Distributed file system including multicast retrieval
AssigneeIntel Corporation
InventorsJames P. Ketrenos, Edward R. Rhoads, Charles R. Lynch
Life of this patent
Estimating the term…
Abstract
A distributed file system intelligently allocates portions of a file system from a server to one or more clients on a network. File system data used during power-on of a client may be stored on the client. A retrieval of the file system may subsequently be made to the extent the client has capacity to store the file system. A multicast operation, performed as a background operation on the client, may be used to retrieve the file system. For portions of the file system not allocated to the client, the client may still access the file system from the server. Network bandwidth may thus be reduced and client access to the file system may generally be more efficient.
Claims15
A method comprising:
- upon an initial connection to a network, accessing a first portion of a file system from a server and storing said first portion in non-volatile memory;
- receiving a request for a second portion of a file system after said initial connection;
- identifying whether the second portion is stored in said non-volatile memory by associating portions of the file system used by the client during start-up with the first location;
- wherein associating further comprises:
- retrieving a plurality of portions from the file system using multicasting;
- storing the plurality of portions in the second location;
- if not, determining whether the second portion is stored in a volatile storage associated with portions of the file system that were multicast to the client by a server;
- and
- if not, retrieving the second portion from the server in a multicast operation.
A system including:
- a processor;
- a non-volatile memory coupled to said processor;
- a volatile memory coupled to said processor;
- and
- a storage medium including a software program that, upon execution:
- upon an initial connection to a network, accesses a first portion of a file system from a server and storing said first portion in the non-volatile memory, receives a request for a second portion of a file system after said initial connection, identifies whether the second portion is stored in the non-volatile memory by associating portions of the file system used by the client during start-up with the first location;
- wherein associating further comprises:
- monitoring accesses to a plurality of portions of the file system during start-up;
- retrieving the plurality of portions from the file system;
- storing the plurality of portions in the first location;
- retrieving a plurality of portions from the file system using multicasting;
- storing the plurality of portions in the second location;
- and
- if not, determining whether the second portion is stored in the volatile memory and, if not, retrieving the second portion from the server in a multicast operation.
An article comprising a non-transitory medium storing instructions that cause a processor-based system to:
- upon an initial connection to a network, access a first portion of a file system from a server and storing said first portion in non-volatile memory;
- receive a request for a second portion of a file system after said initial connection;
- identify whether the second portion is stored in the non-volatile memory by associating portions of the file system used by the client during start-up with the first location;
- wherein associating comprises:
- monitoring accesses to a plurality of portions of the file system during start-up;
- retrieving the plurality of portions from the file system;
- storing the plurality of portions in the first location;
- retrieving a plurality of portions from the file system using multicasting;
- storing the plurality of portions in the second location;
- if not, determine whether the second portion is stored in a volatile storage associated with portions of the file system that were multicast to the client by a server;
- and
- if not, retrieve the second portion from the server in a multicast operation.
Dependencies are inferred from the claim text.