1 / 30

PlanetLab Research Activities

PlanetLab Research Activities. Aki Nakao Univ. of Tokyo / NICT. PlanetLab. The largest and most popular overlay network testbed Currently consists of 863 nodes at 447 sites 800+ Projects/ 1000+ Researchers JGN2/NICT collocate overlay nodes in Japan Several Universities in Japan have joined.

maite-york
Download Presentation

PlanetLab Research Activities

An Image/Link below is provided (as is) to download presentation Download Policy: Content on the Website is provided to you AS IS for your information and personal use and may not be sold / licensed / shared on other websites without getting consent from its author. Content is provided to you AS IS for your information and personal use only. Download presentation by click this link. While downloading, if for some reason you are not able to download a presentation, the publisher may have deleted the file from their server. During download, if you can't get a presentation, the file might be deleted by the publisher.

E N D

Presentation Transcript

  1. PlanetLab Research Activities Aki Nakao Univ. of Tokyo / NICT

  2. PlanetLab • The largest and most popular overlay network testbed • Currently consists of 863 nodes at 447 sites • 800+ Projects/ 1000+ Researchers • JGN2/NICT collocate overlay nodes in Japan • Several Universities in Japan have joined 863 nodes 447 sites 40+ countries 1000+ researchers 800+ Projects

  3. Brief History of PlanetLab • PlanetLab 1.0 (2002-3) • UNIX account slivers • PlanetLab 2.0 (2003-4) • Vserver slivers • PlanetLab 3.0 (2004-2006) • PLCAPI 1.0 • PlanetLab 4.0 (2007-) • MyPLC1.0 • Federation Idea • PlanetLab 4.2 (2008) • Federation (PLE, PLJ, (PLK, PLC,=>PLA?)) • New Development (RSpec/GENI-wrapper, New Node Type, Monitoring, QA,VINI) We are here

  4. PlanetLab Consortium • Missions • Support and enhance the PlanetLab • Overseeing the long-term growth • Designing and evolving its software architecture • Providing day-to-day operational support • Defining policies that govern appropriate use • Users are required to join the consortium • Free for academic/non-profit organization • Annual due for corporate members ($300k-$25k)

  5. Two Aspects • Substrate/test-bed for testing distributed applications • Evaluate the new applications on the real networks • Bridge the deployment gap • Prototyping of new generation network architectures • PlanetLab itself is the running code of slice-based network architecture 5

  6. Economic Reality User & Network Reality Implementation Reality Deployment Gap PlanetWorks Coblitz Commercial Adoption Target Pilot Demonstration (PL Gold) Maturity Deployment Study (PlanetLab) Controlled Experiment (EmuLab) Analysis (MatLab) Time [http://www.cs.princeton.edu/~llp/planetlab_oct07.ppt]

  7. New Generation Network and Overlay Network Test-bed • What is Overlay Network Testbed for ? Innovation Feedback Cycle Creation of Ideas Limitations in Prior Models Evaluation at Labs Publish Evaluation at Planetary Scale Acquire Users (Pilot Services) Overlay Test-beds Enables These Establish Innovative Business Contributions to Society New Generation Network Our Goals

  8. CCC.COM BBB.COM A A A A C C C C AAA.COM B B B B client server surrogate redirector CoDeeN: Partial Replication CDN →PlanetWorks (2007-) →Coblitz(2007-) Large File Transfer! Faster than BitTorrent!

  9. Large File Transfer via Coblitz Coblitz [Park 06] Bittorrent [Cohen 03] Info HTTP Tracker Server Client Proxy Peer Peer Peer Server Client Multi Path + Cache Peer

  10. What made PlanetLab successful? • Centralized trust • Centralized resource control • Decentralized management (unbundled management) • The bandwidth as free • Provide only best-effort service • Make Linux the execution environment • Do not provide distributed OS services (up to users) • Evolve the API • Self-Scaling Architecture [Tom Anderson, Timothy Roscoe, “Learning from PlanetLab”, WORLDS’06] [Aki Nakao]

  11. Self-Scaling Architecture (as in P2P) • Consortium • Loosely bound • Membership Agreement • Donate a few resources • At least two machines (minimum H/W requirement) • Bandwidth • “Tit-for-Tat” • Resource reciprocity • The more join, the more useful the system gets • Primary incentives in P2P applications

  12. PLC (PlanetLab Central) Resources resource management PlanetLab Architecture Cambridge Stanford PlanetLab Node U.Tokyo The Internet Princeton U.C.Berkeley MIT CMU PlanetLab Architecture

  13. Future Directions (1) Accelerate the deployment of emerging overlay applications (traditional mission) • CDN, routing, measurement, P2P, DHT, streaming, distributed storage,… (2) Extend PlanetLab architecture itself (towards new generation network architecture) • Federation • Private PlanetLab • Wireless technologies integration • Hardware support (C/D separation) • GENI, VINI 13

  14. PlanetLab New Generation • PlanetLabNG = GENI Prototype • PlanetLab 4.2 + geniwrapper • PLC wrapper: prototype done, integration underway • NM wrapper: prototype in progress • Wrapper includes… • interfaces • namespaces • security mechanisms • Migration plan • seed registries from PLC’s DB • Current and new interfaces coexist • unbundle PLC over time • experiment with peering [PlanetLab Developer's Meeting May 13-14, 2008 (Princeton University) Overview, Deconstructing PLC and Meeting Notes (Larry Peterson)]

  15. PlanetLab Research Activities on JGN2 • JGN2/NICT PlanetLab Collocation • PlanetLab Japan (PLJ) Federation (>PLAsia?) • Private PlanetLab : CORE

  16. Public PlanetLab and Private PlanetLab Birth of Private PlanetLab (enabled by MyPLC) • PlanetLab → Public PlanetLab • Private PlanetLab • Smaller-scale, experimental PlanetLab-like environment From JGN2/NICT stand point • Public PlanetLab Activity • JGN/NICT Collocation • PLJ Federation • Prvate PlanetLab Activity • CORE (Utokyo/NICT)

  17. JGN2/NICT PlanetLab Collocation • JGN2/NICT Collocation • Princeton has donated machines • PIs: NICT/UTokyo Researchers

  18. Research Activity Matrix

  19. SORA Overview SORA makes Routing-Overlay scalable…

  20. SORA: One-Hop Striping Routing

  21. SORA: One-Hop Striping Routing • Enabling Single-Home Multipath [SORA++, J. R. Lane and A.Nakao, under submission]

  22. Research Activity Matrix

  23. Xen-Enabled Private PlanetLab Database VServer Wrapper Control PLC API Xen VM VServer VM Control Xen Wrapper Control Boot Server Control Web Server VMM Framework API Server VMM Framework API Server Communicate Control Communicate Control Xen Kernel MyPLC VServer Kernel New Node New Node As VServer Node As Xen Node

  24. Research Activity Matrix

  25. New Generation Perspectives to Overlay Network - Testbed for prototype and evaluate a new generation network design - Evolutional nature of overlay network to incorporate into the design CORE: Private PlanetLab Current: CORE Sapporo • 10 sites, 52 servers • Multi-Homed • Collaborative Overlay Research Environment • Overlay test-bed based on “Private PlanetLab” • Provision resources for mission critical services • Features we would like to have… • Custom hardware to optimize overlay forwarding • PoP/Core collocation (nodes “inside” network) • Custom hardware to optimize overlay forwarding • Federation (e.g. PlanetLab, OneLab) • Target overlay research • Not just on distributed system apps • More on network core architectures • Utilize both private & public environments • Local v.s. Global / Provisioned v.s. Best-Effort Sapporo Medical U. Tohoku U. Sendai Hiroshima U. NII Kanazawa Nagano Kyutech Tsukuba Nagoya Tokyo U. Tokyo Okayama Kitakyushu Osaka Keihanna Fukuoka Kochi NICT Otemachi Osaka U. NICT Koganei Kochi-tech

  26. PlanetLab Two PlanetLab One Sliver Sliver Sliver Sliver Sliver Sliver Sliver Sliver Federation PLCAPI calls nodes slices nodes slices Sliver Sliver Sliver Sliver Sliver Sliver Non-authoritative caches

  27. PlanetLab Future Activities in Japan • Public, Two kinds of Privates Private PlanetLab to develop Services • Local • Richer Resources • Less Restricted Policy • Small Business PLC PLC PLC PLC Private PlanetLab to develop Infrastructure Federation Public PlanetLab (Federated)

  28. Members • MURATA Masayuki (Advisory) • ATA Shingo • OHZAHATA Satoshi • KAMEI Satoshi (NTT Lab) • KAWAHARA Ryoichi (NTT Lab) • Eng LUA (NTT Lab) • ENOMOTO Nobuyuki (NEC) • FUJINAMI Makoto (NEC) • NISHIKI Ken’ya (Hitachi) • SATOH Hiroki (Hitachi) • MATSUI Susumu (Hitachi) • SHUDO Kazuyuki (Utagoe/NICT) • KDDI Lab people • NAKAO Akihiro (Project Leader) • YAMAMOTO Shu (KDDI) • NAKAUCHI Kiyohide • OZAKI Ryota • NISHIDA Yuji Joined from abroad… • Kurt TUTSCHK (Germany) • Aun HAIDER (New Zealand) • Yufeng WANG (China) • Richard Potter (U.S.) • Du Ping (China) • …inviting more researchers • 3 more candidates (foreign)

  29. Research Lab Location • Hakusan, Tokyo (near Utokyo) 3-Floors (3F, 4F, 6F)

  30. Conclusion • Need to fill these cells with more research items!!

More Related