Proactive identification of hotspots in a cloud computing environment
원문보기
IPC분류정보
국가/구분
United States(US) Patent
등록
국제특허분류(IPC7판)
G06F-015/173
G06F-009/50
출원번호
US-0893302
(2010-09-29)
등록번호
US-9329908
(2016-05-03)
발명자
/ 주소
Gopisetty, Sandeep
Murthy, Seshashayee S.
Singh, Aameek
Uttamchandani, Sandeep M.
Weck, David D.
출원인 / 주소
International Business Machines Corporation
대리인 / 주소
Sharkan, Noah A.
인용정보
피인용 횟수 :
1인용 특허 :
10
초록▼
The present invention proactively identifies hotspots in a cloud computing environment through cloud resource usage models that use workload parameters as inputs. In some embodiments the cloud resource usage models are based upon performance data from cloud resources and time series based workload t
The present invention proactively identifies hotspots in a cloud computing environment through cloud resource usage models that use workload parameters as inputs. In some embodiments the cloud resource usage models are based upon performance data from cloud resources and time series based workload trend models. Hotspots may occur and can be detected at any layer of the cloud computing environment, including the server, storage, and network level. In a typical embodiment, parameters for a workload are identified in the cloud computing environment and inputted into a cloud resource usage model. The model is run with the inputted workload parameters to identify potential hotspots, and resources are then provisioned for the workload so as to avoid these hotspots.
대표청구항▼
1. A method for proactively identifying hotspots in a particular cloud computing environment, comprising: identifying parameters associated with a workload, of a plurality of workloads, running in the particular cloud computing environment, the cloud computing environment comprising a plurality of r
1. A method for proactively identifying hotspots in a particular cloud computing environment, comprising: identifying parameters associated with a workload, of a plurality of workloads, running in the particular cloud computing environment, the cloud computing environment comprising a plurality of resources;obtaining resource configuration, performance measures, and workload usage statistics information for the cloud computing environment;correlating server, storage, and network data to identify resources, of the plurality of resources, involved for each workload of the plurality of workloads;creating a regression based model based on the correlation of the server, storage, and network data;predicting an amount of load that the plurality of workloads will generate in the future through a time-series based workload trend model;forming a cloud resource usage model based on the workload trend model and the regression based model;providing the parameters to the cloud resource usage model;detecting, in response to a timed wake-up trigger, at least one potential hotspot in the particular cloud computing environment using the cloud resource usage model, the hotspot comprising one or more resources of the particular cloud computing environment, which become constrained such that at least one of application performance and throughput is limited; andprovisioning at least one resource of the particular cloud computing environment for the workload in response to the detecting so as to minimize triggering the at least one potential hotspot;wherein the one or more resources comprises at least one of a compute node, a storage node, or a networking resource. 2. The method of claim 1, wherein the detecting occurs at one or more of: a server, a storage, and a network level, of the cloud computing environment. 3. The method of claim 1, wherein the workload parameters comprise at least one of the following: I/O rate, random/sequential ratios, read/write ratios, and cache hit percentage. 4. The method of claim 1, wherein the cloud resource usage model comprises performance data collected from a plurality of cloud resources, the plurality of cloud resources correlated with a plurality of potential workloads. 5. A system for proactively identifying hotspots in a particular cloud computing environment, comprising: a bus;a processor coupled to the bus; anda memory medium coupled to the bus, the memory medium comprising instructions to: identify parameters associated with a workload, of a plurality of workloads, running in the particular cloud computing environment, the cloud computing environment comprising a plurality of resources;obtain resource configuration, performance measures, and workload usage statistics information for the cloud computing environment;correlate server, storage, and network data to identify resources, of the plurality of resources, involved for each workload of the plurality of workloads;create a regression based model based on the correlation of the server, storage, and network data;predict an amount of load that the plurality of workloads will generate in the future through a time-series based workload trend model;form a cloud resource usage model based on the workload trend model and the regression based model;provide the parameters to the cloud resource usage model;detect, in response to a timed wake-up trigger, at least one potential hotspot in the particular cloud computing environment using the cloud resource usage model, the hotspot comprising one or more resources of the particular cloud computing environment, which become constrained such that at least one of application performance and throughput is limited; andprovision at least one resource of the particular cloud computing environment for the workload in response to the detecting so as to minimize triggering the at least one potential hotspot;wherein the one or more resources comprises at least one of a compute node, a storage node, or a networking resource. 6. The system of claim 5, wherein the workload parameters comprise at least one of the following: I/O rate, random/sequential ratios, read/write ratios, and cache hit percentage. 7. The system of claim 5, wherein the cloud resource usage model comprises performance data collected from a plurality of cloud resources, the plurality of cloud resources correlated with a plurality of potential workloads. 8. The system of claim 5, wherein the detection occurs at one or more of: a server, a storage, and a network level, of the cloud computing environment. 9. A computer program product for proactively identifying hotspots in a particular cloud computing environment, the computer program product comprising a non-transitory computer readable storage medium and program instructions stored on the non-transitory computer readable storage medium, to: identify parameters associated with a workload, of a plurality of workloads, running in the particular cloud computing environment, the cloud computing environment comprising a plurality of resources;obtain resource configuration, performance measures, and workload usage statistics information for the cloud computing environment;correlate server, storage, and network data to identify resources, of the plurality of resources, involved for each workload of the plurality of workloads;create a regression based model based on the correlation of the server, storage, and network data;predict an amount of load that the plurality of workloads will generate in the future through a time-series based workload trend model;form a cloud resource usage model based on the workload trend model and the regression based model;provide the parameters to the cloud resource usage model;detect, in response to a timed wake-up trigger, at least one potential hotspot in the particular cloud computing environment using the cloud resource usage model, the hotspot comprising one or more resources of the particular cloud computing environment, which become constrained such that at least one of application performance and throughput is limited; andprovision at least one resource of the particular cloud computing environment for the workload in response to the detecting so as to minimize triggering the at least one potential hotspot;wherein the one or more resources comprises at least one of a compute node, a storage node, or a networking resource. 10. The computer program product of claim 9, wherein the workload parameters at least one of the following: I/O rate, random/sequential ratios, read/write ratios, and cache hit percentage. 11. The computer program product of claim 9, wherein the cloud resource usage model comprises performance data collected from a plurality of cloud resources, the plurality of cloud resources correlated with a plurality of potential workloads. 12. The computer program product of claim 9, wherein the detection occurs at one or more of: a server, a storage, and a network level of the cloud computing environment. 13. A method for proactively identifying hotspots in a particular cloud computing environment, comprising: providing a computer infrastructure being operable to: identify parameters associated with a workload, of a plurality of workloads, running in the particular cloud computing environment, the cloud computing environment comprising a plurality of resources;obtain resource configuration, performance measures, and workload usage statistics information for the cloud computing environment;correlate server, storage, and network data to identify resources, of the plurality of resources, involved for each workload of the plurality of workloads;create a regression based model based on the correlation of the server, storage, and network data;predict an amount of load that the plurality of workloads will generate in the future through a time-series based workload trend model;form a cloud resource usage model based on the workload trend model and the regression based model;provide the parameters to the cloud resource usage model;detect, in response to a timed wake-up trigger, at least one potential hotspot in the particular cloud computing environment using the cloud resource usage model, the hotspot comprising one or more resources of the particular cloud computing environment, which become constrained such that at least one of application performance and throughput is limited; andprovision at least one resource of the particular cloud computing environment for the workload in response to the detecting so as to minimize triggering the at least one potential hotspot;wherein the one or more resources comprises at least one of a compute node, a storage node, or a networking resource. 14. The method of claim 13, wherein the workload parameters at least one of the following: I/O rate, random/sequential ratios, read/write ratios, and cache hit percentage. 15. The method of claim 13, wherein the cloud resource usage model further comprises: performance data collected from a plurality of cloud resources, the plurality of cloud resources correlated with a plurality of potential workloads. 16. The method of claim 13, wherein the detection occurs at one or more of: a server, a storage, and a network level of the cloud computing environment.
연구과제 타임라인
LOADING...
LOADING...
LOADING...
LOADING...
LOADING...
이 특허에 인용된 특허 (10)
Devarakonda, Murthy V.; Naik, Vijay K., Analyzing anticipated value and effort in using cloud computing to process a specified workload.
Blake Russell P. ; Hovel David O. ; Davidson Robert I. ; Heckerman David E. ; Breese John S., Automatic bottleneck detection by means of workload reconstruction from performance measurements.
Xiao, Lin; Liu, Jie; Nath, Suman Kumar; Rigas, Leonidas; Zhao, Feng; Chen, Gong; He, Wenbo, Framework for joint analysis and design of server provisioning and load dispatching for connection-intensive server.
Uysal,Mustafa; Becker Szendy,Ralph; Merchant,Arif; Alvarez,Guillermo, Method and apparatus for morphological modeling of complex systems to predict performance.
Rolia, Jerome; Gaisbauer, Sebastian; Schneider, Sebastian Phillipp; Edwards, Nigel; Kirschnick, Johannes, Sizing an infrastructure configuration optimized for a workload mix using a predictive model.
Randal Lee Bertram ; Frederick Scott Hunter Krauss ; Gregory J. McKnight, System and method for predicting computer system performance and for making recommendations for improving its performance.
Duyanovich, Linda M.; Gomez, Juan C.; Pollack, Kristal T.; Uttamchandani, Sandeep M., Technique for mapping goal violations to anamolies within a system.
Gopisetty, Sandeep; Murthy, Seshashayee S.; Singh, Aameek; Uttamchandani, Sandeep M.; Weck, David D., Proactive identification of hotspots in a cloud computing environment.
※ AI-Helper는 부적절한 답변을 할 수 있습니다.