Project 1-Task 1 Routing Performance in Distributed SDC under Synchronization Constraint PhD students: Ziyao Zhang and Qiaofeng Qin PI and Collaborators: Liang Ma, Konstantinos Poularakis, Kin Leung, Leandros Tassiulas, Dave Conway-Jones, Andreas Martens, Franck Le, Sastry Kompella, and Jeremy Tucker Imperial, Yale, IBM US/UK, NRL, Dstl
P1T1 US-UK Collaborations Experiment Modeling Qiaofeng Qin, Konstantinos Ziyao Zhang, Liang Ma, Konstantinos Poularakis, Leandros Tassiulas, Poularakis, Kin Leung, Leandros Sastry Kompella, Andreas Tassiulas, Franck Le, Sastry Martens Kompella, Jeremy Tucker Yale, NRL, IBM UK Imperial, IBM US, Yale, P1T1 NRL, Dstl Distributed Theory Demo SDC Ziyao Zhang, Liang Ma, Qiaofeng Qin, Konstantinos Konstantinos Poularakis, Kin Poularakis, Leandros Tassiulas, Kin Leung, Leandros Tassiulas, Franck Leung, Sastry Kompella, Andreas Le, Sastry Kompella Martens, Dave Conway-Jones, Franck Le, Jeremy Tucker Imperial, IBM US, Yale, NRL Yale, Imperial, IBM US/UK, NRL, Dstl 2
Motivations Distributed SDC Software Defined Coalitions (SDC) • programmable coalition management • easy reconfiguration enclave • on-demand resource allocation • rapid response to failures in military networks enclave enclave enclave Challenges in realizing distributed SDC • fundamental understanding of key factors affecting the overall performance in distributed SDC Ø Experiments Ø Analytical Results 3
Experiments § Implement a real wireless SDN system by installing commercial SDN components (ONOS controller, Open vSwitch data path) into mobile devices (Android smartphones) Wi-Fi � Hotspot Android Smartphone ONOS � � Open vSwitch Controller Controller Wi-Fi Interface � § Measure the delay of SDN control (time required to reconfigure a data plane device by its nearest controller): – The average delay is highly sensitive to #hops and the controller placement strategy 4
Large-scale Emulations § Emulate networks with hundreds of nodes using Mininet virtual testbed. § Two types of SDN control overheads measured: – Controller-node traffic to collect state information and send flow setup rules. – Inter-controller traffic to synchronize the states among controllers. Inter-Controller Traffic Controller Cluster ONOS ONOS ONOS Controller-Node Traffic Edge Node 2 Edge Node 3 Edge Node 1 Edge Node 4 · · · · · · Mininet Edge Node 5 Edge Node N – The two types of overhead are significant and of the same order of magnitude (up to a few Mbps). – Increase almost linearly with the network size (#nodes/flows/controllers). 5
Impact of Synchronization on Network Performance § The above experiments/emulations highlight the feasibility of distributed SDN and the operational overheads due to synchronizations § challenging to achieve full status synchronizations among controllers in a real system • we therefore focus on analyzing and quantifying the network performance in distributed SDN , under incomplete synchronization levels and different network structural properties 6
Problem Formulation – Network Model (two-layer model) top-layer • vertex: domain • edge: two domains are connected bottom-layer physical intra-/inter-domain connections constrained by the top- layer topology A generic model: • input: #domains, #nodes/#gateways in each domain, top-layer vertex degree distribution, and intra-domain node degree distribution • no assumptions on specific random graph models 7
Problem Formulation - Performance under Dynamically Adjusted Link Preference Levels § Link preference level: SDN controllers assign weight (called link preference ) to links according to traffic status, security policies, and other collected network information – smaller the link weight à better for path construction – link preference is dynamically adjusted by controllers à modeled as random variables § no assumptions on the pdf of these random variables – Goal : find the path that incurs the minimum accumulated end-to-end path cost between two arbitrary nodes in different domains (average path cost - APC) Objective: derive APC expression under various link preference levels and inter-domain synchronization scenarios when a basic routing mechanism is used 8
Synchornization Scenarios § Synchronization: domain A is synced with B if A knows the minimum path cost for any two nodes in B § Synchronization radius: max integer τ à all domains within τ -1 hops in the domain-wise topology are synced Highest sync level: generally cannot achieve Complete Sync (CS) each domain is synced with all other domains Highest Level sync level between SS and CS; quantified by the synchronization radius Partial Sync (PS) intra-domain link preference is Self-domain Sync (SS) known; no inter-domain sync ( τ =1) only domain reachability and intra-domain Minimum Sync (MS) topology without link Basic Sync preference are known 9
Path construction mechanism - RCPC ü a new path construction mechanism a basic and representative mechanism RCPC (Routing Cluster based Path Construction) • Select the shortest domain-wise path (e.g., BGP-like protocols) • According to the given synchronization level (synchronization radius) , partition domains on this domain-wise path into routing clusters (RCs) – e.g., sync radius=2 • Construct the shortest path segment in each RC • Concatenate all path segments into a path RC 1 RC 2 RC 3 10
Asymptotic Analysis Theorem 1. Given the synchronization radius τ , the asymptotic APC ( L ) in the two- layer network model is • It captures dominant parameters Network Structural Parameters: • Theorem 1 applies to any sync scenario • m/n/ 𝛿 : #domains, #nodes/#gateways in each domain • ζ i : average #vertices that are i-hop away • When τ is small à minimum sync, from a random vertex in an auxiliary graph Theorem 1 is reduced to à related to degree distributions ~ O ( m*log(n) ). • Δ : average domain-wise distance wrt two • When τ is large à complete sync, domains ~ log(m) Theorem 1 is reduced to Synchronization-related Parameters: ~ O ( log(n*log(m)) ). • τ ’ = min( τ , Δ +1) 11
Asymptotic Analysis – cont’d Theorem 1. Given the synchronization radius τ , the asymptotic APC ( L ) in the two- layer network model is Network Structural Parameters: • m/n/ 𝛿 : #domains, #nodes/#gateways in each domain • ζ i : average #vertices that are i-hop away from a random vertex in an auxiliary graph à related to degree distributions • Δ : average domain-wise distance wrt two domains ~ log(m) Synchronization-related Parameters: • APC reduction declines with the increase of τ • τ ’ = min( τ , Δ +1) (sync level) & the increase of 𝛿 (#gateways) • Performance and cost trade-off in distributed SDC 12
Fine-grained APC Expressions • Fine-grained accurate APCs à for link preference levels that are dynamically adjusted by the controllers based on up-to-date network status information • Methodology Sketch: Ø Given the distribution of the link preference levels, compute the intra-domain path cost distribution using mixture distribution Ø Compute the minimum path cost between an arbitrary node and the closest gateway within each routing cluster Ø Add the costs of all path segments in all traversed routing clusters Results are widely applicable and accurate • input: #domains, #nodes/#gateways in each domain, top-layer vertex degree distribution, and intra-domain node degree distribution • no assumptions on specific random graph models • no assumptions on the distribution of link preference levels 13
Evaluations • Data sources: Ø Real network traces: CAIDA, Routeview, and Rocketfuel data Ø Synthetic networks: Erdos-Renyi and Barabasi-Albert network models • Methodology: Ø Use the network parameters extracted from the above real and synthetic data sources Ø Randomly select src/dst pairs; compare the real against the analytical APCs #gateways sync radius #nodes in each domain • APC changes with varying parameters are closely captured by the asymptotic analysis • APC is a decreasing convex function of the number of gateways à diminishing benefits when the inter-domain connection is dense • Increasing #gateways is more effective in reducing APC than increasing the synchronization radius 14 • The network size n does not have a significant impact on APC
Evaluations – Cont’d • when link preference levels are random variables • the simulation curves are closely approximated by the theoretical results for all synchronization scenarios • higher synchronization level is beneficial in reducing APCs Ø SS (self-domain sync) outperforms MS (minimum sync) by ~30%; CS (complete sync) outperforms MS by ~70% 15
Relation to Other Projects P3 on P2 on policy functional design entity placement Design Inspiration P1T2 on P3/P4 on SDC resource systems management P1T1 distributed SDC foundations 16
Recommend
More recommend
