1 Netcomm 2005 Communication Networks Recitation 5

2 Netcomm 2005 Input Queuing Scheduling & Combined Switches

3 Netcomm 2005 Output-queued switches Best delay and throughput performance - Possible to erect “bandwidth firewalls” between sessions Main problem - Requires high fabric speedup (S = N) Unsuitable for high-speed switching

4 Netcomm 2005 Input-queued switches Big advantage - Speedup of one is sufficient Main problem - Can’t guarantee delay due to input contention Overcoming input contention: use higher speedup

5 Netcomm 2005 Input Queue Scheduling First Goal : maximize throughputFirst Goal : maximize throughput Second Goal : control packet delaySecond Goal : control packet delay Methods :Methods : –maximum matching –maximal matching –maximum/maximal weight matching –stable matching using Virtual Output Queuing and moderate speedup

6 Netcomm 2005 Example of Maximal Size Matching A1 B C D E F A1 B C D E F Maximal Size Matching Maximum Size Matching A B C D E F

7 Netcomm 2005 Parallel Iterative Matching Requests Grant Accept/Match #1 #2 Random Selection

8 Netcomm 2005 Parallel Iterative Matching Convergence Time Number of iterations to converge:

9 Netcomm 2005 iSLIP  1: Requests  2: Grant  3: Accept/Match #1 #2 Round-Robin Selection

10 Netcomm 2005 iSLIP Properties Random under low loadRandom under low load TDM under high loadTDM under high load Lowest priority to Most Recently UsedLowest priority to Most Recently Used 1 iteration: fair to outputs1 iteration: fair to outputs Converges in at most N iterations.Converges in at most N iterations. On average < log 2 N.On average < log 2 N.

11 Netcomm 2005 Input Queueing Longest Queue First or Oldest Cell First Weight Waiting Time 100% Queue Length { } =

12 Netcomm 2005 Input Queueing Why is serving long/old queues better than serving maximum number of queues? When traffic is uniformly distributed, servicing the maximum number of queues leads to 100% throughput. When traffic is non-uniform, some queues become longer than others. A good algorithm keeps the queue lengths matched, and services a large number of queues. VOQ # Avg Occupancy Uniform traffic VOQ # Avg Occupancy Non-uniform traffic

13 Netcomm 2005 Speedup: Context MemoryMemory MemoryMemory The placement of memory gives - Output-queued switches - Input-queued switches - Combined input and output queued switches A generic switch

14 Netcomm 2005 Using Speedup

15 Netcomm 2005 The Speedup Problem Find a compromise: 1 < Speedup << N - to get the performance of an OQ switch - close to the cost of an IQ switch Essential for high speed QoS switching

16 Netcomm 2005 What is exact mimicking? Apply same inputs to an OQ and a CIOQ switch - packet by packet Obtain same outputs - packet by packet Key concept: urgency value - urgency = departure time - present time

17 Netcomm 2005 Most Urgent Cell First (MUCF) The algorithm - Outputs try to get their most urgent packets - Inputs grant to output whose packet is most urgent, ties broken by port number - Loser outputs for next most urgent packet - Algorithm terminates when no more matches are possible Speedup of 4 is sufficient for exact emulation of FIFO OQ switches, with MUCF (Prabhakar & McKeown, 1997) Joined Preferred Matching (JPM) – Speedup 2 (Stoica & Zhang, 1998)