US5130992A
Expired / Lapsed
US
⏱️ 0.0 years remaining
File-based redundant parity protection in a parallel computing system
Assignee: International Business Machines Corp
•
Filing: 1990-04-16
•
Granted: 1992-07-14
•
Expires: 2010-04-16
Abstract
Abstract This is method for parity protecting distributed data files in a multi-node, parallel data processing network, with each node having a data store. Each data file is organized as a series of fixed size file data blocks, each file data block being comprised of a block identifier and a plurality of data bit positions. The method comprises: distributing at least N-1 file data blocks across N-1 nodes, each of the N-1 file data blocks being stored in a data store at an available physical location, which physical location may be selected from any within an area of the data store reserved for file data blocks, each data store having an associated directory indicating where each file data block is located; exclusive OR'ing data bits in corresponding bit positions in each of the N-1 file data blocks; and storing the Exclusive OR results in corresponding bit positions of a parity file data block in a data store in node N.
Inventors
- 👤 Alexander H. Frey, Jr.
- 👤 Richard C. Mosteller
Bibliographic Details
Application Number
—
Jurisdiction
US
Data Source
google_patents
Last Synchronized
2026-10-24 14:24
CPC Classifications
G; G06; G06F; G06F11/00; G06F11/07; G06F11/08; G06F11/10; G06F11/1076; G06F11/14; G06F11/1402; G06F2211/00; G06F2211/10; G06F2211/1002; G06F2211/1028
Claims Analysis
Total Claims: 10
Claim 1
Independent Claim
165 words
A method for parity protecting distributed data files in a multi-node computer network having at least N nodes, each node having data storage means, each data file organized as a series of file data blocks, each data block being comprised of a block identifier and a plurality of data bit positions, the method comprising: a. distributing at least N-1 file data blocks across N-1 nodes, each of said N-1 file data blocks being stored in a physical location in a data storage means, said physical location selected from any available physical location within an area of said data storage means allocated for file data blocks, each said data storage means maintaining a directory of where each file data block is located therein; b. exclusive OR'ing data bits in corresponding data bit positions in each of said N-1 file data blocks; and c. storing the results of step b in corresponding bit positions of a parity data block in a data storage means in node N.
Claim 2
Independent Claim
165 words
A method for parity protecting distributed data files in a multi-node computer network having at least N nodes, each node having data storage means, each data file organized as a series of file data blocks, each data block being comprised of a block identifier and a plurality of data bit positions, the method comprising: a. distributing at least N-1 file data blocks across N-1 nodes, each of said N-1 file data blocks being stored in a physical location in a data storage means, said physical location selected from any available physical location within an area of said data storage means allocated for file data blocks, each said data storage means maintaining a directory of where each file data block is located therein; b. exclusive OR'ing data bits in corresponding data bit positions in each of said N-1 file data blocks; and c. storing the results of step b in corresponding bit positions of a parity data block in a data storage means in node N.
Claim 3
Dependent Claim
29 words
The method of claim 1 wherein steps a-c are repeated across another set of N-1 nodes of said multi-node computer network for succeeding groups of N-1 file data blocks.
Claim 4
Dependent Claim
24 words
The method of claim 2 wherein each of said file data blocks in a given file has an identical number of data bit positions.
Claim 5
Dependent Claim
38 words
The method of claim 3 wherein, said nodes are sequential and step (a) further comprises the step of: a1. serially storing across sequential nodes in their respective data storage means, interspersed file data blocks and parity data blocks.
Claim 6
Dependent Claim
52 words
The method of claim 3, wherein said nodes are sequential, and step (a) further comprises the steps of: a1. serially storing across sequential nodes in their respective data storage means, file data blocks; and a2. storing in areas in said data storage means, segregated from said file data blocks, parity data blocks.
Claim 7
Dependent Claim
81 words
The method of claim 1 wherein in response to the failure of one said N nodes, every file data block stored in the data storage means in said failed node is reconstructed by the steps of: d. exclusive OR'ing data bits and parity bits from corresponding bit positions in the data storage means in non-failed ones of said N nodes; and e. storing the results of step (d) in an operational node separate from said non-failed ones of said N nodes.
Claim 8
Independent Claim
91 words
A method for parity protecting a file system distributed across a multi-node, parallel computing system, comprising the steps of: a. allocating and storing a sequential series of N-1 file data blocks across N-1 separate nodes, said file data blocks having no predetermined physical storage relationship across said nodes; b. exclusive-OR'ing values in corresponding bit positions in said series of file data blocks to derive a parity data block; and c. storing said parity data block in an Nth node, said Nth node not being identical with any of said N-1 nodes.
Claim 9
Independent Claim
91 words
A method for parity protecting a file system distributed across a multi-node, parallel computing system, comprising the steps of: a. allocating and storing a sequential series of N-1 file data blocks across N-1 separate nodes, said file data blocks having no predetermined physical storage relationship across said nodes; b. exclusive-OR'ing values in corresponding bit positions in said series of file data blocks to derive a parity data block; and c. storing said parity data block in an Nth node, said Nth node not being identical with any of said N-1 nodes.
Claim 10
Dependent Claim
72 words
The method of claim 7 wherein in response to the failure of one of said N nodes, a file data block stored in a failed node is reconstructed by the steps of: d. exclusive OR'ing data bits and parity bits from corresponding bit positions in non-failed ones of said N nodes; and e. storing the results of step (d) in an operational node separate from said non-failed ones of said N nodes.
References Cited (Backward Citations)
US4396983A
Cited
US4430699A
Cited
US4412285A
Cited
US4817035A
Cited
US4722085A
Cited
US4761785A
Cited
US4761785B1
Cited
US4914656A
Cited
US4989205A
Cited
USPTO Annuity & Maintenance Windows
| Annuity Stage | Window Opens | Payment Deadline | Surcharge Period Until | Estimated Fee | Status |
|---|---|---|---|---|---|
| 3.5 Years (Year 4) | 1995-07-14 | 1996-01-13 | 1996-07-14 | $2000.00 | Window Closed / Lapsed |
| 7.5 Years (Year 8) | 1999-07-14 | 2000-01-13 | 2000-07-14 | $3760.00 | Window Closed / Lapsed |
| 11.5 Years (Year 12) | 2003-07-14 | 2004-01-13 | 2004-07-14 | $7700.00 | Window Closed / Lapsed |