Pub Date : 2018-06-01DOI: 10.1109/IWQoS.2018.8624136
Yu He, Lin Ma, Chuanhe Huang
GPU cloud computing is emerging as a new type of cloud service that drives computation-extensive jobs, such as big data analytics and distributed machine learning. The introduction of GPU brings parallel processing power at the cost of excessive energy consumption. Dynamic Voltage and Frequency Scaling (DVFS) is a promising method to control energy consumption of GPU VMs. This work focuses on using DVFS to reduce energy of cloud computing in datacenter demand response. We first consider an online demand response scenario where users arrive stochastically, aiming at maximizing social welfare and meeting energy reduction goals by employing DVFS. We address the challenge posed by DVFS through a new technique of compact infinite optimization. A more practical scenario where both energy and resource limitations present is further studied. We design a primal-dual approximation algorithm that can compute a feasible solution in polynomial time with guaranteed approximation ratio, and a payment scheme that works in concert to form a truthful cloud job auction.
{"title":"Online Demand Response of GPU Cloud Computing with DVFS","authors":"Yu He, Lin Ma, Chuanhe Huang","doi":"10.1109/IWQoS.2018.8624136","DOIUrl":"https://doi.org/10.1109/IWQoS.2018.8624136","url":null,"abstract":"GPU cloud computing is emerging as a new type of cloud service that drives computation-extensive jobs, such as big data analytics and distributed machine learning. The introduction of GPU brings parallel processing power at the cost of excessive energy consumption. Dynamic Voltage and Frequency Scaling (DVFS) is a promising method to control energy consumption of GPU VMs. This work focuses on using DVFS to reduce energy of cloud computing in datacenter demand response. We first consider an online demand response scenario where users arrive stochastically, aiming at maximizing social welfare and meeting energy reduction goals by employing DVFS. We address the challenge posed by DVFS through a new technique of compact infinite optimization. A more practical scenario where both energy and resource limitations present is further studied. We design a primal-dual approximation algorithm that can compute a feasible solution in polynomial time with guaranteed approximation ratio, and a payment scheme that works in concert to form a truthful cloud job auction.","PeriodicalId":222290,"journal":{"name":"2018 IEEE/ACM 26th International Symposium on Quality of Service (IWQoS)","volume":"36 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2018-06-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"126796597","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Pub Date : 2018-06-01DOI: 10.1109/IWQoS.2018.8624142
Ye Yu, Chen Qian, Wenfei Wu, Ying Zhang
Network failures are inevitable due to its increasing complexity, which significantly hampers system availability and performance. While adopting checkpointing and rollback recovery protocols (C/R for abbreviation) from distributed systems into computer networks is promising, several specific challenges appear as we design a C/R system for Software-Defined Networks (SDN). The C/R should be coordinated with other applications in the SDN controller, each individual switch C/R should not interrupt traffic traversing it, and SDN controller C/R faces the challenge of time and space overhead. We propose a C/R framework for SDN, named NetCP. NetCP coordinates C/R and other applications to get consistent global checkpoints, it leverages redundant forwarding tables in SDN switches for C/R so as to avoid interrupting traversing traffic, and it analyzes the dependencies between controller applications to make minimal C/R decision. We have implemented NetCP in a prototype system using the current standard SDN tools and demonstrate that it achieves consistency, non-interruption, and efficiency with negligible overhead.
{"title":"NetCP: Consistent, Non-Interruptive and Efficient Checkpointing and Rollback of SDN","authors":"Ye Yu, Chen Qian, Wenfei Wu, Ying Zhang","doi":"10.1109/IWQoS.2018.8624142","DOIUrl":"https://doi.org/10.1109/IWQoS.2018.8624142","url":null,"abstract":"Network failures are inevitable due to its increasing complexity, which significantly hampers system availability and performance. While adopting checkpointing and rollback recovery protocols (C/R for abbreviation) from distributed systems into computer networks is promising, several specific challenges appear as we design a C/R system for Software-Defined Networks (SDN). The C/R should be coordinated with other applications in the SDN controller, each individual switch C/R should not interrupt traffic traversing it, and SDN controller C/R faces the challenge of time and space overhead. We propose a C/R framework for SDN, named NetCP. NetCP coordinates C/R and other applications to get consistent global checkpoints, it leverages redundant forwarding tables in SDN switches for C/R so as to avoid interrupting traversing traffic, and it analyzes the dependencies between controller applications to make minimal C/R decision. We have implemented NetCP in a prototype system using the current standard SDN tools and demonstrate that it achieves consistency, non-interruption, and efficiency with negligible overhead.","PeriodicalId":222290,"journal":{"name":"2018 IEEE/ACM 26th International Symposium on Quality of Service (IWQoS)","volume":"50 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2018-06-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"125956079","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Pub Date : 2018-06-01DOI: 10.1109/IWQoS.2018.8624163
Danilo Cerović, Valentin Del Piccolo, Ahmed Amamou, K. Haddadou
TRILL is a Layer 2 protocol which allows the establishment of a layer 2 mesh network while improving infrastructure utilization in comparison with Ethernet. Indeed, TRILL does not use STP and keeps all links active. It always uses the shortest path between any two nodes and can dispatch the flows following ECMP. However, the problem is that throughput wise the performances of TRILL are not on par with Ethernet. This is the consequence of the fact that Linux does not have a fast path solution for TRILL and, moreover, the fact that CPU and memory resources have to be used in order to process the frames. The goal of this paper is to propose a fast path solution for TRILL that is based on a smart NIC. We experimented with our solution and the results show that we successfully increased the throughput of TRILL by 100%, thus reaching the network interface limit of 10Gbps while reducing latency.
{"title":"Improving TRILL Mesh Network's Throughput Using Smart NICs","authors":"Danilo Cerović, Valentin Del Piccolo, Ahmed Amamou, K. Haddadou","doi":"10.1109/IWQoS.2018.8624163","DOIUrl":"https://doi.org/10.1109/IWQoS.2018.8624163","url":null,"abstract":"TRILL is a Layer 2 protocol which allows the establishment of a layer 2 mesh network while improving infrastructure utilization in comparison with Ethernet. Indeed, TRILL does not use STP and keeps all links active. It always uses the shortest path between any two nodes and can dispatch the flows following ECMP. However, the problem is that throughput wise the performances of TRILL are not on par with Ethernet. This is the consequence of the fact that Linux does not have a fast path solution for TRILL and, moreover, the fact that CPU and memory resources have to be used in order to process the frames. The goal of this paper is to propose a fast path solution for TRILL that is based on a smart NIC. We experimented with our solution and the results show that we successfully increased the throughput of TRILL by 100%, thus reaching the network interface limit of 10Gbps while reducing latency.","PeriodicalId":222290,"journal":{"name":"2018 IEEE/ACM 26th International Symposium on Quality of Service (IWQoS)","volume":"13 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2018-06-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"129984580","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Pub Date : 2018-06-01DOI: 10.1109/IWQoS.2018.8624188
Chuwen Zhang, Yong Feng, Haoyu Song, Ying Wan, Wenquan Xu, Yilun Wang, Huichen Dai, Y. Li, B. Lin
Software-based IP route lookup is one of the key components in Software Defined Networks. To address challenges on density, power and cost, Commodity CPU is preferred over other platforms to run lookup algorithms. As network functions become richer and more dynamic, route updates are more frequent. Unfortunately, previous works put less effort on fast incremental updates. On the other hand, The cache in CPU could be a performance limiter due to its small size, which requires algorithm designers to give high priority on storage efficiency in addition to time complexity. In this paper, we propose a new route lookup algorithm, OBMA, which improves update performance and storage efficiency while maintaining high lookup speed. The extensive experiments over real-word traces show that OBMA reduces the memory footprint to just 4.52 bytes/prefix, supports update speed up to 7.2 M/s which is 12.5 times faster than the state-of-the-art algorithm Poptrie. Besides, OBMA achieves up to 195.87 Mpps lookup speed with a single thread. Tests on comprehensive performance of lookup and update show that OBMA can sustain high lookup speed with update speed increasing.
{"title":"OBMA: Minimizing Bitmap Data Structure with Fast and Uninterrupted Update Processing","authors":"Chuwen Zhang, Yong Feng, Haoyu Song, Ying Wan, Wenquan Xu, Yilun Wang, Huichen Dai, Y. Li, B. Lin","doi":"10.1109/IWQoS.2018.8624188","DOIUrl":"https://doi.org/10.1109/IWQoS.2018.8624188","url":null,"abstract":"Software-based IP route lookup is one of the key components in Software Defined Networks. To address challenges on density, power and cost, Commodity CPU is preferred over other platforms to run lookup algorithms. As network functions become richer and more dynamic, route updates are more frequent. Unfortunately, previous works put less effort on fast incremental updates. On the other hand, The cache in CPU could be a performance limiter due to its small size, which requires algorithm designers to give high priority on storage efficiency in addition to time complexity. In this paper, we propose a new route lookup algorithm, OBMA, which improves update performance and storage efficiency while maintaining high lookup speed. The extensive experiments over real-word traces show that OBMA reduces the memory footprint to just 4.52 bytes/prefix, supports update speed up to 7.2 M/s which is 12.5 times faster than the state-of-the-art algorithm Poptrie. Besides, OBMA achieves up to 195.87 Mpps lookup speed with a single thread. Tests on comprehensive performance of lookup and update show that OBMA can sustain high lookup speed with update speed increasing.","PeriodicalId":222290,"journal":{"name":"2018 IEEE/ACM 26th International Symposium on Quality of Service (IWQoS)","volume":"11 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2018-06-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"130046133","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Pub Date : 2018-06-01DOI: 10.1109/IWQoS.2018.8624182
Kun Huang, Zhaohua Wang
Name prefix lookup is a core function in Named Data Networking (NDN). It is challenging to perform high-speed name-based longest prefix match lookups against a large amount of variable-length, hierarchical name prefixes in NDN. However, prior work concentrates on software-based name prefix lookup, and can't satisfy the scalability demands of high-speed lookups, low memory cost, and fast incremental updates. In this paper, we propose a hybrid approach to scalable name prefix lookup with hardware and software. We propose SACS, a shape and content search framework with ternary content addressable memories (TCAMs) and static random memory access memories (SRAMs). SACS aims to achieve high-speed lookups and low memory cost, while sustaining fast incremental updates. In SACS, a TCAM-based shape search module is first used to determine a subset of possible matching prefixes, and then a SRM-based content search module is used on the subset to find the longest matching prefix. For SACS, we propose a first shrinking least load algorithm to pack large amounts of shapes of name prefixes in a small TCAM. A shape of a name prefix is a sequence of its component lengths. We also propose a dual fingerprint-based hash table to improve the content search performance in SRAMs. Experimental results demonstrate that SACS outperforms state-of-the-art schemes by achieving up to 2.4X higher lookup throughput, up to 53% lower memory cost, and up to 96% higher insert throughput.
名称前缀查找是NDN (Named Data Networking)的核心功能。在NDN中，针对大量变长、分层的名称前缀执行高速的基于名称的最长前缀匹配查找是一项挑战。然而，先前的工作主要集中在基于软件的名称前缀查找上，不能满足高速查找、低内存成本和快速增量更新的可伸缩性需求。在本文中，我们提出了一种基于硬件和软件的可扩展名称前缀查找的混合方法。我们提出了SACS，一个具有三元内容可寻址存储器(TCAMs)和静态随机存储器访问存储器(sram)的形状和内容搜索框架。SACS旨在实现高速查找和低内存成本，同时保持快速增量更新。在SACS中，首先使用基于tcam的形状搜索模块来确定可能匹配前缀的子集，然后在该子集上使用基于srm的内容搜索模块来查找最长匹配前缀。对于SACS，我们提出了一种压缩最小负载算法，在一个小的TCAM中封装大量形状的名称前缀。名称前缀的形状是其组件长度的序列。我们还提出了一种基于双指纹的哈希表来提高ram的内容搜索性能。实验结果表明，SACS通过实现高达2.4倍的查找吞吐量，高达53%的内存成本和高达96%的插入吞吐量，优于最先进的方案。
{"title":"A Hybrid Approach to Scalable Name Prefix Lookup","authors":"Kun Huang, Zhaohua Wang","doi":"10.1109/IWQoS.2018.8624182","DOIUrl":"https://doi.org/10.1109/IWQoS.2018.8624182","url":null,"abstract":"Name prefix lookup is a core function in Named Data Networking (NDN). It is challenging to perform high-speed name-based longest prefix match lookups against a large amount of variable-length, hierarchical name prefixes in NDN. However, prior work concentrates on software-based name prefix lookup, and can't satisfy the scalability demands of high-speed lookups, low memory cost, and fast incremental updates. In this paper, we propose a hybrid approach to scalable name prefix lookup with hardware and software. We propose SACS, a shape and content search framework with ternary content addressable memories (TCAMs) and static random memory access memories (SRAMs). SACS aims to achieve high-speed lookups and low memory cost, while sustaining fast incremental updates. In SACS, a TCAM-based shape search module is first used to determine a subset of possible matching prefixes, and then a SRM-based content search module is used on the subset to find the longest matching prefix. For SACS, we propose a first shrinking least load algorithm to pack large amounts of shapes of name prefixes in a small TCAM. A shape of a name prefix is a sequence of its component lengths. We also propose a dual fingerprint-based hash table to improve the content search performance in SRAMs. Experimental results demonstrate that SACS outperforms state-of-the-art schemes by achieving up to 2.4X higher lookup throughput, up to 53% lower memory cost, and up to 96% higher insert throughput.","PeriodicalId":222290,"journal":{"name":"2018 IEEE/ACM 26th International Symposium on Quality of Service (IWQoS)","volume":"204 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2018-06-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"121170299","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Pub Date : 2018-06-01DOI: 10.1109/IWQoS.2018.8624164
Yangming Zhao, Jingyuan Fan, Huang Chen, C. Qiao
Combining Virtual Network Functions (VNF) and Software Defined Networking (SDN) enables fine-grained traffic steering to provide required network services to flows. However, online routing calculation and flow table enforcement incurs an non-negligible overhead. In this work, we propose to design a nonblocking network with fixed routing and VNF provisioning schemes to improve the network performance (e.g. the flow completion time). We first formulate this problem as a linear programming (LP) problem with infinite number of constraints, and leverage primal-dual technology to reformulate the problem as a polynomial size LP. The LP formulation is also extended to reconfigure the network when some components become unavailable, in order to keep the network nonblocking. Since solving the LP formulation is time consuming or even impossible in large scale networks, an efficient algorithm based on optimization decomposition and column generation is proposed to find a near optimal solution quickly. Simulation results show that nonblocking networks can speed up 60% of the flows by 2x, with a small increase in the required network capacity, compared with approaches that do not use the nonblocking networks.
VNF (Virtual Network Functions)和SDN (Software Defined Networking)的结合，可以实现细粒度的流量引导，为流提供所需的网络服务。然而，在线路由计算和流表强制执行会导致不可忽略的开销。在这项工作中，我们建议设计一个具有固定路由和VNF提供方案的非阻塞网络，以提高网络性能(例如流完成时间)。我们首先将该问题表述为具有无限数量约束的线性规划(LP)问题，并利用原始对偶技术将该问题重新表述为多项式大小的LP。LP公式还扩展到当某些组件不可用时重新配置网络，以保持网络的非阻塞。针对求解LP公式在大规模网络中耗时甚至不可能求解的问题，提出了一种基于优化分解和列生成的高效算法，以快速找到近最优解。仿真结果表明，与不使用非阻塞网络的方法相比，非阻塞网络可以使60%的流量加快2倍，所需的网络容量略有增加。
{"title":"Providing VNF Services with Pipe&Hose Model Based Nonblocking SDN Networks","authors":"Yangming Zhao, Jingyuan Fan, Huang Chen, C. Qiao","doi":"10.1109/IWQoS.2018.8624164","DOIUrl":"https://doi.org/10.1109/IWQoS.2018.8624164","url":null,"abstract":"Combining Virtual Network Functions (VNF) and Software Defined Networking (SDN) enables fine-grained traffic steering to provide required network services to flows. However, online routing calculation and flow table enforcement incurs an non-negligible overhead. In this work, we propose to design a nonblocking network with fixed routing and VNF provisioning schemes to improve the network performance (e.g. the flow completion time). We first formulate this problem as a linear programming (LP) problem with infinite number of constraints, and leverage primal-dual technology to reformulate the problem as a polynomial size LP. The LP formulation is also extended to reconfigure the network when some components become unavailable, in order to keep the network nonblocking. Since solving the LP formulation is time consuming or even impossible in large scale networks, an efficient algorithm based on optimization decomposition and column generation is proposed to find a near optimal solution quickly. Simulation results show that nonblocking networks can speed up 60% of the flows by 2x, with a small increase in the required network capacity, compared with approaches that do not use the nonblocking networks.","PeriodicalId":222290,"journal":{"name":"2018 IEEE/ACM 26th International Symposium on Quality of Service (IWQoS)","volume":"74 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2018-06-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"131602174","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Pub Date : 2018-06-01DOI: 10.1109/IWQoS.2018.8624124
Chang Liu, Zigang Cao, G. Xiong, Gaopeng Gou, S. Yiu, Longtao He
With the explosion of network applications, network anomaly detection and security management face a big challenge, of which the first and a fundamental step is traffic classification. However, for the sake of user privacy, encrypted communication protocols, e.g. the SSL/TLS protocol, are extensively used, which results in the ineffectiveness of traditional rule-based classification methods. Existing methods cannot have a satisfactory accuracy of encrypted traffic classification because of insufficient distinguishable characteristics. In this paper, we propose the Multi-attribute Markov Probability Fingerprints (MaMPF), for encrypted traffic classification. The key idea behind MaMPF is to consider multi-attributes, which includes a critical feature, namely “length block sequence” that captures the time-series packet lengths effectively using power-law distributions and relative occurrence probabilities of all considered applications. Based on the message type and length block sequences, Markov models are trained and the probabilities of all the applications are concatenated as the fingerprints for classification. MaMPF achieves 96.4% TPR and 0.2% FPR performance on a real-world dataset from campus network (including 950,000+ encrypted traffic flows and covering 18 applications), and outperforms the state-of-the-art methods.
{"title":"MaMPF: Encrypted Traffic Classification Based on Multi-Attribute Markov Probability Fingerprints","authors":"Chang Liu, Zigang Cao, G. Xiong, Gaopeng Gou, S. Yiu, Longtao He","doi":"10.1109/IWQoS.2018.8624124","DOIUrl":"https://doi.org/10.1109/IWQoS.2018.8624124","url":null,"abstract":"With the explosion of network applications, network anomaly detection and security management face a big challenge, of which the first and a fundamental step is traffic classification. However, for the sake of user privacy, encrypted communication protocols, e.g. the SSL/TLS protocol, are extensively used, which results in the ineffectiveness of traditional rule-based classification methods. Existing methods cannot have a satisfactory accuracy of encrypted traffic classification because of insufficient distinguishable characteristics. In this paper, we propose the Multi-attribute Markov Probability Fingerprints (MaMPF), for encrypted traffic classification. The key idea behind MaMPF is to consider multi-attributes, which includes a critical feature, namely “length block sequence” that captures the time-series packet lengths effectively using power-law distributions and relative occurrence probabilities of all considered applications. Based on the message type and length block sequences, Markov models are trained and the probabilities of all the applications are concatenated as the fingerprints for classification. MaMPF achieves 96.4% TPR and 0.2% FPR performance on a real-world dataset from campus network (including 950,000+ encrypted traffic flows and covering 18 applications), and outperforms the state-of-the-art methods.","PeriodicalId":222290,"journal":{"name":"2018 IEEE/ACM 26th International Symposium on Quality of Service (IWQoS)","volume":"52 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2018-06-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"127669228","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Pub Date : 2018-06-01DOI: 10.1109/IWQoS.2018.8624150
S. Sundar, J. Champati, B. Liang
We study task scheduling and offloading in a cloud computing system with multiple users, where tasks have different processing times, release times, communication times, and weights. Each user may schedule a task locally or offload it to a finite-capacity shared cloud with heterogeneous processors by paying a price for the resource usage. Our work aims at identifying a task scheduling decision that minimizes the weighted sum completion time of all tasks, while satisfying the users' budget constraints. We propose an efficient solution framework for this NP-hard problem. As a first step, we solve an integer-relaxed problem and use a rounding technique to obtain an integer solution that is a constant factor approximation to the minimum weighted sum completion time. This solution violates the budget constraints, but the average budget violation decreases as the number of users increases. Thus, we develop a scalable Single-Task Unload for Budget Resolution (STUBR) algorithm, which resolves budget violations and orders the tasks to reduce the weighted sum completion time. Our trace-driven simulation shows that STUBR exhibits robust performance under practical scenarios and outperforms several alternatives.
{"title":"Completion Time Minimization in Multi-User Task Scheduling with Heterogeneous Processors and Budget Constraints","authors":"S. Sundar, J. Champati, B. Liang","doi":"10.1109/IWQoS.2018.8624150","DOIUrl":"https://doi.org/10.1109/IWQoS.2018.8624150","url":null,"abstract":"We study task scheduling and offloading in a cloud computing system with multiple users, where tasks have different processing times, release times, communication times, and weights. Each user may schedule a task locally or offload it to a finite-capacity shared cloud with heterogeneous processors by paying a price for the resource usage. Our work aims at identifying a task scheduling decision that minimizes the weighted sum completion time of all tasks, while satisfying the users' budget constraints. We propose an efficient solution framework for this NP-hard problem. As a first step, we solve an integer-relaxed problem and use a rounding technique to obtain an integer solution that is a constant factor approximation to the minimum weighted sum completion time. This solution violates the budget constraints, but the average budget violation decreases as the number of users increases. Thus, we develop a scalable Single-Task Unload for Budget Resolution (STUBR) algorithm, which resolves budget violations and orders the tasks to reduce the weighted sum completion time. Our trace-driven simulation shows that STUBR exhibits robust performance under practical scenarios and outperforms several alternatives.","PeriodicalId":222290,"journal":{"name":"2018 IEEE/ACM 26th International Symposium on Quality of Service (IWQoS)","volume":"100 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2018-06-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"132387259","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Pub Date : 2018-04-19DOI: 10.1109/IWQoS.2018.8624129
Matteo Grandi, D. Camps-Mur, A. Betzler, Joan Josep Aleixendri, Miguel Catalan-Cid
In this paper we present SWAM, a system that builds on commodity Wi-Fi routers with multiple wireless interfaces to provide a wireless access infrastructure supporting multi-tenancy, mobility, and integrated wireless access and backhaul. An infrastructure provider can deploy inexpensive SWAM nodes to cover a given geographical area providing on-demand connectivity for Mobile Network Operators. Our main contribution is the design of the SWAM datapath and control plane, which are inspired by the overlay techniques used to enable multi-tenancy in data-center networks. We prototype SWAM in an office wireless testbed and validate experimentally its functionality.
{"title":"SWAM: SDN-Based Wi-Fi Small Cells with Joint Access-Backhaul and Multi-Tenant Capabilities","authors":"Matteo Grandi, D. Camps-Mur, A. Betzler, Joan Josep Aleixendri, Miguel Catalan-Cid","doi":"10.1109/IWQoS.2018.8624129","DOIUrl":"https://doi.org/10.1109/IWQoS.2018.8624129","url":null,"abstract":"In this paper we present SWAM, a system that builds on commodity Wi-Fi routers with multiple wireless interfaces to provide a wireless access infrastructure supporting multi-tenancy, mobility, and integrated wireless access and backhaul. An infrastructure provider can deploy inexpensive SWAM nodes to cover a given geographical area providing on-demand connectivity for Mobile Network Operators. Our main contribution is the design of the SWAM datapath and control plane, which are inspired by the overlay techniques used to enable multi-tenancy in data-center networks. We prototype SWAM in an office wireless testbed and validate experimentally its functionality.","PeriodicalId":222290,"journal":{"name":"2018 IEEE/ACM 26th International Symposium on Quality of Service (IWQoS)","volume":"112 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2018-04-19","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"131677805","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
京公网安备 11010802042870号
京ICP备2023020795号-1
扫码关注我们
求助内容：
应助结果提醒方式：