Google Cloud London power event knocks out UK banks and services

As of 17:37 UTC on October 20, Google Cloud says the disruption in its London region that began at 06:08 UTC is mitigated for most customers, with a very small number still affected ^[4]. The company confirmed that a power event in the europe-west2-b zone caused the outage and said it will publish an incident analysis after an internal investigation ^[2][4].

How the outage unfolded

The first failures hit at 06:08 UTC ^[3][4]. Revolut reported a service disruption across multiple features; its status page showed ATM withdrawals, identity verification, card payments, transfers, sign-in, chat support, stocks and crypto trading down ^[2]. Downdetector showed a spike for Revolut around 8am with more than 1,500 issues reported ^[1]. Problems were also reported at Lloyds, HSBC, Barclays, Halifax, Bank of Scotland, Royal Bank of Scotland, ING Germany, DPD, Royal Mail, Rightmove, the NHS app and court livestreams ^{[1][2][3][5][6]}.

At 11:58 UTC, Google Cloud said recovery should be complete tentatively by 13:00 UTC ^[4]. At 14:03 UTC, it said the issue had been mitigated for most customers and normal service resumed for the majority ^[4]. Google advised affected customers to migrate workloads to another zone or region if possible ^[2][5].

Revolut told customers that their money and data were safe ^[3][5]. Lloyds said its app was operational again and that it expected all services to be back to normal soon because the root issues had been resolved ^[3].

Regulators and resilience questions

On the same day, the Financial Conduct Authority said it was aware of the incident and was engaging with Google and affected firms ^[1]. The Bank of England was also in contact with affected firms and Google ^[1]. The Treasury Select Committee chair has asked the Bank governor and FCA chief for an initial response by 4 November and a full response in three months ^[1]. UK regulators gained powers in July to oversee the UK arms of cloud providers such as Google Cloud, AWS and Microsoft ^[1].

Dr Amro Al-Said Ahmad of Keele University estimated that 38 services were down and said the incident shows how failures in a core cloud region can cascade through applications, APIs, payment platforms and third-party SaaS products ^[4]. He said true resilience requires multi-region deployments, workload portability and tested disaster recovery procedures ^[4]. The outage came almost exactly one year after an AWS outage in the US-EAST-1 region took down a large part of the internet ^[6]. The EU's Digital Operational Resilience Act already requires banks to show how they would cope with failure of key IT service providers ^[6].

Google has apologised to everyone affected ^[6]. There is no indication of a cyberattack, according to Trending Topics ^[6]. The company has promised a full incident report after its investigation ^[1][3][4].