Presentation is loading. Please wait.

Presentation is loading. Please wait.

Management Plane Analytics Aaron Gember-Jacobson, Wenfei Wu, Xiujun Li, Aditya Akella, Ratul Mahajan 1.

Similar presentations


Presentation on theme: "Management Plane Analytics Aaron Gember-Jacobson, Wenfei Wu, Xiujun Li, Aditya Akella, Ratul Mahajan 1."— Presentation transcript:

1 Management Plane Analytics Aaron Gember-Jacobson, Wenfei Wu, Xiujun Li, Aditya Akella, Ratul Mahajan 1

2 What is the management plane? Data plane Forwards packets Data plane Forwards packets Control plane Generates forwarding tables Control plane Generates forwarding tables Management plane Defines data plane structure and control plane config Management plane Defines data plane structure and control plane config Config Routing Table Forwarding Table We can model these How do we model this? 2

3 Why study the management plane? Important to well functioning networks! But…there’s no systematic understanding of how management practices impact the health of networks ? Operators have a diversity of opinions on what matters 3

4 Our goals 1.Characterize management practices in modern networks 2.Infer the practices that matter most toward health (e.g., # of failures) 3.Predict health, based on practices →Perform what-if analysis 4.Suggest control plane configurations, given some objectives Inspired by empirical software engineering 4

5 Challenges Management practices aren’t explicitly logged Data may be incomplete or insufficient – Use data from many networks and time periods Configs Inventory Practices Health & Tickets ++ 5

6 Characterizing management practices 850+ networks from an online service provider Two classes of practices – Design: long-term decisions Define network structure and provisioning E.g., how many switches and which vendors – Operational: day-to-day activities Changes to address emerging needs E.g., adding subnets 6

7 Design Practices Heterogeneous physical composition – Multiple roles (86% of networks), vendors (81%), and models (96%) Heterogeneous logical composition – 2+ layer-2 protocols (e.g., VLAN, MSTP) – 1+ routing protocol (89%) 7

8 Operational practices # changes ≈ # devices Different devices changed each month Interface changes are the most frequent Lots of variability in automation; not correlated with # changes 8

9 Are current languages good? Example: adding a VLAN – Cisco IOS – Pyretic – Intent: isolation  want a construct that allows operators to specify this intent (e.g., Merlin?) interface GigabitEthernet1/1 switchport access vlan 101 switchport mode access interface GigabitEthernet1/1 switchport access vlan 101 switchport mode access match(switch=s,inport=1)[modify(vlan=101)>>learn] 9

10 Predicting network health Build a decision tree classifier – Benefit: intuitive for operators to understand – 5 bins for practices; 2 or 5 bins for health – Build with C4.5; prune to avoid over-fitting 91.6% accuracy81.1% accuracy Few unhealthy data points 10

11 Improving predictions Boosting – Increases (decreases) the weight of examples that were classified incorrectly (correctly) Minority oversampling – Clusters data points in the minority class – Generates examples in the same cluster 11

12 Summary Management plane is important to well functioning networks, but not well understood Modern networks have a heterogeneous design and frequent, sometimes automated changes Enable organizations to perform what-if analysis How do we capture intent? 12


Download ppt "Management Plane Analytics Aaron Gember-Jacobson, Wenfei Wu, Xiujun Li, Aditya Akella, Ratul Mahajan 1."

Similar presentations


Ads by Google