Presentation is loading. Please wait.

Presentation is loading. Please wait.

Endpoint Admission Control WebTP Presentation 9/26/00 Presented by Ye Xia Reference: L. Breslau, E. W. Knightly, S. Shenkar, I. Stoica, H. Zhang, “Endpoint.

Similar presentations


Presentation on theme: "Endpoint Admission Control WebTP Presentation 9/26/00 Presented by Ye Xia Reference: L. Breslau, E. W. Knightly, S. Shenkar, I. Stoica, H. Zhang, “Endpoint."— Presentation transcript:

1 Endpoint Admission Control WebTP Presentation 9/26/00 Presented by Ye Xia Reference: L. Breslau, E. W. Knightly, S. Shenkar, I. Stoica, H. Zhang, “Endpoint Admission Control: Architectural Issues And Performance”. Sigcomm 2001.

2 Why Endpoint? Aim of admission control (AC): provide QOS to real-time flows IntServ has per-flow and router-based AC; requires hop-by-hop signalling (RSVP); each router keeps per-flow state; scalability problem. DiffServ lacks AC; providing QOS to each flow is not a primary concern; but more scalable. Hope: endpoint AC can combine the strength of both.

3 Algorithm Admission decision based on loss only Probing phase: each flow (at the end host) probes the network for loss or marking ratio (say, for 5 seconds) If the ratio is below a threshold, , flow is admitted. Loss model:

4 Router scheduling mechanisms Fair Queueing has “stolen bandwidth” problem. Example: suppose two types of flows; r2 > r1; and  = 0. Type 1 flow is admitted if r 1 (n 1 +n 2 ) < C; type 2 flow is admitted if r 1 n 1 + r 2 n 2 < C. When r 1 (n 1 +n 2 ) = C, type 1 flows experience no loss; type 2 flows’ loss ratio is (r 2 – r 1 )/ r 2

5 Best-Effort (TCP) Traffic Need to isolate TCP traffic and AC traffic. Consider what happens when –TCP traffic source is idle –TCP induces loss

6 Architecture Choice Priority queues –High priority for AC traffic –Low priority for TCP traffic –Probe traffic may take intermediate priority –FIFO queueing for AC traffic AC traffic is rate-limited and served at that rate. –non-work conserving scheduler

7 Probing Algorithms Difficulty in sampling loss/mark ratio Out-of-band probing –probing traffic takes lower priority than regular data traffic –Probing traffic has higher loss ECN marking: –marking rate higher than dropping rate –Router simulates a virtual queue drained at 90% capacity Problem: cannot relate specified threshold, , with actual loss ratio

8 Slow-Start Probing Thrashing: when many flows waiting for admission, probing traffic overloads the link. Cause: flow of rate r probes at rate r. Solution: slow-start probing. Gradually ramp up rate of probing traffic.

9 Thrashing Utilization collapses for both in-band and out-band probing For in-band probing, data loss ratio increases as well

10 Simulation Models Leaky-bucket constrained traffic sources –On-off sources and movie traces Poisson arrival of flows; exponential holding time with mean 300s. Interfering TCP traffic needs not to be simulated.  = 0,.01,.02,.03,.04,.05,.1,.15,.2. Comparison with router-based AC.

11 Traffic Sources

12 Basic Scenario Offered load: 20% blocking prob. Loss rate competitive with MBAC  is meaningful only for in-band drop. Other probing algo. reduce utilization. For in-band drop, 0.4% loss rate when  = 0. For out-band marking, low loss ratio can be achieve after probing for 5 seconds.

13 Longer Probing Time In-band dropping Lower loss ratio and lower utilization

14 High Load – In-band Dropping 400% offered load; 75% blocking prob. High loss Slow-start probing does better

15 High Load – Out-band Probing All algorithms are similar Probing traffic does not cause extra loss to data traffic Slow-start probing has higher utilization and loss ratio

16 High Load - Marking

17 Heterogeneous Traffic Large flow has 4 times the peak rate and higher blocking probability MBAC has similar behavoir

18 Multi-hop Loss Probability

19 Multi-hop – Blocking Probability

20 Sharing FIFO Queue with TCP Two lower curves are for  = 0.04 and 0.05 TCP prevents AC traffic to be admitted

21 Comments Quick conclusion on queueing/scheduling –Reconcile scheduling with end-to-end measurement Probing time is long. –can aggregate probing traffic –What to probe? AC criteria needs to be expanded (not just loss)  has no relationship with actual loss ratio WebTP has similar setup and similar issues.


Download ppt "Endpoint Admission Control WebTP Presentation 9/26/00 Presented by Ye Xia Reference: L. Breslau, E. W. Knightly, S. Shenkar, I. Stoica, H. Zhang, “Endpoint."

Similar presentations


Ads by Google