45
ElasticTree: Saving Energy in Data Center Networks 許許許 2013/5/28

ElasticTree : Saving Energy in Data Center Networks

  • Upload
    finian

  • View
    22

  • Download
    0

Embed Size (px)

DESCRIPTION

ElasticTree : Saving Energy in Data Center Networks . 許倫愷 2013/5/28. About the paper. Brandon Heller , Srini Seetharaman , Priya Mahadevan , Yiannis Yiakoumis , Puneet Sharma , Sujata Banerjee , Nick McKeown NSDI’10 ( USENIX conference on Networked systems design and implementation ) - PowerPoint PPT Presentation

Citation preview

Page 1: ElasticTree : Saving Energy in Data Center Networks

ElasticTree: Saving Energy in Data Center Networks 許倫愷2013/5/28

Page 2: ElasticTree : Saving Energy in Data Center Networks

About the paperBrandon Heller, Srini Seetharaman, Priya Mahadevan, Yiannis Yiakoumis, Puneet Sharma, Sujata Banerjee, Nick McKeownNSDI’10 (USENIX conference on Networked systems design and implementation)Citation: 17416 pages

Page 3: ElasticTree : Saving Energy in Data Center Networks

OutlineThe big pictureIntroductionElasticTree systemAnalysisConclusion

Page 4: ElasticTree : Saving Energy in Data Center Networks

OutlineThe big pictureIntroductionElasticTree systemAnalysisConclusion

Page 5: ElasticTree : Saving Energy in Data Center Networks

The motivation

Page 6: ElasticTree : Saving Energy in Data Center Networks

The motivation

Very inefficient!!

Desired

Page 7: ElasticTree : Saving Energy in Data Center Networks

Why wasting powerProvisioning for peak Time varying traffic demands Low efficiency at low loads

Page 8: ElasticTree : Saving Energy in Data Center Networks

The goal of ElasticTree

Page 9: ElasticTree : Saving Energy in Data Center Networks

The approach…Turn off unneeded links and switches

Page 10: ElasticTree : Saving Energy in Data Center Networks

The challengePerformanceFault toleranceScalability

Page 11: ElasticTree : Saving Energy in Data Center Networks

OutlineThe big pictureIntroductionElasticTree systemAnalysisConclusion

Page 12: ElasticTree : Saving Energy in Data Center Networks

IntroductionWhat is ElasticTree:

ElasticTree is a system for dynamically adapting the energy consumption of a data center network

• What does it do:

Finding minimum-power network subsets across a range of traffic patternsTrade-off:

energy efficiency, performance and robustness

Page 13: ElasticTree : Saving Energy in Data Center Networks

Introduction

Page 14: ElasticTree : Saving Energy in Data Center Networks

Data center network(Traditional) 2N Tree:

One failure can cut the effective bisection bandwidth in half; two failures can disconnect servers

Page 15: ElasticTree : Saving Energy in Data Center Networks

Data center networkFat tree: SIGCOMM 2008, A Scalable, Commodity Data Center Network Architecture

Page 16: ElasticTree : Saving Energy in Data Center Networks

Data center networkprovision for peak workload Traffic varies daily, weekly, monthly, and yearly.

Page 17: ElasticTree : Saving Energy in Data Center Networks

Energy Proportionality The strategy: turn off the links and switches that we don’t need

Page 18: ElasticTree : Saving Energy in Data Center Networks

OutlineThe big pictureIntroductionElasticTree systemAnalysisConclusion

Page 19: ElasticTree : Saving Energy in Data Center Networks

ElasticTreeElasticTree is a system for dynamically adapting the energy consumption of a data center network

Page 20: ElasticTree : Saving Energy in Data Center Networks

ElasticTreeIf 0.2 Gbps of traffic per host ,1 Gbps link…

Page 21: ElasticTree : Saving Energy in Data Center Networks

ElasticTree13/20 switches and 28/48 links stay active ElasticTree reduces network power by 38%

0.2

0.4

0.8

Page 22: ElasticTree : Saving Energy in Data Center Networks

ElasticTreeThe optimizer: find the minimum- power network subset which satisfies current traffic conditions

Page 23: ElasticTree : Saving Energy in Data Center Networks

OptimizerAs traffic conditions change, the optimizer continuously re-computes the optimal network subset 3 approaches:Formal Model , Greedy Bin-Packing , Topology-aware Heuristic

Page 24: ElasticTree : Saving Energy in Data Center Networks

Optimizer comparison

Page 25: ElasticTree : Saving Energy in Data Center Networks

Formal modelFinding the optimal flow assignment alone is an NP-complete problem for integer flows.Derived from standard multi-commodity flow (MCF) problem The model outputs a subset of the original topology, plus the routes taken by each flow to satisfy the traffic matrix O(n^3.5+)

Page 26: ElasticTree : Saving Energy in Data Center Networks

Greedy Bin-PackingStrategy: choose the leftmost one with sufficient capacity O(n^2+)

1G link

Page 27: ElasticTree : Saving Energy in Data Center Networks

Greedy Bin-Packing1G link

Page 28: ElasticTree : Saving Energy in Data Center Networks

Topo-aware Heuristic1. does not compute the set of flow routes 2. assumes perfectly divisible flows => pack every link to full utilization and reduce TCP bandwidth => starter subset Decoupling power optimization from routing : => can be applied alongside any fat tree routing algorithm

Page 29: ElasticTree : Saving Energy in Data Center Networks

Topo-aware HeuristicAn edge switch doesn’t care which aggregation switches are active, but instead, how many are active

Page 30: ElasticTree : Saving Energy in Data Center Networks

Topo-aware HeuristicDecoupling power optimization from routing

Page 31: ElasticTree : Saving Energy in Data Center Networks

Optimizer comparison

Page 32: ElasticTree : Saving Energy in Data Center Networks

OutlineThe big pictureIntroductionElasticTree systemAnalysisConclusion

Page 33: ElasticTree : Saving Energy in Data Center Networks

How to testK = 6, fat tree

OpenFlow

Page 34: ElasticTree : Saving Energy in Data Center Networks

AnalysisTraffic pattern:

Near: servers communicate only with other servers through their edge switch Far: servers communicate only with servers in other pods

Page 35: ElasticTree : Saving Energy in Data Center Networks

AnalysisRandom demand:

Individual aggregation/core switches turning on/off

Page 36: ElasticTree : Saving Energy in Data Center Networks

Analysis 70% to outside, 30% inside DCN

Different traffic load

Page 37: ElasticTree : Saving Energy in Data Center Networks

Analysis: redundancyIf only the MST is on => no redundancy => no fault tolerance

Page 38: ElasticTree : Saving Energy in Data Center Networks

Analysis: redundancy+MST: additive cost, multiplicative benefit

Page 39: ElasticTree : Saving Energy in Data Center Networks

Analysis: latency

0.25 0.33 0.5

Need safety margin!!

Ethernet overheads (preamble, inter-frame spacing, and the CRC) cause the egress buffer to fill up Packets either get dropped or significantly delayed

Page 40: ElasticTree : Saving Energy in Data Center Networks

Analysis: latencySafety margin is the amount of capacity reserved at every link by the optimizer Traffic overload is the amount each host sends and receives beyond the original traffic matrix

Trade-off between Energy and Performance

Page 41: ElasticTree : Saving Energy in Data Center Networks

OutlineThe big pictureIntroductionElasticTree systemAnalysisConclusion

Page 42: ElasticTree : Saving Energy in Data Center Networks

Summary

Page 43: ElasticTree : Saving Energy in Data Center Networks

Reference The paperThe slide (by the author)A youtube video (by the author, too)http://www.youtube.com/watch?v=G2_D-CH4tQk

Page 44: ElasticTree : Saving Energy in Data Center Networks

Questions

Page 45: ElasticTree : Saving Energy in Data Center Networks

Thank you!