PeertoPeer Networks Outline Survey Selforganizing overlay network File
- Slides: 19
Peer-to-Peer Networks Outline Survey Self-organizing overlay network File system on top of P 2 P network Contributions from Peter Druschel 1
Background • • Distribution Decentralized control Self-organization Symmetric communication 2
Examples • Pioneers – Napster, Gnutella, Free. Net • Academic Prototypes – Pastry, Chord, CAN, … 3
Common Issues • Organize, maintain overlay network – node arrivals – node failures • Resource allocation/load balancing • Resource location • Locality (network proximity) Idea: generic p 2 p substrate 4
Architecture Event notification Network storage P 2 P Substrate TCP/IP ? P 2 p application layer self-organizing overlay network Internet 5
Object Distribution 2128 - 1 Consistent hashing [Karger et al. ‘ 97] 0 objid 128 bit circular id space node. Ids (uniform random) nodeids obj. Ids (uniform random) Invariant: node with numerically closest node. Id maintains object 7
Object Insertion/Lookup 2128 - 1 O X Msg with key X is routed to live node with node. Id closest to X Problem: complete routing table not feasible Route(X) 8
Routing Properties • log 16 N steps • O(log N) state 9
Leaf Sets Each node maintains IP addresses of the nodes with the L numerically closest larger and smaller node. Ids, respectively. • routing efficiency/robustness • fault detection (keep-alive) • application-specific local coordination 10
Routing Procedure if (destination is within range of our leaf set) forward to numerically closest member else let l = length of shared prefix let d = value of l-th digit in D’s address if (Rld exists) forward to Rld else forward to a known node that (a) shares at least as long a prefix (b) is numerically closer than this node 11
Routing Integrity of overlay: • guaranteed unless L/2 simultaneous failures of nodes with adjacent node. Ids Number of routing hops: • No failures: < log 16 N expected, 128/b + 1 max • During failure recovery: – O(N) worst case, average case much better 12
Node Addition 13
Node Departure (Failure) Leaf set members exchange keep-alive messages • Leaf set repair (eager): request set from farthest live node in set • Routing table repair (lazy): get table from peers in the same row, then higher rows 14
API • route(M, X): route message M to node with node. Id numerically closest to X • deliver(M): deliver message M to application • forwarding(M, X): message M is being forwarded towards key X • new. Leaf(L): report change in leaf set L to application 15
PAST: Cooperative, archival file storage and distribution • • • Layered on top of Pastry Strong persistence High availability Scalability Reduced cost (no backup) Efficient use of pooled resources 16
PAST API • Insert - store replica of a file at k diverse storage nodes • Lookup - retrieve file from a nearby live storage node that holds a copy • Reclaim - free storage associated with a file Files are immutable 17
PAST: File storage file. Id Insert file. Id 18
PAST: File storage k=4 file. Id Storage Invariant: File “replicas” are stored on k nodes with node. Ids closest to file. Id Insert file. Id (k is bounded by the leaf set size) 19
PAST: File Retrieval C k replicas Lookup file. Id file located in log 16 N steps (expected) usually locates replica nearest client C 20
- System.net.peertopeer
- Pros and cons of peer to peer network
- "peertopeer networking"
- "peertopeer networking"
- Overlay networks in distributed systems
- File-file yang dibuat oleh user pada jenis file di linux
- Overlay network
- Nvo agenda
- A switch in a datagram network uses
- Basestore iptv
- 叫叫abcd
- Difference between logical file and physical file
- Fungsi dari create file pada operasi-operasi file (cont.)
- Distributed file system definition
- Markup tag tells the web browser
- In a file-oriented information system, a transaction file
- Fire team symbols usmc
- Otv configuration
- Triggered overlay
- Hfw map overlay