METHODS AND APPARATUS FOR MANAGEMENT OF HETEROGENEOUS WORKLOADS

• US 20080270199A1
• Filed: 04/30/2007
• Published: 10/30/2008
• Est. Priority Date: 04/30/2007
• Status: Active Grant

• Current Assignee: International Business Machines Corporation
• Original Assignee: International Business Machines Corporation
• Inventors: Steinder, Malgorzata, Whalley, Ian Nicholas, Chess, David Michael
• Granted Patent: US 9,405,585 B2
• Time in Patent Office: Days
• US Class Current: 705/7
• CPC Class Codes: G06F 2209/5017 Task decomposition
• CPC Class Codes: G06F 9/455 Emulation; Interpretation; Software simulation, e.g. virtualisation or emulation of application or operating system execution engines
• CPC Class Codes: G06F 9/505 considering the load
• CPC Class Codes: G06F 9/5072 Grid computing
• CPC Class Codes: G06Q 10/06316 Sequencing of tasks or work

Abstract

Systems and methods for managing a system of heterogeneous workloads are provided. Work that enters the system is separated into a plurality of heterogeneous workloads. A plurality of high-level quality of service goals is gathered. At least one of the plurality of high-level quality of service goals corresponds to each of the plurality of heterogeneous workloads. A plurality of control functions are determined that are provided by virtualizations on one or more containers in which one or more of the plurality of heterogeneous workloads run. An expected utility of a plurality of settings of at least one of the plurality of control functions is determined in response to the plurality of high-level quality of service goals. At least one of the plurality of control functions is exercised in response to the expected utility to effect changes in the behavior of the system.

Claims

11. Apparatus for managing a system of heterogeneous workloads, comprising:

a memory; and

at least one processor coupled to the memory and operative to;

(i) separate work that enters the system into a plurality of heterogeneous workloads;

(ii) gather a plurality of high-level quality of service goals, wherein at least one of the plurality of high-level quality of service goals corresponds to each of the plurality of heterogeneous workloads;

(iii) determine a plurality of control functions that are provided by virtualizations on one or more containers in which one or more of the plurality of heterogeneous workloads run;

(iv) determine an expected utility of a plurality of settings of at least one of the plurality of control functions in response to the plurality of high-level quality of service goals; and

(v) exercise at least one of the plurality of control functions in response to the expected utility to effect changes in the behavior of the system.

12. A method for making a computer implemented process to enable management of a system of heterogeneous workloads comprising the steps of:

instantiating first computer instructions onto a computer readable medium, the first computer instructions configured to separate work that enters the system into a plurality of heterogeneous workloads;

instantiating second computer instructions onto a computer readable medium, the second computer instructions configured to gather a plurality of high-level quality of service goals, wherein at least one of the plurality of high-level quality of service goals corresponds to each of the plurality of heterogeneous workloads;

instantiating third computer instructions onto a computer readable medium, the third computer instructions configured to determine a plurality of control functions that are provided by virtualizations on one or more containers in which one or more of the plurality of heterogeneous workloads run;

instantiating fourth computer instructions onto a computer readable medium, the fourth computer instructions configured to determine an expected utility of a plurality of settings of at least one of the plurality of control functions in response to the plurality of high-level quality of service goals;

instantiating fifth computer instructions onto a computer readable medium, the fifth computer instructions configured to exercise at least one of the plurality of control functions in response to the expected utility to effect changes in the behavior of the system.

13. A system for management of heterogeneous workloads comprising:

a plurality of heterogeneous server machines;

a placement controller, driven by utility functions of allocated computer processing unit (CPU) demand, that places web applications on one or more of the plurality of heterogeneous server machines;

a request router that receives and dispatches requests to one or more web applications on one or more of the plurality of heterogeneous server machines in accordance with a scheduling mechanism;

a flow controller in communication with the request router and the placement controller that dynamically adjusts the scheduling mechanism in response to at least one of workload intensity and system configuration; and

a job scheduler that allocates jobs to one or more of the plurality of heterogeneous server machines in accordance with placement decisions communicated to the job scheduler by the placement controller.

1. A method for managing a system of heterogeneous workloads, comprising the steps of:

separating work that enters the system into a plurality of heterogeneous workloads;

gathering a plurality of high-level quality of service goals, wherein at least one of the plurality of high-level quality of service goals corresponds to each of the plurality of heterogeneous workloads;

determining a plurality of control functions that are provided by virtualizations on one or more containers in which one or more of the plurality of heterogeneous workloads run;

determining an expected utility of a plurality of settings of at least one of the plurality of control functions in response to the plurality of high-level quality of service goals; and

exercising at least one of the plurality of control functions in response to the expected utility to effect changes in the behavior of the system.

2. The method of claim 1, wherein the step of separating work comprises the steps of:

receiving web application requests at a request router; and

receiving jobs at a job scheduler.

3. The method of claim 2, wherein the step of determining a plurality of control functions comprises the steps of:

placing web applications on one or more of a plurality of heterogeneous server machines through a placement controller driven by utility functions of allocated CPU demand;

dispatching the web application requests from the request router to one or more web applications on one or more of the plurality of heterogeneous server machines in accordance with a scheduling mechanism; and

attributing jobs to one or more of the plurality of heterogeneous server machines in accordance with placement decisions communicated to a job scheduler by the placement controller.

4. The method of claim 3, wherein the step of placing web applications further comprises the step of calculating a web application placement that maximizes the minimum utility across all web applications.

5. The method of claim 3, wherein the step of dispatching the web application requests comprises the steps of:

classifying requests into flows at the request router depending on at least one of target web application and service class;

placing classified requests into per-flow queues within the request router;

dispatching requests from the per-flow queues based on a weighted-fair scheduling discipline that observes a concurrency limit of the system.

6. The method of claim 3, wherein the step of attributing jobs comprises the steps of:

managing dependencies among jobs at the job scheduler;

matching jobs with one or more of the plurality of heterogeneous server machines;

receiving jobs from the job scheduler at a job scheduler proxy of the placement controller;

estimating requirements for jobs for a given value of utility function at a job utility estimator of the placement controller;

calculating job placement that maximizes the minimum utility across all web applications at a placement optimizer of the placement controller;

communicating the job placements to the job scheduler through the job scheduler proxy; and

attributing jobs to one or more of the plurality of heterogeneous server machines in accordance with the communicated job placements.

7. The method of claim 3, wherein the step of determining one or more control functions further comprises the steps of:

managing virtual machines inside a given heterogeneous server machine by a machine agent in a first domain of the given heterogeneous server machine in communication with a node agent in a second domain of the given heterogeneous server machine; and

providing job management functionality within the heterogeneous server machine through interaction with the machine agent.

8. The method of claim 3, wherein the step of determining an expected utility comprises the steps of:

obtaining profiles for web application requests in the form of an average number of CPU cycles consumed by requests of a given flow;

obtaining profiles for jobs in the form of at least one of the number of CPU cycles required to complete the job, the number of threads used by the job, and the maximum CPU speed at which the job may progress;

communicating the profiles for web application requests to the placement controller and the flow controller, and the profiles for jobs to the job scheduler.

9. The method of claim 3, wherein the step of exercising at least one of the one or more control functions comprises the step of dynamically adjusting the scheduling mechanism in response to at least one of workload intensity and system configuration.

10. The method of claim 9, wherein the step of dynamically adjusting the scheduling mechanism comprises the steps of:

building a model of the system that allows the flow controller to predict the performance of a flow for any choice of concurrency limit and weights; and

adjusting at least one of weights of the weighted-fair scheduling discipline and the concurrency limit of the system in response to at least one of changing workload intensity and system configuration.

14. The system of claim 13, wherein the web applications placed on one or more of the plurality of heterogeneous server machines comprise application server clusters.

15. The system of claim 13, wherein the placement controller comprises:

a job scheduler proxy that receives jobs from the job scheduler and communicates job placement decisions to the job scheduler;

a job utility estimator that estimates requirements for jobs for a given value of utility function;

a placement optimizer that calculates job and web application placement that maximizes the minimum utility across all web applications; and

a web application executor that places web applications on one or more of the plurality of heterogeneous server machines.

16. The system of claim 13 wherein the request router classifies requests into flows depending on at least one of target web applications and service class.

17. The system of claim 16, wherein the request router places classified requests into per-flow queues within the request router.

18. The system of claim 17, wherein the request router dispatches requests from the per-flow queues based on a weighted-fair scheduling discipline that observes a concurrency limit of the system.

19. The system of claim 18, wherein the flow controller adjusts at least one of weights of the weighted-fair scheduling discipline and the concurrency limit of the system in response to at least one of changing workload intensity and system configuration.

20. The system of claim 19, wherein the flow controller builds a model of the system that allows it to predict the performance of a flow for any choice of concurrency limit and weights.

21. The system of claim 13, wherein the flow controller comprises a utility function calculator in communication with the placement controller.

22. The system of claim 13, wherein the job scheduler manages dependencies among jobs and performs resource matching of the jobs with one or more of the plurality of heterogeneous server machines.

23. The system of claim 13, further comprising:

a web application workload profiler that obtains profiles for web application requests in the form of an average number of CPU cycles consumed by requests of a given flow, and provides the profiles for web application requests to the flow controller and placement controller; and

a job workload profiler that obtains profiles for jobs in the form of at least one of the number of CPU cycles required to complete the job, the number of threads used by the job, and the maximum CPU speed at which the job may progress, and provides the profiles for jobs to the job scheduler.

24. The system of claim 13, wherein the each of the plurality of heterogeneous server machines comprise a plurality of domains.

24-1. The system of claim 13, wherein a first domain of the plurality of domains comprises a node agent in communication with the placement controller and the job scheduler.

26. The system of claim 25, wherein a second domain of the plurality of domains comprises a machine agent in communication with the node agent that manages virtual machines inside a given heterogeneous server machine.

27. The system of claim 26, wherein the node agent provides job management functionality within the heterogeneous server machine through interaction with the machine agent.

28. The system of claim 26, wherein the machine agent is capable of at least one of creating and configures a virtual machine image for a new domain, copying files from the second domain to another domain, starting a process in another domain, and controlling the mapping of physical resources to virtual resources.