US 10,474,532 B1Granted

Automatic fault tolerance in a computing system providing concurrent access to shared computing resource objects

AssigneeEMC IP Holding Company LLC

InventorsAmitava Roy, Rajesh Kumar Gandhi, Daniel S. Keefe, Norman Speciner, Lorenzo Bailey, Hongxin Zhang

Life of this patent

Estimating the term…

Loading patent…

Abstract

Techniques are disclosed for provided automatic fault tolerance in data storage systems and other computer systems managing access to shared computing resources using the construct of a resource instance manager together with an architecture for designing and implementing task-oriented state-based commands for accessing the shared computing resources. A set of resource instance managers respond to all commands requesting access to a set of respective shared resources. Access to each shared resource is managed by a unique resource instance manager for that resource which maintains a consistent state for that shared resource. When commands are designed appropriately, the system can be restored using a system state history maintained transparently by a system-provided application program interface.

Claims19

Dependent claims

A method of providing automatic fault tolerance in a computing system managing concurrent access to shared computing resources, the method comprising:

executing, by processing circuitry of the computing system, multiple commands which collectively access and modify shared computing resources, each command:
(i) implementing a finite set of command states,
(ii) remaining idle while in each of the command states of that command until receiving an expected set of events for that command state,
(iii) maintaining command state data which is accessed and modified by at least one command state of that command, and
(iv) transitioning between command states in response to messages received as part of the expected set of events for each command state and the command state data;
maintaining a system state history of the computing system which includes recording:
(i) a current set of commands being executed by the processing circuitry,
(ii) a running history of changes to the command state data for each command of the current set of commands, and
(iii) a running history of changes made to attributes of the shared computing resources;
and
in response to a system failure event, reconstructing the command state data of each command of the current set of commands using the system state history and restoring the computing system to a previous system state before resuming normal operation.

8 more elements

A computer program product comprising a non-transitory computer-readable storage medium storing instructions which, when executed by processing circuitry of a computing system managing concurrent access to shared computing resources, cause the processing circuitry to:

maintain a system state history of the computing system by recording:
(i) a current set of commands being executed by the processing circuitry,
(ii) a running history of changes to command state data for each command of the current set of commands, and
(iii) a running history of changes made to attributes of the shared computing resources;
and
in response to a system failure event, reconstruct the command state data of each command of the current set of commands using the system state history and restore the computing system to a previous system state before resuming normal operation;
wherein the instructions cause the processing circuitry to maintain the system state history of the computing system while the processing circuitry executes the current set of commands which collectively access and modify shared computing resources, each command:
(i) implementing a finite set of command states,
(ii) remaining idle while in each of the command states of that command until receiving an expected set of events for that command state,
(iii) maintaining command state data which is accessed and modified by at least one command state of that command, and
(iv) transitioning between command states in response to messages received as part of the expected set of events for each command state and the command state data.

8 more elements

A computing system for providing automatic fault while managing concurrent access to shared computing resources, the computing system comprising processing circuitry coupled to memory configured to:

execute multiple commands which collectively access and modify shared computing resources, each command:
(i) implementing a finite set of command states,
(ii) remaining idle while in each of the command states of that command until receiving an expected set of events for that command state,
(iii) maintaining command state data which is accessed and modified by at least one command state of that command, and
(iv) transitioning between command states in response to messages received as part of the expected set of events for each command state and the command state data;
maintain a system state history of the computing system by recording:
(i) a current set of commands being executed by the processing circuitry,
(ii) a running history of changes to the command state data for each command of the current set of commands, and
(iii) a running history of changes made to attributes of the shared computing resources;
and
in response to a system failure event, reconstruct the command state data of each command of the current set of commands using the system state history and restore the computing system to a previous system state before resuming normal operation.

8 more elements

Dependencies are inferred from the claim text.