Click here to flash read.
Switching, routing, and security functions are the backbone of packet
processing networks. Fast and efficient processing of packets requires
maintaining the state of a large number of transient network connections. In
particular, modern stateful firewalls, security monitoring devices, and
software-defined networking (SDN) programmable dataplanes require maintaining
stateful flow tables. These flow tables often grow much larger than can be
expected to fit within on-chip memory, requiring a managed caching layer to
maintain performance. This paper focuses on improving the efficiency of
caching, an important architectural component of the packet processing data
planes. We present a novel predictive approach to network flow table cache
management. Our approach leverages a Hashed Perceptron binary classifier as
well as an iterative approach to feature selection and ranking to improve the
reliability and performance of the data plane caches. We validate the
efficiency of the proposed techniques through extensive experimentation using
real-world data sets. Our numerical results demonstrate that our techniques
improve the reliability and performance of flow-centric packet processing
architectures.
No creative common's license