After the disastrous fire at OVHcloud in Strasbourg, we need information on the risk

OVHcloud was known as a bold innovator. When the cause of the SBG2 fire in Strasbourg is finally revealed, this may be a factor

Just because it's unlikely doesn't mean it won't happen

Power problems are no longer the top cause of outages

As many of us continue to work remotely, outages have become more frequent and more acute

Although the system is resilient, there have been some alarming staff shortages

The big dangers - and how to manage them

As Internet traffic has increased and databases have become more outdated, the importance of routing validation has increased

The US Government Accountability Office recently issued a report in which it documented 34 IT outages from 2015 through 2017 that affected 11 of the 12 selected domestic US airlines included in the report

There are a range of varying claims to BGP visibility or monitoring out there, terms which are themselves quite vague

Explaining Cloudflare's major outage

Three approaches to determine the impact of changing a script

When data is unavailable, lost or unprotected, there’s a huge price to pay

A simple error can dramatically alter the service delivery landscape in the Internet

What we saw when Google went down, and how you should think about resiliency and visibility as you move into the cloud

Linking data center failures to organizational dysfunction and a lack of diversity

MySpace doesn’t make headlines too often these days — and its most recent appearance in the news was for all the wrong reasons

An effective disaster recovery plan is all about the details

The world’s most successful companies all have something in common – agility

Don’t underestimate the power of using OCPD fuses in your data center

When a service goes down, the impact can vary from disastrous to so-what

The most effective disaster recovery plan is one that caters to the business’s specific needs

ARP creates a control plane where decisions about routing electrical can be taken and enacted, based on a real-time assessment of the actual needs of the data center. Peter Judge talks to Ed Ansett about an invention due to be revealed at DCD>London

Bad weather sparked last week's Azure outage. In the long term, AI and analytics may save us from this sort of incident - but for now, you need to get ready for the next storm

Equipment, expertise, and management are so much more advanced than they were five or 10 years ago. How could failures possibly be more common?

The causes of data center downtime are diverse, but there is an important trend that puts the ultimate responsibility on generators

The biggest lesson from the meltdown at British Airways is this: don’t have a single point of failure

The airline could win back some trust if it helped to break the secrecy around IT failures
Our latest on the BA outage is here