Software Defined Traffic Measurement with OpenSketch

By Minlan Yu, Lavanya Jose, Rui Miao. Symposium on Networked Systems Design and Implementation, 2013

689 citations recorded by the source corpus.

View Paper: https://www.semanticscholar.org/paper/f1ad95a898ba4d8a96557178d731760e083cafdb

How researchers see this paper

The researchers whose trusted networks rank it highest, strongest advocate first. Every researcher gets a different order.

Citations in the corpus

Planck (2014, methodology): “OpenSketch [44] proposes adding reconfigurable measurement logic to switches and exposing an in0 0.”
Packet-Level Telemetry in Large Datacenter Networks (2015, background): “…multiple hops or switches, and effective diagnosis requires intelligently tracing small subsets of packets over the network, as well as the ability to search the packet traces based on sophisticated query patterns, e.g., protocol headers, sources and destinations, or even devices along the path.”
SketchVisor: Robust Network Measurement for Software Packet Processing (2017, methodology): “SketchVisor’s design follows the line of software-defined measurement [23, 30, 36, 37, 56].”
A roadmap for traffic engineering in SDN-OpenFlow networks (2014, background): “OpenSketch [96] is a software defined traffic measurement architecture, which separates the measurement data plane from the control plane.”
Elastic sketch: adaptive and fast network-wide measurements (2018, methodology): “Recently, well-known systems for measurements include UnivMon [2], Trumpet [40], OpenSketch [11], FlowRadar [18], SketchVisor [12], Marple[41], Pingmesh[42], and DREAM[43].”
A Survey of Software-Defined Networking: Past, Present, and Future of Programmable Networks (2014, unknown): “The work presented in [111] proposes a software-defined traffic measurement architecture, which separates the measurement data plane from the control”
One Sketch to Rule Them All: Rethinking Network Flow Monitoring with UnivMon (2016, methodology): “While recent tools like OpenSketch [47] and SCREAM [41] provide libraries to reduce the implementation effort and offer efﬁcient resource allocation, they do not address the fundamental need to de-sign and operate new custom sketches for each task.”
Software Defined Networking Architecture, Security and Energy Efficiency: A Survey (2017, methodology): “OpenSketch has been proposed in [155] as a push based traffic flow monitoring scheme which follows the similar concept of decoupling the planes as SDN and uses three major stages namely hashing, filtering and counting.”
Hybrid SDN Networks: A Survey of Existing Approaches (2018, methodology): “For instance, OpenSketch [378] performs network measurement by using sketch based streaming algorithms.”
Sonata: query-driven streaming network telemetry (2018, methodology): “…NetQRE[58] Filter-DP Apply only filter operations on the switch EverFlow[60] Max-DP Execute asmanydataflowoperationsas possible on the switch Univmon[26],OpenSketch[56] Fix-REF Iteratively zoom-in one refinenement level at a time DREAM[29] Table 4: Telemetry systems emulated for evaluation.”
PINT: Probabilistic In-band Network Telemetry (2020, methodology): “, queues status switchID, queue occupancy Power Management [31] Determine under-utilized network elements switchID, port utilization Real-Time Anomaly Detection [66, 86] Detect sudden changes in network status timestamp, port utilization, queue occupancy Static per-flow aggregation Path Tracing [36,”
Packet Transactions: High-Level Programming for Line-Rate Switches (2015, background): “Examples include active queue management [53, 52, 67, 74, 76], scheduling [88], congestion control with switch feedback [64, 93, 60, 28], network measurement [98, 51, 50], security [34], and traffic load balancing [27].”
Heavy-Hitter Detection Entirely in the Data Plane (2016, background): “of processing sampled packets in software make it infeasible to sample at sufﬁciently high rates (sampling just 1 in 1000 packets is common in practice [40]). An alternative is to use sketches, e.g., [16,30,31,50] that hash and count all packets in switch hardware. However, these systems incur a lar”
A Survey of Security in Software Defined Networks (2016, unknown): “OpenSketch [126] is a software-defined traffic measurement architecture using sketches (compact data structures storing summary information about the state of packets) for customized and dynamic measurement data collection.”
Language-Directed Hardware Design for Network Performance Monitoring (2017, methodology): “Sketches [34, 48, 49, 52, 63] and programmable switch counters [38, 54] expose traffic volume statistics using summary data structures and flow counters on switches.”
PayLess: A low cost network monitoring framework for Software Defined Networks (2014, background): “proposes OpenSketch [8], a three stage packet processing pipeline design for SDN.”
FlowRadar: A Better NetFlow for Data Centers (2016, background): “There are many hash-based data structures that can keep per-flow state with small memory [15, 42, 36, 43].”
RouteNet: Leveraging Graph Neural Networks for Network Modeling and Optimization in SDN (2019, methodology): “eceives timely updates of the network state (e.g., trafﬁc matrix, delay measurements). This can be achieved by means of “conventional” SDNbased measurement techniques (e.g., OpenFlow [14], OpenSketch [15]) or more novel telemetry proposals such as INT for P4 [16] or iOAM [17]. Likewise, in the knowl”