dynamics of end-host controlled routing
DESCRIPTION
Dynamics of End-host controlled Routing. Mukund Seshadri Prof. Randy Katz. Sahara Retreat Jan 2004. Problem. Consider multiple independent overlay networks/flows, each choosing the best overlay route Can this be unstable/inefficient? Identify such scenarios. Suggest improvements. - PowerPoint PPT PresentationTRANSCRIPT
![Page 1: Dynamics of End-host controlled Routing](https://reader035.vdocument.in/reader035/viewer/2022070500/56816838550346895dddfd4e/html5/thumbnails/1.jpg)
1
Dynamics of End-host controlled
Routing
Mukund SeshadriProf. Randy Katz
Sahara Retreat Jan 2004
![Page 2: Dynamics of End-host controlled Routing](https://reader035.vdocument.in/reader035/viewer/2022070500/56816838550346895dddfd4e/html5/thumbnails/2.jpg)
2
Problem Consider multiple independent overlay
networks/flows, each choosing the best overlay route Can this be unstable/inefficient?
Identify such scenarios. Suggest improvements.
![Page 3: Dynamics of End-host controlled Routing](https://reader035.vdocument.in/reader035/viewer/2022070500/56816838550346895dddfd4e/html5/thumbnails/3.jpg)
3
Motivation Overlay routing can provide better
functionality, performance or resilience. e.g. RON[3], Detour[4], ESM[5].
What if several entities set up their own overlay flows?
e.g. using overlay support primitives [2]. Primary app – multimedia streams.
Flows can have some physical links in common, no explicit coordination.
e.g. on popular shared test-beds like PlanetLab[6]. Different networks/independent flows from same network.
![Page 4: Dynamics of End-host controlled Routing](https://reader035.vdocument.in/reader035/viewer/2022070500/56816838550346895dddfd4e/html5/thumbnails/4.jpg)
4
More Background Resilient Overlay Networks
Recovers from routing failures in around 20s, as opposed to several minutes in normal BGP.
If default route from Node A to B fails, then data is redirected through Node C.
All available paths are probed frequently Does not scale beyond 50 nodes
End System Multicast End-hosts form a low-delay or low-b/w degree-
bounded mesh and then a multicast tree.
Extra Slide
![Page 5: Dynamics of End-host controlled Routing](https://reader035.vdocument.in/reader035/viewer/2022070500/56816838550346895dddfd4e/html5/thumbnails/5.jpg)
5
Sources
Destinations
1+ Mbps(L2)
1 Mbps(L3)
Sources
Destinations
Sources
Destinations
Sources
Destinations
Sources
Destinations
Sources
Destinations
Unstable Routing ExampleData Paths
Available Paths
BottleneckPhysical Link
Overlay Nodes
Oscillation of both flows between the two alternate paths is possible.
Each source has a 1Mbps flow.
![Page 6: Dynamics of End-host controlled Routing](https://reader035.vdocument.in/reader035/viewer/2022070500/56816838550346895dddfd4e/html5/thumbnails/6.jpg)
6
Outline of Study Used simulations to study requirements for
good performance and factors affecting it. Some form of “restraint” is needed
Hysteresis Threshold (H) Randomized selection Decision times.
Automatic discovery of H Factors affecting performance
Size and number of flows, path density, cross-traffic, more…
![Page 7: Dynamics of End-host controlled Routing](https://reader035.vdocument.in/reader035/viewer/2022070500/56816838550346895dddfd4e/html5/thumbnails/7.jpg)
7
Simulation Model M overlay networks/flows with N available overlay paths each
All paths monitored Available b/w inferred “perfectly” in a time window (Tm)
Configurable error factor Best path is selected to send traffic on (GREEDY) Route change based on bandwidth improvement threshold (H)
Periodic decisions (Tr) M: 100-1000, N: 5-50.
Path-level simulator Characterizes shared bottleneck links. The level of sharing is characterized by “path density” (Pf) Unicast CBR flows with bandwidth requirement. Flows arrive and depart with lifetimes around 1000 sec.
Metric: Loss Rate (related to bandwidth).
![Page 8: Dynamics of End-host controlled Routing](https://reader035.vdocument.in/reader035/viewer/2022070500/56816838550346895dddfd4e/html5/thumbnails/8.jpg)
8
Simulation Parameters Unless mentioned otherwise, these are the values used for
system parameters.
Extra Slide
![Page 9: Dynamics of End-host controlled Routing](https://reader035.vdocument.in/reader035/viewer/2022070500/56816838550346895dddfd4e/html5/thumbnails/9.jpg)
9
Need for Hysteresis No/Low hysteresis => very unstable, high loss : red line. H too high => high loss due to poor route selection : blue
line. Optimal value of H : green line.
![Page 10: Dynamics of End-host controlled Routing](https://reader035.vdocument.in/reader035/viewer/2022070500/56816838550346895dddfd4e/html5/thumbnails/10.jpg)
10
Path density and H The best value of H varies significantly with
path density (Pf), flow size and other parameters.
The minimum of each each line is the best setting of H, for that value of Pf .
High Pf => greater chance of interaction => worse stability and loss rate.
![Page 11: Dynamics of End-host controlled Routing](https://reader035.vdocument.in/reader035/viewer/2022070500/56816838550346895dddfd4e/html5/thumbnails/11.jpg)
11
Other factors and H The best value of H varies
with other parameters too: Relative flow size –
proportional to inter-arrival-time (IAT).
Cross-traffic percentage.
Explanation of observed trends: the impact of a flow’s re-routing is more significant when a it is a larger fraction of link capacity.
Extra Slide
![Page 12: Dynamics of End-host controlled Routing](https://reader035.vdocument.in/reader035/viewer/2022070500/56816838550346895dddfd4e/html5/thumbnails/12.jpg)
12
Other factors - Summary Combination of following factors
leads to poor performance High path density Large flow size and number Low cross-traffic High load High variation in bandwidths.
![Page 13: Dynamics of End-host controlled Routing](https://reader035.vdocument.in/reader035/viewer/2022070500/56816838550346895dddfd4e/html5/thumbnails/13.jpg)
13
Routing window (Tr) and H Increasing routing window
while keeping measurement window constant can improve performance
Since the no. of flows re-routing during the measurement window decreases.
But can increase reaction time after failure.
Best value of H (line minimum) varies a lot…
![Page 14: Dynamics of End-host controlled Routing](https://reader035.vdocument.in/reader035/viewer/2022070500/56816838550346895dddfd4e/html5/thumbnails/14.jpg)
14
Improvements to GREEDY Randomly select path to be chosen
ARAND: In proportion to available bandwidths SRAND: Best of randomly selected subset of
size S …in proportion to capacity Reduces measurement overhead Works well for server load balancing [1]
(different work model: jobs are assigned to only one server for their lifetime)
GRAND: Randomly select from the best S paths
![Page 15: Dynamics of End-host controlled Routing](https://reader035.vdocument.in/reader035/viewer/2022070500/56816838550346895dddfd4e/html5/thumbnails/15.jpg)
15
Randomized Selection Much lower loss than
GREEDY SRAND and ARAND best
Best value of H still varies w.r.t. path density, etc, for SRAND
![Page 16: Dynamics of End-host controlled Routing](https://reader035.vdocument.in/reader035/viewer/2022070500/56816838550346895dddfd4e/html5/thumbnails/16.jpg)
16
Automatic Discovery of H We propose that flows automatically discover
the most suitable values of H. Flows can independently “probe” values of H
No route change => decrease H Route change => increase H
MIMD works slightly better than other methods.
High initial value; “quick-start” decrease phase (high decrease factor)
![Page 17: Dynamics of End-host controlled Routing](https://reader035.vdocument.in/reader035/viewer/2022070500/56816838550346895dddfd4e/html5/thumbnails/17.jpg)
17
Performance of H-discovery
Very low loss-rates compared to fixed-H.•Upper edge of C.I. is much lower than GREEDY.
• H-discovery works well in all scenarios, including high IAT, below.
![Page 18: Dynamics of End-host controlled Routing](https://reader035.vdocument.in/reader035/viewer/2022070500/56816838550346895dddfd4e/html5/thumbnails/18.jpg)
18
“Cheating” flows What if most flows use “restrained” selection,
while some “cheat” by using more aggressive GREEDY methods?
When “good” flows use fixed H The cheaters obtain much lower loss rates Good flows don’t suffer unless cheaters exceed 35%
of all flows. When good flows use H-discovery
The cheaters do not benefit Good flows’ loss increases when cheaters exceed
20% of all flows, but the loss is still lower than with fixed-H.
![Page 19: Dynamics of End-host controlled Routing](https://reader035.vdocument.in/reader035/viewer/2022070500/56816838550346895dddfd4e/html5/thumbnails/19.jpg)
19
“Cheating” flows - Graphs The cheaters benefit when “good” flows use fixed
H …but not with the H-discovery method
Extra Slide
![Page 20: Dynamics of End-host controlled Routing](https://reader035.vdocument.in/reader035/viewer/2022070500/56816838550346895dddfd4e/html5/thumbnails/20.jpg)
20
Conclusion Already summarized the effect of different
factors on performance. Restraint is useful in route selection.
H, randomization, Tr We propose dynamic discovery of H
Low loss rate in all scenarios. Future work
Investigate dynamic models of flow and cross-traffic.
Study the usefulness of these forms restraint in network-layer routing.
![Page 21: Dynamics of End-host controlled Routing](https://reader035.vdocument.in/reader035/viewer/2022070500/56816838550346895dddfd4e/html5/thumbnails/21.jpg)
21
References1. How Useful is Old Information – M.Mitzenmacher –
PODC 19972. Infrastructure Primitives for Overlay Networks –
Karthik Lakshminarayanan et al. – under submission.3. Resilient Overlay Networks – Andersen et al – SOSP
20014. Detour: a Case for Informed Routing and Transport –
Savage et al. – IEEE Micro Jan 1999.5. A Case for End System Multicast – Yang-hua Chu et al.
– JSAC 2002.6. PlanetLab – http://www.planet-lab.org
Extra Slide