Vector Packet Processing (VPP) platform is an extensible, open-source framework, which offers the functionality of network switches or routers. V''ector processing'' is the process of processing multiple packets at a time, with low latency. Single packet processing and high latency are present in the ''scalar processing'' approach, which VPP aims to make obsolete.
This open-source,
Linux Foundation backed framework is part of the '
Fast Data Project'' (FD.io)
VPPuses the
Data Plane Development Kit device drivers and libraries for many of its layer 1 functions - however, this functionality is separated into an optional plugin-in for VPP.
Technology
In order to push for scalability of networks, VPP reads the largest available sector of packets in the networks
I/O layer. Instead of processing each packet individually throughout an entire graph with several
nodes
In general, a node is a localized swelling (a "knot") or a point of intersection (a vertex).
Node may refer to:
In mathematics
*Vertex (graph theory), a vertex in a mathematical graph
*Vertex (geometry), a point where two or more curves, lines, ...
, VPP selects the entire vector of packets and pushes them through a graph node, before moving on to the next node. The instruction
cache
Cache, caching, or caché may refer to:
Places United States
* Cache, Idaho, an unincorporated community
* Cache, Illinois, an unincorporated community
* Cache, Oklahoma, a city in Comanche County
* Cache, Utah, Cache County, Utah
* Cache Coun ...
then adapts to the process and the remaining packets are processed even faster, due to the previously learned instructions from the first vector packet.
External links
FD.io Project PagesFD.io Wiki on VPP
References
{{Routing software
Free routing software
Networking hardware