john-users - Re: Crowd-sourcing statistics and rules

Follow @Openwall on Twitter for new release announcements and other news

[<prev] [next>] [<thread-prev] [thread-next>] [day] [month] [year] [list]

Date: Wed, 18 Apr 2012 00:45:45 +0200
From: Frank Dittrich <frank_dittrich@...mail.com>
To: john-users@...ts.openwall.com
Subject: Re: Crowd-sourcing statistics and rules

On 04/18/2012 12:04 AM, magnum wrote:
> I already added a workaround for this issue long ago, it's there in
> released Jumbo. The --mkpc=N option (note it's not shown in usage blob,
> but in docs/OPTIONS) will force John to just do N (normally you'd use 1)
> at a time, at the cost of performance.

This is another proof that nobody reads documentation ;)

Thanks for your information.

I just did a few tests on my atom netbook (linux-x86-sse2i build).

$ ./john --test --format=DES
Benchmarking: Traditional DES [128/128 BS SSE2]... DONE
Many salts:	940800 c/s real, 940800 c/s virtual
Only one salt:	886784 c/s real, 895741 c/s virtual

$ ./john --test --format=DES --mkpc=1
Benchmarking: Traditional DES [128/128 BS SSE2]... DONE
Many salts:	7260 c/s real, 7260 c/s virtual
Only one salt:	7213 c/s real, 7213 c/s virtual

$ ./john --test --format=dummy
Benchmarking: dummy [N/A]... DONE
Raw:	20712K c/s real, 20712K c/s virtual

$ ./john --test --format=dummy --mkpc=1
Benchmarking: dummy [N/A]... DONE
Raw:	7965K c/s real, 8046K c/s virtual

$ ./john --test --format=bf
Benchmarking: OpenBSD Blowfish (x32) [32/32 X2]... DONE
Raw:	170 c/s real, 170 c/s virtual

$ ./john --test --format=bf --mkpc=1
Benchmarking: OpenBSD Blowfish (x32) [32/32 X2]... DONE
Raw:	84.1 c/s real, 85.0 c/s virtual

As you can see, DES takes a huge performance hit (the --mkpc=1 version
has less than 1% of the original version's speed).
This is to be expected, since the bitslice implementation doesn't make
any sense with a simulated buffer size of 1.

For dummy and bf, things look better.
(If I would want to get exact statistics for bf, I would nevertheless
use --format=bf without --mkpc=1, and replay everything with
--format=dummy --mkpc=1.)

Frank

Confused about mailing lists and their use? Read about mailing lists on Wikipedia and check out these guidelines on proper formatting of your messages.