Detecting Shared Congestion of Flows Via End-to-end Measurement

1
Detecting Shared Congestion of Flows Via
End-to-end Measurement

• Dan Rubenstein
• Jim Kurose
• Don Towsley
• Computer Networks Research Group

2
Motivation

• When flows share common point of congestion
  (POC), bandwidth can be transferred between
  flows w/o impacting other traffic

• Applications WWW servers, multi-flow
  (multi-media) sessions, multi-sender multicast
• Can limit transfer to flows w/ identical e2e
  data paths Balak99
• ensures flows have common bottleneck
• but limits applicability

3
Detecting Shared POCs

• Q Can we identify whether two flows share the
  same Point of Congestion (POC)?

• Network Assumptions
• routers use FIFO forwarding
• The two flows POCs are either all shared or all
  separate

4
Techniques for detecting shared POCs

• Requirement flows senders or receivers are
  co-located

co-located senders
co-located receivers

• Packet ordering through a potential SPOC same as
  that at the co-located end-system
• Good SPOC candidates

5
Simple Queueing Models of POCs for two flows
Separate POCs
A Shared POC
FG Flow 1
FG Flow 2
FG Flow 1
FG Flow 2
BG
BG
BG
6
Approach (High level)

• Idea Packets passing through same POC close in
  time experience loss and delay correlations
  Moon98, Yajnik99
• Using either loss or delay statistics, compute
  two measures of correlation
• Mc cross-measure (correlation between flows)
• Ma auto-measure (correlation within a flow)
• such that
• if Mc lt Ma then infer POCs are separate
• else Mc gt Ma and infer POCs are shared

7
The Correlation Statistics...
i-4

• Loss-Corr for co-located senders
• Mc Pr(Lost(i) Lost(i-1))
• Ma Pr(Lost(i) Lost(prev(i)))
• Loss-Corr for co-located receivers in paper
  (complicated)

i-3
Flow 1 pkts
i-2
time
i-1
Flow 2 pkts
i

• Delay Either co-located topology
• Mc C(Delay(i), Delay(i-1))
• Ma C(Delay(i), Delay(prev(i))

i1
8
Intuition Why the comparison works

• Recall Pkts closer together exhibit higher
  correlation
• ETarr(i-1, i) lt ETarr(prev(i), i)
• On avg, i more correlated with i-1 than with
  prev(i)
• True for many distributions, e.g.,
• deterministic, any
• poisson, poisson
• Rest of talk assume poisson, poisson

Tarr(prev(i), i)
Tarr(i-1, i)
9
Analytical Results

• As samples
• Loss-Correlation technique
• Assume POC(s) are MM/M/1/K queues
• Thm Co-located senders, then Mc gt Ma iff flows
  share POCs
• co-located receivers Mc gt Ma iff flows share
  POCs shown via extensive tests using recursive
  solutions of Mc and Ma

• Delay-Correlation technique Assume POC(s) are
  MG/G/1/ queues
• Thm Both co-located topologies Mc gt Ma iff
  flows share POCs

10
Simulation Setup

• Co-located senders Shared POCs

on/off sources
R1
30ms
TCP traffic
20ms
20 pps
30ms
S1
10ms
30ms
10ms
1000 Mbs
S2
20 pps
20ms
1.5 Mbs
R2
20ms
11
2nd Simulation Setup

• Co-located senders Independent POCs

on/off sources
TCP traffic
R1
30ms
20ms
20pps
30ms
S1
10ms
30ms
10ms
1.5 Mbs
S2
20pps
20ms
1000 Mbs
R2
20ms
on/off sources
TCP traffic
12
Simulation results
Independent POCs
Shared POCs

• Delay-corr an order of magnitude faster than
  loss-corr
• The Shared loss-corr dip bias due to delayed Mc
  samples
• Similar results on co-located receiver topology
  simulations

13
Internet Experiments

• Goal Verify techniques using real Internet
  traces
• Experimental Setup
• Choose topologies where POC status (shared or
  unshared)
• Use traceroute to assess shared links and
  approximate per-link delays

264 ms
UMass
30 ms
UCL
ACIRI
193 ms
Separate POCs (?)
14
Experimental Results
15
Summary

• E2E Shared-POC detecting techniques
• Delay-based techniques more accurate, take less
  time (order of magnitude)
• Future Directions
• Experiment with non-Poisson foreground traffic
• Focus on making techniques more practical (e.g.,
  Byers _at_ BU CS for recent TR)