2018 IEEE 24th International Conference on Parallel and Distributed Systems (ICPADS)最新文献

{"title":"How Does the Workload Look Like in Production Cloud? Analysis and Clustering of Workloads on Alibaba Cluster Trace","authors":"Wenyan Chen, Kejiang Ye, Yang Wang, Guoyao Xu, Chengzhong Xu","doi":"10.1109/PADSW.2018.8644579","DOIUrl":"https://doi.org/10.1109/PADSW.2018.8644579","url":null,"abstract":"Cloud computing technology is widely used in today's datacenters due to the benefits such as high scalability, on-demand services and low cost. An in-depth understanding of the characteristics of workloads running in production cloud environments is very important for improving the resource management efficiency. In this paper, we make a detailed analysis with visualization techniques and clustering methods on the trace dataset released by Alibaba which contains 11089 online services and 12951 batch jobs running on 1313 machines. Our methodology for clustering workloads contains: i) Select effective feature vectors as the dimensions of clustering; ii) Identify the cluster boundaries of each dimension using K-Means algorithm; iii) Classify jobs by combining the feature vectors which uses the results from previous step; iv) Analyze the characteristics of workload groups at runtime. Our analysis reveals several insights which previous work has not found on Alibaba cluster trace. For batch jobs: a) Average CPU cores of all batch jobs show bimodal-distribution obviously. b) At a random sampling time, more than 50 % machines only run one group of jobs with a short duration, medium CPU cores and small memory utilization, the remaining machines run mixed groups of jobs. For online instances: a) The resource usage (CPU, Memory, and Disk) of most online instances is low; b) There are up to six groups running on the same machine according to our clustering method at a random sampling time.","PeriodicalId":361947,"journal":{"name":"2018 IEEE 24th International Conference on Parallel and Distributed Systems (ICPADS)","volume":"127 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2018-12-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"123085173","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}

{"title":"UpPreempt: A Fine-Grained Preemptive Scheduling Strategy for Container-Based Clusters","authors":"D. Zou, Shiyou Qian, Guangtao Xue, Jian Cao, Jiadi Yu, Yanmin Zhu, Minglu Li, Wenjuan Li","doi":"10.1109/PADSW.2018.8644608","DOIUrl":"https://doi.org/10.1109/PADSW.2018.8644608","url":null,"abstract":"A distributed cluster provides a common computation platform to efficiently run different types of jobs, such as real-time and batch jobs that have different QoS requirements. One challenge of a distributed cluster is to find a scheduling strategy that can reduce the overtime ratio of real-time jobs as much as possible while also improving the completion time of batch jobs, aiming to promote QoS even though the resources in the cluster are stretched. To address this issue, many efficient scheduling methods have been proposed. However, most existing approaches are naive and coarse-grained in means of either killing batch jobs to preempt resources for real-time jobs or reserving some resources in advance for real-time jobs to minimize the overtime ratio of real-time jobs, which prolongs the completion time of batch jobs and reduces the resource utilization of the cluster. In this paper, we propose UpPreempt, a fine-grained preemptive scheduling strategy for container-based clusters. When scheduling real-time jobs, UpPreempt considers the deadline of jobs and the resource usage of existing batch jobs. Performing resource preemption from multiple batch jobs is the basic idea of UpPreempt. The set of batch jobs to be preempted and the amount of resources taken from each job are finely determined. In this way, UpPreempt greatly alleviates the effect of preemption on the batch jobs in terms of completion time and avoids reserving resources for real-time jobs. We implement UpPreempt in YARN to evaluate its performance. The evaluation with various workloads shows that our proposed scheduling strategy can achieve a good trade-off between the overtime ratio of real-time jobs and the completion time of batch jobs without reducing the resource utilization of the cluster.","PeriodicalId":361947,"journal":{"name":"2018 IEEE 24th International Conference on Parallel and Distributed Systems (ICPADS)","volume":"111 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2018-12-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"116111843","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}

{"title":"Statistical Monitoring for NVM Write","authors":"Yijie Mei, Kaixin Huang, Yanmin Zhu, Linpeng Huang","doi":"10.1109/PADSW.2018.8644629","DOIUrl":"https://doi.org/10.1109/PADSW.2018.8644629","url":null,"abstract":"Emerging non-volatile memory (NVM) technologies promise persistence, byte-addressability, low power consumption and high density. The potential of NVM implies that it can improve persistence performance and availability for high-performance computing tasks in data centers. However, NVM suffers from limited write endurance; skewed writes can extremely curtail the lifetime of NVM. Although several wear-leveling algorithms have been proposed to address the wear-out problem, based on estimation of write counts, they come with limitations in accuracy and compatibility with existing hardware and softwares. In this paper, we propose several software-based ways of monitoring NVM writes and obtaining the write counts, which are more accurate and non-intrusive for existing programs. We compare our proposed monitoring approaches in the aspects of granularity and portability; we conduct extensive experiments to evaluate them and the results show that our proposed methods can obtain good accuracy with an affordable time overhead.","PeriodicalId":361947,"journal":{"name":"2018 IEEE 24th International Conference on Parallel and Distributed Systems (ICPADS)","volume":"67 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2018-12-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"122330944","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}

{"title":"A Non-Intrusive Multi-Parameter Fault Diagnosis System for Industrial Machineries","authors":"Shanqing Wang, Chengpei Tang, Chancheng Zhou, Xiaolong Zheng","doi":"10.1109/PADSW.2018.8644893","DOIUrl":"https://doi.org/10.1109/PADSW.2018.8644893","url":null,"abstract":"Induction motor, especially driving motor, is the critical component for various modern industrial machineries. Fault diagnosis of induction motor is therefore a necessary and crucial task to ensure the machinery health and prevent vital damages. Conventional diagnosis methods are mainly based on intrusive sensors to measure certain physical parameters. However, intrusive sensors are costly and hard to apply to update traditional machines. In this paper, we propose EMFD, an energy-image based non-intrusive multi-parameter fault diagnosis system. We design an EMFD sensing platform to monitor the electric circuit parameters. Then we build a fault model that describes the relationships between two major kinds of faults and the electric circuit parameters. Based on the model, we propose a novel fault diagnosis algorithm that exploits a sparse auto-encoder based deep neural network. Different from the existing single-parameter methods, EMFD takes advantage of multiple circuit parameters and achieves accurate and robust diagnosis even in dynamic operating environments. We implement and deploy the proposed system in a real-world factory. The evaluation results show that EMFD can achieve the diagnosis accuracy of 96 %.","PeriodicalId":361947,"journal":{"name":"2018 IEEE 24th International Conference on Parallel and Distributed Systems (ICPADS)","volume":"14 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2018-12-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"129564445","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}

{"title":"cuBool: Bit-Parallel Boolean Matrix Factorization on CUDA-Enabled Accelerators","authors":"Robin Kobus, Adrian Lamoth, André Müller, Christian Hundt, Stefan Kramer, B. Schmidt","doi":"10.1109/PADSW.2018.8644574","DOIUrl":"https://doi.org/10.1109/PADSW.2018.8644574","url":null,"abstract":"Boolean Matrix Factorization (BMF) is a commonly used technique in the field of unsupervised data analytics. The goal is to decompose a ground truth matrix C into a product of two matrices A and $B$ being either an exact or approximate rank k factorization of C. Both exact and approximate factorization are time-consuming tasks due to their combinatorial complexity. In this paper, we introduce a massively parallel implementation of BMF - namely cuBool - in order to significantly speed up factorization of huge Boolean matrices. Our approach is based on alternately adjusting rows and columns of A and B using thousands of lightweight CUDA threads. The massively parallel manipulation of entries enables full usage of all available cores on modern CUDA-enabled GPUs. Additionally, modelling up to 32 consecutive entries of the Boolean matrices A, Band C as 32-bit integer results in fewer data accesses and faster computation of inner products. This bit-parallel approach allows for a significant decrease of memory requirements in contrast to gradient-based continuous updates of entries on dense representations. cuBool is compared to other state-of-the-art matrix factorization algorithms. Experiments on a number of real-world data sets show highly competitive results at only a fraction of computation time. cuBool proves to be a good compromise between low run time and a high-quality factorization for the decomposition of large-scale Boolean matrices. It can freely be accessed under https://github.com/funatiq/cubool.","PeriodicalId":361947,"journal":{"name":"2018 IEEE 24th International Conference on Parallel and Distributed Systems (ICPADS)","volume":"1 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2018-12-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"129777859","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}

{"title":"Energy-Efficient Core Allocation and Deployment for Container-Based Virtualization","authors":"Ching-Chi Lin, Jian-Jia Chen, Pangfeng Liu, Jan-Jan Wu","doi":"10.1109/PADSW.2018.8644537","DOIUrl":"https://doi.org/10.1109/PADSW.2018.8644537","url":null,"abstract":"Infrastructure-as-a-Service (IaaS) is a popular form of cloud computing that provides virtualized computing resources. The current trend of IaaS is moving from virtual machine-based into container-based. In this paper, we study the energy-efficient resource allocation problem for container-based virtualization in a data center. Our goal is to minimize the energy consumption by determining 1) the number of cores allocated to a container, 2) the operating frequency of the container, and 3) the deployment of the container to server. Every container has to meet its service level agreement (SLA). We propose dynamic programming algorithms that can be used under different scenarios, depending on the affordable time complexity. The performance of the proposed algorithms is evaluated with energy consumption data collected from experiments.","PeriodicalId":361947,"journal":{"name":"2018 IEEE 24th International Conference on Parallel and Distributed Systems (ICPADS)","volume":"50 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2018-12-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"124507701","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}

{"title":"Seal: Efficient Training Large Scale Statistical Machine Translation Models on Spark","authors":"Rong Gu, Min Chen, Wenjia Yang, C. Yuan, Y. Huang","doi":"10.1109/PADSW.2018.8644562","DOIUrl":"https://doi.org/10.1109/PADSW.2018.8644562","url":null,"abstract":"Statistical machine translation (SMT) is an important research branch in natural language processing (NLP). Similar to many other NLP applications, large scale training data can potentially bring higher translation accuracy for SMT models. However, the traditional single-node SMT model training systems can hardly cope with the fast-growing amount of large scale training corpus in the big data era, which makes the urgent requirement of efficient large scale machine translation model training systems. In this paper, we propose Seal, an efficient, scalable, and end-to-end offline SMT model training toolkit based on Apache Spark which is a widely-used distributed data-parallel platform. Seal parallelizes the training process of the entire three key SMT models that are the word alignment model, the translation model, and the N -Gram language model, respectively. To further improve the performance of the model training in Seal, we also propose a number of system optimization methods. In word alignment model training, by optimizing the block size tuning, the overhead of IO operation and communication is greatly reduced. In translation model training, by well encoding the training corpus, the data size transferred over the network can be reduced significantly, thus improving the overall training efficiency. We also optimize the maximum likelihood estimation (MLE) algorithm to solve the data skew issue on the join operation which is adopted both in the translation model training and the language model training. The experiment results show that Seal outperforms the well-known SMT training system Chaski with about 5x speedup for word alignment model training. For the syntactic translation model and language model training, Seal outperforms the existing cutting-edge tools with about 9~18x speedup and 8~9x speedup on average, respectively. On the whole, Seal outperforms the existing distributed system with 4~6x speedup and the single-node system with 9~60x speedup on average respectively. Besides, Seal achieves near-linear data and node scalability.","PeriodicalId":361947,"journal":{"name":"2018 IEEE 24th International Conference on Parallel and Distributed Systems (ICPADS)","volume":"20 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2018-12-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"128118500","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}

{"title":"GraphEL: A Graph-Based Ensemble Learning Method for Distributed Diagnostics and Prognostics in the Industrial Internet of Things","authors":"Chongyu Zhou, C. Tham","doi":"10.1109/PADSW.2018.8644943","DOIUrl":"https://doi.org/10.1109/PADSW.2018.8644943","url":null,"abstract":"Ensemble learning (EL)methods have been shown to be effective for diagnostics and prognostics in industrial systems. By combining the learning ability of different base learners, EL has the potential to reduce the total complexity of the learning system while solving a difficult problem satisfactorily. Recent advantages in Industrial Internet of Things (IIoT)and edge computing technologies have started a new paradigm of distributed diagnostics and prognostics. However, existing EL methods that mainly focus on a centralized setting cannot adapt to the edge computing scenario, which significantly constrains the application of these EL methods in real industrial environments. In this paper, we present a new approach to EL called Graph-based Ensemble Learning (GraphEL)to enable distributed diagnostics and prognostics in real industrial environments. Comparing with existing methods, the proposed GraphEL framework builds different base learners for different subsystems. Furthermore, a graphical model is constructed to define the correlation structures among the outputs of different base learners in the ensemble such that they can be collaboratively trained to optimize the learning performance of the ensemble. Via simple message passing, the proposed GraphEL framework can be executed in a fully distributed manner which is suitable for edge computing. The performance of the proposed GraphEL framework is evaluated using two real-world industrial data sets where we demonstrate the advantages of GraphEL compared to existing EL methods. Index Terms-Industrial Internet of Things (IIoT), smart manufacturing, diagnostics and prognostics, distributed ensemble learning.","PeriodicalId":361947,"journal":{"name":"2018 IEEE 24th International Conference on Parallel and Distributed Systems (ICPADS)","volume":"28 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2018-12-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"134000053","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}

{"title":"Parallelizing Recursive Backtracking Based Subgraph Matching on a Single Machine","authors":"Shixuan Sun, Qiong Luo","doi":"10.1109/PADSW.2018.8644869","DOIUrl":"https://doi.org/10.1109/PADSW.2018.8644869","url":null,"abstract":"We propose PSM, an algorithmic framework to parallelize a common class of subgraph matching algorithms, which are based on recursive backtracking. Specifically, we abstract the matching process as a tree search in the state space and different matching algorithms as different orders in the search. Subsequently, we parallelize such subgraph matching by dividing up the state space search tree and exploring it in parallel. Different from traditional approaches that parallelize the search by each individual state, we dynamically split the state tree into search regions each of which consist of a subtree. We further optimize PSM for load balance and communication efficiency. As case studies, we have parallelized three representative recursive backtracking based subgraph matching algorithms in PSM and studied their performance in comparison with their sequential counterparts. Our results show that the PSM -style parallel algorithms achieved a speedup of 15X-19X on the in-memory execution time on a twenty-core machine.","PeriodicalId":361947,"journal":{"name":"2018 IEEE 24th International Conference on Parallel and Distributed Systems (ICPADS)","volume":"67 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2018-12-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"130812661","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}

{"title":"Acknowledgements ICPADS 2018","authors":"","doi":"10.1109/padsw.2018.8644530","DOIUrl":"https://doi.org/10.1109/padsw.2018.8644530","url":null,"abstract":"","PeriodicalId":361947,"journal":{"name":"2018 IEEE 24th International Conference on Parallel and Distributed Systems (ICPADS)","volume":"32 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2018-12-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"128905712","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}