System and method for graph based K-redundant resiliency for IT cloud

• US 9,077,613 B2
• Filed: 04/10/2013
• Issued: 07/07/2015
• Est. Priority Date: 04/10/2013
• Status: Active Grant

• Current Assignee: International Business Machines Corporation
• Original Assignee: International Business Machines Corporation
• Inventors: Deng, Yu, Karve, Alexei A., Kochut, Andrzej, Rendahl, Randy A., Sailer, Anca, Shaikh, Hidayatullah, Tomala-Reyes, Angel E.
• Primary Examiner(s): DUNCAN, MARC M
• Application Number:
  US13/859,956
• Publication Number:
  US 20140310554A1
• Time in Patent Office: 818 Days
• Field of Search: 714/4.1, 714/26, 714/37, 714/43
• US Class Current: 1/1
• CPC Class Codes: G06F 11/008 Reliability or availability analysis
• CPC Class Codes: G06F 9/45533 Hypervisors; Virtual machine monitors
• CPC Class Codes: H04L 41/0604 using filtering, e.g. reduction of information by using priority, element types, position or time
• CPC Class Codes: H04L 41/0663 Performing the actions predefined by failover planning, e.g. switching to standby network elements
• CPC Class Codes: H04L 41/12 Discovery or management of network topologies
• CPC Class Codes: H04L 41/5019 Ensuring fulfilment of SLA
• CPC Class Codes: H04L 67/1095 Replication or mirroring of data, e.g. scheduling or transport for data synchronisation between network nodes

Abstract

A method for enabling resiliency for cloud computing systems is described. The method includes modifying a topology graph of a network architecture by mapping processes flows onto the topology graph. A resiliency graph is created based on the modified topology graph. The method includes modifying the resiliency graph by translating at least one SLA into the resiliency graph. Overlaps and dependencies in the modified resiliency graph are identified. Apparatus and computer readable instructions are also described.

Claims

1. A method comprising:

modifying a topology graph of a network architecture by mapping processes flows onto the topology graph;

creating a resiliency graph based on the modified topology graph;

modifying the resiliency graph by translating at least one service level agreement into the resiliency graph;

identifying overlaps and dependencies in the modified resiliency graph; and

in response to determining that a potential point of failure is a plurality of critical subsystems shared by multiple processes, ensuring the plurality of critical subsystems does not share a hypervisor.

2. The method of claim 1, further comprising determining at least one potential point of failure based on the overlaps and dependencies.

3. The method of claim 2, further comprising classifying the at least one potential point of failure.

4. The method of claim 2, further comprising in response to determining that the at least one potential point of failure is a subsystem shared by multiple processes, splitting the subsystem into a plurality of instances of the subsystem.

5. The method of claim 2, further comprising in response to determining that the at least one potential point of failure is a plurality of non-critical subsystem shared by multiple processes, allowing the plurality of non-critical subsystem to share infrastructure resources.

6. The method of claim 2, further comprising in response to determining that the at least one potential point of failure is a replicated subsystem, determining a primary and backup split for the replicated subsystem.

7. The method of claim 1, further comprising calculating resiliency based on an infrastructure of the network architecture.

8. The method of claim 1, further comprising classifying processes based on resiliency requirements.

9. A apparatus, comprising a processor;

and a memory including computer program code, the memory and the computer program code configured to, with the processor, cause the apparatus to perform at least the following;

to modify a topology graph of a network architecture by mapping processes flows onto the topology graph;

to create a resiliency graph based on the modified topology graph;

to modify the resiliency graph by translating at least one service level agreement into the resiliency graph;

to identify overlaps and dependencies in the modified resiliency graph; and

in response to determining that a potential point of failure is a plurality of critical subsystems shared by multiple processes, ensuring the plurality of critical subsystems does not share a hypervisor.

10. The apparatus of claim 9, where the memory and the computer program code are further configured to cause the apparatus to determine at least one potential point of failure based on the overlaps and dependencies.

11. The apparatus of claim 10, where the memory and the computer program code are further configured to cause the apparatus to classify the at least one potential point of failure.

12. The apparatus of claim 10, where the memory and the computer program code are further configured to cause the apparatus to split the subsystem into a plurality of instances of the subsystem in response to determining that the at least one potential point of failure is a subsystem shared by multiple processes.

13. The apparatus of claim 10, where the memory and the computer program code are further configured to cause the apparatus to allow the plurality of non-critical subsystem to share infrastructure resources in response to determining that the at least one potential point of failure is a plurality of non-critical subsystem shared by multiple processes.

14. The apparatus of claim 10, where the memory and the computer program code are further configured to cause the apparatus to, determine a primary and backup split for the replicated subsystem in response to determining that the at least one potential point of failure is a replicated subsystem.

15. An article of manufacture comprising a non-transitory computer-readable medium tangibly embodying computer readable instructions which, when implemented, cause a computer to carry out the steps of a method comprising:

modifying a topology graph of a network architecture by mapping processes flows onto the topology graph;

creating a resiliency graph based on the modified topology graph;

modifying the resiliency graph by translating at least one service level agreement into the resiliency graph;

identifying overlaps and dependencies in the modified resiliency graph; and

in response to determining that a potential point of failure is a plurality of critical subsystems shared by multiple processes, ensuring the plurality of critical subsystems does not share a hypervisor.

16. The article of manufacture of claim 15, where the steps of the method further comprise, in response to determining that the at least one potential point of failure is a subsystem shared by multiple processes, splitting the subsystem into a plurality of instances of the subsystem.

17. The article of manufacture of claim 15, where the steps of the method further comprise, in response to determining that the potential point of failure is a plurality of non-critical subsystem shared by multiple processes, allowing the plurality of non-critical subsystem to share infrastructure resources.

18. The article of manufacture of claim 15, where the steps of the method further comprise, in response to determining that the potential point of failure is a replicated subsystem, determining a primary and backup split for the replicated subsystem.