Problem Statement of Peer to Peer Streaming Protocol (PPSP)

1
Problem Statement of Peer to Peer Streaming
Protocol (PPSP)

• IETF77_at_Anaheim
• Yunfei Zhang
• Ning Zong
• Gonzalo Camarillo
• David Byran
• Hirold Liu
• Yingjie Gu

2
Whats now and Whats new

• Now
• We have got overwhelming consensus on PPSP
  problem statement in IETF76
• Whats new
• Supplements on motivations of PPSP from
• better network resource utilization perspectives
• mobile and wireless requirements
• Supplements on the
• protocol descriptions
• candidates protocol discussions
• scope discussions

3
Key Facts Outline

• Streaming traffic is dominating on the
  Internet,50
• Dealing with streaming transfer using P2P is more
  and more popular and important
• CNTV China National Network Television for CCTV
  programs with P2P live and VoD programs, launched
  since 2010, with a rapid user increase
• The key in P2P streaming solutions is to use edge
  network resources (e.g., peers) efficiently

4
Why Standards in P2P Streaming?(1)

• Technical feasibility strong similarity among
  major systems
• Tracker-based architecture
• Similar tracker and peer communication process,
  and inter-peer communication process
• (See survey and measurement draft)
• Standards gt focusing on key issues, not
  reinventing the wheel

5
Why Standards in P2P Streaming?(2)

• User desire
• broadcasters from the BBC to Germanys ARD
  just seem to love the idea of ditching their
  proprietary platforms.
• -- Johan Pouwelse,
  scientific director of P2P Next
• UUSee will start to build an open platform and
  would like to participate in open protocols to
  cooperate with content providers, operators and
  many more participants for a better p2p streaming
  service.
• -- Zhu Li, CEO of UUSee
• The biggest feature of Mobile Market is its
  openness. We welcome more participants involved
  in the Mobile market development with standards.
• ---Jianzhou Wang,
  President of China Mobile

6
Why Standards in P2P Streaming?(3)
- Open protocols-gtBetter network resource
utilization-gtHigher efficiency

• In case of more content demand as the trend
• Proprietary protocols-gtmore deployed DIFFERENT
  supernodes with LIMITED bandwidth
  competition-gtShare less-gtLow efficiency!!
• Open protocols-gt Share more-gtHigh efficiency
• Open protocols-gtEnhancing P2P network capability
  to existing edge nodes (CDN, caches,NATs)-gtMore
  storage and bandwidth to explore-gthigher
  efficiency

7
More problems for proprietary protocols

• More and more mobile and wireless peers
• Have more possibility to support P2P
• Better CPU, memory and storage
• Better network bandwidth (esp. more uplink waste
  for nothing for symmetric links)
• But
• Unsteady network connections
• Less steady power
• Different media coding for mobile devices
• Current proprietary protocols dont address this
• Hard to extend to address this without open
  protocols

8
To address all these motivation, open protocols
are required

• With this
• Different kinds of Super-peers in the edge
  networks can have more available resource
• can have more options to better resource
  utilization if there are common interests
  (commercial or others)
• P2P streaming can extend to new areas like mobile
  and wireless environments

9
Problems to address

• How to get to know the real-time stream swarm
  peers and what content chunk they have quickly
  even there are some Ms of concurrent requests?
• The current best practice is a tracker-based
  architecture
• Tasks
• Tracker-peer communication For information
  request/answer to provide suitable peers, esp. in
  the initial stage
• Peer-peer communication For information
  gossip-like exchange for each others available
  stream data status and more neighbor peers it
  knows besides tracker tells

10
Discussions(1)-Tracker Protocol

• Tracker organization Tracker discovery
• Centralized no trackers interactions
• Distributed more tasks, trackers to share peer
  lists
• Bittorrent is a good reference for open
  protocols, but not enough
• Different group size
• Bittorent tracker medium size lt1000, global view
  of ALL peers
• PPLIve like tracker Part view of peers and peer
  incrementally by peer protocol to achieve
  scalability
• Different options in the message
• e.g., possible bitmap in VoD for the tracker
  protocol
• Different requirements and user visiting patterns
• video quality and delay
• Channel switch
• Additional peer recruitment
• Different peer roles (super-nodes VS peers)
• Should learn both from Bittorrent and
  PPLive/PPStream/Ravy for more thoughts on
  improving the tracker protocol

11
Discussions(2)-Peer Protocol

• How to exchange chunk availability?
• Modeled as gossip-like protocol, with periodic,
  pairwise,inter-process interactions of changed
  available neighbor peers and media piece states
  called bitmap between peers.
• Information exchanged is of bounded size
• Carried by TCP or UDP,likely together with ICE
  for NAT traversal support.
• Dont involve in chunk transfer
• Including connection negotiation?

12
Thanks!