CS252 Graduate Computer Architecture Lecture 8: Network 1: Definitions, Metrics, 252 ProjectsReview: A Little Queuing TheoryReview: I/O BenchmarksReview: Availability benchmarksNetworksSlide 6Interconnections (Networks)SAN: Storage vs. SystemSlide 9More Network BackgroundABCs of NetworksA Simple ExampleQuestions About Simple ExampleA Simple Example RevistedSoftware to Send and ReceiveNetwork Performance MeasuresCS 252 AdministriviaUniversal Performance MetricsTotal Latency ExampleSlide 20Universal MetricsSimplified Latency ModelOverhead, BW, SizeMeasurement: Sizes of Message for NFSImpact of Overhead on Delivered BWInterconnect IssuesNetwork MediaFiberWave Division Multiplexing FiberCompare MediaSlide 31Connecting Multiple ComputersSummary: InterconnectionsProjectsIf time permitsCS252/PattersonLec 8.12/9/01CS252Graduate Computer ArchitectureLecture 8: Network 1: Definitions, Metrics, 252 ProjectsFebruary 9, 2001Prof. David A. PattersonComputer Science 252Spring 2001CS252/PattersonLec 8.22/9/01Review: A Little Queuing Theory•Queuing models assume state of equilibrium: input rate = output rate•Notation: r average number of arriving customers/secondTseraverage time to service a customer (tradtionally µ = 1/ Tser )u server utilization (0..1): u = r x Tser Tqaverage time/customer in queue Tsysaverage time/customer in system: Tsys = Tq + TserLqaverage length of queue: Lq = r x Tq Lsysaverage length of system : Lsys = r x Tsys •Little’s Law: Lengthsystem = rate x Timesystem (Mean number customers = arrival rate x mean service time)Proc IOC DeviceQueueserverSystemCS252/PattersonLec 8.32/9/01Review: 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 measure•Benchmarks to measure Availability, Maintainability?CS252/PattersonLec 8.42/9/01Review: Availability benchmarks•Availability benchmarks can provide valuable insight into availability behavior of systems–reveal undocumented availability policies–illustrate impact of specific faults on system behavior•Methodology is best for understanding the availability behavior of a system–extensions are needed to distill results for automated system comparison•A good fault-injection environment is critical–need realistic, reproducible, controlled faults–system designers should consider building in hooks for fault-injection and availability testing•Measuring and understanding availability will be crucial in building systems that meet the needs of modern server applications–this benchmarking methodology is just 1st step towards goalCS252/PattersonLec 8.52/9/01Networks•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–Error tolerance critical as well•Warning: Terminology-rich environmentCS252/PattersonLec 8.62/9/01Networks•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–reliabilityCS252/PattersonLec 8.72/9/01Interconnections (Networks)•Examples (see Figure 7.19, page 633):–Wide Area Network (ATM): 100-1000s nodes; ~ 5,000 kilometers–Local Area Networks (Ethernet): 10-1000 nodes; ~ 1-2 kilometers–System/Storage Area Networks (FC-AL): 10-100s nodes; ~ 0.025 to 0.1 kilometers per linka.k.a.network,communication subneta.k.a.end systems,hostsInterconnection NetworkCS252/PattersonLec 8.82/9/01SAN: Storage vs. System •Storage Area Network (SAN): A block I/O oriented network between application servers and storage –Fibre Channel is an example•Usually high bandwidth requirements, and less concerned about latency –in 2001: 1 Gbit bandwidth and millisecond latency OK •Commonly a dedicated network (that is, not connected to another network)•May need to work gracefully when saturated•Given larger block size, may have higher bit error rate (BER) requirement than LANCS252/PattersonLec 8.92/9/01SAN: Storage vs. System •System Area Network (SAN): A network aimed at connecting computers –Myrinet is an example•Aimed at High Bandwidth AND Low Latency. –in 2001: > 1 Gbit bandwidth and ~ 10 microsecond•May offer in order delivery of packets•Given larger block size, may have higher bit error rate (BER) requirement than LANCS252/PattersonLec 8.102/9/01More Network Background•Connection of 2 or more networks: Internetworking•3 cultures for 3 classes of networks–WAN: telecommunications, Internet–LAN: PC, workstations, servers cost–SAN: Clusters, RAID boxes: latency (System A.N.) or bandwidth (Storage A.N.)•Try for single terminology•Motivate the interconnection complexity incrementallyCS252/PattersonLec 8.112/9/01ABCs 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 signalingCS252/PattersonLec 8.122/9/01A 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)CS252/PattersonLec 8.132/9/01Questions 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., Cyclic Redundancy Chk)•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 => complexityCS252/PattersonLec 8.142/9/01A 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
View Full Document
Unlocking...