170 likes | 269 Views
Communication Networks. Recitation 5. Input Queuing Scheduling & Combined Switches. Output-queued switches. Best delay and throughput performance. Possible to erect “bandwidth firewalls” between sessions. Main problem. Requires high fabric speedup (S = N).
E N D
Communication Networks Recitation 5 Netcomm 2005
Input Queuing Scheduling& Combined Switches 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 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 Netcomm 2005
Input Queue Scheduling • First Goal : maximize throughput • Second Goal : control packet delay • Methods : • maximum matching • maximal matching • maximum/maximal weight matching • stable matchingusing Virtual Output Queuing and moderate speedup Netcomm 2005
A 1 A 1 A 1 2 B 2 B 2 B 3 C 3 C 3 C 4 D 4 4 D D 5 E 5 5 E E 6 F 6 6 F F Example of Maximal Size Matching Maximal Size Matching Maximum Size Matching Netcomm 2005
1 1 1 1 2 2 2 2 #1 1 1 3 3 3 3 2 2 4 4 4 4 Grant Accept/Match 3 3 1 1 1 1 1 1 4 4 2 2 2 2 2 2 #2 3 3 3 3 3 3 4 4 4 4 4 4 Parallel Iterative Matching Random Selection Random Selection Requests Netcomm 2005
Parallel Iterative MatchingConvergence Time Number of iterations to converge: Netcomm 2005
1 1 1 1 2 2 2 2 #1 1 1 3 3 3 3 2 2 4 4 4 4 F2: Grant F3: Accept/Match 3 3 1 1 1 1 1 1 4 4 2 2 2 2 2 2 #2 3 3 3 3 3 3 4 4 4 4 4 4 Round-Robin Selection Round-Robin Selection iSLIP F1: Requests Netcomm 2005
iSLIP Properties • Random under low load • TDM under high load • Lowest priority to Most Recently Used • 1 iteration: fair to outputs • Converges in at most N iterations. • On average < log2N. Netcomm 2005
1 1 1 1 1 10 2 2 2 2 1 w e i g h t M m m a x i u 3 3 3 3 1 10 4 4 4 4 1 Input QueueingLongest Queue First orOldest Cell First { = } Queue Length Weight 100% Waiting Time Netcomm 2005
Non-uniform traffic Uniform traffic Avg Occupancy Avg Occupancy VOQ # VOQ # Input QueueingWhy is serving long/old queues better than serving maximum number of queues? • When traffic is uniformly distributed, servicing themaximum 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. Netcomm 2005
Speedup: Context Memory Memory A generic switch The placement of memory gives • Output-queued switches • Input-queued switches • Combined input and output queued switches Netcomm 2005
1 2 1 2 1 Using Speedup 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 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 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) Netcomm 2005