Moabcon 2012 Technical Sessions

Moabcon 2012 Technical Sessions


Click Here to view an overview of Moabcon, including dates and activities

Click here to register for Moabcon 2012.

Monday, April 9

7:00 – 9:30 pm
Welcome Reception

  • Presenter: Chad Harrington | Vice President of Marketing, Adaptive Computing
  • Entertainment: Adaptive Computing Band – ACE

Tuesday, April 10

7:45 – 8:45 am
Breakfast at The Company Provision Restaurant – Sponsored by Cray

8:45 – 9:15 am
Keynote by Rob Clyde, CEO Adaptive Computing

9:15 – 10:15 am
Product Roadmap and Customer Feedback Round Table

Presenter: Lane Franks

Abstract:
Last year at Moabcon, Adaptive asked its customers what was needed and wanted. Adaptive listened. Lane Franks will take us through 2012′s road map and then turn the time over to its customers to give Adaptive feedback. Each table will have an Adaptive representative to listen and learn to help mold the future of Moab.

10:15 – 10:30 am
Break

Track 1 Track 2
10:30 – 11:20 am
Scalability – How to configure and manage scalability for Moab and Torque

Presenters: Jason Booth and David Beer

Abstract:
Many changes have been made to Moab and TORQUE recently to enhance the scalability. This lecture will summarize the changes that have been made, as well as discuss the benefits of each. We will also discuss what situations these changes have been made for, and what settings users can adjust to best take advantage of the changes. This should help users and administrators best take advantage of these improvements and provide the knowledge required for adjusting these features when they aren’t working as expected.

Customer Case Study

Presenter: Bryan Caron, Compute Canada

Abstract:
The High Performance Computing Centre at McGill University in Montreal, Quebec is a leading member of Canada’s national HPC platform for the advancement of scientific research and innovation. The centre’s latest system, Guillimin, was launched in June 2011 and currently consists of 14,400 processor cores and 2 PetaBytes of storage. The facility serves a community of nearly 1000 users and 350 research groups from across Canada and beyond, and serves as a Tier-2 centre for the Worldwide LHC Computing Grid.

In this talk we will outline the experiences of the centre with Moab and Torque in providing a scalable, performant system for managing and processing workloads for a diverse community of users. Aspects of that experience to be discussed include the use of hierarchical fair share trees, resource management for overall system stability, and scheduler tunings to enable high throughput submission of workloads. The plans for the growth of the centre in 2012 will also be described with an emphasis on scheduler scalability and flexibility to meet the operational challenges in that environment.

10:30 – 11:20 am
Job Arrays – Deep Dive Moab and TORQUE

Presenters: Ken Nielsen and Julie Banks

Abstract:
This presentation will introduce Moab and TORQUE job arrays and how they differ. We will discuss how to configure TORQUE and Moab so job arrays get along between the two systems. We will discuss syntax, system configuration, cancellation policies for Moab and dependencies for TORQUE.

 

11:30 – 12:00 pm
Industry Trends – Chris Willard, Intersect 360

12:00 – 1:00 pm
Lunch

12:00 – 12:30 pm
Presenter: Penguin Computing

Abstract:

12:30 – 1:00 pm
Customer Speaker – GTSWD
Georgia Tech Cluster Management

Presenter: Paul Manno

Abstract:
Based on 15 years experience, the Georgia Tech PACE team has opted for a stateful system management approach, avoiding re-imaging for node updates. The GTSWD (Georgia Tech SoftWare Distribution) system has become an integral and efficient way to manage OS, libraries, authorization, and user-experience code on nearly 1000 compute, storage, and head nodes.

Track 1 Track 2
1:00 – 1:50 pm
Productivity Acceleration – Auto Power Management

Presenter: Ryan Chabot

Abstract:
Included in Moab HPC Suite – Enterprise Edition, the Auto Power Management feature enforces user-specified policies to determine when to migrate jobs and control the power of individual nodes. Adaptive Computing’s goal is to enable customers to take advantage of system downtime by consolidating jobs or even turning off machines, enabling both optimized performance and energy cost savings. In this session we will be covering some real world scenarios of how Auto Power Management has benefited Adaptive Computing Customers and walk-through the configuration of this feature. After this course, Moab users should be able to enable the Auto Power Management feature, create policies and fully understand how it may benefit business.

Customer Case Study

Presenter: Michael Jennings, Lawrence Berkeley National Laboratory

Abstract:
The Warewulf 3 project is reinventing HPC management and provisioning from the ground up to be modular, scalable, and simple. Moab’s intelligence engine provides unprecedented flexibility and control over resources and policy. We hope to combine these tools’ unique capabilities to create an energy-efficient, environmentally aware solution for computational resource delivery.

1:00 – 1:50 pm
Moab Viewpoint – HPC

Presenter: Mike Saavedra

Abstract:
At the Viewpoint 7.0 Presentation, we will discuss many different aspects of Viewpoint for both the HPC and Cloud centric audiences, along with topics that are common to all Moab Viewpoint customers. Our main focus will be on: 1) New Features, 2) Administration, 3) Configuration, and 4) Troubleshooting. Then there will be a Q&A session as long as time permits.

2:00 – 2:50 pm
Productivity Acceleration – Intelligent Optimized Scheduling/Policy Based Scheduling

Presenter: Trev Harmon

Abstract:
In this session we will discuss the Moab scheduling cycle, priority system, placement strategies, future reservations and how they interact to provide optimized scheduling in an HPC environment. This session will focus on the concepts with limited configuration “how-to” discussion.

2:00 – 2:50 pm
Moab Web Services – Customizing Portal Easier way to Integrate HPC

Presenters: Sean Moe and Nathan Wells

Abstract:
This session will demonstrate how to write a web application that submits jobs to Moab using Moab Web Services (MWS). Also explained will be the principles, which define the MWS interface, and the future of integrating Moab into your solution.

Customer Case Study

Presenter: Ross G. Miller, Oak Ridge National Laboratory

Abstract:
Managing A Dedicated Cluster Using Moab Web Services: Scientists analyzing neutron scattering data at the Oak Ridge National Laboratory use a custom written package called Mantid. These datasets are becoming too large to analyze on a single workstation. This talk discusses efforts to interface a dedicated compute cluster to the existing Mantid GUI using Moab Web Services.


3:00 – 3:30 pm Break

3:00 – 3:30 pm Break
3:30 – 4:20 pm
Productivity Acceleration – Workload Optimized Provisioning and Scheduling/Windows and Linux OS

Presenter: Brian Saville

Abstract:

Customer Case Study 1

Presenter: Jonathan Hunt, Birmingham University

Abstract:
Case Study carried out at the University of Birmingham UK, comparing and contrasting the scheduler in Windows 2008 HPC Server R2 and MOAB. Additional work was undertaken with Adaptive to integrate the schedulers using MSMHPC, with a view to implementing this on our incoming Windows cluster.

Customer Case Study 2

Presenter: Mariana Cristina Coelho, Eng., Institute of Technology for Development LACTEC

Abstract:
Our team was participating on a multidisciplinary project to develop a methodology to solve economic dispatch considering the Brazilian electrical system. The tests needed to be performed on both Windows and Linux operational systems on a very short period. Moab allowed us to do this. It has been helping us to manage our cluster resources to conclude our project.

3:30 – 4:20 pm
HPC Transformation with HP Insight CMU and Moab HPC

Presenters: Alanna Dwyer, Clusters Marketing Manager, HP ISS Hyperscale – HP

Michael Jackson, Founder and President – Adaptive Computing

Abstract:
This session will address how HP Insight CMU and Moab provide solutions to address the limitations within today’s HPC environments. Topics will include:

  • Insight CMU overview and base capabilities
  • Dynamic workload management with Moab HPC integration
  • Deploying a private cloud with Insight CMU and Moab (dynamic resource management)
  • Demonstration of the CMU/Moab integration
  • Cloud bursting and remote visualization
  • Discussion of future use case priorities
  • Sneak peek of the HP ProLiant portfolio for Hyperscale
4:30 – 5:30 pm
Uptime Automation – Preventing Failures, Service and Support, Auto Response, Triggers and Demo

Presenters: Chad Harrington and Tim Shaw

Abstract:
Restarting HPC jobs costs you time and money. This session focuses on how you can use Moab to protect your jobs and increase uptime. We’ll discuss how to use Moab to:

  • Minimize failure through job placement
  • Automatically respond to failures
  • Set up maintenance window
4:30 – 5:30 pm
GPGPU – Deep Dive Scheduling

Presenter: John Rosenquist

Abstract:
In the last year we have greatly expanded our support for GPGPUs. This lecture will discuss setup and configuration, as well as best practices. We will be covering the different options for setup in depth and explains the reasons for the different options and the ‘gotchas’ for setting them up, as well as how users should alter their scripts to take advantage of these features. Additionally, we will give a demo to preview the support for GPGPUs on Cray hardware, and briefly discuss the setup for those systems. This should help both the users and the administrators take advantage of these new features and know how to use them in their clusters.

Customer Case Study

Presenter: Troy Baer, Senior HPC System Administrator, NICS

Abstract:
GPU Scheduling at NICS: The Good, the Bad, and the Weird

The National Institute for Computational Sciences operates two systems with GPU resources: Nautilus, a 1024-core SGI UV-1000 used for analysis and visualization; and Keeneland, an 120-node HP cluster used for GPU experimentation and code development. This talk will discuss experiences with GPU scheduling using TORQUE and Moab on these two systems.

5:30 – 6:30 pm
Break

6:30 pm
Transportation for the Evening’s Event

7:00 – 9:00 pm
HP Presents a Night at the Olympics

Gondola Ride to the top of the mountain, Zip Lining, Olympic Games, Networking, Dinner

Wednesday, April 11

7:30 – 8:30 am
Breakfast – sponsored by NICE Software

8:30 – 9:15 am
Keynote by HP

“The Morning Panel: What’s Happening in the Cloud”

Abstract:
Is the Cloud for you? Join HP executives, Marc Hamilton and Jerome Labat, in a lively discussion on the State of Cloud Technology, and what it means for HPC and beyond, moderated by Adaptive Computing CEO Rob Clyde. Marc and Jerome will share HP’s experiences in deploying cloud technology, lessons learned, and share perspectives on where cloud computing can have the most impact, and considerations unique to HPC deployments.

9:15 – 9:45 am
Media Speaker – Steve Campbell, HPC in the Cloud

9:45 – 10:00 am
Break

Track 1 Track 2
10:00 – 10:50 am
Best Practices for Setting Polices – Tips and Tricks

Presenter: Josh Butikofer

Abstract:
Moab has a lot of “policies.” But what exactly constitutes a policy? How are they best configured? Comes learn about some of Moab’s most used policies and how to get them working in your environment.

10:00 – 10:50 am
Cloud Track – Introduction to Cloud for HPC

Presenter: Dan Croft

Abstract:
A brief introduction to the world of cloud from an HPC point of view. We will explore the core concepts of a public and private cloud setup and see how these can benefit traditional HPC workloads. We will look at Moab’s new cloud model and how it can be used in a traditional HPC environment and look ahead to where cloud and HPC are going in the future.

11:00 – 11:50 am
Open Source – TORQUE Case Study Session

Customer Case Study 1

Presenter: Jenett Tillotson, Indiana University

Abstract:

  • An overview of Indiana University cluster compute systems and user base
  • TORQUE queue design
  • Compare and contrast LoadLeveler and TORQUE
  • Priority algorithms focused on fair share, X-factor, and parallel job prioritization
  • User limits to prevent queue stuffing
  • Job prioritization using the QOS system versus node reservations

Customer Case Study 2

Presenter: Michael Jennings, Lawrence Berkeley National Laboratory

Abstract:
TORQUE has long offered the ability to periodically monitor compute node health and report misconfigured or failed nodes. Sites often overlook this feature or use ad hoc, homegrown scripts to perform the checks they need. Mr. Jennings will present a flexible, extensible alternative, which are both a working implementation and a model/framework for node health checks.

11:00 – 11:50 am
Cloud Track – What’s New – Moab Cloud Suite 7.0

Presenter: Luis Silva and Ken Baldwin

Abstract:
In this presentation we will be covering the new exciting features of Moab Cloud Suite 7.0 xCAT edition. For this release, we focused heavily around enhancing the user experience and providing our customers with tools that make their lives easier.One example of this is our Service Catalog Manager, where our customers can define service dependency flows to more easily automate the provisioning process for their users. With it, administrators can easily define new catalog entries and so that their users can submit new service requests without having to go through tedious and costly bureaucratic processes. We will also be doing a demo focused around “a day in the life” of an admin and an end user, showing how admins can create cost centers in the Moab Accounting Manager, allocate users to them, creating new service templates and having users request these in just a few minutes.

 

12:00 – 12:30 pm
Industry Trends – Rich Tehrani, Cloud Computing Magazine

12:00 – 1:00 pm
Lunch

12:30 – 1:00 pm
Keynote: Michael Jackson | President and Founder, Adaptive Computing

Abstract:

1:00 – 1:30 pm
Customer Speaker – NCSA

Private Sector Program – Accelerating Business with HPC as a service
Presenter: Merle Giles

Abstract:

Track 1 Track 2
1:30 – 2:20 pm
Grid and Multi Cluster Management Customer Case Studies

Case Study 1

Presenter: Troy Baer, Senior HPC System Administrator, NICS

Abstract:
Techniques for Balancing Capability and Capacity Workloads for Maximum UtilizationWorkloads on HPC resources are generally considered either “capability” (a few large jobs) or “capacity” (many small jobs). However, it is possible to have both types of workloads coexist on the same system using a few straightforward scheduling techniques. This talk will discuss how those techniques have been applied at the National Institute for Computational Sciences.

Case Study 2

Presenter: Frederick Lefebvre, Compute Canada

Abstract:
Colosse is a mid-size cluster used for academic research deployed at CLUMEQ/Universite Laval in late 2009. This 7680 cores system, initially using Sun Grid Engine, was transitioned to TORQUE/Moab in 2012. This talk will focus on our experience in migrating from Grid Engine to Moab.

1:30 – 2:20 pm
Cloud Track – Moab Cloud Suite 7.0 CSA Edition Overview with HP(Partner Technical Session)

Presenter: Nathan Wells

 

Abstract:
Get a close up look at Moab Cloud Suite – CSA Edition with a demonstration, and presentation on how the integration works.

Partner Presentation

Presenters: Mak Ghangurde, James Matthews

Abstract:
An overview of HP Cloud Service Automation (with Moab Cloud Suite) – a new partnership and product offering between HP and Adaptive Computing that offers enterprises the foundation to venture into the cloud and evolve to the cloud needs of tomorrow. This session will focus on CSA’s new Advanced Workload Management functionalities that can help enterprises dynamically allocate resources and adapt to changing resource requirements.

2:30 – 3:20 pm
Auto SLA Enforcement – SLA, Priority Policies and QOS

Presenter: Brian Christiansen

Abstract:
Configuring Real-World SLA’s in Moab.This session will go over several real-world examples of SLA’s and how they can be configured in Moab. Examples include:

  • Sharing heterogeneous sets of nodes that have specific owners.
  • Giving node access to developers during the day for testing.
  • Assigning priority based on job size.

Customer Case Study

Presenter: Matt Ismail, University of Warwick

Abstract:
UK University HPC service provision is currently expanding in both scope and scale. Universities are now expected to build on their established central HPC services to contribute resources into geographically distributed national facilities and construct regional e-infrastructure intended to catalyse engagement with industry. This talk will describe how Moab is applied at the Centre for Scientific Computing, University of Warwick to implement the diverse set of policies and service levels required of a multi-tier HPC facility. There will be particular emphasis on the fundamentals of scheduling such as ensuring fairness, delivering quality of service and managing mixed workloads from various application domains and external organisations.

2:30 – 3:20 pmCloud Track – Cloud Bursting for HPC

Presenter: Scott Bateman

Abstract:
Sharing resources between 2 compute clusters can grant users from both the benefit of on-demand elasticity in their resource pool. Moab’s HPC Cloud Bursting offering connects separate groups of compute resources and allows one to assume control over nodes from the other based on sophisticated, customizable rules of priority and preemption.

3:30 – 3:40 pm Break 3:30 – 3:40 pm Break
3:40 – 4:30 pm
Auto SLA Enforcement – Usage Accounting Manager

Presenter: Scott Jackson

Abstract:
This session will introduce the Moab Accounting Manager and describe how it can be used for usage tracking, charge accounting and allocation enforcement. We will demonstrate using Moab Accounting Manager in an HPC context to establish per-project limits on the use of compute resources.

Customer Case Study

Presenter: Andrew Caird, University of Michigan

Abstract:
Using Gold, Moab, and Torque to Run a Campus-wide Allocation-based HPC Service

The University of Michigan has moved some condo-style cluster workload to an allocation-based system that is based on Gold with some extensions, the Moab Identity Manager, Moab, and Torque. Using those tools we support over 150 research projects and maintain high-resource utilization in a financially sustainable hardware and software ecosystem.

3:40 – 4:30 pm
Cloud Track – Application Integration Portal/Visualization

Presenter: Nick Ihli

Abstract:
With Moab, NICE DCV and Enginframe site’s can consolidate expensive high-end GPU workstations providing users greater access to high-performance visualization of complex 3D interactive application alongside traditional HPC workload. The rendering is accomplished in the “cloud” and instead of moving data, pixels are sent to the remote display.

4:40 – 5:30 pmAuto SLA Enforcement – Continuous and Future Scheduling, Reservation and Preemption

Presenter: Douglas Wightman

Abstract:
Moab is the most advanced scheduler on the planet. This session will explain how to take advantage of Moab’s patented reservation scheduling and preemption engine. Learn how to maximize your system’s resources while delivering the fastest response to your users.

4:40 – 5:30 pm
Cloud Track – Cloud Pay Per Use Accounting/Showback/Chargeback Accounting

Presenter: Scott Jackson

Abstract:
This session will describe the use of the Moab Accounting Manager within a cloud context and will go into greater depth about customizing the usage record and creating a customized departmental hierarchy.

 

5:30 – 6:30 pm
Break

6:30 pm
Transportation for Evening’s Event

7:00 – 9:00
Downtown Park City – Dinner and Pub Crawl

Thursday, April 12

7:30 – 8:30 am
Breakfast – sponsored by Bright Computing

8:30 – 9:15 am
Customer Keynote by Preston Smith – Purdue University

9:15 – 10:15 am
2012 New Product – Moab HPC Suite 7.0 – What’s New

Presenter: Brady Kimball

Abstract:
The Moab HPC Suite 7.0 has been designed to accelerate productivity by providing reliable scalability and improved usability monumental. This session will highlight what’s new to Moab 7.0, Torque 4.0, Moab Web Services, and the updated Moab Viewpoint.

10:15 – 10:30 am
Break

 

Track 1 Track 2
10:30 – 11:20 am
2012 Moab HPC Suite 7.0 – TORQUE 4.0 – Lessons Learned and Best Practices

Presenter: Ken Nielson

Abstract:
How Does TORQUE 4.0 Change Your JobTORQUE 4.0 added new capabilities, which in practice will change the way administrators need to tune their systems. This presentation will discuss key new features and how they change the behavior of TORQUE as well as how to tune the new features to take advantage of the full power of TORQUE. Features to be discussed include setting up a MOM hierarchy; at what number of nodes do you need to use a MOM hierarchy, setting a thread pool size, TCP communications change and job radix.

10:30 – 12:20 pm
Training Moab Diagnostics and Troubleshooting

Presenter: Shawn Hoopes

Abstract:
Have you ever wondered why your jobs end up in a Deferred state? In this session, you will learn why and much more, by understanding the Moab scheduling cycle and determine where to troubleshoot job issues along this path. You will learn how to effectively use the mdiag and other troubleshooting commands, how to look at log and event files and check the messages, notify Admins when handling certain events, how to track system failures, and learn how to use the included diagnostic scripts.

11:30 – 12:20 pm
2012 New Product – 7.0 Upgrade Path / Migration

Presenter: Ryan Chabot

Abstract:
Upgrading Moab HPC Suite can be complicated at times and it is vital to understand the process of upgrading between major versions. This session will cover the installation / upgrade best practices as presented by members of the Adaptive Computing support group. Topics include: Operating System configuration, verifying proper permissions, ensuring correct file locations, installing updated binaries, database upgrades and insights in to what and upgrade modifies and installs. We will also discuss some of the most common trouble areas related to upgrading and how to troubleshoot and fix these issues. After this course, you should be able to migrate or upgrade your Moab HPC Suite with a full understanding of the process.

 

12:30 – 2:00 pm
Lunch

Keynote:

Dave Jackson, CTO – Adaptive Computing, the AC Labs Team, and Customer Panel

“What’s the Future: Adaptive and its Customers”

Closing Remarks – Chad Harrington, Vice President of Marketing – Adaptive Computing