The Economics Of Fuzz Testing With The Intel Edison

The Intel Edison is an incredibly small and cheap x86 computing platform, and with that comes the obvious applications for robotics and wearable computing. [mz] had another idea: what if the Edison could do work that is usually done by workstations? Would it make economic sense to buy a handful of Edisons over a single quad-core Xeon system?

[mz] thought the Edison would be an ideal platform for fuzz testing, or sending random, automated data at a program or system to figure out if they’ll misbehave in interesting ways. After figuring out where to solder power and ground wires to boot an Edison without a breakout board, [mz] got to work benchmarking his fuzz testing setup.

Comparing the benchmarks of a fuzzing job running on the Edison and a few servers and workstations, calculations of cost-efficiency worked out well for this tiny x86 system on module. For parallelizable tasks, the Edison is about 8x less powerful than a reasonably modern server, but it’s also about 5-8x cheaper than a comparable desktop machine. Although renting a server is by far the more economic solution for getting a lot of computing power easily, there are a few use cases where a cluster of Edisons in your pocket would make sense.

16 thoughts on “The Economics Of Fuzz Testing With The Intel Edison

    1. The SEO shills were telling us those plugs would be DIY friendly.

      Fuzzing usually requires precision timing to reproduce the exploits.
      A low power CPU would essentially be a probabalictic bug generator.

    1. Testing workloads aren’t exactly the sort of thing that is tremendously “parallelizable” by the parallella. It’s aimed mostly at large-scale DSP type stuff. Not general purpose branchy code.

  1. Pretty nice, even if it is not as powerful and econimical, who can say to hold that amount of calculation power on the palm of your hand?

    Another side not, you have to have something to calculate on this dense box of calculation wizardy…

  2. What, quad core xeon? That’s what you get if ýou buy 10 year old 4P machines or really lame C2D stuff. Nowadays good xeon machines have 20++ cores and go up to 80 or even 144 cores if you consider 8P machines and and the new 18 core E7-V3. ARM will bite hard on this, if they want to compete in performance.

    1. The SoC is heavily underclocked so it doesn’t need much of a heatsink. Every “fast” Arm board I’ve seen hits thermal throttling in 30secs of hard work, including phones, also nothing I’ve seen beats this on size. I’m looking forward to mine arriving. Not sure I’m going to enjoy systemd though. Hope I can reflash it with a more traditional init.

Leave a Reply

This site uses Akismet to reduce spam. Learn how your comment data is processed.