Cloudflare's cache purge system failed for users in Qingdao, Shandong, China for 18 minutes on 31 October 2026. The delay was on Cloudflare's side and sat inside their CDN Cache Purge component.
Started
06:41 UTC
Duration
Lasted 18m
Source
IsDown
Next time
Cloudflare is degraded. Is your product working?
An incident on their side does not always mean an outage on yours, and the only way to know is to already be watching your own endpoints. Set that up in under a minute and you will be notified the next time your own site is affected. And there will be a next time.
50 monitors for your own websites. No card.
Affected components: Cloudflare Sites and Services, CDN Cache Purge
What happened?
Cloudflare's status page logged one incident on this day, titled "Cache purge delays in Qingdao in Shandong, China". It started at 06:41 UTC and ran for 18 minutes. The affected components were Cloudflare Sites and Services and CDN Cache Purge. Cloudflare's first update at 06:41 said they were "observing cache purge delay in Qingdao in Shandong, China" and that they were working on it. Nine minutes later, at 06:50, they posted that "a fix has been implemented and we are monitoring the results." That is where the public record stops. No further update was filed, and Cloudflare did not say what caused the delay or confirm resolution beyond that monitoring note. No user reports were filed during this window, so there is no independent account of what the delay felt like from outside Cloudflare. Over the last 90 days Cloudflare has logged 209 incidents with a median duration of 1 hour 54 minutes, and this one at 18 minutes finished well under that median. Across all time Cloudflare's status history shows 3,476 incidents. This particular event affected a single geography and a single function, cache purging, rather than Cloudflare's broader edge network.
Learning
A cache purge delay is a narrow fault: it means requests to clear cached content from Cloudflare's edge in one region were slow to take effect, not that content stopped being served. UptimeRobot's own probes against api-control, dns-1111 and edge-data components, run from the EU and North America, stayed fully green through this window, showing 100% uptime over 24 hours and 7 days. That is not a contradiction. A purge delay in Qingdao would not necessarily touch EU or North America probe traffic, and it would not show up as a failed request if the cached content being served was simply stale rather than absent. This is the general shape of these incidents: your own endpoint checks test whether your product answers, not whether every internal Cloudflare mechanism behind it is running on schedule. If your product depends on fast cache invalidation in a specific region, an outage like this could leave stale content live for users there while every uptime check you run comes back clean. Your monitoring covers your half, UptimeRobot now watches the provider's half too, so next time you know which side broke without guessing.