Transcript ppt - Sahara - University of California, Berkeley

SAHARA/I3 First Summer Retreat
10-12 June 2002
Randy H. Katz, Anthony Joseph, Ion Stoica
Computer Science Division
Electrical Engineering and Computer Science Department
University of California, Berkeley
Berkeley, CA 94720-1776
1
Retreat Goals &
Technology Transfer
People
Project Status
Work in Progress
Prototype Technology
Early Access to Technology
Promising Directions
Industrial Collaborators
UC Berkeley Project Team
Reality Check
Friends
Feedback
2
Who is Here (Industry)
• AT&T Research
– Yatin Chawathe
• CMU
– Hui Zhang
• Ericsson Research
• Nortel Networks
– Tal Lavian (PhD student)
• NTTDoCoMo
– Takashi Suzuki (VIF)
– Gang Wu
– Per Johansson (VIF)
– Martin Korling
• Sprint ATL
– John Apostolopoulos
– Wai-Tian Dan Tan
• UC Davis
• Hewlett-Packard Labs
• Intel Research
– Timothy Roscoe
– Bryan Lyles
– Paul Jardetzky
– Chen-nee Chuah
– Dipak Ghosal
• Keynote Systems
• Univ. Helsinki
• Microsoft Research
• Univ. Washington
– Chris Overton
– Venkat Padmanabhan
– Lili Qui
– Helen Wang
• Nokia
– Hannu Flinck
– Kimmo Raatikainen
– Tom Anderson
• Other Affiliation
– Peter Danzig
Italics indicates Ph.D. from Berkeley
VIF=Visiting Industrial Fellow
3
Who is Here (Berkeley)
• Professors
–
–
–
–
Anthony Joseph
Randy Katz
Ion Stoica
Doug Tygar
• Postdocs
– Kevin Lai
• Technical & Admin Staff
– Nathan Berneman
– Bob Miller
– Keith Sklower
• Grad Students
–
–
–
–
Sharad Agarwal
Matt Caesar
Weidong Cui
Steve Czerwinski
• Grad Students
–
–
–
–
–
–
–
–
–
–
–
–
–
–
–
Yitao Duan
Ling Huang
Almadena Konrad
Karthik Lakshminarayanan
Yin Li
Huang Ling
Sridhar Machiraju
George Porter
Bhaskar Raman
Anantha Rajagoplala-Rao
Mukund Seshadri
Jimmy Shih
Lakshmi Subramanian
Ben Zhao
Shelley Zhuang
4
Retreat Purpose
• Second SAHARA retreat
– Project launched 1 July 2001
– Review progress, set directions, particularly in terms of integrating
the diverse efforts underway
• “Generation after next” networks
– Software “agents,” not protocols
– Converged data and telecommunications networks
– Heterogeneous access plus core networks
• Emerging network-aware distributed architecture
– Confederation vs. brokering in service provisioning
– Exploiting network structure-awareness
– Four layer “reference” architecture
• Industrial feedback and directions
– Real-world networking problems/limitations
– Helping us do relevant research at Internet-scale
5
Plan for the Retreat
• Monday, 10 June 2002
– 1200-1315 Lunch
– 1315-1500 Retreat Overview and Introductions (Randy)
» Retreat Overview & Sahara Progress, Randy Katz
» Research on Adaptive Systems, Anthony Joseph
» I3 Overview, Ion Stoica
– 1500-1530 Break
– 1530-1700 Routing as a Cross-Domain Service (Randy)
» Ion Student: Multicast on I3
» Mukund: Interdomain Multicast
» Sharad: Policy Agent for Interdomain Routing
» Lakshmi: Overlay QoS
– 1700-1730 View from a Tier-1 ISP (Chen-nee)
– 1730-1800 Break
– 1800-1915 Dinner (Joint with ROC Retreat)
– 1915-2015 Alfred Spector, IBM (Joint with ROC Retreat)
– 2015-2100 Student Poster Session
6
Plan for the Retreat
• Tuesday, 11 June 2002
– 0730-0830 Breakfast
– 0830-1000 Joint I3/Tapestry Session (Kubi/Ion)
» Services on Infrastructure, Kubi/Ion
» Mobility on I3, Shelley/Kevin
» Mobility on Tapestry, Ben
– 1000-1030 Break
– 1030-1200 Adaptation and Applications (Anthony)
» Modeling/Analysis of Non-Stationary Net Characteristics, Almudena
» Always Best Connected, Machi
» VoIP Gateway Selection, Matt
– 1200-1300 Lunch
– 1300-1600 Long Break
– 1600-1800 SAHARA Architecture and Brainstorming Session (Randy)
» Four Layer Architecture, Bhaskar
» Hot Spot WLAN Testbed for Sahara Integration, Jimmy
– 1800-1915 Dinner (Joint with ROC Retreat)
– 1915-2000 Panel on Robust Manageable Distributed Systems
7
– 2000-2130 Second Graduate Student Poster Session
Plan for the Retreat
• Wednesday, 12 June 2002
–
–
–
–
–
–
0730-0830 Breakfast
0830-1000 Six Month Planning (Anthony)
1000-1030 Break/Room Checkout/Photo Session
1030-1200 Industrial Feedback (Randy)
1200-1300 Lunch
1300-1700 Bus back to Berkeley
8
SAHARA: 2001-2003
•
•
•
•
•
•
Service
Architecture for
Heterogeneous
Access,
Resources, and
Applications
9
Scenario: Service
Composition
Restaurant
Guide Service
JAL
UI
Babblefish
Translator
NTTDoCoMo
Zagat Guide
User
Tokyo
Sprint
Salt Lake
City
User
10
Sahara Research Themes
• New mechanisms, techniques for end-to-end services
w/ desirable, predictable, enforceable properties
spanning potentially distrusting service providers
– Architecture for service composition & inter-operation across
separate admin domains, supporting peering & brokering, and diverse
business, value-exchange, access-control models
– Functional elements
» Service discovery
» Service-level agreements
» Service composition under constraints
» Redirection to a service instance
» Performance measurement infrastructure
» Constraints based on performance, access control,
accounting/billing/settlements
» Service modeling and verification
11
Cable
Modem
Connectivity and Processing
Premisesbased
Access
Networks
Core Networks
WLAN
Transit Net
WLAN
Operatorbased
Cell
Cell
Cell
Regional
LAN
Transit Net
Premisesbased
WLAN
LAN
Internet
Datacenter
NAP
Public
Peering
Data
Voice
Analog
Transit Net
H.323
RAS
H.323
PSTN
LAN
Private
Peering
DSLAM
Data
Voice
Wireline
Regional
12
Service Composition Models
Cooperative
Negotiation & control path
Service
Service
Service
Data flow
Brokered
Negotiation & control path
Broker
Service
Data flow
Service
Service
13
Layered Reference Model for
Service Composition
Middleware Services
End-to-End Network
With Desirable Properties
Enhanced Paths
Enhanced Links
Connectivity
Plane
Service
Composition
Applications Services
Application
Plane
End-User Applications
IP Network
14
Layered Reference Model
for Service Composition
Composed Service at Layer i
Measurement-based
Adaptation
Interoperabilty
Dynamic Resource
Allocation
Policy
Management
Trust Management/
Verification
Underlying
Composition
Techniques
Services
at Layer i-1
Services
ServicesatatLayer
Layeri-1
i-1
Component Services
Services
at Layer
i-1
Other
Services
at Layer i
15
Mechanisms for Service
Composition
• Measurement-based Adaptation
– Examples
» General-purpose third party end-to-end Internet host
distance monitoring and estimation service
» Universal In-box: Application-specific middleware
measurement layer to exchange network and server
load using link-state algorithm
» Content Distribution Networks: measurement-based
DNS-based server selection to redirect client to
closest service instance
16
Mechanisms for Service
Composition
• Utility-based Resource Allocation Mechanisms
– Examples
» Auctions to dynamically allocate resources; applied for
spectrum/bandwidth resource assignments to MVNO from
underlying competiting MNOs
» Congestion pricing: influence user behavior to better utilize
scarce resources; applied in:
• Voice port allocation to user-initiated calls in H.323 gateway/Voice over IP
service management
• Wireless LAN bandwidth allocation and management
• H.323 gateway selection, redirection, and load balancing for Voice over IP
services
17
Mechanisms for Service
Composition
• Trust Mgmt/Verification of Service & Usage
– Authentication, Authorization, Accounting Services
» Authorization control scheme w/ credential transformations to
enable cross-domain service invocation
» Federated admin domains with credential transformation rules
based on established peering agreements
» AAA server makes authorization decisions, liberating providers
from preparing rules for each affiliated domain
– Service Level Agreement Verification
» Verification and usage monitoring to ensure properties specified in
SLA are being honored
» Border routers monitoring control traffic from different
providers to detect malicious route advertisements
18
Mechanisms for Service
Composition
• Policy Management
– Visibility into local policies to better coordinate global
policies among (cooperating) service providers
– Developing inter-AS architecture for load balancing,
performance and failure mode policies to be applied
throughout the network
» Internet topology discovery through AS relationship
map of the Internet plus measurement infrastructure
» Policy agent framework for inter-AS negotiation to
manage incoming traffic
19
Mechanisms for Service
Composition
• Interoperability through Transformation
– Interoperability of data, protocols, policies among
composed service providers
– Example
» Broadcast federation: global multicast service
composed from multicast implementations in different
provider domains
» Protocol transformation gateways between admin
domains employing non-interoperable multicast
protocol implementations
20
Summary and Conclusions
• Goal: Evolve (mobile) Internet architecture to better
support multi-network/multi-service provider model
– Dynamic environment, location-based implies larger numbers of
service providers & service instances
• Status: architectural specification driven by selected
applications and underlying wide-area services
• Focus:
– Composition across confederated vs. independent service providers:
peer-to-peer vs. brokering
– Explore new techniques/technologies:
» Market-based mechanisms
» Trust management, SLA verification, perf. monitoring
21
Our Mascot
44