Dynamically upgradeable fault-tolerant storage system permitting variously sized storage devices and method
First Claim
Patent Images
1. A method of storing data in a number of storage devices, the storage devices being under control of a storage manager external to the storage devices, the method comprising:
- under control of the storage manager, storing fixed-size blocks of data in a first set of storage devices including at least a first storage device;
under control of the storage manager, causing a selected portion of the blocks to be stored, in a fault tolerant manner using block-based mirroring, in only the first storage device when the selected portion cannot be stored in a fault tolerant manner across a plurality of the storage devices; and
in response to a change of composition of the first set of storage devices resulting in a second set of storage devices, the second set including at least the first storage device and a new storage device, causing, under control of the storage manager, automatic reconfiguring of storage of the selected portion of the blocks, using information from the first storage device, such reconfiguring including using the new storage device as part of a storage pattern providing fault tolerance for the selected portion across a plurality of the storage devices in the second set, so that at least some storage space, on the first storage device, that had been utilized to provide fault tolerance for the selected portion becomes available for storage of other blocks of data.
16 Assignments
0 Petitions
Accused Products
Abstract
A dynamically upgradeable fault-tolerant storage system permits a storage device to be replaced with a larger storage device. Data stored redundantly across multiple storage devices is reproduced on the replacement device, and the additional storage space on the replacement device is made available for redundantly storing additional data.
367 Citations
26 Claims
-
1. A method of storing data in a number of storage devices, the storage devices being under control of a storage manager external to the storage devices, the method comprising:
-
under control of the storage manager, storing fixed-size blocks of data in a first set of storage devices including at least a first storage device; under control of the storage manager, causing a selected portion of the blocks to be stored, in a fault tolerant manner using block-based mirroring, in only the first storage device when the selected portion cannot be stored in a fault tolerant manner across a plurality of the storage devices; and in response to a change of composition of the first set of storage devices resulting in a second set of storage devices, the second set including at least the first storage device and a new storage device, causing, under control of the storage manager, automatic reconfiguring of storage of the selected portion of the blocks, using information from the first storage device, such reconfiguring including using the new storage device as part of a storage pattern providing fault tolerance for the selected portion across a plurality of the storage devices in the second set, so that at least some storage space, on the first storage device, that had been utilized to provide fault tolerance for the selected portion becomes available for storage of other blocks of data. - View Dependent Claims (2, 3, 4, 5, 6, 7, 8, 9, 10, 11, 12, 13)
-
-
14. A system for storing data, the system comprising:
-
a first set of storage devices having at least a first storage device; and a storage manager, external to the storage devices, the storage manager being configured; (i) to store fixed-size blocks of data in the first set of storage devices, (ii) to cause a selected portion of the blocks to be stored, in a fault tolerant manner using block-based mirroring, in only the first storage device when the selected portion cannot be stored in a fault tolerant manner across a plurality of the storage devices, and (iii) in response to a change of composition of the first set of storage devices resulting in a second set of storage devices including at least the first storage device and a new storage device, to automatically reconfigure storage of the selected portion of the blocks, using information from the first storage device, such reconfiguring including using the new storage device as part of a storage pattern providing fault tolerance for the selected portion across a plurality of the storage devices in the second set, so that at least some storage space, on the first storage device, that had been utilized to provide fault tolerance for the selected portion becomes available for storage of other blocks of data. - View Dependent Claims (15, 16, 17, 18, 19, 20, 21, 22, 23, 24, 25, 26)
-
Specification