PlanetLab: a Petri dish for the next Internet. Timothy Roscoe Intel Research at Berkeley



Similar documents
Facility Usage Scenarios

Sales Slide Midokura Enterprise MidoNet V1. July 2015 Fujitsu Limited

Virtualized Networks based on System Virtualization

GENI Network Virtualization Concepts

Overlay Network / Network Virtualization Towards New Generation Network Architecture. Aki Nakao The University of Tokyo & NICT

CSci 8980 Mobile Cloud Computing. Mobile Cloud Programming

SURVEY OF INTEREST IN ECE FROM THE BEST UNIVERSITIES IN THE WORLD

NVLAB - Network Virtualization Research Lab (UTokyo and NICT) AKARI Project. Activities toward NWGN

How To Use An Ibm Cloud Server For Business

Data Centers and Cloud Computing

Network Virtualization: A Tutorial

Data Centers and Cloud Computing. Data Centers

Data Center Content Delivery Network

Network Virtualization Server for Adaptive Network Control

Networks and Services

Network Virtualization

Network Virtualization and New Generation Network Research. Aki Nakao

ENABLING INNOVATION THROUGH NETWORK VIRTUALIZATION (AND INTEGRATION OF COMPUTE AND STORAGE)

ServerCentral Cloud Services Reliable. Adaptable. Robust.

Why ISPs need SDN: SDN-based Network Service Chaining and Software-defined Multicast

RCL: Software Prototype

The Platform as a Service Model for Networking

Analysis on Virtualization Technologies in Cloud

Plug-and-play Virtual Appliance Clusters Running Hadoop. Dr. Renato Figueiredo ACIS Lab - University of Florida

Keynote 1. Scale and Programmability in Google s Software Defined Data Center WAN. Amin M. Vahdat University of California San Diego

SoftLayer: Introduction

OVERLAYING VIRTUALIZED LAYER 2 NETWORKS OVER LAYER 3 NETWORKS

The Case for a Hybrid P2P Search Infrastructure

Isaku Yamahata CloudOpen Japan May 22, 2014

REMOTE ASSISTANCE SOLUTIONS Private Server

Ch. 4 - Topics of Discussion

centralized package management using Stork

Performance Analysis of IPv4 v/s IPv6 in Virtual Environment Using UBUNTU

Bring your virtualized networking stack to the next level

The University of California at Berkeley. A Brief Overview July 2007 For Presentation in Tokyo by Professor Stephen Cohen

The old Internet. Software in the Network: Outline. Traditional Design. 1) Basic Caching. The Arrival of Software (in the network)

S06: Open-Source Stack for Cloud Computing

Agenda. Understanding of Firewall s definition and Categorization. Understanding of Firewall s Deployment Architectures

Distributed Systems Lecture 1 1

Software Defined Networking

HYBRID CLOUD Why is it important & how do you manage it?

Server and Storage Virtualization. Virtualization. Overview. 5 Reasons to Virtualize

AKAMAI WHITE PAPER. The Challenges of Connecting Globally in the Pharmaceutical Industry

Copyright 2015 Splunk Inc. Go Big or Go Home. Sean Delaney Specialist SE Mustafa Ahamed Director, Product Management

Virtualization. Types of Interfaces

Software-Defined Networks Powered by VellOS

Software Defined Networking

Data Center Use Cases and Trends

Performance Evaluation of the Illinois Cloud Computing Testbed

The Internet. On October 24, 1995, the FNC unanimously passed a resolution defining the term Internet.

Networking Virtualization Using FPGAs

The Internet Introductory material.

Information- Centric Networks. Section # 13.2: Alternatives Instructor: George Xylomenos Department: Informatics

Cloud Security Best Practices

TRILL Large Layer 2 Network Solution

Network Virtualization and SDN/OpenFlow for Optical Networks - EU Project OFELIA. Achim Autenrieth, Jörg-Peter Elbers ADVA Optical Networking SE

Distributed and Cloud Computing

Cisco Dynamic Workload Scaling Solution

Virtualization Technologies and Blackboard: The Future of Blackboard Software on Multi-Core Technologies

Beyond the Internet? THIN APPS STORE FOR SMART PHONES BASED ON PRIVATE CLOUD INFRASTRUCTURE. Innovations for future networks and services

Converging P2P with clouds towards advanced real time media distribution architectures.

HAWAII TECH TALK SDN. Paul Deakin Field Systems Engineer

Test Requirements at Top Colleges

CPET 581 Cloud Computing: Technologies and Enterprise IT Strategies. Virtualization of Clusters and Data Centers

A Case for Overlays in DCN Virtualization Katherine Barabash, Rami Cohen, David Hadas, Vinit Jain, Renato Recio and Benny Rochwerger IBM

Operation Architecture for Virtualized Infrastructure. Service Platform Architecture

Virtualization. Jukka K. Nurminen

Denial of Service Attacks and Resilient Overlay Networks

Virtualization Technologies (ENCS 691K Chapter 3)

Security in Structured P2P Systems

Title: Scalable, Extensible, and Safe Monitoring of GENI Clusters Project Number: 1723

How To Build A Software Defined Data Center

Installation Guide Avi Networks Cloud Application Delivery Platform Integration with Cisco Application Policy Infrastructure

Using SouthBound APIs to build an SDN Solution. Dan Mihai Dumitriu Midokura Feb 5 th, 2014

SDN/Virtualization and Cloud Computing

Using Proxies to Accelerate Cloud Applications

Cloud3DView: Gamifying Data Center Management

Transcription:

: a Petri dish for the next Internet Timothy Roscoe Intel Research at Berkeley

What is? An open, shared testbed for Developing Deploying Accessing - planetary-scale services. What would you do if you had Akamai s infrastructure?

Motivation New class of applications emerging that spread over sizable fraction of the web Architectural components starting to emerge The next Internet will be created as an overlay on the current one It will be defined by services, not transport There is NO vehicle to try out the next n great ideas in this area

Guidelines (1) Thousand viewpoints on the cloud is what matters not the thousand servers not the routers, per se not the pipes

Guidelines (2) and you must have the vantage points of the crossroads co-location centers, peering points, etc.

Guidelines (3) Each service needs an overlay covering many points logically isolated Many concurrent services and applications must be able to slice nodes => VM per service service has a slice across large subset Must be able to run each service / app over long period to build meaningful workload traffic capture/generator must be part of facility Consensus on a node more important than which node

Guidelines (4) Test-lab as a whole must be up a lot global remote administration and management redundancy within Each service will require own management capability Testlab nodes cannot bring down their site not on forwarding path Relationship to firewalls and proxies is key

Guidelines (5) Storage has to be a part of it edge nodes have significant capacity Needs a basic well-managed capability Initial core of ~100 stable, supported sites. May grow to less managed contributors in time

Initial core team: Intel Research: David Culler Timothy Roscoe Brent Chun See website for all Mic Bowman the rest Princeton: Larry Peterson Mike Wawrzoniak University of Washington: Tom Anderson Steven Gribble

Some signed-up Planet-Lab Sites UBC UW WI Chicago UPenn Intel Seattle Utah Harvard Intel OR Intel MIT Intel Berkeley CMU Cornell UCB ICIR Princeton St. Louis Duke Columbia UCSB Washu KY UCLA GIT UCSD Rice UT ISI Uppsala Copenhagen Cambridge Amsterdam Karlsruhe Barcelona Beijing Tokyo Brazil Canterbury Melbourne

Implementers and Users community seems to divide into two groups at this stage: Folks who want to build this Folks who want to use this Both have diverse and promising research agendas

Implementation Research Issues Sliceability: distributed virtualization Isolation and resource control Security and integrity: exposed machines Management of a very large, widely dispersed system Instrumentation and measurement Building blocks and primitives

Confluence of Technologies Cluster-based management Overlay and P2P networks Virtual machines and sandboxing Service composition frameworks Internet measurement Packet processors Colo services Web services The time is now.

Emerging applications Content distribution Peer-to-Peer networks Global storage Mobility services Etc. etc. Vibrant research community embarking on new direction and none can try out their ideas.

Overlapping Phases of Development 2003 2004 2005 0: seed 1: get API & interfaces right 2: get underlying arch. and impl. right

Development trajectory Node operating system Start with Linux Add isolation and resource management Controlled access to raw sockets Create new thin VMM API Eventually, invert the APIs Distributed components Will run in slices on the platform Community will be enlisted to contribute

The Plan Intel Research is seeding the effort Success: adoption and growth of the research community and creation of novel network services Bring in NSF, Darpa, industry partners Create a non-profit or consortium to manage by late 2004 takes on a life of its own Services define the next Internet Organization manages the central core

What will enable: Open infrastructure for next generation of wide-area ( planetary-scale ) services Foundation on which the next Internet can emerge Think beyond TCP/IP/BGP/DNS/etc. Different kind of network testbed Focus and mobilize the Network / Systems research communities to define the emerging Internet.

Current status Sites coming up each week Second underground meeting in August (SIGCOMM) Website and lists online http://www.planet-lab.org/

What can YOU do for? Be a part of the design process As designers, look at the platform architecture As users, participate in defining the requirements We are looking for all the input we can get.