Browse Prior Art Database

Method of Storing Hardware Scan Data

IP.com Disclosure Number: IPCOM000013355D
Original Publication Date: 2001-Jun-10
Included in the Prior Art Database: 2003-Jun-18

Publishing Venue

IBM

Abstract

In the past, the scan dump routine collects hardware scan data after a system error. Typically, this data is stored in Non Volatile Random Access Memory (NVRAM). Upon completion of storing the hardware scan data into NVRAM, the scan dump routine sets a "valid" bit. During the next system boot, another software component, Run Time Abstract Services (RTAS) examines the "valid" bit. If the "valid" bit is set, RTAS reads the scan data from NVRAM and passes the data to the Operation System for Service Engineer to analyze. As systems are getting more complex, the scan data increases in size and no longer fits into a reasonably-sized NVRAM. Without a solution, only a very small portion of scan data is available for the Service Engineer to analyze the problem after system failure. To resolve the problem, the hardware scan data is moved to a different persistent memory area: the Persistent Control Store space in Service Processor (SP) memory. This space offers roughly 10 times more storage space than NVRAM at a given cost. Additional complexity is required in using the SP Persistent Control Store, however. The SP allocates space from the Persistent Control Store during SP initialization.