Informed Content Delivery Across Adaptive Overlay Networks

1
Informed Content Delivery Across Adaptive Overlay
Networks

• Presented by Kelly Whitacre
• Written by John W. Byers, Jeffrey Considine,
  Michael Mitzenmacher, Member, IEEE, and Stanislav
  Rost

2
Problem

• Distributing a large new file across the Internet
  to millions of users simultaneously has proven to
  be challenging

3
Possible Solution Point-to-Point?

• Wasted Bandwidth

• Limited Transfer Rates

• Having individual point-to-point connections from
  a single source wastes bandwidth
• Server must handle load of possible many clients
• Bandwidth costs money
• Server should utilize available Bandwidth

• Transfer rates are limited by the characteristics
  of the end-to-end paths

4
Possible Solution IP Multicast?

• Pros

• Cons

• Solves bandwidth problems of point-to-point
• Server sends one copy
• Network handles the rest

• No flow control
• No retransmission of lost packets
• Limited deployment

5
Reliable Multicast

• Digital fountain approach
• Erasure codessends parity information with
  packets to recover lost (no feedback channels are
  needed to ensure reliable delivery)
• Recirculationinformation is re-circulated
  (fountain) for asynchronous client arrivals
• Parallel Transfer ratesheterogeneous client
  transfer rates so as to not flood network

6
Digital Fountain Approach
k
Source
Instantaneous
Encoding Stream
Transmission
Received
k
Instantaneous
Message
k
Can recover file from any set of k encoding
packets.
7
Digital Fountain Approach
Transmission
File
User 1
User 2
8
Cyclic Interleaving
Transmission
Encoded Blocks
Interleaved Encoding
Blocks
Encoding Copy 1
File
Encoding Copy 2
Tornado Encoding
9
Solution Adaptive Overlay Networks
10
Adaptive Overlay Networks

• Differs from IP Multicast

• Do not use Multicast tree
• Flexibly adapt to changing network conditions
• End systems are explicitly required to
  collaborate!
• Can improve performance by additional
  cross-connections and active collaboration

11
Addressing Limitations Content Delivery Scenario
Consider Initial Delivery Tree
S Source Shaded Area each node has a working
set of packets, the subset of packets it has
received
12
Addressing Limitations Improving Transfer Rates
Harnessing the Power of Parallel Downloads
Tree
Directed Acyclic Graph
Establishing concurrent connections to multiple
servers or peers with complete copies of the file
13
Addressing Limitations Improving Transfer Rates
Harnessing the Power of Collaborative Transfer
Establishing concurrent connections to multiple
peers
14
Addressing Limitations Improving Transfer Rates
Power of Cross-Connections Collaboration
(d) depicts the portions of content which can be
beneficially exchanged via pair-wise transfers
15
Considerations

• (a) (b) impede the full flow of content to
  downstream receivers
• Opportunistic connections of (c) (d) allow for
  higher transfer rates
• Yet, demand more careful orchestration between
  end systems
• Must determine set difference of working sets
• Reconciliation is simple in working sets limited
  to small contiguous blocks
• Limits flexibility of frequent changes that arise
  in AON

16
Content Delivery Across Adaptive Overlay Networks

• Challenges
• Stateful vs. Non-Stateful Solutions

17
Adaptive Overlay Networks in a Fluid Internet

• Challenges

• Need to

• Asynchrony
• Receivers may open and close connections or leave
  and rejoin the infrastructure at arbitrary times
• Heterogeneity
• Connections vary in speed and loss rates
• Transience
• Routers, links, and end systems may fail and
  their performance may fluctuate over time
• Scalability
• The service must scale to large receiver
  populations and large content

• Adaptively detect and avoid congested or
  temporarily unstable areas of the network
• Dynamically establish paths with the most
  desirable end-to-end characteristics
• Deliver useful content, often in parallel with a
  minimum of setup overhead and message complexity

18
Limitations of Stateful Solutions

• Addresses

• A significant per-connection state

• Issues of connection
• Connections that vary in speed and loss rates
• Clients coming and going at arbitrary times

• Is highly unscalable
• May impact performance
• state must be maintained in the face of
  reconfiguration and reconnection
• With parallel downloading is problematic

19
Alternative Encoded Content through Digital
Fountain Approach

• Digital Fountain Approach
• Resilience to packet losserasure-correcting code
• Guarantee
• Claims recover the original source file from
  any subset of distinct symbols in the encoding
  stream equal to the size of the original file
• In practice recover a file from a few percent
  more than the number of symbols in the original
  file

20
Encoded Content through Digital Fountain Approach

• Pros

• Continuous Encoding
• Senders with a complete copy of a file may
  continuously produce fresh encoding symbols
• Time Invariance
• New encoding symbols are produced independently
  from symbols produced in the past
• Tolerance
• Digital fountain streams are useful to all
  receivers regardless of the times of their
  connections or disconnections and their rates of
  sampling the stream
• Additivity
• Parallel downloads from multiple servers with
  complete copies of the content require no
  orchestration

Stateless!
21
Encoded Content through Digital Fountain Approach

• Cons

• Encoding/Decoding Overhead
• Reconciliation methods are needed for those
  collaborating end systems have only a portion of
  the content

22
Reconciliation and Informed Delivery

• Coarse-grained reconciliation
• Speculative transfers
• Fine-grained reconciliation

23
Note

• Approaches proposed are local in scope and
  typically involve a pair or a small number of end
  systems
• Goal is to provide the most cost-effective
  reconciliation mechanisms measuring cost both in
  computation and message complexity

24
Coarse-Grained Reconciliation

• Estimate resemblance working sets of pairs of
  nodes prior to establishing connections
• Quick estimates of the fraction of symbols common
  to the working sets of both peers
• Approach 1 Employs Random Sampling
• Approach 2 Employs sketches of each peers
  working set
• High-level information
• Lightweight, computed efficiently
• Incrementally updated
• Fit into a single 1-kB packet

25
Notation Framework

• Let peers A and B have working sets SA and SB
  containing symbols from an encoding of the file
• Containment
• The containment of B in A is the quantity
• Resemblance
• The resemblance of A and B is the quantity

26
Notation Framework

• Each element of a working set is identified by an
  integer key (sending an element entails sending
  its key)
• Keys are distributed over the key space uniformly
  at random
• With 64-bit keys, a 1-kB packet can hold roughly
  128 keys
• Can be the same
• If the elements are determined by a hash function
  seeded by the key, two keys may generate the same
  element with small probability
• Minimal impact

27
Random Sampling

• Select elements of the working set at random and
  transport those to the peer.

28
Random Sampling

• Pros

• Cons

• Unbiased estimate of containment
• Can be incrementally updated using reservoir
  sampling

• Must search its own working set for each element
  in random set
• Do not easily allow one peer to check the
  resemblance between prospective peers
• A cannot check resemblance between B C

29
Min-Wise Sketches

• Calculates working set resemblance based on
  min-wise sketches

30
Min-Wise Sketches

• ?i represents a random permutation on the key
  universe
• A sends B a vector of As minima (elements that
  lie in both sets)
• B Counts the number of positions where the two
  are equal
• Divides by the total number of permutations

The result is an unbiased estimate of the
resemblance
31
Min-Wise Sketches

• Pros

• Cons

• Unbiased estimate of resemblance
• Allows similarity comparisons given any two
  sketches for any two peers
• A can check resemblance between B and C

• Truly random permutations cannot be used
• Storage requirements are impractical
• Possibility of false positives
• ?i values are hashed to fewer bits to allow for
  more sketch elements in packet
• (Details not discussed)

32
Speculative Transfers

• Involve a sender performing educated guesses as
  to which symbols to generate and transfer
• Send symbols which are probably useful to the
  other
• This process can be fine-tuned using the results
  of coarse-grained reconciliation

33
Speculative Transfers

• When containment of B in A is low, speculative
  transfers is trivial since most of Bs symbols
  are useful to A
• When containment of B in A is high, strategy is
  inefficientuse recoding

34
Recoding

• A recoding symbol is simply the bitwise XOR of a
  set of encoding symbols
• Must be accompanied by a specification of the
  encoding symbols blended to create it
• Must explicitly list the random seeds of the
  encoding symbols from which it was produced

35
Encoding/Decoding Recoding Symbols

• Similar to the substitution rule
• Examplepeers with y5, y8, y13 generate recoding
  symbols
• Z1 y13
• Z2 y5 XOR y8
• Z3 y5 XOR y13
• Peer receives Z1, Z2, Z3 can recover y13
• By substitution recover y5 y8

36
Fine-grained Reconciliation

• Is a set-difference problem
• Tries to determine the exact difference of SA -
  SB
• Many approaches
• Polynomial-Based
• Enumeration-Based
• Bloom filter
• Search-Based
• Approximate Reconciliation Trees (ART) which
  combine the compact representation of Bloom
  filters with the speed of a search-based approach

37
Bloom Filter

• A set of n elements that represent the working
  set calculated by independent random hash
  functions
• Flow
• Peer A sends B a Bloom filter FA of SA
• Peer B then checks for each element of SB in FA
• Peer B has determined SA - SB
• This solution is effective particularly when the
  number of differences is a large fraction of the
  set size

38
Experimental Results

• Demonstrate the benefits and costs of using
  reconciliation in peer-to-peer transfers and in
  parallel downloads

39
Simulation Parameters

• All consider transfer of a 128-MB file
• Origin server
• Divides this file into input symbols of 1400
  bytes each (fit it in an Ethernet packet with
  headers)
• Encodes this file into a large set of encoding
  symbols
• Associate each encoding symbol with a 64-bit
  identifier representing the set of input symbols
  used to produce it
• Min-wise sketches used 180 permutations, yielding
  180 entries of 64 bits each for a total of 1440
  bytes per summary
• Bloom filters used 6 hash functions and 8(1
  0.0025)L bits for a total of 96 kB per filter

40
Collaboration Methods

• Uninformed
• The sending peer picks a symbol to send at random
• Speculative
• The sending peer uses a min-wise sketch from the
  receiving peer to estimate the containment
• Reconciled
• The sending peer uses either a Bloom filter or an
  ART from the receiving peer to filter out
  duplicate symbols and sends a random permutation
  of the differences.

41
Scenarios and Evaluation

• Varying 3 experimental factors
• Set of connections in the overlay formed between
  sources and peers
• Distribution of content among collaborating peers
• Slack of the scenario (1.1 1.3)
• When smaller than (1 decoding overhead), the set
  of peers will be unable to recover the file
• When larger than (1decoding overhead), the set
  of peers will most likely recover the file
• Methods provide the most significant benefits
  over naive methods when there is only a small
  amount of slack

42
Scenario 1 Two peers with Partial Content

• One peer sends symbols to the other

of Shared Encoding Symbols

• Uninformed collaboration performs poorly and
  degrades significantly as the containment
  increases
• Speculative collaboration is more efficient, but
  the overhead still increases slowly with
  containment
• Overhead of reconciliation is purely from the
  cost of transmitting a Bloom filter or ART (less
  than a )

43
Scenario 2 Download from a Server with Complete
Content

• With concurrent transfer from a peer

of Shared Encoding Symbols

• Uninformed collaboration overhead is
  considerably lower than in the scenario 1 (larger
  fraction of the content is sent directly via
  fresh symbols from the server)
• Speculative collaboration performs similarly to
  scenario 1
• Reconciled collaboration has overhead slightly
  higher than receiving symbols directly from the
  server

44
Scenario 3 Parallel Download from Peers with
Partial Content

• Collaborating With Multiple Peers in Parallel

of Shared Encoding Symbols

• Can leverage bandwidth from peers with partial
  content with only a slight increase in overhead
• Uninformed collaboration performs extremely
  poorly
• Speculative collaboration dramatically improves
  as containment increases
• Reconciled collaboration has much higher
  overhead than before

45
Conclusions

• Adaptive overlay networks offer a powerful
  alternative to traditional mechanisms for content
  delivery
• Flexibility, scalability, and deploy-ability.
• Informed and effective collaboration between end
  systems can be achieved through the digital
  fountain approach
• Care is needed to provide methods for
  representing and transmitting the content in a
  manner that is as flexible and scalable as the
  underlying capabilities of the delivery model

46
Questions?
47
Supplemental Reading and Resources

• A Digital Fountain Approach to Reliable
  Distribution of Bulk Data http//www.ecse.rpi.edu/
  Homepages/shivkuma/teaching/sp2001/readings/digita
  l-fountain.pdf
• ACM SIGCOM 98, A Digital Fountain Approach to
  Reliable Distribution of Bulk Data
  http//www.sigcomm.org/sigcomm98/tp/abs_05.html