Resource overbooking and application profiling in shared hosting platforms

Urgaonkar, Bhuvan; Shenoy, Prashant; Roscoe, Timothy

doi:10.1145/1060289.1060312

Cited by 158 publications

(153 citation statements)

References 9 publications

Supporting

Mentioning

146

Contrasting

Unclassified

Order By: Relevance

“…Many research groups have used a similar approach to characterize application behaviour and applied trace-based methods to support what-if analysis in the assignment of workloads to consolidated servers [23,7,8,24,25,1,3]. A consolidation analysis presented in [23] packs existing server workloads onto a smaller number of servers using an Integer Linear Programming based bin-packing method.…”

Section: Related Workmentioning

confidence: 99%

“…The approach is able to minimize migrations over successive control intervals. Some researchers propose to limit the capacity requirement of an application workload to a percentile of its demand [24]. This does not take into account the impact of sustained performance degradation over time on user experience as our required capacity definition does.…”

Section: Related Workmentioning

confidence: 99%

See 1 more Smart Citation

Resource pool management: Reactive versus proactive or let’s be friends

et al. 2009

View full text Add to dashboard Cite

The consolidation of multiple workloads and servers enables the efficient use of server and power resources in shared resource pools. We employ a trace-based workload placement controller that uses historical information to periodically and proactively reassign workloads to servers subject to their quality of service objectives. A reactive migration controller is introduced that detects server overload and underload conditions. It initiates the migration of workloads when the demand for resources exceeds supply. Furthermore, it dynamically adds and removes servers to maintain a balance of supply and demand for capacity while minimizing power usage. A host-load simulation environment is used to evaluate several different management policies for the controllers in a time effective manner. A case study involving three months of data for 138 SAP applications compares three integrated controller approaches with the use of each controller separately. The study considers trade-offs between i) required capacity and power usage, ii) resource access quality of service for CPU and memory resources, and iii) the number of migrations. Our study sheds light on the question of whether a reactive controller or proactive workload placement controller alone is adequate for resource pool management. The results show that the most tightly integrated controller approach offers the best results in terms of capacity and quality but requires more migrations per hour than the other strategies.

show abstract

Section: Related Workmentioning

confidence: 99%

Section: Related Workmentioning

confidence: 99%

Resource pool management: Reactive versus proactive or let’s be friends

et al. 2009

View full text Add to dashboard Cite

show abstract

“…Urgaonkar et al, propose techniques to overbook cluster resources in a controlled way, guaranteeing applications performance even despite overbooking [12]. Nevertheless, they assume that users provide information regarding the degree of overbooking that their applications may tolerate as well as their time periods, which may be known by the users in a cluster environments but is not available for cloud infrastructures.…”

Section: Related Workmentioning

confidence: 99%

“…As highlighted in [12], taking overbooking actions by only considering average resource requirements or only one dimension can result in significantly reduced performance. This is one of the main reasons why different logics for risk assessment were implemented [13].…”

mentioning

confidence: 99%

Cloudy with a Chance of Load Spikes: Admission Control with Fuzzy Risk Assessments

Tomás

Tordsson

2013

2013 IEEE/ACM 6th International Conference on Utility and Cloud Computing

View full text Add to dashboard Cite

Abstract-Elasticity is key for the cloud paradigm, where the pay-per use nature provides great flexibility for end-users. However, elasticity complicates long-term capacity planning for cloud providers as the exact amount of resources required over time becomes uncertain. Admission control techniques are thus needed to handle the trade-off between resource utilization and potential overload. We define a set of admission control algorithms that combine risk assessment methods with a fuzzy aggregation framework. An experimental evaluation using a mixture of bursty and steady applications demonstrate that our algorithms can increase resource utilization by a factor of two while limiting overload problems to a few percent.

show abstract

“…This approach is not application-centricit focuses on global throughput-and considers only transactional applications. The algorithm proposed in [20] allows applications to share physical machines, but does not change the number of instances of an application, does not minimize placement changes, and considers a single bottleneck resource.…”

Section: Related Workmentioning

confidence: 99%

Enabling Resource Sharing between Transactional and Batch Workloads Using Dynamic Application Placement

Carrera

Steinder²,

Whalley³

et al. 2008

Middleware 2008

View full text Add to dashboard Cite

Abstract. We present a technique that enables existing middleware to fairly manage mixed workloads: batch jobs and transactional applications. The technique leverages a generic application placement controller, which dynamically allocates compute resources to application instances. The controller works towards a fairness goal while also trying to maximize individual workload performance. We use relative performance functions to drive the application placement controller. Such functions are derived from workload-specific performance models-in the case of transactional workloads, we use queuing theory to build the performance model. For batch workloads, we evaluate a candidate placement by calculating long-term estimates of the completion times that are achievable with that placement according to a scheduling policy. In this paper, we propose a lowest relative performance first scheduling policy as a way to also achieve fair resource allocation among batch jobs. Our technique permits collocation of the workload types on the same physical hardware, and leverages control mechanisms such as suspension and migration to perform online system reconfiguration. In our experiments we demonstrate that our technique maximizes mixed workload performance while providing service differentiation based on highlevel performance goals.

show abstract

Resource overbooking and application profiling in shared hosting platforms

Abstract: In this paper, we present techniques for provisioning CPU and network

Cited by 158 publications

References 9 publications

Resource pool management: Reactive versus proactive or let’s be friends

Resource pool management: Reactive versus proactive or let’s be friends

Cloudy with a Chance of Load Spikes: Admission Control with Fuzzy Risk Assessments

Enabling Resource Sharing between Transactional and Batch Workloads Using Dynamic Application Placement

Contact Info

Product

Resources

About