Scyld ClusterWare

After evaluating multiple cluster management products, we chose Scyld ClusterWare for the processing of large amounts of image data. Scyld ClusterWare contains a robust, easy-to-use and unique Single System Image architecture, which we believe will resonate well with researchers using the SOLiD platform for a wide variety of applications,

Life Technologies

Dr. Timothy Burcham, Senior Director of SOLiD R&D at Life Technologies.

Overview

Scyld ClusterWare is a complete HPC cluster management solution that is scalable, flexible, and easy to use. It is fully compatible with RedHat Enterprise Linux and CentOS. Scyld ClusterWare offers

  • Super-fast cluster provisioning
  • Single System Image Architecture that guarantees configuration consistency
  • Support for internal clouds and cloud bursting
  • Web-service-based architecture for management and workflow submission from anywhere
  • Qualification and optimization for Penguin hardware for an optimal user experience
  • Certification as Intel Cluster Ready reference architecture for SSI clusters

Scyld ClusterWare, the web-enabled cluster management software system that ‘just works’
Start evaluating Scyld ClusterWare today after filling out our short sign-up form.

Scyld ClusterWare management diagram

Features and Benefits

Scyld ClusterWare offers: many important features and benefits.

Fast Provisioning - Shorter Time to Productivity, Quick and Easy Scale Out

Compute nodes are provisioned from the master node over the network with a lightweight, cluster-aware operating environment that resides entirely in memory. Compute nodes can be replaced quickly and a cluster can be scaled out just by adding systems to a rack and powering them up.

Single System Image - Cluster Management Made Easy

The master node is the central point of control for the entire cluster. Scyld ClusterWare only uses one set of configuration files on the master node. Compute nodes are provisioned using software images on the master and libraries and device drives are loaded as needed. This design eliminates the possibility of version and configuration inconsistencies and makes management of Scyld ClusterWare almost as easy as managing a single system.

One Process Space for the Entire Cluster - Complete Process Visibility and Control at All Times

Scyld ClusterWare aggregates process information from all compute nodes and propagates process control signals from the master node to the respective compute node(s). This unified process space gives the cluster the appearance of a single SMP system. A direct login into a Scyld ClusterWare compute node is never required. Managing processes in the cluster is as easy as managing processes on a single system.

‘Beoweb’ Web Service Architecture – Remote and Secure Access from Anywhere

Scyld ClusterWare’s built-in web service Beoweb exposes Scyld functionality for cluster management, monitoring and job submission through APIs for integration in web applications. A corresponding set of client tools packaged with Scyld ClusterWare enables secure, remote job submission and data staging from any system with internet connectivity.

Directory Services - Seamless Integration with Existing Infrastructures

Scyld ClusterWare combines cluster specific user- and host name resolution services with generic directory services. The resolution of cluster internal names is handled efficiently while the resolution of external host or user names can be passed on to global directory services such as NIS+ or LDAP. Integration of directory services with Scyld ClusterWare only requires client access for the master node making it easy to integrate Scyld ClusterWare with existing infrastructures.

Integrated Workload Management - Optimized Resource Utilization

Resource managers in conjunction with schedulers arbitrate resource demand and supply. The Torque resource manager and scheduler is pre-configured with Scyld ClusterWare and fully supported by Penguin; we fully support other schedulers, such as Sun's Grid Engine are fully supported. For advanced scheduling needs, Penguin Computing offers Adaptive Computing’s Moab scheduler.

Standards-based - Runs on Commodity Hardware, Supports Standard Linux Distributions

Scyld ClusterWare runs on any system based on the x86-64 processor architecture. Scyld ClusterWare is layered on top of a standard Linux distribution, typically RedHat Enterprise Linux or CentOS and is package based (RPMs). Upgrades are generally as easy as executing a single command. Scyld also supports ‘hybrid’ clusters that comprise native ‘lightweight’ Scyld compute nodes in conjunction with compute nodes that run a different operating system installed to a local hard drive, for example SuSE Enterprise Linux.

Commercial Support - Get Help from the Experts

Scyld ClusterWare was developed in-house and is supported by Penguin Computing's cluster experts. We have worked closely with many application providers and customers. Expertise down to the source code level is always at hand.