Dynamic dispatching of workloads spanning heterogeneous services

• US 10,261,836 B2
• Filed: 03/21/2017
• Issued: 04/16/2019
• Est. Priority Date: 03/21/2017
• Status: Active Grant

• Current Assignee: Oracle International Corporation (Oracle Corporation)
• Original Assignee: Oracle International Corporation (Oracle Corporation)
• Inventors: Bansal, Ajeet, Srivastava, Rohit
• Primary Examiner(s): Kim, Dong U
• Application Number:
  US15/464,902
• Publication Number:
  US 20180276041A1
• Time in Patent Office: 756 Days
• CPC Class Codes: G06F 11/30 Monitoring
• CPC Class Codes: G06F 11/3006 where the computing system is distributed, e.g. networked systems, clusters, multiprocessor systems multiprogramming arrangements G06F9/46; allocation of resources G06F9/50
• CPC Class Codes: G06F 11/3414 Workload generation, e.g. scripts, playback
• CPC Class Codes: G06F 11/3433 for load management allocation of a server based on load conditions G06F9/505; load rebalancing G06F9/5083; redistributing the load in a network by a load balancer H04L67/1029
• CPC Class Codes: G06F 9/5083 Techniques for rebalancing the load in a distributed system
• CPC Class Codes: H04L 12/14 Charging , metering or billing arrangements for data wireline or wireless communications
• CPC Class Codes: H04L 41/5003 Managing SLA; Interaction between SLA and QoS
• CPC Class Codes: H04L 43/0876 Network utilisation, e.g. volume of load or congestion level
• CPC Class Codes: H04L 67/10 in which an application is distributed across nodes in the network software deployment G06F8/60; multiprogramming arrangements G06F9/46
• CPC Class Codes: H04M 15/09 Third party charged communications
• CPC Class Codes: H04W 4/24 Accounting or billing

Abstract

A system for executing a workload that includes a plurality of transactions for a first time slot determines whether a metered cloud service has a sufficient quota of operations available to execute respective metered transactions. For the first time slot, the system determines whether a non-metered cloud service has a sufficient processing load to execute respective non-metered transactions. The system executes the plurality of transactions during the first time slot when each metered cloud service has the sufficient quota and each non-metered cloud service has the sufficient processing load. Further, the system waits to execute the plurality of transactions of the workload during a time slot subsequent to the first time slot when any of the metered cloud services does not have the sufficient quota or any of the non-metered cloud services does not have a sufficient processing load.

Claims

1. A method of executing a workload that includes a plurality of transactions, the method comprising:

determining a plurality of cloud services needed to execute each of the plurality of transactions, wherein at least one of the determined cloud services is a metered cloud service that executes metered transactions and limits a number of operations that can be performed within a given time interval, and at least one of the determined cloud services is a non-metered cloud service that executes non-metered transactions and does not limit the number of operations that can be performed within the given time interval;

for a first time slot, determining whether each metered cloud service has a sufficient quota of operations available to execute respective metered transactions;

for the first time slot, determining whether each non-metered cloud service has a sufficient processing load to execute respective non-metered transactions;

executing the plurality of transactions of the workload during the first time slot when each metered cloud service has the sufficient quota and each non-metered cloud service has the sufficient processing load, wherein executing the plurality of transactions of the workload uses both metered cloud services and non-metered cloud services; and

waiting to execute the plurality of transactions of the workload during a time slot subsequent to the first time slot when any of the metered cloud services does not have the sufficient quota or any of the non-metered cloud services does not have a sufficient processing load.

2. The method of claim 1, wherein the determining whether each metered cloud service has the sufficient quota of operations available to execute respective metered transactions comprises invoking each metered cloud service using a Representational State Transfer (REST) application program interface (API).

3. The method of claim 2, further comprising receiving metadata in response to the invoking, the metadata comprising a maximum number of transactions allowed to be performed during the first time slot.

4. The method of claim 3, wherein at least one metered cloud service comprises a microservice.

5. The method of claim 1, wherein the determining whether each non-metered cloud service has the sufficient processing load to execute respective non-metered transactions comprises invoking each non-metered cloud service using a Representational State Transfer (REST) application program interface (API).

6. The method of claim 5, further comprising receiving metadata in response to the invoking, the metadata comprising an average processor load over a time duration or a memory utilization level.

7. The method of claim 6, wherein the memory utilization level comprises a Java heap usage.

8. A non-transitory computer readable medium having instructions stored thereon that, when executed by a processor, executes a workload that includes a plurality of transactions, the executes workload comprising:

determining a plurality of cloud services needed to execute each of the plurality of transactions, wherein at least one of the determined cloud services is a metered cloud service that executes metered transactions and limits a number of operations that can be performed within a given time interval, and at least one of the determined cloud services is a non-metered cloud service that executes non-metered transactions and does not limit the number of operations that can be performed within the given time interval;

for a first time slot, determining whether each metered cloud service has a sufficient quota of operations available to execute respective metered transactions;

for the first time slot, determining whether each non-metered cloud service has a sufficient processing load to execute respective non-metered transactions;

executing the plurality of transactions of the workload during the first time slot when each metered cloud service has the sufficient quota and each non-metered cloud service has the sufficient processing load, wherein executing the plurality of transactions of the workload uses both metered cloud services and non-metered cloud services; and

waiting to execute the plurality of transactions of the workload during a time slot subsequent to the first time slot when any of the metered cloud services does not have the sufficient quota or any of the non-metered cloud services does not have a sufficient processing load.

9. The computer readable medium of claim 8, wherein the determining whether each metered cloud service has the sufficient quota of operations available to execute respective metered transactions comprises invoking each metered cloud service using a Representational State Transfer (REST) application program interface (API).

10. The computer readable medium of claim 9, the executes workload further comprising receiving metadata in response to the invoking, the metadata comprising a maximum number of transactions allowed to be performed during the first time slot.

11. The computer readable medium of claim 10, wherein at least one metered cloud service comprises a microservice.

12. The computer readable medium of claim 8, wherein the determining whether each non-metered cloud service has the sufficient processing load to execute respective non-metered transactions comprises invoking each non-metered cloud service using a Representational State Transfer (REST) application program interface (API).

13. The computer readable medium of claim 12, the executes workload further comprising receiving metadata in response to the invoking, the metadata comprising an average processor load over a time duration or a memory utilization level.

14. The computer readable medium of claim 13, wherein the memory utilization level comprises a Java heap usage.

15. A cloud based dynamic dispatcher for a workload that includes a plurality of transactions, the dispatcher comprising:

a processor executing instructions stored in a memory, the processor;

determining a plurality of cloud services needed to execute each of the plurality of transactions, wherein at least one of the determined cloud services is a metered cloud service that executes metered transactions and limits a number of operations that can be performed within a given time interval, and at least one of the determined cloud services is a non-metered cloud service that executes non-metered transactions and does not limit the number of operations that can be performed within the given time interval;

for a first time slot, determining whether each metered cloud service has a sufficient quota of operations available to execute respective metered transactions;

for the first time slot, determining whether each non-metered cloud service has a sufficient processing load to execute respective non-metered transactions;

executing the plurality of transactions of the workload during the first time slot when each metered cloud service has the sufficient quota and each non-metered cloud service has the sufficient processing load, wherein executing the plurality of transactions of the workload uses both metered cloud services and non-metered cloud services; and

waiting to execute the plurality of transactions of the workload during a time slot subsequent to the first time slot when any of the metered cloud services does not have the sufficient quota or any of the non-metered cloud services does not have a sufficient processing load.

16. The dynamic dispatcher of claim 15, wherein the determining whether each metered cloud service has the sufficient quota of operations available to execute respective metered transactions comprises invoking each metered cloud service using a Representational State Transfer (REST) application program interface (API).

17. The dynamic dispatcher of claim 16, further comprising receiving metadata in response to the invoking, the metadata comprising a maximum number of transactions allowed to be performed during the first time slot.

18. The dynamic dispatcher of claim 17, wherein at least one metered cloud service comprises a microservice.

19. The dynamic dispatcher of claim 15, wherein the determining whether each non-metered cloud service has the sufficient processing load to execute respective non-metered transactions comprises invoking each non-metered cloud service using a Representational State Transfer (REST) application program interface (API).

20. The dynamic dispatcher of claim 19, further comprising receiving metadata in response to the invoking, the metadata comprising an average processor load over a time duration or a memory utilization level.