To maintain their competitive advantage, Cray’s customers need to squeeze out every ounce of value from their supercomputing investments. And to sustain maximum value, even the most resilient systems will undergo a multitude of underlying repairs and upgrades over their life span. Keeping pace with system changes while meeting the operational uptime requirements of today’s state-of-the-art supercomputers is making advanced system support tools a necessity.
To support its customers’ 24/7 operations while keeping users as productive as possible, Cray is launching the first stages of a new support framework. As part of this framework, Cray will be leveraging decades of field support experience to deliver new and improved system analysis tools and methodologies.
Proactively Address Your System’s Health with Cray SSA
The System Snapshot Analyzer (SSA) is a managed technology program designed to collect and analyze customer system information such as major software release versions, updates, patches, system state and error logs. Classified as a ‟call-home” program, SSA is a distributed application that securely monitors and analyzes machine information from Cray customer systems, and then directs corrective actions or triage.
With SSA, we can help customers leverage trend identification, system configuration analysis, version interactions, component dependencies, upgrade tracking and more.
With SSA, Cray is targeting three areas of improvement:
- Reducing turnaround time for the collection of data in response to customer inquiries and issues;
- Improving the detection of and resolution time for customer system issues; and
- Improving Cray’s knowledge of the product configurations in the field throughout their life cycle.
Collect – Upload – Analyze – Act
Automated and remote system status checks, or “snapshots,” reduce the overhead imposed on users and can save time when failures or issues occur. In turn, end users are able to accelerate support diagnosis and time to resolution. SSA collects specific metrics and measurements for Cray systems over user-scheduled periods of time, then securely uploads and warehouses that data at Cray via an advanced and mature remote monitoring program.
As a foundation of historical data is built, the direction is to provide streamlined support processes that can detect updates, upgrades, problematic configuration settings and degrading system conditions, and can help expedite system health triage activity.
With the configurability that the new SSA architecture affords, Cray’s goal over time is to integrate SSA as a standard interface across all Cray platforms. Through standardization with SSA, we envision a new class of productive customer-service features. We are building SSA to complement existing and future Cray system monitoring and diagnostic capabilities, not to supplant them. In addition to instrumenting current platforms with SSA, architectural teams across Cray are working to ensure it is a standard component of future products.
Leverage Cray’s domain knowledge and technology
Over the years Cray has strategically invested in its global support organization. Such investments, we believe, better position us to serve our growing customer base. We recently created U.S.- and EMEA-based remote (support) groups and an advanced technical support group in EMEA (Europe, the Middle East and Africa). Our U.S.-based central support team is also growing.
To complement our established support expertise, we continually evaluate the methods and technologies used to deliver world-class customer service. In addition to our core case management and software delivery services, we have invested in knowledge management, project and time management, training and documentation. We are also reviewing our current customer portal technology in preparation for a more featured successor.
What’s good for our users is also good for Cray.