigating an issue affecting network performance in Ashburn, US has been identified and a fix is being implemented. Customers may experience elevated error rates and increased latency.
17 Nov 00:41 UTCInvestigatingCloudflare identified an issue affecting network performance in Ashburn, US has been identified and a fix is being implemented. Customers may experience elevated error rates and increased latency.
Around it2 other incidents at the same time · 5 earlier incidents
Cloudflare identified an issue that affected network performance in Montreal, Canada, between 20:10 and 20:40 UTC on November 16, 2026. During this time, customers may have experienced increased HTTP 499 errors and elevated latency. This incident has been resolved.
Around it3 other incidents at the same time · 5 earlier incidents
The issue affecting Sign in with Apple on the Claude iOS app has been resolved. Impact occurred from 16:29 PT on November 13 / 00:29 UTC on November 14 to 10:31 PT / 18:31 UTC on November 16.
2 earlier updates
14 Nov 20:12 UTCUpdateWe are continuing to investigate an issue with Sign in with Apple on the Claude iOS app, which is mainly affecting new accounts. New users can sign up with Google or email instead. We will provide another update as soon as possible.
14 Nov 07:11 UTCInvestigatingWe are investigating an issue with Sign in with Apple on the Claude iOS app, which is mainly affecting new accounts. New users can sign up with Google or email instead. We will provide an update as soon as possible.
Around it6 other incidents at the same time · 5 earlier incidents
Elsewhere at the same time · within 12 hours of its start
GitHubIncident with Pull Requestslast seen 16:26 UTCunknown
Posted 16 Nov 11:59 UTCUpdated 5d ago
Pull RequestsActions
On November 16, 2026, between 09:30 and 15:55 UTC, some pull request merges on GitHub timed out. On average, 2.9% of merge attempts timed out, with a peak of 7.1% at 15:17 UTC. Some GitHub Actions workflow runs triggered by pull requests were also delayed. Git operations such as push and fetch stayed available, with higher latency. This was a repeat of a shorter event on November 13, between 13:15 and 17:50 UTC, when 1.7% of merges timed out.Both events had the same cause: some of the storage servers that hold Git repository data reached their disk read bandwidth limits. A merge must be written to every copy of a repository, so one overloaded server slowed merges for every repository it hosts. Read load on these servers had been growing as part of a planned move of repositories to new infrastructure. A disk configuration setting on those servers also made them read far more data than necessary, which cut their usable bandwidth roughly in half. We mitigated the incident by correcting that setting and moving some load away from the busiest servers.The corrected setting is now applied permanently across our storage fleet. We are adding storage capacity in the affected region and alerting on per-server disk bandwidth so we catch saturation before it affects customers. Sustained merge timeouts will now page our on-call engineers directly. We are also adding capacity checks before moving repositories or traffic onto new infrastructure.
12 earlier updates
16 Nov 16:26 UTCResolvedThis incident has been resolved. Thank you for your patience and understanding as we addressed this issue. A detailed root cause analysis will be shared as soon as it is available.
16 Nov 16:16 UTCUpdateWe’ve mitigated the issue affecting pull request merges and Actions workflow start times by reducing load on affected systems. Pull Requests and Actions have recovered, and we’re continuing to monitor their performance.
16 Nov 16:07 UTCMonitoringThe degradation affecting Actions and Pull Requests has been mitigated. We are monitoring to ensure stability.
16 Nov 15:55 UTCUpdateWe’re seeing early signs of improvement in pull request merge times & workflow start times, but recovery is not yet confirmed. Users may still have difficulty merging pull requests. We’re reducing load on affected systems and monitoring the impact. We’ll share another update as we learn more.
16 Nov 15:46 UTCUpdateWe’re seeing early signs of improvement in pull request merge times, but recovery is not yet confirmed. The last confirmed timeout rate was 2.5%, compared with a baseline near 0.2%, so some users may still have difficulty merging pull requests. We’ll share another update as we learn more.
16 Nov 15:33 UTCUpdateActions is experiencing degraded performance. We are continuing to investigate.
16 Nov 15:03 UTCUpdateWe’re continuing to investigate elevated pull request merge timeouts. The latest reported rate is 4.75%, compared with a baseline near 0.2%, so some users may have difficulty merging pull requests. We’ll share another update as we learn more.
16 Nov 14:06 UTCUpdateWe’re continuing to investigate elevated pull request merge timeouts. Approximately 3% of merges are timing out, compared with a baseline near 0.2%. Mitigations so far have not materially improved performance, and our teams are working to reduce load and restore normal service. We’ll share another update as we learn more.
16 Nov 13:24 UTCUpdateWe’re continuing to investigate elevated pull request merge timeouts. Approximately 2–3% of merges are timing out, compared with a baseline near 0.2%. Mitigations so far have not restored normal performance, and our teams are continuing to investigate. We’ll share another update as we learn more.
16 Nov 12:35 UTCUpdateWe’re continuing to investigate elevated pull request merge timeouts. Approximately 2–3% of merges are timing out, compared with a baseline near 0.2%. We’ll share another update as we learn more.
16 Nov 12:00 UTCUpdateWe’re investigating elevated timeouts when merging pull requests. Some users may be unable to merge pull requests successfully; timeouts are occurring at a higher rate than usual. We’re working to identify the cause and restore normal performance.
16 Nov 11:59 UTCInvestigatingWe are investigating reports of degraded performance for Pull Requests
Around it5 other incidents at the same time · 4 earlier incidents · 1 change in the 14 days before
GitHub Enterprise updatesStatus: Other commercial announcement → Product or portal update · 2 times, latest 14 Nov
CloudflareErrors creating predictions for some modelsresolved 16:19 UTC1 h 48 min
Started 16 Nov 14:30 UTCUpdated 5d ago
Replicate
This incident has been resolved.
3 earlier updates
16 Nov 15:52 UTCMonitoringA fix has been implemented and we are monitoring the results.
16 Nov 15:30 UTCIdentifiedThe issue has been identified and a fix is being implemented.
16 Nov 14:30 UTCInvestigatingWe are currently investigating this issue. Cloudflare is aware of, and investigating, an issue affecting prediction creation for some models on Replicate. Customers may see requests fail with the error "Failed to create prediction." We are working to understand the full impact and mitigate this problem. More updates to follow shortly.
Around it5 other incidents at the same time · 5 earlier incidents
The issue affecting claude.ai, the Claude API, Claude Code, and Claude Cowork has been resolved. Impact occurred from 23:32 PT on November 15 / 07:32 UTC on November 16 to 00:45 PT / 08:45 UTC on November 16.
2 earlier updates
16 Nov 08:02 UTCMonitoringA fix has been deployed for Claude Sonnet 5.5 and other Claude models and we are monitoring for recovery.
16 Nov 07:49 UTCInvestigatingWe are currently investigating this issue.
Around it3 other incidents at the same time · 5 earlier incidents
Bars compare how long each incident lasted, up to three days; a lighter bar is a lower bound and a hatched one is unknown. Older incidents are kept for 90 days on the timeline.
Azure post-incident reviews
What went wrong in major incidents and what Microsoft is changing