[Beowulf] more automatic building

Thu Oct 6 02:46:15 PDT 2016

Hi,

In the same vein, Benoit (cc of this mail) created an automatic way to 
install a whole cluster based on centos/salt/slurm... Take a look here : 
https://github.com/oxedions/banquise

On my side, I play with LXD to automate all this stuff (but I thought 
about doing it with singularity too). The main idea is to have a stable 
OS on the hardware that you do not need to (re-)install anymore but just 
some containers that you can move or resize to fit your needs. I do not 
know how exactly, but IMHO, I think our work should move to this kind of 
DevOps things as in the cloud area. Actually I have some salt recipies 
to orchestrate hardware reinstallation for some nodes (not all my 
clusters), and then, I apply automatically other formulas to deploy the 
containers based on some specifications.

Best regards,

Remy

Le 29/09/2016 à 13:33, Olli-Pekka Lehto a écrit :
> We have our latest cluster software stack for a distributed set of 
> clusters built on Ansible:
> https://github.com/CSC-IT-Center-for-Science/fgci-ansible
>
> A recent presentation at the SLURM User Group on Ansiblizing SLURM:
> https://gitpitch.com/CSC-IT-Center-for-Science/ansible-role-slurm/gitpitch
>
> I see benefits also in being able to share playbooks and collaborate 
> on improving them with other teams in our organization and the 
> Universities, even ones working in non-HPC areas.
>
> Best regards,
> Olli-Pekka
> -- 
> Olli-Pekka Lehto
> Development Manager
> Computing Platforms
> CSC - IT Center for Science Ltd.
> E-Mail: olli-pekka.lehto at csc.fi
> Tel: +358 50 381 8604
> skype: oplehto // twitter: ople
>
> ------------------------------------------------------------------------
>
>     *From: *"Craig Andrew" <cbandrew at wi.mit.edu>
>     *To: *"Tim Cutts" <tjrc at sanger.ac.uk>
>     *Cc: *beowulf at beowulf.org
>     *Sent: *Wednesday, 28 September, 2016 18:01:59
>     *Subject: *Re: [Beowulf] more automatic building
>
>     I agree with Tim.
>
>     We are finishing up an Ansible install and it has worked well for us.
>
>     Initially, we used it internally to help standardize our cluster
>     builds, but is has many more uses. We recently used it to
>     provision a VM that we saved off and uploaded to Amazon for
>     building an AMI. You can also use it to change attributes on your
>     running systems. I have used at Cobler in the past and it works
>     well, too. I just find Ansible to be a little easier.
>
>     Good luck,
>     Craig
>
>     Craig Andrew
>     Manager of Systems Administration
>     Whitehead Institute for Biomedical Research
>
>     ------------------------------------------------------------------------
>     *From: *"Tim Cutts" <tjrc at sanger.ac.uk>
>     *To: *"Mikhail Kuzminsky" <mikky_m at mail.ru>, beowulf at beowulf.org
>     *Sent: *Wednesday, September 28, 2016 10:46:41 AM
>     *Subject: *Re: [Beowulf] more automatic building
>
>     Any number of approaches will work.  When I used to do this years
>     ago (I've long since passed on the technical side) I'd PXE boot,
>     partition the hard disk and set up a provisioning network and base
>     OS install using the Debian FAI (Fully Automated Install) system,
>     and then use cfengine to configure the machine once it had come in
>     that minimal state.  This approach was used across the board for
>     all of our Linux boxes, from Linux desktops to database servers to
>     HPC compute nodes.
>
>     These days the team uses tools like cobbler and ansible to achieve
>     the same thing. There are lots of ways to do it, but the principle
>     is the same.
>
>     Tim
>
>     -- 
>
>     Head of Scientific Computing
>
>     Wellcome Trust Sanger Institute
>
>     On 28/09/2016, 15:34, "Beowulf on behalf of Mikhail Kuzminsky"
>     <beowulf-bounces at beowulf.org <mailto:beowulf-bounces at beowulf.org>
>     on behalf of mikky_m at mail.ru <mailto:mikky_m at mail.ru>> wrote:
>
>         I worked always w/very small HPC clusters and built them
>         manually (each server).
>         But what is reasonable to do for clusters containing some tens
>         or hundred of nodes ?
>         Of course w/modern Xeon (or Xeon Phi KNL) and IB EDR, during
>         the next year for example.
>         There are some automatic systems like OSCAR or even ROCKS.
>
>         But it looks that ROCKS don't support modern interconnects,
>         and there may be problems
>         w/OSCAR versions for support of systemd-based distributives
>         like CentOS 7. For next year -
>         is it reasonable to wait new OSCAR version or something else ?
>
>         Mikhail Kuzminsky,
>         Zelinsky Institute of Organic Chemistry RAS,
>         Moscow
>
>
>     -- The Wellcome Trust Sanger Institute is operated by Genome
>     Research Limited, a charity registered in England with number
>     1021457 and a company registered in England with number 2742969,
>     whose registered office is 215 Euston Road, London, NW1 2BE.
>     _______________________________________________
>     Beowulf mailing list, Beowulf at beowulf.org sponsored by Penguin
>     Computing
>     To change your subscription (digest mode or unsubscribe) visit
>     http://www.beowulf.org/mailman/listinfo/beowulf
>
>     -- 
>     ___________________________________________
>
>
>
>     _______________________________________________
>     Beowulf mailing list, Beowulf at beowulf.org sponsored by Penguin
>     Computing
>     To change your subscription (digest mode or unsubscribe) visit
>     http://www.beowulf.org/mailman/listinfo/beowulf
>
>
>
> _______________________________________________
> Beowulf mailing list, Beowulf at beowulf.org sponsored by Penguin Computing
> To change your subscription (digest mode or unsubscribe) visit http://www.beowulf.org/mailman/listinfo/beowulf

-- 
Rémy Dernat
Ingénieur d'Etudes
MBB/ISE-M

-------------- next part --------------
An HTML attachment was scrubbed...
URL: <http://www.beowulf.org/pipermail/beowulf/attachments/20161006/9f402d16/attachment.html>