UnitIV q Distributed Computing Systems q Distributed Computing

Unit-IV q Distributed Computing Systems q Distributed Computing models q Issues in designing distributed operating systems q DCE

Computer Architecture Multiprocessors Types • Tightly Coupled Multiprocessor System (Parallel )

Computer Architecture Multiprocessors Types • Loosely Coupled Multiprocessor System(Distributed )

Parallel v/s Distributed Systems Parallel Systems Distributed Systems Memory Tightly coupled shared memory UMA, NUMA Distributed memory Message passing, RPC, and/or used of distributed shared memory Control Global clock control SIMD, MIMD No global clock control Synchronization algorithms needed Processor interconnection Order of Tbps Bus, mesh, tree, mesh of tree, and hypercube (-related) network Order of Gbps Ethernet(bus), token ring and SCI (ring), myrinet(switching network) Main focus Performance Scientific computing Performance(cost and scalability) Reliability/availability Information/resource sharing 4

What is a distributed system? • Tanenbaum’s definition of a distributed system: “ A distributed system is a collection of independent computers that appear to the users of the system as a single coherent system. ”

An example of a Distributed System • Nationalized Bank with multiple Branch Offices

Requirements of Distributed systems • Security and reliability. • Consistency of replicated data. • Concurrent transactions (operations which involve accounts in different banks; simultaneous access from several users, etc) • Fault tolerance

What is a Distributed Computing System? • "a collection of processors interconnected by a communication network in which each processor has its own local memory and other peripherals and the communication between any two processors of the system takes place by message passing over the communication network" (Sinha 97) 8

Evaluation of Distributed Computing System 1945 -1950 s Loading monitor 1950 s-1960 s Batch system 1960 s Multiprogramming 1960 s-1970 s Time sharing systems Multics, IBM 360 1969 -1973 WAN and LAN ARPAnet, Ethernet 1960 s-early 1980 s Minicomputers PDP, VAX Early 1980 s Workstations Alto 1980 s – present Workstation/Server models Sprite, V-system 1990 s Clusters Beowulf Late 1990 s Grid computing Globus, Legion 9

Distributed Computing System Models • • • Minicomputer model Workstation-server model Processor-pool model Cluster model Grid computing 10

Minicomputer Model Minicomputer ARPA net Minicomputer • Extension of Time sharing system – User must log on his/her home minicomputer. – Thereafter, he/she can log on a remote machine by telnet. • Resource sharing – Database – High-performance devices 11

Workstation Model Workstation 100 Mbps LAN Workstation • Process migration – Users first log on his/her personal workstation. – If there are idle remote workstations, a heavy job may migrate to one of them. • Problems: – How to find an idle workstation? – How to migrate a job? – What if a user log on the remote machine? 12

Workstation-Server Model Client workstations – Diskless Workstation – Graphic/interactive applications processed in local – All file, print, http and even cycle computation requests are sent to servers. Workstation • Server minicomputers – Each minicomputer is dedicated to one or more different types of services (print, database, …etc). 100 Gbps • Client-Server model of communication LAN – RPC (Remote Procedure Call) – RMI (Remote Method Invocation) • A Client process calls a server process’ function. Mini • No process migration invoked Computer • Example: NFS file server • http server print server • Disadvantage : capability of idle workstations is not utilized. 13

Processor-Pool Model • Clients: – They log in one of terminals (diskless workstations or X terminals) – All services are dispatched to servers. • Servers: – Necessary number of processors are allocated to each user from the pool. • Better utilization but less interactivity 100 Mbps LAN Server 1 Server N 14

Cluster Model Workstation • Client – Takes a client-server model Workstation • Server – Consists of many 100 Mbps PC/workstations connected LAN to a high-speed network. http server 2 http server N – Puts more focus on http server 1 performance: serves for Slave Master Slave requests in parallel. node 1 2 N 1 Gbps SAN 15

Grid Computing • Workstation Supercomputer • Minicomputer High-speed Information high way Cluster • • Supercomputer Cluster • • Workstation Goal – Collect computing power of supercomputers and clusters sparsely located over the nation and make it available as if it were the electric grid Distributed Supercomputing – Very large problems needing lots of CPU, memory, etc. High-Throughput Computing – Harnessing many idle resources On-Demand Computing – Remote resources integrated with local computation Data-intensive Computing – Using distributed data Collaborative Computing – Support communication among multiple parties 16

Why are Distributed Computing Systems Gaining Popularity? • Inherently distributed applications – Distributed DB, worldwide airline reservation, banking system • Information sharing among distributed users – CSCW (Computer Supported Cooperative Works )or groupware • Resource sharing – Sharing DB/expensive hardware and controlling remote lab. devices • Better cost-performance ratio / Performance – Emergence of Gbit network and high-speed/cheap MPUs – Effective for coarse-grained or embarrassingly parallel applications • Reliability – Non-stopping (availability) and voting features. • Scalability, Extensibility and Incremental Growth – Loosely coupled connection and hot plug-in • Flexibility – Reconfigure the system to meet users’ requirements 17

Distributed Computing Environment (DCE) Ø What is DCE? Ø DCE Architecture Ø DCE Components

DCE • • • § § § Vendor Independent Environment Defined by OSF a consortium of computer manufacturers. Nither OS or an application , integrated set of services software that supplies a framework and toolkit for developing client/server applications The framework includes a Remote Procedure Call (RPC) mechanism, a naming (directory) service, a time service, authentication service, authorization service Distributed File System.

Distributed Computing Environment DCE Applications Threads RPC Distributed Time Service Security Distributed File Service Name Platforms 20

DCE • Support the development of distributed application in a single system • Platform independent , runs on all OS and heterogeneous DS • Middle ware software between OS and networking layer and DCE applications layer. • Hides the difference between machines by automatically performing data type conversion

DCE Architecture

DCE(Components ) • Fundamental distributed services provide tools for software developers to create the end-user services needed for distributed computing. They include – Remote Procedure Call, which provides portability, network independence, and secure distributed applications. – Directory services, which provides a single naming model to allow programmers and maintainers to identify and access distributed resources more easily. – Time service, which provides a mechanism to monitor and track clocks in a distributed environment and accurate time stamps to reduce the load on system administrator. – Security service, which provides the network with authentication, authorization, and user account management services to maintain the integrity, privacy, and authenticity of the distributed system. – Thread service, which provides a simple, portable, programming model for building concurrent applications.

DCE • Data-sharing services provide end users with capabilities built upon the fundamental distributed services. These services require no programming on the part of the end user and facilitate better use of information. They include – Distributed file system, which interoperates with the network file system to provide a high-performance, scalable, and secure file access system. – Diskless support, which allows low-cost workstations to use disks on servers, possibly reducing the need/cost for local disks, and provides performance enhancements to reduce network overhead.

DCE components

DCE Cell Ø Largest management unit in DCE is cell. (group of users, machines and other resources) Ø The highest privileges within a cell are assigned to a role called cell administrator Ø Breakdown a large system into small , manageable units called cell. Ø Major components of DCE within every cell are: – The security server that is responsible for authentication – The Cell Directory Server (CDS) that is the repository of resources and Access Control Lists – The Distributed Time Server that provides an accurate clock for proper functioning of the entire cell.

DCECell • Setting up a DCE system , decide cell boundaries • Four factors 1. Purpose : users and m/c’s with same task must be put in same cells. 2. Administration: to register new users in the system. 3. Security : machines of those users have trust in each other put in same cell 4. Overhead : m/c’s of users frequently interacting put in same cell