Presentation is loading. Please wait.

Presentation is loading. Please wait.

Scalable QoS Provision Through Buffer Management Roch Guerin Sanjay Kamat Vinod Peris Raju Rajan IBM Thomas J. Watson Research Labs.

Similar presentations


Presentation on theme: "Scalable QoS Provision Through Buffer Management Roch Guerin Sanjay Kamat Vinod Peris Raju Rajan IBM Thomas J. Watson Research Labs."— Presentation transcript:

1 Scalable QoS Provision Through Buffer Management Roch Guerin Sanjay Kamat Vinod Peris Raju Rajan IBM Thomas J. Watson Research Labs

2 Outline Differentiated Packet Treatment for QoS Performance Objectives Design Space Scheduling and Buffer Management Schemes Comparing FIFO vs WFQ -- Worst case buffer tradeoffs Examining tradeoffs with strict buffer partitioning Examining tradeoffs with buffer sharing Hybrid Schemes Conclusions

3 Differentiated Packet Treatment Flows (Unit of service guarantee -- varying granularity) QoS Resources -- Link capacity and Buffer Space Scalability –Processing time per packet versus number of flows –State size versus number of flows Routing and Classification Policing Discard Buffer Management Scheduling

4 QoS Performance Objectives Throughput maximization Flow Isolation & rate guarantees Fair allocation of excess resources. Implementation cost MemoryProcessing

5 QoS Allocation Schemes. Scheduling FIFO WFQ Buffer Management No Buffer Management (FIFO) Buffer Partitioning Buffer Sharing Fair Excess Capacity distribution (Choudhury and Hahne) No Buffer Management (FIFO) Buffer Partitioning Buffer Sharing headroom Excess capacity sharing & fairness Empty buffer spaces

6 Design Space FIFO Buffer Management Per-Flow Scheduling (WFQ) FIFO Scheduling. FIFO treatment of excess traffic Fair and flexible excess capacity distribution Rate Based Per Flow Buffer Management

7 Benchmarks. FIFO scheduling & Buffer Management WFQ Scheduling & No Buffer Management WFQ scheduling & Buffer Management FIFO scheduling & No Buffer Management

8 Rate Guarantees through buffer management alone Buffer Size B bits Link Capacity R bits/sec Partitioned Buffer FIFO Scheduler Reservation Buffer Partition Offered Service Size Load Achieved bits/sec B /R bits Conformant Lossless Non-conformant Losses limited by non-conformance ( bits bits/sec + B /R bits Conformant Lossless Non-conformant Losses limited by non-conformance

9 R i Buffer Partitioning w. FIFO vs. WFQ ( Worst case comparison ) WFQ Admissibility Checks FIFO Admissibility Checks Bandwidth availability Buffer availability B i R i Bandwidth availability B i + ( i ) B/R Buffer availability Equivalently B i /(1-utilization)

10 Experimental Setup Flow Token TokenMean Peak Number bucket Rate RateRate 050 kB2Mbps2Mbps16Mbps 150 kB2Mbps2Mbps16Mbps 250 kB2Mbps2Mbps16Mbps 3100 kB8Mbps8Mbps40Mbps 4 100 kB8Mbps8Mbps40Mbps 5 100 kB8Mbps8Mbps40Mbps 650 kB0.4Mbps4Mbps40Mbps 750 kB0.4Mbps4Mbps40Mbps 850 kB2Mbps16Mbps40Mbps On-off sourceRegulator 500KB to 5MB Buffer Manager Link Scheduler 48Mbps

11 Benchmarks. FIFO scheduling & Buffer Management WFQ Scheduling & No Buffer Management WFQ scheduling & Buffer Management FIFO scheduling & No Buffer Management

12 Aggregate Throughput Buffer Partitioning vs. No Buffer Management Buffer Size (Mb) Throughput (Mbps

13 Losses for conformant flows Buffer Partitioning vs. No Buffer Management Buffer Size (Mb) Loss (percent)

14 Aggregate Throughput Buffer Sharing vs. No Buffer Management Buffer Size (Mb) Throughput (Mbps)

15 Excess Capacity Sharing Buffer Size (Mb) Throughput (Mbps)

16 The Hybrid Scheme Flow -- Unit of buffer allocation Queue -- unit of bandwidth allocation WFQ Scheduler Fair Excess Capacity distribution based on holes Protect individual flows while sharing buffers Allocation & Headroom

17 Throughput Integrated Scheme Buffer Size (Mb) Throughput(Mbps)

18 Flow Isolation and Rate Guarantees Integrated Scheme Buffer Size (Mb) Loss (percent)

19 Excess Capacity Distribution Integrated Scheme Buffer Size (Mb) Throughput (Mbps)

20 Conclusions The Integrated Scheme Scheduling on a fixed number of Queues and buffer management on the finer granularity of Flows Rules of thumb for flow grouping Buffer sharing & flow isolation within a single use headroom to limit impact on conformant flows in buffer limited system Empty buffers (holes) to regulate the sharing of excess bandwidth flexible notion of fairness Flexibility to choose tradeoffs depending on operational environment Some quantitative guidelines on the choice of design and setting of parameters


Download ppt "Scalable QoS Provision Through Buffer Management Roch Guerin Sanjay Kamat Vinod Peris Raju Rajan IBM Thomas J. Watson Research Labs."

Similar presentations


Ads by Google