A Power Event in Google Cloud's London Region Knocked Out Banking Apps and Delivery Services for Hours
One availability zone lost power at 06:08 UTC on Tuesday. Customers saw Lloyds, HSBC and Revolut disrupted, and Google says an analysis will follow its investigation.
Outspoken Digest Technology Desk
Wednesday, October 21, 2026/2 min read
For most of a Tuesday morning, a fault in a single building in London turned into a problem for millions of people trying to use their bank. Google Cloud's europe-west2 region began failing at 06:08 UTC on 20 October, and services across the UK and parts of Europe stuttered with it.
Google's status page blamed a power event in one zone, europe-west2-b, The Register reported. The zone is one of three in the London region.
What caused the Google Cloud outage?
The status page said: "A power event caused an outage within europe-west2-b zone." Early updates were blunter. The Register quoted Google saying multiple services were seeing elevated errors and intermittent network failures, with no workaround at first, and later suggesting customers migrate affected workloads to another location if feasible.
The affected products included BigQuery Data Transfer Service, Cloud Filestore, Cloud Run, App Engine, Google Kubernetes Engine and Managed Service for Apache Kafka. Google also said customers might be unable to create new workloads while it prioritised restoring existing ones.
Which services and banks were disrupted?
Down Detector reports named Lloyds Bank, HSBC, Royal Mail, Rightmove, DPD, BT, Screwfix and Revolut, The Register noted, and it presented them as user reports rather than confirmed impacts, apart from Revolut. Revolut said all customers' money and data were safe.
Tech Xplore reports that Lloyds, Halifax, HSBC and Revolut were hit and that Lloyds said its app was working again and expected a return to normal. It describes the disruption as largely over about six hours after it began. Google said the issue affected "a very small number of customers" at that stage, according to the same report.
How long did it last?
By 11:58 UTC, Google said recovery should complete, tentatively, by 13:00. At 14:03 it said the problem was mitigated for most customers and normal service had resumed for the majority, with a small number still affected. Keele University lecturer Dr Amro Al-Said Ahmad estimated 38 services were down, The Register reported.
The Register cautioned that the Down Detector reports reflect what users saw, not what each company has confirmed, and Tech Xplore notes that some outages elsewhere in Europe were reported but that it is unclear whether they were connected.
What should companies take from it?
The episode is a reminder that a regional zone is a shared dependency. Firms that run in only one zone, or one region, inherit its failures. Whether the banks' customers saw a short blip or a long outage depended on how each had built its fallback.
Google has promised an analysis after its internal investigation. That document, not the status page, will say why the power event happened and what Google will change.
Published in The Outspoken Digest
Editorial desk
Outspoken Digest Technology DeskSoftware, hardware, artificial intelligence and what they change for everyone else.
Newsletter
The Digest, in your inbox
One edition, sent when it is ready. No noise, and your address is never passed on.
Read Next
More Technology →
Astronomers Say a Pulsar's Odd Slowdown Is Explained by a Hidden Sunlike Star, Making It a Rare Stellar Trio
Oct 21, 2026/2 min read
Interstellar Comet 3I/ATLAS May Have Lost Metres of Its Surface to the Sun, a New Estimate Finds
Oct 21, 2026/2 min read
An Indian Certificate Authority's Private Keys Were Trivially Guessable, and Browsers Have Revoked Them
Oct 21, 2026/2 min read
Anthropic Is Pitching Congress a Bill That Could Block an AI Model Only if It Risks Killing More Than 50 People
Oct 21, 2026/2 min read