MARS: The Magnet II Real-Time Scheduling Algorithm

1
MARS The Magnet IIReal-Time Scheduling Algorithm

• Hyman, Lazer, and Pacifici
• 1991 ACM ?
• Presented by
• ???

2
Abstract

• A real-time scheduling algorithm, MARS, for
  Asynchronous Time Sharing (ATS) based switching
  modes.
• 3 classes of traffic sources
• real-time video sources
• guaranteed maximum end-to-end delay SI for all
  cells
• real-time voice sources
• guaranteed maximum end-to-end delay SII
• ? cell loss rate
• maximum average cell loss gap ?
• data traffic
• guaranteed minimum average throughput
• guaranteed maximum average time delay

3
1. Introduction

• Goal
• To evaluate the performance of Asynchronous Time
  Sharing (ATS) based integrated networks
• ATS based integrated network is novel
• the concept of quality of service explicitly
  appears in the design specification at both the
  edge and the core of the network
• the core of the network makes a distinction
  between traffic classes
• it is necessary in order to efficiently provide
  QoS
• it is not a requirement of ATM based integrated
  networks

4

• The study of this paper is limited to
• a switching nodes taken in isolation
• This paper
• presents the performance of the MAGNET II
  scheduling algorithm
• compares it with the performance of other known
  algorithms, with
• quantitative data
• implementation complexity and knowledge

5
2. Review of Past Work

• The early literature on real-time scheduling
  relates to an operation systems environment,in
  which arriving tasks need to be scheduled at an
  available processor, such that each task is
  completed by its deadline
• Assume
• a priori knowledge of all of the arrival times,
  processing times, and deadlines for the entire
  set of tasks to be scheduled

6

• Various criteria for optimization have been used
• Cheng and Stankovic 3
• Liu and Laylan
• Tobagi and Peha
• Baker
• Chipalkatti et al.
• Ferarri and Verma
• Sriram

7
3. The Architecture of the Switching Nodes

• 3 elements
• Input Buffers
• Switching Fabric
• Output Buffers
• Fundamental Requirement
• The transfer of information from its inputs to
  its output such that time delay and blocking
  sensitive performance criteria are met.

8

• 4 traffic classes Class I, II, III, and C
• 4 input buffers / access point.
• Traffic arriving at an access point is stored,
  according to its class, in one of the four
  buffers.
• ? Minimum Average User ThroughputT Maximum
  Average User Time Delay

9
3.1 The Multi-class Traffic Model

• Contention Packet Loss
• Clipping Network Congestion ? Delay gt Max
  Delay, SI or SII
• Blocked Buffer Overflow ? Packet discarded
• For Class II
• ? Contention packet loss ? Upper bound
  on the average number consecutively lost packet

10
3.2 The Link Scheduling Model

• ATS-based switching node
• was first implemented on MAGNET II
• and also adopted by TeraNet.

Buffer ManagerLink Scheduler
3 input links
3 output links
3 x (3 x 4)
J x (3 x 1)output buffers
J x (3 x 1)input buffers
Ring Switch Fabric
11

• Model the output link of TeraNet
• A queuing system with 4 buffers 1 server
• At server
• Fixed capacity - C bits/secFixed cell size - D
  bits/cell
• Service rate ? C/D cells/sec
• Slotted channel

• MX dynamically adjusted
• Fixed Cycle Length H ? M

12
3.3 Real-Time Traffic Source Models

• Video

• Fixed frame duration F 62.5 ms
• Constant cell rate CI 1M bps
• Active period ?active 10ms, 40ms
  (uniformly distributed)
• E?(t,video) E?active CI / F 4M bps

13

• Voice
• On-off source
• Fixed frame duration F 62.5 ms
• Constant cell rate CI 1M bps
• Active period ?onInactive period ?off
  (exponentially distributed)
• E?on 352 msE?off 650 ms
• E?(t,voice) E?on / (E?on E?off) 22.5K
  bps
• Data
• Poisson distributed
• E?(t,data) 1M bps

14
4. MARS The MAGNET II Real-Time Scheduling
Algorithm

• Assume 1 server 3 queues (for Class I, II, and
  III only)
• Scheduler Operations
• H is kept constant
• 2 schedules (lists) number of Class I and II
  cells to be transmitted during the future cycle
• the lists are updated at the end of each
  cycle(new cells arrived during the previous
  cycle)
• only the min. amount of resources is allocated to
  each class
• QoS requirements of Class I must always be met
• exceeding Class II cells are clipped
• the remaining bandwidth (if available) is
  allocated toClass III traffic.

15

• To determine the bandwidth allocation
• At the end of each cycle
• The scheduler generates 2-dimensional (hI gt hII)
  schedules, with hk ? Sk ? / H ? -
  1 (k1,2)
• 2 logical partitions (bins) for Class I and II
• Mki,j the number of Class k cells that at the
  beginning of cycle i are predicted to be
  scheduled in the next hk cycles, j lt hk.

16

• The updating process for Class I traffic
• MIi,j min(MIi-1,j1OIi,j1,H)
• OIi,j max(0,MIi-1,j1OIi,j1-H)

17

• The updating process for Class II traffic
• MIIi,j min(MIIi-1,j1OIIi,j1,Rj,j)OII
  i,j max(0,MIi-1,j1OIIi,j1-RI,j)where
  RI,j H- MIi,j j 0,1,,hI H -
  (1/hI) ? MIi,j j hI,, hII-1

18
5. Experimental Results

• Compare MARS with
• SPS (Static Priority Scheduling)
• MLT (Minimum Laxity Threshold)
• Assume
• Link capacity C 100M bps
• Fixed cell size D 1024 bits/cell
• Fixed cycle size H 39 cells
• QOS SI,SII,?,?,T
• SI,SII max. delay of Class I and II traffic (in
  seconds)
• ? percentage of contention packet loss
• ? max. gap between consecutive packet loss (in
  cells)
• T max. average user time delay (in seconds)

19

• Experiment 1
• KI KII 0..20 calls, KIII 0..80 Poisson
  data callsH 39 cellsQOS 1ms, 1ms, 0.001,
  5.0, 1msFixed KI and KIII ? Find KII
• For KI lt 10 same performance of the 3
  algorithms.For KI gt 10 MARS and MLT allow more
  KII users.

20

• Let KIII 0 in Experiment 1

• KI increases ? KII decreases
• MARS/MLT gt SPS

• When KI 16
• MARS/MLT KII 500 voice calls.
• SPS KII 0

21

• Experiment 2 (for smaller delay)
• H 9 cellsQOS 400?s, 800?s, 0.001, 5.0, 1ms
• Same performance of the 3 algorithms.
• Little effect for SPSDrastic decreases for MARS
  and SPS

22

• Conclusions from EXP 1 and 2
• (1) When Class I and II requires smaller delays,
  the SPS is very nearly optimal. (Same in
  EXP. 1 and 2)
• (2) When Class I and II have larger traffic, a
  significant gain in utlilization can be
  achieved by usin one of the more complex
  algorothms, MARS or MLT. (KI gt 10)

23

• Experiment 3 (for correlated and bursty traffic)
• CI 10Mbps ? 50Mbps
• ?active 10ms, 40ms ? 2ms, 8ms
• E?active 25ms ? 5ms
• F 62.5ms
• E?(t,video) E?active CI / F 4Mbps
• Only when both Class I and II loads are low is
  the performance of SPS, MARS, and MLT the same.

24

• Let KIII 0 in Experiment 3

• Worse performance when bursty traffic.
• Improved by using MARS and MLT.

25
6. Conclusions (1)

• When the network load is highly correlated (video
  or on-off voice), ? MARS and MLT improved the
  performance considerably.
• When the cells are multiplexed together, ?
  their correlation decreases as the number of
  sources increases. ?The improvement due to
  MARS and MLT is considerably smaller.

26
6. Conclusions (2)

• Resources allocation
• SPS Class I traffic first
• smaller delay for Class I traffic
• MARS and MLT that is necessary to satisfy
  Class I QoS parameters
• maximum delay for Class I traffic
• Class II and III have more resources, and thus,
  the multiplexer has a greater network
  utilization factor.

27
6. Conclusions (3)

• MARS has at most twice the computation time of
  SPS, while MLT runs much slower.
• MARS and MLT are closed to the upper bound for
  network utilization.
• Additional knowledge requirement for MLT leads to
  substantial increase in complexity without
  proportional improvement in network utilization.
• MARS is recommended for real-time scheduling
  algorithms in ATS-based nodes.