study on adaptation of cdn request-routing to scalable conference system
Post on 01-Feb-2016
18 Views
Preview:
DESCRIPTION
TRANSCRIPT
1
Study on Adaptation of CDN Request-Routing
to Scalable Conference System
Toshiyuki KAWASAKI* Koji OKAMURA*** Graduate School of Information Science and
Electrical Engineering (ISEE), Kyushu University** Computing and Communications Center,
Kyushu University
Aug 28,2003
2
1. Background
2. Goal and approach
3. Evaluation
4. Consideration
5. Conclusion
Contents
3
• H.323 conference system is popular– Remote conference
– Remote medical care
– Remote education
• H.323– Standard of video conference
on IP networks
• MCU(Multipoint Control Unit)– Enable multipoint conference
– Mixing the video and audio streams
Host A Host B
Host A Host B
Host C Host D
1. Background - H.323 conference system
4
1 . Background - Overload of MCU
• Problem of H.323 multipoint conference systemWhen hosts (participants) increase ・・・
MCU may become overload → load sharing is needed MCU
←overload
• Existing method of load sharing– Distribute the load to several MCUs
When more hosts increase → MCUs may become overload after all
Lack of scalability for the number of hosts
←overload
5
Proposal method • Don’t use any MCUs
• Hosts connect with each other
• Hosts play a role of MCUs– Hosts distribute load – increase of hosts
→ increase of MCUs
2. Goal and approach - Load Sharing by Hosts
Obtain scalability for the number of hosts
Existing method
Proposal method
6
• Problem of the multipoint conference system without MCU– Each host should select the host which it connects with.
• Existing method– ALM ( Application Level Multicast)
• Multicast on logical network (overlay network)• Hosts play the role of multicast router on logical network.
2. Goal and approach - Application Level Multicast
Lobby server
New host
Entry
IP address list
Make links
AS1AS2
Make high cost links between ASs
Overlay network
7
2. Goal and approach - ORIO and CDN Request Routing
• Proposal method ORIO( Optimal Routing Inter Organization)– Using CDN Request-Routing
• CDN ( Content Delivery Network )– Network of severs to distribute content efficiently– Load sharing by using many surrogates
• Request Routing– Select the optimal surrogate for the clients– Tell clients their optimal surrogates
Origin server
surrogate surrogatesurrogate surrogate
client clientclientclientclientclient
Redirection server
contents
request
select
notify
notifyDeliverycontents
8
• Process of participation at ORIO– Request Routing using DNS
• Prepare DNS to redirect requests.• New participants write the certain host name for participation into the packets destination address.• DNS tell the optimal hosts IP address at name resolution.
→ Connected with its optimal host automatically
2. Goal and approach - Request routing using DNS
New host
DNS server
conference.ac.jp ( host name )133.x.x.xxx
133.x.x.xxx ( IP address )
select
connect
AS 1
AS 3
AS 2
9
3. Evaluation - Evaluation Environment
• Evaluation standard– Maximum network load
• Comparing with the method using ALM
• Experimental Network– SuperSINET– The number of ASs is 18– The number of hosts per ASs is 64
• Environment– Speakers※ 1、 Hosts※ 1~2
56• Change distribution of hosts• Change the number of active AS
– Speakers 1~128、 Hosts128
Experimental Network ( SuperSINET )
Simulation based evaluation using network simulator “NS2”
※Speakers = the number of source hosts, hosts = the number of destination hosts
10
3. Evaluation - simulation under the 3 distribution of hosts
• Speakers 1 , Hosts 1~256– Distribute hosts to 6 ASs– Measure under the 3 distrib
ution of hosts• Concentrate at 1 area• Concentrate at 2 areas• Concentrate at 3 areas
• Result– the increase amount of network load is decreasing as the number
of participants increase
→ Scalability to the number of hosts.
– ORIO is better than ALM at load sharing
Maximum use of bandwidth (kbps)
The number of hosts
1 area (ORIO) 2 area (ORIO)
3 area (ORIO)
1 area (ALM)
2 area (ALM)
3 area (ALM)
11
3.Evaluation - Change the number of ASs
• Speakers1,Hosts 1~256– Changing the number of A
Ss which hosts belong to• Select hosts from 6 ASs
• Select hosts from 12 ASs
• Select hosts from 18 ASs
• Result– ORIO is better than ALM at load sharing
– ORIO’s efficiency of load sharing become worse when the number of AS is small ( hosts per AS is big).
→ Policy of routing within AS should be improved.
The number of hosts
Maximum use of bandwidth (kbps)
12
3.Evaluation - Speakers
• Change the number of Speakers Speakers 1~128 Hosts 128– Select hosts randomly
• Result– Network load increase linearly at both ORIO and ALM.
→ Don’t provide scalability in this case.
The number of speakers should be limited.
Maximum use of bandwidth (Mbps)
The number of speakers
13
• ORIO provide more efficient load sharing than ALM
• Possible reason・ ALM uses logical network for routing,
but ORIO doesn’t use it.
In ALM, there are two restrictions in receiving streams
• Receivable only from its neighbors on the overlay network
• Receivable only from its upstream hosts
4. Consideration - Efficiency of ORIO and restriction of ALM
14
• Receivable only from its neighbors on the overlay network
• Receivable only from its upstream hosts→ Promote the concentration of the load
4. Consideration - restriction of ALM
Router Router
Host B
Concentrate the loadConcentrate the load
Host B
Speaker Speaker
Host A Host A
Host C Host C
Not neighbor
Can’t use thislink though it is useful
router router
Host B
Concentrate the loadConcentrate the load
Host B
speaker speaker
Host A Host A
Host C Host C
B is not A’s upstream host(B’s delay is bigger than A)
Can’t use thislink though it is useful
delay5ms
delay10ms
delay7ms
delay7ms
delay10ms
delay5ms
delay9ms
delay9ms
delay7ms
delay7ms
15
• Existing multipoint conference system– MCU easily become overload
• Method of load sharing– Any MCU is not used– Hosts play a role of MCUs instead
• The system which tells the hosts their connection partner is required– CDN Request-Routing
• Result– Prove the scalability of ORIO
• Future work– Adding the function which support the hosts exi
ting process– Improve the policy of routing within AS
5. Conclusion
top related