Lecture 7: Interconnection NetworksReview: Storage System IssuesReview: I/O BenchmarksI/O to External Devices and Other ComputersNetworksExample Major NetworksSlide 7Interconnections (Networks)More Network BackgroundABCs of NetworksA Simple ExampleQuestions About Simple ExampleA Simple Example RevistedSoftware to Send and ReceiveNetwork Performance MeasuresUniversal Performance MetricsExample Performance MeasuresTotal Latency ExampleSimplified Latency ModelImpact of Overhead on Delivered BWBuilding a Better Butterfly: The Multiplexed MetabutterflyTransformationsOutlineButterflySplitter NetworkDilated ButterflyWiring SplittersExpansionFaults and CongestionMultibutterfliesWhat’s Wrong?Wiring ComplexityRelative ComplexityMetabutterflyHierarchyRandom K-ExtensionsK-Extension PropertiesEmpirical ResultsMultiplexingMultiplexing (Bit-Inverse)Load BalancingUnbalanced LoadingRandomized MultiplexingSummaryConclusionsInterconnect OutlineHW Interface IssuesSW Interface IssuesCM-5 Software InterfaceInterconnect IssuesNetwork MediaCosts of Network Media (1995)Slide 54Connecting Multiple ComputersExample InterconnectsSwitch TopologyImportant TopologiesTopologies (cont)Slide 60Example MPP NetworksSummary: InterconnectionsConnection-Based vs. ConnectionlessSlide 64Routing MessagesDeterministic Routing ExamplesStore and Forward vs. Cut-ThroughSlide 68Congestion ControlPractical Issues for Inteconnection NetworksPractical IssuesCross-Cutting Issues for NetworkingProtocols: HW/SW InterfaceFTP From Stanford to BerkeleyProtocolTCP/IP packetExample NetworksConnecting NetworksSlide 79Example Networks (cont’d)Examples: Interface to ProcessorPacket FormatsExample Switched LAN PerformanceExample Switched LAN Performance (1995)UDP/IP performanceNFS performanceEstimated Database performance (1995)Summary: NetworkingParallel ComputersParallel Processors “Religion”Opportunities: Scientific ComputingExample: Scientific ComputingOpportunities: Commercial ComputingWhat level Parallelism?Whither Supercomputing?Parallel ArchitectureParallel FrameworkShared Address Model SummaryFTC.W99 1Lecture 7:Interconnection Networks Prof. Fred ChongECS 250A Computer ArchitectureWinter 1999(Adapted from Patterson CS252 Copyright 1998 UCB)FTC.W99 2Review: Storage System Issues•Historical Context of Storage I/O•Secondary and Tertiary Storage Devices•Storage I/O Performance Measures•Processor Interface Issues•Redundant Arrays of Inexpensive Disks (RAID)•ABCs of UNIX File Systems•I/O BenchmarksFTC.W99 3Review: I/O Benchmarks•Scaling to track technological change•TPC: price performance as nomalizing configuration feature•Auditing to ensure no foul play•Throughput with restricted response time is normal measureFTC.W99 4I/O to External Devices and Other ComputersProcessorCacheMemory - I/O BusMainMemoryI/OControllerDisk DiskI/OControllerI/OControllerGraphicsNetworkinterruptsideal: high bandwidth, low latencyFTC.W99 5Networks•Goal: Communication between computers•Eventual Goal: treat collection of computers as if one big computer, distributed resource sharing•Theme: Different computers must agree on many things –Overriding importance of standards and protocols–Fault tolerance critical as well•Warning: Terminology-rich environmentFTC.W99 6Example Major NetworksARPA netT1, 56KbpsT3, 230KbpsIP - internet ProtocolTCP - TransmissionControl ProtocolToken RingEthernetFDDICS NetRelayX.25 (Telenet, Uninet_PhonenetCS NetBitnetNSF Net1.6Mbps10 Mbps4Mbps100MbpsATMFTC.W99 7Networks•Facets people talk a lot about:–direct (point-to-point) vs. indirect (multi-hop)–topology (e.g., bus, ring, DAG)–routing algorithms–switching (aka multiplexing)–wiring (e.g., choice of media, copper, coax, fiber)•What really matters:–latency–bandwidth–cost–reliabilityFTC.W99 8Interconnections (Networks)•Examples:–MPP networks (SP2): 100s nodes; Š 25 meters per link–Local Area Networks (Ethernet): 100s nodes; Š 1000 meters–Wide Area Network (ATM): 1000s nodes; Š 5,000,000 metersa.k.a.network,communication subneta.k.a.end systems,hostsInterconnection NetworkFTC.W99 9More Network Background•Connection of 2 or more networks: Internetworking•3 cultures for 3 classes of networks–MPP: performance, latency and bandwidth–LAN: workstations, cost–WAN: telecommunications, phone call revenueFTC.W99 10ABCs of Networks•Starting Point: Send bits between 2 computers•Queue (FIFO) on each end•Information sent called a “message”•Can send both ways (“Full Duplex”)•Rules for communication? “protocol”–Inside a computer: »Loads/Stores: Request (Address) & Response (Data)»Need Request & Response signalingFTC.W99 11A Simple Example•What is the format of mesage?–Fixed? Number bytes?Request/ResponseAddress/Data1 bit32 bits0: Please send data from Address1: Packet contains data corresponding to request•Header/Trailer: information to deliver a message•Payload: data in message (1 word above)FTC.W99 12Questions About Simple Example•What if more than 2 computers want to communicate?–Need computer “address field” (destination) in packet•What if packet is garbled in transit?–Add “error detection field” in packet (e.g., CRC)•What if packet is lost?–More “elaborate protocols” to detect loss (e.g., NAK, ARQ, time outs)•What if multiple processes/machine?–Queue per process to provide protection•Simple questions such as these lead to more complex protocols and packet formats => complexityFTC.W99 13A Simple Example Revisted•What is the format of packet?–Fixed? Number bytes?Request/ResponseAddress/Data1 bit 32 bits00: Request—Please send data from Address01: Reply—Packet contains data corresponding to request10: Acknowledge request11: Acknowledge reply4 bitsCRCFTC.W99 14Software to Send and Receive•SW Send steps1: Application copies data to OS buffer2: OS calculates checksum, starts timer3: OS sends data to network interface HW and says start•SW Receive steps3: OS copies data from network interface HW to OS buffer2: OS calculates checksum, if matches send ACK; if not, deletes message (sender resends when timer expires)1: If OK, OS copies data to user address space and signals application to continue•Sequence of steps for SW: protocol–Example similar to UDP/IP protocol in UNIXFTC.W99 15Network Performance Measures•Overhead: latency of interface vs. Latency: networkFTC.W99 16Universal Performance MetricsSenderReceiverSenderOverheadTransmission