Planck

By Jeff Rasley, Brent E. Stephens, Colin Dixon, Eric Rozner, Wes Felter, Kanak B. Agarwal, John B. Carter, Rodrigo Fonseca. Conference on Applications, Technologies, Architectures, and Protocols for Computer Communication, 2014

2,118 citations recorded by the source corpus.

Software-defined networking introduces the possibility of building self-tuning networks that constantly monitor network conditions and react rapidly to important events such as congestion. Unfortunately, state-of-the-art monitoring mechanisms for conventional networks require hundreds of milliseconds to seconds to extract global network state, like link utilization or the identity of "elephant" flows. Such latencies are adequate for responding to persistent issues, e.g., link failures or long-lasting congestion, but are inadequate for responding to transient problems, e.g., congestion induced by bursty workloads sharing a link. In this paper, we present Planck, a novel network measurement architecture that employs oversubscribed port mirroring to extract network information at 280 µs--7 ms timescales on a 1 Gbps commodity switch and 275 µs--4 ms timescales on a 10 Gbps commodity switch,over 11x and 18x faster than recent approaches, respectively (and up to 291x if switch firmware allowed buffering to be disabled on some ports). To demonstrate the value of Planck's speed and accuracy, we use it to drive a traffic engineering application that can reroute congested flows in milliseconds. On a 10 Gbps commodity switch, Planck-driven traffic engineering achieves aggregate throughput within 1--4% of optimal for most workloads we evaluated, even with flows as small as 50 MiB, an improvement of up to 53% over previous schemes.

Subfields: Computer Networks and Communications, Electrical and Electronic Engineering

View Paper: https://www.semanticscholar.org/paper/83caf2c83bb08679fbe3ff3ab039d11657fba3b5

How researchers see this paper

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

In Computer Networks and Communications

In Electrical and Electronic Engineering

Citations in the corpus

DRILL: Micro Load Balancing for Low-latency Data Center Networks (2017, methodology): “[3, 13, 14, 23], as even the fastest ones have control loops with 10s of millisecond to a few second delays [19, 25, 61].”
FlowRadar: A Better NetFlow for Data Centers (2016, methodology): “With FlowRadar, operators can get better views into their networks as demonstrated by two new monitoring applications we build on top of FlowRadar.”
α-attractors: Planck, LHC and dark energy (2015, methodology): “In this sense, the method used for deriving the model described in section 5, as well as of some other similar models found earlier in [24], preserves the attractor features of the theory by construction, for all values of the SUSY breaking parameters and arbitrary cosmological constant.”
Does Hubble tension signal a breakdown in FLRW cosmology? (2021, neutral): “It is intriguingto compare the orientations of these few quasars with the CMB dipole [2], α = 168 ◦ , δ = − 7 ◦ , approximately along which most of the superclusters in the local Universe are lined up.”
Joint Analysis of BICEP2/Keck Array and Planck Data (2015, neutral): “Copyright a n d m o r al right s for p u blications m a d e available in ORCA a r e r e t ain e d by t h e copyrig ht hold e rs.”
DESI 2024: reconstructing dark energy using crossing statistics with DESI DR1 BAO data (2024, methodology): “The spacing between these peaks is exquisitely measured by Planck [84], providing constraints on the late-time expansion history through the acoustic scale θ s ( z rec ) ∝ 1 /D A ( z rec ), assuming standard pre-recombination physics.”
SPHINX: Detecting Security Attacks in Software-Defined Networks (2015, methodology): “Alternatively, SPHINX can also be augmented by making use of network monitoring frameworks such as Planck [39] and PayLess [23] for greater accuracy in link utilization measurements.”
Packet-Level Telemetry in Large Datacenter Networks (2015, methodology): “isting systems that rely on packet-level analysis [14, 31] indiscriminately trace packets; they cannot scale to the size of large DCNs or search for packets based on complex patterns.”
Robust preference for Dynamical Dark Energy in DESI BAO and SN measurements (2024, background): “We make no secret that due to the large number of analyzed models and the similarity of the results obtained, the following discussion may appear somewhat repetitive (though necessary).”
SketchVisor: Robust Network Measurement for Software Packet Processing (2017, background): “Planck [43] mirrors traffic to remote sites in a best-effort manner.”
Presto: Edge-based Load Balancing for Fast Datacenter Networks (2015, methodology): “These approaches are fundamentally reactive to congestion and are very coarse-grained due to the large time constraints of their control loops [3] or require extra network infrastructure [54].”
Hybrid SDN Networks: A Survey of Existing Approaches (2018, methodology): “Different types of network measurement and monitoring tools, such as OpenSketch [378], Payless [379], planck [380], and Opennetmon [381], are available for pure SDN networks.”
Assessing observational constraints on dark energy (2024, positive): “Models of time-varying dark energy ( e.g. , quintessence) [1–6] can be constrained by combining observations at different redshifts, such as the cosmic microwave background (CMB), baryon acoustic oscillations (BAO), and Type IA supernovae (SNe Ia) [7–11].”