Automated control for elastic n-tier workloads based on empirical modeling

Malkowski, Simon; Hedwig, Markus; Li, Jack; Pu, Calton; Neumann, Dirk

doi:10.1145/1998582.1998604

Cited by 38 publications

(29 citation statements)

References 19 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Malkowski et al proposed a multi-model controller for dynamically provisioning Virtual Machines (VMs) to multi-tier applications in clouds [33]. A knowledge base is used to store all VM configurations encountered during previous deployments of the applications and the measured performance, e.g., request throughput, of such configurations.…”

Section: Control-theoretic Techniquesmentioning

confidence: 99%

Burstiness-aware service level planning for enterprise application clouds

Youssef

Krishnamurthy

2017

J Cloud Comp

View full text Add to dashboard Cite

Enterprise applications are being increasingly deployed on cloud infrastructures. Often, a cloud service provider (SP) enters into a Service Level Agreement (SLA) with a cloud subscriber, which specifies performance requirements for the subscriber's applications. An SP needs systematic Service Level Planning (SLP) tools that can help estimate the resources needed and hence the cost incurred to satisfy their customers' SLAs. Enterprise applications typically experience bursty workloads and the impact of such bursts needs to be considered during SLP exercises. Unfortunately, most existing approaches do not consider workload burstiness. We propose a Resource Allocation Planning (RAP) technique, which allows an SP to identify a time varying allocation plan of resources to applications that satisfies bursts. Extensive simulation results show that the proposed RAP variants can identify resource allocation plans that satisfy SLAs without exhaustively generating all possible plans. Furthermore, the results show that RAP can permit SPs to more accurately determine the capacity required for meeting specified SLAs compared to other competing techniques especially for bursty workloads.

show abstract

Section: Control-theoretic Techniquesmentioning

confidence: 99%

Burstiness-aware service level planning for enterprise application clouds

Youssef

Krishnamurthy

2017

J Cloud Comp

View full text Add to dashboard Cite

show abstract

“…Many of the proposals scale the infrastructure horizontally by adding new VMs, typically via predefined VM classes [22][23][24][25][26][27][28][29][30][31][32]. While this is simpler to apply, compared to fine grain CPU and memory configuration, it may lead to wastage by over-allocating resources to workloads as well consume more power.…”

Section: Vm Adaptation -Cpu and Memorymentioning

confidence: 99%

“…A common adaptation technique is Control theory [23,25,26,35,41,44,49,50], which aims to guarantee system stability by adapting resource configurations at defined intervals. Some of the control theory proposals react to monitored metrics such as CPU utilisation thresholds and workload throughput [50], but most of the proposals surveyed use a proactive mechanism to forecast the future workloads, typically using time series.…”

Section: Adaptation Techniquementioning

confidence: 99%

“…Proposals typically build utility frameworks by constructing a performance model of multitier applications embedded in an optimisation problem [19,22,25,36,42], where a utility function expresses satisfaction of each workload towards assigned resources. Utility has also been combined with control theory in [41,44] to apply a fine grain configuration of CPU and memory, by estimating the benefits of potential adaptations and incorporating a notion of risk.…”

Section: Adaptation Techniquementioning

confidence: 99%

See 1 more Smart Citation

Adaptation in cloud resource configuration: a survey

2016

View full text Add to dashboard Cite

With increased demand for computing resources at a lower cost by end-users, cloud infrastructure providers need to find ways to protect their revenue. To achieve this, infrastructure providers aim to increase revenue and lower operational costs. A promising approach to addressing these challenges is to modify the assignment of resources to workloads. This can be used, for example, to consolidate existing workloads; the new capability can be used to serve new requests or alternatively unused resources may be turned off to reduce power consumption. The goal of this paper is to highlight features, approaches and findings in the literature, in order to identify open challenges and facilitate future developments. We present a definition of cloud systems adaptation, a classification of the key features and a survey of adapting compute and storage configuration. Based on our analysis, we identify three open research challenges: characterising the workload type, accurate online profiling of workloads, and building highly scalable adaptation mechanisms.

show abstract

“…There are many approaches to solve the elasticity problem [5,7,10,17,18,20,24,27,28], each with its own strengths and weaknesses. Desired properties of an elasticity controller include the following:…”

Section: Introductionmentioning

confidence: 99%

Efficient provisioning of bursty scientific workloads on the cloud using adaptive elasticity control

Ali-Eldin

Kihl

Tordsson

et al. 2012

Proceedings of the 3rd Workshop on Scientific Cloud Computing

View full text Add to dashboard Cite

Elasticity is the ability of a cloud infrastructure to dynamically change the amount of resources allocated to a running service as load changes. We build an autonomous elasticity controller that changes the number of virtual machines allocated to a service based on both monitored load changes and predictions of future load. The cloud infrastructure is modeled as a G/G/N queue. This model is used to construct a hybrid reactive-adaptive controller that quickly reacts to sudden load changes, prevents premature release of resources, takes into account the heterogeneity of the workload, and avoids oscillations. Using simulations with Web and cluster workload traces, we show that our proposed controller lowers the number of delayed requests by a factor of 70 for the Web traces and 3 for the cluster traces when compared to a reactive controller. Our controller also decreases the average number of queued requests by a factor of 3 for both traces, and reduces oscillations by a factor of 7 for the Web traces and 3 for the cluster traces. This comes at the expense of between 20% and 30% over-provisioning, as compared to a few percent for the reactive controller.

show abstract

Automated control for elastic n-tier workloads based on empirical modeling

Cited by 38 publications

References 19 publications

Burstiness-aware service level planning for enterprise application clouds

Burstiness-aware service level planning for enterprise application clouds

Adaptation in cloud resource configuration: a survey

Efficient provisioning of bursty scientific workloads on the cloud using adaptive elasticity control

Contact Info

Product

Resources

About