JuxMem: An Adaptive Supportive Platform for Data Sharing on the Grid Gabriel Antoniu, Luc Bougé, Mathieu Jan IRISA / INRIA & ENS Cachan, France Grid Data.

Slides:



Advertisements
Similar presentations
Efficient Event-based Resource Discovery Wei Yan*, Songlin Hu*, Vinod Muthusamy +, Hans-Arno Jacobsen +, Li Zha* * Chinese Academy of Sciences, Beijing.
Advertisements

Christian Delbe1 Christian Delbé OASIS Team INRIA -- CNRS - I3S -- Univ. of Nice Sophia-Antipolis November Automatic Fault Tolerance in ProActive.
P2P data retrieval DHT (Distributed Hash Tables) Partially based on Hellerstein’s presentation at VLDB2004.
High Performance Computing Course Notes Grid Computing.
Study of Hurricane and Tornado Operating Systems By Shubhanan Bakre.
Using DSVM to Implement a Distributed File System Ramon Lawrence Dept. of Computer Science
Extensible Networking Platform IWAN 2005 Extensible Network Configuration and Communication Framework Todd Sproull and John Lockwood
Distributed components
Rheeve: A Plug-n-Play Peer- to-Peer Computing Platform Wang-kee Poon and Jiannong Cao Department of Computing, The Hong Kong Polytechnic University ICDCSW.
Dynamic adaptation of parallel codes Toward self-adaptable components for the Grid Françoise André, Jérémy Buisson & Jean-Louis Pazat IRISA / INSA de Rennes.
Peer services: from Description to Invocation Manuel Oriol International Workshop on Agents and Peer-to-Peer Computing (AP2PC 2002)
Spring 2003CS 4611 Peer-to-Peer Networks Outline Survey Self-organizing overlay network File system on top of P2P network Contributions from Peter Druschel.
Chord and CFS Philip Skov Knudsen Niels Teglsbo Jensen Mads Lundemann
Efficient Content Location Using Interest-based Locality in Peer-to-Peer Systems Presented by: Lin Wing Kai.
Rutgers PANIC Laboratory The State University of New Jersey Self-Managing Federated Services Francisco Matias Cuenca-Acuna and Thu D. Nguyen Department.
1 Introduction to Load Balancing: l Definition of Distributed systems. Collection of independent loosely coupled computing resources. l Load Balancing.
1 Client-Server versus P2P  Client-server Computing  Purpose, definition, characteristics  Relationship to the GRID  Research issues  P2P Computing.
Chord-over-Chord Overlay Sudhindra Rao Ph.D Qualifier Exam Department of ECECS.
Introspective Replica Management Yan Chen, Hakim Weatherspoon, and Dennis Geels Our project developed and evaluated a replica management algorithm suitable.
Distributed Systems & Networks i206 Fall 2010 John Chuang Some slides adapted from Coulouris, Dollimore and Kindberg.
1 Peer-to-Peer Networks Outline Survey Self-organizing overlay network File system on top of P2P network Contributions from Peter Druschel.
Focus on Distributed Hash Tables Distributed hash tables (DHT) provide resource locating and routing in peer-to-peer networks –But, more than object locating.
1CS 6401 Peer-to-Peer Networks Outline Overview Gnutella Structured Overlays BitTorrent.
Middleware for P2P architecture Jikai Yin, Shuai Zhang, Ziwen Zhang.
Wide-Area Cooperative Storage with CFS Robert Morris Frank Dabek, M. Frans Kaashoek, David Karger, Ion Stoica MIT and Berkeley.
Cli/Serv.: JXTA/151 Client/Server Distributed Systems v Objective –explain JXTA, a support environment for P2P services and applications ,
RUNNING PARALLEL APPLICATIONS BEYOND EP WORKLOADS IN DISTRIBUTED COMPUTING ENVIRONMENTS Zholudev Yury.
Distributed Systems Concepts and Design Chapter 10: Peer-to-Peer Systems Bruce Hammer, Steve Wallis, Raymond Ho.
A Performance Evaluation of Azure and Nimbus Clouds for Scientific Applications Radu Tudoran KerData Team Inria Rennes ENS Cachan 10 April 2012 Joint work.
JuxMem: An Adaptive Supportive Platform for Data Sharing on the Grid Gabriel Antoniu, Luc Bougé, Mathieu Jan IRISA / INRIA & ENS Cachan, France Workshop.
Presenter: Dipesh Gautam.  Introduction  Why Data Grid?  High Level View  Design Considerations  Data Grid Services  Topology  Grids and Cloud.
LEGO – Rennes, 3 Juillet 2007 Deploying Gfarm and JXTA-based applications using the ADAGE deployment tool Landry Breuil, Loïc Cudennec and Christian Perez.
Deploying DIET and JuxMem: GoDIET + JDF Mathieu Jan PARIS Research Group IRISA INRIA & ENS Cachan / Brittany Extension Rennes Lyon, July 2004.
1 A P2P Collaborative System Using JXTA Hosei Graduation School ITPC 02R3315 Katsuhiro CHIBA.
Chord: A Scalable Peer-to-peer Lookup Protocol for Internet Applications Xiaozhou Li COS 461: Computer Networks (precept 04/06/12) Princeton University.
Peer-to-Pee Computing HP Technical Report Chin-Yi Tsai.
Large-scale Deployment in P2P Experiments Using the JXTA Distributed Framework Gabriel Antoniu, Luc Bougé, Mathieu Jan & Sébastien Monnet PARIS Research.
Peer-to-Peer Distributed Shared Memory? Gabriel Antoniu, Luc Bougé, Mathieu Jan IRISA / INRIA & ENS Cachan/Bretagne France Dagstuhl seminar, October 2003.
Programming Parallel and Distributed Systems for Large Scale Numerical Simulation Application Christian Perez INRIA researcher IRISA Rennes, France.
Februar 17, 2006GDS meeting - LIP1 MOve: an application-Malleable Overlay UIUC / INRIA Collaboration.
Introduction to DFS. Distributed File Systems A file system whose clients, servers and storage devices are dispersed among the machines of a distributed.
Building Hierarchical Grid Storage Using the GFarm Global File System and the JuxMem Grid Data-Sharing Service Gabriel Antoniu, Lo ï c Cudennec, Majd Ghareeb.
The JuxMem-Gfarm Collaboration Enhancing the JuxMem Grid Data Sharing Service with Persistent Storage Using the Gfarm Global File System Gabriel Antoniu,
A Peer-to-Peer Approach to Resource Discovery in Grid Environments (in HPDC’02, by U of Chicago) Gisik Kwon Nov. 18, 2002.
Towards high-performance communication layers for JXTA on grids Mathieu Jan GDS meeting, Lyon, 17 February 2006.
Latest news on JXTA and JuxMem-C/DIET Mathieu Jan GDS meeting, Rennes, 11 march 2005.
The Replica Location Service The Globus Project™ And The DataGrid Project Copyright (c) 2002 University of Chicago and The University of Southern California.
1 Peer-to-Peer Technologies Seminar by: Kunal Goswami (05IT6006) School of Information Technology Guided by: Prof. C.R.Mandal, School of Information Technology.
Paper Survey of DHT Distributed Hash Table. Usages Directory service  Very little amount of information, such as URI, metadata, … Storage  Data, such.
A Utility-based Approach to Scheduling Multimedia Streams in P2P Systems Fang Chen Computer Science Dept. University of California, Riverside
11 CLUSTERING AND AVAILABILITY Chapter 11. Chapter 11: CLUSTERING AND AVAILABILITY2 OVERVIEW  Describe the clustering capabilities of Microsoft Windows.
University of Pennsylvania 7/15/98 Asymmetric Bandwidth Channel (ABC) Architecture Insup Lee University of Pennsylvania July 25, 1998.
Going Large-Scale in P2P Experiments Using the JXTA Distributed Framework Mathieu Jan & Sébastien Monnet Projet PARIS Paris, 13 February 2004.
18-1 Summary (Day 2) Learning Summary – What is JXTA ? – Understand the fundamental concepts of JXTA – Learn about the various implementations of.
Peer to Peer Network Design Discovery and Routing algorithms
Making a DSM Consistency Protocol Hierarchy-Aware: An Efficient Synchronization Scheme Gabriel Antoniu, Luc Bougé, Sébastien Lacour IRISA / INRIA & ENS.
1/12 Distributed Transactional Memory for Clusters and Grids EuroTM, Paris, May 20th, 2011 Michael Schöttner.
1 VLDB - Data Management in Grids B. Del-Fabbro, D. Laiymani, J.M. Nicod and L. Philippe Laboratoire d’Informatique de l’Université de Franche-Comté Séoul,
Monitoring and Securing New Functions Deployed in a Virtualized Networking Environment Bertrand Mathieu, Guillaume Doyen, Wissam Mallouli, Thomas Silverston,
Bruce Hammer, Steve Wallis, Raymond Ho
November, 19th GDS meeting, LIP6, Paris 1 Hierarchical Synchronization and Consistency in GDS Sébastien Monnet IRISA, Rennes.
Introduction to Load Balancing:
Distributed DBMS Concepts of Distributed DBMS
University of Technology
IROP Research Presentation
Mobile P2P Data Retrieval and Caching
Chord and CFS Philip Skov Knudsen
L. Glimcher, R. Jin, G. Agrawal Presented by: Leo Glimcher
Presentation transcript:

JuxMem: An Adaptive Supportive Platform for Data Sharing on the Grid Gabriel Antoniu, Luc Bougé, Mathieu Jan IRISA / INRIA & ENS Cachan, France Grid Data Service (GDS) meeting, Rennes, September 22 th 2003

2 Context: Data Management on the Grid Distributed numerical simulations (code coupling) Needs data sharing No many functional systems Solid mechanics Thermodynamics Optics Dynamics Designing a satellite

3 Existing Data Management Systems Non-transparent large scale data management GridFTP (Globus) and MPI-IO Internet Backplane Protocol (IBP) Explicit transfert No consistency ensured Transparent small-scale data management Distributed shared memory (DSM) Consistency models and protocols Transparent access Small-scale, static and homogeneous architecture TreadMarks TM

4 Another approache: peer-to-peer systems Peer-to-peer systems (P2P) Distributed (large-scale) Volatile peers Peers have the same capacities and responsabilities Sharing of immutable data Centralized (Napster) Flooding (Gnutella, KaZaA) Distributed hash table (CFS, PAST) Sharing of mutable data One writer per data + static architecture (OceanStore) Conflicts have to be manually resolved (Ivy)

5 Design principles Proposition: data sharing service for the grid DSM systems: consistency and transparent access P2P systems: scalability and high dynamicity DSMService for the GridP2P Scale DynamicityNullMediumHigh Resource homogeneity Homogeneous (clusters) Rather heterogeneous (clusters of clusters) Heterogeneous (Internet) Data typeMutable Immutable Typical applications Scientific computation Scientific computation and data storage File sharing and storage

6 A Data Sharing Service for the Grid Internet Data transfert ? Persistent storage Transparency of localization

7 A Data Sharing Service for the Grid Data transfert Internet Optimization of access Data consistency Internet

8 A Data Sharing Service for the Grid Internet Scalability of the architecture Internet

9 A Data Sharing Service for the Grid Internet Handling volatility

10 JXTA: a framework for P2P Open-source platform for programming P2P applications Specify a set of protocols A peer Uniquely identified (ID) Address independent of the physical location Several network access point (TCP, HTTP, etc) Peer Firewall Peer TCP/IP HTTP Peer ID Firewall

11 JXTA: peer groups Set of peers that share a common set of interests Scope of communications Specific policy of management Peer group services Peer ID NetPeerGroup PeerGroupA PeerGroupB

12 JXTA: Advertisements Every resource is described by an advertisement Peers Peer groups Communication channels Services … PeerGroup Advertisement: urn:jxta: uuid- BCBCDEABDBBBABEABBBABA urn:jxta:uuid- BFEFDEDFBABAFRUDBACE My Group This group is to be used for my own testing

13 JuxMem: a prototype Peer group juxmem Peer group cluster A Peer group cluster B Peer group cluster C Peer group data Physical architecture Logical architecture

14 API of JuxMem Alloc (size, attribs) Map (id, attribs) Put (id, value) Get (id) Lock (id) Unlock (id)

15 Managing Memory Resources Peer group cluster Peer group juxmem Size 10 Memory provided Advertisement of type provider: peer group cluster Advertisement of type cluster: peer group juxmem

16 Managing Shared Data Blocks Allocation of a memory area = creation of a peer group data Data blocks identified by the ID of the peer group Advertisement published in the peer group juxmem Shared access for clients by knowing the ID Consistency Data blocks are replicated on providers Updated simultaneously (logical multicast) Clients are not notified of updates Synchronization Lock for each data block

17 Handling the Volatility of Peers A manager by peer group (cluster and data) Dynamic monitoring of available peers Data blocks are automatically replicated (data) Updates advertisement of type cluster (cluster) Volatility of managers Periodic exchange of hearbeats Dynamic replication of managers if needed on other peers

18 Implementation of JuxMem JuxMem JXTA service lines Graphical tool

19 Preliminary Evaluations Cluster PentiumII: 450 Mhz and 256 Mb of RAM Network used: FastEthernet 100 Mb/s Number of nodes used: 20 Experiments Overhead memory consumption Low:  6 % with respect to the underlying JXTA peers used Study of the volatility of providers

20 Study of the Volatility of Providers (1) Peer group juxmem Peer group cluster Peer group data Data of one byte Degree of redundancy = 3 Data manager is not killed 1 client: 100 iterations lock-put-unlock 16 providers

21 Study of the Volatility of Providers (1) Peer group juxmem Peer group cluster Peer group data 1 client: 100 iterations lock-put-unlock 16 providers Data of one byte Degree of redundancy = 3 Data manager is not killed

22 Study of the Volatility of Providers (2) Internal lock when replicating Ensure the consistency of the new replica Client is blocked Peer group juxmem Peer group cluster Peer group data

23 Study of the Volatility of Providers (3) JXTA and Java Time-out detection adapted for the WAN Independent of the data size Reconfiguration time  11 seconds Targeted volatility is weaker ( >> 80 seconds)

24 Conclusion Defines an hierarchical architecture for a data sharing service for the grid Specific policy for each cluster Scalability Storage and transparent access to data blocks Application level: data block ID Persistency Shared consistency Handling volatility of peers Actively taken into account

25 Future Work Transparent mobility of data blocks Unavaibility of nodes or even clusters Affinity data – computations Affinity data – data Parameterizable consistency Specific for each client Hierarchical synchronization

26

27 Allocation Request 2 1 3a 3b 4 5 6