Today, from approximately 21:12 to 21:39 UTC, a configuration error in our backbone network caused an outage for Internet properties that use Cloudflare. During this period we saw traffic drop by about 50% across our network. Because of the architecture of our backbone this outage didn’t affect the entire Cloudflare network and was localized only to certain geographies. This service disruption was not the result of an attack. It was caused by a network configuration error which caused traffic across our backbone to be sent to a single router on our global network. This quickly overwhelmed that router and caused Cloudflare network locations connected to the backbone to fail. Other locations not connected to the backbone continued to operate normally. We have posted an initial of this incident on the Cloudflare blog. We’ve already made a change to the backbone configuration to make sure that this cannot happen again. We’re deeply sorry about how this disruption may have impacted your services. Our business is based on trust and transparency and we are committed to your success. ~The Cloudflare TeamW nocy prezes Prince zaktualizował oświadczenie, informując o wykryciu przyczyn problemu:
We had an issue that impacted some portions of the @Cloudflare network. It appears that a router in Atlanta had an error that caused bad routes across our backbone. That resulted in misrouted traffic to PoPs that connect to our backbone. 1/2
— Matthew Prince ? (@eastdakota) July 17, 2020
Niektórzy internauci zauważają jednak, że kłopot nie dotyczy jedynie usług Cloudflare'a, zaś awaria dotknęła także innych stron, korzystających z narzędzi innych dostawców bądź też posiadających własną infrastrukturę.We isolated the Atlanta router and shut down our backbone, routing traffic across transit providers instead. There was some congestion that caused slow performance on some links as the logging caught up. Everything is restored now and we're looking into the root cause. 2/2
— Matthew Prince ? (@eastdakota) July 17, 2020
"Popularną" hipotezą, dotyczącą wyjaśnienia przyczyn, jest olbrzymi atak DDoS – jak wiadomo, Cloudflare oferuje stronom ochronę przed takimi atakami, toteż przy odpowiednim ich natężeniu mógłby istotnie ucierpieć. Niektórzy zauważają także podobieństwo w skali do ataku na Twittera sprzed kilku dni. Na razie teorie te pozostają oczywiście niepotwierdzone, nie można jednakże oczywiście ich wykluczyć. Możliwe jest także, iż doszło do nałożenia się na siebie problemów – zarówno ataku DDoS, jak i wewnętrznej awarii Cloudflare'a. Ciąg dalszy z pewnością nastąpi, w miarę odkrywania nowych faktów.This is NOT just Cloudflare, as far as I can tell. Half the Internet is down, even small VPS providers and local routes in other countries that are unaffiliated with CloudFlare.
I've been monitoring through //t.co/xvLSDEZIUk and it's a *lot* of sites #outage pic.twitter.com/giOuooNegf — Jeff Geerling (@geerlingguy) July 17, 2020
Komentarze