Network file server using a cached disk array storing a network file directory including file locking information and data mover computers each having file system software for shared read-write file access

• US 5,948,062 A
• Filed: 11/13/1996
• Issued: 09/07/1999
• Est. Priority Date: 10/27/1995
• Status: Expired due to Term

• Current Assignee: EMC Corporation (Dell Technologies Inc.)
• Original Assignee: EMC Corporation (Dell Technologies Inc.)
• Inventors: Ting, Dennis P.J., Tzelnic, Percy, Gupta, Uday, Vahalia, Uresh K
• Primary Examiner(s): Maung, Zarni
• Assistant Examiner(s): Barot, Bharat
• Application Number:
  US08/747,875
• Time in Patent Office: 1,028 Days
• Field of Search: 395/200.3, 395/200.31-200.33, 395/200.49-200.5, 395/200.56-200.59, 395/182.04, 395/183.01, 707/10, 707/104, 707/203-205, 707/1, 348/6-8, 348/12-13, 348/170, 348/501, 348/563, 455/4.2, 455/5.1, 709/200-203, 709/214-220, 709/226-229, 711/100, 711/111-113
• US Class Current: 709/219
• CPC Class Codes: G06F 11/1435 using file system or storage system metadata
• CPC Class Codes: G06F 12/0804 with main memory updating G06F12/0806 takes precedence
• CPC Class Codes: G06F 12/0813 with a network or matrix configuration
• CPC Class Codes: G06F 12/0815 Cache consistency protocols
• CPC Class Codes: G06F 12/0866 for peripheral storage systems, e.g. disk cache
• CPC Class Codes: G06F 16/1774 Locking methods, e.g. locking methods for file systems allowing shared and concurrent access to files
• CPC Class Codes: G06F 16/1858 Parallel file systems, i.e. file systems supporting multiple processors
• CPC Class Codes: G06F 2212/312 In storage controller
• CPC Class Codes: H04L 65/1101 Session protocols
• CPC Class Codes: H04L 67/01 Protocols
• 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 67/2895 Intermediate processing functionally located close to the data provider application, e.g. reverse proxies
• CPC Class Codes: H04L 67/568 Storing data temporarily at an intermediate stage, e.g. caching
• CPC Class Codes: H04N 21/2182 involving memory arrays, e.g. RAID disk arrays RAID arrays per se G06F3/0689; use of parity to protect data in RAID systems G06F11/1008
• CPC Class Codes: H04N 21/23106 involving caching operations prefetching while addressing of a memory level in which the access to the desired data or data block requires associative addressing means within memory systems or architectures G06F12/0862; caching at an intermediate stage in a data network H04L67/568
• CPC Class Codes: H04N 21/2396 characterized by admission policies admission control, resource allocation in open networks H04L12/5692; arrangements for network security using user profiles for access control H04L63/102; access security in wireless networks H04W12/08
• CPC Class Codes: H04N 21/47202 for requesting content on demand, e.g. video on demand
• CPC Class Codes: H04N 21/816 involving special video data, e.g 3D video
• CPC Class Codes: H04N 7/17318 Direct or substantially direct transmission and handling of requests
• CPC Class Codes: H04N 7/17336 Handling of requests in head-ends
• CPC Class Codes: Y10S 707/99953 : Recoverability

Abstract

For network file access, a plurality of data mover computers are linked to a cached disk array. Read-write files stored in the cached disk array are accessible to network clients through more than one of the data mover computers so that the data mover computers are not a bottleneck to file access. The cached disk array stores a network file directory including file locking information, and the data mover computers each have file system software that accesses the network file directory for shared read-write file access. The data mover computers perform the file system tasks such as managing the file directory for mapping of file names to logical blocks and for locking and unlocking of the files in order to minimize loading on the cached disk array. Therefore, the network file server need not use any particular one of the data mover computers to serve as a control point for read-write file access. Instead, file system software for managing the file directory is replicated in each data mover computer. The cached disk array recognizes logical block addresses, and the cached disk array has a limited internal locking facility ensuring that reading or writing to a logical block is an atomic operation. Preferably the data mover computers are commodity personal computers.

Claims

1. A file server for serving clients in a data network, the file server comprising:

a cached disk storage subsystem including an array of disk drives and a semiconductor cache memory coupled to the disk drives for storage of data written to and read from the disk drives; and

a plurality of data mover computers connected to the cached disk storage subsystem and linked to the data network for responding to a request for file access from a client in the data network by transferring data between the cached disk storage subsystem and the data network;

wherein the cached disk storage subsystem stores read-write files which are shared among the clients and each read-write file is accessible by the clients through more than one of the data mover computers, and the data mover computers maintain in the cached disk storage subsystem a file directory accessible by the data mover computers in response to file access requests to determine whether or not file access for a client is permitted, to map file names to logical blocks of data that comprise the files and said logical blocks of data are stored in the cached disk storage subsystem, and to lock and unlock each of the read-write files for shared read-write access among the clients through more than one of the data mover computers, wherein each data mover computer is programmed to access the locking information in the cache memory of the cached disk storage subsystem in order to obtain a read lock or a write lock on at least a portion of each of the read-write files to be accessed.

2. The file server as claimed in claim 1, wherein file system software for managing the file directory is replicated in each data mover computer, and the file system software for managing the file directory includes software for managing mapping of names of files accessible by the clients to the logical blocks of data that comprise the files and said logical blocks of data are stored in the cached disk storage subsystem, and software for accessing the file directory to determine whether or not a read-write file to be accessed is locked, and when a read-write file to be accessed is not locked, to update the file directory by placing a lock on at least a portion of the read-write file to be accessed.

3. The file server as claimed in claim 1, wherein the cached disk storage subsystem responds to requests from the data mover computers for access to logical block addresses of the logical blocks comprising the files to be accessed by the clients, and the cached disk storage subsystem has a limited internal locking facility for ensuring that reading and writing to a logical block is an atomic operation.

4. The file server as claimed in claim 1, wherein the data mover computers are commodity personal computers that share a data link internal to the file server.

5. The file server as claimed in claim 4, further including a data terminal linked to the commodity personal computers for permitting an operator at the data terminal to communicate with the commodity personal computers.

6. The file server as claimed in claim 5, wherein the file server supports a Simple Network Management Protocol (SNMP) for the operator to manage and control resources of the file server from the data terminal.

7. The file server as claimed in claim 4, wherein each of the commodity personal computers is linked to the cached disk storage subsystem by at least one respective fast, wide differential (FWD) SCSI connection.

8. The file server as claimed in claim 1, wherein the data mover computers each include a real-time scheduler for scheduling real-time tasks and general purpose tasks.

9. The file server as claimed in claim 1, wherein the file server supports at least one industry standard network file access protocol.

10. The file server as claimed in claim 1, wherein the file server has multiple file systems existing concurrently over multiple communication stacks, with shared data access.

11. The file server as claimed in claim 1, wherein the cached disk storage subsystem includes a plurality of channel directors for interfacing the semiconductor cache memory to the data mover computers, and a plurality of disk directors and disk adapters for interfacing the semiconductor cache memory to the array of disk drives.

12. The network file server as claimed in claim 1, wherein at least one of the data mover computers is a spare for use as a replacement for any one of the other data mover computers that would experience a failure.

13. A file server for serving clients in a data network, the file server comprising:

a cached disk storage subsystem including a semiconductor cache memory, an array of disk drives, a plurality of channel directors for interfacing the semiconductor cache memory to the data mover computers, and a plurality of disk directors and disk adapters for interfacing the semiconductor cache memory to the array of disk drives; and

a plurality of data mover computers connected to the cached disk storage subsystem and linked to the data network for responding to a request for file access from a client in the data network by transferring data between the cached disk storage subsystem and the data network;

wherein the cached disk storage subsystem stores read-write files which are shared among the clients and each read-write file is accessible by the clients through more than one of the data mover computers, and the data mover computers maintain in the cached disk storage subsystem a file directory accessible by the data mover computers in response to file access requests to determine whether or not file access for a client is permitted, to map file names to logical blocks of data that comprise the files and said logical blocks of data are stored in the cached disk storage subsystem, and to lock and unlock each of the read-write files for shared read-write access among the clients through more than one of the data mover computers, wherein each data mover computer is programmed to access the locking information in the cache memory of the cached disk storage subsystem in order to obtain a read lock or a write lock on at least a portion of each of the read-write files to be accessed;

wherein file system software for managing the file directory is replicated in each data mover computer, the file system software including software for managing mapping of names of files accessible by the clients to the logical blocks of data that comprise the files and said logical blocks of data are stored in the cached disk storage subsystem, and software for accessing the file directory to determine whether or not a read-write file to be accessed is locked, and when a read-write file to be accessed is not locked, to update the file directory by placing a lock on at least a portion of the read-write file to be accessed, and

wherein the cached disk storage subsystem responds to requests from the data mover computers for access to logical block addresses of the logical blocks comprising the files to be accessed by the clients, and the cached disk storage subsystem has a limited internal locking facility for ensuring that reading and writing to a logical block is an atomic operation.

14. The file server as claimed in claim 13, wherein the data mover computers are commodity personal computers that share a data link internal to the file server, and the file server further includes a data terminal linked to the commodity personal computers for permitting an operator at the data terminal to communicate with the commodity personal computers to manage and control resources of the file server.

15. The file server as claimed in claim 14, wherein the file server supports a Simple Network Management Protocol (SNMP) for the operator to manage and control resources of the file server from the data terminal.

16. The file server as claimed in claim 14, wherein the data terminal is linked to two of the data mover computers by a link different from the data link internal to the file server, and only one of said two of the data mover computers is active at any given time for servicing the data terminal.

17. The file server as claimed in claim 13, wherein the data mover computers are commodity personal computers, and each of the commodity personal computers is linked to the cached disk storage subsystem by at least one respective fast, wide differential (FWD) SCSI connection.

18. The file server as claimed in claim 13, wherein the data mover computers each include a real-time scheduler for scheduling real-time tasks and general purpose tasks.

19. The file server as claimed in claim 13, wherein the file server supports at least one industry standard network file access protocol, and the file server has multiple file systems existing concurrently over multiple communication stacks, with shared data access.

20. The file server as claimed in claim 13, wherein at least one of the data mover computers is a spare for use as a replacement for any one of the other data mover computers that would experience a failure.

21. A file server for serving clients in a data network, the file server comprising:

a cached disk storage subsystem including a semiconductor cache memory, an array of disk drives, a plurality of channel directors for interfacing the semiconductor cache memory to the data mover computers, and a plurality of disk directors and disk adapters for interfacing the semiconductor cache memory to the array of disk drives; and

a plurality of data mover computers connected to the cached disk storage subsystem and linked to the data network for responding to a request for file access from a client in the data network by transferring data between the cached disk storage subsystem and the data network;

wherein the cached disk storage subsystem stores read-write files which are shared among the clients and each read-write file is accessible by the clients through more than one of the data mover computers, and the data mover computers maintain in the cached disk storage subsystem a file directory accessible by the data mover computers in response to file access requests to determine whether or not file access for a client is permitted, to map file names to logical blocks of data that comprise the files and said logical blocks of data are stored in the cached disk storage subsystem, and to lock and unlock each of the read-write files for shared read-write access among the clients through more than one of the data mover computers, wherein each data mover computer is programmed to access the locking information in the cache memory of the cached disk storage subsystem in order to obtain a read lock or a write lock on at least a portion of each of the read-write files to be accessed;

wherein each of the data mover computers is a commodity personal computer, the data movers are linked together by a data link internal to the file server, and each of the data mover computers includes a real-time scheduler for scheduling real-time tasks and general purpose tasks;

wherein file system software for managing the file directory is replicated in each data mover computer, the file system software including software for managing mapping of names of files accessible by the clients to the logical blocks of data that comprise the files and said logical blocks of data are stored in the cached disk storage subsystem, and software for accessing the file directory to determine whether or not a read-write file to be accessed is locked, and when a read-write file to be accessed is not locked, to update the file directory by placing a lock on at least a portion of the read-write file to be accessed, and wherein the file server supports at least one industry standard network file access protocol, and the file server has multiple file systems existing concurrently over multiple communication stacks, with shared data access; and

wherein the cached disk storage subsystem responds to requests from the data mover computers for access to the logical block addresses of the logical blocks that comprise the files to be accessed by the clients, and the cached disk storage subsystem has a limited internal locking facility for ensuring that reading and writing to a logical block is an atomic operation.

22. The file server as claimed in claim 21, further including a data terminal linked to the commodity personal computers for permitting an operator at the data terminal to communicate with the commodity personal computers to manage and control resources of the file server.

23. The file server as claimed in claim 22, wherein the file server supports a Simple Network Management Protocol (SNMP) for the operator to manage and control resources of the file server from the data terminal.

24. The file server as claimed in claim 22, wherein the data terminal is linked to two of the data mover computers by a link different from the data link internal to the file server, and only one of said two of the data mover computers is active at any given time for servicing the data terminal.

25. A method of operating a file server for serving clients in a data network, the file server including a cached disk storage subsystem and a plurality of data mover computers linking the cached disk storage subsystem to the data network for transfer of data between the cached disk storage subsystem and the data network, and the cached disk storage subsystem having an array of disk drives and a semiconductor cache memory for storing data written to and read from the array of disk drives, said method comprising the steps of:

(a) maintaining in the cached disk storage subsystem a file directory accessible by the data mover computers in response to file access requests to determine whether or not file access by a client is permitted, and to map file names to logical blocks of data storage that comprise the files and said logical blocks of data are stored in the cached disk storage subsystem, the file directory including locking information for read-write files which are shared among the clients, wherein the read-write files are accessible by the clients through more than one of the data mover computers; and

(b) one of the data mover computers receiving from one of the clients a request for read/write file access to a shared read/write file, said one of the data mover computers accessing the file directory to determine whether or not file access by said one of the clients is permitted, and when read/write file access by said one of the clients is permitted, said one of the data mover computers accessing the locking information in the semiconductor cache memory of the cached disk storage subsystem in order to obtain a read lock or a write lock on a portion of the shared read-write file, and satisfying the request by transferring data between the cached disk storage subsystem and the data network.

26. The method as claimed in claim 25, which includes said one of the data mover computers invoking a real-time scheduler to schedule operations to satisfy the request.

27. The method as claimed in claim 25, which includes said one of the data mover computers providing file access to said one of the clients by using the NFS file access protocol.

28. The method as claimed in claim 25, which includes buffering said data in a buffer in said one of the data mover computers.

29. The method as claimed in claim 25, which includes the file server concurrently supporting multiple file systems over multiple communication stacks, with shared data access, and exporting to the clients multiple file systems.

30. A method of operating a file server for serving clients in a data network, the file server including a cached disk storage subsystem and a plurality of data mover computers linking the cached disk storage subsystem to the data network for transfer of data between the cached disk storage subsystem and the data network, and the cached disk storage subsystem having an array of disk drives and a semiconductor cache memory for storing data written to and read from the array of disk drives, said method comprising the steps of:

(a) maintaining in the cached disk storage subsystem a file directory accessible by the data mover computers in response to file access requests to determine whether or not file access by a client is permitted, and to map file names to logical blocks of data said logical blocks of data comprise the files and that are stored in the cached disk storage subsystem, the file directory including locking information for read-write files which are shared among the clients, wherein the read-write files are accessible by the clients through more than one of the data mover computers; and

(b) one of the data mover computers receiving from one of the clients a request for read/write file access to a shared read/write file, said one of the data mover computers accessing the file directory to determine whether or not file access by said one of the clients is permitted, and when read/write file access by said one of the clients is permitted, said one of the data mover computers accessing the locking information in the semiconductor cache memory of the cached disk storage subsystem in order to obtain a read lock or a write lock on at least a portion of the shared read-write file, and satisfying the request by transferring data between the cached disk storage subsystem and the data network;

wherein said one of the data mover computers maintains the file directory by managing mapping of names of files accessible by the clients to logical blocks of data that comprise the files and said logical blocks of data are stored in the integrated cached disk array storage subsystem, and wherein the cached disk storage subsystem responds to requests from the data mover computers for access to logical block addresses of the logical blocks that comprise the files to be accessed by the clients, and ensures that reading and writing to a logical block is an atomic operation.

31. The method as claimed in claim 30, which includes said one of the data mover computers invoking a real-time scheduler to schedule operations to satisfy the request.

32. The method as claimed in claim 30, which includes said one of the data mover computers providing file access to said one of the clients by using the NFS file access protocol.

33. The method as claimed in claim 30, which includes buffering said data in a buffer in said one of the data mover computers.

34. The method as claimed in claim 30, which includes the file server concurrently supporting multiple file systems over multiple communication stacks, with shared data access, and exporting to the clients multiple file systems.