Building an energy efficient home computer

Building an energy efficient home computer

Summary: You say you want a revolution?Energy efficient data centers are in the news again, with the EPA reporting that data centers use 1.


You say you want a revolution? Energy efficient data centers are in the news again, with the EPA reporting that data centers use 1.5% of US electricity - almost 6 million home's worth - and doubling in five years.

But what about your home data center? My house has 2 wireless routers, 3 systems, 4 monitors, 6 cores and 8 GB RAM. They don't use as much power as a refrigerator, but I'd like them to be more efficient anyway.

Measuring & comparing power use Can we cut the power requirement? We could, if we had a way to reliably benchmark power consumption across architectures. Which is what JouleSort: A Balanced Energy-Efficiency Benchmark (PDF) by Suzanne Rivoire, Mehul A. Shah, Parthasarathy Ranganathan and Christos Kozyrakis tries to do.

The benchmark of the future The authors chose a sort algorithm that would exercise the entire system:

JouleSort is an I/O-centric benchmark that measures the energy efficiency of systems at peak use. Like previous sort benchmarks, one of its goals is to gauge the end-to-end effectiveness of improvements in system components. To do so, JouleSort allows us to compare the energy efficiencies of a variety of disparate system configurations. . . . previous sort benchmarks have been technology trend bellwethers, for example, foreshadowing the transition from supercomputers to clusters. Similarly, an important purpose of JouleSort is to chart past trends and gain insight into future trends in energy efficiency.

Prototyping an energy efficient server They used the benchmark to evaluate several systems, some "unbalanced" systems such as a laptop and systems "balanced" or configured to meet the needs of the benchmark most efficiently.

They found that unbalanced CPU utilization was quite low, ranging from 1% to 26%. As a result, the system didn't accomplish much work for the power it consumed.

Since the CPU is usually the highest power component, these results suggest that building a system with more I/O to complement the available processing capacity should provide better energy efficiencies.

Ah, the irony! 40 years after the minicomputer we are back to a batch mainframe I/O-centric architecture. All things old are new again.

Design for efficiency Disks and bandwidth are critical for efficiency in this benchmark. At 15 W each, it doesn't take many SATA disks to overtake the CPU as the major power sink. The balanced system required 2 trays of 6 disks each to keep a dual-core CPU busy.

Here's the configuration of a balanced server and note the disk components. picture-151.png

A really efficient server The team then built a server optimized for the benchmark. As I noted in Power pushing 2.5? drives to tipping point 2.5" notebook drives are 2-3 watts, not 10-15. And sure enough, the paper found that an energy efficient system did much better with notebook drives. The configuration: winning_system.gif

File systems, RAM and power supplies The benchmark is a sequential sort. The authors found that file systems with higher sequential access rates more efficient. Developers, the time may not too far away when your code is measured on power efficiency as well as performance.

They also found that reducing the RAM footprint to the needed capacity raised efficiency as well. FB-DIMMs, with their 5 watt per stick penalty, are a definite efficiency target.

They also found that the winning system could use a much smaller power supply. The authors suggest that power-factor corrected power supplies are required to make energy efficient servers economic as well.

The StorageMojo take As the breadth of the paper suggests, power efficiency requires a holistic understanding of computes, I/O, software, power factors and configuration trade-offs. Some of the supercomputer folks can do this, but the average data center or home user is years away from this level of workload understanding.

Instead the research points to a few things that increase efficiency and reduce consumption across a wide range of workloads and configurations. Mobile CPUs and notebook disks are 2 likely candidates. Software effects are significant as well because widely used software affects so many systems.

Will we all be buying home servers with a half dozen disks any time soon? No. But saving power while increasing performance is always a good thing.

Comments welcome, as always. For home users power cost is not a big issue. How much more would you be willing to pay for a more efficient system?

Topics: Servers, Data Centers, Hardware, Laptops, Processors

Kick off your day with ZDNet's daily email newsletter. It's the freshest tech news and opinion, served hot. Get it.


Log in or register to join the discussion
  • Can you add a price column to the first table...

    So we can see a cost ???
  • These power numbers are not accurate

    These power numbers are not accurate. What's accurate is power at the plug. I measure 50W to 70W idle in the new computers I build.
    • George, George, must you?

      Here's what the team said in the paper: <br>
      Power Measurement: To measure the full-system AC power consumption, we used
      a digital power meter interposed between the system and the wall outlet. We
      sampled this power at a rate of once per second. The meter used was Brand
      Electronics Model 20-1850CI which reports true power with ?1.5% accuracy. In
      this paper, we always re- port the average power over several trials and the
      standard deviation in the average power.
      Sounds reasonable to me.

      R Harris
      • Pay no attention to George,

        His bad comb-over tells him what to do. Lot's of ramblings on other people's
        blogs, very attention starved.
      • George is Venomous

        I mean really, he blasts fellow writers on the same site. Taking his internal issues with co-workers public is in verrrry bad form.

        But then again, we shouldn't be surprised. Everything he writes is with a tinge of rage. I'd really like to understand why he is that way. It's gotten to the point that when I see an angry headline on ZDNet, I know instantly it's George. And when I click on the article, sho' nuff 100% of the time, it IS George.

        George, why are you such an angry man? Why is everything you write so venomous? And why do you attack people who respond to your articles?

        I say let's all boycott George Ou until he tones it down and learns to be a good little boy, instead of an antagonist. You all with me?
        • ignore him

          The best way to deal with him is to deprive him of the attention that he seeks.

          If he falls in the technology jungle and no one is around to hear him, does he make a sound?
      • It's hard to read those charts.

        The way the chart is presented is just hard to read and hard to understand what the actual power consumption is.
        • A better metric

          A better metric for me isn't watts based on averages over a number of
          benchmarks. What makes sense to me is, "watts per Karazhan hour." My home
          computer is mostly used for playing WoW, so a better benchmark for me is the
          power consumption of my home electronics while busy raiding Karazhan or any of
          the 25 man instances.

          Is WiFi more efficient than wired Ethernet? Would I be better off using a Raid 10
          enclosure full of laptop drives instead of my LaCie BigDisk d2 Extreme? FireWire or
          USB 2.0?

          Heck, I should go hire a decent power meter and find out :)
          • oops...

            Oh... and I'd only be prepared to pay more for a computer that consumed less
            power (for the same performance) if the extra cost of the computer was worth
            more than the savings on my power bill.

            Ultimately, you could add "carbon tax" onto the power bill and the computer/
            peripherals I buy, and the same decision would apply - but the Carbon Tax has to
            come first. Which leads to all kinds of social repercussions when you consider that
            some families can't afford computers in the first place, so Carbon Tax will just be
            doubling their power bill with no means to reduce their consumption below 1
            fridge running all day (they're too poor for TV, and only have a line-powered

            Or I could go and try to calculate the "carbon cost" of my computer and determine
            what alternatives exist for me to lower the "carbon footprint" of the next one I buy
            - and just work on lowering my personal "carbon footprint" as an exercise in
            applied altruism.
    • Power Numbers?

      But what power factor are you ending up with? This is not usually the same as Wattage. In a perfect world it would be, in practice it is a long way from it.

      Power factor is corrected in the better power supplies and will help your power bill. I corrected my entire home's power factor and reduced my total billable wattage by 18%. That resulted in a 24% reduction in power cost because of our usage surcharge.
    • RE: Building an energy efficient home computer

      Very cautious <a href="">youtube converter free</a>, be converted into assemble fairly accurate <a href="">youtube to mp3 converter free</a> beside along with <a href="">youtube to mp3</a>|<a href="">youtube mp3</a>
      youtube converter
  • HOME computer???

    Why not just commission an electrical engineering firm to do an optimization study? They could probably do it for no more than $50k. Plus hardware, of course ...

    Of course, the ridiculous aspect of the suggestion is that within 6 months the study would be obsolete when someone came out with SOME new item that saved a few watts.

    HELLO! It's a [i]HOME[/i] computer!

    Years ago (late '70s) I planned on building a [b][i]really[/i][/b] hot audio system. (This was back when you still could build amps with better performance than most commercial audiophile stuff.) I bought transformers, capacitors, etc., for a 1KW supply, amp modules, etc.

    What finally shocked me into seeing reality was when I seriously started trying to figure out how to build a SPECTRUM ANALYZER so I could have a really accurate idea of distortion levels.

    I realize these blogs are aimed at techno/geek types, but some of these articles really go off the deep end! Like using RAID in home systems!

    (Okay, if there are roaches near the computer, that's another story ....)
    • Nature of evolution

      I agree that most of what is being discussed here isn't applicable to the average home user. However, let's look at history and technology in general. There are dozens, if not hundreds, of examples where grassroots type technology improvements have evolved into commercialized solutions.

      I think the author, in this case, is simply trying to wake up those who know how to tinker with this in their garages to start doing this. In truth, it's beyond me. As more of these super-uber geeks come up with solutions and start posting it, commercial outfits will take notice (if it grows in popularity) and incorporate it into their own products.

      When you think about it, if 1.5% of U.S. power consumption comes from the data center, what percentage comes from home users' computers? There is a rather slow movement going on right now to green our devices. But as it starts to pick up steam, and consumers themselves start to demand greener products, these commercial outfits will turn to the solutions posted online. The very solutions posted by people that this author is trying to wake up in the first place.

      So I commend the author for his efforts, though I totally agree with you that much of what is being discussed here and in other articles is going over the heads of the average reader.

      But I am excited to know that there is someone out there who WILL read this, be inspired to come up with solutions, and those solutions will trickle down to my home devices (not just computers, but everything with a chipset in it) and help me cut back on my electric bills! I am tired of relying on that windmill in my backyard to generate electricity. It's so big, I have no room for bbq parties anymore!
    • Red-neck RAID Solution

      Being a cost-conscious nut case that I am, my solution to home system RAID is to put a duplicate HDD in the box, do a user initiated copy the changed files at the end of the day and the entire contents on a weekly basis.

      That way I don't often run into automatic copying of malware to the backup, and if one drive fails, I can do a quick BIOS switch to boot from the backup while I wait for the replacement to arrive.
    • roach motel

      Actually there are a lot of roaches in the ashtray sitting on top my PC case. Maintaining my RAID and swapping our components for the latest more energy efficient component takes a lot of time an um... patience.
      Then there's all that overclocking stress...
  • Pretty good, but processor is too pricey.

    I would go with the Merom T7100 at 214.00 at Newegg. No need to spend 639.99 for a processor when it is used in server enviroment to store data mainly. The server will not be straining itself loading heavy duty apps to tax the processor.
    • There is delay between testing

      and publication. They did do some price/performance calculations that I chose not to
      focus on .<br>
      R Harris
      • I figured that.

        Why not? You talk about the home data center. You must keep the price down so that the average Joe can afford it. Old Pentium 2 processors make very good servers to store data to. The slowest Core Duo would be a F1 race car by comparison.
    • AMD TL-37!

      Newegg had been giving these 25w cpus away at $65; w/a $50 Asrock motherboard and WDsata2 400gb drive I have a really nice, fast, low-power server. Motherboards for Intel mobile chips are too expensive, though Yonah chips are reasonable.

      I went this route instead of a $450 laptop because laptop drives and fan is less reliable, and all the components cost more. A low power display comes with, though.
      • A little light on spec.

        AMDs do not always go into sleep mode. They also do not transfer as much data per watt like the Core Duo. Also do not go too cheap on the mobo cause the quality isn't there. I mean it is your data the most expensive thing about computing.

        I would have went with a E4300 Core Duo and some Asus mobo with not too many features except with ICH8R controller. I also would go with 2 500gig Seagate Barracudas commercial grade and DVD for backup. A little more expensive but more durable for the data.