TY - GEN
T1 - Network-wide heavy hitter detection with commodity switches
AU - Harrison, Rob
AU - Cai, Qizhe
AU - Gupta, Arpit
AU - Rexford, Jennifer L.
PY - 2018/3/28
Y1 - 2018/3/28
N2 - Many network monitoring tasks identify subsets of traffic that stand out, e.g., top-k flows for a particular statistic. A Protocol Independent Switch Architecture (PISA) switch can identify these "heavy hitter" flows directly in the data plane, by aggregating traffic statistics across packets and comparing against a threshold. However, network operators often want to identify interesting traffic on a network-wide basis. To bridge the gap between line-rate monitoring and networkwide visibility, we present a distributed heavy-hitter detection scheme for networks modeled as one-big switch.We use adaptive thresholds to perform efficient threshold monitoring directly in the data plane. We implement our system using the P4 language, and evaluate it using real-world packet traces. We demonstrate that our solution can accurately detect network-wide heavy hitters with up to 70% savings in communication overhead compared to an existing approach with a provable upper bound.
AB - Many network monitoring tasks identify subsets of traffic that stand out, e.g., top-k flows for a particular statistic. A Protocol Independent Switch Architecture (PISA) switch can identify these "heavy hitter" flows directly in the data plane, by aggregating traffic statistics across packets and comparing against a threshold. However, network operators often want to identify interesting traffic on a network-wide basis. To bridge the gap between line-rate monitoring and networkwide visibility, we present a distributed heavy-hitter detection scheme for networks modeled as one-big switch.We use adaptive thresholds to perform efficient threshold monitoring directly in the data plane. We implement our system using the P4 language, and evaluate it using real-world packet traces. We demonstrate that our solution can accurately detect network-wide heavy hitters with up to 70% savings in communication overhead compared to an existing approach with a provable upper bound.
UR - http://www.scopus.com/inward/record.url?scp=85049393374&partnerID=8YFLogxK
UR - http://www.scopus.com/inward/citedby.url?scp=85049393374&partnerID=8YFLogxK
U2 - 10.1145/3185467.3185476
DO - 10.1145/3185467.3185476
M3 - Conference contribution
AN - SCOPUS:85049393374
T3 - Proceedings of the Symposium on SDN Research, SOSR 2018
BT - Proceedings of the Symposium on SDN Research, SOSR 2018
PB - Association for Computing Machinery, Inc
T2 - 2018 Symposium on SDN Research, SOSR 2018
Y2 - 28 March 2018 through 29 March 2018
ER -