|
IBM's years of development experience at building RAS capabilities into mainframes and mission-critical servers coupled with extensive field experience have been applied to the IBM eServer™ pSeries 680.
Features like:
- automatic error capture and isolation capabilities,
- dynamic error recovery,
- error checking and correction (ECC) protection on main memory, L1 and L2 caches and internal processor arrays,
- bit steering and scrubbing on main memory,
- fault tolerance with N+1 redundancy and concurrent maintenance for power and cooling,
- predictive failure analysis on processors, memory, I/O and DASD,
- processor run-time and boot-time deallocation based on run-time errors (Dynamic CPU Deallocation and Persistent CPU Deallocation),
- highly reliable components,
- and concurrent run-time diagnostics,
provide these servers with industry-leading RAS features. Excellent quality and reliability are inherent in all facets of the pSeries 680 product. These measures are designed to ensure that products operate when required, perform reliably, efficiently handle infrequent failures in a nondisruptive fashion, and provide timely repair in many cases either concurrently or on a deferred basis to allow operational resumption with minimal inconvenience.
Reliability is one of the most significant factors in the design of high-end products. RAS (Reliability, Availability, and Serviceability) is an integral part of the pSeries 680 and AIX* Version 4 philosophy. It begins with the development of architectures, where RAS innovations are of paramount importance. It flows through design and product development stages, where RAS designs are reviewed, assessed, developed, evaluated, and perfected. It continues through the manufacturing and release processes, where the manufacturing quality is extensively measured and is under continual evaluation. It culminates in service and support; where the reliability is consistently monitored for deviation from the criteria, where warranty and maintenance have high priority, and where significant customer problems are assigned to and addressed by an expert team.
All of the development processes, from the architectural and concept phases of development, through the manufacturing process, and culminating in the provision of service and support are ISO** certified and audited periodically for ISO compliance by representatives of Underwriters Laboratories.
|