Follow @Openwall on Twitter for new release announcements and other news
[<prev] [next>] [<thread-prev] [thread-next>] [day] [month] [year] [list]
Date: Wed, 9 Nov 2016 23:18:33 +0100
From: Patrick Proniewski <>
Subject: Re: alter default rules or filter, best way to focus on proper candidates?

On 09 nov. 2016, at 22:12, Solar Designer wrote:

> On Wed, Nov 09, 2016 at 02:50:33PM +0100, wrote:
>> If I understand correctly, "./john --wordlist=spanish.dic --rules=jumbo" will not create candidates as fast as it could consume them against Raw-SHA1.
> It might or it might not, but your tests don't show either way because
> they may very well be bottlenecked by "--stdout", even when you're
> directing output to /dev/null.  You should test performance with an
> instance of your target hash type, not with "--stdout".  Computing a raw
> SHA-1 hash is possibly quicker (on average, amortized with SIMD) than
> outputting a candidate password to a pipe.

I've made a test with proper data (27131539 password hashes with no different salts): 

$ ./john --format=Raw-SHA1 --wordlist=spanish.dic --rules=jumbo ~/WORK/dump-sha1 --pot=dumb.pot
0g 0:00:02:52 DONE (2016-11-09 22:42) 0g/s 3329Kp/s 3329Kc/s 90635GC/s voluntariosamen..zarrapastrosame

$ ./john --format=Raw-SHA1 --wordlist=spanish.dic --rules=jumbo --max-length=10 ~/WORK/dump-sha1 --pot=dumb.pot
0g 0:00:01:55 DONE (2016-11-09 22:44) 0g/s 1914Kp/s 1914Kc/s 52330GC/s ZURRIAGAZO..ZURRUMBERA

$ ./john --format=Raw-SHA1 --wordlist=spanish.dic --rules=jumbo --external=Filter_LowerNum ~/WORK/dump-sha1 --pot=dumb.pot
0g 0:00:03:23 DONE (2016-11-09 22:49) 0g/s 1005Kp/s 1005Kc/s 27279GC/s zzutanoz..zzuzoz

$ ./john --format=Raw-SHA1 --wordlist=spanish.dic --rules=jumbo --external=Filter_LowerNum --max-length=10 ~/WORK/dump-sha1 --pot=dumb.pot
0g 0:00:02:19 DONE (2016-11-09 22:52) 0g/s 862940p/s 862940c/s 23532GC/s zzuzarz..zzuzoz

I'm quite surprised by the relative slowness of "--external=Filter_LowerNum" alone: 1min more than "--external=Filter_LowerNum --max-length=10".
The shortest is "--max-length=10", followed by "--external=Filter_LowerNum --max-length=10", then vanilla, and the longest is "--external=Filter_LowerNum" alone.
The fastest is vanilla with 90635GC/s, followed by "--max-length=10" (42% slower), then "--external=Filter_LowerNum". And the slowest is "--external=Filter_LowerNum --max-length=10" achieving about 26% of vanilla's performance.


Powered by blists - more mailing lists

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