Failover system and method for cluster environment

• US 20050268156A1
• Filed: 07/25/2005
• Published: 12/01/2005
• Est. Priority Date: 08/09/2001
• Status: Active Grant

• Current Assignee: Dell Products LP (Dell Technologies Inc.)
• Original Assignee: Dell Products LP (Dell Technologies Inc.)
• Inventors: Rooholamini, Mohamad Reza, Hsieh, Jenwei, Mashayekhi, Victor
• Granted Patent: US 7,139,930 B2
• Time in Patent Office: Days
• US Class Current: 714/4
• CPC Class Codes: G06F 11/2028 eliminating a faulty processor or activating a spare
• CPC Class Codes: G06F 11/2035 without idle spare hardware
• CPC Class Codes: G06F 11/2046 where the redundant components share persistent storage G06F11/2043 takes precedence
• CPC Class Codes: H04L 69/40 for recovering from a failure of a protocol instance or entity, e.g. service redundancy protocols, protocol state redundancy or protocol service redirection management of faults, events, alarms or notifications in data switching networks H04L41/06

Abstract

A failover method and system is provided for a computer system having at least three nodes operating as a cluster. One method includes the steps of detecting failure of one node, determining the weight of at least two surviving nodes, and assigning a failover node based on the determined weights of the surviving nodes. Another method includes the steps detecting failure of one node and determining the time of failure, and assigning a failover node based in part on the determined time of failure. This method may also include the steps of determining a time period during which nodes in the cluster are heavily utilized, and assigning a failover node that is not heavily utilized during that time period.

Claims

1. A failover method for a computer system having at least three nodes operating as a cluster, said method comprising the steps of:

detecting a failure of one of said at least three nodes;

determining a time of failure of said one node;

assigning a failover node taking into consideration said determined time; and

assigning applications running on said failed node to said failover node.

2. The failover method according to claim 1, further comprising the steps of:

for at least one node in said cluster, determining a time period during which said node is heavily utilized; and

preventing said at least one node from being assigned as a failover node during said time period during which it is heavily utilized.

3. The failover method according to claim 2, further comprising the steps of:

for at least said failed node, determining in advance of failure a time during which at least one application running on said failed node is heavily utilized; and

following the failure of said node, if failure occurs during said determined time period, then assigning a failover node for said at least one application first.

4. A cluster computer system, comprising:

at least three nodes, wherein said at least three nodes are computer systems operating as a cluster, wherein said cluster computer system is capable of determining a time of failure of one of said at least three nodes, and implementing a failover policy in which, following a failure of said one node, a failover node is selected based in part on said determined time.

5. The cluster computer system of claim 4, wherein said cluster computer system is further capable of determining a time period which at least one of said nodes is heavily utilized, and preventing said at least one node from being assigned as a failover node during said determined time period.

6. The cluster computer system of claim 5, wherein said cluster computer system is further capable of determining a time period which at least one application on said failed node is heavily utilized, and upon failure of said failed node, if said failure occurs during said determined time, then failing over said at least one application first.

7. A failover method for a computer system having at least three nodes operating as a cluster, said method comprising the steps of:

determining a time period during which each of said at least three nodes are heavily utilized;

detecting a failure of one of said at least three nodes;

determining a time of failure of said one node; and

preventing failover of applications running on said one node to other of said at least three nodes if said determined time period for said other node includes said determined time of failure.