Aggregated opportunistic lock and aggregated implicit lock management for locking aggregated files in a switched file system

• US 7,788,335 B2
• Filed: 01/02/2003
• Issued: 08/31/2010
• Est. Priority Date: 01/11/2001
• Status: Active Grant

• Current Assignee: RPX Corporation
• Original Assignee: F5 Networks, Inc. (F5 Incorporated)
• Inventors: Miloushev, Vladimir, Nickolov, Peter
• Primary Examiner(s): Hu, Jinsong
• Application Number:
  US10/336,784
• Publication Number:
  US 20040133652A1
• Time in Patent Office: 2,798 Days
• Field of Search: 709/213, 709/214, 709/226, 709/229, 709/231, 707/8, 707/9, 707/10
• US Class Current: 709/213
• CPC Class Codes: G06F 11/1076 Parity data used in redundant arrays of independent storages, e.g. in RAID systems
• CPC Class Codes: G06F 11/2056 by mirroring
• CPC Class Codes: G06F 11/2058 using more than 2 mirrored copies
• CPC Class Codes: G06F 16/1824 implemented using Network-attached Storage [NAS] architecture distributed or networked storage systems G06F3/067; protocols for distributed storage of data in a network H04L67/1097
• CPC Class Codes: G06F 2211/1028 Distributed, i.e. distributed RAID systems with parity
• CPC Class Codes: H04L 67/06 specially adapted for file transfer, e.g. file transfer protocol [FTP]
• CPC Class Codes: H04L 67/1001 for accessing one among a plurality of replicated servers
• CPC Class Codes: H04L 67/10015 Access to distributed or replicated servers, e.g. using brokers
• CPC Class Codes: H04L 67/1008 based on parameters of servers, e.g. available memory or workload monitoring of computer activity G06F11/30
• CPC Class Codes: H04L 67/1012 based on compliance of requirements or conditions with available server resources
• CPC Class Codes: H04L 67/1014 based on the content of a request
• CPC Class Codes: H04L 67/1017 based on a round robin mechanism
• CPC Class Codes: H04L 67/1019 Random or heuristic server selection
• CPC Class Codes: H04L 67/1023 based on a hash applied to IP addresses or costs
• CPC Class Codes: H04L 67/1029 using data related to the state of servers by a load balancer
• CPC Class Codes: H04L 67/1034 Reaction to server failures by a load balancer
• CPC Class Codes: H04L 67/1095 Replication or mirroring of data, e.g. scheduling or transport for data synchronisation between network nodes
• CPC Class Codes: H04L 67/1097 for distributed storage of data in networks, e.g. transport arrangements for network file system [NFS], storage area networks [SAN] or network attached storage [NAS]
• CPC Class Codes: H04L 67/56 Provisioning of proxy services store-and-forward switching systems in data switching networks H04L12/54
• CPC Class Codes: H04L 67/567 Integrating service provisioning from a plurality of service providers
• CPC Class Codes: H04L 69/22 : Parsing or analysis of headers
• CPC Class Codes: H04L 69/329 : in the application layer [OSI layer 7]
• CPC Class Codes: H04L 9/40 : Network security protocols

Abstract

A switched file system, also termed a file switch, is logically positioned between client computers and file servers in a computer network. The file switch distributes user files among multiple file servers using aggregated file, transaction and directory mechanisms. The file switch supports caching of a particular aggregated data file either locally in a client computer or in the file switch in accordance with the exclusivity level of an opportunistic lock granted to the entity that requested caching. The opportunistic lock can be obtained either on the individual data files stored in the file servers or on the metadata files that contain the location of each individual data files in the file servers. The opportunistic lock can be broken if another client tries to access the aggregated data file. Opportunistic locks allows client-side caching while preserving data integrity and consistency, hence the performance of the switched file system is increased.

Claims

1. A file switch for use in a computer network having a group of file servers and a plurality of client computers, wherein the file switch may be logically positioned between a client computer from which a user request is received and the group of file servers, the file switch comprising:

at least one processing unit;

at least one port for exchanging information with the file servers and client computers, the information exchanged including information concerning a specified user file;

a file aggregation module including one or more stored computer programs for execution by the at least one processing unit, the computer programs including instructions for;

receiving a user request to access a subset of a specified user file;

identifying a subset of file servers that store portions of the user file that together comprise the subset of the specified user file;

sending an oplock request to each file server in the subset of file servers, and receiving oplock request replies from the subset of file servers;

aggregating the received oplock request replies to produce an aggregated oplock reply, such that the aggregated oplock reply is an oplock grant only when all the received oplock request replies are oplock grants; and

caching data from the subset of the specified user file only when the aggregate oplock reply is an oplock grant.

2. The file switch of claim 1, the file aggregation module further including instructions for:

receiving an oplock break from a respective file server in the set of file servers; and

disabling said caching of data from the subset of the specified user file.

3. The file switch of claim 1, the file aggregation module further including instructions for:

accessing a metafile that stores information identifying a set of file servers for storing respective defined portions of the specified user file; and

identifying, based on the information stored in the metafile, a subset of the file servers that store portions of the user file that together comprise the subset of the specified user file.

4. The file switch of claim 1, wherein the user request does not include an oplock request.

5. A method of caching data from user files stored in shared data computer network, where each user file of at least a plurality of the user files is divided into portions stored on a plurality of file servers, among a group of file servers in a computer network, comprising:

receiving a user request to access a subset of a specified user file, wherein the request does not include a request for lock on the subset of the specified user file;

identifying a subset of file servers that store portions of the user file that together comprise the subset of the specified user file;

sending a lock request to each file server in the subset of file servers, and receiving lock replies from the subset of file servers;

aggregating the received lock replies to produce an aggregated lock reply, such that the aggregated lock reply is a lock grant only when all the received oplock request replies are oplock grants; and

only when the aggregated lock reply is a lock grant, continuing processing of the user request by performing an operation on the subset of the specified user file.

6. The method of claim 5, including:

when the aggregated lock reply is not a lock grant, deferring processing of the user request and then repeating performance of the lock acquisition operation at each file server in the subset of file servers.

7. The method of claim 5, including:

wherein the method is performed by a file switch logically positioned between a client computer from which the user request is received and the group of file servers.

8. The method of claim 7, wherein identifying the subset of file servers includes:

accessing a metafile that stores information identifying a set of file servers for storing respective defined portions of the specified user file; and

determining, based on the information stored in the metafile, a subset of the file servers that store portions of the user file that together comprise the subset of the specified user file.

9. A file switch for use in a computer network having a group of file servers and a plurality of client computers, the file switch comprising:

at least one port for exchanging information with the file servers and client computers, the information exchanged including information concerning a specified user file;

a file aggregation module including;

means for receiving a user request to access a subset of a specified user file, wherein the request does not include a request for lock on the subset of the specified user file;

means for identifying a subset of file servers that store portions of the user file that together comprise the subset of the specified user file;

means for sending a lock request to each file server in the subset of file servers, and receiving lock replies from the subset of file servers;

means for aggregating the received lock replies to produce an aggregated lock reply, such that the aggregated lock reply is a lock grant only when all the received oplock request replies are oplock grants; and

means, operative only when the aggregated lock reply is a lock grant, for continuing processing of the user request by performing an operation on the subset of the specified user file.

10. A file switch for use in a computer network having a group of file servers and a plurality of client computers, the file switch comprising:

at least one processing unit;

at least one port for exchanging information with the file servers and client computers, the information exchanged including information concerning a specified user file;

a file aggregation module including one or more stored computer programs for execution by the at least one processing unit, the computer programs including instructions for;

receiving a user request to access a subset of a specified user file, wherein the request does not include a request for lock on the subset of the specified user file;

identifying a subset of file servers that store portions of the user file that together comprise the subset of the specified user file;

sending a lock request to each file server in the subset of file servers, and receiving lock replies from the subset of file servers;

aggregating the received lock replies to produce an aggregated lock reply, such that the aggregated lock reply is a lock grant only when all the received oplock request replies are oplock grants; and

only when the aggregated lock reply is a lock grant, continuing processing of the user request by performing an operation on the subset of the specified user file.

11. The file server of claim 10, the file aggregation module further including instructions for:

when the aggregated lock reply is not a lock grant, deferring processing of the user request and then repeating performance of the lock acquisition operation at each file server in the subset of file servers.

12. The file server of claim 10, wherein the method is performed by a file switch logically positioned between a client computer from which the user request is received and the group of file servers.

13. The file server of claim 10, wherein the instructions for identifying the subset of file servers includes instructions for:

accessing a metafile that stores information identifying a set of file servers for storing respective defined portions of the specified user file; and

determining, based on the information stored in the metafile, a subset of the file servers that store portions of the user file that together comprise the subset of the specified user file.

14. A system for use in a computer network having a plurality of client computers, the system comprising:

a group of file servers;

a file switch, the file switch including;

at least one port for exchanging information with the file servers and client computers, the information exchanged including information concerning a specified user file;

at least one processing unit;

a file aggregation module including one or more stored computer programs for execution by the at least one processing unit, the computer programs including instructions for;

receiving a user request to access a subset of a specified user file, the request including a request for an opportunistic lock on the subset of the specified user file;

accessing metadata identifying a set of file servers for storing respective defined portions of the specified user file;

identifying, based on the metadata, a subset of the file servers that store portions of the user file that together comprise the subset of the specified user file;

sending an oplock request to each file server in the subset of file servers, and receiving oplock request replies from the subset of file servers;

aggregating the received oplock request replies to produce an aggregated oplock reply, such that the aggregated oplock reply is an oplock grant only when all the received oplock request replies are oplock grants;

sending the aggregated oplock reply to a sender of the user request, thereby enabling the sender to cache data from the subset of the specified user file only when the aggregate oplock reply is an oplock grant.

15. The system of claim 14, the file aggregation module further including instructions for:

receiving an oplock break from a respective file server in the set of file servers;

forwarding the oplock break to the sender of the user request.

16. The system of claim 14, the file aggregation module further including instructions for:

waiting to receive an oplock break acknowledgement from the sender of the user request, and upon receiving the oplock break acknowledgement from the sender of the user request, forwarding the oplock break acknowledgement to the respective file server in the set of file servers.

17. The system of claim 14, the file aggregation module further including instructions for:

upon receiving the oplock break, disabling caching of data from the subset of the specified user file.

18. The system of claim 14, the file aggregation module further including instructions for:

upon receiving the oplock break, disabling caching, within the file switch, of data from the subset of the specified user file.

19. The system of claim 14, wherein the file switch is logically positioned between a client computer from which the user request is received and the group of file servers.

20. A system for use in a computer network having a plurality of client computers, the system comprising:

a group of file servers;

a file switch, the file switch including;

at least one port for exchanging information with the file servers and client computers, the information exchanged including information concerning a specified user file;

means for receiving a user request to access a subset of a specified user file, the request including a request for an opportunistic lock on the subset of the specified user file;

means for identifying a subset of file servers that store portions of the user file that together comprise the subset of the specified user file;

means for sending an oplock request to each file server in the subset of file servers, and receiving oplock request replies from the subset of file servers;

means for aggregating the received oplock request replies to produce an aggregated oplock reply, such that the aggregated oplock reply is a lock grant only when all the received lock request replies are oplock grants; and

means for sending the aggregated oplock reply to a sender of the user request, thereby enabling the sender to cache data from the subset of the specified user file only when the aggregate lock reply is an oplock grant.

21. A system for use in a computer network having a plurality of client computers, the system comprising:

a group of file servers;

a file switch, the file switch including;

at least one port for exchanging information with the file servers and client computers, the information exchanged including information concerning a specified user file;

at least one processing unit;

a file aggregation module including one or more stored computer programs for execution by the at least one processing unit, the computer programs including instructions for;

receiving a user request to access a subset of a specified user file, the request including a request for an opportunistic lock on the subset of the specified user file;

identifying a subset of file servers that store portions of the user file that together comprise the subset of the specified user file;

sending an oplock request to each file server in the subset of file servers, and receiving oplock request replies from the subset of file servers;

aggregating the received oplock request replies to produce an aggregated oplock reply, such that the aggregated oplock reply is an oplock grant only when all the received oplock request replies are oplock grants; and

sending the aggregated oplock reply to a sender of the user request, thereby enabling the sender to cache data from the subset of the specified user file only when the aggregate oplock reply is an oplock grant.

22. The system of claim 21, the file aggregation module further including instructions for:

receiving an oplock break from a respective file server in the set of file servers;

forwarding the oplock break to the sender of the user request.

23. The system of claim 21, the file aggregation module further including instructions for:

waiting to receive an oplock break acknowledgement from the sender of the user request, and upon receiving the oplock break acknowledgement from the sender of the user request, forwarding the oplock break acknowledgement to the respective file server in the set of file servers.

24. The system of claim 21, the file aggregation module further including instructions for:

upon receiving the oplock break, disabling caching of data from the subset of the specified user file.

25. The system of claim 21, the file aggregation module further including instructions for:

upon receiving the oplock break, disabling caching of data within the file switch from the subset of the specified user file.

26. The system of claim 21, wherein the file switch is logically positioned between a client computer from which the user request is received and the group of file servers.