160 likes | 199 Views
Explore the benefits and challenges of input-queued switches, delve into queue scheduling methods like matching algorithms and virtual output queuing, and discover how speedup can enhance performance. Learn about key concepts like urgency values and most urgent cell first (MUCF) algorithms.
E N D
Communication Networks Recitation 5 Input Queuing Scheduling& Combined Switches Comnet 2006
Output-queued switches Best delay and throughput performance Main problem • Requires high fabric speedup (S = N) Unsuitable for high-speed switching Comnet 2006
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 Comnet 2006
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 Comnet 2006
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 Comnet 2006
Maximum vs. Maximal • Maximum matching • Maximizes instantaneous throughput • Starvation • Time complexity is very high in Hardware (o(n3)) • Maximal matching • Can’t add any connection on the current match without alert existing connections • More practical Comnet 2006
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 (PIM) Random Selection Random Selection Requests Comnet 2006
Parallel Iterative MatchingConvergence Time Number of iterations to converge: Comnet 2006
Improving PIM • RRM - Round-Robin Matching • Choose the link to Grant/Accept in RR manner • Simpler • More fair • Starvation is rare but exists due to synchronization • iSLIP - Iterative Serial-Line IP • Only forward RR pointers if accepted • Starvation free Comnet 2006
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 Comnet 2006
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. Comnet 2006
Speedup: Context Memory Memory A generic switch The placement of memory gives • Output-queued switches • Input-queued switches • Combined input and output queued switches Comnet 2006
1 2 1 2 1 Using Speedup Comnet 2006
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 Comnet 2006
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 in OQ - present time Comnet 2006
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) Comnet 2006