1. CSE 124 Networked Services Fall 2009 B. S. Manoj, Ph.D http://cseweb.ucsd.edu/classes/fa09/cse124 11/03/2009CSE 124 Network Services FA 2009 Some of these slides are adapted from various sources/individuals including but not limited to the images and text from the text book by Kurose and Ross and the IEEE/ACM digital libraries. Use of these slides other than for pedagogical purpose for CSE 124, may require explicit permissions from the respective sources.

2. Announcements Midterm: November 5 Help sheet specs (optional) Must be computer printed Single side of a letter size paper 1-inch margin all sides 10 point font Single-spaced Times New Roman Font Programming Project-2 Innovation on Networked Services Computing services over Email Web proxy service provider 11/03/2009CSE 124 Network Services FA 2009

3. Relevant Topics for Midterm For more details see the course website Kurose and Ross – Chapter 1 – Chapter 2: Sections 2.1, 2.2, 2.4, 2.5, 2.7, and 2.8 – Chapter 3: Sections 3.1, 3.2, 3.3, 3.4, 3.5, 3.7 – Chapter 7: Sections 7.1, 7.2, 7.3, 7.4 Peterson and Davie – Chapter 1: Sections 1.1, 1.2, 1.3, 1.4, and 1.5 – Chapter 5: Sections 5.2, 5.3, 5.4, and 7.1 – Chapter 9: Section 9.1 IEEE papers: Discussion paper 1 and Scalable TCP paper Class lecture slides 11/03/2009CSE 124 Network Services FA 2009

4. Paper Discussion 2 11/03/2009CSE 124 Network Services FA 2009

5. Challenges and benefits Challenges – Inexpensive PCs (unreliable too) – Frequent scaling or reconfiguration – Custom software (limited testing) – Rely on networks (between clusters) – High availability requirement Some benefits High redundancy of hardware Geographical distribution of facilities In-house development of software 11/03/2009CSE 124 Network Services FA 2009

6. Global Deployment of Data Centers 11/03/2009CSE 124 Network Services FA 2009

7. Architectural cases Online Site (AOL?) Content (Hotmail?) ReadMostly (Google?) 11/03/2009CSE 124 Network Services FA 2009

8. Node Architectures Online – Write Anywhere File Layout (WAFL) Content – Custom ReadMostly – Unix Online – 10:1 Content – 1:10 ReadMostly – 1:50 11/03/2009CSE 124 Network Services FA 2009

9. Architecture of on-line site 11/03/2009CSE 124 Network Services FA 2009

10. Architecture of Content Site 11/03/2009CSE 124 Network Services FA 2009

11. Architecture of ReadMostly service 11/03/2009CSE 124 Network Services FA 2009

12. Failures Online – 18 service failures over 4 months Content – 20 service failures over 1 month ReadMostly – 21 service failures over 6 months 11/03/2009CSE 124 Network Services FA 2009

13. Discussion 11/03/2009CSE 124 Network Services FA 2009

14. Peer-to-Peer Network Systems 11/03/2009CSE 124 Network Services FA 2009

15. Pure P2P architecture no always-on server arbitrary end systems directly communicate peers are intermittently connected and change IP addresses Three topics: – File distribution – Searching for information – Case Study: Skype peer-peer 11/03/2009CSE 124 Network Services FA 2009

16. File Distribution: Server-Client vs P2P Question : How much time to distribute file from one server to N peers? usus u2u2 d1d1 d2d2 u1u1 uNuN dNdN Server Network (with abundant bandwidth) File, size F u s : server upload bandwidth u i : peer i upload bandwidth d i : peer i download bandwidth 11/03/2009CSE 124 Network Services FA 2009

17. File distribution time: server-client usus u2u2 d1d1 d2d2 u1u1 uNuN dNdN Server Network (with abundant bandwidth) F server sequentially sends N copies: – NF/u s time client i takes F/d i time to download increases linearly in N (for large N) = d cs = max { NF/u s, F/min(d i ) } i Time to distribute F to N clients using client/server approach 11/03/2009CSE 124 Network Services FA 2009

18. File distribution time: P2P usus u2u2 d1d1 d2d2 u1u1 uNuN dNdN Server Network (with abundant bandwidth) F server must send one copy: F/u s time client i takes F/d i time to download NF bits must be downloaded (aggregate) rfastest possible upload rate: u s +  u i d P2P = max { F/u s, F/min(d i ), NF/(u s +  u i ) } i 11/03/2009CSE 124 Network Services FA 2009

19. Server-client vs. P2P: example Client upload rate = u, F/u = 1 hour, u s = 10u, d min ≥ u s 11/03/2009CSE 124 Network Services FA 2009

20. File distribution: BitTorrent tracker: tracks peers participating in torrent torrent: group of peers exchanging chunks of a file obtain list of peers trading chunks peer rP2P file distribution 11/03/2009CSE 124 Network Services FA 2009

21. BitTorrent (1) file divided into 256KB chunks. peer joining torrent: – has no chunks, but will accumulate them over time – registers with tracker to get list of peers, connects to subset of peers (“neighbors”) while downloading, peer uploads chunks to other peers. peers may come and go once peer has entire file, it may (selfishly) leave or (altruistically) remain 11/03/2009CSE 124 Network Services FA 2009

22. BitTorrent (2) Pulling Chunks at any given time, different peers have different subsets of file chunks periodically, a peer (Alice) asks each neighbor for list of chunks that they have. Alice sends requests for her missing chunks – rarest first Sending Chunks: tit-for-tat rAlice sends chunks to four neighbors currently sending her chunks at the highest rate  re-evaluate top 4 every 10 secs revery 30 secs: randomly select another peer, starts sending chunks  newly chosen peer may join top 4  “optimistically unchoke” 11/03/2009CSE 124 Network Services FA 2009

23. BitTorrent: Tit-for-tat (1) Alice “optimistically unchokes” Bob (2) Alice becomes one of Bob’s top-four providers; Bob reciprocates (3) Bob becomes one of Alice’s top-four providers With higher upload rate, can find better trading partners & get file faster! 11/03/2009CSE 124 Network Services FA 2009

24. Distributed Hash Table (DHT) DHT = distributed P2P database Database has (key, value) pairs; – key: ss number; value: human name – key: content type; value: IP address Peers query DB with key – DB returns values that match the key Peers can also insert (key, value) peers 11/03/2009CSE 124 Network Services FA 2009

25. DHT Identifiers Assign integer identifier to each peer in range [0,2 n -1]. – Each identifier can be represented by n bits. Require each key to be an integer in same range. To get integer keys, hash original key. – eg, key = h(“Led Zeppelin IV”) – This is why they call it a distributed “hash” table 11/03/2009CSE 124 Network Services FA 2009

26. How to assign keys to peers? Central issue: – Assigning (key, value) pairs to peers. Rule: assign key to the peer that has the closest ID. Convention in lecture: closest is the immediate successor of the key. Ex: n=4; peers: 1,3,4,5,8,10,12,14; – key = 13, then successor peer = 14 – key = 15, then successor peer = 1 11/03/2009CSE 124 Network Services FA 2009

27. 1 3 4 5 8 10 12 15 Circular DHT (1) Each peer only aware of immediate successor and predecessor. “Overlay network” 11/03/2009CSE 124 Network Services FA 2009

28. Circle DHT (2) 0001 0011 0100 0101 1000 1010 1100 1111 Who’s resp for key 1110 ? I am O(N) messages on avg to resolve query, when there are N peers 1110 Define closest as closest successor 11/03/2009CSE 124 Network Services FA 2009

29. Summary Source: Kurose and Ross 11/03/2009CSE 124 Network Services FA 2009