Get documents about "iGrid2005 Panel Enabling Data Intensive Apps MAMBRETTI
Document Sample
Enabling Data Intensive Applications with Advanced
Optical Technologies
Joe Mambretti, Director, (j-mambretti@northwestern.edu)
International Center for Advanced Internet Research (www.icair.org)
Director, Metropolitan Research and Education Network (www.mren.org)
Partner, StarLight/STAR TAP, PI-OMNINet (www.icair.org/omninet)
iGRID 2005
University of California, San Diego
Sept. 26-30, 2005
Introduction to iCAIR:
Accelerating Leading Edge Innovation
and Enhanced Global Communications
through Advanced Internet Technologies,
in Partnership with the Global Community
• Creation and Early Implementation of Advanced Networking
Technologies - The Next Generation Internet All Optical Networks,
Terascale Networks
• Advanced Applications, Middleware, Large-Scale Infrastructure, NG
Optical Networks and Testbeds, Public Policy Studies and Forums
Related to NG Networks
World Of Tomorrow 2005
iGrid 2oo5
TH E G L OBAL LAMBDA INTE GRAT ED FACIL ITY
September 26-30, 2005
University of California, San Diego
California Institute for Telecommunications and Information Technology [Cal-(IT)2]
United States
Co-Organizers: Tom DeFanti, Maxine Brown
Enabling Applications With Advanced
Controllable Optical Transport
• Flexibility and Control (Not Simply ‘Bit Blasting”)
• Providing Applications With Direct Control of Core Resources,
Including at Layer 1 and Layer 2, Nationally and Internationally
• AMROEBA-EA Distributed Computational Astrophysics Modeling
• DataWave: Ultra-High-Performance File Transfer Enabled by
Dynamic Lightpaths (Parallel Optical Data Transport)
• LightForce: High-Performance Data Multicast Enabled by Dynamic
Lightpaths
• Exploring Remote and Distributed Data Using Teraflows
International 10Gb Line Speed Security
• Virtual Machine Turntable
• Multiple OptIPuter Applications
LambdaGrid Control Plane
Paradigm Shift
Traditional Provider Services:
Distributed Device, Dynamic Services,
Invisible, Static Resources,
Visible & Accessible Resources,
Centralized Management
Integrated As Required By Apps
Invisible Nodes,
Elements,
Hierarchical,
Centrally Controlled,
Fairly Static
Unlimited Functionality,
Limited Functionality,
Flexibility Flexibility
Ref: OptIPuter Backplane Project, UCLP
A Next Generation Architecture: Distributed Facility
Enabling Many Types Network/Services
Environment: VO FinancialNet Environment: Sensors
SensorNet HPCNet
Environment: Real Org1
TransLight Environment: Real Org
Environment: Intelligent Commodity Environment: Real Org2
Power Grid Control R&DNet Internet GovNet1
Environment: Gov Agency
Environment: RFIDNet MedNet
RFIDNet Environment:
Environment: Bio Org Control Plane
PrivNet
Environment:
Environment: Lab
Large Scale System Control BioNet
MediaGridNet
Environment: Global App Environment:
International Gaming Fabric
Environment: Financial Org
HP-PPFS HP-APP2 HP-APP3 HP-APP4
VS VS VS VS
Previously OGSA/OGSI, Soon OGSA/OASIS WSRF
Lambda Routing:
tcp Topology discovery, DB of physical links
tcp Create new path, optimize path selection
Traffic engineering
Architecture
ODIN Server Access Constraint-based routing
O-UNI interworking and control integration
Creates/Deletes Policy (AAA) Path selection, protection/restoration tool - GMPLS
LPs, Status Inquiry Process Registration
GMPLS Tools (with CR-
System Manager
LDP)
Discovery
Discovery/Resource Process LP Signaling for I-NNI
Config
Manager, Incl Link Groups Attribute Designation, eg
Instantiation Uni, Bi directional
Communicate
Addresses Interlink
LP Labeling
Monitoring Link Group designations
Stop/Start Module
Resource Balance
ConfDB OSM Interface Adjustments
UNI-N
Data Physical Processing Monitoring and Adjustment
Plane
Resource Resource Resource Resource
Control Channel monitoring, physical fault detection, isolation, adjustment, connection validation etc
New: Intelligent Application Signaling *
IAS
Client Layer Control Plane: Communications Service Layer
Server Service Layer, Policy Based Access Control, Client Message
Receiver, Signal Transmission, Data Plane Controller, Optical Layer Control Plane
UNI Data Plane Monitor
Controlle
Controlle Controlle r
Controlle r r
r I-UNI
CI
Client CI CI
Data
Plane
Server
Client Layer
Traffic Plane
Optical Layer – Switched Traffic (Data) Plane
Multiiservice: Unicast, BiDirectional, Multicast,
Burst Switching
* Also Control Signaling, et al
Multilayer Layer Control Planes and Optical Packet Switching
Edge
Device- Edge
Router
Device Ubiquitous
Cluster
Management
Optical
Plane
Optical
Packet Access
Router
Packet Engineering
Router
Restoration
Performance
Optical Routing Optical
Packet Resource Use
Router
Audits
Optical Optical
Packet Packet
Router Router Ubiquitous
Control
Plane
Provisioning
Wavelength
Data Plane – Assignment
Optical Transport Wavelength
Routing
Optical Layer – Switched Lightpaths
10GE Links GE Links
IEEE 802.3 LAN PHY
Interface, eg, 15xx nm ASW
l1 CSW
10GE serial
l2 10GE Links
Multiwavelength Fiber l3
Grid Clusters
Multiple l Per Fiber l4
ASW
DWDM Links Near Term GE Links
N*N*N Potential for 10 G Elec.
to BP
Multiwavelength Optical Amplifier Longer Term Potential for
Driving Light to BP via Si,
Power Spectral Density Optical, New Polymers
Processor,
Source + Measured PSD
l Monitors, for
Wavelength Precision, etc.
Multiple Optical Impairment Grid Clusters
Issues, Including Accumulations
Computer Clusters Each Node = 1GE
Multi 10s, 100s, 1000s of Nodes
OMNInet Network Configuration
• 8x8x8l Scalable photonic switch
• Trunk side – 10 G WDM
UIC Northwestern
• OFA on all trunks
10 GE l 1 Photonic Photonic
l1 10 GE
PP 10 GE l 2 Node Node PP 10/100/ DOT
8600 l2 10 GE
8600
GIGE
10/100/ Optera
5200
l3 NWUEN-1
l3 Optera Clusters
GIGE 5200
10Gb/s l4 l4 10Gb/s
TSPR TSPR
Optera Metro 5200 OFA
Optera 5200 OFA NWUEN-5 INITIAL
CAMPUS
… CAMPUS CONFIG:
FIBER (16) NWUEN-2 NWUEN-6
FIBER (4) 10 LAMBDAS
NWUEN-3 (ALL GIGE)
EVL/UIC
OM5200
5200 OFA StarLight TECH/NU-E
10 GE OM5200
l PP
Photonic 1 10 GE 10/100/
l
INITIAL Node 2 Optera
8600 GIGE
CAMPUS CONFIG: l3 5200
Fiber
FIBER (4) 10 LAMBDA l4 10Gb/s
TSPR
(all GIGE) NWUEN Span Length
5200 OFA StarLight Link
KM MI
Interconnect
LAC/UIC with other 1* 35.3 22.0
NWUEN-8 NWUEN-9
OM5200 2 10.3 6.4
NWUEN-7 research
3* 12.4 7.7
networks
NWUEN-4 4 7.2 4.5
5 24.1 15.0
5200 OFA
S. Federal 6
7*
24.1
24.9
15.0
15.5
10GE LAN PHY (Dec 03) 8 6.7 4.2
Photonic l 1
10 GE PP
9 5.3 3.3
Node l 2
10 GE 8600 To Ca*Net 4
l3 Optera 10/100/ Fiber in use
5200 1310 nm 10 GbE
l4 10Gb/s GIGE
TSPR WAN PHY interfaces Fiber not in use
DOT Sites, I-WIRE, and OMNInet
OMNInet
Starlight
Argonne Because of SL
(NU-Chicago) Renovation
18 pair
Not Yet Part of Testbed This Cluster is at iCAIR
4 pair
Not Yet Provisioned
Qwest
455 N. Cityfront
UC Gleacher
450 N. Cityfront 4 10 pair 4 pair
UIC McLeodUSA UIUC/NCSA
4 pair
12 pair 151/155 N. Michigan
Doral Plaza
All DOT Links 12 pair
Level(3) Illinois Century Network
Here= GE 111 N. Canal James R. Thompson Ctr
City Hall
State of IL Bldg
2 pair 2 pair
2 pair
IIT UChicago
Chicago
OMNInet
• The OMNInet Testbed is Developing New Architectural Designs for
Communication Services Based on Dynamically Provisioned Lightpaths, Supported
by Agile Optical Networks
• This Research is Investigating New Architecture and Technologies for L1 – L2,
While Also Exploring New Complementary L3 and L4 Methods
• This Research is Creating Fundamentally New Methods for Agile Optical
Transport Enabling Migration From Legacy Architecture, Esp. Those Oriented to
Centralized Management and Control
• The OMNInet Testbed Reduces Hierarchical Layers and Implements Highly
Distributed Controls, e.g., Enabling Applications To Provision Lightpaths
Dynamically
• Since 2001, the Testbed Has Had No SONET Components, OOO Switches at the
Core Have Supported 24 Individually Addressable Lightpaths Among 4 Core Nodes
• Next - Integration of SONET-Less Optical Transport W/SONET Switching
• Through Various Research Projects, the Testbed has Been Extended to Sites
Nationally and Internationally
OMNInet Key Themes and Issues
• A Key Goal Is Enhancing Service Layer Abstractions and
Enabling Direct Manipulation of Core Optical Resources
• Major Improvements Over Centralized Control of Core
Resources Via High Distributed Control
• Decentralization: Applications Can Directly Control Lightpaths
• Advanced Dynamic Lightpath Provisioning Based on
Controllable, Deterministic Optical Networks
• Increased Integration Between Edge and Core Infrastructure
• Agile Solid State Components (e.g, CMOS-Based, PIC-Based)
• Availability of Cost-Effective Fiber and DWDM Equipment
Provides for Highly Disruptive Price/Capability Ratios
Some Results
• Almost Lightpaths Had Minimal to No Packet Loss
• In a Number of Tests, Large Scale Data Streams Were Transported For Many Hours
With No Packet Losses (Measured)
• Measured Performance of Various Provisioning Processes
• More Than 1000 Successful Lightpath Setup/Teardown Operations
• No Optical Component Failures - Several Electronic Component Failures
• Multiple Successful Demonstrations of Multiple New Service/Tech Capabilities
including New Provider Services, New Internal Optical Transport Capabilities
• For Some Traffic, SONET/Routers Not Required (Would Have Been a Performance
Barrier), for Some Traffic, Multi-Service Approach
• Exceptional Grid Application Results – Extremely High Performance
• Have Created and Successfully Demonstrated Multi Times a Basic
Control/Management Plane Architectural Model, & Prototype Implementation
• Demonstrated Utility of Dynamic Lightpath Switching to High Perf. Applications
• Created “Optical Dynamic Intelligent Network” Service Layer Architecture
• Created Lightpath Control Protocol
• Demonstrated the Potential of Photonic Data Services, Wavelength SWng, L1 Sec
• Demonstrated that Many Emerging Technologies Are Ready for Production (e.g.,
GMPLS Can be a Basis for Production Services)
OptIPuter
• The OptIPuter Meets Precise Needs of Applications vs. Today’s Environments
• Centralized Management and Infrastructure Restrictions
• Compromised Applications
• The OptIPuter Enables Creation of Dynamic Distributed Virtual Computers
• Assumes Ubiquitous Lightpaths
• Resources Include Optical Networking Components:
• Dynamic Lightpaths
• Supported by Deterministic Next Generation Optical Networks
• For the OptIPuter, the “Network” is
• A Large Scale, Distributed System Bus and Distributed Control Architecture
• A“Backplane” Based on Dynamically Provisioned Datapaths
• The OptIPuter Addresses the Needs of Extremely Large Scale Sustained Data Flows
• Even Those Exhibiting Dynamic Unpredictable Behaviors
• New Architecture, Methods and New Technologies at All Levels – L1 – L7
AMROEBA-EA
• The AMROEBA-EA Project Was Established to
Investigate the Potential for Conducting Data Intensive
ENZO Simulations On a Large Scale, Distributed
Infrastructure Based on Dynamic Lightpath
Provisioning.
• This Project Is Investigating New Mechanisms That
Allow ENZO Processes to Utilize Additional Resources,
Including Those at Remote Locations World-Wide.
AMROEBA-EA and AMR-ENZO
• AMROEBA-EA: An Adaptive Mesh Refinement Optical Enzo
Backplane Architecture Enabled Application
• AMR-ENZO is used for Computational Astrophysics Modeling
• AMR-ENZO Is Used To Create Many Types of Cosmological
Structure Formation Simulations
• Originally Created By Greg Bryan Under Supervision of Michael
Norman While at NCSA
• AMR-ENZO Has Been Parallelized Using the MPI Message-Passing
Library
• AMR-ENZO and Can Run On Any Shared or Distributed Memory
Parallel Supercomputer or Compute Cluster
• AMROEBA-EA: Shows How These Types of Applications Can
Utilize Distributed Computational Resources And Lightpath
Switching
Visualization
Source Code: Mike Norman, UCSD
Source Code: Mike Norman, UCSD
Overall Networking Plan
Seattle
PW/CENIC
NetherLight
Dedicated Lightpaths
Dedicated Lightpaths
NLR
Pacific Wave Chicago
CENIC
4*1Gpbs
San Diego (iGRID,UCSD) Paths +
One Control Channel
San Diego (iGRID, UCSD) NetherLight 4 Dedicated Paths
Seattle StarLight University of Amsterdam
Route B
AMROEBA Network Topology
iGRID Conference SURFNet/
StarLight University of Amsterdam
Visualization
L2SW L2SW
L2SW OME
L3 (GbE) L2SW
L2SW
L2SW
Control
iGRID Demonstartion iCAIR DOT Grid Clusters UvA VanGogh Grid Clusters
Summary Optical Services: Baseline + 5 Years
2005 2006 2007 2008 2009 2010
New Services Enhanced Direct WS Multidomain Multi New Enhanced Reach Multiple Sites
Abstractions Addressing Announcements Services National, Global
Application Optical Grid Net Extensions to Extensions to Optical Edge Multiple Sites
Optical LP And Instrument Additional Edge Optical BPs Services National, Global
Integration Services API-Op Devices
Access to Highly Multi-Domain Multi Site Access Persistent Inter Extension to Persistence:
Distributed Distributed to Services, Domain Additional Net Common
Control Plane Control Access National, Global Signaling Elements Facilities
National, Global
Deterministic Close Integration Increased Increased Performance Enhanced
Paths (App as w/ App Signaling Attribute Adjustment Metrics and Recovery
Service) Parameters Parameters Methods Restoration
Dynamic Multi-Domain Wavelength Extensions of E2E DLP Large Scale Dist
Lightpath Alloc of DLP Conversion DLP Peering Virtual Optical
Allocation Backplanes
Dedicated Enhanced via Enhanced Increased Increased Increased
Switched WDM Mux Granularity Allocation Allocation Allocation
Lightpaths Demux Capacity Global Capacity US Capacity: Sites
SONET-Less Integration With Optical E2E Transport New Digital New E2E
Optical Trans. SONET SubChanneling Frame Services Framed Services
Multi-Service Integration with Multi-Domain Distributed Monitoring Analysis
Layer Integration Optical Services Integrated Servs Management Techniques Techniques
Wavelength Selectable Multi-Domain Multi-layer Multi-Services Enhanced
Routing Wavelength Wavelength Integration Integration Recovery
Routing Routing Restoration
Summary Optical Technologies: Baseline + 5 Years
2005 2006 2007 2008 2009 2010
O-APIs O-API Signaling App Specific Variable APIs Multidomain E2E Signaling
APIs Signaling
Distributed Integration with Integration with Enhanced Enhanced Enhanced Edge
Control Systems, Standard OADM ROADMs Granularity Addressibility Integration
Multi-Domain
OOO Core At Selected At Selected + Experimental Solid State OSW Solid State (PIC)
Switches Core Sites Core, Edge Sites Solid State Deployment At Core, Edge
OSWs
O-UNIs O-UNI v2 O-UNI v3 Enhanced O-UNI At Selected Deployment At
Signaling Core, Edge Sites Key Sites Global
Service Additional Sig. Increased Increas’d Integra. Prototype Arch Enhanced
Abstraction – Integration Transparency, w/ ID/Obj.Dis for App Specific Architecture
GMPLS Integr. ODIN 2.0 LayerElimination ODIN3 Serv Abstraction ODIN v 3.n
SONET-Less New Types of Metro Core LH Framing Integration With Integration with
Transport Digital Framing Framing Architecture PICs BPs
Architecture
New Id, Object Integration of Integration Integration Extensions to Persistent at
and Discovery New Id, Obj, Dis With Multiple w/New various TE Core, Edge
Mechanisms w/ New Arch. Integrated Serv. Management Functions Facilities
Sys
DWDM DWDM Integration with Integration with Additional Increased
CWDM Edge Optics BP Optics MUX/DMUX Stream
Granularity
2D MEMs 3D LP Switches Experimental Opt Prototype NanoPhotonic At Edge and
Packet SWs Deployed OPSW Devices Core Sites
