[<prev] [next>] [<thread-prev] [thread-next>] [day] [month] [year] [list]
Message-ID: <CA+E3k92kC3910wxrFgCZNtxyGqLHJv6SfrEHdD4d9fDdXpfLMg@mail.gmail.com>
Date: Wed, 5 Aug 2020 15:38:29 -0800
From: Royce Williams <royce@...ho.org>
To: john-users@...ts.openwall.com
Subject: Re: sha512crypt-opencl / Self test failed (cmp_all(1))
On Wed, Aug 5, 2020 at 11:07 AM Solar Designer <solar@...nwall.com> wrote:
> On Wed, Aug 05, 2020 at 10:47:23AM -0800, Royce Williams wrote:
> > FWIW, I have recently been consistently getting the same self-test errors
> > on sha512crypt-ztex.
>
> Not exactly a topic for this thread (I wish you had started a new one
> for that), but please do share more on those errors - what has changed
> in your setup (hardware? John version?), are the errors for all boards
> or only some, if only software changed then do the errors go away when
> you revert? Anyway, there's little we can do about that. You can try
> troubleshooting your setup. You can also try lowering the clock rate.
>
> Out of the 5 bitstreams, the sha512crypt+Drupal7 one consumes the most
> power (and produces the most heat) when in active use. It's about 44W
> per board, vs. e.g. 27W for bcrypt. (As measured at the 12V input.) So
> if e.g. some of your cooling fans failed, that may show up on
> sha512crypt and Drupal7 first.
>
> I'd show you how sha512crypt-ztex still passes self-test on my 4 boards,
> but Aleksey is using them precisely for sha512crypt-ztex at the moment
> for his skills warm-up for the upcoming contest. So I assume it passed
> self-test for him OK. ;-)
>
Heh, indeed. Thanks for the tips. I'll definitely start another thread if
general troubleshooting doesn't resolve it for me.
I had no idea whether this issue was fork-related or OpenCL-related. For
all I knew, the issue might only emerge when forking reaches a certain
device count, which would explain why I'm seeing it on ZTEX when others
might not. My reasoning was that if the same error was appearing on a
non-OpenCL system, that this might be a diagnostically useful data point,
and was therefore topical for the thread. As someone not steeped in john's
development, this line of reasoning seemed ... reasonable. :)
But since that's not the case, I'll stop hijacking this thread. :)
Royce
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.
