Archival storage and retrieval system
First Claim
1. A file storage and retrieval system comprising:
- a processing unit;
a plurality of storage nodes; and
a memory storing instructions, wherein the processing unit is configured to execute the instructions to;
receive a Quality of Service (QoS) levels and uniform resource name for a file enabling fine grained control over file availability stored across the plurality of storage nodes;
determine k data chunks and m parity chunks fragmented from file chunks by a file encoding and placement scheme wherein the QoS level associated with the each file specifies presence of desired number md of parity chunks and ensures total number of available chunks for any file to be above k+mmin chunks wherein mmin<
md;
determine a file chunk Uniform Resource Name (URN) for the k data chunks and m parity chunks;
determine a hash for each of the file chunk URNs;
determine a node key for each of the plurality of storage nodes using a hash function; and
store the k data chunks and m parity chunks across the plurality of storage nodes based on the node keys and the hashs for the file chunks;
a monitoring engine to track the status of lost file chunks stored on any one of the storage nodes for their participation in input/output operations performed on the system and regeneration mechanism on the lost chunks wherein regeneration is delayed as long as minimum number of available chunks is greater than k+mmin.
1 Assignment
0 Petitions
Accused Products
Abstract
A highly reliable data archival and retrieval method that enables fine grained control over data availability is implemented across a Quality of Service driven archival system, configured to fragment the data into data and parity chunks for storing onto the storage node. The technique employed by the archival system enables files to be read without having need to access any metadata, thereby tolerating complete loss of such metadata. Further, the Quality of Service driven system architecture improves upon the system performance and throughput by means of a storage node regeneration process which ensures balanced load on participating storage node during various storage, retrieval and regeneration operations.
112 Citations
14 Claims
-
1. A file storage and retrieval system comprising:
-
a processing unit; a plurality of storage nodes; and a memory storing instructions, wherein the processing unit is configured to execute the instructions to; receive a Quality of Service (QoS) levels and uniform resource name for a file enabling fine grained control over file availability stored across the plurality of storage nodes; determine k data chunks and m parity chunks fragmented from file chunks by a file encoding and placement scheme wherein the QoS level associated with the each file specifies presence of desired number md of parity chunks and ensures total number of available chunks for any file to be above k+mmin chunks wherein mmin<
md;determine a file chunk Uniform Resource Name (URN) for the k data chunks and m parity chunks; determine a hash for each of the file chunk URNs; determine a node key for each of the plurality of storage nodes using a hash function; and store the k data chunks and m parity chunks across the plurality of storage nodes based on the node keys and the hashs for the file chunks; a monitoring engine to track the status of lost file chunks stored on any one of the storage nodes for their participation in input/output operations performed on the system and regeneration mechanism on the lost chunks wherein regeneration is delayed as long as minimum number of available chunks is greater than k+mmin. - View Dependent Claims (2, 3, 4, 5, 6, 7, 8, 9, 10, 11, 12, 13, 14)
-
Specification