Triple data centre capacity without new servers
Recycle what you've got for cheap, green fun
The trick to avoiding spending millions of dollars on new data centres is to make do and mend the existing ones, according to Dell.
Dell reckons there is a huge amount of fixed cost in IT that can be recovered by running data centres more efficiently. Optimising existing data centres can be so beneficial that customers would no longer need to build new ones. There are three main things that are needed.
Firstly, run data centres at 25 degrees Celsius rather than the usual 16-18 degrees. Significant cooling costs can be obtained and the data centre IT kit runs perfectly well.
Secondly, Dell increases effective server capacity by 270 per cent across its server estate by running 5,000 virtual machines (VMs) virtualising servers. Chris Ratcliffe, Dell's global marketing director for solutions and services, said: "Next year we'll be at 7,500 VMs and the 3-year savings will be $52,450,000 using existing server hardware with very little outlay from us initially. Microsoft's entry into the virtualisation market will [also] help drive down costs."
The third thing to do is to update power delivery equipment - transformers, power level cleaners, UPS etc. Ratcliffe said: "Most data centres have a 10-year-old power delivery infrastructure. Replace it and you gain efficiency - you can save about 25 per cent of the power costs." Asked about whether AC or DC power was best he replied: "It's much of a muchness." The main event is the modernity of the power delivery equipment not the nature of the current.
Another tactic has been to move data that hasn't been accessed for 90 days off tier-one storage onto cheaper SATA drive arrays and so free up 25 percent of tier-one storage at Dell's Limerick data centre.
Dell has a range of short-term, fixed-fee, fixed-length Data Centre Optimisation services it is now offering. They are based, Ratcliffe says, on Dell's own internal IT experience. It consolidated 22 data centres to six a few years ago, when Randy Mott was its CIO. After that it was able to avoid building new data centres as its business grew and it expanded into managed services, by optimising the six using the methods above.
Ratcliffe reckons that what Mott is now doing at HP means the company is actually following in Dell's footprints. Take that HP. ®
Hardware Support Fail
We have tried several times to make better use of older hardware by increasing RAM and Hardrive capacity and introducing virtualisation for systems that don't require a large amount of fast cpu but each time we've been stymied by the hardware companies not supporting the older models because they've moved to a different architecture/model. It's all very well for a hardware manufacturer to make the claims that Dell do but it's unrealistic for most companies - if we can get support for our older kit, it costs more than it's worth once the kit becomes EOL which seems to come sooner and sooner these days.
Upsizing hard disks and system RAM
I would suggest the idea of upsizing hard disks to take advantage of the fact that these disks are becoming cheaper and larger in data capacity. Same too with the RAM. Then you are gaining more mileage from your existing servers.
Dell says - burn your kit!
Dell says: "Firstly, run data centres at 25 degrees Celsius rather than the usual 16-18 degrees. Significant cooling costs can be obtained and the data centre IT kit runs perfectly well."
Hmm prior studies seem to suggest you knock roughly one month off the lifetime of a server for every degree ceclius increase. Of course, a kit maker would probably see this as a benefit :-).