Resource management in a multiple resource system where each resource includes an availability state stored in a memory of the resource

• US 5,361,347 A
• Filed: 10/22/1992
• Issued: 11/01/1994
• Est. Priority Date: 04/06/1990
• Status: Expired due to Term

• Current Assignee: EMC Corporation (Dell Technologies Inc.)
• Original Assignee: MTI Technology Corporation
• Inventors: Glider, Joseph S., Jaffe, David H.
• Primary Examiner(s): Kulik, Paul V.
• Application Number:
  US07/965,135
• Time in Patent Office: 740 Days
• Field of Search: 395/575, 395/500, 395/650, 395/725, 371/15.1, 371/16.1, 371/16.5, 371/18, 371/11.1, 371/11.3, 371/29.1
• US Class Current: 714/44
• CPC Class Codes: G06F 11/22 Detection or location of defective computer hardware by testing during standby operation or during idle time, e.g. start-up testing
• CPC Class Codes: G06F 2209/503 Resource availability
• CPC Class Codes: G06F 9/5011 the resources being hardware resources other than CPUs, Servers and Terminals

Abstract

A computing system providing resource management in a multiple resource system. In the preferred embodiment, the computing system has a plurality of resources for storing, transmitting or manipulating data. The system also has a fault management subsystem that accesses and operates the resources when the resources are in a first availability state and an operational subsystem for accessing and operating the resources when the resources are in a second availability state. The system has a mechanism for providing real time sharing of any of the resources between the fault management subsystem and the operational subsystem without disrupting the services provided by the operational subsystem. In addition, the system has a mechanism for representing the operational interdependencies of the resources by organizing the resources in a logical structure in which each resource is a node conceptually connected to at least one other resource.

Claims

1. A method for determining the availability of resources in a computing subsystem coupled to a host computer, each resource having an availability state, comprising the steps of:

storing information in a memory coupled to one of said resources regarding the operational relationship between said one resource and at least one other resource in the computing subsystem;

determining whether a resource is operable;

changing the availability state of a resource in response to a determination of a fault management subsystem that a resource is inoperable; and

determining, internally to each resource, how a change in the availability state of a resource affects the availability of other resources in the computing subsystem.

2. A method for allocating resources in a computing subsystem coupled to a host computer comprising the steps of:

providing a plurality of resources for storing, transmitting or manipulating data, each resource having an availability state stored in a memory in said resource;

accessing and operating resources that are in a first availability state with a fault management subsystem;

providing services to the host computer with an operational subsystem, distributed throughout said computing subsystem, by generating a plurality of resource requests in response to a host request from said host computer, said host request having a time-out period;

accessing and operating resources that are in a second availability state with said operational subsystem; and

controlling access to an individual resource by the fault management subsystem and the operational subsystem, including changing the availability state of a resource from the second state to the first state to permit the fault management subsystem to gain access to the resource and holding a request for access to said resource from said operational subsystem for less than said time-out period and causing said fault management subsystem to complete its access of said resource in less than said time-out period.

3. A computing system for coupling to a host computer comprising:

a plurality of resources for storing, transmitting or manipulating data, each resource having an availability state stored in a memory in said resource;

a fault management subsystem having means for accessing and operating resources that are in a first availability state;

an operational subsystem, distributed throughout said computing system, for providing services to the host computer, the operational subsystem generating a plurality of resource requests in response to a host request from said host computer, said host request having a time-out period;

said operational subsystem having means for accessing and operating resources that are in a second availability state;

means for controlling access to an individual resource by the fault management subsystem and the operational subsystem, including means for changing the availability state of a resource from the second state to the first state to permit the fault management subsystem to gain access to the resource and holding a request for access to said resource from said operational subsystem for less than said time-out period and means for causing said fault management subsystem to complete its access of said resource in less than said time-out period.

4. The computing system of claim 3 wherein the fault management subsystem further comprises means for determining whether a resource is operable, and wherein the means for controlling access further comprises means for changing the availability state of the resource in response to said means for determining that a resource is inoperable.

5. The computing system of claim 3 wherein the means for controlling access comprises memory means for storing information regarding each resource'"'"'s availability state.

6. The computing system of claim 5 wherein the means for controlling access further comprises means for controlling access to a resource by the fault management subsystem and the operational subsystem using the information regarding the resource availability state stored in the memory means.

7. A data storage subsystem for connecting to a main central processing unit, comprising:

at least one element, said element having a local processor, a memory, and a plurality of resources, said resources forming part of a data storage path for connecting to said main central processing unit;

a plurality of resource control blocks in said memory, each of said resources having one of said resource control blocks associated with it;

each of said resource control blocks having an availability entry and means for causing a request for a resource to wait;

an operating subsystem, distributed throughout said data storage subsystem, for providing data to and from said main central processing unit;

a diagnostic system coupled to said element; and

means for providing real time sharing of said resources between said diagnostic system and said main central processing unit by putting a test indication in said availability entry during access of the resource by said diagnostic system and putting a request for said resource from said operating subsystem in said means for causing a request for a resource to wait, until said diagnostic system is finished with said resource, then changing said availability state and returning a resource available signal to said operating subsystem, or determining the existence of and assigning an equivalent resource in response to said operating subsystem request.

8. The data storage subsystem of claim 7 wherein said operating subsystem includes a first program in said memory run by said local processor and said diagnostic system includes a second program in said memory run by said local processor.

9. The data storage subsystem of claim 8 further comprising a plurality of disk drives and a plurality of said elements, at least two of said elements comprising data routing systems coupled between said main central processing unit and a plurality of said disk drives.

10. A computing system for coupling to a host computer comprising:

a plurality of resources for storing, transmitting or manipulating data, each resource having an availability state;

a fault management subsystem having means for accessing and operating resources that are in a first availability state;

an operational subsystem for providing services to the host computer, the operational subsystem generating a plurality of resource requests in response to a host request from said host computer, said host request having a time-out period;

said operational subsystem having means for accessing and operating resources that are in a second availability state;

means for controlling access to an individual resource by the fault management subsystem and the operational subsystem, including means for changing the availability state of a resource from the second state to the first state to permit the fault management subsystem to gain access to the resource and selectively either holding a request for access to said resource from said operational subsystem for less than said time-out period or redirecting said request for access to a redundant resource.