VM power metering

Krishnan, Bhavani; Amur, Hrishikesh; Gavrilovska, Ada; Schwan, Karsten

doi:10.1145/1925019.1925031

Cited by 102 publications

(11 citation statements)

References 8 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Such models are particularly needed because it is not possible to attach a power meter to a virtual machine [16]. In general, VMs can be monitored as black-box systems for coarse-grained scheduling decisions.…”

Section: Vm Power Modelsmentioning

confidence: 99%

Process-level power estimation in VM-based systems

Colmant

Kurpicz

Felber

et al. 2015

Proceedings of the Tenth European Conference on Computer Systems

View full text Add to dashboard Cite

Power estimation of software processes provides critical indicators to drive scheduling or power capping heuristics. State-of-the-art solutions can perform coarse-grained power estimation in virtualized environments, typically treating virtual machines (VMs) as a black box. Yet, VM-based systems are nowadays commonly used to host multiple applications for cost savings and better use of energy by sharing common resources and assets.In this paper, we propose a fine-grained monitoring middleware providing real-time and accurate power estimation of software processes running at any level of virtualization in a system. In particular, our solution automatically learns an application-agnostic power model, which can be used to estimate the power consumption of applications.Our middleware implementation, named BITWATTS, builds on a distributed actor implementation to collect process usage and infer fine-grained power consumption without imposing any hardware investment (e.g., power meters). BITWATTS instances use high-throughput communication channels to spread the power consumption across the VM levels and between machines. Our experiments, based on CPU-and memory-intensive benchmarks running on different hardware setups, demonstrate that BITWATTS scales both in number of monitored processes and virtualization levels. This non-invasive monitoring solution therefore paves the way for scalable energy accounting that takes into account the dynamic nature of virtualized environments.

show abstract

Section: Vm Power Modelsmentioning

confidence: 99%

Process-level power estimation in VM-based systems

Colmant

Kurpicz

Felber

et al. 2015

Proceedings of the Tenth European Conference on Computer Systems

View full text Add to dashboard Cite

show abstract

“…Most of the proposed models apply linear regression to fit model parameters. The minimum average estimation error that is reported for a linear model is 1.5% while the maximum is 10% [15]. For the nonlinear models the minimum estimation error is < 1% [17] and the maximum is 6.67% [13].…”

Section: B Choice Of Model Training Techniquesmentioning

confidence: 83%

“…Similarly, Krishnan et al [15] present a linear model to compute the power consumption of virtual machines. They use PMC as model inputs but point out that the mapping of inst_retired/s to CPU power consumption is not straight forward, since memory references that hit in different cache levels consume slightly different amounts of power.…”

Section: Cpu Modelsmentioning

confidence: 99%

“…Of all the employed PMEs, the one most frequently used and which is highly correlated with the power consumption of a processor is the instructions retired event [34], [15], [45], [29]. Nevertheless, Bircher et al [35] argue that the event does not account for instructions that are aborted even though aborted instructions may have their own share of the CPU power consumption.…”

Section: A Model Parametersmentioning

confidence: 99%

“…The hardwareprovided inputs generally refer to performance monitoring counters (PMC) which are provided by the CPU [13], [14], [15]. While it is possible that other subsystems may provide similar performance monitoring counters, no publication is known to the authors on this subject.…”

Section: Introductionmentioning

confidence: 99%

See 2 more Smart Citations

Power Consumption Estimation Models for Processors, Virtual Machines, and Servers

Möbius

Dargie

Schill

2014

IEEE Trans. Parallel Distrib. Syst.

131

View full text Add to dashboard Cite

Abstract-The power consumption of presently available Internet servers and data centers is not proportional to the work they accomplish. The scientific community is attempting to address this problem in a number of ways, for example, by employing dynamic voltage and frequency scaling, selectively switching off idle or underutilized servers, and employing energy-aware task scheduling. Central to these approaches is the accurate estimation of the power consumption of the various subsystems of a server, particularly, the processor. We distinguish between power consumption measurement techniques and power consumption estimation models. The techniques refer to the art of instrumenting a system to measure its actual power consumption whereas the estimation models deal with indirect evidences (such as information pertaining to CPU utilization or events captured by hardware performance counters) to reason about the power consumption of a system under consideration. The paper provides a comprehensive survey of existing or proposed approaches to estimate the power consumption of single-core as well as multicore processors, virtual machines, and an entire server.

show abstract

Characterizing the power cost of virtualization environments

Tadesse

Chiasserini

Malandrino

2018

Trans Emerging Tel Tech

View full text Add to dashboard Cite

Virtualization is a key building block of next‐generation mobile networks. It can be implemented through two main approaches: traditional virtual machines (VMs) and lighter‐weight containers. Our objective in this paper is to compare these approaches and study the power consumption they are associated with. To this end, we perform a large set of real‐world measurements, using both synthetic workloads and real‐world applications, and use them to model the relationship between the resource usage of the hosted application and the power consumption of both VMs and containers hosting it. We find that containers incur substantially lower power consumption than VMs and that such consumption increases more slowly with the application load.

show abstract

VM power metering

Cited by 102 publications

References 8 publications

Process-level power estimation in VM-based systems

Process-level power estimation in VM-based systems

Power Consumption Estimation Models for Processors, Virtual Machines, and Servers

Characterizing the power cost of virtualization environments

Contact Info

Product

Resources

About