Enabling Innovation Inside the Network CHANGE

Enabling Innovation Inside the Network CHANGE www.phwiki.com

Enabling Innovation Inside the Network CHANGE

Kay, Abby, On-Air Personality has reference to this Academic Journal, PHwiki organized this Journal Enabling Innovation Inside the Network Jennifer Rex as long as d Princeton University http://www.cs.princeton.edu/~jrex http://www.frenetic-lang.org/ The Internet: A Remarkable Story Tremendous success From research experiment to global infrastructure Brilliance of under-specifying Network: best-ef as long as t packet delivery Hosts: arbitrary applications Enables innovation in applications Web, P2P, VoIP, social networks, virtual worlds But, change is easy only at the edge Inside the ‘Net: A Different Story Closed equipment Software bundled with hardware Vendor-specific interfaces Over specified Slow protocol st in addition to ardization Few people can innovate Equipment vendors write the code Long delays to introduce new features Impacts per as long as mance, security, reliability, cost

University of Sopron HU www.phwiki.com

This Particular University is Related to this Particular Journal

Do We Need Innovation Inside Many boxes (routers, switches, firewalls, ), with different interfaces. How Hard are Networks to Manage Operating a network is expensive More than half the cost of a network Yet, operator error causes most outages Buggy software in the equipment Routers with 20+ million lines of code Cascading failures, vulnerabilities, etc. The network is “in the way” Especially a problem in data centers in addition to home networks Creating Foundation as long as Networking A domain, not a discipline Alphabet soup of protocols Header as long as mats, bit twiddling Preoccupation with artifacts From practice, to principles Intellectual foundation as long as networking Identify the key abstractions in addition to support them efficiently To build networks worthy of society’s trust

Rethinking the “Division of Labor” Traditional Computer Networks Data plane: Packet streaming Forward, filter, buffer, mark, rate-limit, in addition to measure packets Traditional Computer Networks Track topology changes, compute routes, install as long as warding rules Control plane: Distributed algorithms

Traditional Computer Networks Collect measurements in addition to configure the equipment Management plane: Human time scale Shortest-Path Routing Management: set the link weights Control: compute shortest paths Data: as long as ward packets to next hop 1 1 3 1 1 Shortest-Path Routing Management: set the link weights Control: compute shortest paths Data: as long as ward packets to next hop 1 1 3 1 1

Inverting the Control Plane Traffic engineering Change link weights to induce the paths that alleviate congestion 5 1 3 1 1 Avoiding Transient Anomalies Distributed protocol Temporary disagreement among the nodes leaves packets stuck in loops Even though the change was planned! 1 5 1 3 1 1 Death to the Control Plane! Simpler management No need to “invert” control-plane operations Faster pace of innovation Less dependence on vendors in addition to st in addition to ards Easier interoperability Compatibility only in “wire” protocols Simpler, cheaper equipment Minimal software

Software Defined Networking (SDN) API to the data plane (e.g., OpenFlow) Logically-centralized control Switches Smart, slow Dumb, fast OpenFlow Networks Data-Plane: Simple Packet H in addition to ling Simple packet-h in addition to ling rules Pattern: match packet header bits Actions: drop, as long as ward, modify, send to controller Priority: disambiguate overlapping patterns Counters: bytes in addition to packets src=1.2.., dest=3.4.5. drop src = …, dest=3.4. as long as ward(2) 3. src=, dest= send to controller

Controller: Programmability App 1 App 2 App 3 Events from switches Topology changes, Traffic statistics, Arriving packets Comm in addition to s to switches (Un)install rules, Query statistics, Send packets OpenFlow in the Wild Open Networking Foundation Creating Software Defined Networking st in addition to ards Google, Facebook, Microsoft, Yahoo, Verizon, Deutsche Telekom, in addition to many other companies Commercial OpenFlow switches HP, NEC, Quanta, Dell, IBM, Juniper, Network operating systems NOX, Beacon, Floodlight, Nettle, ONIX, POX, Frenetic Network deployments Eight campuses, in addition to two research backbone networks Commercial deployments Dynamic Access Control Inspect first packet of each connection Consult the access control policy Install rules to block or route traffic

Seamless Mobility/Migration See host sending traffic at new location Modify rules to reroute the traffic Example Applications Dynamic access control Seamless mobility/migration Server load balancing Using multiple wireless access points Energy-efficient networking Adaptive traffic monitoring Denial-of-Service attack detection Network virtualization See http://www.openflow.org/videos/ Challenges of Programming Software Defined Networks

Kay, Abby WRSA-FM On-Air Personality www.phwiki.com

Programming OpenFlow Networks OpenFlow makes programming possible Network-wide view at controller Direct control over data plane The APIs do not make it easy Low level of abstraction Challenges Composition Concurrency Controller Switches Modularity: Simple Repeater def repeater(switch): Repeat Port 1 to Port 2 pat1 = {in-port:1} act1 = [ as long as ward(2)] install(switch, pat1, DEFAULT, act1) Repeat Port 2 to Port 1 pat2 = {in-port:2} act2 = [ as long as ward(1)] install(switch, pat2, DEFAULT, act2) Simple Repeater 1 2 Controller When a switch joins the network, install two as long as warding rules. Composition: Web Traffic Monitor def web-monitor(switch): Web traffic from Internet pat = {inport:2,tp-src:80} install(switch, pat, DEFAULT, []) query-stats(switch, pat) def stats-in(switch, pat, bytes, ) print bytes sleep(30) query-stats(switch, pat) Monitor Web (“port 80”) traffic 1 2 Web traffic When a switch joins the network, install one monitoring rule.

Composition: Repeater + Monitor def switch-join(switch): pat1 = {inport:1} pat2 = {inport:2} pat2web = {in-port:2, tp-src:80} install(switch, pat1, DEFAULT, None, [ as long as ward(2)]) install(switch, pat2web, HIGH, None, [ as long as ward(1)]) install(switch, pat2, DEFAULT, None, [ as long as ward(1)]) query-stats(switch, pat2web) def stats-in(switch, xid, pattern, packets, bytes): print bytes sleep(30) query-stats(switch, pattern) Repeater + Monitor Must think about both tasks at the same time. Concurrency: Switch-Controller Delays Common programming idiom First packet goes to the controller Controller installs rules packets Concurrency: Switch-Controller Delays More packets arrive be as long as e rules installed Multiple packets reach the controller packets

Consistent Writes [HotNets’11] Transition from policy P1 to P2 Security: new access control lists Routing: new shortest paths without a link Load balancer: new split over server replicas Transient policy violations Packets in flight experience a mix of policies Modifying switch rules is not instantaneous Consistent update semantics Packets experience either P1 or P2 but never a mixture of the two Enables verification of just P1 in addition to P2 CHANGE We Can Believe In Many Hard Questions Remain Higher-level abstractions Network-wide policy Domain-specific languages Heterogeneous components Mix of end hosts in addition to switches FPGAs in addition to network processors Distributed controllers Replication, distribution, in addition to aggregation Consistency in addition to durability of state Multiple administrative domains Trust, scalability Conclusion SDN is exciting Enables innovation Simplifies management Rethinks networking SDN is happening Practice: useful APIs in addition to good industry traction Principles: start of higher-level abstractions Great opportunities Practical impact on future networks Placing networking on a strong foundation

Kay, Abby On-Air Personality

Kay, Abby is from United States and they belong to WRSA-FM and they are from  Huntsville, United States got related to this Particular Journal. and Kay, Abby deal with the subjects like Music

Journal Ratings by University of Sopron

This Particular Journal got reviewed and rated by University of Sopron and short form of this particular Institution is HU and gave this Journal an Excellent Rating.