Scalable file server with highly available pairs

• US 6,961,749 B1
• Filed: 08/25/1999
• Issued: 11/01/2005
• Est. Priority Date: 08/25/1999
• Status: Expired due to Term

• Current Assignee: NetApp, Inc.
• Original Assignee: Network Appliance Incorporated (NetApp, Inc.)
• Inventors: Kleiman, Steven
• Primary Examiner(s): Dinh, Dung C.
• Application Number:
  US09/383,340
• Time in Patent Office: 2,260 Days
• Field of Search: 709200-203, 709/212, 709/216, 709/201, 709/208, 709/209, 709/211, 709/238, 709/230, 714/1, 714/9, 714 10- 13, 710/100, 710305-306
• US Class Current: 709/203
• CPC Class Codes: G06F 11/2005 using redundant communication controllers
• CPC Class Codes: G06F 11/2007 using redundant communication media
• CPC Class Codes: G06F 11/2038 with a single idle spare processing component
• CPC Class Codes: G06F 11/2092 Techniques of failing over between control units
• CPC Class Codes: G06F 3/0601 Interfaces specially adapted for storage systems
• CPC Class Codes: G06F 3/0673 Single storage device

Abstract

The invention provides a file server system and a method for operating that system, which is easily scalable in number and type of individual components. A plurality of file servers are coupled using inter-node connectivity, such as an inter-node network, so that any one node can be accessed from any other node. Each file server includes a pair of file server nodes, each of which has a memory and each of which conducts file server operations by simultaneously writing to its own memory and to that of its twin, the pair being used to simultaneously control a set of storage elements such as disk drives. File server requests directed to particular mass storage elements are routed among file servers using an inter-node switch and processed by the file servers controlling those particular storage elements. The mass storage elements are disposed and controlled to form a redundant array, such as a RAID storage system. The inter-node network and inter-node switch are redundant, so that no single point of failure prevents access to any individual storage element. The file servers are disposed and controlled to recognize failures of any single element in the file server system and to provide access to all mass storage elements despite any such failures.

Claims

1. A file server including

a common set of storage elements;

at least a pair of nodes disposed in said file server, each of said nodes being connected to said common set of storage elements and including a processor and a memory so as to be capable of processing file server commands for said common set of storage elements;

at least one inter-node connectivity element coupled to said nodes and disposed to communicate with at least another pair of nodes disposed in another file server; and

a connection for coupling said file server commands to said nodes.

2. A file server as in claim 1, wherein each of said pair of nodes are disposed to failover to each other.

3. A file server as in claim 1, wherein

each of said storage elements corresponds to one node of said pair;

each of said storage elements is coupled to both nodes of said pair;

whereby both nodes of said pair are equally capable of controlling said storage elements.

4. A file server as in claim 1, wherein said connectivity element includes a NUMA network.

5. A file server as in claim 1, wherein sealing for a file server system that includes said file server can be achieved by coupling said pair of nodes to another pair of nodes in another file server through said inter-node connectivity element.

6. A file server as in claim 1, wherein said common set of storage elements includes a RAID storage system.

7. A file server as in claim 1,

wherein said pair of nodes includes a first node and a second node;

wherein when said file server commands are directed to said first node, said file server commands are executed at said first node, and a copy of said file server commands are stored at said second node; and

wherein when said file server commands are directed to said second node, said file server commands are executed at said second node, and a copy of said file server commands are stored at said first node.

8. A file server as in claim 7,

wherein when said file server commands are directed to said first node and said first node is inoperable, said file server commands are executed at said second node;

and

wherein when said file server commands are directed to said second node and said second node is inoperable, said file server commands are executed at said first node.

9. A file server as in claim 1,

wherein said pair of nodes includes a first node and a second node;

wherein said first node responds to said file server commands while said second node records said file server commands; and

wherein said pair of nodes are disposed to failover from said first node to said second node.

10. A file server as in claim 1,

wherein said pair of nodes includes a first node and a second node;

wherein said first node responds to a first one of said file server commands while said second node records said first one of said file server commands;

wherein said second node responds to a second one of said file server commands while said first node records said second one of file server commands; and

said pair of nodes are disposed to failover from said first node to said second node.

11. A file server as in claim 1,

wherein said pair of nodes includes a first node and a second node;

wherein said first node controls said storage elements in response to said file server commands while said second node is coupled to said storage elements and does not control said storage elements in response to said file server commands.

12. A method of operating a file server including

operating at least a pair of nodes disposed in said file server, each of said nodes being connected to a common set of storage elements and including a processor and a memory so as to be capable of processing file server commands for said common set of storage elements;

communicating with at least another pair of nodes in at least another file server through at least one inter-node connectivity element coupled to said nodes; and

coupling said file server commands to said nodes.

13. A method of operating a file server as in claim 12, wherein each of said pair of nodes are disposed to failover to each other.

14. A method of operating a file server as in claim 12, wherein

each of said storage elements corresponds to one node of said pair;

each of said storage elements is coupled to both nodes of said pair;

whereby both nodes in said pair are equally capable of controlling said storage elements.

15. A method of operating a file server as in claim 12, wherein said connectivity element includes a NUMA network.

16. A method of operating a file server as in claim 12, wherein scaling for a file server system that includes said file server can be achieved by coupling said pair of nodes to another pair of nodes in another file server through said inter-node connectivity element.

17. A method of operating a file server as in claim 12, wherein said common set of storage elements includes a RAID storage system.

18. A method of operating a file server as in claim 12,

wherein said pair of nodes includes a first node and a second node;

wherein when said file server commands are directed to said first node, said file server commands are executed at said first node, and a copy of said file server commands are stored at said second node; and

wherein when said file server commands are directed to said second node, said file server commands are executed at said second node, and a copy of said file server commands are stored at said first node.

19. A method of operating a file server as in claim 18,

wherein when said file server commands are directed to said first node and said first node is inoperable, said file server commands are executed at said second node;

and

wherein when said file server commands are directed to said second node and said second node is inoperable, said file server commands are executed at said first node.

20. A method of operating a file server as in claim 12,

wherein said pair of nodes includes a first node and a second node;

wherein said first node responds to said file server commands while said second node records said file server commands; and

wherein said pair of nodes are disposed to failover from said first node to said second node.

21. A method of operating a file server as in claim 12,

wherein said pair of nodes includes a first node and a second node;

wherein said first node responds to a first one of said file server commands while said second node records said first one of said file server commands;

wherein said second node responds to a second one of said file server commands while said first node records said second one of file server commands; and

said pair of nodes are disposed to failover from said first node to said second node.

22. A method of operating a file server as in claim 12,

wherein said pair of nodes includes a first node and a second node;

wherein said first node controls said storage elements in response to said file server commands while said second node is coupled to said storage elements and does not control said storage elements in response to said file server commands.

23. A memory storing information including instructions, the instructions executable by a processor to operate a file server, the instructions comprising:

operating at least a pair of nodes disposed in said file server, each of said nodes being connected to a common set of storage elements and including a processor and a memory so as to be capable of processing file server commands for said common set of storage elements;

communicating with at least another pair of nodes in at least another file server through at least one inter-node connectivity element coupled to said nodes; and

coupling said file server commands to said nodes.

24. A memory as in claim 23, wherein each of said pair of nodes are disposed to failover to each other.

25. A memory as in claim 23, wherein

each of said storage elements corresponds to one node of said pair;

each of said storage elements is coupled to both nodes of said pair;

whereby both nodes in said pair are equally capable of controlling said storage elements.

26. A memory as in claim 23, wherein said connectivity element includes a NUMA network.

27. A memory as in claim 23, wherein scaling for a file server system that includes said file server can be achieved by coupling said pair of nodes to another pair of nodes in another file server through said inter-node connectivity element.

28. A memory as in claim 23, wherein said common set of storage elements includes a RAID storage system.

29. A memory as in claim 23,

wherein said pair of nodes includes a first node and a second node;

wherein when said file server commands are directed to said first node, said file server commands are executed at said first node, and a copy of said file server commands are stored at said second node; and

wherein when said file server commands are directed to said second node, said file server commands are executed at said second node, and a copy of said file server commands are stored at said first node.

30. A memory as in claim 29,

wherein when said file server commands are directed to said first node and said first node is inoperable, said file server commands are executed at said second node;

and

wherein when said file server commands are directed to said second node and said second node is inoperable, said file server commands are executed at said first node.

31. A memory as in claim 23,

wherein said pair of nodes includes a first node and a second node;

wherein said first node responds to said file server commands while said second node records said file server commands; and

wherein said pair of nodes are disposed to failover from said first node to said second node.

32. A memory as in claim 23,

wherein said pair of nodes includes a first node and a second node;

wherein said first node responds to a first one of said file server commands while said second node records said first one of said file server commands;

wherein said second node responds to a second one of said file server commands while said first node records said second one of file server commands; and

said pair of nodes are disposed to failover from said first node to said second node.

33. A memory as in claim 23,

wherein said pair of nodes includes a first node and a second node;

wherein said first node controls said storage elements in response to said file server commands while said second node is coupled to said storage elements and does not control said storage elements in response to said file server commands.