Architecture and Topology - ITTCjpgs/courses/hsnets/lecture-arch-topo-hsn-print.pdf · KU EECS 881...
Transcript of Architecture and Topology - ITTCjpgs/courses/hsnets/lecture-arch-topo-hsn-print.pdf · KU EECS 881...
KU EECS 881 – High-Performance Networking – Architecture and Topology
– 1 –
© James P.G. SterbenzITTCHigh-Performance Networking
The University of Kansas EECS 881Architecture and Topology
© 2004–2010 James P.G. Sterbenz02 September 2010
James P.G. Sterbenz
Department of Electrical Engineering & Computer ScienceInformation Technology & Telecommunications Research Center
The University of Kansas
http://www.ittc.ku.edu/~jpgs/courses/hsnets
rev. 10.0
02 September 2010 KU EECS 881 – High-Speed Networking – Topology HSN-AT-2
© James P.G. SterbenzITTC
Network Architecture and TopologyOutline
AT.1 Topology and geographyAT.2 ScaleAT.3 Resource tradeoffs
KU EECS 881 – High-Performance Networking – Architecture and Topology
– 2 –
02 September 2010 KU EECS 881 – High-Speed Networking – Topology HSN-AT-3
© James P.G. SterbenzITTC
Network Architecture and TopologyOutline
AT.1. Topology and geographyAT.2. Scale AT.3. Resource Tradeoffs
network
application
session
transport
network
link
end system
network
link
node
network
link
nodenetwork
link
node
application
session
transport
network
link
end system
02 September 2010 KU EECS 881 – High-Speed Networking – Topology HSN-AT-4
© James P.G. SterbenzITTC
Network Architecture and TopologyTopology and Geography
AT.1 Topology and geographyAT.1.1 ScalabilityAT.1.2 LatencyAT.1.3 BandwidthAT.1.4 Virtual overlays and lightpathsAT.1.5 Practical constraints
AT.2 ScaleAT.3 Resource tradeoffs
KU EECS 881 – High-Performance Networking – Architecture and Topology
– 3 –
02 September 2010 KU EECS 881 – High-Speed Networking – Topology HSN-AT-5
© James P.G. SterbenzITTC
Ideal Network ModelNetwork Path Principle
Network Path Principle N-II
The network must provide high-bandwidth low-latency paths between end systems.
networkCPU
M app
end system
D = 0
R = ∞
zero latency
infinite bandwidth
CPU
M app
end system
02 September 2010 KU EECS 881 – High-Speed Networking – Topology HSN-AT-6
© James P.G. SterbenzITTC
Link TopologiesShared Medium
• Shared medium (e.g. bus topology)problems?
KU EECS 881 – High-Performance Networking – Architecture and Topology
– 4 –
02 September 2010 KU EECS 881 – High-Speed Networking – Topology HSN-AT-7
© James P.G. SterbenzITTC
Link TopologiesShared Medium
• Shared medium (e.g. bus topology)– topology constrained by medium
• longest path• limited to LAN lengths due to delay
02 September 2010 KU EECS 881 – High-Speed Networking – Topology HSN-AT-8
© James P.G. SterbenzITTC
Link TopologiesShared Medium
• Shared medium (e.g. bus topology)– topology constrained by medium
• longest path• limited to LAN lengths due to delay
Network scalability?
KU EECS 881 – High-Performance Networking – Architecture and Topology
– 5 –
02 September 2010 KU EECS 881 – High-Speed Networking – Topology HSN-AT-9
© James P.G. SterbenzITTC
Link TopologiesShared Medium
• Shared medium (e.g. bus topology)– topology constrained by medium
• longest path• limited to LAN lengths due to delay
• Limited scalability– all hosts share capacity of bus
02 September 2010 KU EECS 881 – High-Speed Networking – Topology HSN-AT-10
© James P.G. SterbenzITTC
Link TopologiesShared Medium
• Shared medium (e.g. bus topology)– topology constrained by medium
• longest path• limited to LAN lengths due to delay
• Limited scalability– all hosts share capacity of bus – contention for shared medium
KU EECS 881 – High-Performance Networking – Architecture and Topology
– 6 –
02 September 2010 KU EECS 881 – High-Speed Networking – Topology HSN-AT-11
© James P.G. SterbenzITTC
Link TopologiesShared Medium
• Shared medium (e.g. bus topology)– topology constrained by medium
• longest path• limited to LAN lengths due to delay
• Limited scalability– all hosts share capacity of bus – contention for shared medium
• collisions in shared medium• need MAC (medium access control)
02 September 2010 KU EECS 881 – High-Speed Networking – Topology HSN-AT-12
© James P.G. SterbenzITTC
Link TopologiesShared Medium
• Shared medium (e.g. bus topology)– topology constrained by medium
• longest path• limited to LAN lengths due to delay
• Limited scalability– all hosts share capacity of bus – contention for shared medium
• collisions in shared medium• need MAC (medium access control)
• Example– original DIX Ethernet
KU EECS 881 – High-Performance Networking – Architecture and Topology
– 7 –
02 September 2010 KU EECS 881 – High-Speed Networking – Topology HSN-AT-13
© James P.G. SterbenzITTC
Link TopologiesPoint-to-Point Mesh
• Point-to-point links between switches– space division mesh
02 September 2010 KU EECS 881 – High-Speed Networking – Topology HSN-AT-14
© James P.G. SterbenzITTC
Link TopologiesPoint-to-Point Mesh
• Point-to-point links between switches– space division mesh
Network scalability?
KU EECS 881 – High-Performance Networking – Architecture and Topology
– 8 –
02 September 2010 KU EECS 881 – High-Speed Networking – Topology HSN-AT-15
© James P.G. SterbenzITTC
Link TopologiesPoint-to-Point Mesh
• Point-to-point links between switches– space division mesh
• Scalable:– add links and expand switches
02 September 2010 KU EECS 881 – High-Speed Networking – Topology HSN-AT-16
© James P.G. SterbenzITTC
Link TopologiesPoint-to-Point Mesh
• Point-to-point links between switches– space division mesh
• Scalable:– add links and expand switches– add switches
KU EECS 881 – High-Performance Networking – Architecture and Topology
– 9 –
02 September 2010 KU EECS 881 – High-Speed Networking – Topology HSN-AT-17
© James P.G. SterbenzITTC
Scalable TopologiesMesh vs. Shared Medium
Scalability of Mesh Topologies N-II.4
Mesh network technologies scale better then shared medium. Use power control and directional antennæ to increase spatial reuse in shared medium wireless networks.
02 September 2010 KU EECS 881 – High-Speed Networking – Topology HSN-AT-18
© James P.G. SterbenzITTC
LatencyNetwork Path
Network Latency Principle N-1Al
The latency along a path is the sum of all its components. The benefit of optimising an individual link is directly proportional to its relative contribution to the end-to-end latency.
short path
D = ∑di
di
long path
KU EECS 881 – High-Performance Networking – Architecture and Topology
– 10 –
02 September 2010 KU EECS 881 – High-Speed Networking – Topology HSN-AT-19
© James P.G. SterbenzITTC
LatencyTopology and Geography
• Constituents of network latency D = (h–1)ds + ∑hdi– Geography: speed of light delay di
– Topology: number of hops h; switching delay ds
Network Diameter Principle N-1AhThe number of per hop latencies along a path is bounded by the diameter of the network. The network topology should keep the diameter low.
480 ms
72 000 km
GEO
1 μs
100 m
SAN
6 – 45 min200 ms1 ms10 μsRTT
400×106 km20 000 km100 km1 kmDia
MarsWANMANLAN
02 September 2010 KU EECS 881 – High-Speed Networking – Topology HSN-AT-20
© James P.G. SterbenzITTC
BandwidthNetwork Path
Network Bandwidth Principle N-1Ab
The maximum bandwidth along a path is limited by the minimum bandwidth link or node, which is the bottleneck. There is no point in optimising a link that is not a bottleneck.
bottleneck
R = min(ri)
ri
long path
KU EECS 881 – High-Performance Networking – Architecture and Topology
– 11 –
02 September 2010 KU EECS 881 – High-Speed Networking – Topology HSN-AT-21
© James P.G. SterbenzITTC
Overlay NetworksAbstract and Hide Underlying Network
• Overlay networks hide underlying topology– VPNs (virtual private networks)– secure overlay sessions– datagram overlay meshes– lightpaths
Network Overlay Principle N-IIo
Overlay networks must provides the same high-performance paths as he physical networks. The number of overlay layers should be kept as small as possible, and overlays must be adaptable based on end-to-end path requirements and topology information form the lower layers.
02 September 2010 KU EECS 881 – High-Speed Networking – Topology HSN-AT-22
© James P.G. SterbenzITTC
Overlay NetworksLightpath Assignment
• Lightpath assignment problem– preserve high-performance along overlay such that– no link carries more than one light path of given wavelength
λ2
λ3
λ1
λ4
KU EECS 881 – High-Performance Networking – Architecture and Topology
– 12 –
02 September 2010 KU EECS 881 – High-Speed Networking – Topology HSN-AT-23
© James P.G. SterbenzITTC
Network Architecture and TopologyNetwork Scale
AT.1 Topology and geographyAT.2 Scale
AT.2.1 Network engineeringAT.2.2 HierarchyAT.2.3 Bandwidth aggregation and isolationAT.2.4 Latency optimisationAT.2.5 Wireless network densityAT.2.5 Practical constraints
AT.3 Resource tradeoffs
02 September 2010 KU EECS 881 – High-Speed Networking – Topology HSN-AT-24
© James P.G. SterbenzITTC
Network ScaleNetwork Engineering Parameters
highlowlowhighdensely connected
lowhighhighlowsparsely connected
aggregationdiameter# nodesdegreetopology
Network Scaling Principle N-5Ct
Networks should be able to scale in size while balancing switch cost against hop count.
sparse dense
KU EECS 881 – High-Performance Networking – Architecture and Topology
– 13 –
02 September 2010 KU EECS 881 – High-Speed Networking – Topology HSN-AT-25
© James P.G. SterbenzITTC
Network ScaleHierarchy
• Hierarchy– important technique to
• control latencyand aggregation
• bound state maintained
– divide network into clusters• state aggregated per cluster• examples: Nimrod, P-NNI
Network Hierarchy Principle N-5C
Use hierarchy and clustering to manage network scale and complexity, and reduce the overhead of routing algorithms.
α
A1
2 3
4
B
3
1 2
C 9
6 8
4
02 September 2010 KU EECS 881 – High-Speed Networking – Topology HSN-AT-26
© James P.G. SterbenzITTC
Network ScaleAggregation, Isolation, Latency
• Physical hierarchy to– limit number of hops and control aggregation– example: Internet (NSFNET) prior to 1994
regional net
LAN
neighborhood
DAN
personal net home
MAN
Backbone WAN
KU EECS 881 – High-Performance Networking – Architecture and Topology
– 14 –
02 September 2010 KU EECS 881 – High-Speed Networking – Topology HSN-AT-27
© James P.G. SterbenzITTC
Network ScaleAggregation, Isolation, Latency
Hierarchy to Aggregate and Isolate Bandwidth N-5B
Use hierarchy to manage bandwidth aggregation in the core of the network, and to isolate clusters of traffic locality from one another.
• Hierarchy: bandwidth isolation– isolate bandwidth in different subnet layers– exploit locality at network edge
• e.g. within campus or enterprise network
– aggregate bandwidth in network core
02 September 2010 KU EECS 881 – High-Speed Networking – Topology HSN-AT-28
© James P.G. SterbenzITTC
Network ScaleAggregation, Isolation, Latency
Hierarchy to Minimise Latency N-5Cl
Use hierarchy and cluster size to minimise network diameter and resultant latency.
• Hierarchy: latency engineering– control network diameter and latency– engineer low diameter at each level– shallow hierarchy ≈ 3 – 5 levels
• home network or LAN• access or campus network• MAN• WAN backbone
KU EECS 881 – High-Performance Networking – Architecture and Topology
– 15 –
02 September 2010 KU EECS 881 – High-Speed Networking – Topology HSN-AT-29
© James P.G. SterbenzITTC
Network ScaleWireless Network Density
Wireless Density Control to Optimise Degree and N-5Cw
Diameter Use density control and long link overlays to optimise the tradeoff between dense low-diameter and sparse high-diameter wireless networks.
no control power control overlay
• Transmission power gives tradeoff between– transmission range– degree of connectivity
02 September 2010 KU EECS 881 – High-Speed Networking – Topology HSN-AT-30
© James P.G. SterbenzITTC
Network ScalePractical Constraints
• Policy-based routing• Network provider deployment
– complex topologies– peering not high-performance– many hops/POP
Backbone S
Backbone W
MAN V
Backbone A
MAN B2
1
Administrative Constraints Increase the N-III.2
Importance of Good Design Policy and administrative constraints distort the criteria that govern the application of many high-performance network design principles. The importance of good (principled) design is elevated when these constraints are present.
KU EECS 881 – High-Performance Networking – Architecture and Topology
– 16 –
02 September 2010 KU EECS 881 – High-Speed Networking – Topology HSN-AT-31
© James P.G. SterbenzITTC
Network Architecture and TopologyResource Tradeoffs
AT.1 Topology and geographyAT.2 ScaleAT.3 Resource tradeoffs
AT.3.1 Bandwidth, processing, and memoryAT.3.2 Latency as a constraintAT.3.3 Relative scaling with high speedAT.2.4 Active networking
02 September 2010 KU EECS 881 – High-Speed Networking – Topology HSN-AT-32
© James P.G. SterbenzITTC
Resource TradeoffsResources and Constraints
• Network is a collection of resources and constraints:P processing M memoryB bandwidth E energy or powerL latency
• Relative composition– must be balanced to optimise cost and performance– determine topology, engineering, and functional placement
Network Resource Tradeoff & Engineering Principle N-2
Networks are collections of resources. The relative compositionof these resources must be balanced to optimise cost and performance, and to determine network topology, engineering, and functional placement.
KU EECS 881 – High-Performance Networking – Architecture and Topology
– 17 –
02 September 2010 KU EECS 881 – High-Speed Networking – Topology HSN-AT-33
© James P.G. SterbenzITTC
Resource TradeoffsResources and Constraints
• Network is a collection of resources and constraints:P processing M memoryB bandwidth E energy or powerL latency
• Relative composition– must be balanced to optimise cost and performance– determine topology, engineering, and functional placement
• Objective function to determine optimal mixƒ(π(P), β(B), μ(M), ε(E), λ(L))
02 September 2010 KU EECS 881 – High-Speed Networking – Topology HSN-AT-34
© James P.G. SterbenzITTC
Resource TradeoffsExample3.5 Content Cache Location
• Example:content cache location$(B) = ∞, $(M) = 0
⇒ where goes the content?
KU EECS 881 – High-Performance Networking – Architecture and Topology
– 18 –
02 September 2010 KU EECS 881 – High-Speed Networking – Topology HSN-AT-35
© James P.G. SterbenzITTC
Resource TradeoffsExample3.5 Content Cache Location
• Example: content cache location$(B) = ∞, $(M) = 0
⇒ everyone has local copy of everything$(B) = 0, $(M) = ∞
⇒ where goes the content?
02 September 2010 KU EECS 881 – High-Speed Networking – Topology HSN-AT-36
© James P.G. SterbenzITTC
Resource TradeoffsExample3.5 Content Cache Location
• Example: content cache location$(B) = ∞, $(M) = 0
⇒ everyone has local copy of everything$(B) = 0, $(M) = ∞
⇒ single copy on server: stream every time demanded
KU EECS 881 – High-Performance Networking – Architecture and Topology
– 19 –
02 September 2010 KU EECS 881 – High-Speed Networking – Topology HSN-AT-37
© James P.G. SterbenzITTC
Resource TradeoffsExample3.5 Content Cache Location
• Example: content cache location$(B) = ∞, $(M) = 0
⇒ everyone has local copy of everything$(B) = 0, $(M) = ∞
⇒ single copy on server: stream every time demandedis this realistic?
02 September 2010 KU EECS 881 – High-Speed Networking – Topology HSN-AT-38
© James P.G. SterbenzITTC
Resource TradeoffsExample3.5 Content Cache Location
• Example: content cache location$(B) = ∞, $(M) = 0
⇒ everyone has local copy of everything$(B) = 0, $(M) = ∞
⇒ single copy on server: stream every time demandedM and B both have finite (and bounded cost): solution?
KU EECS 881 – High-Performance Networking – Architecture and Topology
– 20 –
02 September 2010 KU EECS 881 – High-Speed Networking – Topology HSN-AT-39
© James P.G. SterbenzITTC
normalized depth
cost
bandwidth
root leaves
Resource TradeoffsExample3.5 Content Cache Location
• Example: content cache location– plot cost of bandwidth vs. depth in network distribution tree
02 September 2010 KU EECS 881 – High-Speed Networking – Topology HSN-AT-40
© James P.G. SterbenzITTC
normalized depth
cost
bandwidth
memory
root leaves
Resource TradeoffsExample3.5 Content Cache Location
• Example: content cache location– plot cost of bandwidth vs. depth in network distribution tree– plot cost of memory "
KU EECS 881 – High-Performance Networking – Architecture and Topology
– 21 –
02 September 2010 KU EECS 881 – High-Speed Networking – Topology HSN-AT-41
© James P.G. SterbenzITTC
normalized depth
cost
bandwidth
memory
root leaves
Resource TradeoffsExample3.5 Content Cache Location
• Example: content cache location– plot cost of bandwidth
– plot cost of memorywhat next?
02 September 2010 KU EECS 881 – High-Speed Networking – Topology HSN-AT-42
© James P.G. SterbenzITTC
normalized depth
cost
bandwidth
memory
lopt root leaves
Resource TradeoffsExample3.5 Content Cache Location
• Example: content cache location– plot cost of bandwidth
– plot cost of memorylopt = min[β(B) + μ(M)]
• optimal level l
KU EECS 881 – High-Performance Networking – Architecture and Topology
– 22 –
02 September 2010 KU EECS 881 – High-Speed Networking – Topology HSN-AT-43
© James P.G. SterbenzITTC
normalized depth
cost
bandwidth
memory
lopt root leaves llat
Resource TradeoffsExample3.5 Content Cache Location
• Example: content cache location– plot cost of bandwidth
– plot cost of memorylopt = min[β(B) + μ(M)]
• optimal level l– latency constrains level
• maximum distancefrom client
lopt = max(lLmax, lopt)
02 September 2010 KU EECS 881 – High-Speed Networking – Topology HSN-AT-44
© James P.G. SterbenzITTC
Resource TradeoffsRelative Scaling
• Relative scaling of resources is important– if all resources/constraints scale uniformly, no change– speed of light remains constant
• latency becomes relatively more important • bandwidth-×-delay product requires increasing M
– technology scales non-uniformly• example: Moore’s law increase in P
– enables IP lookup/classification in hardware, active networking
Resource Tradeoffs Change and Enable New N-2A
Paradigms The relative cost of resources and constraints changes over time due to non-uniform advances in different aspects of technology. This should motivate constant rethinkingabout the way in which networks are structured and used.
KU EECS 881 – High-Performance Networking – Architecture and Topology
– 23 –
02 September 2010 KU EECS 881 – High-Speed Networking – Topology HSN-AT-45
© James P.G. SterbenzITTC
Resource TradeoffsActive Networking
• Decreasing cost of processing and memory– enables more computation in the network nodes
• Active networking– strong AN
• users inject capsules of code• executed on nodes
– moderate AN• network service providers provisions protocols and services• may be dynamically provisioned with active packets
02 September 2010 KU EECS 881 – High-Speed Networking – Topology HSN-AT-46
© James P.G. SterbenzITTC
High-Performance NetworkingAcknowledgements
The material in these foils comes from the textbook supplementary materials:
• Sterbenz & Touch,High-Speed Networking:A Systematic Approach toHigh-Bandwidth Low-Latency Communicationhttp://hsn-book.sterbenz.org