Presentation is loading. Please wait.

Presentation is loading. Please wait.

Admission Control and Dynamic Adaptation for a Proportional-Delay DiffServ-Enabled Web Server Yu Cai.

Similar presentations


Presentation on theme: "Admission Control and Dynamic Adaptation for a Proportional-Delay DiffServ-Enabled Web Server Yu Cai."— Presentation transcript:

1 Admission Control and Dynamic Adaptation for a Proportional-Delay DiffServ-Enabled Web Server Yu Cai

2 Paper Admission Control and Dynamic Adaptation for a Proportional-Delay DiffServ-Enabled Web Server Sam C. M. Lee, John C. S. Lui, David K. Y. Yau SIGMETRICS 2002

3 Why this paper? Information fusion in distributed environment. Data transmission from multiple sources with QoS requirements. –Then come to real data fusion techniques. –Data transmission is related to our specialties and my thesis. Paper last week: video stream –a carefully designed scheme to define the data transmission unit: avoid overhead and provide flexibility. –data transmission through multiple path: algorithm

4 Summary of this paper A web server that can provide proportional- delay differentiated services to clients with different QoS requirements. –3 classes - 1, 2, 3 –average waiting time of class 1 W1=1.4 * W2 –W2=1.4 * W3 –Real world example: an e-commerce site: general browsing - 1; client in the process of buying - 2; client check out - 3

5 Summary of this paper Admission control and class assignment –6 clients : a,b,c,d,e,f,g –with maximum traffic rate (work load) λ max –with maximum average waiting time (QoS) W max Admit clients to different classes and meet the QoS requirements –class vector C={1,2,1,1,3,1}

6 Summary of this paper Dynamic class adaptation –Previous step is based on the maximum client workload λ max –Dynamically adjust the service classes based on the client real traffic condition –C={1,2,1,1,3,1} => C={1,2,1,1,2,1} Goal: admit client to the lowest possible class while meeting the QoS requirements –The higher class is, the higher price to pay

7 Formulation 3 classes: 1,2,3 –W1=1.4 * W2; W2=1.4 * W3 6 clients: a,b,c,d,e,f,g –with λ max, W max Class vector C={1,2,1,1,3,1} Considerations when admit a client –Is it possible to admit the client with the QoS? –All other admitted clients need to keep the QoS –Assign lowest classes if possible

8 Formulation Based on conservation law: –λ 1 * W 1 + λ 2 * W 2 + λ 3 * W 3 = (λ 1 + λ 2 + λ 3 )*W –W is measurable, λ 1, λ 2, λ 3 is measurable. –W 1 = 1.4 * W 2 ; W 3 = 1/1.4 * W 2 –λ 1 * 1.4 * W 2 + λ 2 * W 2 + λ 3 / 1.4 * W 2 = (λ 1 + λ 2 + λ 3 )*W –So W 2 = (λ 1 + λ 2 + λ 3 )*W / (λ 1 * 1.4 + λ 2 + λ 3 / 1.4) –similarly W 1 and W 3 Out goal is to maximize : –V = 1/ W 1 + 1/ W 2 + 1/ W 3 –Same as minimize the sum of W i

9 Original formula

10 Admission control algorithms Maximum Profit Algorithm (MPA) Rationale: –two clients i and j with requirements of Wmaxi and Wmaxj –Wmaxi < Wmaxj, –client i is willing to pay a higher usage cost than client j so as to receive better service. –By admitting client i, the service provider may obtain a higher profit. –admit a client who has a more stringent maximum average waiting time requirement first.

11 MPA Sort Wa<=Wb<=Wc<=Wd<=We<=Wf For i=1 to 6{ –Assign client i in class 1 –While{ Compute delay of all admitted clients If all admitted clients meet QoS, admit client i, quit while If some admitted clients don’t meet QoS –If anyone of them is in the lowest class N, then »stop admitting client i, quit while//impossible to admit –Else »increase all their classes by 1//update class –}//end while }//end for

12 MPA analysis In essence, MPA is a greedy algorithm. Therefore it can only give local optimal. It likely will not achieve the global optimal. The authors kind of mislead the readers by making a vague and complicated definition: “MPA can always give a minimum feasible admitted class vector” –Sounds like global optimal, but still local optimal –C= {2,2,1,1,3,1}; C1={1,2,1,1,3,1}; C2={2,1,1,1,3,1} –MPA knows C1 and C2 are better than C, but can not decide which is better between C1 and C2

13 MPA analysis MPA updates all the unsatisfied clients’ class by 1, which adjust too much. C1={1,2,1,1,3,1} => C2={2,3,1,1,3,2}; But probably C3={2,2,1,1,3,2} is enough, or perhaps C4={3,1,1,1,3,2} is better

14 Maximum Admission Algorithm (MAA) Rationale: –Admit as many clients as possible to popularize the site –Admit clients with larger maximum average waiting time first, because they consume less resources. –Still greedy algorithm, same local optimal problem and adjust too much problem.

15 Dynamic Class Adaptation Why –AC is based on the maximum client workload λ max –Need to dynamically adjust the service classes based on the real traffic condition Measurement window: a period of time for web server to estimate the client arrival rate. Assumption: no major change in the future workload.

16 SBDA Centralized Approach: Server-Based Dynamic Adaptation (SBDA) –Server measures the client arrival rate λ –Server use λ as λ max to calculate the class vector –Server send this vector info to clients –Client then get the upper bound of the class to choose from. Client needs to choose the lowest possible class –Say, client b get class 2 assigned from server, it means if client choose class 2, the server guarantee the QoS; so the client needs to decide if it can go lower to class 1; if yes, use class 1, if no, use class 2.

17 CBDA SBDA drawbacks –Computation complexity –Communication overhead: unicast Distributed & Game-Theoretic Approach: Client- Based Dynamic Adaptation (CBDA) –Server measure and estimate the arrival rate for each class –Server multicast the information –Client can determine its lowest class based on the received information and its own arrival rate information

18 CBDA In essence, this is a non-cooperative game problem in which distributed optimization is performed by each client Guaranteed termination: upper bound is given in Admission control. Low computational complexity: client can even ignore this step.

19 My questions A typical client traffic pattern is like this: –80 % is λ max, 10 % is 0.9 * λ max, 10 % is 0.8 * λ max –Is this a realistic traffic pattern? –If traffic changes too much, the result seems to get bad. Algorithm improvement. Greedy? adjust too much? No simulation or analysis on how much the MPA and MAA is different from the optimal result

20 For our project Multiple data sources with different QoS and different data amount/load, Server side has a fixed data fusion ability how to admit and classify the data into different classes based on the data load and server capacity while keeping the QoS?

21 Example


Download ppt "Admission Control and Dynamic Adaptation for a Proportional-Delay DiffServ-Enabled Web Server Yu Cai."

Similar presentations


Ads by Google