With the proliferation of data movement across the Internet, global data traffic per year has already exceeded the Zettabyte scale. The network infrastructure and end-systems facilitating the vast data movement consume an extensive amount of electricity, measured in terawatt-hours per year. This massive energy footprint costs the world economy billions of dollars partially due to energy consumed at the network end-systems. Although extensive research has been done on managing power consumption within the core networking infrastructure, there is little research on reducing the power consumption at the end-systems during active data transfers. This paper presents a novel cross-layer optimization framework, called Cross-LayerHLA, to minimize energy consumption at the end-systems by applying machine learning techniques to historical transfer logs and extracting the hidden relationships between different parameters affecting both the performance and resource utilization. It utilizes offline analysis to improve online learning and dynamic tuning of application-level and kernel-level parameters with minimal overhead. This approach minimizes end-system energy consumption and maximizes data transfer throughput. Our experimental results show that Cross-LayerHLA outperforms other state-of-the-art solutions in this area.
more »
« less
Cross-Layer Optimization of Big Data Transfer Throughput and Energy Consumption
With the emergence of data deluge, the energy footprint of global data movement has surpassed 100 terawatt hours, costing more than 20 billion US dollars to the world economy. During an active data transfer, depending on the number of hops between the source and destination, the networking infrastructure consumes between 10% - 75% of the total energy, and the rest is consumed by the end systems. Even though there has been extensive research on reducing the power consumption at the networking infrastructure, the work focusing on saving energy at the end systems has been limited to the tuning of a few application-level parameters. In this paper, we introduce a novel cross-layer optimization framework which jointly considers application-level and kernel-level parameters to minimize the energy consumption without sacrificing from the transfer throughput. We present three different algorithms which can dynamically tune the CPU frequency level, number of active CPU cores, number of active transfer threads, number of parallel TCP streams, and the level of transfer command pipelining to achieve different user-set goals. Experimental results show that our proposed algorithms outperform the state-of-the-art solutions, achieving up to 80% higher throughput while consuming 48% less energy.
more »
« less
- NSF-PAR ID:
- 10113313
- Date Published:
- Journal Name:
- 2019 IEEE 12th International Conference on Cloud Computing (CLOUD)
- Page Range / eLocation ID:
- 25 to 32
- Format(s):
- Medium: X
- Sponsoring Org:
- National Science Foundation
More Like this
-
-
The global data movement over Internet has an estimated energy footprint of 100 terawatt hours per year, costing the world economy billions of dollars. The networking infrastructure together with source and destination nodes involved in the data transfer contribute to overall energy consumption. Although considerable amount of research has rendered power management techniques for the networking infrastructure, there has not been much prior work focusing on energy-aware data transfer solutions for minimizing the power consumed at the end-systems. In this paper, we introduce a novel application-layer solution based on historical analysis and real-time tuning called GreenDataFlow, which aims to achieve high data transfer throughput while keeping the energy consumption at the minimal levels. GreenDataFlow supports service level agreements (SLAs) which give the service providers and the consumers the ability to fine tune their goals and priorities in this optimization process. Our experimental results show that GreenDataFlow outperforms the closest competing state-of-the art solution in this area 50% for energy saving and 2.5× for the achieved end-to-end performance.more » « less
-
The increase and rapid growth of data produced by scientific instruments, the Internet of Things (IoT), and social media is causing data transfer performance and resource consumption to garner much attention in the research community. The network infrastructure and end systems that enable this extensive data movement use a substantial amount of electricity, measured in terawatt-hours per year. Managing energy consumption within the core networking infrastructure is an active research area, but there is a limited amount of work on reducing power consumption at the end systems during active data transfers. This paper presents a novel two-phase dynamic throughput and energy optimization model that utilizes an offline decision-search-tree based clustering technique to encapsulate and categorize historical data transfer log information and an online search optimization algorithm to find the best application and kernel layer parameter combination to maximize the achieved data transfer throughput while minimizing the energy consumption. Our model also incorporates an ensemble method to reduce aleatoric uncertainty in finding optimal application and kernel layer parameters during the offline analysis phase. The experimental evaluation results show that our decision-tree based model outperforms the state-of-the-art solutions in this area by achieving 117% higher throughput on average and also consuming 19% less energy at the end systems during active data transfers.more » « less
-
While distributed computing infrastructures can provide infrastructure-level techniques for managing energy consumption, application-level energy consumption models have also been developed to support energy-efficient scheduling and resource provisioning algorithms. In this work, we analyze the accuracy of a widely-used application-level model that have been developed and used in the context of scientific workflow executions. To this end, we profile two production scientific workflows on a distributed platform instrumented with power meters. We then conduct an analysis of power and energy consumption measurements. This analysis shows that power consumption is not linearly related to CPU utilization and that I/O operations significantly impact power, and thus energy, consumption. We then propose a power consumption model that accounts for I/O operations, including the impact of waiting for these operations to complete, and for concurrent task executions on multi-socket, multi-core compute nodes. We implement our proposed model as part of a simulator that allows us to draw direct comparisons between real-world and modeled power and energy consumption. We find that our model has high accuracy when compared to real-world executions. Furthermore, our model improves accuracy by about two orders of magnitude when compared to the traditional models used in the energy-efficient workflow scheduling literature.more » « less
-
Chi-Wang Shu (Ed.)GPU computing is expected to play an integral part in all modern Exascale supercomputers. It is also expected that higher order Godunov schemes will make up about a significant fraction of the application mix on such supercomputers. It is, therefore, very important to prepare the community of users of higher order schemes for hyperbolic PDEs for this emerging opportunity. Not every algorithm that is used in the space-time update of the solution of hyperbolic PDEs will take well to GPUs. However, we identify a small core of algorithms that take exceptionally well to GPU computing. Based on an analysis of available options, we have been able to identify weighted essentially non-oscillatory (WENO) algorithms for spatial reconstruction along with arbitrary derivative (ADER) algorithms for time extension followed by a corrector step as the winning three-part algorithmic combination. Even when a winning subset of algorithms has been identified, it is not clear that they will port seamlessly to GPUs. The low data throughput between CPU and GPU, as well as the very small cache sizes on modern GPUs, implies that we have to think through all aspects of the task of porting an application to GPUs. For that reason, this paper identifies the techniques and tricks needed for making a successful port of this very useful class of higher order algorithms to GPUs. Application codes face a further challenge—the GPU results need to be practically indistinguishable from the CPU results—in order for the legacy knowledge bases embedded in these applications codes to be preserved during the port of GPUs. This requirement often makes a complete code rewrite impossible. For that reason, it is safest to use an approach based on OpenACC directives, so that most of the code remains intact (as long as it was originally well-written). This paper is intended to be a one-stop shop for anyone seeking to make an OpenACC-based port of a higher order Godunov scheme to GPUs. We focus on three broad and high-impact areas where higher order Godunov schemes are used. The first area is computational fluid dynamics (CFD). The second is computational magnetohydrodynamics (MHD) which has an involution constraint that has to be mimetically preserved. The third is computational electrodynamics (CED) which has involution constraints and also extremely stiff source terms. Together, these three diverse uses of higher order Godunov methodology, cover many of the most important applications areas. In all three cases, we show that the optimal use of algorithms, techniques, and tricks, along with the use of OpenACC, yields superlative speedups on GPUs. As a bonus, we find a most remarkable and desirable result: some higher order schemes, with their larger operations count per zone, show better speedup than lower order schemes on GPUs. In other words, the GPU is an optimal stratagem for overcoming the higher computational complexities of higher order schemes. Several avenues for future improvement have also been identified. A scalability study is presented for a real-world application using GPUs and comparable numbers of high-end multicore CPUs. It is found that GPUs offer a substantial performance benefit over comparable number of CPUs, especially when all the methods designed in this paper are used.more » « less
- Free Publicly Accessible Full Text
-
Accepted Manuscript1.0
- Conference Paper:
- https://doi.org/10.1109/CLOUD.2019.00017
