Chris,
Is anyone working on DMTCP or MANA going to start monitoring the
dmtcp-forum mailing list? If you remember, I reached out here about
having trouble getting DMTCP to work, and posted a call for help on that
mailing list. I still subscribe to that mailing list, and I've seen
several other people post to that mailing list, but no one from DMTCP or
MANA ever replies there.
The DMTCP web page (https://dmtcp.sourceforge.io/contactUs.html) says
that is the way to contact the DMCTP developers, but it seems that no
one monitors that mailing list.
Prentice
On 2/18/23 3:42 PM, Christopher Samuel wrote:
Hi all,
The list has been very quiet recently, so as I just posted something
to the Slurm list in reply to the topic of checkpointing MPI
applications I thought it might interest a few of you here (apologies
if you've already seen it there).
If you're looking to try checkpointing MPI applications you may want
to experiment with the MANA ("MPI-Agnostic, Network-Agnostic MPI")
plugin for the DMTCP C/R effort here:
https://github.com/mpickpt/mana
We (NERSC) are collaborating with the developers and it is installed
on Cori (our older Cray system) for people to experiment with. The
documentation for it may be useful to others who'd like to try it out
- it's got a nice description of how it works too which even I, as a
non-programmer, can understand.
https://docs.nersc.gov/development/checkpoint-restart/mana/
Pay special attention to the caveats in our docs though!
I've not used it myself, though I'm peripherally involved to give
advice on system related issues.
I'm curious if there are other methods that people are using out there
for transparent checkpointing of MPI applications?
All the best,
Chris
_______________________________________________
Beowulf mailing list, Beowulf@beowulf.org sponsored by Penguin Computing
To change your subscription (digest mode or unsubscribe) visit
https://beowulf.org/cgi-bin/mailman/listinfo/beowulf
