# US 8,788,872 B2 · Managing failover operations on a cluster of computers

> Agents: this data is available as JSON from the patentgrep API and MCP server — see https://patentgrep.com/llms.txt

- Number: US 8,788,872 B2
- Document ID: US8788872B2
- Status: Granted
- Kind: B2
- Application number: 13/689,170
- Filed: 2012-11-29
- Published: 2013-04-18
- Granted: 2014-07-22
- Earliest claimed: 2011-10-18
- Assignees: International Business Machines Corporation
- Applicants: International Business Machines Corporation
- Inventors: Travis M. Drucker; Joel C. Dubbels; Thomas J. Eggebraaten; Janice R. Glowacki; Richard J. Stevens; David A. Wall
- Web page: https://patentgrep.com/patent/US8788872B2

## CPC

- G16H 30/20: for handling medical images, e.g. DICOM, HL7 or PACS
- G06F 11/1482: using middleware or operating system [OS] functionalities
- G06F 11/20: using active fault-masking, e.g. by switching out faulty elements or by switching in spare elements
- G06F 11/1466: {to make the backup process non-disruptive}
- G06F 11/2094: {Redundant storage or storage space (G06F11/2056 takes precedence)}
- G16H: HEALTHCARE INFORMATICS, i.e. INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR THE HANDLING OR PROCESSING OF MEDICAL OR HEALTHCARE DATA
- G06F: ELECTRIC DIGITAL DATA PROCESSING (computer systems based on specific computational models G06N)

## Abstract

Managing failover operations on a cluster of computers, including: identifying, by a failover hold module, a failure to access data storage in the cluster of computers; preventing the execution of all read operations directed to the data storage that were received after the failure to access data storage was identified; executing all write operations directed to the data storage that were received after the failure to access data storage was identified, including writing data to a cache; identifying that a failover to alternative data storage is complete; executing the held read operations, including reading data from the alternative data storage; and copying, from cache to the alternative data storage, the data written to the cache as part of the write operations.

## Claims

### Claim 1

A method of managing failover operations on a cluster of computers, the method comprising:
identifying, by a failover hold module, a failure to access data storage in the cluster of computers;
in response to identifying the failure to access data storage:
holding all read operations directed to the data storage; and
executing all write operations directed to the data storage by redirecting the write operations to a cache;
identifying that a failover to an alternative data storage is complete;
in response to identifying that the failover to the alternative data storage is complete:
copying, from cache to the alternative data storage, the data written to the cache as part of execution of the write operations; and
executing held read operations by reading data from the alternative data storage instead of the data storage to which the read operation is directed.

### Claim 2 (depends on 1)

The method of claim 1 wherein identifying a failure to access data storage includes identifying that a read operation failed.

### Claim 3 (depends on 1)

The method of claim 1 wherein identifying a failure to access data storage includes identifying that a write operation failed.

### Claim 4 (depends on 1)

The method of claim 1 wherein identifying a failure to access data storage includes identifying a failure to access a file system.

### Claim 5 (depends on 1)

The method of claim 1 wherein identifying a failure to access data storage includes identifying a failure to access a database.

### Claim 6

A method of managing maintenance of a cluster of computers, the method comprising:
identifying, by a failover module, one or more scheduled maintenance operations to be executed on the cluster of computers;
initiating the execution of the scheduled maintenance operations;
in response to initiating the execution of the scheduled maintenance operations, holding all received data storage access requests;
determining that the scheduled maintenance operations are complete; and
in response to determining that the scheduled maintenance operations are complete, executing all held data storage access requests including executing all write requests that were received after initiating the execution of the scheduled maintenance operations.

### Claim 7 (depends on 6)

The method of claim 6 wherein holding all received data storage access requests further comprises storing, in a cache, all data storage access requests that were received after initiating the execution of the scheduled maintenance operations.

### Claim 8 (depends on 6)

The method of claim 6 wherein executing all held data storage access requests includes executing all read requests that were received after initiating the execution of the scheduled maintenance operations.

### Claim 9 (depends on 6)

The method of claim 6 wherein the one or more scheduled maintenance operations to be executed on the cluster of computers includes backing up data storage on the cluster of computers.