GPFS/TSM Day during SPXXL Winter Workshop 2016

(Posted on behalf of Stefano from SPXXL):

During February we had a wonderful GPFS Day during the SPXXL Winter Meeting that took place at LRZ in “Garching bei München, Germany”.

For those who are not familiar, here are a few notes on what SPXXL is and does:

SPXXL is a user group for sites which have large installations of IBM or Lenovo equipment. The focus of the SPXXL group is on large-scale scientific/technical computing using IBM or Lenovo hardware. Some of the areas we cover are: Applications, Code Development Tools, Communications, Networking, Parallel I/O, Resource Management, System Administration, and Training. We address topics across a wide range of issues that are important to sustained petascale scientific/technical computing on scaleable parallel machines.

The SPXXL is a self-organized and self-supporting group. Members and affiliates are expected to participate actively in the SPXXL meetings and activities and to cover their own costs for participating. SPXXL meetings are open only to members and affiliates of the SPXXL. SPXXL member institutions must have an appropriate non-disclosure agreement in place with IBM and Lenovo, since at times both vendors disclose and discuss information of a confidential nature with the group. Beginning in 2015 the winter workshop was focused on Lenovo and their partners and the summer workshop will be focused on IBM and their partners.

Coming back to the GPFS Day, as usual, it was one of the most important days of the SPXXL week where we went through many interesting arguments approached mainly from a user prospective with no intent to do any kind of marketing.
As a speaker, we had 3 IBM people (1 GPFS developer, 1 TSM/HSM Developer and 1 IT Specialist), 1 Lenovo and 2 Site updates from the community.

I have been really surprised by people engagement during and after the presentations. Every speaker included has been really open and willing to get any possible challenge creating an atmosphere of a real user group meeting.

Another nice surprise has been to get direction from IBM developers on what they expect from a user when there is a problem. It has been a kind of myth buster on what a standard user does and on what should be done in order to help debugging.

This has been the kind of day we had and we hope to do this more often under the umbrella of SPXXL & GPFSUG.

May 2016 UK User Group

The UK May user group will take place over two days on 17th and 18th May 2016 at the IBM Client Centre in South Bank, London. We’d like to thank IBM and our sponsors for supporting the event and the evening networking/social event on the evening of 17th May 2016.
As usual we’ll have a packed agenda with speakers from the IBM development teams, user talks as well as technical talks from our sponsors. This is the first year we’ve run a two day user group event, so we’re hoping it’ll be a great event with more talks and networking opportunities than ever before! And in addition to that, we’ve planned a networking/social event just a few minutes walk from the user group venue where we’ll have food, drinks, pool, ping-pong, bowling and tokens for the machines and bumper cars! … Anyone for an IBM vs tournament?


The slides from the day are now available on the presentations page.

The agenda for the day is a bit further down the page…


We’d very much like to thank the following sponsors for supporting the user group meeting by providing funding to support the evening social event:



Day 1 – 17th May 2016

10:00 Registration & Coffee
10:30 Opening & Welcome – Simon Thompson & Claire O’Toole
10:45 Keynote talk – Doris Conti
11:05 4.2 Roadmap & 2016 Priorities, Ulf Troppens
11:35 Deep Dive – 4.2 GUI & Live Demo, Markus Rohwedder
12:05 Sponsor Talk 1 – Seagate: Using Spectrum Scale in the IoT World, Ray Coetzee
12:25 Lunch & Networking
13:25 Sponsor Talk 2 – ArcaStream: Python API & Demo, Jez Tucker
14:00 User Talk 1 – NCAR’s Globally Accessible Data Environment, Pamela Gillman, NCAR
14:20 Sponsor Talk 3 – NetApp: TBC, Mohinder Toor
14:40 User Talk 2 – Milk flows freely from London to Cardiff with AFM, Dave Goodbourn, Milk Visual Effects
15:00 Deep Dive – Hadoop Integration, Piyush Chaudhary
15:30 Coffee Break
16:00 Sponsor Talk 4 – Mellanox: Accelerating storage functions in a co-design network, Darren Harkins
16:20 Technical Deep Dive – Tiering to the Cloud / MC Store, Robert Basham
16:50 Technical Deep Dive – Problem Determination Enhancements, Mathias Dietz
17:50 Wrap-up
18:00 Finish
18:30 Evening Social Event – Namco Funscape

Day 2 – 18th May 2016

09:00 Arrival & Coffee
09:30 Parallel Talk Session

  • Talk 1: Licensing, David Cremise
  • Sponsor Talk 5 – OCF: Scale out NAS for the masses, Laurence Horrocks-Barlow
10:00 Parallel Breakout/workshop session 1

  • Spectrum Scale ILM & Spectrum Archive, Nils Haustein (introductory)
  • Metadata sizing / tuning, Indulis Bernsteins, Madhav Ponamgi (advanced)
  • Upcoming GUI Enhancements / I have a Spectrum Scale question, Markus Rohwedder, Sven Oehme, Olaf Weiser
11:00 Parallel Breakout/workshop session 2

  • AFM Introduction and use cases, Madhav Ponamgi (introductory)
  • Spectrum Protect Integration & Best Practices, Nils Haustein (Backup and HSM) (advanced)
  • Upcoming GUI Enhancements / I have a Spectrum Scale question, Markus Rohwedder, Sven Oehme, Olaf Weiser
12:00 Parallel Breakout/workshop session 3

  • Encryption / Compression, Olaf Weiser, Yoann Lechevallier (introductory)
  • Spectrum Protect with Spectrum Scale, Nils Haustein (Backup and HSM) (advanced)
  • Upcoming GUI Enhancements / I have a Spectrum Scale question, Markus Rohwedder, Sven Oehme, Madhav Ponamgi
13:00 Lunch & Networking
14:00 Sponsor Talk 6 – DDN: Adventures in AFM, Vic Cornell
14:20 Deep Dive – OpenStack Integration, Gaurang Tapase
15:00 Sponsor Talk 7 – IBM: Life Sciences, Frank Lee
15:20 Coffee Break
15:50 Sponsor Talk 8 – Lenovo, Michael Hennecke
16:10 A look into the future by IBM Research, Sven Oehme
17:10 Wrap-up and feedback
17:30 Finish


To register for this year’s event, please use our EventBrite event page at:

Registration opens for users from 14th March 2016.

Please note that we are currently limiting registrations to 3 per organisation to ensure as many organisations as possible are able to attend and places are strictly limited due to room capacity. We will be operating a wait list, so if you can’t get a ticket now, then we’ll hold details in case they become available nearer the date.

May User group meeting … save the date!

The next UK user group meeting will be held on May 17th and 18th 2016. This will be our first venture into a two day event and we still have a fun packed agenda!

We’ll be opening user registrations in mid March, so check back for registration details and agenda then.

We’d like to thank our sponsors from ArcaStreamDDNIBMLenovoNetAppMellanox and OCF for supporting the user group with speakers and supporting the evening networking/social event on 17th.


Performance Round Table – Round Two

On January 12th, Paul Roberts, Patrick Byrne, Sophie Carsten and I ran a second iteration of performance talks with a small subset of UK Spectrum Scale users. As Paul covered in a previous post, the goal of the meeting was to have an informal chat with these users to gain insights on how they use their clusters, what issues they have concerning their cluster’s performance, and what we can do to help improve the product. We met in the IBM Manchester Development Lab, which allowed us to have developers from the performance, install and upgrade, and system health teams available to discuss the product.

As is the case with all Spectrum Scale User Group meetings, the participants were very happy and open to discuss their Spectrum Scale deployments with us. Since the meeting was designed to be an open and free-flowing meeting, there were a few issues raised by the users and our conversations ebbed and flowed from there.

Continue reading “Performance Round Table – Round Two”