Multi-function server input/output subsystem and method

• US 5,757,642 A
• Filed: 06/27/1997
• Issued: 05/26/1998
• Est. Priority Date: 01/20/1995
• Status: Expired due to Term

• Current Assignee: Dell USA LP (Dell Technologies Inc.)
• Original Assignee: Dell USA LP (Dell Technologies Inc.)
• Inventors: Jones, Craig Steven
• Primary Examiner(s): Gordon, Paul P.
• Application Number:
  US08/883,907
• Time in Patent Office: 333 Days
• Field of Search: 364/131, 364/133, 364/134, 364/176, 364/187, 371/8.1, 371/9.1, 395/200.33, 395/200.43, 340/825.15, 340/825.16
• US Class Current: 700/5
• CPC Class Codes: G06F 11/201 between storage system components
• CPC Class Codes: G06F 11/2038 with a single idle spare processing component
• CPC Class Codes: G06F 11/2046 where the redundant components share persistent storage G06F11/2043 takes precedence
• CPC Class Codes: G06F 11/2071 using a plurality of controllers

Abstract

A method and system for providing fault tolerance in a networked client/server computing environment by introducing a server computer comprised of a first computer with a first secondary storage controller and a first communications controller and a second computer with a second secondary storage controller and a secondary communications controller. The invention introduces a high speed communications channel that runs between secondary storage controllers and communications controllers in each of the computers, thereby allowing data flow between the communications controllers and enabling the first and second computers to mirror each other or cooperate to form a cluster server. In addition, the communications channel serves as a pathway for secondary storage I/O dataflow, thereby enabling the first and second computers to share secondary storage resources.

Claims

1. A server computer system comprising:

a first computer having a first processor executing a first operating system, said first processor being coupled to a first secondary storage controller and a first communications controller;

a second computer having a second processor executing a second operating system, said second processor being coupled to a second secondary storage controller and a second communications controller;

a communications channel coupling said first and second secondary storage controllers and said first and second communications controllers and providing a channel for communication of data between said first and second processors to thereby allow an operation of said second computer to mirror an operation of said first computer; and

a single common fault tolerant secondary storage redundant array of disks (RAID) subsystem coupled to said communications channel and accessible by said first and second processors, said communications channel further providing a channel for communication of data between said first and second computers and said secondary storage RAID subsystem, said secondary storage RAID subsystem thereby being available to said second computer upon occurrence of a failure in said first computer.

2. The system as recited in claim 1 wherein said first secondary storage controller and said first communications controller are embodied as a single, integrated controller.

3. The system as recited in claim 1 further comprising a second communications channel coupling said first and second secondary storage controllers.

4. The system as recited in claim 1 further comprising a second communications channel coupled to said first and second secondary storage controllers and said first and second communications controllers to thereby provide a redundant channel for communication of data therebetween.

5. The system as recited in claim 1 wherein said secondary storage RAID subsystem is dual-ported, said system further comprising a second communications channel coupling a second port on said secondary storage RAID subsystem to said first and second secondary storage controllers.

6. The system as recited in claim 1 wherein the secondary storage RAID subsystem includes a plurality of secondary storage units coupled to said communications channel.

7. The system as recited in claim 1 wherein said communications channel is a loop channel passing through said secondary storage RAID subsystem.

8. A method of operating a server computer system, comprising the steps of:

coupling a first computer having a first processor executing a first operating system to a first secondary storage controller and a first communications controller;

coupling a second computer having a second processor executing a second operating system to a second secondary storage controller and a second communications controller;

communicating data via a communications channel coupling said first and second secondary storage controllers and said first and second communications controllers, said communications channel providing a channel for communication of data between said first and second processors to thereby allow an operation of said second computer to mirror an operation of said first computer; and

accessing a single common fault tolerant secondary storage redundant array of disks (RAID) subsystem coupled to said communications channel with said first and second processors, said communications channel further providing a channel for communication of data between said first and second computers and said secondary storage RAID subsystem, said secondary storage RAID subsystem thereby being available to said second computer upon occurrence of a failure in said first computer.

9. The method as recited in claim 8 wherein said step of coupling said first computer to a first secondary storage controller and a first communications controller comprises the step of coupling said first computer to a single, integrated first secondary storage and communications controller.

10. The method as recited in claim 8 further comprising the step of coupling a second serial communications channel to said first and second secondary storage controllers.

11. The method as recited in claim 8 further comprising the step of coupling a second communications channel to said first and second secondary storage controllers and said first and second communications controllers to thereby provide a redundant channel for communication of data therebetween.

12. The method as recited in claim 8 wherein said secondary storage RAID subsystem includes a secondary storage unit;

and said step of accessing comprises the step of accessing a dual-ported secondary storage unit and said method further comprises the step of coupling a second communications channel to a second port on said secondary storage unit and to said first and second secondary storage controllers.

13. The method as recited in claim 8 wherein said secondary storage RAID subsystem includes a plurality of secondary storage units;

and said step of accessing comprises the step of accessing the plurality of secondary storage units coupled to said communications channel.

14. The method as recited in claim 8 further comprising the step of controlling said first and second secondary storage controllers with said first and second processors via first and second secondary storage driver routines executed in said first and second processors, respectively.

15. The method as recited in claim 8 further comprising the step of controlling said first and second secondary storage controllers with said first and second processors via first and second secondary storage driver routines and first and second communications driver routines executed in said first and second processors, respectively.

16. The method as recited in claim 8 further comprising the step of controlling said first and second secondary storage controllers with first and second operating systems executing in said first and second processors, respectively.

17. The method as recited in claim 8 wherein said step of communicating data comprises the step of communicating data via a communications channel that is a loop channel passing through said secondary storage subsystem.

18. A server computer system, comprising:

a first computer having a first processor executing a first operating system, said first processor being coupled to a first secondary storage controller and a first communications controller;

a second computer having a second processor executing a second operating system, said second processor being coupled to a second secondary storage controller and a second communications controller;

a first communications channel coupling said first and second secondary storage controllers and said first and second communications controllers and providing a channel for communication of data between said first and second processors to thereby allow an operation of said second computer to mirror an operation of said first computer;

a second communications channel coupling said first and second secondary storage controllers; and

a single common fault tolerant secondary storage redundant array of disks (RAID) subsystem, the RAID subsystem including a plurality of secondary storage units coupled to said first and second communications channels and accessible by said first and second processors, first and second communications channels providing redundant channels for communication of data between said first and second computers and said plurality of secondary storage units, said plurality of secondary storage units thereby being available to said second computer upon occurrence of a failure in said first computer.

19. The system as recited in claim 18 wherein said first secondary storage controller and said first communications controller are embodied as a single, integrated controller.

20. The system as recited in claim 18 wherein said plurality of secondary storage units are dual-ported, a first port of each said secondary storage unit being coupled to said first communications channel, a second port on each said secondary storage unit being coupled to said second communications channel.

21. The system as recited in claim 18 wherein said first communications channel is a portion of a loop channel passing through each said secondary storage unit.

22. The system as recited in claim 18 wherein said first and second communications channels have a data rate of at least 10 megabytes per second.

23. A method of operating a server computer system, comprising the steps of:

coupling a first computer having a first processor executing a first operating system to a first secondary storage controller and a first communications controller;

coupling a second computer having a second processor executing a second operating system to a second secondary storage controller and a second communications controller;

communicating data via a first communications channel coupling said first and second secondary storage controllers and said first and second communications controllers, said first communications channel providing a channel for communication of data between said first and second processors to thereby allow an operation of said second computer to mirror an operation of said first computer;

communicating data via a second communications channel coupling said first and second secondary storage controllers; and

accessing selectable ones of a plurality of secondary storage units within a single common fault tolerant redundant array of disks (RAID) storage subsystem coupled to said first and second communications channels and accessible by said first and second processors, said first and second communications channels providing redundant channels for communication of data between said first and second computers and said plurality of secondary storage units, said plurality of secondary storage units thereby being available to said second computer upon occurrence of a failure in said first computer.

24. The method as recited in claim 23 wherein said step of coupling said first computer to a first secondary storage controller and a first communications controller comprises the step of coupling said first computer to a single, integrated first secondary storage and communications controller.

25. The method as recited in claim 23 wherein said step of accessing selectable ones of a plurality of secondary storage units comprises the step of accessing selectable ones of a plurality of dual-ported secondary storage units, a first port of said secondary storage unit coupled to said first communications channel, a second port on said secondary storage unit coupled to said second communications channel.

26. The method as recited in claim 23 wherein said step of communicating data via said first communications channel comprises the step of communicating data via a first communications channel that is a portion of a loop channel passing through said secondary storage unit.

27. The method as recited in claim 23 wherein said step of communicating data via said first and second communications channels comprises the steps of communicating data via said first and second communications channels having a data rate of at least 10 megabytes per second.

28. The method as recited in claim 23 further comprising the step of allowing said first and second computers to function as a cluster with operating systems executing in said first and second processors.

29. A server computer system comprising:

a first computer having a first processor executing a first operating system, the first processor being coupled to a first integrated controller;

a second computer having a second processor executing a second operating system, the second processor being coupled to a second integrated controller;

a communications channel coupling said first and second integrated controllers and providing a channel for communication of data between the first and second processors to thereby selectively allow the first and second computers to mirror their operation and to operate as a cluster; and

a single common, fault tolerant secondary storage redundant array of disks (RAID) subsystem coupled to the communications channel and accessible by the first and second processors, the communications channel further providing a channel for communication of data between the first and second computers and the secondary storage RAID subsystem.

30. The server computer system of claim 29 wherein the communications channel is a serial communications channel.

31. The server computer system of claim 30 wherein the serial communications channel supports a serial communications standard selected from P1394, Fibre Channel, and SSA.

32. The server computer system of claim 30 wherein the serial communications channel has a data transmission rate of at least 10 megabytes per second.

33. The server computer system of claim 29 further comprising a second communications channel coupling the first and second integrated controllers to thereby provide a second channel for communication of data between the first and second processors.

34. The server computer system of claim 33 wherein secondary storage RAID subsystem is coupled to the second communications channel.