10 most common surprises for data centre and IT managers

Emerson Network Power has released a list of the 10 most common surprises for data centre and IT managers. Released at AFCOM Data Center World Spring, the list offers tips to help managers prepare for these nasty surprises in order to minimise downtime.

Emerson Network Power has released a list of the 10 most common surprises for data centre and IT managers. Released at AFCOM Data Center World Spring 2012, the list offers tips to help managers prepare for these nasty surprises in order to minimise downtime.

“When you are a data centre or IT manager, very few things are more unsettling than the unexpected,” said Peter Panfil, Vice President of Global Power, Emerson Network Power.

“We hope this list helps IT professionals better anticipate these issues and prepares them with the appropriate technologies, solutions and best practices.”

1. High-density predictions are coming true. Average densities sat around 6.0 to 7.4 kW per rack between 2006 and 2009 and it seemed that double-digit rack density predictions weren’t going to happen. But the latest Data Center Users’ Group (DCUG) survey has predicted that we’ll be seeing average rack densities of up to 12.0 kW in the next three years, putting a premium on adequate UPS capacity and power distribution and cooling to deal with the increased heat output.
2. Data centre managers will replace servers three times before they replace UPS or cooling systems. Server refreshes occur every three years or thereabouts; cooling and UPS systems are sometimes expected to last decades. This means the infrastructure a business invests in today must be able to support servers that are up to four generations removed from today’s models.
3. Downtime is expensive. Outages can cost an average of $5000 a minute, according to a Ponemon Institute study - that’s a staggering $300,000 an hour. The study also shows that UPS battery failure and exceeding UPS capacity are the two most common causes of downtime. The best way to avoid these issues is to invest in the right UPS and monitor and maintain batteries.
4. Water and data centres don’t mix. The Ponemon study shows that 35% of all unplanned outages result from water incursion. Leaky valves can be to blame, but more often than not it’s spilt coffee or soft drink that is the culprit. Emerson’s simple solution to this problem is to ensure valves are maintained - and make data centres no-drink zones.
5. New servers are more power hungry than old servers. Despite new servers being more efficient than their predecessors, new virtualised servers, especially powerful blade servers, can use up to five times as much energy as older-generation servers. Because of this, server consolidation and virtualisation can reduce server inventories, but still result in only modest savings. While acknowledging there’s no solution for this, Emerson recommends businesses make sure their infrastructure will support the power and cooling needs of new servers.
6. Monitoring’s a mess. According to an Emerson Network Power survey, data centre managers use at least four different software platforms to manage their physical infrastructure. With the majority of managers producing more than three reports for their supervisors each month, and reports often taking in excess of three hours to prepare, accessing and making sense of data can be a time-consuming task. Emerson recommends a single monitoring and management platform to streamline operations. Data Centre Infrastructure Management (DCIM) solutions consolidate information, manage infrastructure and improve energy, operational efficiency and availability.
7. The IT department runs the HVAC system. Traditionally, IT and data centre managers have had to work alongside Facilities to increase power or cooling to support IT systems. This process is becoming more streamlined, partly due to DCIM solutions increasing visibility and control over a building’s infrastructure.
8. Integration is imperative. Historically, data centre managers have mixed and matched components from various vendors because the systems worked together only tangentially. This is starting to change: the advent of increasingly intelligent, dynamic infrastructure technologies and monitoring and management systems has increased the amount of actionable data across the data centre, delivering real-time modelling capabilities that make operations efficient. Emerson claims that IT and infrastructure systems can still work independently, but integration is imperative to fully harness their capabilities.
9. Data centre on demand is a reality. Today’s businesses have access to modular, integrated, rapidly deployable data centre solutions for any space. Integrated, virtually plug-and-play solutions that include rack, server and power and cooling can be installed in a closet or conference room. Containerised data centres can be used to quickly establish a network or add capacity to an existing data centre. The solution to most problems, according to Emerson, is only a phone call away.
10. IT loads vary - greatly. Peaks and valleys in network usage are peculiar to each industry. Financial institutions may experience heavy use during business hours but virtually nothing at night. Public holidays, end of financial year and Christmas shopping can create unusual spikes in IT activity. A scalable infrastructure with intelligent controls can adjust to ensure efficient operation during both the peaks and valleys.