Method for allocating shared computing infrastructure for application server-based deployments

• US 20060277307A1
• Filed: 07/14/2006
• Published: 12/07/2006
• Est. Priority Date: 06/07/2005
• Status: Active Grant

• Current Assignee: Cloud Software Group
• Original Assignee: DataSynapse, Inc. (Cloud Software Group)
• Inventors: Iskold, Alexander, Bernardin, James
• Granted Patent: US 7,584,281 B2
• Time in Patent Office: Days
• US Class Current: 709/226
• CPC Class Codes: H04L 67/02 based on web technology, e.g. hypertext transfer protocol [HTTP]
• CPC Class Codes: H04L 67/56 Provisioning of proxy services store-and-forward switching systems in data switching networks H04L12/54
• CPC Class Codes: H04L 67/562 Brokering proxy services

Abstract

A shared computing infrastructure includes a plurality of computing engines, applications servers, and computing domains. A broker component executes a method for dynamically allocating the computing engines among the computing domains. The allocation method begins with the step of determining an expected number of computing engines to be allocated to each of the computing domains as a function of a predetermined service policy and a predicted demand for the domain While fewer than the expected number of computing engines has been allocated to each domain, the computing domains are sequentially selecting as a function of predetermined domain priorities. Unallocated computing engines are identified, and the unallocated computing engines are allocated to each selected computing domain according to predetermined selection rules for the domain. During an allocation improvement step, allocations among the computing domains are further adjusted to maximize a fitness statistic computed for the allocations.

Claims

1. In a system for provisioning a shared computing infrastructure including a plurality of computing engines, a plurality of applications servers, a plurality of computing domains and a broker, the shared computing infrastructure supporting a plurality of software applications and the plurality of applications servers including a plurality of applications server types, each application server type capable of providing a run-time environment for executing at least one of the plurality of software applications;

each computing domain being hosted by an application server of a given type, and the broker being operative to dynamically allocate the plurality of computing engines among the plurality of computing domains based on allocation policies provided to the broker, a method for specifying the allocation policy for one of the plurality of domains via an administrative interface to the broker, the method comprising the steps of;

specifying a desired minimum number of computing engines to be allocated to the one domain in any broker allocation;

specifying a desired maximum number of computing engines to be allocated to the one domain in any broker allocation; and

specifying a priority of allocation for the one domain.

2. The method of claim 1, further comprising the step of:

specifying a service level agreement (SLA) target, wherein performance of the one domain against the SLA target may be judged by the broker in determining whether to allocate one or more additional computing engines to the one domain.

3. The method of claim 1, further comprising the step of:

specifying one or more of the plurality of computing engines which may be allocated to the one domain.

4. The method of claim 3, wherein the one or more computing engines are each specified by an engine identification number or engine configuration information, the engine configuration information including one or more of a free memory size, the number of central processing units (CPUs) or the engine operating system.

5. The method of claim 1, further comprising the step of:

specifying a daily time interval for the broker to apply the policy to the allocation of computing engines to the one domain.

6. In a system for provisioning a shared computing infrastructure including a plurality of computing engines, a plurality of applications servers, a plurality of computing domains and a broker, the shared computing infrastructure supporting a plurality of software applications and the plurality of applications servers including a plurality of applications server types, each application server type capable of providing a run-time environment for executing at least one of the plurality of software applications;

each computing domain being hosted by an application server of a given type, a method performed by the broker for allocating the plurality of computing engines among the plurality of computing domains based on an allocation policy, the method comprising the steps of;

determining an expected number of computing engines to be allocated to each of the plurality of computing domains, wherein the expected number for each computing domain is determined as a function of a predetermined service policy of the computing domain and a predicted demand for the computing domain; and

while one or more of the computing engines is unallocated and one or more of the plurality of computing domains has been allocated fewer than its expected number of computing resources, sequentially selecting a next computing domain as a function of predetermined priorities for the computing domains, selecting an unallocated computing engine, and allocating the selected computing engine to the selected computing domain.

7. The method of claim 6, further comprising the steps of:

calculating a fitness value representative of the current allocation of computing engines to computing domains;

identifying a first computing domain for which fewer than the expected number of computing engines has been allocated;

selecting one of an unallocated computing engine or a computing engine allocated to a second computing domain for which the expected number of computing engines has been allocated;

re-allocating the selected computing engine to the first computing domain;

re-calculating a fitness value representative of allocation of computing engines to computing domains after re-allocation; and

discarding the re-allocation of the selected computing engine to the first computing domain if the fitness value for the current allocation exceeds the fitness value for the re-allocation.

8. The method according to claim 7, wherein the selecting, re-allocating, re-calculating and discarding steps are repeated for a predetermined number of iterations.

9. The method of claim 7, wherein the selection of an unallocated computing engine or a computing engine allocated to a second computing domain is made randomly.

10. The method of claim 7, wherein the selection of an unallocated computing engine or a computing engine allocated to a second computing domain is made by application of a constraint programming search algorithm.

11. The method of claim 6, wherein the predetermined service policy for each computing domain specifies a minimum number of computing engines to be allocated to the computing domain, a maximum number of computing engines to be allocated to the computing domain, and an allocation priority for allocating computing engines to the computing domain.

12. The method of claim 11, wherein the predetermined service policy further specifies a service level agreement (SLA) target for judging the performance of the computing domain.

13. The method of claim 12, wherein the step of determining an expected number of computing engines for each domain further includes the steps of:

setting the expected number of computing engines equal to the minimum number of computing engines for the computing domain;

initially adjusting the expected number of computing engines to equal to a current number of computing engines allocated to the computing domain when the current number of allocated computing engines exceeds the minimum number of computing engines;

determining whether the computing domain has a current unmet demand;

further adjusting the expected number of computing engines when there is a current unmet demand; and

finally adjusting the expected number of computing engines to equal a lesser of the maximum number of computing engines to be allocated to the computing domain and the further adjusted expected number of computing engines.

14. The method of claim 13, wherein the current unmet demand is determined as a function of a statistical performance measure for the domain and an associated service level agreement (SLA).

15. The method of claim 14, wherein the current unmet demand is validated as a function of a variability of the statistical performance measure among computing engines in the domain.

16. The method of claim 15, wherein the variability is determined as a normalized geometric variance computed as a geometric mean value of the statistical performance measure among computing engines in the domain divided by an arithmetic mean of the statistical performance measure among computing engines in the domain.

17. The method of claim 16, wherein the current unmet demand is validated when the statistical performance measure falls below a first threshold based on the SLA, and the normalized geometric variance exceeds a second threshold.

18. The method of claim 17, wherein the second threshold is 0.85.

19. The method of claim 11, wherein the predetermined priorities provide an ordinal ranking of computing domains, and the sequence of selected computing domains progresses from one or more computing domains having a highest priority ranking among the computing domains to one or more computing domains having a lowest priority ranking among the computing domains.

20. The method of claim 19, wherein the computing domain selection sequence comprises one or more selection rounds, and wherein each selection round is associated with a priority ranking value, such that each of the plurality of computing domains having a priority ranking that is greater than or equal to the rank value is selected during the selection round.

21. The method of claim 20, wherein the step of selecting an unallocated computing engine for a selected computing domain in a current selection round is made according to a selection rule selected from the group consisting of:

selecting a computing engine currently assigned to the selected computing domain;

selecting a computing engine previously assigned to the selected computing domain;

selecting a computing engine among unallocated computing engines that is not identified as being needed by another one of the plurality of computing domains; and

selecting a computing engine among unallocated computing engines.