1 / 29

Exploiting Route Redundancy via Structured Peer to Peer Overlays

Exploiting Route Redundancy via Structured Peer to Peer Overlays. Ben Y. Zhao, Ling Huang, Jeremy Stribling, Anthony D. Joseph, and John D. Kubiatowicz University of California, Berkeley ICNP 2003. Challenges Facing Network Applications. Network connectivity is not reliable

howell
Download Presentation

Exploiting Route Redundancy via Structured Peer to Peer Overlays

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. Exploiting Route Redundancy via Structured Peer to Peer Overlays Ben Y. Zhao, Ling Huang, Jeremy Stribling, Anthony D. Joseph, and John D. Kubiatowicz University of California, Berkeley ICNP 2003

  2. Challenges Facing Network Applications • Network connectivity is not reliable • Disconnections frequent in the wide-area Internet • IP-level repair is slow • Wide-area: BGP  3 mins • Local-area: IS-IS  5 seconds • Next generation network applications • Mostly wide-area • Streaming media, VoIP, B2B transactions • Low tolerance of delay, jitter and faults • Our work: transparent resilient routing infrastructure that adapts to faults in not seconds, but milliseconds ravenben@eecs.berkeley.edu

  3. Talk Overview • Motivation • Why structured routing • Structured Peer to Peer overlays • Mechanisms and policy • Evaluation • Summary ravenben@eecs.berkeley.edu

  4. Routing in “Mesh-like” Networks • Previous work has shown reasons for long convergence [Labovitz00, Labovitz01] • MinRouteAdver timer • Necessary to aggregate updates from all neighbors • Commonly set to 30 seconds • Contributes to lower bound of BGP convergence time • Internet becoming more mesh-like [Kaat99,labovitz99] • Worsens BGP convergence behavior • Question • Can convergence be faster in context of structured routing? ravenben@eecs.berkeley.edu

  5. Resilient Overlay Networks (MIT) • Fully connected mesh • Allows each node full knowledge of network • Fast, independent calculation of routes • Nodes can construct any path, maximum flexibility • Cost of flexibility • Protocol needs to choose the “right” route/nodes • Per node O(n) state • Monitors n - 1 paths • O(n2) total path monitoring is expensive D S ravenben@eecs.berkeley.edu

  6. Leveraging Structured Peer-to-Peer Overlays source 0 • Key based routing (IPTPS 03) • Large sparse ID space N (160 bits: 0 – 2160) • Nodes in overlay network have nodeIDs  N • Given some key k  N, overlay deterministically maps k to its root node (live node in the network) • route message to root (k) root(k) k • Distributed Hashtables (DHT) is interface on KBR • Key is leveraging underlying routing mesh ravenben@eecs.berkeley.edu

  7. Proximity Neighbor Selection • PNS = network aware overlay construction • Within routing constraints, choose neighbors closest in network distance (latency) • Generally reduces # of IP hops • Important for routing • Reduce latency • Reduce susceptibility to faults • Less IP links = smaller chance of link/router failure • Reduce overall network bandwidth utilization • We use Tapestry to demonstrate our design • P2P protocol with PNS overlay construction • Topology-unaware P2P protocols will likely perform worse ravenben@eecs.berkeley.edu

  8. O V E R L A Y v v v v v v v v v v v v v System Architecture • Locate nearby overlay proxy • Establish overlay path to destination host • Overlay traffic routes traffic resiliently Internet ravenben@eecs.berkeley.edu

  9. register register get (hash(B)) P’(B) put (hash(B), P’(B)) put (hash(A), P’(A)) Traffic Tunneling A, B are IP addresses Legacy Node B Legacy Node A B P’(B) Proxy P’(B) = B P’(A) = A Proxy Structured Peer to Peer Overlay • Store mapping from end host IP to its proxy’s overlay ID • Similar to approach in Internet Indirection Infrastructure (I3) ravenben@eecs.berkeley.edu

  10. Tradeoffs of Tunneling via P2P • Less neighbor paths to monitor per node: O(log(n)) • Large reduction in probing bandwidth: O(n)  O(log(n)) • Increase probing frequency • Faster fault detection with low bandwidth consumption • Actively maintain path redundancy • Manageable for “small” # of paths • Redirect traffic immediately when a failure is detected • Eliminate on-the-fly calculation of new routes • Restore redundancy when a path fails • End result • Fast fault detection + precomputed paths = increased responsiveness to faults • Cons • Overlay imposes routing stretch (more IP hops), generally < 2 ravenben@eecs.berkeley.edu

  11. Some Details • Efficient fault detection • Use soft-state to periodically probe log(n) neighbor paths • “Small” number of routes  reduced bandwidth • Exponentially weighted moving averagein link quality estimation • Avoid route flapping due to short term loss artifacts • Loss rate Ln = (1 - )  Ln-1 +   p • p = instantaneous loss rate,  = hysteresis factor • Maintaining backup paths • Each hop has flexible routing constraint • Create and store backup routes at node insertion • Restore redundancy via “intelligent” gossip after failures • Simple policies to choose among redundant paths ravenben@eecs.berkeley.edu

  12. First Reachable Link Selection (FRLS) • Use estimated loss results to choose shortest “usable” path • Sort next hop paths by latency • Use shortest path withminimal quality > T • Correlated failures • Reduce with intelligent topology construction • Key is to leverage redundancy available 2225 2299 2274 2286 2046 2281 2530 1111 ravenben@eecs.berkeley.edu

  13. Evaluation • Metrics for evaluation • How much routing resiliency can we exploit? • How fast can we adapt to faults? • What is the overhead of routing around a failure? • Proportional increase in end to end latency • Proportional increase in end to end bandwidth used • Experimental platforms • Event-based simulations on transit stub topologies • Data collected over different 5000-node topologies • PlanetLab measurements • Microbenchmarks on responsiveness • Bandwidth measurements from 200+ node overlays • Multiple virtual nodes run per physical machine ravenben@eecs.berkeley.edu

  14. Exploiting Route Redundancy (Sim) • Simulation of Tapestry, 2 backup paths per routing entry • Transit-stub topology shown, results from TIER and AS graphs similar ravenben@eecs.berkeley.edu

  15. 660 300 Responsiveness to Faults (PlanetLab) • Response time increases linearly with probe period • Minimum link quality threshold T = 70%, 20 runs per data point ravenben@eecs.berkeley.edu

  16. Link Probing Bandwidth (Planetlab) • Medium sized routing overlays incur low probing bandwidth • Bandwidth increases logarithmically with overlay size ravenben@eecs.berkeley.edu

  17. Related Work • Redirection overlays • Detour (IEEE Micro 99) • Resilient Overlay Networks (SOSP 01) • Internet Indirection Infrastructure (SIGCOMM 02) • Secure Overlay Services (SIGCOMM 02) • Topology estimation techniques • Adaptive probing (IPTPS 03) • Peer-based shared estimation (Zhuang 03) • Internet tomography (Chen 03) • Routing underlay (SIGCOMM 03) • Structured peer-to-peer overlays • Tapestry, Pastry, Chord, CAN, Kademlia, Skipnet, Viceroy, Symphony, Koorde, Bamboo, X-Ring… ravenben@eecs.berkeley.edu

  18. Conclusion • Benefits of structure outweigh costs • Structured routing lowers path maintenance costs • Allows “caching” of backup paths for quick failover • Can no longer construct arbitrary paths • Structured routing with low redundancy gets very close to ideal in connectivity • Incur low routing stretch • Fast enough for highly interactive applications • 300ms beacon period  response time < 700ms • On overlay networks of 300 nodes, b/w cost is 7KB/s • Future work • Deploying a public routing and proxy service on PlanetLab • Examine impact of • Network aware topology construction • Loss sensitive probing techniques ravenben@eecs.berkeley.edu

  19. Questions… • Related websites: • Tapestry http://www.cs.berkeley.edu/~ravenben/tapestry • Pastry http://research.microsoft.com/~antr/pastry • Chord http://lcs.mit.edu/chord • Acknowledgements • Thanks to Dennis Geels and Sean Rhea for their work on the BMark benchmark suite ravenben@eecs.berkeley.edu

  20. Backup Slides ravenben@eecs.berkeley.edu

  21. Another Perspective on Reachability Portion of all pair-wise paths where no failure-free paths remain A path exists, but neither IP nor FRLS can locate the path Portion of all paths where IP and FRLS both route successfully FRLS finds path, where short-term IP routing fails ravenben@eecs.berkeley.edu

  22. Constrained Multicast • Used only when all paths are below quality threshold • Send duplicate messages on multiple paths • Leverage route convergence • Assign unique messageIDs • Mark duplicates • Keep moving window of IDs • Recognize and drop duplicates • Limitations • Assumes loss not from congestion • Ideal for local area routing 2225 2299 2274 2286 2046 2281 2530 ? ? ? 1111 ravenben@eecs.berkeley.edu

  23. Latency Overhead of Misrouting ravenben@eecs.berkeley.edu

  24. Bandwidth Cost of Constrained Multicast ravenben@eecs.berkeley.edu

  25. Challenge 2: Tunneling Application Traffic • Basic idea • Tunnel “legacy” traffic via overlay proxies • Should be protocol independent • Desired properties • Traffic redirection transparent to end hosts • Stable mapping between a proxy and its legacy nodes • Incremental deployment • Details • Making a connection to D • Determine if D is reachable from overlay • If so, retrieve D’s overlay ID from storage in overlay • Redirect traffic through overlay to D’s overlay ID • Assign legacy nodes IDs in the overlay • Routing to IDs automatically reach respective proxies ravenben@eecs.berkeley.edu

  26. A proxy close by in networkassigns a legacy node a non-random overlay ID Assign closest possible ID to proxy’s ID such that: root (ID) = proxy Chord/Tapestry: ID = proxyID – 1 Stable ID mapping Probability of a new node“hijacking” legacy node very low 1 million nodes, 1000 nodes / proxy, 160 bit names, Ph < 10-40 Assigning Overlay Identifiers proxy 0 proxy source node ID destination node ID ravenben@eecs.berkeley.edu

  27. Unused Slides ravenben@eecs.berkeley.edu

  28. Summary • Highly adaptive to link failures • Fast adaptation time w/ low monitoring BW cost • 300ms beacon period, 7KB/s (300 overlay nodes), response time < 700ms • Low latency and BW overhead for misrouting • Limitation: less useful for congested IP links • Constrained multicast can exacerbate congestion • Can utilize more physically-aware overlay construction • Issue: using loss as congestion indicator • Can fix with more intelligent protocols such as XCP ravenben@eecs.berkeley.edu

  29. Possible Approaches • Modify basic IP protocols • BGP, OSPF, IS-IS • Millions of deployed routers  Significant deployment challenge • “Helper” infrastructures to assist protocols • Manipulate input to improve performance without modification • Deploy intelligent protocols above IP layer • Overlay approach taken by many • Relies on basic point to point IP routing ravenben@eecs.berkeley.edu

More Related