US5857112A
Expired / Lapsed
US
⏱️ 0.0 years remaining
System for achieving enhanced performance and data availability in a unified redundant array of disk drives by using user defined partitioning and level of redundancy
Assignee: Hitachi Computer Products (America) Inc
•
Filing: 1992-09-09
•
Granted: 1999-01-05
•
Expires: 2012-09-09
Abstract
Abstract The present invention provides a system of hardware and software that combine to efficiently integrate the various requirements for system performance and system reliability in a RAID system. A user of the present invention is able to select from a range of system performance and reliability configurations, independently of each other. From user specifications, the present invention initially constructs a user space which must be mapped onto the physical storage space in the array of disk drives. The present invention preserves the orthogonality of performance and reliability concepts through a series of mappings that relate to these concepts independently as it transforms user space into the physical space of the disk array.
Inventors
- 👤 Ebrahim Hashemi
- 👤 Martin Schulze
- 👤 Jim Morris
- 👤 Bob Harper
- 👤 Swami Nathan
- 👤 Paul Boulay
- 👤 Dave Scheffey
Bibliographic Details
Application Number
—
Jurisdiction
US
Data Source
google_patents
Last Synchronized
2026-11-02 05:00
CPC Classifications
G; G06; G06F; G06F11/00; G06F11/07; G06F11/08; G06F11/10; G06F11/1076; G06F11/1096; G06F11/16; G06F11/20; G06F11/2053; G06F2211/00; G06F2211/10; G06F2211/1002; G06F2211/103
Claims Analysis
Total Claims: 21
Claim 1
Independent Claim
237 words
In a data storage system for storing host data upon user request comprising a computational section, a data bus controller, a data bus responsive to signals from said data bus controller, a plurality of peripheral controllers coupled to said data bus, a plurality of data storage devices coupled to each said peripheral controllers, said data storage devices providing a physical storage space for the storage of said host data, and at least one host controller coupled to said data bus; a method for orthogonally mapping a subset of host data, whereas different subsets of data contains associated parameters, from user specifications for system performance and data availability onto said physical storage space, said method comprising the steps of: (a) receiving as an input user specifications associated with a subset of host data to be stored in said storage system, said user specifications including the average command size in said subset, the overall size of said subset and the meantime between data loss desirable for said subset of host data; (b) calculating a partition for said subset of said host data, said partition sized using said user specifications for the average command size and the overall size of said subset; (c) calculating the level of redundancy for said subset of said host data using said user specification for meantime between data loss; and (d) mapping the resulting redundancy group formed in step (c) into said physical storage space.
Claim 2
Dependent Claim
237 words
In a data storage system for storing host data upon user request comprising a computational section, a data bus controller, a data bus responsive to signals from said data bus controller, a plurality of peripheral controllers coupled to said data bus, a plurality of data storage devices coupled to each said peripheral controllers, said data storage devices providing a physical storage space for the storage of said host data, and at least one host controller coupled to said data bus; a method for orthogonally mapping a subset of host data, whereas different subsets of data contains associated parameters, from user specifications for system performance and data availability onto said physical storage space, said method comprising the steps of: (a) receiving as an input user specifications associated with a subset of host data to be stored in said storage system, said user specifications including the average command size in said subset, the overall size of said subset and the meantime between data loss desirable for said subset of host data; (b) calculating a partition for said subset of said host data, said partition sized using said user specifications for the average command size and the overall size of said subset; (c) calculating the level of redundancy for said subset of said host data using said user specification for meantime between data loss; and (d) mapping the resulting redundancy group formed in step (c) into said physical storage space.
Claim 3
Dependent Claim
49 words
The method as recited in claim 1 wherein the step of calculating a partition for the subset of host data using user specifications further comprises the steps of: determining the stripe degree from user specifications for system performance; determining the stripe unit size from user specification for system performance.
Claim 4
Dependent Claim
61 words
The method as recited in claim 2 wherein the step of determining the stripe degree from user specifications for system performance further comprises calculating the stripe degree according to the formula: ##EQU4## where L=the average command size, M=the stripe degree, D=the drive controller latency, S=the average seek time, R=the average rotational latency on a drive, and N=the total number of drives.
Claim 5
Dependent Claim
32 words
The method as recited in claim 2 wherein the step of determining the stripe degree from user specifications for system performance further comprises calculating the stripe degree according to the formula: ##EQU5##
Claim 6
Dependent Claim
40 words
The method as recited in claim 2 wherein the step of determining the stripe unit size from user specifications for system performance further comprises setting the stripe unit size equal to the average command size divided by the stripe degree.
Claim 7
Dependent Claim
80 words
The method as recited in claim 1 wherein the step of calculating the level of redundancy for said partition using user specifications for data availability further comprises the steps of: calculating the mean time between data loss according to the formula ##EQU6## where MTBDL=mean time between data loss MTBF=mean time between failure MTTR=mean time to repair; choosing the level of redundancy for said partition that gives the least upper bound on the mean time to data loss specified by user.
Claim 8
Dependent Claim
57 words
The method as recited in claim 6 wherein the step of choosing the level of redundancy for said partition that gives the least upper bound on the mean time to data loss specified by user further comprises choosing the greatest number of levels of redundancy offered by the system if said least upper bound does not exist.
Claim 9
Dependent Claim
184 words
A data storage apparatus having a computational section, a data bus controller, a data bus responsive to signals from said data bus controller, a plurality of peripheral controllers coupled to said data bus, a plurality of data storage devices coupled to each of said peripheral controllers, said data storage devices providing a physical storage space for the storage of host data, at least one host controller coupled to said data bus, said data storage apparatus comprising: means for calculating a partition required to store a subset of said host data, whereas different subsets of data contains associated parameters, said means for calculating a partition receiving as an input user specifications for the average command size in said subset and the overall size of said subset, said partition sized based on said average command size and said overall size; means for calculating a level of redundancy for said subset using user specifications for the meantime between data loss; means for creating a redundancy group from said partition and said calculated level of redundancy; and means for mapping said redundancy group into said physical storage space.
Claim 10
Dependent Claim
184 words
A data storage apparatus having a computational section, a data bus controller, a data bus responsive to signals from said data bus controller, a plurality of peripheral controllers coupled to said data bus, a plurality of data storage devices coupled to each of said peripheral controllers, said data storage devices providing a physical storage space for the storage of host data, at least one host controller coupled to said data bus, said data storage apparatus comprising: means for calculating a partition required to store a subset of said host data, whereas different subsets of data contains associated parameters, said means for calculating a partition receiving as an input user specifications for the average command size in said subset and the overall size of said subset, said partition sized based on said average command size and said overall size; means for calculating a level of redundancy for said subset using user specifications for the meantime between data loss; means for creating a redundancy group from said partition and said calculated level of redundancy; and means for mapping said redundancy group into said physical storage space.
Claim 11
Dependent Claim
48 words
The apparatus as recited in claim 8 wherein the means for calculating a partition further comprises: means for determining the stripe degree; and means for determining the stripe unit size from said user specifications for the average command size and the overall size of said host data subset.
Claim 12
Dependent Claim
214 words
A data storage apparatus having a computational section, a data bus controller, a data bus responsive to signals from said data bus controller, a plurality of peripheral controllers coupled to said data bus, a plurality of data storage devices coupled to each said peripheral controllers, said data storage devices providing the physical storage space for said system, at least one host controller coupled to said data bus, said data storage apparatus comprising: a) means for calculating a partition for the host data using user specifications for the average command size and the total capacity required, said means for calculating a partition including means for determining the stripe degree calculated according to the formula: ##EQU7## where L=the average command size, M=the stripe degree, D=the drive controller latency, S=the average seek time, R=the average rotational latency on a drive, and N=the total number of drives and means for determining the stripe unit size from user specifications for the average command size and the total capacity required; b) means for calculating the level of redundancy for said partition using user specifications for the mean time between data loss; c) means for creating a redundancy group from said partition and said calculated level of redundancy; and d) means for mapping said redundancy group into said physical storage space.
Claim 13
Dependent Claim
214 words
A data storage apparatus having a computational section, a data bus controller, a data bus responsive to signals from said data bus controller, a plurality of peripheral controllers coupled to said data bus, a plurality of data storage devices coupled to each said peripheral controllers, said data storage devices providing the physical storage space for said system, at least one host controller coupled to said data bus, said data storage apparatus comprising: a) means for calculating a partition for the host data using user specifications for the average command size and the total capacity required, said means for calculating a partition including means for determining the stripe degree calculated according to the formula: ##EQU7## where L=the average command size, M=the stripe degree, D=the drive controller latency, S=the average seek time, R=the average rotational latency on a drive, and N=the total number of drives and means for determining the stripe unit size from user specifications for the average command size and the total capacity required; b) means for calculating the level of redundancy for said partition using user specifications for the mean time between data loss; c) means for creating a redundancy group from said partition and said calculated level of redundancy; and d) means for mapping said redundancy group into said physical storage space.
Claim 14
Dependent Claim
192 words
A data storage apparatus having a computational section, a data bus controller, a data bus responsive to signals from said data bus controller, a plurality of peripheral controllers coupled to said data bus, a plurality of data storage devices coupled to each said peripheral controllers, said data storage devices providing the physical storage space for said system, at least one host controller coupled to said data bus, said data storage apparatus comprising: a) means for calculating a partition for the host data using user specifications for the average command size and the total capacity required, said means for calculating a partition including means for determining the stripe degree and means for determining the stripe unit size from user specifications for the average command size and the total capacity required, said means for determining the stripe degree calculated according to the formula: ##EQU8## b) means for calculating the level of redundancy for said partition using user specifications for the mean time between data loss; c) means for creating a redundancy group from said partition and said calculated level of redundancy; and d) means for mapping said redundancy group into said physical storage space.
Claim 15
Dependent Claim
192 words
A data storage apparatus having a computational section, a data bus controller, a data bus responsive to signals from said data bus controller, a plurality of peripheral controllers coupled to said data bus, a plurality of data storage devices coupled to each said peripheral controllers, said data storage devices providing the physical storage space for said system, at least one host controller coupled to said data bus, said data storage apparatus comprising: a) means for calculating a partition for the host data using user specifications for the average command size and the total capacity required, said means for calculating a partition including means for determining the stripe degree and means for determining the stripe unit size from user specifications for the average command size and the total capacity required, said means for determining the stripe degree calculated according to the formula: ##EQU8## b) means for calculating the level of redundancy for said partition using user specifications for the mean time between data loss; c) means for creating a redundancy group from said partition and said calculated level of redundancy; and d) means for mapping said redundancy group into said physical storage space.
Claim 16
Dependent Claim
34 words
The apparatus as recited in claim 9 wherein the means for determining the stripe unit size further comprises setting the stripe unit size equal to the average command size divided by the stripe degree.
Claim 17
Dependent Claim
211 words
A data storage apparatus having a computational section, a data bus controller, a data bus responsive to signals from said data bus controller, a plurality of peripheral controllers coupled to said data bus, a plurality of data storage devices coupled to each said peripheral controllers, said data storage devices providing the physical storage space for said system, at least one host controller coupled to said data bus, said data storage apparatus comprising: means for calculating a partition for the host data using user specifications for the average command size and the total capacity required; means for calculating the level of redundancy for said partition using user specifications for the mean time between data loss, said means for calculating the level of redundancy for said partition further includes a) means for calculating the mean time between data loss according to the formula ##EQU9## where MTBDL=mean time between data loss MTBF=mean time between failure MTTR=mean time to repair; and b) means for choosing the level of redundancy for said partition that gives the least upper bound on the mean time to data loss specified by user; means for creating a redundancy group from said partition and said calculated level of redundancy; and means for mapping said redundancy group into said physical storage space.
Claim 18
Dependent Claim
211 words
A data storage apparatus having a computational section, a data bus controller, a data bus responsive to signals from said data bus controller, a plurality of peripheral controllers coupled to said data bus, a plurality of data storage devices coupled to each said peripheral controllers, said data storage devices providing the physical storage space for said system, at least one host controller coupled to said data bus, said data storage apparatus comprising: means for calculating a partition for the host data using user specifications for the average command size and the total capacity required; means for calculating the level of redundancy for said partition using user specifications for the mean time between data loss, said means for calculating the level of redundancy for said partition further includes a) means for calculating the mean time between data loss according to the formula ##EQU9## where MTBDL=mean time between data loss MTBF=mean time between failure MTTR=mean time to repair; and b) means for choosing the level of redundancy for said partition that gives the least upper bound on the mean time to data loss specified by user; means for creating a redundancy group from said partition and said calculated level of redundancy; and means for mapping said redundancy group into said physical storage space.
Claim 19
Dependent Claim
57 words
The apparatus as recited in claim 13 wherein the means for choosing the level of redundancy for said partition that gives the least upper bound on the mean time to data loss specified by user further comprises choosing the greatest number of levels of redundancy offered by the system if said least upper bound does not exist.
Claim 20
Dependent Claim
49 words
The apparatus as recited in claim 8 wherein said means for mapping said redundancy group into said physical storage space further comprises: means for programming said data bus controller such that said data bus controller controls the data flow on said data bus without intervention from said computation section.
Claim 21
Dependent Claim
55 words
The apparatus as recited in claim 15 wherein said means of programming said data bus controller further comprises: a storage area; a plurality of data structures, said data structures representing the manner in which host data will be stored in said physical storage space; a means for storing data structure values into said storage area.
References Cited (Backward Citations)
US4947477A
Cited
US5167032A
Cited
US5303244A
Cited
US5257362A
Cited
US5301297A
Cited
US5257391A
Cited
US5159608A
Cited
US5237658A
Cited
USPTO Annuity & Maintenance Windows
| Annuity Stage | Window Opens | Payment Deadline | Surcharge Period Until | Estimated Fee | Status |
|---|---|---|---|---|---|
| 3.5 Years (Year 4) | 2002-01-04 | 2002-07-06 | 2003-01-05 | $2000.00 | Window Closed / Lapsed |
| 7.5 Years (Year 8) | 2006-01-04 | 2006-07-06 | 2007-01-05 | $3760.00 | Window Closed / Lapsed |
| 11.5 Years (Year 12) | 2010-01-04 | 2010-07-06 | 2011-01-05 | $7700.00 | Window Closed / Lapsed |