When Does Powering Down Servers Make Sense?

snydeq writes "Powering down servers to conserve energy is a controversial practice that, if undertaken wisely, could greatly benefit IT in its quest to rein in energy costs in the datacenter. Though power cycling's long-term effects on server hardware may be mythical, its effects on IT and business operations are certainly real and often detrimental. Yet, development, staging, batch processing, failover — several server environments seem like prime candidates for routine power cycling to reduce datacenter energy consumption. Under what conditions and in what environments does powering down servers seem to make the most economic and operational sense, and what tips do folks have to offer to those considering making use of the practice?"

Comments

Virtualize! Virtualize! Virtualize!

[Anonymous Coward]

If you virtualized your servers, you could create a managed power-down/power-up scenario. In the morning, your servers would turn on, your virtualized instances would move around (so they have more power for the day's activities), and then at night they'd retreat to a smaller group of servers. The unused servers could shut down for the night. You could even rotate which servers stay on overnight keeping the virtual servers running to spread the wear around if there is some.

Re:Virtualize! Virtualize! Virtualize!

[nabsltd]

First, let's assume "several hundred" equals 200, and we have exactly 65000 employees. Let's also assume that these extra servers are on for exactly 48 hours. Let's also assume perfect load balancing and distribution of the process over the servers.

That means that each server processes payroll for 325 employees in 48 hours, or about 7 employees per hour. So, each of these servers is basically the equivalent of a Commodore 64 in computing power. I suggest that the best way to save money at this task is to replace the 200 servers with a single Pentium 4 quad core running at 3GHz.

The other explanation—that the software is so unbelievably bad that it really does take 8½ minutes for it to run a single employee—is possible, but would going out and buying "QuickBooks" really cost more than the 200 servers to run this awful beast of a payroll program?

Re:Virtualize! Virtualize! Virtualize!

[Silentknyght]

If you have a consulting or legal business, where your employees bill time by the tenth of an hour, then yes, this could be a much longer process than you estimate. You have to tabulate all the hours for each employee for the month, and then allocate each hour spent on each day to each client, each client's job, each phase of said job, and each task under that job. Spread that across 1000 active clients with 1-2 jobs each, many with multiple phases, and all with multiple task codes. None of that has to do with processing a paycheck for me. The billing cycle isn't about getting a check from your employer, but getting a check from your client. The above may seem overly complex, but they ask for it and they pay the bills.

Like a car...

[fiftysixquarters]

Seriously, this analogy makes sense. When a car is cruising on the high way it's able to maintain speed using 4/8 cylinders. Servers could be cycled in a similar fashion. Do you really need 20 web servers running at 3 am on a Sunday?

Power Management

[Super_Z]

Powering down your servers tends to introduce response issues. :-)
Some servers, like the HP ProLiant line, has power management features. Try experimenting with features like these first.

Re:Not often

[CFTM]

Uh I am the administrator of a server that archives all email for our company. We no longer use this solution for our email archiving, but according to federal regulations this email needs to be accessible for at least another 26 months. The only people who use the server anymore are the various alphabet soups of regulators who came in twice a year, maybe I'm the exception but not the rule but I can't see a reason to keep the server on...

XenServer

[Obsession12]

Full disclosure, I work for Citrix. Check out XenServer, which can remotely provision server workloads to virtual and bare metal machines - based on load, you can remotely power up resources as needed. I have seen the future, and it is awesome. And green.

Re:Business needs and Risk

[vwjeff]

Example Setup The organization I work for has a well known usage patterns that we use to make decisions like this. 95% or more of our traffic occurs during business hours which we define as 7:00 AM - 7:00 PM. During business hours we have dedicated servers for various functions. We have a cluster of servers running virtual server instances that duplicate the dedicated servers. During off hours the dedicated servers are powered down and the virtual server instances take over. It works for us and we have seen a significant decrease in power usage with no impact on our users.

Re:Old gear

[xaxa]

Analogy (this time, light bulbs).
- Light bulbs fail just as you turn them on. Or off.
- They hardly ever fail whilst switched on.

I think servers are the same. You're in trouble if a server you've had switched on for two years and forgotten about loses power and doesn't come back up. If it'd been switched off every weekend it would have failed earlier -- but probably at a more convenient time.

Re:Old gear

[LeafOnTheWind]

Light bulbs fail when they're turned on because there's a warmup spike as the electricity flows through the wire. This causes the tungsten to heat up more than it will when the circuit is complete, and break the circuit.

If your lightbulb fails it's because the filament has worn down - it's just that you usually find out about it when you turn the light bulb on or off.

Also, your analogy means nothing. Servers are nothing like light bulbs.