Follow @Openwall on Twitter for new release announcements and other news
[<prev] [next>] [<thread-prev] [day] [month] [year] [list]
Date: Fri, 12 Aug 2011 07:39:08 -0700 (PDT)
From: firstname lastname <>
Subject: Re: JTR MPI in Virtual Machine - Stats Prob

At first, why does my name display here as "firstname, lastname"? It's configured correctly in my mail as Neon Flash. Anyway, this is off topic, but would be glad if someone could answer this.

Ok, the solution was simple. I just had to configure the number of processor cores in the VMWare Workstation for my Ubuntu VM Image.

By default it was set to 1 processor, 1 core. I changed it to 1 processor, 4 cores.

cat /proc/cpuinfo | grep processor

processor: 0
processor: 1
processor: 2
processor: 3

cat /proc/cpuinfo | grep processor | wc -l


Now, there's a significant increase in the value of real c/s while benchmarking.

mpirun -np 4 ./john --format=DES --test

Many salts: 8935K c/s real, 8940K c/s virtual
Only one salt: 7594K c/s real, 7602K c/s virtual

This is good! :)


--- On Thu, 8/11/11, Stephen John Smoogen <> wrote:

> From: Stephen John Smoogen <>
> Subject: Re: [john-users] JTR MPI in Virtual Machine - Stats Prob
> To:
> Date: Thursday, August 11, 2011, 11:53 PM
> On Thu, Aug 11, 2011 at 06:56,
> firstname lastname
> <>
> wrote:
> > Hello Alexander and others,
> ring, if this problem is due to any of the following
> reasons:
> >
> > I am running JTR inside a Virtual Machine. It reports,
> 0 processors. There's no change in the real c/s value.
> >
> > Please let me know, where I am going wrong with this
> and if you need more information in order to point me in the
> right direction.
> Well first, what are you expecting? You have a system with
> 1
> processor. [It doesn't report 0 processors, it reports that
> it has one
> processor in the 0 slot (C arrays start counting from 0
> versus 1).] So
> your aren't going to see any real increase because MPI is
> not going to
> go out to other processors. In order for MPI or other tools
> to make it
> go faster, they are going to need to have more processors
> to run on.
> I believe you are seeing the virtual go up because you have
> created 4
> processes all running at X/sec. Now I doubt they would
> really perform
> at that long term because without additional
> cores/processors/etc you
> are only getting any "throughput" via processor
> acceleration tricks
> (they work short term but will shut down when the processor
> overheats
> etc.)
> > Regards,
> > NeonFlash
> >
> >
> -- 
> Stephen J Smoogen.
> "The core skill of innovators is error recovery, not
> failure avoidance."
> Randy Nelson, President of Pixar University.
> "Let us be kind, one to another, for most of us are
> fighting a hard
> battle." -- Ian MacLaren

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.