TY - GEN
T1 - A black-box method for accelerating measurement algorithms with accuracy guarantees
AU - Basat, Ran Ben
AU - Einziger, Gil
AU - Luizelli, Marcelo Caggiani
AU - Waisbard, Erez
N1 - Publisher Copyright:
© 2019 IFIP.
PY - 2019/5/1
Y1 - 2019/5/1
N2 - Network Function Virtualization (NFV) enables software implementations of middleboxes such as load balancing, traffic engineering and quality of service. These often rely on network measurement such as per-flow frequency estimation, bandwidth estimation, counting distinct elements and estimating the traffic entropy. Keeping up with the line speed is an active challenge for NFV measurement techniques, and library algorithms are simply too slow. Sampling is a natural technique to increase the measurement throughput, but it requires a certain amount of traffic before accuracy is guaranteed. In this work, we introduce a throughput acceleration method that preserves accuracy from the very first packet. This technique works with a variety of existing measurement algorithms (e.g., the ones mentioned above), and improves their throughput while guaranteeing their correctness throughout the entire measurement. Our work includes a rigors analysis, an extensive evaluation with real network traces, and a real DPDK enabled Open vSwitch implementation.
AB - Network Function Virtualization (NFV) enables software implementations of middleboxes such as load balancing, traffic engineering and quality of service. These often rely on network measurement such as per-flow frequency estimation, bandwidth estimation, counting distinct elements and estimating the traffic entropy. Keeping up with the line speed is an active challenge for NFV measurement techniques, and library algorithms are simply too slow. Sampling is a natural technique to increase the measurement throughput, but it requires a certain amount of traffic before accuracy is guaranteed. In this work, we introduce a throughput acceleration method that preserves accuracy from the very first packet. This technique works with a variety of existing measurement algorithms (e.g., the ones mentioned above), and improves their throughput while guaranteeing their correctness throughout the entire measurement. Our work includes a rigors analysis, an extensive evaluation with real network traces, and a real DPDK enabled Open vSwitch implementation.
KW - NFV
KW - OVS
KW - frequency estimation
KW - heavy hitters
KW - high-performance
KW - network measurement
UR - http://www.scopus.com/inward/record.url?scp=85072801573&partnerID=8YFLogxK
U2 - 10.23919/IFIPNetworking.2019.8816858
DO - 10.23919/IFIPNetworking.2019.8816858
M3 - Conference contribution
AN - SCOPUS:85072801573
T3 - 2019 IFIP Networking Conference, IFIP Networking 2019
BT - 2019 IFIP Networking Conference, IFIP Networking 2019
PB - Institute of Electrical and Electronics Engineers
T2 - 2019 IFIP Networking Conference, IFIP Networking 2019
Y2 - 20 May 2019 through 22 May 2019
ER -