1 / 23

Priority Scheduling and Buffer Management for ATM Traffic Shaping

Priority Scheduling and Buffer Management for ATM Traffic Shaping. Authors: Todd Lizambri, Fernando Duran and Shukri Wakid Present: Hongming Wu. Outline. Introduction Buffer Partitioning, Discard Policies and Scheduling Algorithms Network and Traffic Scenario

nakashima
Download Presentation

Priority Scheduling and Buffer Management for ATM Traffic Shaping

An Image/Link below is provided (as is) to download presentation Download Policy: Content on the Website is provided to you AS IS for your information and personal use and may not be sold / licensed / shared on other websites without getting consent from its author. Content is provided to you AS IS for your information and personal use only. Download presentation by click this link. While downloading, if for some reason you are not able to download a presentation, the publisher may have deleted the file from their server. During download, if you can't get a presentation, the file might be deleted by the publisher.

E N D

Presentation Transcript


  1. Priority Scheduling and Buffer Management for ATM Traffic Shaping • Authors: Todd Lizambri, Fernando Duran and Shukri Wakid • Present: Hongming Wu

  2. Outline • Introduction • Buffer Partitioning, Discard Policies and Scheduling Algorithms • Network and Traffic Scenario • Dynamically Weighted Priority Scheduling Algorithm • Implementation of the Simulation • Results • Conclusions

  3. Introduction • Congestion control Congestion occurs when too many cells try to access the same buffer pool in a switch. So congestion control mechanism is needed

  4. Introduction • Logical approach of congestion control - Open loop: Prevents congestion from happening * Admission control * Policing * Traffic shaping — My topic today - Closed loop: rely on feedback to regulate the source rate

  5. Introduction • Traffic shaper The basic function of a traffic shaper is regulating the traffic flow as per the Quality of Service (QoS) negotiated during the session set up to achieve better network efficiency

  6. Introduction • Shaping method: ^ Buffering(+leaky bucket) ^ Spacing ^ Peak cell rate reduction ^ Scheduling ^ Burst length limiting ^ Source rate limitation ^ Priority queuing ^ Framing

  7. Introduction • QoS Parameters ^ Negotiable parameters ! Peak-to-peak Cell Delay Variation (CDV) ! Maximum Cell Transfer Delay (Max CTD) ! Mean Cell Transfer Delay (Mean CTD) ! Cell Loss Ratio (CLR) ^ Non-negotiable parameters ! Cell Error Ratio (CER) ! Severely Errored Cell Block Ratio (SECBR) ! Cell Misinsertion Ratio (CMR)

  8. Introduction • We concentrate on two of the most important internal design factors in traffic shapers ^ Buffer management ^ Scheduling algorithms we examine the impact of buffer management and scheduling algorithms on the two most important QoS attributes, cell loss and delay, under stress conditions

  9. Buffer Partitioning, Discard Policies and Scheduling Algorithms • Buffer partitioning delineates the amount of buffer space available to a given queue and defines how space is shared among the different queues • The discard policy determines whether an incoming cell is to be dropped or placed into the buffer space • The scheduling algorithm is the component that determines which queue is given the opportunity to transmit a cell that is stored in the buffer

  10. Buffer Partitioning methods • Complete Partitioning scheme: each queue gets a fixed amount of the buffer space • Complete Sharing scheme: where all the buffer space is fully shared among all the queues • Sharing with Minimum Allocation scheme: a compromise method which reserves a minimum buffer space for each queue while the rest of the buffer is completely shared among the queues

  11. Scheduling Algorithms • First-In-First-Out(FIFO) • Round Robin(RR) • Fixed Priorities A queue with higher priority is always served before a queue with a lower priority • Dynamically Weighted Priority scheduling algorithm

  12. Network and Traffic Scenario • We consider two classes of services • Constant Bit Rate (CBR) • Variable Bit Rate (VBR)

  13. Dynamically Weighted Priority Scheduling Algorithm • We consider a time dependent instantaneous priority index Pj(t) for a jth class of service at a given time t to be: - uj is the associated fixed priority number • wj(t) is the amount of time the oldest cell in the jth class has waited in queue j • The floor function is used to get integer units of time

  14. Dynamically Weighted Priority Scheduling Algorithm • The priority index for each queue is recalculated for every output time slot • The queue with the lowest value of priority index is awarded the time slot and is permitted to transmit a cell during that time • If ß=0 we have a fixed priority scheduling • For a very large ß, Pj(t) is heavily influenced by the wait time of the cell and the scheduling mechanism behaves as a FIFO

  15. Implementation of the Simulation • The configuration of the traffic shaper consisted of two queues - Queue 1: CBR traffic class • Queue 2: VBR traffic class * The total buffer space = 1024 entries * The CBR sources were transmitting data at rate of 155 Mbs * The VBR sources were transmitting bursty traffic at a rate of 155 Mbs for 2 milliseconds followed by an OFF period where no data was transmitted for 2 milliseconds.

  16. Results - FIFO Scheduling • Because the VBR source is only transmitting 50% of the time the number of cells dropped from the VBR source (Queue 2) is approximately half of the cells dropped from the CBR source (Queue 1) • Since the traffic for both queues is transmitted at the same rate (155 Mbs), the average cell delay for each queue will be the same

  17. Result - Round Robin Scheduling (1) • The cell loss of the CBR data is prevalent in this scenario due to the constant arrival of data in Queue 1

  18. Result - Round Robin Scheduling (2) • The average cell delay of Queue 1 is greater than that of Queue 2 due to nature characteristic of RR scheduling

  19. Results - Dynamically Weighted Priority Scheduling • The effect of Beta value

  20. Result-Dynamically Weighted Priority Scheduling

  21. Result-Dynamically Weighted Priority Scheduling

  22. Result-Dynamically Weighted Priority Scheduling

  23. Conclusions • The dynamically weighted priority scheduling algorithm provides a mechanism for simultaneously improving the balance of cell loss and delay • Optimal value for ß is based input traffic

More Related