Change search
Refine search result
1 - 22 of 22
CiteExportLink to result list
Permanent link
Cite
Citation style
  • apa
  • ieee
  • modern-language-association-8th-edition
  • vancouver
  • Other style
More styles
Language
  • de-DE
  • en-GB
  • en-US
  • fi-FI
  • nn-NO
  • nn-NB
  • sv-SE
  • Other locale
More languages
Output format
  • html
  • text
  • asciidoc
  • rtf
Rows per page
  • 5
  • 10
  • 20
  • 50
  • 100
  • 250
Sort
  • Standard (Relevance)
  • Author A-Ö
  • Author Ö-A
  • Title A-Ö
  • Title Ö-A
  • Publication type A-Ö
  • Publication type Ö-A
  • Issued (Oldest first)
  • Issued (Newest first)
  • Created (Oldest first)
  • Created (Newest first)
  • Last updated (Oldest first)
  • Last updated (Newest first)
  • Disputation date (earliest first)
  • Disputation date (latest first)
  • Standard (Relevance)
  • Author A-Ö
  • Author Ö-A
  • Title A-Ö
  • Title Ö-A
  • Publication type A-Ö
  • Publication type Ö-A
  • Issued (Oldest first)
  • Issued (Newest first)
  • Created (Oldest first)
  • Created (Newest first)
  • Last updated (Oldest first)
  • Last updated (Newest first)
  • Disputation date (earliest first)
  • Disputation date (latest first)
Select
The maximal number of hits you can export is 250. When you want to export more records please use the Create feeds function.
  • 1. Conejero, Javier
    et al.
    Caminero, Blanca
    Carrion, Carmen
    Tomas, Luis
    Umeå University, Faculty of Science and Technology, Department of Computing Science.
    From volunteer to trustable computing: Providing QoS-aware scheduling mechanisms for multi-grid computing environments2014In: Future generations computer systems, ISSN 0167-739X, E-ISSN 1872-7115, Vol. 34, p. 76-93Article in journal (Refereed)
    Abstract [en]

    The exploitation of service oriented technologies, such as Grid computing, is being boosted by the current service oriented economy trend, leading to a growing need of Quality of Service (QoS) mechanisms. However, Grid computing was created to provide vast amounts of computational power but in a best effort way. Providing QoS guarantees is therefore a very difficult and complex task due to the distributed and heterogeneous nature of their resources, specially the volunteer computing resources (e.g., desktop resources). The scope of this paper is to empower an integrated multi QoS support suitable for Grid Computing environments made of either dedicated and volunteer resources, even taking advantage of that fact. The QoS is provided through SLAs by exploiting different available scheduling mechanisms in a coordinated way, and applying appropriate resource usage optimization techniques. It is based on the differentiated use of reservations and scheduling in advance techniques, enhanced with the integration of rescheduling techniques that improve the allocation decisions already made, achieving a higher resource utilization and still ensuring the agreed QoS. As a result, our proposal enhances best-effort Grid environments by providing QoS aware scheduling capabilities. This proposal has been validated by means of a set of experiments performed in a real Grid testbed. Results show how the proposed framework effectively harnesses the specific capabilities of the underlying resources to provide every user with the desired QoS level, while, at the same time, optimizing the resources' usage. (C) 2013 Elsevier B.V. All rights reserved.

  • 2. Dürango, Jonas
    et al.
    Tärneberg, William
    Tomas, Luis
    Umeå University, Faculty of Science and Technology, Department of Computing Science.
    Tordsson, Johan
    Umeå University, Faculty of Science and Technology, Department of Computing Science.
    Kihl, Maria
    Maggio, Martina
    A control theoretical approach to non-intrusive geo-replication for cloud services2016In: 2016 IEEE 55TH CONFERENCE ON DECISION AND CONTROL (CDC), IEEE, 2016, p. 1649-1656Conference paper (Refereed)
    Abstract [en]

    Complete data center failures may occur due to disastrous events such as earthquakes or fires. To attain robustness against such failures and reduce the probability of data loss, data must be replicated in another data center sufficiently geographically separated from the original data center. Implementing geo-replication is expensive as every data update operation in the original data center must be replicated in the backup. Running the application and the replication service in parallel is cost effective but creates a trade-off between potential replication consistency and data loss and reduced application performance due to network resource contention. We model this trade-off and provide a control-theoretical solution based on Model Predictive Control to dynamically allocate network bandwidth to accommodate the objectives of both replication and application data streams. We evaluate our control solution through simulations emulating the individual services, their traffic flows, and the shared network resource. The MPC solution is able to maintain a consistent performance over periods of persistent overload, and is quickly able to indiscriminately recover once the system return to a stable state. Additionally, the MPC balances the two objectives of consistency and performance according to the proportions specified in the objective function.

  • 3. Goumas, Georgios
    et al.
    Nikas, Konstantinos
    Lakew, Ewnetu Bayuh
    Umeå University, Faculty of Science and Technology, Department of Computing Science.
    Kotselidis, Christos
    Attwood, Andrew
    Elmroth, Erik
    Umeå University, Faculty of Science and Technology, Department of Computing Science.
    Flouris, Michail
    Foutris, Nikos
    Goodacre, John
    Grohmann, Davide
    Karakostas, Vasileios
    Koutsourakis, Panagiotis
    Kersten, Martin
    Lujan, Mikel
    Rustad, Einar
    Thomson, John
    Tomás, Luis
    Umeå University, Faculty of Science and Technology, Department of Computing Science.
    Vesterkjaer, Atle
    Webber, Jim
    Zhang, Ying
    Koziris, Nectarios
    ACTiCLOUD: Enabling the Next Generation of Cloud Applications2017In: 2017 IEEE 37TH INTERNATIONAL CONFERENCE ON DISTRIBUTED COMPUTING SYSTEMS (ICDCS 2017) / [ed] Lee, K Liu, L, IEEE Computer Society, 2017, p. 1836-1845Conference paper (Refereed)
    Abstract [en]

    Despite their proliferation as a dominant computing paradigm, cloud computing systems lack effective mechanisms to manage their vast amounts of resources efficiently. Resources are stranded and fragmented, ultimately limiting cloud systems' applicability to large classes of critical applications that pose non-moderate resource demands. Eliminating current technological barriers of actual fluidity and scalability of cloud resources is essential to strengthen cloud computing's role as a critical cornerstone for the digital economy. ACTiCLOUD proposes a novel cloud architecture that breaks the existing scale-up and share-nothing barriers and enables the holistic management of physical resources both at the local cloud site and at distributed levels. Specifically, it makes advancements in the cloud resource management stacks by extending state-of-the-art hypervisor technology beyond the physical server boundary and localized cloud management system to provide a holistic resource management within a rack, within a site, and across distributed cloud sites. On top of this, ACTiCLOUD will adapt and optimize system libraries and runtimes (e.g., JVM) as well as ACTiCLOUD-native applications, which are extremely demanding, and critical classes of applications that currently face severe difficulties in matching their resource requirements to state-of-the-art cloud offerings.

  • 4.
    Kostentinos Tesfatsion, Selome
    et al.
    Umeå University, Faculty of Science and Technology, Department of Computing Science.
    Proaño, Julio
    Tomás, Luis
    Umeå University, Faculty of Science and Technology, Department of Computing Science.
    Caminero, Blanca
    Carrión, Carmen
    Tordsson, Johan
    Umeå University, Faculty of Science and Technology, Department of Computing Science.
    Power and Performance Optimization in FPGA-accelerated Clouds2018In: Concurrency and Computation, ISSN 1532-0626, E-ISSN 1532-0634, Vol. 30, no 18, article id e4526Article in journal (Other academic)
    Abstract [en]

    Energy management has become increasingly necessary in data centers to address all energy-related costs, including capital costs, operating expenses, and environmental impacts. Heterogeneous systems with mixed hardware architectures provide both throughput and processing efficiency for different specialized application types and thus have a potential for significant energy savings. However, the presence of multiple and different processing elements increases the complexity of resource assignment. In this paper, we propose a system for efficient resource management in heterogeneous clouds. The proposed approach maps applications' requirement to different resources reducing power usage with minimum impact on performance. A technique that combines the scheduling of custom hardware accelerators, in our case, Field-Programmable Gate Arrays (FPGAs) and optimized resource allocation technique for commodity servers, is proposed. We consider an energy-aware scheduling technique that uses both the applications' performance and their deadlines to control the assignment of FPGAs to applications that would consume the most energy. Once the scheduler has performed the mapping between a VM and an FPGA, an optimizer handles the remaining VMs in the server, using vertical scaling and CPU frequency adaptation to reduce energy consumption while maintaining the required performance. Our evaluation using interactive and data-intensive applications compare the effectiveness of the proposed solution in energy savings as well as maintaining applications performance, obtaining up to a 32% improvement in the performance-energy ratio on a mix of multimedia and e-commerce applications.

  • 5. Kyriazis, Dimosthenis
    et al.
    Anagnostopoulos, Vasileios
    Arcangeli, Andrea
    Gilbert, David
    Kalogeras, Dimitrios
    Kat, Ronen
    Klein, Cristian
    Umeå University.
    Kokkinos, Panagiotis
    Kuperman, Yossi
    Nider, Joel
    Svärd, Petter
    Umeå University.
    Tomas, Luis
    Umeå University.
    Varvarigos, Emmanuel
    Varvarigou, Theodora
    High performance fault-tolerance for clouds2015In: 2015 IEEE SYMPOSIUM ON COMPUTERS AND COMMUNICATION (ISCC), Larnaca, Cyprus, July 6-9, 2015, IEEE , 2015, p. 251-257Conference paper (Refereed)
    Abstract [en]

    Cloud computing and virtualized infrastructures are currently the baseline environments for the provision of services in different application domains. While the number of service consumers increasingly grows, service providers aim at exploiting infrastructures that enable non-disruptive service provisioning, thus minimizing or even eliminating downtime. Nonetheless, to achieve the latter current approaches are either application-specific or cost inefficient, requiring the use of dedicated hardware. In this paper we present the reference architecture of a fault-tolerance scheme, which not only enhances cloud environments with the aforementioned capabilities but also achieves high-performance as required by mission critical every day applications. To realize the proposed approach, a new paradigm for memory and I/O externalization and consolidation is introduced, while current implementation references are also provided.

  • 6.
    Lorido-Botran, Tania
    et al.
    University of Deusto.
    Huerta, Sergio
    University of Deusto.
    Tomás, Luis
    Umeå University, Faculty of Science and Technology, Department of Computing Science.
    Tordsson, Johan
    Umeå University, Faculty of Science and Technology, Department of Computing Science.
    Sanz, Borja
    University of Deusto.
    An unsupervised approach to online noisy-neighbor detection in cloud data centers2017In: Expert systems with applications, ISSN 0957-4174, E-ISSN 1873-6793, Vol. 89, p. 188-204Article in journal (Refereed)
    Abstract [en]

    Resource sharing is an inherent characteristic of cloud data centers. Virtual Machines (VMs) and/or Containers that are co-located in the same physical server often compete for resources leading to interference. The noisy neighbor’s effect refers to an anomaly caused by a VM/container limiting resources accessed by another one. Our main contribution is an online, lightweight and application-agnostic solution for anomaly detection, that follows an unsupervised approach. It is based on comparing models for different lags: Dirichlet Process Gaussian Mixture Models to characterize the resource usage profile of the application, and distance measures to score the similarity among models. An alarm is raised when there is an abrupt change in short-term lag (i.e. high distance score for short-term models), while the long-term state remains constant. We test the algorithm for different cloud workloads: websites, periodic batch applications, Spark-based applications, and Memcached server. We are able to detect anomalies in the CPU and memory resource usage with up to 82–96% accuracy (recall) depending on the scenario. Compared to other baseline methods, our approach is able to detect anomalies successfully, while raising low number of false positives, even in the case of applications with unusual normal behavior (e.g. periodic). Experiments show that our proposed algorithm is a lightweight and effective solution to detect noisy neighbor effect without any historical info about the application, that could also be potentially applied to other kind of anomalies.

  • 7. Proaño Orellana, Julio
    et al.
    Caminero, Bianca
    Carrión, Carmen
    Tomas, Luis
    Umeå University, Faculty of Science and Technology, Department of Computing Science.
    Kostentinos Tesfatsion, Selome
    Umeå University, Faculty of Science and Technology, Department of Computing Science.
    Tordsson, Johan
    Umeå University, Faculty of Science and Technology, Department of Computing Science.
    FPGA-Aware Scheduling Strategies at Hypervisor Level in Cloud Environments2016In: Scientific Programming, ISSN 1058-9244, E-ISSN 1875-919X, article id 4670271Article in journal (Refereed)
    Abstract [en]

    Current open issues regarding cloud computing include the support for nontrivial Quality of Service-related Service Level Objectives (SLOs) and reducing the energy footprint of data centers. One strategy that can contribute to both is the integration of accelerators as specialized resources within the cloud system. In particular, Field Programmable Gate Arrays (FPGAs) exhibit an excellent performance/energy consumption ratio that can be harnessed to achieve these goals. In this paper, a multilevel cloud scheduling framework is described, and several FPGA-aware node level scheduling strategies (applied at the hypervisor level) are explored and analyzed. These strategies are based on the use of a multiobjective metric aimed at providing Quality of Service (QoS) support. Results show how the proposed FPGA-aware scheduling policies increment the number of users requests serviced with their SLOs fulfilled while energy consumption is minimized. In particular, evaluation results of a use case based on a multimedia application show that the proposal can save more than 20% of the total energy compared with other baseline algorithms while a higher percentage of Service Level Agreement (SLA) is fulfilled.

  • 8. Saeid Masoumzadeh, Seyed
    et al.
    Hlavacs, Helmut
    Tomas, Luis
    Umeå University, Faculty of Science and Technology, Department of Computing Science.
    A Self-Adaptive Performance-Aware Capacity Controller in Overbooked Datacenters2016In: 2016 INTERNATIONAL CONFERENCE ON CLOUD AND AUTONOMIC COMPUTING (ICCAC) / [ed] Gupta, I; Diao, Y, Institute of Electrical and Electronics Engineers (IEEE), 2016, p. 12-23Conference paper (Refereed)
    Abstract [en]

    Interference between co-located VMs may lead to performance fluctuations and degradation, especially in overbooked datacenters. To limit this problem, VMs access to physical resources needs to be controlled to ensure certain degree of isolation among them. However, the mapping between virtual and physical resources must be performed in a dynamic way so that it can be adapted to the changing applications requirements, as well as to the different set of co-located VMs. To address this problem we propose a twofold approach: (1) a Quality of Service (QoS) scheme that provides different isolation levels for VMs with different QoS requirements, and (2) a self-adaptive fuzzy Q-learning capacity controller that proactively readjusts the isolation degree based on applications performance. Our evaluation based on real cloud applications and workloads demonstrates that the efficient, adaptive mapping between VMs and physical resources reduces the interference between VMs, enabling the possibility of co-locating more VMs, increases overall utilization, and ensures the performance of critical applications while providing more resources to the low QoS applications.

  • 9.
    Souza, Abel
    et al.
    Umeå University, Faculty of Science and Technology, Department of Computing Science.
    Papadopoulos, Alessandro Vittorio
    Tomás Bolivar, Luis
    Umeå University, Faculty of Science and Technology, Department of Computing Science. Red Hat Inc..
    Gilbert, David
    Tordsson, Johan
    Umeå University, Faculty of Science and Technology, Department of Computing Science.
    Hybrid Adaptive Checkpointing for Virtual Machine Fault Tolerance2018In: Proceedings - 2018 IEEE International Conference on Cloud Engineering, IC2E 2018 / [ed] Li J., Chandra A., Guo T., Cai Y., Institute of Electrical and Electronics Engineers (IEEE), 2018, p. 12-22Conference paper (Refereed)
    Abstract [en]

    Active Virtual Machine (VM) replication is an application independent and cost-efficient mechanism for high availability and fault tolerance, with several recently proposed implementations based on checkpointing. However, these methods may suffer from large impacts on application latency, excessive resource usage overheads, and/or unpredictable behavior for varying workloads. To address these problems, we propose a hybrid approach through a Proportional-Integral (PI) controller to dynamically switch between periodic and on-demand check-pointing. Our mechanism automatically selects the method that minimizes application downtime by adapting itself to changes in workload characteristics. The implementation is based on modifications to QEMU, LibVirt, and OpenStack, to seamlessly provide fault tolerant VM provisioning and to enable the controller to dynamically select the best checkpointing mode. Our evaluation is based on experiments with a video streaming application, an e-commerce benchmark, and a software development tool. The experiments demonstrate that our adaptive hybrid approach improves both application availability and resource usage compared to static selection of a checkpointing method, with application performance gains and neglectable overheads.

  • 10.
    Tesfatsion, Selome Kostentinos
    et al.
    Umeå University, Faculty of Science and Technology, Department of Computing Science.
    Tomás, Luis
    Red Hat, Madrid, Spain.
    Tordsson, Johan
    Umeå University, Faculty of Science and Technology, Department of Computing Science.
    OptiBook: Optimal Resource Booking for Energy-efficient Datacenters2017In: 2017 IEEE/ACM 25th International Symposium on Quality of Service (IWQoS), IEEE Communications Society, 2017Conference paper (Refereed)
    Abstract [en]

    A lack of energy proportionality, low resource utilization, and interference in virtualized infrastructure make the cloud a challenging target environment for improving energy efficiency. In this paper we present OptiBook, a system that improves energy proportionality and/or resource utilization to optimize performance and energy efficiency. OptiBook shares servers between latency-sensitive services and batch jobs, over- books the system in a controllable manner, uses vertical (CPU and DVFS) scaling for prioritized virtual machines, and applies performance isolation techniques such as CPU pinning and quota enforcement as well as online resource tuning to effectively improve energy efficiency. Our evaluations show that on average, OptiBook improves performance per watt by 20% and reduces energy consumption by 9% while minimizing SLO violations. 

  • 11.
    Tomas, Luis
    et al.
    Umeå University, Faculty of Science and Technology, Department of Computing Science.
    Bayuh Lakew, Ewnetu
    Umeå University, Faculty of Science and Technology, Department of Computing Science.
    Elmroth, Erik
    Umeå University, Faculty of Science and Technology, Department of Computing Science.
    Service Level and Performance Aware Dynamic Resource Allocation in Overbooked Data Centers2016In: 2016 16TH IEEE/ACM INTERNATIONAL SYMPOSIUM ON CLUSTER, CLOUD AND GRID COMPUTING (CCGRID), 2016, p. 42-51Conference paper (Refereed)
    Abstract [en]

    Many cloud computing providers use overbooking to increase their low utilization ratios. This however increases the risk of performance degradation due to interference among co-located VMs. To address this problem we present a service level and performance aware controller that: (1) provides performance isolation for high QoS VMs; and (2) reduces the VM interference between low QoS VMs by dynamically mapping virtual cores to physical cores, thus limiting the amount of resources that each VM can access depending on their performance. Our evaluation based on real cloud applications and both stress, synthetic and realistic workloads demonstrates that a more efficient use of the resources is achieved, dynamically allocating the available capacity to the applications that need it more, which in turn lead to a more stable and predictable performance over time.

  • 12.
    Tomas, Luis
    et al.
    Umeå University, Faculty of Science and Technology, Department of Computing Science.
    Caminero, Blanca
    University of Castilla-La Mancha.
    Carrión, Carmen
    University of Castilla-La Mancha.
    Opportunistic Energy-Aware Rescheduling in Desktop Grid Environments2013In: 2013 International Conference on High Performance Computing & Simulation (HPCS2013), 2013, p. 178-185Conference paper (Refereed)
    Abstract [en]

    Nowadays either maximizing energy efficiency andimproving resource utilization is a challenge among the differentexisting distributed systems, specially in large scale distributedenvironments such as Grids or Clouds. With this objective, wepropose a rescheduling technique that tries to improve resourceusage, whilst at the same time tries to minimize the energy neededfor the executions of the already accepted jobs by using first/morethe resources that are more energy efficient and without reducingthe QoS provided. The information obtained from a devicecapable of measuring the energy that each desktop resourceneeds is used by the algorithm at the resource selection process,resulting in a noticeable reduction in the energy used as it hasbeen demonstrated in a real desktop Grid environment.

  • 13.
    Tomas, Luis
    et al.
    Umeå University, Faculty of Science and Technology, Department of Computing Science.
    Masoumzadeh, Seyed Saeid
    Hlavacs, Helmut
    Self-Adaptive Capacity Controller: A Reinforcement Learning Approach2016In: 2016 IEEE INTERNATIONAL CONFERENCE ON AUTONOMIC COMPUTING (ICAC), LOS ALAMITOS: IEEE Computer Society, 2016, p. 233-234Conference paper (Refereed)
    Abstract [en]

    Interference between co-located VMs may lead to performance fluctuations and degradation. To limit this problem, VMs access to physical resources needs to be controlled to ensure certain degree of isolation among them. This mapping between virtual and physical resources must be performed in a dynamic way so that it can be adaptive to the changing applications requirements, as well as to the different set of co-located VMs. To address this problem we propose a self-adaptive fuzzy Q-learning capacity controller that proactively readjusts the isolation degree based on applications performance. Our evaluation demonstrates a reduction into VMs interference and an increment on the overall utilization, while still ensuring critical applications performance, and providing more resources to non-critical applications.

  • 14.
    Tomas, Luis
    et al.
    Umeå University, Faculty of Science and Technology, Department of Computing Science.
    Saeid Masoumzadeh, Seyed
    Hlavacs, Helmut
    Self-Adaptive Capacity Controller: A Reinforcement Learning Approach2016In: 2016 IEEE International Conference on Autonomic Computing (ICAC), IEEE, 2016Conference paper (Refereed)
    Abstract [en]

    Interference between co-located VMs may lead to performance fluctuations and degradation. To limit this problem, VMs access to physical resources needs to be controlled to ensure certain degree of isolation among them. This mapping between virtual and physical resources must be performed in a dynamic way so that it can be adaptive to the changing applications requirements, as well as to the different set of co-located VMs. To address this problem we propose a self-adaptive fuzzy Q-learning capacity controller that proactively readjusts the isolation degree based on applications performance. Our evaluation demonstrates a reduction into VMs interference and an increment on the overall utilization, while still ensuring critical applications performance, and providing more resources to non-critical applications.

  • 15.
    Tomas, Luis
    et al.
    Umeå University, Faculty of Science and Technology, Department of Computing Science.
    Tordsson, Johan
    Umeå University, Faculty of Science and Technology, Department of Computing Science.
    An autonomic approach to risk-aware data center overbooking2014In: IEEE Transactions on Cloud Computing, ISSN 2168-7161, Vol. 2, no 3, p. 292-305Article in journal (Refereed)
    Abstract [en]

    Elasticity is a key characteristic of cloud computing that increases the flexibility for cloud consumers, allowing them to adapt the amount of physical resources associated to their services over time in an on-demand basis. However, elasticity creates problems for cloud providers as it may lead to poor resource utilization, specially in combination with other factors, such as user overestimations and pre-defined VM sizes. Admission control mechanisms are thus needed to increase the number of services accepted, raising the utilization without affecting services performance. This work focuses on implementing an autonomic risk-aware overbooking architecture capable of increasing the resource utilization of cloud data centers by accepting more virtual machines than physical available resources. Fuzzy logic functions are used to estimate the associated risk to each overbooking decision. By using a distributed PID controller approach, the system is capable of self-adapting over time – changing the acceptable level of risk – depending on the current status of the cloud data center. The suggested approach is extensively evaluated using a combination of simulations and experiments executing real cloud applications with real-life available workloads. Our results show a 50% increment at both resource utilization and capacity allocated with acceptable performance degradation and more stable resource utilization over time.

  • 16.
    Tomas, Luis
    et al.
    Umeå University, Faculty of Science and Technology, Department of Computing Science.
    Tordsson, Johan
    Umeå University, Faculty of Science and Technology, Department of Computing Science.
    Cloudy with a Chance of Load Spikes: Admission Control with Fuzzy Risk Assessments2013In: 6th IEEE International Conference on Utility and Cloud Computing, 2013, p. 155-162Conference paper (Refereed)
    Abstract [en]

    Elasticity is key for the cloud paradigm, wherethe pay-per use nature provides great flexibility for end-users.However, elasticity complicates long-term capacity planning forcloud providers as the exact amount of resources requiredover time becomes uncertain. Admission control techniques arethus needed to handle the trade-off between resource utilizationand potential overload. We define a set of admission controlalgorithms that combine risk assessment methods with a fuzzyaggregation framework. An experimental evaluation using amixture of bursty and steady applications demonstrate that ouralgorithms can increase resource utilization by a factor of twowhile limiting overload problems to a few percent.

  • 17.
    Tomas, Luis
    et al.
    Umeå University, Faculty of Science and Technology, Department of Computing Science.
    Tordsson, Johan
    Umeå University, Faculty of Science and Technology, Department of Computing Science.
    Improving Cloud Infrastructure Utilization through Overbooking2013In: Proceedings of the 2013 ACM Cloud and Autonomic Computing Conference, 2013Conference paper (Refereed)
    Abstract [en]

    Despite the potential given by the combination of multitenancyand virtualization, resource utilization in today’sdata centers is still low. We identify three key characteristicsof cloud services and infrastructure as-a-service managementpractices: burstiness in service workloads, fluctuationsin virtual machine resource usage over time, and virtual machinesbeing limited to pre-defined sizes only. Based on thesecharacteristics, we propose scheduling and admission controlalgorithms that incorporate resource overbooking to improveutilization. A combination of modeling, monitoring, andprediction techniques is used to avoid overpassing the totalinfrastructure capacity. A performance evaluation using amixture of workload traces demonstrates the potential forsignificant improvements in resource utilization while stillavoiding overpassing the total capacity.

  • 18.
    Tomas, Luis
    et al.
    Umeå University, Faculty of Science and Technology, Department of Computing Science.
    Tordsson, Johan
    Umeå University, Faculty of Science and Technology, Department of Computing Science.
    Vazquez, Carlos
    University of Castilla-La Mancha.
    Moreno, Gines
    Reducing Noisy-Neighbor Impact with a Fuzzy Affinity-Aware Scheduler2015In: 2015 INTERNATIONAL CONFERENCE ON CLOUD AND AUTONOMIC COMPUTING (ICCAC), New York: IEEE Computer Society, 2015, p. 33-44Conference paper (Refereed)
    Abstract [en]

    Overbooking techniques have been proven efficientto increase overall utilization of cloud datacenters. However,overbooking may also degrade applications performance as (atleast) some applications need to share physical resources suchas CPU or memory. Consequently, interference may increaseamong the virtual machines that share resources, the so callednoisy neighbors effect. We present an affinity-aware schedulerto reduce the impact of such interference. A fuzzy logic engineaccounts for the uncertainty in these environments and estimateswhich CPU cores are currently more suitable for each incomingapplication. This helps the scheduler make virtual machine tophysical resource mapping decisions, also known as vcpu pinning.An experimental evaluation based on a combination of interactiveservices and batch applications confirms that our affinity-awarefuzzy scheduler reduces the interference among applications,enabling more predictable performance and consequently saferoverbooking.

  • 19.
    Tomás, Luis
    et al.
    Umeå University, Faculty of Science and Technology, Department of Computing Science.
    Klein, Cristian
    Umeå University, Faculty of Science and Technology, Department of Computing Science.
    Tordsson, Johan
    Umeå University, Faculty of Science and Technology, Department of Computing Science.
    Hernández, Francisco
    Umeå University, Faculty of Science and Technology, Department of Computing Science.
    The straw that broke the camel’s back: safe cloud overbooking with application brownout2014In: 2014 International Conference on Cloud and Autonomic Computing (ICCAC 2014), IEEE Press, 2014, p. 151-160Conference paper (Refereed)
    Abstract [en]

    Resource overbooking is an admission control technique to increase utilization in cloud environments. However, due to uncertainty about future application workloads, overbooking may result in overload situations and deteriorated performance. We mitigate this using brownout, a feedback approach to application performance steering, that ensures graceful degradation during load spikes and thus avoids overload. Additionally, brownout management information is included into the overbooking system, enabling the development of improved reactive methods to overload situations. Our combined brownout-overbooking approach is evaluated based on real-life interactive workloads and non-interactive batch applications. The results show that our approach achieves an improvement of resource utilization of 11 to 37 percentage points, while keeping response times lower than the set target of 1 second, with negligible application degradation.

  • 20.
    Tomás, Luis
    et al.
    Umeå University, Faculty of Science and Technology, Department of Computing Science.
    Tordsson, Johan
    Umeå University, Faculty of Science and Technology, Department of Computing Science.
    Cloud Service Differentiation in Overbooked Data Centers2014In: 2014 IEEE/ACM 7th International Conference on Utility and Cloud Computing (UCC), IEEE, 2014, p. 541-546Conference paper (Refereed)
    Abstract [en]

    Low resource utilization in cloud data centers can be mitigated by overbooking but this increases the risk of performance degradation. We propose a three level Quality of Service (QoS) scheme for overbooked cloud data centers to assure high performance QoS for applications that need it. We design a controller that dynamically maps virtual cores to physical cores and whenever feasible shares physical cores among applications. Our evaluation based on real cloud applications and workloads demonstrates that performance isolation can be achieved for critical applications while overall utilization is increased thanks to overbooking.

  • 21.
    Vazquez, Carlos
    et al.
    University of Castilla-La Mancha, Spain.
    Moreno, Gines
    University of Castilla-La Mancha, Spain.
    Tomas, Luis
    Umeå University, Faculty of Science and Technology, Department of Computing Science.
    Tordsson, Johan
    Umeå University, Faculty of Science and Technology, Department of Computing Science.
    A Cloud Scheduler Assisted by a Fuzzy Affinity-Aware Engine2015In: 2015 IEEE International Conference on Fuzzy Systems (FUZZ-IEEE) / [ed] Adnan Yazici, Nikhil R.Pal, Uzay Kaymak, Trevor Martin, Hisao Ishibuchi, Chin-Teng Lin, Joao M. C. Sousa and Bulent Tutmez, IEEE Computer Society, 2015, p. 1-8Conference paper (Refereed)
    Abstract [en]

    Recent advances on declarative paradigms have introduced expressive resources based on fuzzy logic. These are very useful for increasing the flexibility of the so-called fuzzy logicprogramming paradigm, resulting in highly expressive languages where the treatment of uncertainty and approximate reasoning is performed in a natural, efficient way. Therefore, making it extremely useful for decision-making scenarios dealing with highlevels of uncertainty. One such scenario is capacity management in cloud environments, where the amount of resources that users will request is unknown and can vary significantly overtime, usually leading to poor resource utilization. Overbooking techniques allow cloud providers to increase utilization, but the risk of degrading application performance due to exhausting resources also increases as applications need to share the servers. Fuzzy logic programming can be used to decide how cloud applications should be co-located with each other, minimizing the interference among them. Therefore, we propose a newscheduling mechanism based on fuzzy logic cores clustering, and applications–cores affinity estimation to decide which applications to co-locate reducing the interference. An experimental evaluation confirms that our affinity-aware fuzzy logic assisted scheduler minimizes the interference among applications, enabling a moresafe overbooking and consequently higher cloud provider revenue.

  • 22.
    Vázquez, Carlos
    et al.
    Umeå University, Faculty of Science and Technology, Department of Applied Physics and Electronics. University of Castilla-La Mancha.
    Tomas, Luis
    Umeå University, Faculty of Science and Technology, Department of Computing Science.
    Moreno, Ginés
    University of Castilla-La Mancha.
    Tordsson, Johan
    Umeå University, Faculty of Science and Technology, Department of Computing Science.
    A fuzzy approach to cloud admission control for safe overbooking2013In: 10th International Workshop on Fuzzy Logic and Applications (WILF), 2013, p. 212-225Conference paper (Refereed)
    Abstract [en]

    Cloud computing enables elasticity - rapid provisioning and deprovisioning of computational resources.Elasticity allows cloud users to quickly adapt resource allocation to meet changes in their workloads.For cloud providers, elasticity complicates capacity management as the amount ofresources that can be requested by users is unknown and can vary significantly over time. Overbooking techniques allowproviders to increase utilization of their data centers. For safe overbooking, cloud providersneed admission control mechanisms to handle the tradeoff between increasedutilization (and revenue), and risk of exhausting resources, potentially resulting in penalty fees and/or lost customers.We propose a flexible approach (implemented with fuzzy logic programming) to admission control and the associated risk estimation.Our measures exploit different fuzzy logic operators in order to model optimistic, realistic, and pessimistic behaviour under uncertainty.An experimental evaluation confirm that our fuzzy admission control approach can significantly increaseresource utilization while minimizing the risk of exceeding the total available capacity.

1 - 22 of 22
CiteExportLink to result list
Permanent link
Cite
Citation style
  • apa
  • ieee
  • modern-language-association-8th-edition
  • vancouver
  • Other style
More styles
Language
  • de-DE
  • en-GB
  • en-US
  • fi-FI
  • nn-NO
  • nn-NB
  • sv-SE
  • Other locale
More languages
Output format
  • html
  • text
  • asciidoc
  • rtf