Home > Encryption > Time to generate a 15,360-bit RSA key

Time to generate a 15,360-bit RSA key

$ time openssl genrsa 15360
Generating RSA private key, 15360 bit long modulus

<magic happens>

real    2m39.541s
user    2m39.236s
sys    0m0.006s

Categories: Encryption Tags:
  1. 2014-04-15 at 15:35 EDT

    impressive… mine was:

    real 5m10.269s
    user 5m10.209s
    sys 0m0.035s

    Memory – 62.4 GiB
    Processor – Intel® Core™ i7-3930K CPU @ 3.20GHz × 12

    Only question is how did it take nearly twice as long for my beastly machine? What kind of system are you running this test on?

    • 2014-04-15 at 16:16 EDT

      I’m not sure why that’s the case. I believe it is a single-processor process.

      My box is a Intel® Core™ i7-3520M CPU @ 2.90GHz × 4 with 4GB of RAM.

  2. cmurf
    2014-04-15 at 18:10 EDT

    Are both systems using RDRAND?

  3. usr/bin/nice
    2014-04-15 at 19:32 EDT

    Andy, your gonna be really mad :)

    real 4m23.028s
    user 4m22.389s
    sys 0m0.013s

    My laptop has 4gb ram and a 1.4ghz i3 processor.

  4. 2014-04-16 at 00:17 EDT

    real 0m27.663s
    user 0m27.491s
    sys 0m0.006s

    model name : Intel(R) Core(TM) i7-3537U CPU @ 2.00GHz
    MemTotal: 3739636 kB

  5. nath_schwarz
    2014-04-16 at 06:26 EDT

    real 1m38.719s
    user 1m35.441s
    sys 0m0.095s

    On a x61t:
    Intel Core2Duo L7500, 1,6GHz

    I think it depends heavily on what else you’re doing at the moment. My laptop is mostly just the input for my tower, it only runs thunderbird and awesome-wm while working at my station.

  6. 2014-04-17 at 18:31 EDT

    Hey Folks…

    Your results are not going to be repeatable …..
    On my laptop (i7 3840QM, Turbo Boost @ 2.8GHz, 32GB RAM)
    I ran 1 instance and got:
    real 6m19.305s
    user 6m18.246s
    sys 0m0.009s

    I ran 6 instances concurrently and got:
    real 0m19.863s
    user 0m19.811s
    sys 0m0.001s

    real 5m2.677s
    user 5m1.292s
    sys 0m0.227s

    So …. a a test CPU vs Task vs Time …. it could take anywere from 0m19.863s to 6m19.305s on the same gear (depending on the initial seed value from entropy that you get?)

    Yup, Eric …… it’s definately single threaded :-)


  7. Heke
    2014-04-17 at 19:54 EDT

    $ top shows than almost no memory is consumed and the process takes all the CPU, thus execution time differences must come from somewhere else than HW capabilities.

    With my average box with Intel(R) Pentium(R) 4 CPU 3.20GHz took
    real 10m55.269s
    user 10m50.525s
    sys 0m0.317s

    • Doesn't matter
      2016-05-31 at 06:32 EDT

      Not repeatable because probabilistic prime gen

  1. 2014-04-17 at 10:25 EDT

Leave a Reply

Fill in your details below or click an icon to log in:

WordPress.com Logo

You are commenting using your WordPress.com account. Log Out /  Change )

Google photo

You are commenting using your Google account. Log Out /  Change )

Twitter picture

You are commenting using your Twitter account. Log Out /  Change )

Facebook photo

You are commenting using your Facebook account. Log Out /  Change )

Connecting to %s