There is nothing like a datacentre outage to highlight just how reliant the digital economy is on these facilities, with the 2018 news cycle dominated by tales of server rooms going awry and causing mass disruption to end users across the globe.
Regardless, user appetites for cloud-hosted services show no signs of waning, prompting the hyperscale cloud and internet giants to double-down on their datacentre investments to ensure they have enough capacity to cater to the needs and requirements of their customers.
And the challenges all this growth poses to the datacentre industry has come into sharp focus over the course of 2018, as the hyperscalers grapple with location constraints, planning permission issues and hardware security problems.
With all this in mind, here’s a look back over Computer Weekly’s top 10 datacentre stories of 2018.
Cloud datacentre operators across the world were rocked by the discovery of two major chip flaws at the very start of 2018 that could leave users of the platforms at risk of having their data accessed and tampered with by unauthorised third parties.
The first of the two flaws, Meltdown, was thought to affect every Intel processor made since 1995 that makes use of out-of-order execution, while the second – Spectre – was present in chips made by Intel, AMD and ARM.
In response, all of the major cloud providers issued assurances their systems had been patched, while the speed of the response was seized upon by some to highlight exactly why using public cloud is safer and more secure than on-premise datacentres.
The past 12 months has seen the colocation market continue to reap the benefits of the apparently insatiable demand from users for online and cloud services, prompting the hyperscalers to lease datacentre space from them in record amounts. And it is a trend that shows no signs of stopping.
For the hyperscalers, colocation offers near-ready access to new datacentre capacity but – as a Computer Weekly analysis of this trend revealed – the benefits for the colocation community are far more hard-fought.
The British Airways bank holiday outage was one of the biggest datacentre stories of 2017, and the after-effects of the incident – which grounded thousands of planes and air passengers at Heathrow and Gatwick – are still playing out.
The outage, which is known to have been caused by a power failure at one of the airline’s two datacentres in Heathrow, is now the subject of legal action, with British Airways now in the throes of suing its managed service provider CBRE, who was overseeing the running of the facility at the time.
At the time of writing, legal proceedings were still due to start, suggesting this is a story that could also go on to dominate the datacentre news cycle in 2019 as well.
After three years of legal challenges and planning permission appeals, consumer electronics giant Apple conceded defeat and confirmed in May 2018 that it was abandoning its plans to build a €850m datacentre in the west Ireland town of Athenry.
The prospect of Apple siting its datacentre in the area had proved a hugely divisive issue in the local community, with supporters hailing the economic benefits of the project, while others have expressed concerns about the environmental impact it could have.
While Apple has pulled the plug on the project, the legal wrangling into the development is still ongoing, with the objectors currently seeking clarification through the courts as to why Apple was granted permission to proceed with the build in the first place.
A defective switch in one of Visa’s UK datacentres stopped millions of people across the country using their credit cards for a 10-hour period on Friday 1 June 2018.
According to a retrospective analysis of the outage, put together by Visa at the behest of the Treasury Select Committee, of the 51.2m transactions that were attempt during the peak of the outage, just 5.2m made it through.
As the demand for cloud datacentre capacity increases, concerns abound about how much physical space there is in the world to actually accommodate it all, prompting some hyperscalers to start thinking outside of the box when it comes to their next-generation datacentre designs.
Chief among them is Microsoft, who deployed a 40ft long underwater datacentre off the coast of the Orkney Islands near Scotland in June 2018, as part of its ongoing research into the potential use cases for subsea server farms.
The unmanned facility contains more than 860 servers and is expected to stay in place for a year, during which time its performance – including the amount of sound an heat it emits – will be closely monitored.
The datacentre community found itself divided in August 2018 over an EU-backed bid to introduce measures to help lower the collective power consumption of server farms across Europe.
The EU EcoDesign Directive is still be in throes of being approved by EU lawmakers, but could potentially see large numbers of server products removed from sale within the EU from March 2020 based on how much energy they consume while idle.
IBM, Dell-EMC and HPE are among the suppliers who have raised objections to the move, while a number of noted academics and energy use researchers have praised the EU for what it is trying to achieve with the move.
Given the high demand for spare colocation capacity in London, news of Infinity SDC’s sell-off of its highly-publicised Here East facility in the former Olympic Park in Stratford, London, certainly came as a surprise to some. Particularly as the firm sold the site to the V&A Museum.
At the time of its launch, the company claimed the site would go on to become one of the largest and most efficient datacentres in Europe, but the firm failed to attract the requisite number of clients needed to make the site a success, and offloaded it accordingly.
A major datacentre outage in January 2018 left healthcare professionals working for NHS Wales unable to access multiple IT systems, including those used to book patient appointments, retrieve test results, and log notes taken during consultations.
While few details were forthcoming at the time about the root cause of the incident, it is understood a networking fault resulted in two datacentres failing that underpin the NHS Wales IT systems.
While some colocation providers have been riding the cloud wave, others have been cashing in on the growing demand for cryptocurrency mining by throwing over all or parts of their facilities to processing transaction on specialised hardware equipment.
However, debate continues to rage over how sustainable a source of supplementary income this will be for operators in the long-term, with some predicting it will prove to be rather shortlived.