[<prev] [next>] [<thread-prev] [thread-next>] [day] [month] [year] [list]
Message-ID: <20111120041319.GA8685@openwall.com>
Date: Sun, 20 Nov 2011 08:13:19 +0400
From: Solar Designer <solar@...nwall.com>
To: john-users@...ts.openwall.com
Subject: Re: OpenMP not using all threads
On Sat, Nov 19, 2011 at 10:38:30PM -0500, Stephen Reese wrote:
> Thanks for the quick response. There are 42 hashes and 42 unique salts
> (13/node). I am going to change this so there are 42 hashes per node
> and specify the length, (1-6, 7, 8 for All.chr).
>
> OpenMP has consistently been around 5000K but I tested another
> recommendation of yours for running non-OpenMP due to the previously
> discussed system load woes (GOMP_SPINCOUNT did not help). Four
> non-OpenMP run at 2000K and a fifth at ~1000K using the same john.pots
> and password file via multiple sessions--they seem to even out after a
> bit but a combined 9000K is great! This is what I was looking for.
It is unclear how you distribute the workload among these 5 processes.
And why 5? If you have 8 logical CPUs, then you need 8 processes to use
the machine optimally. You'd have 6 of them run on 5 hashes each, and 2
on 6 hashes each. As passwords will be getting cracked, the numbers of
hashes per process will be non-equal anyway, so that's sort of OK.
Alexander
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.
