Error detection/correction and fault detection/recovery – Data processing system error or fault handling – Reliability and availability
Reexamination Certificate
1999-07-27
2002-06-11
Le, Dieu-Minh (Department: 2184)
Error detection/correction and fault detection/recovery
Data processing system error or fault handling
Reliability and availability
C714S036000
Reexamination Certificate
active
06405329
ABSTRACT:
BACKGROUND
The disclosures herein relate generally to interfacing between a host computer system and a storage device, and more particularly, to a method and apparatus for hard disk drive time stamp benchmark and installation identification of the hard disk drive in a computer system.
The hard disk drive (HDD) industry is besieged with returned disk drives where the personnel receiving the reportedly failed HDD could not duplicate (CND) the reported failure. A new industry wide self-monitoring, analysis, and reporting technology (SMART) initiative is seeking to provide tools that can be incorporated within a hard disk drive to assist in failure analysis, prior to sending the disk drive back to the manufacturer. HDD's have a very impressive set of recovery mechanisms. The frequency of these events can indicate the pending failure of the device, but in many cases, the drive can successfully avert data loss and in-fact repair the drive without operator intervention or even knowledge that there was a potential problem with the device. One tool involves saving the error conditions, in some cases, with power on hours (POH's) of when an error occurred, in a reserved area of the hard disk drive. The saving of the POH's is only a partial solution, since POH's only increment when there is power applied to the hard disk drive.
In the past, a computer manufacturer has had to accept alleged defective hard disk drive devices back, with little troubleshooting in the field, since failure analysis in the field is generally difficult and time consuming. When there is any question about the health of the hard disk drive, the hard disk drive is generally sent back to the computer manufacturer, frequently CND. The return of hard disk drives that are CND negatively affects the reputation of the computer manufacturer and increases the computer manufacturer's initial failure incident rate (IFIR) on HDD's, one of the most expensive IFIR hits. IFIR is a metric used to measure failure of a product, i.e., a computer system, within a first thirty (30) day period of use in the field by a customer.
In addition to the above, while the return rate for HDDs may have gone down in recent history, the ever-increasing number of computer systems being shipped has resulted in an increase in the number of HDDs being returned. Tracking the hard disk drive through the return system at the factory and correlating the returned equipment activity logs from multiple databases has become very difficult. There are too many places in the returned equipment system at the factory where the hard disk drive device can be separated from the data stream, the data stream being one that permits meaningful information required for failure and trend analysis. While virtually all return activity of computer systems has been tracked in the past using a computer system service tag, a method is needed to semi-permanently mark a particular HDD as being a component of a particular computer system.
The prior methods for solving the above-mentioned problem relied on all repair personnel maintaining logs, tying the alleged defective component to the service tag of a given computer system. Paper logs were physically taped to the various device carriers used for transporting the defective devices, wherein the paper log method relied on HDDs always being returned to the appropriate carrier. In general, the previous system was not very-successful in accurately keeping track of a given HDD. With direct return, control of the tracking method needed to associate a given HDD device to the given HDD's prior computer system was lost.
An improved method and apparatus for tracking a given alleged failed HDD upon return to the factory for repair and error analysis is thus desired. In addition, a storage device having improved failure diagnostic capability is desired.
SUMMARY
According to one embodiment, the above problem is solved by the correlation of the POH's with a real date and time. A storage device includes at least one computer readable medium and an interface for use in coupling the storage device to a host. The interface is further for routing information to and from the at least one computer readable medium. At least one non-volatile buffer is located in a reserved area of the at least one computer readable medium. Lastly, an embedded controller with firmware is provided for logging characteristic operational information of the storage device in the at least one buffer upon an occurrence of an event initiated by the host. In addition to the characteristic operational information, at least a power on hours (POHs) and a corresponding time stamp information are provided.
The embodiments of the present disclosure advantageously provide an improved method of correlating the storage device to a computer system and correlating recent operating characteristics with the time and date of the behavior. In addition, the present embodiments provide an improved method and apparatus for tracking a given alleged failed HDD upon return to the factory for repair and error analysis.
REFERENCES:
patent: 4811278 (1989-03-01), Bean et al.
patent: 5613082 (1997-03-01), Brewer et al.
“Technical Committee T13 AT Attachment”, Updated Jul. 9, 1999, pp. 1-13.
Pete McLean, “SMART Device Error Log Reporting”, Oct. 15, 1998, pp. 1-10.
Mark Evans, “Proposal For Extensions To The SMART Protocol”, Dec. 11, 1998, pp. 1-8.
Thomas R. Colligan, “SMART Device Error/Activity Log Reporting”, Oct. 23, 1998, pp. 1-15.
Thomas R. Colligan, “Proposal For Extensions To The D98135RO”, Oct. 23, 1998, pp. 1-10.
“File Support For SMART Read/Write Logging And SMART Attributes And Thresholds”, Apr. 27, 1999, pp. 1-4.
Western Digital, “Proposed Modification To Self-Test Log Descriptors”, Feb. 11, 1999, p. 1.
Mark Evans, “Proposal For Modification To The SMART Self-Test Log Structure”, Feb. 23, 1999, p. 1.
Peter T. McLean, “Information Technology—AT Attachment With Packet Interface—5 (ATA/ATAPI-5)”, Mar. 5, 1999, p. 1-348.
Brandt Craig
Colligan Thomas R.
Dell USA L.P.
Haynes and Boone LLP
Le Dieu-Minh
LandOfFree
Method and apparatus for HDD time stamp benchmark and... does not yet have a rating. At this time, there are no reviews or comments for this patent.
If you have personal experience with Method and apparatus for HDD time stamp benchmark and..., we encourage you to share that experience with our LandOfFree.com community. Your opinion is very important and Method and apparatus for HDD time stamp benchmark and... will most certainly appreciate the feedback.
Profile ID: LFUS-PAI-O-2921220