1. Univ. of TehranIntroduction to Computer Network1 Introduction to Computer Networks University of Tehran Dept. of EE and Computer Engineering By: Dr. Nasser Yazdani Lecture 9: Packet Switching

2. Univ. of TehranIntroduction to Computer Network2 outline Store-and-Forward Switches Bridges and Extended LANs Packet switching Cell Switching Segmentation and Reassembly

3. Univ. of TehranIntroduction to Computer Network3 Scalable Networks Limitation of directly connected networks. Limit on the number of hosts; For example, Ethernet is 1024 hosts. Limit on the geographical area of LANs. 2500 m in Ethernet. Solution: This is like telephone network. Then, use Switches.

4. Univ. of TehranIntroduction to Computer Network4 Switches forwards packets from input port to output port port selected based on address in packet header If two packets are destined to the same output, one must be buffered (queued). This is called contention. Needs some kinds of scheduling for packet delivery. If the buffer overflow, it will be a congestion. Input ports T3 STS-1 T3 STS-1 Switch Output ports

5. Univ. of TehranIntroduction to Computer Network5 An Ethernet Network Router Outside world Problem:  Shared network limits throughput.  Lots of collisions reduces efficiency.

6. Univ. of TehranIntroduction to Computer Network6 Interconnecting LANs Bridges (aka Ethernet switches) were introduced to allow the interconnection of several local area networks (LANs) without a router. By partitioning a large LAN into multiple smaller networks, there are fewer collisions, and more parallel communications. It is now common for the port of an Ethernet switch to connect to just one (or a small number of) hosts.

7. Univ. of TehranIntroduction to Computer Network7 Ethernet Switching Router Outside world Benefits:  Number of collisions is reduced.  Capacity is increased: Problem? How to determine the output port? Ethernet Switch Ethernet Switch/Bridge

8. Univ. of TehranIntroduction to Computer Network8 One Ethernet Switch in “Packard”

9. Univ. of TehranIntroduction to Computer Network9 Output ports? Learning Bridges Maintain a forwarding table for hosts. How to populate table. Manually by system admin. (not good) Learn table entries based on source address (flexible). PortHost 1A 1B 1C 2X 2Y 2X A Bridge BC XY Z Port 1 Port 2

10. Univ. of TehranIntroduction to Computer Network10 Learning Bridges, (Forwarding) 1. If the frame destination address is in the routing table, forward the frame to the corresponding port. 2. Otherwise, broadcast the frame. 3. Update the table if the source address is not in the table. The table is learned by examining the Ethernet SA of arriving packets. Table is an optimization; need not be complete Always forward broadcast frames

11. Univ. of TehranIntroduction to Computer Network11 Ethernet Switching Learning addresses Router Outside world Ethernet Switch Ethernet Switch Ethernet Switch Ethernet Switch A BCD E FGH I JKL M NOP Q 1 23 4 5 6 J F Switch learns that ‘F’ is reachable through port 5

12. Univ. of TehranIntroduction to Computer Network12 Ethernet Switching Learning addresses Router Outside world Ethernet Switch Ethernet Switch Ethernet Switch Ethernet Switch A BCD E FGH I JKL M NOP Q 1 23 4 5 6 Ethernet addressPort A1 B2 C3 D4 E, F, G, H, Q5 I, J, K, L, M, N, O, P6 Q: How do we prevent loops?

13. Univ. of TehranIntroduction to Computer Network13 Preventing loops Spanning Tree Protocol The network of bridges is a graph. The Spanning Tree Protocol finds a subgraph that spans all the vertices without loops. Spanning => all bridges are included. Tree => the topology has no loops. The distributed protocol runs: To determine which bridge is the root of the tree, and Each bridge turns off ports that are not part of the tree.

14. Univ. of TehranIntroduction to Computer Network14 Spanning Tree Algorithm Spanning tree A distributed spanning tree algorithm select which bridges actively forward developed by Radia Perlman now IEEE 802.1 specification A C E D B K F H J G I B3 B2 B7 B4 B1 B6 B5

15. Univ. of TehranIntroduction to Computer Network15 Example Spanning Tree B3 B5 B7 B2 B1 B6 B4 Protocol operation : 1.Picks a root 2.For each LAN, picks a designated bridge that is closest to the root. 3.All bridges on a LAN send packets towards the root via the designated bridge. B8

16. Univ. of TehranIntroduction to Computer Network16 Example Spanning Tree B3 B5 B7 B2 B1 B6 B4 Root B8 B2B4B5B7 B8 B1 Spanning Tree:

17. Univ. of TehranIntroduction to Computer Network17 Algorithm Details Bridges exchange configuration messages id for bridge sending the message id for what the sending bridge believes to be root bridge distance (hops) from sending bridge to root bridge Each bridge records current best configuration message for each port Initially, each bridge believes it is the root

18. Univ. of TehranIntroduction to Computer Network18 Algorithm Detail (cont) When learn not root, stop generating config messages in steady state, only root generates configuration messages Root continues to periodically send config messages If any bridge does not receive config message after a period of time, it starts generating config messages claiming to be the root

19. Univ. of TehranIntroduction to Computer Network19 Spanning Tree Protocol 1.Each bridge periodically sends a configuration message out of every port. A message contains: (ID of sender, ID of root, distance from sender to root). 2.Initially, every bridge claims to be root and sends a distance field of 0. 3.A bridge keeps sending the same message (periodically) until it hears a “better” message. “Better” means: A root with a smaller ID A root with equal ID, but with shorter distance The root ID and distance are the same as we already have, but the sending bridge has a smaller ID. 4.Once a bridge hears a better configuration message, it stops generating its own messages, and just forwards ones that it receives (adding 1 to the distance). 5.If the bridge realizes that it is not the designated bridge for a LAN, it stops sending configuration messages to that LAN. Eventually: Only the root bridge generates configuration messages, Other bridges send configuration messages to LANs for which they are the designated bridge.

20. Univ. of TehranIntroduction to Computer Network20 Virtual LANs Single physical LAN infrastructure that carries multiple “virtual” LANs simultaneously. Each virtual LAN has a LAN identifier in the packet. Switch keeps track of what nodes are on each segment and what their virtual LAN id is Can bridge and route appropriately. Broadcast packets stay within the virtual LAN. Limits the collision domain for the packet host Switch

21. Univ. of TehranIntroduction to Computer Network21 Broadcast and Multicast Forward all broadcast/multicast frames current practice Learn when no group members downstream Accomplished by having each member of group G send a frame to bridge multicast address with G in source field

22. Univ. of TehranIntroduction to Computer Network22 Limitations of Bridges Do not scale spanning tree algorithm does not scale broadcast does not scale Do not accommodate heterogeneity Caution: beware of transparency

23. Univ. of TehranIntroduction to Computer Network23 Packet Switching Schemes Learning bridges are a special case. We need a general form for packet switching or specifying the output in the packet. They are three format for specifying the output in the a packet Source routing: List entire path in the packet Virtual circuits: like telephone circuit, identify packets with ids. Datagram: Put only destination address in packets’ headers.

24. Univ. of TehranIntroduction to Computer Network24 Source Routing List entire path in packet Driving directions (north 3 hops, east, etc..) Router processing, one option Examine first step in directions Strip first step from packet Forward to step just stripped off Or the address can be implemented by a linked list in the packet header.

25. Univ. of TehranIntroduction to Computer Network25 Source Routing Example Receiver Packet 3,4,3 Sender 2 3 4 1 2 3 4 1 2 3 4 1 R1 R2 R1 4,33 All routing information is provided by the source.

26. Univ. of TehranIntroduction to Computer Network26 Source Routing Advantages Switches can be very simple and fast Disadvantages Variable (unbounded) header size Sources must know or discover topology (e.g., failures) Typical use Debugging and management

27. Univ. of TehranIntroduction to Computer Network27 Virtual Circuits/Tag Switching Use the telephone model virtual circuits Each flow is identified by a Virtual Circuits Identifier (VCI). Connection setup phase, Signaling Use other means to route setup request Each router allocates flow ID on local link Creates mapping of inbound flow ID/port to outbound flow ID/port Each packet carries connection ID Sent from source with 1 st hop connection ID Router processing Lookup flow ID – simple table lookup Replace flow ID with outgoing flow ID Forward to output port Swap labels

28. Univ. of TehranIntroduction to Computer Network28 Virtual Circuit Connection setup establishes a path through switches A virtual circuit ID (VCI) identifies path Uses packet switching, with packets containing VCI VCIs are often indices into per-switch connection tables; change at each hop 1 2 3 4 1 2 3 4 VC1 VC2 VC1 VC2 VC3 VC2 In, VC Out, VC 1, 1 4, 1 1, 2 4, 3 2, 1 4, 2 ….

29. Univ. of TehranIntroduction to Computer Network29 Virtual Circuits Examples Receiver Packet 1,5  3,7 Sender 2 3 4 1 1,7  4,2 2 3 4 1 2 3 4 1 2,2  3,6 R2 R3 R1 5726 In-portIn-VCIOut-portOut-VCI 1537 41108 Lookup table for Switch R1 Subsequence packets follow the same circuit

30. Univ. of TehranIntroduction to Computer Network30 Virtual Circuits Advantages More efficient lookup (simple table lookup) More flexible (different path for each flow) Can reserve bandwidth at connection setup Easier for hardware implementations Small per-packet header overhead. Disadvantages Still need to route connection setup request More complex failure recovery – must recreate connection state Typical uses ATM – combined with fix sized cells MPLS – tag switching for IP networks

31. Univ. of TehranIntroduction to Computer Network31 Virtual Circuit Model Typically wait full RTT for connection setup before sending first data packet. While the connection request contains the full address for destination, each data packet contains only a small identifier, making the per-packet header overhead small. If a switch or a link in a connection fails, the connection is broken and a new one needs to be established. Connection setup provides an opportunity to reserve resources.

32. Univ. of TehranIntroduction to Computer Network32 Datagram Switching No connection setup phase since it is costly. Each packet is forwarded independently Sometimes called connectionless model Analogy: postal system Each switch maintains a forwarding (routing) table Receiver Packet R Sender 2 3 4 1 2 3 4 1 2 3 4 1 R1 R2 R1 R R R  3 R  4 R  3 R

33. Univ. of TehranIntroduction to Computer Network33 Datagram Model There is no round trip time delay waiting for connection setup; a host can send data as soon as it is ready. Source host has no way of knowing if the network is capable of delivering a packet or if the destination host is even up. Since packets are treated independently, it is possible to route around link and node failures. Since every packet must carry the full address of the destination, the overhead per packet is higher.

34. Univ. of TehranIntroduction to Computer Network34 TechniquesTechniques: Comparison DatagramVirtual circuit switching Circuit switching Forwarding cost highlownone Bandwidth utilization highflexiblelow Resource reservations noneflexibleyes Robustness*highlow *The idea is that in case of failure, circuit and VC are lost; datagram routing can adapt after routing update ….

35. Univ. of TehranIntroduction to Computer Network35 Cell Switching Cell Switching (ATM) Connection-oriented packet-switched network Used in both WAN and LAN settings Signaling (connection setup) Protocol: Q.2931 Specified by ATM forum Packets are called cells 5-byte header + 48-byte payload Commonly transmitted over SONET other physical layers possible

36. Univ. of TehranIntroduction to Computer Network36 Variable vs Fixed-Length Packets No Optimal Length if small: high header-to-data overhead if large: low utilization for small messages Fixed-Length Easier to Switch in Hardware simpler enables parallelism

37. Univ. of TehranIntroduction to Computer Network37 Big vs Small Packets Small Improves Queue behavior finer-grained pre-emption point for scheduling link maximum packet = 4KB link speed = 100Mbps transmission time = 4096 x 8/100 = 327.68us high priority packet may sit in the queue 327.68us in contrast, 53 x 8/100 = 4.24us for ATM near cut-through behavior two 4KB packets arrive at same time link idle for 327.68us while both arrive at end of 327.68us, still have 8KB to transmit in contrast, can transmit first cell after 4.24us at end of 327.68us, just over 4KB left in queue

38. Univ. of TehranIntroduction to Computer Network38 Big vs Small (cont) Small Improves Latency (for voice) voice digitally encoded at 64Kbps (8-bit samples at 8KHz) need full cell’s worth of samples before sending cell example: 1000-byte cells implies 125ms per cell (too long) smaller latency implies no need for echo cancellors ATM Compromise: 48 bytes = (32+64)/2

39. Univ. of TehranIntroduction to Computer Network39 Cell Format User-Network Interface (UNI) host-to-switch format GFC: Generic Flow Control (still being defined) VCI: Virtual Circuit Identifier VPI: Virtual Path Identifier Type: management, congestion control, AAL5 (later) CLP: Cell Loss Priority HEC: Header Error Check (CRC-8) Network-Network Interface (NNI) switch-to-switch format GFC becomes part of VPI field GFCHEC (CRC-8) 41631 8 VPIVCICLPTypePayload 384 (48 bytes)8

40. Univ. of TehranIntroduction to Computer Network40 Segmentation and Reassembly ATM Adaptation Layer (AAL) AAL 1 and 2 designed for applications that need guaranteed rate (e.g., voice, video) AAL 3/4 designed for packet data AAL 5 is an alternative standard for packet data AAL ATM AAL ATM ……

41. Univ. of TehranIntroduction to Computer Network41 AAL 3/4 Convergence Sublayer Protocol Data Unit (CS- PDU) CPI: common part indicator (version field) Btag/Etag:beginning and ending tag BAsize: hint on amount of buffer space to allocate Length: size of whole PDU

42. Univ. of TehranIntroduction to Computer Network42 Cell Format Type BOM: beginning of message COM: continuation of message EOM end of message SEQ: sequence of number MID: message id Length: number of bytes of PDU in this cell It uses 4 extra bytes for SAR, not good!

43. Univ. of TehranIntroduction to Computer Network43 AAL5 CS-PDU Format pad so trailer always falls at end of ATM cell Length: size of PDU (data only) CRC-32 (detects missing or misordered cells) Cell Format end-of-PDU bit in Type field of ATM header

44. Univ. of TehranIntroduction to Computer Network44 ATM Layers Higher Layers AAL ATM PHY Aplication TCP IP DLL PHY TCP/IP ATM PHY in ATM is usually SONET. Sending IP over ATM is done by address translation. ATM is also used in LAN. Then, It tries to emulate LAN. The Technology is called LANE.

45. Univ. of TehranIntroduction to Computer Network45 Switches A means to create connectivity Why switching? Efficient utilization of resources Store and forward scheme incoming linksoutgoing links Node Memory

46. Univ. of TehranIntroduction to Computer Network46 Switched Network A network consisting of switching elements. Hosts can connect to the network directly or through LANs. n links Switches Switched Network

47. Univ. of TehranIntroduction to Computer Network47 Basic concepts An ideal switch: route all incoming packet to their requested outputs with the following conditions: No loss Minimum delay Preserving order Output contention: At least two input goes to one output. we need buffer and queuing (how much?) Congestion: no buffer space left. Drop packet

48. Univ. of TehranIntroduction to Computer Network48 Design Factors Throughput Max throughput- N x line speed where N is the # of input line Ave throughput – At random is %60. Packet per second (PPS)- # of packets switched per second Throughput depends on the traffic. Quality of service: Ave delay of cells Jitter Reliability in switching cells.

49. Univ. of TehranIntroduction to Computer Network49 Design Factors Scalability: how the architecture scale, linear? Square? Regarding the speed of input line Regarding the # of input port. Cost: # of logic gates Memory Bandwidth or # of pines

50. Univ. of TehranIntroduction to Computer Network50 Performance Factors Traffic pattern: Packet arrival rate. Destination distribution Addressing and operation: Unicast or multicast operation Priority- Differentiation among packets

51. Univ. of TehranIntroduction to Computer Network51 Functional requirement User plane: Data is carried transparently Header are processed and VPI/VCI is used for routing. LC IPP SFC OPP LC 0 0 … … Central unit

52. Univ. of TehranIntroduction to Computer Network52 Functional requirement Cntrl plane: Signaling Identified by VPI/VCI, 5/0 is for call admission. May use SFC for transporting ctrl packets. LC IPP SFC OPP LC … … IPP+ SFC+ OPP Store and forward system. CAC CAC- Call Admission Control

53. Univ. of TehranIntroduction to Computer Network53 Functional requirement Management plane: System Management (SM) must handle management cell. Should support Network wide operations. May use SFC for transporting management cells. LC IPP SFC OPP LC … … SM

54. Univ. of TehranIntroduction to Computer Network54 Workstation-Based switch Aggregate bandwidth 1/2 of the I/O bus bandwidth capacity shared among all hosts connected to switch example: 800Mbps bus can support 8 T3 ports CPU Main memory I/O bus Interface 1 Interface 2 Interface 3 Packets-per-second must be able to switch small packets 100,000 packets-per- second is achievable e.g., 64-byte packets implies 51.2Mbps

55. Univ. of TehranIntroduction to Computer Network55 Route Table CPU Buffer Memory Line Interface MAC Line Interface MAC Line Interface MAC Typically < 0.5Gbps aggregate capacity Limited by rate of shared memory Shared Backplane Line Interface CPU Memory Slide by Nick McKeown ArchitecturesArchitectures: First Generation

56. Univ. of TehranIntroduction to Computer Network56 Route Table CPU Line Card Buffer Memory Line Card MAC Buffer Memory Line Card MAC Buffer Memory Fwding Cache Fwding Cache Fwding Cache MAC Buffer Memory Typically < 5Gb/s aggregate capacity Limited by shared bus Slide by Nick McKeown ArchitecturesArchitectures: Second Generation

57. Univ. of TehranIntroduction to Computer Network57 Line Card MAC Local Buffer Memory CPU Card Line Card MAC Local Buffer Memory Switched Backplane Line Interface CPU Memory Fwding Table Routing Table Fwding Table Typically < 50Gbps aggregate capacity Slide by Nick McKeown ArchitecturesArchitectures: Third Generation

58. Univ. of TehranIntroduction to Computer Network58 Switch fabric design Shared Media Bus Architecture Shared buffer Space division Cross bar architecture Combination of above Note: Self-routing is to direct packet inside the fabric.

59. Univ. of TehranIntroduction to Computer Network59 Bus Architecture IPP puts cells on bus OPP buffer cells Control Processor (CP) exchanges control messages configures connections Bus interconnects various components. » In nonblocking systems bandwidth is equal to sum of external link bandwidths; » bus width must increase with number of links » capacitive loading reduces clock rate as number of links grows

60. Univ. of TehranIntroduction to Computer Network60 Divided Bus with Knockout Concentrators Split bus into n “minibuses” with w  n wires each Each minibus driven by just one IPP. cuts capacitive loading in half adding fanout components allows higher clock frequencies OPPs concentrate n minibuses onto L<n outputs (optional) OPPs must each be able to buffer up to L cells in parallel Parallel reception complicates control somewhat Concentration reduces required OPP memory bandwidth IPP w wnwn OPPs

61. Univ. of TehranIntroduction to Computer Network61 Knockout Switch Concentrator select l of n packets Complexity: n 2 D 1234 Outputs Inputs D D D DD D D DD D D D D

62. Univ. of TehranIntroduction to Computer Network62 Shared Buffer Switches For switches with 10 or more links, can reduce required memory by up to an order of magnitude. n Queues are rarely full, then, memory for queues is unused mostly n With shared memory, we can achieve same performance level with less memory. n Requires a central memory with bandwidth equal to twice the external link bandwidth. n Per output or per flow queues typically implemented as linked lists.

63. Univ. of TehranIntroduction to Computer Network63 crossbar Architecture crossbar allows multiple cells to pass in parallel to distinct outputs » use of point-to-point transmission eliminates capacitive loading at circuit board level » parallelism reduces data path width at IPPs, OPPs control circuit arbitrates access to outputs retains quadratic complexity, but concentrates it within chip, reducing system cost IPP OPP

64. Univ. of TehranIntroduction to Computer Network64 UT switch Design

65. Univ. of TehranIntroduction to Computer Network65 UT Internal Design Shared Memory (SM) Memory Management (Pointer Path) Input Processor Output Processor Control Path User Interface Central Unit Data Path

66. Univ. of TehranIntroduction to Computer Network66 UT Capacity mode Dual chip mode

67. Univ. of TehranIntroduction to Computer Network67 ExamplesExamples: Cisco GSR - 12416 WAN Router – Large throughput; SONET links Up to 16 line cards at 10 Gbps each Crossbar Fabric Line Cards: 1-port OC-192c 4-port OC48c Many others (ATM, Ethernet, …) Cisco GSR 12416 6ft 19 ” 2ft