SlideShare una empresa de Scribd logo
1 de 35
Descargar para leer sin conexión
Data Center
Network Topologies

.

Raj Jain
Washington University in Saint Louis
Saint Louis, MO 63130
Jain@cse.wustl.edu
These slides and audio/video recordings of this class lecture are at:
http://www.cse.wustl.edu/~jain/cse570-13/
Washington University in St. Louis

http://www.cse.wustl.edu/~jain/cse570-13/

3-1

©2013 Raj Jain
Overview
1.
2.
3.
4.
5.

Data Center Physical Layout
Data Center Network Topologies
ToR vs. EoR
Data Center Networking Issues
Data Center Networking Requirements

Washington University in St. Louis

http://www.cse.wustl.edu/~jain/cse570-13/

3-2

©2013 Raj Jain
Google’s Data Center

Source: http://webodysseum.com/technologyscience/visit-the-googles-data-centers/
http://www.cse.wustl.edu/~jain/cse570-13/
Washington University in St. Louis

3-3

©2013 Raj Jain
Cooling Plant

Source: http://webodysseum.com/technologyscience/visit-the-googles-data-centers/
http://www.cse.wustl.edu/~jain/cse570-13/
Washington University in St. Louis

3-4

©2013 Raj Jain
Modular Data Centers







Small: < 1 MW, 4 racks per unit
Medium: 1-4 MW, 10 racks per unit
Large: > 4 MW, 20 racks per unit
Built-in cooling, high PUE (power usage effectiveness) 1.02
PUE = Power In/Power Used
Rapid deployment

Ref: http://www.sgi.com/products/data_center/ice_cube_air/
http://www.cse.wustl.edu/~jain/cse570-13/
Washington University in St. Louis

3-5

©2013 Raj Jain
Containerized Data Center






Ready to Use. Connect to water and
power supply and go.
Built in cooling. Easy to scale.
 Data Center trailer parks.
Suitable for disaster recovery, e.g., flood,
earthquake
Offered by Cisco, IBM, SGI,
Sun/ORACLE,…

Ref: Datacenter Infrastructure – mobile Data Center from Emerson Network Power
, http://en.m-info.ua/180-container-data-center/755-datacenter-infrastructure-mobile-data-center-from-emerson-network-power
Ref: http://www.datacenterknowledge.com/archives/2010/05/31/iij-will-offer-commercial-container-facility/
http://www.cse.wustl.edu/~jain/cse570-13/
Washington University in St. Louis
©2013 Raj Jain

3-6
Unstructured Cabling

Source: http://webodysseum.com/technologyscience/visit-the-googles-data-centers/
Washington University in St. Louis

http://www.cse.wustl.edu/~jain/cse570-13/

3-7

©2013 Raj Jain
Structured Cabling

Source: http://webodysseum.com/technologyscience/visit-the-googles-data-centers/
Washington University in St. Louis

http://www.cse.wustl.edu/~jain/cse570-13/

3-8

©2013 Raj Jain
Data Center Equipment Cabinets
Three Layers: Bottom: Signal,
Middle: Power, Top: Fiber

Minimize patching between
cabinets and racks

Cabling under raised
floors provides better
appearance and cooling

Ref: Ref: C. DiMinico, "Telecommunications Infrastructure Standard for Data Centers," IEEE 802.3 HSSG Meeting, Nov. 2006,
http://www.ieee802.org/3/hssg/public/nov06/diminico_01_1106.pdf
http://www.cse.wustl.edu/~jain/cse570-13/
Washington University in St. Louis
©2013 Raj Jain

3-9
Data Center Physical Layout

Washington University in St. Louis

http://www.cse.wustl.edu/~jain/cse570-13/

3-10

©2013 Raj Jain
ANSI/TIA-942-2005 Standard







Main Distribution
Area (MDA)
Horizontal
Distribution Area
(HDA)
Equipment
Distribution Area
(EDA)
Zone Distribution
Area (ZDA)

Source: Santana 2014
Washington University in St. Louis

http://www.cse.wustl.edu/~jain/cse570-13/

3-11

©2013 Raj Jain
ANSI/TIA-942-2005 Standard
Computer Room: Main servers
 Entrance Room: Data Center to external cabling
 Cross-Connect: Enables termination of cables
 Main Distribution Area (MDA): Main cross connect. Central
Point of Structured Cabling. Core network devices
 Horizontal Distribution Area (HDA): Connections to active
equipment.
 Equipment Distribution Area (EDA): Active Servers+Switches.
Alternate hot and cold aisle.
 Zone Distribution Area (ZDA): Optionally between HDA and
EDA. ZDA allows easy
 Backbone Cabling: Connections between MDA, HDA, and
Entrance room
http://www.cse.wustl.edu/~jain/cse570-13/
Washington University in St. Louis
©2013 Raj Jain


3-12
Zone Distribution Area



High-fiber count cables connect ZDA to MDA or HDA.
Low-fiber count cables connect ZDA to EDA as needed.

Ref: Jennifer Cline, “Zone Distribution in the data center,”
http://www.graybar.com/documents/zone-distribution-in-the-data-center.pdf
http://www.cse.wustl.edu/~jain/cse570-13/
Washington University in St. Louis

3-13

©2013 Raj Jain
Data Center Network Topologies


Core, Aggregation, Access

Ref: G. Santana, “Data Center Virtualization Fundamentals,” Cisco Press, 2014, ISBN:1587143240
http://www.cse.wustl.edu/~jain/cse570-13/
Washington University in St. Louis

3-14

©2013 Raj Jain
Data Center Networks








20-40 servers per rack
Each server connected to 2 access switches with 1 Gbps
(10 Gbps becoming common)
Access switches connect to 2 aggregation switches
Aggregation switches connect to 2 core routers
Core routers connect to edge routers
Aggregation layer is the transition point between L2-switched
access layer and l3-routed core layer
Low Latency: In high-frequency trading market, a few
microseconds make a big difference.
 Cut-through switching and low-latency specifications.

Ref: A. Greenberg, "VL2: A Scalable and Flexible Data Center Network," CACM, Vol. 54, NO. 3, March 2011, pp. 95-104,
http://research.microsoft.com/pubs/80693/vl2-sigcomm09-final.pdf.
http://www.cse.wustl.edu/~jain/cse570-13/
Washington University in St. Louis
©2013 Raj Jain

3-15
Data Center Networks (Cont)







Core routers manage traffic between aggregation routers and
in/out of data center
All switches below each pair of aggregation switches form a
single layer-2 domain
Each Layer 2 domain typically limited to a few hundred servers
to limit broadcast
Most traffic is internal to the data center.
Network is the bottleneck.
Uplinks utilization of 80% is common.
Most of the flows are small.
Mode = 100 MB. DFS uses 100 MB chunks.

Washington University in St. Louis

http://www.cse.wustl.edu/~jain/cse570-13/

3-16

©2013 Raj Jain
Switch Locations
Smaller cable
between servers and
switches
Network team has to
manage switches on
all racks

All network
switches in
one rack

Source: Santana 2014
Washington University in St. Louis

http://www.cse.wustl.edu/~jain/cse570-13/

3-17

©2013 Raj Jain
ToR vs EoR


ToR:
 Easier cabling




If rack is not fully populated  unused ToR ports
If rack traffic demand is high, difficult to add more ports
Upgrading (1G to 10G) requires complete Rack upgrade





EoR:
 Longer cables
 Severs can be place in any rack
 Ports can easily added, upgraded

Washington University in St. Louis

http://www.cse.wustl.edu/~jain/cse570-13/

3-18

©2013 Raj Jain
Hierarchical Network Design







All servers require application
delivery services for security
(VPN, Intrusion detection,
firewall), performance (load
balancer), networking (DNS,
DHCP, NTP, FTP, RADIUS),
Database services (SQL)
ADCs are located between the
aggregation and core routers
and are shared by all servers
Stateful devices (firewalls) on Aggregation layer
Stateful= State of TCP connection

Washington University in St. Louis

http://www.cse.wustl.edu/~jain/cse570-13/

3-19

Source: Santana 2014

©2013 Raj Jain
Access Aggregation Connections
1.

2.

3.

4.

Looped Triangle:
Most common. Spanning Tree
Protocol (STP) blocks links.
Paid but not used.
Looped Square:
Oversubscription doubles if
failure.
Loop-Free U:
No L2 communication
between aggregation switches
if any switch links fail
Loop-Free Inverted U:
Black-holes on some failures

Washington University in St. Louis

Source: Santana 2014

http://www.cse.wustl.edu/~jain/cse570-13/

3-20

©2013 Raj Jain
Data Center Networking Issues






Higher layers oversubscribed:
 Other servers in the same rack 1:1
 Uplinks from ToR: 1:2 to 1:20
(e.g., 32x10Gb down, 8X10Gb up  4:1 oversubscription)
 Core Routers: 1:240
 Generally keep services in one tree
 Can't arbitrarily move servers
Moving across Subnets is painful
 Requires reconfiguration of IP addresses and VLAN trunks
Service trample on each-other.
Overuse by one service affects others
Poor reliability.
One access switch failure doubles the load on the other.

Washington University in St. Louis

http://www.cse.wustl.edu/~jain/cse570-13/

3-21

©2013 Raj Jain
Data Center Networking Issues (Cont)



Under-utilization.
Even when multiple paths exist only one is used.
ECMP (Equal Cost Multipath) is used by routers to spread
traffic to next hops using a hash function. However, only 2
paths exist.

Washington University in St. Louis

http://www.cse.wustl.edu/~jain/cse570-13/

3-22

©2013 Raj Jain
DCN Requirements


Needs to be Scalable, Secure, Shared, Standardized,
and Simplified (5 S's)



Converged Infrastructure: Servers, storage, and network have
to work together
Workload Mobility: Large L2 domains required for VM
mobility
East-West Traffic: Significant server-to-server traffic as
compared to server to user. One Facebook request required 88
cache looks, 35 database lookups, 392 backend RPC calls.
Internet traffic 935X the http request/response [Farrington]
Storage traffic on Ethernet: Congestion management on
Ethernet






Ref: A. Kindlness, "The Forester Wave: Data Center Networking Hardware," Jan 23, 2013,
http://ca.westcon.com/documents/46488/forrester_wave_data_cetner_networking_hw_q1_2013.pdf
Ref: N. Farringon and A. Andreyev, “Facebook’s Data Center Network Architecture,” 2013 IEEE Optical Interconnect Conference,
http://nathanfarrington.com/papers/facebook-oic13.pdf
http://www.cse.wustl.edu/~jain/cse570-13/
Washington University in St. Louis
©2013 Raj Jain

3-23
4-Post Architecture at Facebook






Each rack switch (RSW) has up to 48 10G downlinks and 4-8 10G uplinks
(10:1 oversubscription) to cluster switch (CSW)
Each CSW has 4 40G uplinks – one to each of the 4 FatCat (FC)
aggregation switches (4:1 oversubscription)
4 CSW’s are connected in a 10G×8 protection ring
4FC’s are connected in a 10G×16 protection ring
No routers at FC. One CSW failure reduces intra-cluster capacity to 75%.

Ref: N. Farringon and A. Andreyev, “Facebook’s Data Center Network Architecture,” 2013 IEEE Optical Interconnect Conference,
http://nathanfarrington.com/papers/facebook-oic13.pdf
http://www.cse.wustl.edu/~jain/cse570-13/
Washington University in St. Louis
©2013 Raj Jain

3-24
Clos Networks








Multi-stage circuit switching network proposed by
Charles Clos in 1953 for telephone switching systems
Allows forming a large switch from smaller switches
The number of cross-points is reduced  Lower cost (then)
3-Stage Clos(n, m, r): ingress (r n×m), middle (m r×r), egress (r m×n)
Strict-sense non-blocking if m > 2n-1. Existing calls unaffected.
Rearrangeably non-blocking if m > n
Can have any odd number of stages, e.g., 5
Folded: Merge input and output in to one switch = Fat-tree
n×m
n×m

r=2, n=4, m=3

r×r
r×r
r×r

Ref: http://en.wikipedia.org/wiki/Clos_network
Washington University in St. Louis

r×r

m×n

r×r

m×n

r×r
n+m port switches r-port switches

http://www.cse.wustl.edu/~jain/cse570-13/

3-25

©2013 Raj Jain
Fat-Tree DCN Example
Core
9

Edge
Servers





…

…

…

…

6 identical 36-port switches. All ports 1 Gbps. 72 Servers.
Each edge switch connects to 18 servers.
9 Uplinks to first core switch. Other 9 links to 2nd core switch.
Throughput between any two servers = 1 Gbps using ECMP
Identical bandwidth at any bisection.
Negative: Cabling complexity

Ref: Teach yourself Fat-Tree Design in 60 minutes, http://clusterdesign.org/fat-trees/
http://www.cse.wustl.edu/~jain/cse570-13/
Washington University in St. Louis

3-26

©2013 Raj Jain
Summary

1.
2.
3.
4.
5.

Modular data centers can be used for easy assembly and
scaling
Three tiers: Access, Aggregation, Core
Application delivery controllers between Aggregation and
core
Need large L2 domains
Fat-tree topology is sometimes used to improve performance
and reliability

Washington University in St. Louis

http://www.cse.wustl.edu/~jain/cse570-13/

3-27

©2013 Raj Jain
Homework 3


Draw a 3-stage clos(4,5,3) topology and its folded version.

Washington University in St. Louis

http://www.cse.wustl.edu/~jain/cse570-13/

3-28

©2013 Raj Jain
Acronyms
ADC
ANSI
BPE
CSW
DCBX
DCN
DFS
DHCP
DNS
ECMP
EDA
EoR

Application Delivery Controller
American National Standards Institute
Business Process Engineering
Core Switch
Data Center Bridging eXtension
Data Center Network
Distributed File System
Dynamic Host Control Protocol
Domain Name System
Equal Cost Multipath
Equipment Distribution Area
End of Row

Washington University in St. Louis

http://www.cse.wustl.edu/~jain/cse570-13/

3-29

©2013 Raj Jain
Acronyms (Cont)
ETS
Enhanced Transmission Selection
EVB
Edge Virtual Bridge
FC
Fibre Channel
FSW
Fabric switch
FTP
File Transfer Protocol
HDA Horizontal Distribution Area
LACP Link Aggregation Control Protocol
LAG
Link Aggregation
LLDP Link Layer Discovery Protocol
MAC Media Access Control
MDA Main Distribution Area
MW
Mega-Watt
NTP
Network Time Protocol
Washington University in St. Louis

http://www.cse.wustl.edu/~jain/cse570-13/

3-30

©2013 Raj Jain
Acronyms (Cont)
NVGRE Network Virtualization using Generic Routing Encapsulation
PFC
Priority Flow Control
PUE
Power Usage Effectiveness
RADIUS
Remote Authentication Dial-In User Service
RPC
Remote Procedue Call
RSW Rack switch
SQL
Structured Query Language
SSW
Spine Switches
STP
Spanning Tree Protocol
TIA
Telecommunications Industry Association
ToR
Top of Rack
TRILL Transparent Interconnection of Lots of Link
VLAN Virtual Local Area Network
VM
Virtual Machine
VPN
Virtual Private Network
Washington University in St. Louis

http://www.cse.wustl.edu/~jain/cse570-13/

3-31

©2013 Raj Jain
Acronyms (Cont)
VRF
Virtual Routing and Forwarding
VXLANVirtual Extensible Local Area Network
ZDA
Zone Distribution Area

Washington University in St. Louis

http://www.cse.wustl.edu/~jain/cse570-13/

3-32

©2013 Raj Jain
Reading List











http://webodysseum.com/technologyscience/visit-the-googles-data-centers/
http://www.sgi.com/products/data_center/ice_cube_air/
Datacenter Infrastructure - mobile Data Center from Emerson Network
Power, http://www.datacenterknowledge.com/archives/2010/05/31/iij-willoffer-commercial-container-facility/
C. DiMinico, "Telecommunications Infrastructure Standard for Data
Centers," IEEE 802.3 HSSG Meeting, Nov. 2006,
http://www.ieee802.org/3/hssg/public/nov06/diminico_01_1106.pdf
Jennifer Cline, “Zone Distribution in the data center,”
http://www.graybar.com/documents/zone-distribution-in-the-datacenter.pdf
G. Santana, “Data Center Virtualization Fundamentals,” Cisco Press, 2014,
ISBN:1587143240 (Safari book)
A. Greenberg, "VL2: A Scalable and Flexible Data Center Network,"
CACM, Vol. 54, NO. 3, March 2011, pp. 95-104,
http://research.microsoft.com/pubs/80693/vl2-sigcomm09-final.pdf

Washington University in St. Louis

http://www.cse.wustl.edu/~jain/cse570-13/

3-33

©2013 Raj Jain
Reading List (Cont)








A. Kindlness, "The Forester Wave: Data Center Networking Hardware," Jan
23, 2013,
http://ca.westcon.com/documents/46488/forrester_wave_data_cetner_netwo
rking_hw_q1_2013.pdf
N. Farringon and A. Andreyev, “Facebook’s Data Center Network
Architecture,” 2013 IEEE Optical Interconnect Conference,
http://nathanfarrington.com/papers/facebook-oic13.pdf
http://en.wikipedia.org/wiki/Clos_network
Teach yourself Fat-Tree Design in 60 minutes, http://clusterdesign.org/fattrees/
M. Al-Fares, et al, "A scalable, commodity data center network
architecture," ACM SIGCOMM, 2008.

Washington University in St. Louis

http://www.cse.wustl.edu/~jain/cse570-13/

3-34

©2013 Raj Jain
Wikipedia Links










http://en.wikipedia.org/wiki/Modular_data_center
http://en.wikipedia.org/wiki/Data_center
http://en.wikipedia.org/wiki/Structured_cabling
http://en.wikipedia.org/wiki/Cable_management
http://en.wikipedia.org/wiki/Raised_floor
http://en.wikipedia.org/wiki/Data_center_environmental_contr
ol
http://en.wikipedia.org/wiki/Fat_tree
http://en.wikipedia.org/wiki/Hierarchical_internetworking_mod
el
http://en.wikipedia.org/wiki/Clos_network

Washington University in St. Louis

http://www.cse.wustl.edu/~jain/cse570-13/

3-35

©2013 Raj Jain

Más contenido relacionado

La actualidad más candente

Datacenter Strategy, Design, and Build
Datacenter Strategy, Design, and BuildDatacenter Strategy, Design, and Build
Datacenter Strategy, Design, and BuildChristopher Kelley
 
Datacenter101
Datacenter101Datacenter101
Datacenter101tarundua
 
COMMON PROBLEMS AND CHALLENGES IN DATA CENTRES
COMMON PROBLEMS AND CHALLENGES IN DATA CENTRESCOMMON PROBLEMS AND CHALLENGES IN DATA CENTRES
COMMON PROBLEMS AND CHALLENGES IN DATA CENTRESKamran Hassan
 
Data center proposal
Data center proposalData center proposal
Data center proposalMuhammad Ahad
 
Tia 942 Data Center Standards
Tia 942 Data Center StandardsTia 942 Data Center Standards
Tia 942 Data Center StandardsSri Chalasani
 
Simplifying Data Center Design/ Build
Simplifying Data Center Design/ BuildSimplifying Data Center Design/ Build
Simplifying Data Center Design/ BuildSchneider Electric
 
Data Center Infrastructure Management Powerpoint Presentation Slides
Data Center Infrastructure Management Powerpoint Presentation SlidesData Center Infrastructure Management Powerpoint Presentation Slides
Data Center Infrastructure Management Powerpoint Presentation SlidesSlideTeam
 
Data Center Infrastructure Management(DCIM)
Data Center Infrastructure Management(DCIM)Data Center Infrastructure Management(DCIM)
Data Center Infrastructure Management(DCIM)MD. IFTEKARUL ALAM
 
Data Center Tiers Explained
Data Center Tiers ExplainedData Center Tiers Explained
Data Center Tiers ExplainedData Cave
 
What Does It Cost to Build a Data Center? (SlideShare)
What Does It Cost to Build a Data Center? (SlideShare)What Does It Cost to Build a Data Center? (SlideShare)
What Does It Cost to Build a Data Center? (SlideShare)SP Home Run Inc.
 
Adaptation of tcp window
Adaptation of tcp windowAdaptation of tcp window
Adaptation of tcp windowpriya Nithya
 
Unit 2 -Cloud Computing Architecture
Unit 2 -Cloud Computing ArchitectureUnit 2 -Cloud Computing Architecture
Unit 2 -Cloud Computing ArchitectureMonishaNehkal
 
POWER POINT PRESENTATION ON DATA CENTER
POWER POINT PRESENTATION ON DATA CENTERPOWER POINT PRESENTATION ON DATA CENTER
POWER POINT PRESENTATION ON DATA CENTERvivekprajapatiankur
 
Network design
Network designNetwork design
Network designcsk selva
 
Data center architecture
Data center architecture Data center architecture
Data center architecture RajuPrasad33
 
W-LAN (Wireless Local Area Network)
W-LAN (Wireless Local Area Network)W-LAN (Wireless Local Area Network)
W-LAN (Wireless Local Area Network)Parvesh Taneja
 

La actualidad más candente (20)

Datacenter Strategy, Design, and Build
Datacenter Strategy, Design, and BuildDatacenter Strategy, Design, and Build
Datacenter Strategy, Design, and Build
 
Datacenter101
Datacenter101Datacenter101
Datacenter101
 
COMMON PROBLEMS AND CHALLENGES IN DATA CENTRES
COMMON PROBLEMS AND CHALLENGES IN DATA CENTRESCOMMON PROBLEMS AND CHALLENGES IN DATA CENTRES
COMMON PROBLEMS AND CHALLENGES IN DATA CENTRES
 
Data center
Data centerData center
Data center
 
Data center proposal
Data center proposalData center proposal
Data center proposal
 
Tia 942 Data Center Standards
Tia 942 Data Center StandardsTia 942 Data Center Standards
Tia 942 Data Center Standards
 
Simplifying Data Center Design/ Build
Simplifying Data Center Design/ BuildSimplifying Data Center Design/ Build
Simplifying Data Center Design/ Build
 
Data Center
Data CenterData Center
Data Center
 
Data center tier standards
Data center tier standardsData center tier standards
Data center tier standards
 
Data Center Infrastructure Management Powerpoint Presentation Slides
Data Center Infrastructure Management Powerpoint Presentation SlidesData Center Infrastructure Management Powerpoint Presentation Slides
Data Center Infrastructure Management Powerpoint Presentation Slides
 
Data Center Networks
Data Center NetworksData Center Networks
Data Center Networks
 
Data Center Infrastructure Management(DCIM)
Data Center Infrastructure Management(DCIM)Data Center Infrastructure Management(DCIM)
Data Center Infrastructure Management(DCIM)
 
Data Center Tiers Explained
Data Center Tiers ExplainedData Center Tiers Explained
Data Center Tiers Explained
 
What Does It Cost to Build a Data Center? (SlideShare)
What Does It Cost to Build a Data Center? (SlideShare)What Does It Cost to Build a Data Center? (SlideShare)
What Does It Cost to Build a Data Center? (SlideShare)
 
Adaptation of tcp window
Adaptation of tcp windowAdaptation of tcp window
Adaptation of tcp window
 
Unit 2 -Cloud Computing Architecture
Unit 2 -Cloud Computing ArchitectureUnit 2 -Cloud Computing Architecture
Unit 2 -Cloud Computing Architecture
 
POWER POINT PRESENTATION ON DATA CENTER
POWER POINT PRESENTATION ON DATA CENTERPOWER POINT PRESENTATION ON DATA CENTER
POWER POINT PRESENTATION ON DATA CENTER
 
Network design
Network designNetwork design
Network design
 
Data center architecture
Data center architecture Data center architecture
Data center architecture
 
W-LAN (Wireless Local Area Network)
W-LAN (Wireless Local Area Network)W-LAN (Wireless Local Area Network)
W-LAN (Wireless Local Area Network)
 

Destacado

Data center network architectures v1.3
Data center network architectures v1.3Data center network architectures v1.3
Data center network architectures v1.3Jeong, Wookjae
 
Dell Data Center Networking Overview
Dell Data Center Networking OverviewDell Data Center Networking Overview
Dell Data Center Networking OverviewDell World
 
Designing Secure Cisco Data Centers
Designing Secure Cisco Data CentersDesigning Secure Cisco Data Centers
Designing Secure Cisco Data CentersCisco Russia
 
A Scalable, Commodity Data Center Network Architecture
A Scalable, Commodity Data Center Network ArchitectureA Scalable, Commodity Data Center Network Architecture
A Scalable, Commodity Data Center Network ArchitectureGunawan Jusuf
 
Security and Virtualization in the Data Center
Security and Virtualization in the Data CenterSecurity and Virtualization in the Data Center
Security and Virtualization in the Data CenterCisco Canada
 
Data Center Security
Data Center SecurityData Center Security
Data Center SecurityCisco Canada
 
Data Center Virtualization @ Cisco
Data Center Virtualization @ CiscoData Center Virtualization @ Cisco
Data Center Virtualization @ Ciscovmug
 
FATTREE: A scalable Commodity Data Center Network Architecture
FATTREE: A scalable Commodity Data Center Network ArchitectureFATTREE: A scalable Commodity Data Center Network Architecture
FATTREE: A scalable Commodity Data Center Network ArchitectureAnkita Mahajan
 
Modern Data Center Network Architecture - The house that Clos built
Modern Data Center Network Architecture - The house that Clos builtModern Data Center Network Architecture - The house that Clos built
Modern Data Center Network Architecture - The house that Clos builtCumulus Networks
 
Data center Building & General Specification
Data center Building & General Specification Data center Building & General Specification
Data center Building & General Specification Ali Mirfallah
 
Reference Architecture-Validated & Tested Approach to Define Network Design
Reference Architecture-Validated & Tested Approach to Define Network DesignReference Architecture-Validated & Tested Approach to Define Network Design
Reference Architecture-Validated & Tested Approach to Define Network DesignDataWorks Summit
 
Data Center Architecture Trends
Data Center Architecture TrendsData Center Architecture Trends
Data Center Architecture TrendsPanduit
 
Introduction to Cloud Data Center and Network Issues
Introduction to Cloud Data Center and Network IssuesIntroduction to Cloud Data Center and Network Issues
Introduction to Cloud Data Center and Network IssuesJason TC HOU (侯宗成)
 
Data Center Proposal (System Network Administration)
Data Center Proposal (System Network Administration)Data Center Proposal (System Network Administration)
Data Center Proposal (System Network Administration)Muhammad Ahad
 
Enterprise data center design and methodology
Enterprise data center design and methodologyEnterprise data center design and methodology
Enterprise data center design and methodologyCarlos León Araujo
 
Data Center Trends 2014
Data Center Trends 2014Data Center Trends 2014
Data Center Trends 2014Belden Inc
 
Murphy Data Center Services Infographic
Murphy Data Center Services InfographicMurphy Data Center Services Infographic
Murphy Data Center Services InfographicGary Woodcock
 
Genesys System - 8dec2010
Genesys System - 8dec2010Genesys System - 8dec2010
Genesys System - 8dec2010Agora Group
 
Data Center Network Trends - Lin Nease
Data Center Network Trends - Lin NeaseData Center Network Trends - Lin Nease
Data Center Network Trends - Lin NeaseHPDutchWorld
 

Destacado (19)

Data center network architectures v1.3
Data center network architectures v1.3Data center network architectures v1.3
Data center network architectures v1.3
 
Dell Data Center Networking Overview
Dell Data Center Networking OverviewDell Data Center Networking Overview
Dell Data Center Networking Overview
 
Designing Secure Cisco Data Centers
Designing Secure Cisco Data CentersDesigning Secure Cisco Data Centers
Designing Secure Cisco Data Centers
 
A Scalable, Commodity Data Center Network Architecture
A Scalable, Commodity Data Center Network ArchitectureA Scalable, Commodity Data Center Network Architecture
A Scalable, Commodity Data Center Network Architecture
 
Security and Virtualization in the Data Center
Security and Virtualization in the Data CenterSecurity and Virtualization in the Data Center
Security and Virtualization in the Data Center
 
Data Center Security
Data Center SecurityData Center Security
Data Center Security
 
Data Center Virtualization @ Cisco
Data Center Virtualization @ CiscoData Center Virtualization @ Cisco
Data Center Virtualization @ Cisco
 
FATTREE: A scalable Commodity Data Center Network Architecture
FATTREE: A scalable Commodity Data Center Network ArchitectureFATTREE: A scalable Commodity Data Center Network Architecture
FATTREE: A scalable Commodity Data Center Network Architecture
 
Modern Data Center Network Architecture - The house that Clos built
Modern Data Center Network Architecture - The house that Clos builtModern Data Center Network Architecture - The house that Clos built
Modern Data Center Network Architecture - The house that Clos built
 
Data center Building & General Specification
Data center Building & General Specification Data center Building & General Specification
Data center Building & General Specification
 
Reference Architecture-Validated & Tested Approach to Define Network Design
Reference Architecture-Validated & Tested Approach to Define Network DesignReference Architecture-Validated & Tested Approach to Define Network Design
Reference Architecture-Validated & Tested Approach to Define Network Design
 
Data Center Architecture Trends
Data Center Architecture TrendsData Center Architecture Trends
Data Center Architecture Trends
 
Introduction to Cloud Data Center and Network Issues
Introduction to Cloud Data Center and Network IssuesIntroduction to Cloud Data Center and Network Issues
Introduction to Cloud Data Center and Network Issues
 
Data Center Proposal (System Network Administration)
Data Center Proposal (System Network Administration)Data Center Proposal (System Network Administration)
Data Center Proposal (System Network Administration)
 
Enterprise data center design and methodology
Enterprise data center design and methodologyEnterprise data center design and methodology
Enterprise data center design and methodology
 
Data Center Trends 2014
Data Center Trends 2014Data Center Trends 2014
Data Center Trends 2014
 
Murphy Data Center Services Infographic
Murphy Data Center Services InfographicMurphy Data Center Services Infographic
Murphy Data Center Services Infographic
 
Genesys System - 8dec2010
Genesys System - 8dec2010Genesys System - 8dec2010
Genesys System - 8dec2010
 
Data Center Network Trends - Lin Nease
Data Center Network Trends - Lin NeaseData Center Network Trends - Lin Nease
Data Center Network Trends - Lin Nease
 

Similar a Data Center Network Topologies

LAN Extension and Network Virtualization for Cloud Computing using Layer 3 Pr...
LAN Extension and Network Virtualization for Cloud Computing using Layer 3 Pr...LAN Extension and Network Virtualization for Cloud Computing using Layer 3 Pr...
LAN Extension and Network Virtualization for Cloud Computing using Layer 3 Pr...rjain51
 
Data Center Ethernet
Data Center EthernetData Center Ethernet
Data Center Ethernetrjain51
 
Networking Issues For Big Data
Networking Issues For Big DataNetworking Issues For Big Data
Networking Issues For Big Datarjain51
 
Network Virtualization in Cloud Data Centers
Network Virtualization in Cloud Data CentersNetwork Virtualization in Cloud Data Centers
Network Virtualization in Cloud Data Centersrjain51
 
Carrier Ethernet
Carrier EthernetCarrier Ethernet
Carrier Ethernetrjain51
 
Application Delivery Networking
Application Delivery NetworkingApplication Delivery Networking
Application Delivery Networkingrjain51
 
Introduction to Software Defined Networking (SDN)
Introduction to Software Defined Networking (SDN)Introduction to Software Defined Networking (SDN)
Introduction to Software Defined Networking (SDN)rjain51
 
Networking tutorials introduction to networking
Networking tutorials   introduction to networkingNetworking tutorials   introduction to networking
Networking tutorials introduction to networkingVinod Jadhav
 
Introduction to OpenFlow
Introduction to OpenFlowIntroduction to OpenFlow
Introduction to OpenFlowrjain51
 
Data Center Interconnects: An Overview
Data Center Interconnects: An OverviewData Center Interconnects: An Overview
Data Center Interconnects: An OverviewXO Communications
 
Internet of Things.pdf
Internet of Things.pdfInternet of Things.pdf
Internet of Things.pdfsateeshka
 
Introduction to Internet of Things
Introduction to Internet of ThingsIntroduction to Internet of Things
Introduction to Internet of Thingsrjain51
 
SDN 101: Software Defined Networking Course - Sameh Zaghloul/IBM - 2014
SDN 101: Software Defined Networking Course - Sameh Zaghloul/IBM - 2014SDN 101: Software Defined Networking Course - Sameh Zaghloul/IBM - 2014
SDN 101: Software Defined Networking Course - Sameh Zaghloul/IBM - 2014SAMeh Zaghloul
 
Storage Virtualization
Storage VirtualizationStorage Virtualization
Storage Virtualizationrjain51
 
Advanced Design and Optimization of Data Center Interconnection Networks.pptx
Advanced Design and Optimization of Data Center Interconnection Networks.pptxAdvanced Design and Optimization of Data Center Interconnection Networks.pptx
Advanced Design and Optimization of Data Center Interconnection Networks.pptxService Solutions Pvt. Ltd. (SSL)
 
Computer networking
Computer networkingComputer networking
Computer networkingtdsparks3
 

Similar a Data Center Network Topologies (20)

LAN Extension and Network Virtualization for Cloud Computing using Layer 3 Pr...
LAN Extension and Network Virtualization for Cloud Computing using Layer 3 Pr...LAN Extension and Network Virtualization for Cloud Computing using Layer 3 Pr...
LAN Extension and Network Virtualization for Cloud Computing using Layer 3 Pr...
 
Data Center Ethernet
Data Center EthernetData Center Ethernet
Data Center Ethernet
 
Networking Issues For Big Data
Networking Issues For Big DataNetworking Issues For Big Data
Networking Issues For Big Data
 
Network Virtualization in Cloud Data Centers
Network Virtualization in Cloud Data CentersNetwork Virtualization in Cloud Data Centers
Network Virtualization in Cloud Data Centers
 
Carrier Ethernet
Carrier EthernetCarrier Ethernet
Carrier Ethernet
 
Application Delivery Networking
Application Delivery NetworkingApplication Delivery Networking
Application Delivery Networking
 
Introduction to Software Defined Networking (SDN)
Introduction to Software Defined Networking (SDN)Introduction to Software Defined Networking (SDN)
Introduction to Software Defined Networking (SDN)
 
Networking tutorials introduction to networking
Networking tutorials   introduction to networkingNetworking tutorials   introduction to networking
Networking tutorials introduction to networking
 
Sem 1 Ch 5
Sem 1 Ch 5Sem 1 Ch 5
Sem 1 Ch 5
 
Csc341 – Lecture 1 network management
Csc341 – Lecture 1 network managementCsc341 – Lecture 1 network management
Csc341 – Lecture 1 network management
 
Introduction to OpenFlow
Introduction to OpenFlowIntroduction to OpenFlow
Introduction to OpenFlow
 
Data Center Interconnects: An Overview
Data Center Interconnects: An OverviewData Center Interconnects: An Overview
Data Center Interconnects: An Overview
 
Internet of Things.pdf
Internet of Things.pdfInternet of Things.pdf
Internet of Things.pdf
 
Virtual local area networks
Virtual local area networksVirtual local area networks
Virtual local area networks
 
Essay On Ethernet
Essay On EthernetEssay On Ethernet
Essay On Ethernet
 
Introduction to Internet of Things
Introduction to Internet of ThingsIntroduction to Internet of Things
Introduction to Internet of Things
 
SDN 101: Software Defined Networking Course - Sameh Zaghloul/IBM - 2014
SDN 101: Software Defined Networking Course - Sameh Zaghloul/IBM - 2014SDN 101: Software Defined Networking Course - Sameh Zaghloul/IBM - 2014
SDN 101: Software Defined Networking Course - Sameh Zaghloul/IBM - 2014
 
Storage Virtualization
Storage VirtualizationStorage Virtualization
Storage Virtualization
 
Advanced Design and Optimization of Data Center Interconnection Networks.pptx
Advanced Design and Optimization of Data Center Interconnection Networks.pptxAdvanced Design and Optimization of Data Center Interconnection Networks.pptx
Advanced Design and Optimization of Data Center Interconnection Networks.pptx
 
Computer networking
Computer networkingComputer networking
Computer networking
 

Más de rjain51

Internet of Things: Challenges and Issues
Internet of Things: Challenges and IssuesInternet of Things: Challenges and Issues
Internet of Things: Challenges and Issuesrjain51
 
SDN and NFV: Facts, Extensions, and Carrier Opportunities
SDN and NFV: Facts, Extensions, and Carrier OpportunitiesSDN and NFV: Facts, Extensions, and Carrier Opportunities
SDN and NFV: Facts, Extensions, and Carrier Opportunitiesrjain51
 
Introduction to Network Function Virtualization (NFV)
Introduction to Network Function Virtualization (NFV)Introduction to Network Function Virtualization (NFV)
Introduction to Network Function Virtualization (NFV)rjain51
 
OpenFlow Controllers and Tools
OpenFlow Controllers and ToolsOpenFlow Controllers and Tools
OpenFlow Controllers and Toolsrjain51
 
Big Data Fundamentals
Big Data FundamentalsBig Data Fundamentals
Big Data Fundamentalsrjain51
 
Data Center Networks:Virtual Bridging
Data Center Networks:Virtual BridgingData Center Networks:Virtual Bridging
Data Center Networks:Virtual Bridgingrjain51
 
Server Virtualization
Server VirtualizationServer Virtualization
Server Virtualizationrjain51
 
Networking Protocols for Internet of Things
Networking Protocols for Internet of ThingsNetworking Protocols for Internet of Things
Networking Protocols for Internet of Thingsrjain51
 

Más de rjain51 (8)

Internet of Things: Challenges and Issues
Internet of Things: Challenges and IssuesInternet of Things: Challenges and Issues
Internet of Things: Challenges and Issues
 
SDN and NFV: Facts, Extensions, and Carrier Opportunities
SDN and NFV: Facts, Extensions, and Carrier OpportunitiesSDN and NFV: Facts, Extensions, and Carrier Opportunities
SDN and NFV: Facts, Extensions, and Carrier Opportunities
 
Introduction to Network Function Virtualization (NFV)
Introduction to Network Function Virtualization (NFV)Introduction to Network Function Virtualization (NFV)
Introduction to Network Function Virtualization (NFV)
 
OpenFlow Controllers and Tools
OpenFlow Controllers and ToolsOpenFlow Controllers and Tools
OpenFlow Controllers and Tools
 
Big Data Fundamentals
Big Data FundamentalsBig Data Fundamentals
Big Data Fundamentals
 
Data Center Networks:Virtual Bridging
Data Center Networks:Virtual BridgingData Center Networks:Virtual Bridging
Data Center Networks:Virtual Bridging
 
Server Virtualization
Server VirtualizationServer Virtualization
Server Virtualization
 
Networking Protocols for Internet of Things
Networking Protocols for Internet of ThingsNetworking Protocols for Internet of Things
Networking Protocols for Internet of Things
 

Último

TrustArc Webinar - Unlock the Power of AI-Driven Data Discovery
TrustArc Webinar - Unlock the Power of AI-Driven Data DiscoveryTrustArc Webinar - Unlock the Power of AI-Driven Data Discovery
TrustArc Webinar - Unlock the Power of AI-Driven Data DiscoveryTrustArc
 
HTML Injection Attacks: Impact and Mitigation Strategies
HTML Injection Attacks: Impact and Mitigation StrategiesHTML Injection Attacks: Impact and Mitigation Strategies
HTML Injection Attacks: Impact and Mitigation StrategiesBoston Institute of Analytics
 
Why Teams call analytics are critical to your entire business
Why Teams call analytics are critical to your entire businessWhy Teams call analytics are critical to your entire business
Why Teams call analytics are critical to your entire businesspanagenda
 
Automating Google Workspace (GWS) & more with Apps Script
Automating Google Workspace (GWS) & more with Apps ScriptAutomating Google Workspace (GWS) & more with Apps Script
Automating Google Workspace (GWS) & more with Apps Scriptwesley chun
 
Artificial Intelligence Chap.5 : Uncertainty
Artificial Intelligence Chap.5 : UncertaintyArtificial Intelligence Chap.5 : Uncertainty
Artificial Intelligence Chap.5 : UncertaintyKhushali Kathiriya
 
Artificial Intelligence: Facts and Myths
Artificial Intelligence: Facts and MythsArtificial Intelligence: Facts and Myths
Artificial Intelligence: Facts and MythsJoaquim Jorge
 
A Year of the Servo Reboot: Where Are We Now?
A Year of the Servo Reboot: Where Are We Now?A Year of the Servo Reboot: Where Are We Now?
A Year of the Servo Reboot: Where Are We Now?Igalia
 
Polkadot JAM Slides - Token2049 - By Dr. Gavin Wood
Polkadot JAM Slides - Token2049 - By Dr. Gavin WoodPolkadot JAM Slides - Token2049 - By Dr. Gavin Wood
Polkadot JAM Slides - Token2049 - By Dr. Gavin WoodJuan lago vázquez
 
Top 10 Most Downloaded Games on Play Store in 2024
Top 10 Most Downloaded Games on Play Store in 2024Top 10 Most Downloaded Games on Play Store in 2024
Top 10 Most Downloaded Games on Play Store in 2024SynarionITSolutions
 
2024: Domino Containers - The Next Step. News from the Domino Container commu...
2024: Domino Containers - The Next Step. News from the Domino Container commu...2024: Domino Containers - The Next Step. News from the Domino Container commu...
2024: Domino Containers - The Next Step. News from the Domino Container commu...Martijn de Jong
 
Understanding Discord NSFW Servers A Guide for Responsible Users.pdf
Understanding Discord NSFW Servers A Guide for Responsible Users.pdfUnderstanding Discord NSFW Servers A Guide for Responsible Users.pdf
Understanding Discord NSFW Servers A Guide for Responsible Users.pdfUK Journal
 
Bajaj Allianz Life Insurance Company - Insurer Innovation Award 2024
Bajaj Allianz Life Insurance Company - Insurer Innovation Award 2024Bajaj Allianz Life Insurance Company - Insurer Innovation Award 2024
Bajaj Allianz Life Insurance Company - Insurer Innovation Award 2024The Digital Insurer
 
Data Cloud, More than a CDP by Matt Robison
Data Cloud, More than a CDP by Matt RobisonData Cloud, More than a CDP by Matt Robison
Data Cloud, More than a CDP by Matt RobisonAnna Loughnan Colquhoun
 
GenAI Risks & Security Meetup 01052024.pdf
GenAI Risks & Security Meetup 01052024.pdfGenAI Risks & Security Meetup 01052024.pdf
GenAI Risks & Security Meetup 01052024.pdflior mazor
 
Cloud Frontiers: A Deep Dive into Serverless Spatial Data and FME
Cloud Frontiers:  A Deep Dive into Serverless Spatial Data and FMECloud Frontiers:  A Deep Dive into Serverless Spatial Data and FME
Cloud Frontiers: A Deep Dive into Serverless Spatial Data and FMESafe Software
 
MINDCTI Revenue Release Quarter One 2024
MINDCTI Revenue Release Quarter One 2024MINDCTI Revenue Release Quarter One 2024
MINDCTI Revenue Release Quarter One 2024MIND CTI
 
Apidays Singapore 2024 - Building Digital Trust in a Digital Economy by Veron...
Apidays Singapore 2024 - Building Digital Trust in a Digital Economy by Veron...Apidays Singapore 2024 - Building Digital Trust in a Digital Economy by Veron...
Apidays Singapore 2024 - Building Digital Trust in a Digital Economy by Veron...apidays
 
Scaling API-first – The story of a global engineering organization
Scaling API-first – The story of a global engineering organizationScaling API-first – The story of a global engineering organization
Scaling API-first – The story of a global engineering organizationRadu Cotescu
 
Repurposing LNG terminals for Hydrogen Ammonia: Feasibility and Cost Saving
Repurposing LNG terminals for Hydrogen Ammonia: Feasibility and Cost SavingRepurposing LNG terminals for Hydrogen Ammonia: Feasibility and Cost Saving
Repurposing LNG terminals for Hydrogen Ammonia: Feasibility and Cost SavingEdi Saputra
 
Axa Assurance Maroc - Insurer Innovation Award 2024
Axa Assurance Maroc - Insurer Innovation Award 2024Axa Assurance Maroc - Insurer Innovation Award 2024
Axa Assurance Maroc - Insurer Innovation Award 2024The Digital Insurer
 

Último (20)

TrustArc Webinar - Unlock the Power of AI-Driven Data Discovery
TrustArc Webinar - Unlock the Power of AI-Driven Data DiscoveryTrustArc Webinar - Unlock the Power of AI-Driven Data Discovery
TrustArc Webinar - Unlock the Power of AI-Driven Data Discovery
 
HTML Injection Attacks: Impact and Mitigation Strategies
HTML Injection Attacks: Impact and Mitigation StrategiesHTML Injection Attacks: Impact and Mitigation Strategies
HTML Injection Attacks: Impact and Mitigation Strategies
 
Why Teams call analytics are critical to your entire business
Why Teams call analytics are critical to your entire businessWhy Teams call analytics are critical to your entire business
Why Teams call analytics are critical to your entire business
 
Automating Google Workspace (GWS) & more with Apps Script
Automating Google Workspace (GWS) & more with Apps ScriptAutomating Google Workspace (GWS) & more with Apps Script
Automating Google Workspace (GWS) & more with Apps Script
 
Artificial Intelligence Chap.5 : Uncertainty
Artificial Intelligence Chap.5 : UncertaintyArtificial Intelligence Chap.5 : Uncertainty
Artificial Intelligence Chap.5 : Uncertainty
 
Artificial Intelligence: Facts and Myths
Artificial Intelligence: Facts and MythsArtificial Intelligence: Facts and Myths
Artificial Intelligence: Facts and Myths
 
A Year of the Servo Reboot: Where Are We Now?
A Year of the Servo Reboot: Where Are We Now?A Year of the Servo Reboot: Where Are We Now?
A Year of the Servo Reboot: Where Are We Now?
 
Polkadot JAM Slides - Token2049 - By Dr. Gavin Wood
Polkadot JAM Slides - Token2049 - By Dr. Gavin WoodPolkadot JAM Slides - Token2049 - By Dr. Gavin Wood
Polkadot JAM Slides - Token2049 - By Dr. Gavin Wood
 
Top 10 Most Downloaded Games on Play Store in 2024
Top 10 Most Downloaded Games on Play Store in 2024Top 10 Most Downloaded Games on Play Store in 2024
Top 10 Most Downloaded Games on Play Store in 2024
 
2024: Domino Containers - The Next Step. News from the Domino Container commu...
2024: Domino Containers - The Next Step. News from the Domino Container commu...2024: Domino Containers - The Next Step. News from the Domino Container commu...
2024: Domino Containers - The Next Step. News from the Domino Container commu...
 
Understanding Discord NSFW Servers A Guide for Responsible Users.pdf
Understanding Discord NSFW Servers A Guide for Responsible Users.pdfUnderstanding Discord NSFW Servers A Guide for Responsible Users.pdf
Understanding Discord NSFW Servers A Guide for Responsible Users.pdf
 
Bajaj Allianz Life Insurance Company - Insurer Innovation Award 2024
Bajaj Allianz Life Insurance Company - Insurer Innovation Award 2024Bajaj Allianz Life Insurance Company - Insurer Innovation Award 2024
Bajaj Allianz Life Insurance Company - Insurer Innovation Award 2024
 
Data Cloud, More than a CDP by Matt Robison
Data Cloud, More than a CDP by Matt RobisonData Cloud, More than a CDP by Matt Robison
Data Cloud, More than a CDP by Matt Robison
 
GenAI Risks & Security Meetup 01052024.pdf
GenAI Risks & Security Meetup 01052024.pdfGenAI Risks & Security Meetup 01052024.pdf
GenAI Risks & Security Meetup 01052024.pdf
 
Cloud Frontiers: A Deep Dive into Serverless Spatial Data and FME
Cloud Frontiers:  A Deep Dive into Serverless Spatial Data and FMECloud Frontiers:  A Deep Dive into Serverless Spatial Data and FME
Cloud Frontiers: A Deep Dive into Serverless Spatial Data and FME
 
MINDCTI Revenue Release Quarter One 2024
MINDCTI Revenue Release Quarter One 2024MINDCTI Revenue Release Quarter One 2024
MINDCTI Revenue Release Quarter One 2024
 
Apidays Singapore 2024 - Building Digital Trust in a Digital Economy by Veron...
Apidays Singapore 2024 - Building Digital Trust in a Digital Economy by Veron...Apidays Singapore 2024 - Building Digital Trust in a Digital Economy by Veron...
Apidays Singapore 2024 - Building Digital Trust in a Digital Economy by Veron...
 
Scaling API-first – The story of a global engineering organization
Scaling API-first – The story of a global engineering organizationScaling API-first – The story of a global engineering organization
Scaling API-first – The story of a global engineering organization
 
Repurposing LNG terminals for Hydrogen Ammonia: Feasibility and Cost Saving
Repurposing LNG terminals for Hydrogen Ammonia: Feasibility and Cost SavingRepurposing LNG terminals for Hydrogen Ammonia: Feasibility and Cost Saving
Repurposing LNG terminals for Hydrogen Ammonia: Feasibility and Cost Saving
 
Axa Assurance Maroc - Insurer Innovation Award 2024
Axa Assurance Maroc - Insurer Innovation Award 2024Axa Assurance Maroc - Insurer Innovation Award 2024
Axa Assurance Maroc - Insurer Innovation Award 2024
 

Data Center Network Topologies

  • 1. Data Center Network Topologies . Raj Jain Washington University in Saint Louis Saint Louis, MO 63130 Jain@cse.wustl.edu These slides and audio/video recordings of this class lecture are at: http://www.cse.wustl.edu/~jain/cse570-13/ Washington University in St. Louis http://www.cse.wustl.edu/~jain/cse570-13/ 3-1 ©2013 Raj Jain
  • 2. Overview 1. 2. 3. 4. 5. Data Center Physical Layout Data Center Network Topologies ToR vs. EoR Data Center Networking Issues Data Center Networking Requirements Washington University in St. Louis http://www.cse.wustl.edu/~jain/cse570-13/ 3-2 ©2013 Raj Jain
  • 3. Google’s Data Center Source: http://webodysseum.com/technologyscience/visit-the-googles-data-centers/ http://www.cse.wustl.edu/~jain/cse570-13/ Washington University in St. Louis 3-3 ©2013 Raj Jain
  • 5. Modular Data Centers      Small: < 1 MW, 4 racks per unit Medium: 1-4 MW, 10 racks per unit Large: > 4 MW, 20 racks per unit Built-in cooling, high PUE (power usage effectiveness) 1.02 PUE = Power In/Power Used Rapid deployment Ref: http://www.sgi.com/products/data_center/ice_cube_air/ http://www.cse.wustl.edu/~jain/cse570-13/ Washington University in St. Louis 3-5 ©2013 Raj Jain
  • 6. Containerized Data Center     Ready to Use. Connect to water and power supply and go. Built in cooling. Easy to scale.  Data Center trailer parks. Suitable for disaster recovery, e.g., flood, earthquake Offered by Cisco, IBM, SGI, Sun/ORACLE,… Ref: Datacenter Infrastructure – mobile Data Center from Emerson Network Power , http://en.m-info.ua/180-container-data-center/755-datacenter-infrastructure-mobile-data-center-from-emerson-network-power Ref: http://www.datacenterknowledge.com/archives/2010/05/31/iij-will-offer-commercial-container-facility/ http://www.cse.wustl.edu/~jain/cse570-13/ Washington University in St. Louis ©2013 Raj Jain 3-6
  • 7. Unstructured Cabling Source: http://webodysseum.com/technologyscience/visit-the-googles-data-centers/ Washington University in St. Louis http://www.cse.wustl.edu/~jain/cse570-13/ 3-7 ©2013 Raj Jain
  • 8. Structured Cabling Source: http://webodysseum.com/technologyscience/visit-the-googles-data-centers/ Washington University in St. Louis http://www.cse.wustl.edu/~jain/cse570-13/ 3-8 ©2013 Raj Jain
  • 9. Data Center Equipment Cabinets Three Layers: Bottom: Signal, Middle: Power, Top: Fiber Minimize patching between cabinets and racks Cabling under raised floors provides better appearance and cooling Ref: Ref: C. DiMinico, "Telecommunications Infrastructure Standard for Data Centers," IEEE 802.3 HSSG Meeting, Nov. 2006, http://www.ieee802.org/3/hssg/public/nov06/diminico_01_1106.pdf http://www.cse.wustl.edu/~jain/cse570-13/ Washington University in St. Louis ©2013 Raj Jain 3-9
  • 10. Data Center Physical Layout Washington University in St. Louis http://www.cse.wustl.edu/~jain/cse570-13/ 3-10 ©2013 Raj Jain
  • 11. ANSI/TIA-942-2005 Standard     Main Distribution Area (MDA) Horizontal Distribution Area (HDA) Equipment Distribution Area (EDA) Zone Distribution Area (ZDA) Source: Santana 2014 Washington University in St. Louis http://www.cse.wustl.edu/~jain/cse570-13/ 3-11 ©2013 Raj Jain
  • 12. ANSI/TIA-942-2005 Standard Computer Room: Main servers  Entrance Room: Data Center to external cabling  Cross-Connect: Enables termination of cables  Main Distribution Area (MDA): Main cross connect. Central Point of Structured Cabling. Core network devices  Horizontal Distribution Area (HDA): Connections to active equipment.  Equipment Distribution Area (EDA): Active Servers+Switches. Alternate hot and cold aisle.  Zone Distribution Area (ZDA): Optionally between HDA and EDA. ZDA allows easy  Backbone Cabling: Connections between MDA, HDA, and Entrance room http://www.cse.wustl.edu/~jain/cse570-13/ Washington University in St. Louis ©2013 Raj Jain  3-12
  • 13. Zone Distribution Area  High-fiber count cables connect ZDA to MDA or HDA. Low-fiber count cables connect ZDA to EDA as needed. Ref: Jennifer Cline, “Zone Distribution in the data center,” http://www.graybar.com/documents/zone-distribution-in-the-data-center.pdf http://www.cse.wustl.edu/~jain/cse570-13/ Washington University in St. Louis 3-13 ©2013 Raj Jain
  • 14. Data Center Network Topologies  Core, Aggregation, Access Ref: G. Santana, “Data Center Virtualization Fundamentals,” Cisco Press, 2014, ISBN:1587143240 http://www.cse.wustl.edu/~jain/cse570-13/ Washington University in St. Louis 3-14 ©2013 Raj Jain
  • 15. Data Center Networks        20-40 servers per rack Each server connected to 2 access switches with 1 Gbps (10 Gbps becoming common) Access switches connect to 2 aggregation switches Aggregation switches connect to 2 core routers Core routers connect to edge routers Aggregation layer is the transition point between L2-switched access layer and l3-routed core layer Low Latency: In high-frequency trading market, a few microseconds make a big difference.  Cut-through switching and low-latency specifications. Ref: A. Greenberg, "VL2: A Scalable and Flexible Data Center Network," CACM, Vol. 54, NO. 3, March 2011, pp. 95-104, http://research.microsoft.com/pubs/80693/vl2-sigcomm09-final.pdf. http://www.cse.wustl.edu/~jain/cse570-13/ Washington University in St. Louis ©2013 Raj Jain 3-15
  • 16. Data Center Networks (Cont)       Core routers manage traffic between aggregation routers and in/out of data center All switches below each pair of aggregation switches form a single layer-2 domain Each Layer 2 domain typically limited to a few hundred servers to limit broadcast Most traffic is internal to the data center. Network is the bottleneck. Uplinks utilization of 80% is common. Most of the flows are small. Mode = 100 MB. DFS uses 100 MB chunks. Washington University in St. Louis http://www.cse.wustl.edu/~jain/cse570-13/ 3-16 ©2013 Raj Jain
  • 17. Switch Locations Smaller cable between servers and switches Network team has to manage switches on all racks All network switches in one rack Source: Santana 2014 Washington University in St. Louis http://www.cse.wustl.edu/~jain/cse570-13/ 3-17 ©2013 Raj Jain
  • 18. ToR vs EoR  ToR:  Easier cabling    If rack is not fully populated  unused ToR ports If rack traffic demand is high, difficult to add more ports Upgrading (1G to 10G) requires complete Rack upgrade   EoR:  Longer cables  Severs can be place in any rack  Ports can easily added, upgraded Washington University in St. Louis http://www.cse.wustl.edu/~jain/cse570-13/ 3-18 ©2013 Raj Jain
  • 19. Hierarchical Network Design     All servers require application delivery services for security (VPN, Intrusion detection, firewall), performance (load balancer), networking (DNS, DHCP, NTP, FTP, RADIUS), Database services (SQL) ADCs are located between the aggregation and core routers and are shared by all servers Stateful devices (firewalls) on Aggregation layer Stateful= State of TCP connection Washington University in St. Louis http://www.cse.wustl.edu/~jain/cse570-13/ 3-19 Source: Santana 2014 ©2013 Raj Jain
  • 20. Access Aggregation Connections 1. 2. 3. 4. Looped Triangle: Most common. Spanning Tree Protocol (STP) blocks links. Paid but not used. Looped Square: Oversubscription doubles if failure. Loop-Free U: No L2 communication between aggregation switches if any switch links fail Loop-Free Inverted U: Black-holes on some failures Washington University in St. Louis Source: Santana 2014 http://www.cse.wustl.edu/~jain/cse570-13/ 3-20 ©2013 Raj Jain
  • 21. Data Center Networking Issues     Higher layers oversubscribed:  Other servers in the same rack 1:1  Uplinks from ToR: 1:2 to 1:20 (e.g., 32x10Gb down, 8X10Gb up  4:1 oversubscription)  Core Routers: 1:240  Generally keep services in one tree  Can't arbitrarily move servers Moving across Subnets is painful  Requires reconfiguration of IP addresses and VLAN trunks Service trample on each-other. Overuse by one service affects others Poor reliability. One access switch failure doubles the load on the other. Washington University in St. Louis http://www.cse.wustl.edu/~jain/cse570-13/ 3-21 ©2013 Raj Jain
  • 22. Data Center Networking Issues (Cont)   Under-utilization. Even when multiple paths exist only one is used. ECMP (Equal Cost Multipath) is used by routers to spread traffic to next hops using a hash function. However, only 2 paths exist. Washington University in St. Louis http://www.cse.wustl.edu/~jain/cse570-13/ 3-22 ©2013 Raj Jain
  • 23. DCN Requirements  Needs to be Scalable, Secure, Shared, Standardized, and Simplified (5 S's)  Converged Infrastructure: Servers, storage, and network have to work together Workload Mobility: Large L2 domains required for VM mobility East-West Traffic: Significant server-to-server traffic as compared to server to user. One Facebook request required 88 cache looks, 35 database lookups, 392 backend RPC calls. Internet traffic 935X the http request/response [Farrington] Storage traffic on Ethernet: Congestion management on Ethernet    Ref: A. Kindlness, "The Forester Wave: Data Center Networking Hardware," Jan 23, 2013, http://ca.westcon.com/documents/46488/forrester_wave_data_cetner_networking_hw_q1_2013.pdf Ref: N. Farringon and A. Andreyev, “Facebook’s Data Center Network Architecture,” 2013 IEEE Optical Interconnect Conference, http://nathanfarrington.com/papers/facebook-oic13.pdf http://www.cse.wustl.edu/~jain/cse570-13/ Washington University in St. Louis ©2013 Raj Jain 3-23
  • 24. 4-Post Architecture at Facebook     Each rack switch (RSW) has up to 48 10G downlinks and 4-8 10G uplinks (10:1 oversubscription) to cluster switch (CSW) Each CSW has 4 40G uplinks – one to each of the 4 FatCat (FC) aggregation switches (4:1 oversubscription) 4 CSW’s are connected in a 10G×8 protection ring 4FC’s are connected in a 10G×16 protection ring No routers at FC. One CSW failure reduces intra-cluster capacity to 75%. Ref: N. Farringon and A. Andreyev, “Facebook’s Data Center Network Architecture,” 2013 IEEE Optical Interconnect Conference, http://nathanfarrington.com/papers/facebook-oic13.pdf http://www.cse.wustl.edu/~jain/cse570-13/ Washington University in St. Louis ©2013 Raj Jain 3-24
  • 25. Clos Networks        Multi-stage circuit switching network proposed by Charles Clos in 1953 for telephone switching systems Allows forming a large switch from smaller switches The number of cross-points is reduced  Lower cost (then) 3-Stage Clos(n, m, r): ingress (r n×m), middle (m r×r), egress (r m×n) Strict-sense non-blocking if m > 2n-1. Existing calls unaffected. Rearrangeably non-blocking if m > n Can have any odd number of stages, e.g., 5 Folded: Merge input and output in to one switch = Fat-tree n×m n×m r=2, n=4, m=3 r×r r×r r×r Ref: http://en.wikipedia.org/wiki/Clos_network Washington University in St. Louis r×r m×n r×r m×n r×r n+m port switches r-port switches http://www.cse.wustl.edu/~jain/cse570-13/ 3-25 ©2013 Raj Jain
  • 26. Fat-Tree DCN Example Core 9 Edge Servers     … … … … 6 identical 36-port switches. All ports 1 Gbps. 72 Servers. Each edge switch connects to 18 servers. 9 Uplinks to first core switch. Other 9 links to 2nd core switch. Throughput between any two servers = 1 Gbps using ECMP Identical bandwidth at any bisection. Negative: Cabling complexity Ref: Teach yourself Fat-Tree Design in 60 minutes, http://clusterdesign.org/fat-trees/ http://www.cse.wustl.edu/~jain/cse570-13/ Washington University in St. Louis 3-26 ©2013 Raj Jain
  • 27. Summary 1. 2. 3. 4. 5. Modular data centers can be used for easy assembly and scaling Three tiers: Access, Aggregation, Core Application delivery controllers between Aggregation and core Need large L2 domains Fat-tree topology is sometimes used to improve performance and reliability Washington University in St. Louis http://www.cse.wustl.edu/~jain/cse570-13/ 3-27 ©2013 Raj Jain
  • 28. Homework 3  Draw a 3-stage clos(4,5,3) topology and its folded version. Washington University in St. Louis http://www.cse.wustl.edu/~jain/cse570-13/ 3-28 ©2013 Raj Jain
  • 29. Acronyms ADC ANSI BPE CSW DCBX DCN DFS DHCP DNS ECMP EDA EoR Application Delivery Controller American National Standards Institute Business Process Engineering Core Switch Data Center Bridging eXtension Data Center Network Distributed File System Dynamic Host Control Protocol Domain Name System Equal Cost Multipath Equipment Distribution Area End of Row Washington University in St. Louis http://www.cse.wustl.edu/~jain/cse570-13/ 3-29 ©2013 Raj Jain
  • 30. Acronyms (Cont) ETS Enhanced Transmission Selection EVB Edge Virtual Bridge FC Fibre Channel FSW Fabric switch FTP File Transfer Protocol HDA Horizontal Distribution Area LACP Link Aggregation Control Protocol LAG Link Aggregation LLDP Link Layer Discovery Protocol MAC Media Access Control MDA Main Distribution Area MW Mega-Watt NTP Network Time Protocol Washington University in St. Louis http://www.cse.wustl.edu/~jain/cse570-13/ 3-30 ©2013 Raj Jain
  • 31. Acronyms (Cont) NVGRE Network Virtualization using Generic Routing Encapsulation PFC Priority Flow Control PUE Power Usage Effectiveness RADIUS Remote Authentication Dial-In User Service RPC Remote Procedue Call RSW Rack switch SQL Structured Query Language SSW Spine Switches STP Spanning Tree Protocol TIA Telecommunications Industry Association ToR Top of Rack TRILL Transparent Interconnection of Lots of Link VLAN Virtual Local Area Network VM Virtual Machine VPN Virtual Private Network Washington University in St. Louis http://www.cse.wustl.edu/~jain/cse570-13/ 3-31 ©2013 Raj Jain
  • 32. Acronyms (Cont) VRF Virtual Routing and Forwarding VXLANVirtual Extensible Local Area Network ZDA Zone Distribution Area Washington University in St. Louis http://www.cse.wustl.edu/~jain/cse570-13/ 3-32 ©2013 Raj Jain
  • 33. Reading List        http://webodysseum.com/technologyscience/visit-the-googles-data-centers/ http://www.sgi.com/products/data_center/ice_cube_air/ Datacenter Infrastructure - mobile Data Center from Emerson Network Power, http://www.datacenterknowledge.com/archives/2010/05/31/iij-willoffer-commercial-container-facility/ C. DiMinico, "Telecommunications Infrastructure Standard for Data Centers," IEEE 802.3 HSSG Meeting, Nov. 2006, http://www.ieee802.org/3/hssg/public/nov06/diminico_01_1106.pdf Jennifer Cline, “Zone Distribution in the data center,” http://www.graybar.com/documents/zone-distribution-in-the-datacenter.pdf G. Santana, “Data Center Virtualization Fundamentals,” Cisco Press, 2014, ISBN:1587143240 (Safari book) A. Greenberg, "VL2: A Scalable and Flexible Data Center Network," CACM, Vol. 54, NO. 3, March 2011, pp. 95-104, http://research.microsoft.com/pubs/80693/vl2-sigcomm09-final.pdf Washington University in St. Louis http://www.cse.wustl.edu/~jain/cse570-13/ 3-33 ©2013 Raj Jain
  • 34. Reading List (Cont)      A. Kindlness, "The Forester Wave: Data Center Networking Hardware," Jan 23, 2013, http://ca.westcon.com/documents/46488/forrester_wave_data_cetner_netwo rking_hw_q1_2013.pdf N. Farringon and A. Andreyev, “Facebook’s Data Center Network Architecture,” 2013 IEEE Optical Interconnect Conference, http://nathanfarrington.com/papers/facebook-oic13.pdf http://en.wikipedia.org/wiki/Clos_network Teach yourself Fat-Tree Design in 60 minutes, http://clusterdesign.org/fattrees/ M. Al-Fares, et al, "A scalable, commodity data center network architecture," ACM SIGCOMM, 2008. Washington University in St. Louis http://www.cse.wustl.edu/~jain/cse570-13/ 3-34 ©2013 Raj Jain