Of Rostock University DuDE: A D istributed Computing System u sing a D ecentralized P2P E nvironment The 4th International Workshop on Architectures, Services.

Slides:



Advertisements
Similar presentations
Cultural Heritage in REGional NETworks REGNET Project Meeting Content Group
Advertisements

A P2P-based Storage Platform for Storing Session Data in Internet Access Networks T. Bahls, D. Duchow Nokia Siemens Networks Broadband Access Division.
Muse confidential Broadband Europe 2007 We3A.4 Document:Emulation and Simulation Tool for Design and Optimization of IMS based FMC Networks Date:
Lecture 1: History of Operating System
Network Coding for Large Scale Content Distribution Christos Gkantsidis Georgia Institute of Technology Pablo Rodriguez Microsoft Research IEEE INFOCOM.
70-290: MCSE Guide to Managing a Microsoft Windows Server 2003 Environment Chapter 11: Monitoring Server Performance.
A Routing Control Platform for Managing IP Networks Jennifer Rexford Princeton University
Hyper-Threading Neil Chakrabarty William May. 2 To Be Tackled Review of Threading Algorithms Hyper-Threading Concepts Hyper-Threading Architecture Advantages/Disadvantages.
Implementation of Distributed Air Traffic Control Simulator Ranko Radovanović, Miloš Cvetanović, Zaharije Radivojević School of Electrical Engineering,
Mobility in the Virtual Office: A Document-Centric Workflow Approach Ralf Carbon, Gregor Johann, Thorsten Keuler, Dirk Muthig, Matthias Naab, Stefan Zilch.
1 Energy Efficient Communication in Wireless Sensor Networks Yingyue Xu 8/14/2015.
U NIVERSITY OF M ASSACHUSETTS, A MHERST Department of Computer Science Black-box and Gray-box Strategies for Virtual Machine Migration Timothy Wood, Prashant.
Computer System Lifecycle Chapter 1. Introduction Computer System users, administrators, and designers are all interested in performance evaluation. Whether.
Can Network Coding Help in P2P Networks? Dah Ming Chiu, Raymond W Yeung, Jiaqing Huang and Bin Fan Chinese University of Hong Kong Presented by Arjumand.
PROOF: the Parallel ROOT Facility Scheduling and Load-balancing ACAT 2007 Jan Iwaszkiewicz ¹ ² Gerardo Ganis ¹ Fons Rademakers ¹ ¹ CERN PH/SFT ² University.
Abstract Load balancing in the cloud computing environment has an important impact on the performance. Good load balancing makes cloud computing more.
Research on cloud computing application in the peer-to-peer based video-on-demand systems Speaker : 吳靖緯 MA0G rd International Workshop.
Introduction to HP LoadRunner Getting Familiar with LoadRunner >>>>>>>>>>>>>>>>>>>>>>
COLLABORATIVE EXECUTION ENVIRONMENT FOR HETEROGENEOUS PARALLEL SYSTEMS Aleksandar Ili´c, Leonel Sousa 2010 IEEE International Symposium on Parallel & Distributed.
SEDA: An Architecture for Well-Conditioned, Scalable Internet Services
Operating Systems.  Operating System Support Operating System Support  OS As User/Computer Interface OS As User/Computer Interface  OS As Resource.
Designing and Evaluating Parallel Programs Anda Iamnitchi Federated Distributed Systems Fall 2006 Textbook (on line): Designing and Building Parallel Programs.
Lecture 8: Design of Parallel Programs Part III Lecturer: Simon Winberg.
CS 1308 Computer Literacy and the Internet. Introduction  Von Neumann computer  “Naked machine”  Hardware without any helpful user-oriented features.
Monitoring for network security and management Cyber Solutions Inc.
Performance Tuning on Multicore Systems for Feature Matching within Image Collections Xiaoxin Tang*, Steven Mills, David Eyers, Zhiyi Huang, Kai-Cheung.
11 SYSTEM PERFORMANCE IN WINDOWS XP Chapter 12. Chapter 12: System Performance in Windows XP2 SYSTEM PERFORMANCE IN WINDOWS XP  Optimize Microsoft Windows.
MapReduce: Simplified Data Processing on Large Clusters Jeffrey Dean and Sanjay Ghemawat.
70-290: MCSE Guide to Managing a Microsoft Windows Server 2003 Environment, Enhanced Chapter 11: Monitoring Server Performance.
◦ What is an Operating System? What is an Operating System? ◦ Operating System Objectives Operating System Objectives ◦ Services Provided by the Operating.
Module 10: Monitoring ISA Server Overview Monitoring Overview Configuring Alerts Configuring Session Monitoring Configuring Logging Configuring.
©NEC Laboratories America 1 Huadong Liu (U. of Tennessee) Hui Zhang, Rauf Izmailov, Guofei Jiang, Xiaoqiao Meng (NEC Labs America) Presented by: Hui Zhang.
1 Wenguang WangRichard B. Bunt Department of Computer Science University of Saskatchewan November 14, 2000 Simulating DB2 Buffer Pool Management.
1 EnviroStore: A Cooperative Storage System for Disconnected Operation in Sensor Networks Liqian Luo, Chengdu Huang, Tarek Abdelzaher John Stankovic INFOCOM.
Monitoring Windows Server 2012
Eneryg Efficiency for MapReduce Workloads: An Indepth Study Boliang Feng Renmin University of China Dec 19.
Cracow Grid Workshop October 2009 Dipl.-Ing. (M.Sc.) Marcus Hilbrich Center for Information Services and High Performance.
Super computers Parallel Processing By Lecturer: Aisha Dawood.
70-290: MCSE Guide to Managing a Microsoft Windows Server 2003 Environment, Enhanced Chapter 11: Monitoring Server Performance.
Peer-Assisted Content Distribution Pablo Rodriguez Christos Gkantsidis.
1 An Adaptive File Distribution Algorithm for Wide Area Network Takashi Hoshino, Kenjiro Taura, Takashi Chikayama University of Tokyo.
11 CLUSTERING AND AVAILABILITY Chapter 11. Chapter 11: CLUSTERING AND AVAILABILITY2 OVERVIEW  Describe the clustering capabilities of Microsoft Windows.
Module 10: Preparing to Monitor Server Performance.
Compiler and Runtime Support for Enabling Generalized Reduction Computations on Heterogeneous Parallel Configurations Vignesh Ravi, Wenjing Ma, David Chiu.
Distributed System Services Fall 2008 Siva Josyula
Network design Topic 6 Testing and documentation.
1 Process Description and Control Chapter 3. 2 Process A program in execution An instance of a program running on a computer The entity that can be assigned.
Data Consolidation: A Task Scheduling and Data Migration Technique for Grid Networks Author: P. Kokkinos, K. Christodoulopoulos, A. Kretsis, and E. Varvarigos.
A Blackboard-Based Learning Intrusion Detection System: A New Approach
Cluster computing. 1.What is cluster computing? 2.Need of cluster computing. 3.Architecture 4.Applications of cluster computing 5.Advantages of cluster.
DataTAG is a project funded by the European Union International School on Grid Computing, 23 Jul 2003 – n o 1 GridICE The eyes of the grid PART I. Introduction.
7.1 Operating Systems. 7.2 A computer is a system composed of two major components: hardware and software. Computer hardware is the physical equipment.
LIOProf: Exposing Lustre File System Behavior for I/O Middleware
MPLS Introduction How MPLS Works ?? MPLS - The Motivation MPLS Application MPLS Advantages Conclusion.
Geethanjali College Of Engineering and Technology Cheeryal( V), Keesara ( M), Ranga Reddy District. I I Internal Guide Mrs.CH.V.Anupama Assistant Professor.
The Biologically Inspired Distributed File System: An Emergent Thinker Instantiation Presented by Dr. Ying Lu.
Accelerating Peer-to-Peer Networks for Video Streaming
Deploy Containerized OPNFV Cluster Efficiently Using Daisy Installer
Software Architecture in Practice
Parallel Programming By J. H. Wang May 2, 2017.
Characterization of Parallel Scientific Simulations
Parallel Programming in C with MPI and OpenMP
湖南大学-信息科学与工程学院-计算机与科学系
Secure Access Node: An FPGA-based Security Architecture for Access Networks The Sixth International Conference on Internet Monitoring and Protection (ICIMP.
MapReduce: Data Distribution for Reduce
A Configurable FPGA-Based Traffic Generator for High-Performance Tests of Packet Processing Systems The Sixth International Conference on Internet Monitoring.
Operating System Introduction.
ContinuStreaming: Achieving High Playback Continuity of Gossip-based Peer-to-Peer Streaming IPDPS 2008 LI Zhenhua Dept. Computer, Nanjing University.
Presentation transcript:

of Rostock University DuDE: A D istributed Computing System u sing a D ecentralized P2P E nvironment The 4th International Workshop on Architectures, Services and Applications for the Next Generation Internet (WASA-NGI-IV) Bonn, Germany, October 4th, 2011 J. Skodzik, P. Danielis, V. Altmann, J. Rohrbeck, D. Timmermann University of Rostock, Germany Institute of Applied Microelectronics and Computer Engineering T. Bahls, D. Duchow Nokia Siemens Networks Broadband Access Division Greifswald, Germany

Outline Introduction & Motivation DuDE in General The DuDE Algorithm in Detail Test Scenario and Evaluation Summary and Future Work 2

Increasing number of Internet users and traffic data Internet Service Providers (ISPs) want to ensure: Quality of Service (QoS) The detection of bottlenecks The detection of attacks How to ensure these issues?  Statistics generated from existing log data Situation today 3 Does an AN have enough resources? Does it provide sufficient statistics at all?

60% Introduction & Motivation 4 CPU MEM Resources utilization

Simple support of new statistics types Simultaneous computation of multiple statistics Processing of increasing log data volumes Processor utilization RAM utilization Drops Number of packets Short term statistics (STS) for single ANs Supported Introduction & Motivation 5 Not supported Long term statistics (LTS) Creation of global statistics

One AN does not have enough hardware ressources  Usage of multiple ANs to compute statistics Efficient resource sharing with high resilience and scalability  Utilization of P2P technology DuDE: Exploitation of already available resources  No extra costs for additional equipment Introduction & Motivation 6

DuDE in General Logical P2P ring ID 7 Node1 Node2 Node4 Node3

DuDE in General 8 Log data (some hundreds of KBs) 8 Data chunk (ca. 100 KBs)

DuDE in General Objective: High log data availability = % Simple replication wastes memory ressources  Reed-Solomon Codes Split log data of each AN into m data chunks 9

DuDE in General Objective: High log data availability = % Simple replication wastes memory ressources  Reed-Solomon Codes Split log data of each AN into m data chunks Encoding: Add k interleaved coding chunks  n=m+k chunks 10

DuDE in General Objective: High log data availability = % Simple replication wastes memory ressources  Reed-Solomon Codes Split log data of each AN into m data chunks Encoding: Add k interleaved coding chunks  n=m+k chunks Decoding: Restore log data from any m of n chunks 11

DuDE in General 12 Log data (some hundreds of KBs) Data chunk (ca. 100 KBs) How to apply our application to P2P?

Task Job = collection of STS and/or LTS tasks Task = part of job, e.g., request for „CPU“ statistics Jobscheduler (JS): Reception and monitoring of job Taskwatcher (TW): Reception and processing of task DuDE in General 13 Admin. Job Which steps are necessary to compute statistics?

60% 50% 30% 10% The DuDE Algorithm in Detail Stage 1: Resource collection 14 Admin. … Job … Task … Log data … Global statistics

The DuDE Algorithm in Detail 1. Resource collection 15 Admin. Stage 2: Jobscheduler determination … Job … Task … Log data … Global statistics

The DuDE Algorithm in Detail 16 Admin. 2. Jobscheduler determination Stage 3: Resource re-collection 1. Resource collection … Job … Task … Log data … Global statistics

The DuDE Algorithm in Detail 17 Admin. 3. Resource re-collection Stage 4: Task assignment 2. Jobscheduler determination 1. Resource collection Request for Processor utilization STS Request for RAM utilization LTS Request for Drops LTS … Job … Task … Log data … Global statistics

The DuDE Algorithm in Detail … Job … Task … Log data … Global statistics 18 Admin. 3. Resource re-collection Stage 4: Task assignment 2. Jobscheduler determination 1. Resource collection How to find all log data for global statistics computation?

Node1 Node2 Node3 Node5 no The DuDE Algorithm in Detail Request for global statistics  All data needed ID Taskwatcher iSucc?NN >=AID yes no yes Node1 Node2 Node3 Node4 Node5 Algorithm is done Global Peer Data Discovery Algorithm - Threshold value A = 2 Algorithm is done 5yes0no Node5 61no Node6 7yes2 Node7 19

The DuDE Algorithm in Detail 20 Admin. 4. Task assignment Stage 5: Log data collection 3. Resource re-collection 2. Jobscheduler determination 1. Resource collection … Job … Task … Log data … Global statistics

The DuDE Algorithm in Detail 21 Admin. 5. Log data collection 4. Task assignment 3. Resource re-collection 2. Jobscheduler determination 1. Resource collection Stage 6: Statistics computation Processor utilization stat. RAM utilization stat. Drops stat. … Job … Task … Log data … Global statistics

The DuDE Algorithm in Detail 22 Admin. 5. Log data collection 4. Task assignment 3. Resource re-collection 2. Jobscheduler determination 1. Resource collection Stage 7: Send results and display them 6. Statistics computation Admin. … Job … Task … Log data … Global statistics

The DuDE Algorithm in Detail 23 Admin. 5. Restore log data 4. Assign tasks 3. Resource recollection 2. Determine job scheduler 1. Resource collection Stage 7: Send results and display them 6. Compute statistics Admin. … Job … Task … Log data … Global statistics

Test Scenario and Evaluation 24 PC Configuration Pentium 4 (1.5 GHz) 512 MB RAM  Equivalent to AN HW

Test Scenario and Evaluation Parameters: Number of tasks inside job Number of log data sets in the P2P network Computational load for statistics computation Measurements: Time for finishing a job Memory utilization 25

Test Scenario and Evaluation 26 Linear Increase of Needed Time  Time is Constant

Test Scenario and Evaluation 27 Linear Increase of Needed Time  Time is Constant

Test Scenario and Evaluation Linear Increase of Memory Utilization  Constant Memory Utilization 28

Test Scenario and Evaluation Memory utilization increases more at the single AN than at the taskwatcher 29

Test Scenario and Evaluation Memory utilization is constant and independent of the computational load 30

Summary and Future work P2P-based system for distributed computing of statistics STS and LTS Statistics for a single AN and the whole network Global Peer Data Discovery Algorithm Successfully developed prototype (demo session) Investigation of further use cases 31

Thanks for your attention! Questions? 32