Marilyn T. Smith, Head, MIT Information Services & Technology DataSpace IS&T Data CenterMIT Optical Network 1.

Slides:



Advertisements
Similar presentations
Distributed Data Processing
Advertisements

DSpace: the MIT Libraries Institutional Repository MacKenzie Smith, MIT EDUCAUSE 2003, November 5 th Copyright MacKenzie Smith, This work is the.
INTRODUCTION TO COMPUTER NETWORKS Zeeshan Abbas. Introduction to Computer Networks INTRODUCTION TO COMPUTER NETWORKS.
NAS vs. SAN 10/2010 Palestinian Land Authority IT Department By Nahreen Ameen 1.
MUNIS Platform Migration Project WELCOME. Agenda Introductions Tyler Cloud Overview Munis New Features Questions.
Skyward Disaster Recovery Options
Chapter 4 Infrastructure as a Service (IaaS)
Take your CMS to the cloud to lighten the load Brett Pollak Campus Web Office UC San Diego.
Introduction to the Internet September 7, 2005 Lecture 1.
Cold Fusion High Availability “Taking It To The Next Level” Presenter: Jason Baker, Digital North Date:
1 Northwestern University Information Technology Data Center Elements Research and Administrative Computing Committee Presented October 8, 2007.
Lesson 11-Virtual Private Networks. Overview Define Virtual Private Networks (VPNs). Deploy User VPNs. Deploy Site VPNs. Understand standard VPN techniques.
1© Copyright 2015 EMC Corporation. All rights reserved. SDN INTELLIGENT NETWORKING IMPLICATIONS FOR END-TO-END INTERNETWORKING Simone Mangiante Senior.
INTRODUCTION TO COMPUTER NETWORKS INTRODUCTION Lecture # 1 (
Data Centers and IP PBXs LAN Structures Private Clouds IP PBX Architecture IP PBX Hosting.
WAN Technology Overview Lecture 3: Introduction to WAN.
Virtual Network Servers. What is a Server? 1. A software application that provides a specific one or more services to other computers  Example: Apache.
Microsoft Load Balancing and Clustering. Outline Introduction Load balancing Clustering.
Introduction IT Department at CEU Contribution to carry out CEU’s mission with appropriate: -Information technology tools and services -Hardware and software.
Hands-On Microsoft Windows Server 2008 Chapter 8 Managing Windows Server 2008 Network Services.
Evolved from ARPANET (Advanced Research Projects Agency of the U.S. Department of Defense) Was the first operational packet-switching network Began.
C LIENT /S ERVER AND P EER TO P EER National 4/5 Computing Science.
Effectively Explaining the Cloud to Your Colleagues.
This courseware is copyrighted © 2011 gtslearning. No part of this courseware or any training material supplied by gtslearning International Limited to.
2 Object-Oriented Analysis and Design with the Unified Process Objectives  Describe the differences between requirements activities and design activities.
© 2007 Cisco Systems, Inc. All rights reserved.Cisco Public ITE PC v4.0 Chapter 1 1 The Internet and Its Uses Working at a Small-to-Medium Business or.
1 October 20-24, 2014 Georgian Technical University PhD Zaza Tsiramua Head of computer network management center of GTU South-Caucasus Grid.
OOI CI R2 Life Cycle Objectives Review Aug 30 - Sep Ocean Observatories Initiative OOI CI Release 2 Life Cycle Objectives Review CyberPoPs & Network.
Networks A network is a collection of computers and devices connected together via communications devices and transmission media Advantages of a network.
Chapter 4. After completion of this chapter, you should be able to: Explain “what is the Internet? And how we connect to the Internet using an ISP. Explain.
Introductionto Networking Basics By Avinash Kulkarni.
 Computer Networking Computer Networking  Networking terminology Networking terminology  Client Server Model Client Server Model  Types of Networks.
Chapter 8 Implementing Disaster Recovery and High Availability Hands-On Virtual Computing.
IT Infrastructure Chap 1: Definition
Summary - Part 1 - Objectives The purpose of this basic IP technology training is to explain video over an IP network. This training describes how video.
Information Availability Brett Paulson Sr. VP and Chief Information Officer Board of Trade Clearing Corporation FIA – November 7, 2002.
CSG - Research Computing Redux John Holt, Alan Wolf University of Wisconsin - Madison.
14 Aug 08DOE Review John Huth ATLAS Computing at Harvard John Huth.
Chapter 8: Internet Operation. Network Classes Class A: Few networks, each with many hosts All addresses begin with binary 0 Class B: Medium networks,
Summary - Part 2 - Objectives The purpose of this basic IP technology training is to explain video over IP network. This training describes how video can.
6/23/2005 R. GARDNER OSG Baseline Services 1 OSG Baseline Services In my talk I’d like to discuss two questions:  What capabilities are we aiming for.
Computer Networks part II 1. Network Types Defined Local area networks Metropolitan area networks Wide area networks 2.
CHAPTER 7 CLUSTERING SERVERS. CLUSTERING TYPES There are 2 types of clustering ; Server clusters Network Load Balancing (NLB) The difference between the.
Data Communications and Networks Chapter 9 – Distributed Systems ICT-BVF8.1- Data Communications and Network Trainer: Dr. Abbes Sebihi.
CITA 310 Section 3 Additional Topics. Common IPv4 Classes ClassFirst numberSubnet maskNumber of networks Number of addresses Class A0 – ,777,216.
Lawrence H. Landweber National Science Foundation SC2003 November 20, 2003
Component 4: Introduction to Information and Computer Science Unit 7: Networks & Networking Lecture 1 This material was developed by Oregon Health & Science.
U N C L A S S I F I E D LA-UR Leveraging VMware to implement Disaster Recovery at LANL Anil Karmel Technical Staff Member
Architecture of a platform for innovation and research Erik Deumens – University of Florida SC15 – Austin – Nov 17, 2015.
“Enterprise Network Design and Implementation for Airports” Master’s Thesis - Ashraf Ali Department of Computing and Information Sciences This project.
Dr. Ir. Yeffry Handoko Putra
Networking Basics.
Lab A: Planning an Installation
Bentley Systems, Incorporated
BEST CLOUD COMPUTING PLATFORM Skype : mukesh.k.bansal.
Clouds , Grids and Clusters
INTRODUCTION TO COMPUTER NETWORKS
Module 8: Concepts of a Network Load Balancing Cluster
Lab A: Installing and Configuring the Network Load Balancing Driver
3.2 Virtualisation.
Magento Enterprise Hosting Magento enterprise hosting is an internet space provider which provides website space and other services to make their website.
CLUSTER COMPUTING.
Distributed computing deals with hardware
Internet and Web Simple client-server model
INTRODUCTION TO COMPUTER NETWORKS
INTRODUCTION TO COMPUTER NETWORKS
Cloud-Enabling Technology
Client/Server and Peer to Peer
Presentation transcript:

Marilyn T. Smith, Head, MIT Information Services & Technology DataSpace IS&T Data CenterMIT Optical Network 1

DataSpace MIT MIT’s Information Services and Technology (IS&T) department is MIT’s central information services organization. Operates all MIT core systems: – Administrative: SAP, Data Warehouse – Course Support: Stellar, MITsis/WebSIS – Networks: , Web, VoIP, Athena, etc At MIT, DataSpace Production hardware and software proposed will be operated by IS&T staff – Note: DataSpace nodes at partner organizations might be operated differently – to experiment with a variety of operating environments. 2

MIT - Computer & Data Cluster MIT’s IS&T department currently supports over 100 computer clusters from manufacturers such as Sun, Dell, Apple, and Hewlett- Packard ranging in size from several computers up to hundreds of computers. – Limited storage (approximately 1 TB) will be needed for local processing at the control node, and storage will be maintained for some research databases for testing purposes. – MIT IS&T will also be able to host processing nodes for individual research projects on a contract basis should individual faculty at MIT or elsewhere desire this type of “co-location” service. Most of the collaborating research groups (i.e., the Martinos Imaging Center at the McGovern Institute of MIT and the Center for Advanced Brain Imaging at Georgia Tech) have computing, storage, and networks resources of their own. – Since the funding and operation of these facilities are pre-existing and they have been partly described in the Project Description section, we will not elaborate upon them here – other than to note that they will be incorporated into the federated architecture of DataSpace. 3

MIT - Networking and access Each computer in the DataSpace central node cluster will have two or more network connections to the internal network of the MIT data center. The data center’s internal network allows multiple sub-nets each operating at 1Gb/second connecting with MIT’s backbone network currently operating at 10Gb/second. – Planned upgrades during the life of the NSF contract will raise these speeds to 10Gb/second and 40Gb/second respectively. Each sub-net can be configured with several “virtual networks” should our research indicate that isolation of network traffic between or among different servers is desirable. The internal MIT network connects to the Internet through multiple paths including Internet 2, NLR, three different commercial ISPs, through a common network ring among other universities in the Boston area, and via MIT’s optical network to a major Internet interconnection point in New York City. – Aggregate capacity from MIT to the Internet is 40Gb/second with upgrades planned to ensure that average load is never more than 10% of capacity. During the life of this contract, it will be possible to have a dedicated connection from the DataSpace control node at MIT to Internet 2 and other external networks at speeds of 10-40Gb/second. These speeds will allow direct data transfers of sizable databases as well as all control information to manage a distributed worldwide network. 4

MIT – Service facility and fail-over All hardware will be housed in MIT’s advanced data center with redundant power and cooling designed to meet specifications for Tier II (N+1) standards of the Up-time Institute. – MIT also maintains long-term leased space in a commercial Tier III data center (expected site availability of %) where redundant DataSpace equipment can also be located. – In addition, we expect to locate reduced capacity redundant hardware and software at another MIT-leased site at least 100 miles distant from the primary site. Software configuration will allow dynamic designation of additional control nodes so that control nodes can be designated at non-MIT sites. – Control data will be replicated in real-time with a target replication delay of no more than two seconds among all control nodes. Fail-over will be based on standard “heart-beat” control protocols with transfer of control in less than two seconds and with no expected loss of control data. – Control data will be archived analytical purposes. 5