Microbursts are traffic events that can cause severe performance degradation in a network. With the advent of modern big data applications, microburst events are not uncommon in a data center. Rather than attempting superficial ad-hoc solutions, such as providing large buffer switches/routers, under provisioning bandwidth, etc., this proposal provides a technique to identify an offending application causing a microburst based on queue-level thresholds. Once identified, appropriate remedial action(s) (e.g., Quality of Service (QoS) actions, security actions, etc.) can be performed by a network administrator.

Creative Commons License

Creative Commons License
This work is licensed under a Creative Commons Attribution 4.0 License.