Philip Lee Childs - Raleigh NC, US Donald R. Frame - Apex NC, US Jeffrey R. Hobbet - Holly Springs NC, US Howard Jeffrey Locker - Cary NC, US Michael Terrell Vanover - Raleigh NC, US
Assignee:
Lenovo (Singapore) Pte. Ltd. - Singapore
International Classification:
G06F 15/177
US Classification:
713 2, 713 1, 713100
Abstract:
A system, method, and program product is provided that recovers from a sector error affecting a critical file. A damaged sector prevents a critical file from being read prevents the computer system from booting. A controller records a sector number corresponding to the damaged sector. The system is rebooted using an alternative boot media. The system accesses the primary nonvolatile storage media after the rebooting. The damaged sector number is read from the error log and a file map is used to determine the critical file that is stored in the damaged sector. A backup copy of the critical file is retrieved from a backup media. The backup copy is written to the primary media using undamaged sectors and the critical file is mapped to the undamaged sectors. The system is subsequently booted successfully from the primary nonvolatile storage media.
Asymmetric Load Balancing For Raid Storage Systems
Jeffrey R. Hobbet - Holly Springs NC, US Donald R. Frame - Apex NC, US Daryl Cromer - Cary NC, US Michael S. Mettler - Durham NC, US
Assignee:
Lenovo (Singapore) Pte. Ltd. - Singapore
International Classification:
G06F 12/00 G06F 12/16
US Classification:
711114, 711E12001, 711E12103, 710301
Abstract:
The instant invention broadly contemplates balancing of asymmetric RAID arrays based on application usage patterns. The instantly claimed invention broadly contemplates balancing the type of workload and delivery of the work load in asymmetric RAID arrays by intelligently implementing different types of applications on disks strategically positioned to deliver workload to the RAID channel that is most capable of handling the work load. The invention makes use of the fact that some applications are more large block, sequential transfer dependant while other applications are more small block, high random, high IOP dependent, and places these applications accordingly within the asymmetric RAID array.
Method And Apparatus For Automatic Solid State Drive Performance Recovery
Donald R. Frame - Apex NC, US Jeffrey R. Hobbet - Holly Springs NC, US Michael Scott Mettler - Durham NC, US Kenneth Dean Timmons - Raleigh NC, US
Assignee:
Lenovo (Singapore) Pte. Ltd. - Tech Park
International Classification:
G06F 12/00 G06F 13/00 G06F 13/28
US Classification:
711162, 711103, 711171
Abstract:
A method and apparatus are disclosed for automatic solid state drive performance recovery. A detection module detects a first SSD exceeding a fragmentation threshold. A plurality of drives comprises the first SSD and stores a data copy of data stored on the first SSD. An erase module erases a mapping table for the first SSD. The mapping table maps Logical Block Addresses LBA to physical addresses for the first SSD. A rebuild module rebuilds the data and the mapping table on the first SSD from the data copy.
Jeffrey R. Hobbet - Holly Springs NC, US Donald R. Frame - Apex NC, US David Timothy Zimmerman - Raleigh NC, US
Assignee:
Lenovo (Singapore) Pte. Ltd. - Singapore
International Classification:
G06F 12/00
US Classification:
711103, 711118
Abstract:
An approach is provided that loads software files, such as an operating system, on a hybrid storage device. The hybrid storage device is a device that includes a nonvolatile storage device and a nonvolatile memory cache. The nonvolatile memory cache has less storage capacity than the nonvolatile storage device. The nonvolatile memory cache is preset (“pinned”) to data corresponding to an initial set of address ranges of the nonvolatile storage device, such as all or part of the operating system that was loaded onto the nonvolatile storage device. A system usage metric is initialized along with a threshold value. The nonvolatile memory cache remains pinned to the initial set of address ranges until the system usage metric reaches the threshold value. When the system usage metric reaches the threshold value, then a caching algorithm is used to determine what data should be cached to the nonvolatile memory cache.
Apparatus, System, And Method For Memory Configuration Analysis
Daryl Cromer - Cary NC, US Donald R. Frame - Apex NC, US Michael Scott Mettler - Durham NC, US Kenneth Dean Timmons - Raleigh NC, US
Assignee:
Lenovo (Singapore) Pte. Ltd. - Tech Park
International Classification:
G06F 3/03 G06F 3/00 G06F 3/023 G06F 3/027
US Classification:
702186, 702185, 702188, 702189
Abstract:
An apparatus, system, and method are disclosed for memory configuration analysis. A classification module determines an overall performance of an array of memory devices in a computer memory , wherein overall performance has a substantially inverse relationship with a highest quantity of members of a subset of the array and a substantially direct relationship with an individual performance capability of the members. A counting module takes a count of members of the array whose individual performance capability varies in a selected direction from the overall performance of the array. A comparison module takes a selected action such as issuing a memory configuration warning if the count crosses a predetermined threshold comprising a predetermined percentage for comparison with the count, as qualified by the individual performance capability, divided by an unqualified count of members of the array.
Apparatus, System, And Method For Memory Upgrade Path Optimization
Daryl Cromer - Cary NC, US Donald R. Frame - Apex NC, US Michael Scott Mettler - Durham NC, US Kenneth Dean Timmons - Raleigh NC, US
Assignee:
Lenovo (Singapore) Pte. Ltd. - Tech Park
International Classification:
G06F 12/00
US Classification:
711114, 711 5, 711104, 711105, 711170
Abstract:
An apparatus, system, and method are disclosed for memory upgrade optimization. A requirements module receives one or more of a capacity upgrade goal for an overall capacity of the array and a performance upgrade goal for an overall performance of the array. An analysis module identifies a first potential capacity change that can be achieved at a lower overall performance and a second potential capacity change that can be achieved at a higher overall performance. A reconfiguration module generates one or more of a first reconfiguration recommendation calculated to yield an overall capacity improvement that takes into consideration the capacity upgrade goal and the first potential capacity change and a second reconfiguration recommendation calculated to yield an overall performance improvement that takes into consideration the performance upgrade goal and the second potential capacity change.
Jeffrey R. Hobbet - Holly Springs NC, US Daryl Cromer - Cary NC, US Donald R. Frame - Apex NC, US Masahiko Nagai - Kanagawa, JP Tin-Lup Wong - Chapel Hill NC, US
International Classification:
H02P 1/00 H02P 3/00 H02P 5/00
US Classification:
318270
Abstract:
Arrangements and methods for implementing a “spin-down policy” for HDD motors that is “smart”, flexible and admirably achieves an objective of ensuring prolonged motor life as just discussed. To this end, one specific implementation involves (among other things) the addition of a dedicated cache that acts as a buffer element of sorts for writing or obtaining data during a period when a motor may be spun down, especially (but not necessarily exclusively) in instances when a notebook needs to be running for a large portion of the day. Other analogous implementations are of course possible that would achieve similar ends.
Techniques For Background Testing A Hard Disk Drive
Robert B. Postage - Hillsborough NC, US Donald R. Frame - Apex NC, US Pamela A. Morse - Durham NC, US Stanley H. Osgood - Hillsborough NC, US
International Classification:
G06F 11/267
US Classification:
714 34, 714E11165
Abstract:
A technique for background testing a hard disk drive, when an associated system is powered and the hard disk drive is available, includes receiving an interrupt test indication that indicates that the background testing of the hard disk drive is to be interrupted. The technique also includes discontinuing, at a current test location, the background testing of the hard disk drive in response to the interrupt test indication. Finally, current test results are saved in response to the interrupt test indication.
Donald M. Frame (born 1911 in Manhattan - died March 8, 1991, in Alexandria, Virginia), a scholar of French Renaissance literature, was Moore Professor ...
Donald Frame (1960-1964), Sky Blue (1968-1972), Denise Matte (1982-1986), Linda Bourque (1968-1972), Lucille Bourgeois (1952-1956), Sara Lavergne (1978-1982)