1. Course Matters

2. Recent Papers from journals

3. Good Posters Bad Posters

4. Improving I/O Performance of Intermediate Multimedia Storage Node Pal Halvorsen Thomas Plagemann Vera Goebel Multimedia Systems 03

5. Problem Improve the performance of I/O in integrated multimedia storage node 3 areas of improvement are identified reduce memory copy checksum computation FEC computation

6. Reduce Memory Copy File system maintain pointer to an area in memory Communication system maintain pointer to same area in memory Memory copy avoided!

7. Network Level Framing Packet payloads are stored with checksum When packets are retrieved for sending, destination address in header is updated Checksum is updated with new destination No need to recompute checksum for payload

8. Integrated Error Management Data are stored on RAID-4 (single parity checks) Use the same error correcting code for RAID and packets Avoid multiple computation of error correcting code

9. Experiment: Memory Copy Read 28662512B file 38 times in a loop The time to transmit data through the storage node is reduced by 45-50% when there is no CPU load, and by 70-73% when CPU load is high

10. Experiment: Network Level Framing Transmit 255MB file Time to calculate checksum is reduced by 95-99% Time spent in kernel is reduced by 51-61%

11. Experiment: Integrated Error Management With encoding FEC, the maximum throughput is 22-24 Mbps. Without encoding FEC, the maximum throughput is 1Gbps

12. Let’s try again..

13. Improving I/O Performance of Intermediate Media Storage Node Pal Halvorsen Thomas Plagemann Vera Goebel

14. Contributions Improve performance by reducing memory copy reducing checksum computation reducing ECC computation

15. Reduce Memory Copy One shared copy of data for different OS component data File System Network System Memory

16. Network Level Framing 1 2 3 store payload with payload’s checksum read payload with checksum update header and checksum Reduce time to packetize data and compute checksum for data

17. Integrated Error Management Avoid multiple computation of error correcting code data ECC RAID ECC reuse RAID ECC as ECC packet

18. Results: Zero Copy

19. Results: Network Level Framing Accumulated UDP Protocol Execution Time for sending 225MB file

20. Results: Integrated Error Management With ECC Encoding Without ECC Encoding 22-24 Mbps1 Gbps Maximum Throughput with/without Encoding using Cauchy-based Reed Solomon Erasure Code

21. Ad Hoc Networks Session 1

22. Mobile Ad Hoc Network Radio Router Host

23. Animation http://www-i4.informatik.rwth-aachen.de/~mesut/manet/manet_en.html

24. Mobile Ad Hoc Network Radio Router Host Radio Router Host Radio Router Host Radio Router Host

25. Examples Battlefield Highway Disaster Zone

26. Challenges All the difficulties of wireless LAN Plus Nodes can move Connections can go up/down No fix route

27. Two Papers IEEE JSAC Special Issues in Wireless Multimedia Baochun Li from U. of Toronto Shiwen Mao from Polytechnic U.

28. NonStop: Continuous Streaming Service on MANET Baochun Li IEEE JSAC 2004

29. Streaming over MANET

30. Network Partition Problem

31. Only Solution.. Predict Partition Replicate Service

32. Partition Prediction

33. Network Partition Problem

34. How to Predict Partition? given velocity of each node cluster nodes into “mobile groups” find mean group velocity

35. Clustering Algorithm

39. Choosing Server ?

40. How to Choose Server? find “stable group” choose server within stable group with the most similar velocity

41. Stable Group AB mean <= radio range and variance is not too large probability distance

42. Stable Group AC D F G H E B

43. AC D F G H E B BCD are in my group AGH are in my group

44. Stable Group AC D F G H E B BCDGH are in my group ABDGH are in my group

45. How to Choose Server? find “stable group” choose server within stable group with the most similar velocity

46. Summary Server construct mobile group by clustering nodes using velocity Use mean mobile group velocity to predict network partition Replicate service before partition to ensure continuous service

47. Summary Node construct stable group by comparing distance over time Choose server within stable group with most similar velocity

48. Multipath Transport and Multistream Coding for MANET Shiwen Mao et. al. IEEE JSAC

49. Single Path Transport

50. Multipath Transport

52. Video Coding: 1 of 3 IPPPPPPP Typical Frame Dependency

53. Video Coding: 1 of 3 I I P P P P P P Multistream Coding

54. Dynamic Reference Frame Choose last received frame as reference believed to be received

55. Predict Network States GOOD :) BAD :( NACKACK

56. Example 0 1 2 3 4 5 6 7 ACK0ACK2ACK4 NACK1NACK3NACK5ACK7 8 9 ACK6 10

57. Video Coding: 2 of 3 IPPP IPPP Base Layer Enhancement Layer

58. Video Coding: 2 of 3 SD EL BL

59. Video Coding: 2 of 3 NACK

60. Video Coding: 2 of 3 SD BL

61. Video Coding: 3 of 3 Multiple Description Coding

62. MDMC +

63. Example of MDMC 359363370 +7 Typical Reference Frame

64. Example of MDMC 359363370 MDMC Reference Frame

65. Example of MDMC 359363+9

66. Example of MDMC 359?+9

67. Example of MDMC 359363370 +9 361

68. Example of MDMC 359?+9,+2

69. Comparisons Reference Frame Layered Coding MDMC Feedback Buffer Decoding Delay

70. Improving Multicast Session 2

71. Organizing Multicast Receivers Brian Neil Levine Sanjoy Paul JJ Garcia-Luna-Aceves Multimedia Systems 03

72. Retransmission in Mcast

73. Idea Ask a neighbour for a missing packet

74. “Helper” Tree

75. Pick Helper By Hop

76. Pick Helper by Hop Not entirely accurate Need to consider latency, link condition etc.

77. Pick Neighbour By Latency

78. Pick Helper by Latency How to measure latency? unicast? multicast? shared-tree? per-source tree?

79. Ideal “Location” of Helper share a common path, and is closer to source (“acceptable”)

80. Idea Suppose node A and B know their path back to the source, then they can deduce if A is acceptable to help B

81. MTrace ABC D E HG F I

82. ERS ABC D E HG F I my path is ABCDF

83. ERS ABC D E HG F I

84. Respond if acceptable not too many helpee

85. Picking Helper packet loss measurement ABC D E HG F I 30% 10%

86. Maintenance Periodic refresh states (soft-states) Periodic repeat procedure

87. Summary Organized receivers based on common path Enable peer-to-peer retransmission

88. THE END