Storage system
First Claim
1. Storage system (100) comprising:
- a plurality of storage units (110-120), each one of which comprising a plurality of storage zones (121-126) having mutually different expected data retrieval times, at least one data unit being stored in said plurality of storage units (110-120), said data unit comprising N blocks, wherein N≧
2, the blocks comprising redundant information such that any one of a plurality of selections comprising N−
K of the N blocks suffices for retrieving the data unit, wherein K≧
1; and
a reader for retrieving said data unit from the plurality of storage units (110-120), the reader being arranged for determining a particular one of said plurality of selections on the basis of a selection procedure, the selection procedure taking into account said expected data retrieval times.
5 Assignments
0 Petitions
Accused Products
Abstract
The invention relates to a storage system (100) such as a video on demand system, comprising a plurality of storage units (110-120) such as disk drives. Each one of the storage units (110-120) has a number of storage zones (121-126) with mutually different expected data retrieval times. Data is stored in data units, with each data unit comprising N blocks, wherein N≧2. The blocks of a data unit are distributed over the storage units (110-120). The blocks comprise redundant information such that any one of a plurality of selections comprising N−K of the N blocks suffices for retrieving the data unit, wherein K≧1. For retrieving a data unit from the storage units (110-120), a reader determines which N−K of the N blocks to retrieve on the basis of a selection procedure. In accordance with the invention, the selection procedure takes into account the expected data retrieval times in order to optimize bandwidth utilization.
-
Citations
7 Claims
-
1. Storage system (100) comprising:
-
a plurality of storage units (110-120), each one of which comprising a plurality of storage zones (121-126) having mutually different expected data retrieval times, at least one data unit being stored in said plurality of storage units (110-120), said data unit comprising N blocks, wherein N≧
2, the blocks comprising redundant information such that any one of a plurality of selections comprising N−
K of the N blocks suffices for retrieving the data unit, wherein K≧
1; and
a reader for retrieving said data unit from the plurality of storage units (110-120), the reader being arranged for determining a particular one of said plurality of selections on the basis of a selection procedure, the selection procedure taking into account said expected data retrieval times. - View Dependent Claims (2, 3, 4)
-
-
5. A storage system (100) comprising:
-
a plurality of storage units (110-120), each one of which comprising a plurality of storage zones (121-126) having mutually different expected data retrieval times;
a loader for storing a data unit in said plurality of storage units, said loader being arranged for converting said data unit into N blocks, wherein N≧
2, the blocks comprising redundant information such that any one of a plurality of selections comprising K of the N blocks suffices for retrieving the data unit, wherein K≧
1 and for storing said N blocks in said plurality of storage units such that each storage unit comprises at most one of said N blocks and that said N blocks are distributed at least approximately equally among faster and slower ones of said storage zones.
-
-
6. A method of retrieving data units from a system (100) comprising a plurality of storage units (110-120), each one of which comprising a plurality of storage zones (121-126) having mutually different expected data retrieval times, at least one data unit being stored in said plurality of storage units (110-120), said data unit comprising N blocks, wherein N≧
- 2, the blocks comprising redundant information such that any one of a plurality of selections comprising N−
K of the N blocks suffices for retrieving the data unit, wherein K≧
1, the method comprising the steps of;determining a particular one of said plurality of selections, thereby taking into account said expected data retrieval times; and
retrieving the blocks pertaining to that particular selection.
- 2, the blocks comprising redundant information such that any one of a plurality of selections comprising N−
-
7. Method of storing a data unit in a system (100) comprising a plurality of a storage units (110-120), each one of which comprising a plurality of storage zones (121-126) having mutually different expected data retrieval times, the method comprising the steps of:
-
converting said data unit into N blocks, wherein N≧
2, the blocks comprising redundant information such that any one of a plurality of selections comprising N−
K of the N blocks suffices for retrieving the data unit, wherein K≧
1;
storing said N blocks in said plurality of storage units such that each storage unit comprises at most one of said N blocks and that said N blocks are distributed at least approximately equally among faster and slower ones of said storage zones.
-
Specification