Download speed - Rutgers ECE

Multicast Algorithms in Service
Overlay Networks
Dario Pompili*, Luca Lopez^, Caterina Scoglio+
*[email protected], ^[email protected], [email protected]
*Broadband and Wireless Networking Laboratory
Georgia Institute of Technology, Atlanta, GA 30332, USA
^Dipartimento di Informatica e Sistemistica
University “La Sapienza,” Rome 00184, Italy
+Department of Electrical and Computer Engineering
Kansas State University, Manhattan, KS 66506, USA
Infocom 2006, April 23-29
1
D. Pompili, L. Lopez, C. Scoglio, Multicast Algorithms in Service Overlay Networks, Infocom 2006
Outline
 Introduction to Overlay Networks
 Native Network vs. Virtual Overlay Network
 Unicast vs. Multicast Transmissions
 Multicast Applications
 Proposed Overlay Multicast Algorithms: DIMRO
and DIMRO-GS
 Performance Evaluation
 Conclusions and Future Work
2
D. Pompili, L. Lopez, C. Scoglio, Multicast Algorithms in Service Overlay Networks, Infocom 2006
Introduction to Overlay Networks
 Overlay routing enhances IP network reliability and performance by
forwarding traffic through intermediate overlay nodes [1-3]. This way:
– It can bypass congestion
– It can overcome transient outages
 Past research [4,5] focused on techniques for:
– Building overlay networks
– Evaluating their performance
[1] H. Zhang, J. Kurose, and D. Towsley, “Can an overlay compensate for a careless
underlay?” in Proceedings of IEEE INFOCOM 2006, Barcelona, Spain, Apr. 2006
[2] Y. Zhu, C. Dovrolis, and M. Ammar, “Dynamic overlay routing based on available
bandwidth estimation: A simulation study,” To appear in the Computer Networks Journal,
2006
[3] S. Y. Shi and J. S. Turner, “Routing in overlay multicast networks,” in Proceedings of IEEE
INFOCOM 2002, New York, NY, USA, June 2002
[4] D. Andersen, H. Balakrishnan, M. Kaashoek, and R. Morris, “Resilient overlay networks,”
in Proceedings of ACM Symposium on Operating Systems Principles, Banff, Canada, Oct.
2001
[5] A. Nakao, L. Peterson, and A. Bavier, “A routing underlay for overlay networks,” in
Proceedings of ACM SIGCOMM, Karlsruhe, Germany, Aug. 2003
3
D. Pompili, L. Lopez, C. Scoglio, Multicast Algorithms in Service Overlay Networks, Infocom 2006
Native Network vs. Virtual Overlay Network
 We consider two layers of network infrastructure:
– The native network, includes end-systems, routers, links, and the
associated routing functionality, and provides best-effort
datagram delivery between its nodes
– The virtual overlay network, formed by a subset of the native
layer nodes interconnected through overlay links to provide
enhanced services
 Overlay links are virtual in the sense that they are IP
tunnels over the native network
4
D. Pompili, L. Lopez, C. Scoglio, Multicast Algorithms in Service Overlay Networks, Infocom 2006
Unicast vs. Multicast Transmissions
 Unicast transmissions:
– The sender transmits data to a single receiver and, if multiple receivers
want the same data content, the sender has to transmit multiple copies
of data
 Multicast transmission:
– The sender transmits only one copy of data that is delivered to multiple
receivers
 A challenging objective in multicasting is to minimize the
amount of network resources to compute multicast trees
3 copies of
the same
message
Only 1 copy
of the
message
R2
S
Unicast
5
R2
S
R3
Multicast
R3
D. Pompili, L. Lopez, C. Scoglio, Multicast Algorithms in Service Overlay Networks, Infocom 2006
Multicast Applications
 We present two algorithms to build virtual multicast trees on an overlay
network for as many applications as:
– Live video, software and file distribution, replicated database, web site
replication, videoconference, distributed games, file sharing, periodic delivery
Source Specific
Group Shared
Real-time
Live video distribution
Videoconference,
distributed games
Non Realtime
Software and file distribution, replicated
database, server and web site replication,
periodic data delivery (sport scores,
magazines, newspapers)
6
File sharing,
collaborative
groupware, replicated
database
D. Pompili, L. Lopez, C. Scoglio, Multicast Algorithms in Service Overlay Networks, Infocom 2006
Proposed Overlay Multicast Algorithms
 DIMRO: DIstributed Multicast algorithm for Internet Resource
Optimization
– It builds virtual source rooted multicast trees for source specific
applications
– It takes the virtual link available bandwidth into account to avoid traffic
congestion and fluctuation, which cause low network performance
 DIMRO-GS: DIstributed Multicast algorithm for Internet
Resources Optimization in Group Shared applications
– It constructs a virtual shared tree for group shared applications
– It connects each member node to all the other member nodes with a
source rooted tree computed using DIMRO
 Both DIMRO and DIMRO-GS algorithms offer service differentiation,
i.e., they provide QoS at the application layer without IP-layer support
7
D. Pompili, L. Lopez, C. Scoglio, Multicast Algorithms in Service Overlay Networks, Infocom 2006
DIMRO: Objectives
 Most of the algorithms in the literature focus on computing multicast
trees for real-time applications (delay sensitive)
– Bandwidth is often taken into account only as a constraint
– Optimization involves only one tree, and not all trees for different
multicast groups
 DIMRO optimizes the overlay network performance when multiple
multicast comunications should take place
 The objective is to exploit the network resource in an efficient way
 The available bandwidth on each virtual link plays a key role in the
multicast tree research
8
D. Pompili, L. Lopez, C. Scoglio, Multicast Algorithms in Service Overlay Networks, Infocom 2006
DIMRO: Motivations
 If the overlay available bandwidth
is not esplicitely taken into
account the risk is to:
– Overload some link
– Leave some other link
unexploited
 Load balancing is NOT achieved
if cost does not explicitely take
available bandwidth on links into
account
SA
R2A
SB
R2B
R1A
Overloaded Link
Unexploited Link
9
R3B
D. Pompili, L. Lopez, C. Scoglio, Multicast Algorithms in Service Overlay Networks, Infocom 2006
R1B
DIMRO: Steps of the Algorithm
1. Receivers are ordered according to decreasing
Step 1
requested bit rates
s Step01
0
2. The optimum path between the sender and the
Step 3
receiver with the highest requested rate is
0
computed
3. Then, paths connecting other receivers are
computed, according to the decreasing order
4. The kth receiver rk is connected to the sender s by
using that path p(s,rk) that minimizes the following
objective function:
auv
f p( s, rk ) 


Buv  (buv  Fk )


1


{( u ,v ) p ( s , rk )}
uv
•
•
•
•
•
10
Buv: total bandwidth of virtual link (u,v)
buv: available bandwidth of virtual link (u,v)
Fk: cumulative rate by the kth receiver rk
auv: binary variable that equals 0 if link (u, v)
already belongs to the tree, 1 otherwise
V and E: number of vertexes and edges in the
overlay network
uv 
Buv
0, (u, v)  T
auv  
1, (u, v)  T
Step 1
0
r1
1024 Kbps
Step 2
0
r2
Step 3512 Kbps
0
r3
256 Kbps
Buv   uv

Buv
   (| V |, | E |, F , B )
D. Pompili, L. Lopez, C. Scoglio, Multicast Algorithms in Service Overlay Networks, Infocom 2006
DIMRO-GS: the Algorithm
 DIMRO-GS (Group Shared DIMRO) is the extension of DIMRO to
the multicast shared tree case
 For M group members, the virtual shared tree is set up by building M
virtual source rooted trees, each one having a different group
member as root and all the other members belonging to the tree
 Each source rooted tree is built using DIMRO
 If each group member has the same bandwidth requirement, the first
step of DIMRO is skipped
 When M source rooted trees are computed, the virtual shared tree is
completed
 DIMRO computational complexity: O(M · |V| · |E|)
– It builds the virtual multicast tree by computing for as many as M times
the spanning tree using the Bellman-Ford algorithm, whose complexity
is O(|V| · |E|)
 DIMRO-GS computational complexity: O(M2 · |V| · |E|)
– It runs DIMRO M times
11
D. Pompili, L. Lopez, C. Scoglio, Multicast Algorithms in Service Overlay Networks, Infocom 2006
Simulation Scenario
 A random overlay network has been
generated following the Waxman’s
model [6], with parameters (α,β)
 The bandwidth capacity Buv of each
virtual link (u, v) is randomly
generated using a uniform
distribution with mean B = 100Mbps
 Two different one hundred node
random overlay networks are
generated
 Network 2 has a higher number of
links than Network 1
 Two metrics are used to compare
the competing algorithms, the
Rejection Rate and the Network
Load
α
β
B
nodes
Network
1
0.2
0.4
100Mbps
100
Network
2
0.3
0.6
100Mbps
100
Re jection Rate 

 
( u ,v )
# Re jeted Trees
# Re quested Trees
uv

[6] B. M. Waxman, “Routing of multipoint connections,” IEEE Journal on Selected
Areas in Communications, vol. 6, no. 9, pp. 1617–1622, Dec. 1988
12
D. Pompili, L. Lopez, C. Scoglio, Multicast Algorithms in Service Overlay Networks, Infocom 2006
DIMRO: Performance Evaluation in Network 1
In Network 1, the DIMRO Rejection Rate is lower than the Rejection Rate of
the Optimal solution of the Steiner Tree Problem (OSTP) with cuv= 1
The DIMRO Network Load is the same as the OSTP Network Load until the
Rejection Rate is the same. Then, since DIMRO rejects less trees, its Network
Load becomes higher than the OSTP one
13
D. Pompili, L. Lopez, C. Scoglio, Multicast Algorithms in Service Overlay Networks, Infocom 2006
DIMRO: Performance Evaluation in Network 2
In Network 2, the DIMRO Rejection Rate is significantly lower than the OSTP
Rejection Rate (less unavoidable bottlenecks exist). Since Network 2 has a
higher number of links, the number of possible paths between two nodes
increases. Thus, it is easier for DIMRO to avoid bottlenecks
A lower Network Load with a higher Rejection Rate proves that OSTP does
not efficiently use the available network resources
14
D. Pompili, L. Lopez, C. Scoglio, Multicast Algorithms in Service Overlay Networks, Infocom 2006
DIMRO-GS: Performance Evaluation in Network 1
When the Number of Requested Trees increases, the FTM Rejection Rate
becomes significantly higher than the one of DIMRO-GS, since FTM uses a
higher amount of network resources
In fact, when the Number of Requested Trees increases, the FTM Network
Load becomes significantly higher than the DIMRO-GS Network Load
15
D. Pompili, L. Lopez, C. Scoglio, Multicast Algorithms in Service Overlay Networks, Infocom 2006
DIMRO-GS: Performance Evaluation in Network 2
Network resources saturate later when DIMRO-GS is used, which causes a
lower Rejection Rate
In Network 2, DIMRO-GS achieves a lower Rejection Rate and Network Load
Note that in Network 1 bottlenecks do not allow efficiently exploiting all
available network resources
16
D. Pompili, L. Lopez, C. Scoglio, Multicast Algorithms in Service Overlay Networks, Infocom 2006
Conclusions and Future Work
Two algorithms for multicast applications in service overlay networks were
presented
The first builds virtual source rooted multicast trees for source specific
applications
The second constructs a virtual shared tree for group shared applications
Their objective is to achieve traffic balancing on the overlay network to avoid
traffic congestion and fluctuation, which cause low network performance
The algorithms actively probe the underlay network and compute virtual
multicast trees by dynamically selecting the least loaded available paths on the
overlay network
Future research will focus on dynamic multicast groups, and on the
interactions between the overlay and the underlay network
17
D. Pompili, L. Lopez, C. Scoglio, Multicast Algorithms in Service Overlay Networks, Infocom 2006