Abstract : We propose a new high resolution – temporal and spatial – 10 Gbps Ethernet monitoring technique based on time-coherent congestion ‘heatmaps’, revealing (all) the queue occupancies at μs granularity. Notably, queues are sampled with a slightly modified version of the new commodity Ethernet hardware congestion management protocol, i.e., IEEE 802 Quantized Congestion Notification. Our technique is evaluated through high-accuracy Layer-2 simulations of a 10 Gbps datacenter Ethernet fabric. Early results reveal that our proposal enables the detection of ephemeral – yet consequential – events and transients essential for datacenter workload characterization: e.g., TCP Incast, Head-of-Line blocking and congestion trees, which may trigger within 10s of μs and were not directly detectable until now.
https://hal.archives-ouvertes.fr/hal-01396469 Contributor : Hal IfipConnect in order to contact the contributor Submitted on : Monday, November 14, 2016 - 2:52:07 PM Last modification on : Tuesday, November 15, 2016 - 12:58:16 PM Long-term archiving on: : Tuesday, March 21, 2017 - 3:29:02 AM
Andreea Anghel, Robert Birke, Mitch Gusat. Scalable High Resolution Traffic Heatmaps: Coherent Queue Visualization for Datacenters. 6th International Workshop on Traffic Monitoring and Analysis (TMA), Apr 2014, London, United Kingdom. pp.26-37, ⟨10.1007/978-3-642-54999-1_3⟩. ⟨hal-01396469⟩