230 likes | 246 Views
This paper explores a distributed scheme for dynamically placing and removing replicas in Content Delivery Networks (CDNs) to satisfy user requests while minimizing costs. It also discusses redirecting user requests based on replica load thresholds. Future work includes comparing different settings and observing distance constraints.
E N D
Distributed Dynamic Replica Placement and Request Redirection in Content Delivery Networks Advisor : Ho-Ting Wu Student : Yu-Chiang Lin Date:2011/5/30
OUTLINE • CDN introduce • Distributed Dynamic Replica Placement • Cloning of a replica • Replica removal • Redirection • Future work • Reference Page 2
OUTLINE • CDN introduce • Distributed Dynamic Replica Placement • Cloning of a replica • Replica removal • Redirection • Future work • Reference Page 3
CDN Introduce Fig:Server Farm(source from EBU technical review) Page 4
CDN Introduce • Consider TCP transmittion,throughput may affect by latency or packet lost。 Page 5
CDN Introduce • The Content Delivery Networks (CDN) paradigm is based on the idea to transparently move third-party content closer to the users • content is replicated on CDN servers which are located close to the final users so that users perceive a better content access service. Page 6
CDN Introduce Fig:Content Delivery Network(source from EBU technical review) Page 7
CDN Introduce Fig:Content Delivery Network Page 8
CDN Introduce • Four Important technique • 1.Content route • 2.Content distribution • 3.Content store • 4.Content management Page 9
CDN Introduce • CDN issue • 1) Deciding the kind of content that should be hosted (replica placement) • 2) selecting the best replica for a given user • 3) designing mechanisms for transparent redirection of the users requests to the best replicas Page 10
OUTLINE • CDN introduce • Distributed Dynamic Replica Placement • Cloning of a replica • Replica removal • Redirection • Future work • Reference Page 11
Distributed Dynamic Replica • Distributed scheme to allocate and deallocate replicas, so that the user requests are satisfied while minimizing the CDN costs in a dynamic scenario • This scheme always accounts for the current replica placement,adding replicas or changing replica location only when needed. • Each site j ∈ VRautonomously decides on whether some of the replicas it stores should be cloned or removed. Page 12
Problem Formulation • VA: access nodes • VR: CDN servers sites • d(i, j): user (access node) i to a replica j • dmax: distance threshold • xi,c: the volume of user requests originated at node i ∈ VAfor content c ∈ C • Umax, Umid, Ulow: load threshold Page 13
Cloning of a replica • Function add_replica(j, c) • 1: lj,c=i∈VA αij,c · xi,c • 2: whilelj,c/rj,c− Umax > 0 • 3: best_served = 0 • 4: best_distance = ∞ • 5: best_vr = undefined • 6: for all j’ ∈ ρ(j) s.t. rj,c < VmaxRdo Page 14
Cloning of a replica • 7: l’j,c=i∈α(j’) αij,c · xi,c • 8: total_distance =i∈α(j’)αij,c · xi,c · di,j’ • 9: if (l’j’,c < best_served) ∨ • 10: (l’j’,c= best_served ∧ • 11: total_distance < best_distance) then • 12: best_distance = total_distance • 13: best_served = l’j’,c Page 15
Cloning of a replica • 14: best_vr = j’ • 15: end if • 16: end for • 17: if best_vr = undefined then • 18: exit • 19: end if • 20: ask best_vr to add a replica Page 16
Cloning of a replica • 21: compute l’’bestvr,c= min(i∈α(bestvr) αij,c · xi,c, 1) • 22: lj,c= lj,c − l’’bestvr,c • 23: remove from the set of requests those that can be offloaded • 24: end while Page 17
Replica removal • A replica can be removed if (and only if) it serves no requests • A replica is removed only when it has not been serving requests for a time long enough to bring the exponential average down to zero. Page 18
Redirection • Based on this feedback users requests are directed away from a replica in response to threshold events (if the replica load exceeds Umaxor falls below Ulow) • As an example, an underloaded replica informs the redirection system which then tries to offload requests to some other replicas (if possible) • A perfect load balancing may be impossible due to the distance constraint Page 19
Redirection Fig. A model for the redirection scheme Page 20
OUTLINE • CDN introduce • Distributed Dynamic Replica Placement • Cloning of a replica • Replica removal • Redirection • Future work • Reference Page 21
Future Work • comparison of different settings of the Umid • observe dmax and add remove replica relationship Page 22
Reference • [1] N. Bartolini, F. Lo Presti, and C. Petrioli, “Optimal dynamic replica placement in Content Delivery Networks,” in Proceedings of the 11th IEEE International Conference on Networks, ICON 2003, Sydney, Australia, September 28–October 1 2003, pp. 125–130. • [2] F. Lo Presti, C. Petrioli, and C. Vicari, “Dynamic replica placement in content delivery networks,” in Proceedings of MASCOTS 05, September 2005. • [3] F. Lo Presti, C. Petrioli, and C. Vicari, “Distributed Dynamic Replica Placement and Request Redirection in Content Delivery Networks ,” in Proceedings of MASCOTS 07, 2008. Page 23