1Vector Packet Processing
6The VPP platform is an extensible framework that provides out-of-the-box
7production quality switch/router functionality. It is the open source version
8of Cisco's Vector Packet Processing (VPP) technology: a high performance,
9packet-processing stack that can run on commodity CPUs.
11The benefits of this implementation of VPP are its high performance, proven
12technology, its modularity and flexibility, and rich feature set.
14For more information on VPP and its features please visit the
15[FD.io website](http://fd.io/) and
16[What is VPP?](https://wiki.fd.io/view/VPP/What_is_VPP%3F) pages.
21Details of the changes leading up to this version of VPP can be found under
25## Directory layout
27| Directory name | Description |
28| ---------------------- | ------------------------------------------- |
29| build-data | Build metadata |
30| build-root | Build output directory |
31| doxygen | Documentation generator configuration |
32| dpdk | DPDK patches and build infrastructure |
33| @ref extras/libmemif | Client library for memif |
34| @ref src/examples | VPP example code |
35| @ref src/plugins | VPP bundled plugins directory |
36| @ref src/svm | Shared virtual memory allocation library |
37| src/tests | Standalone tests (not part of test harness) |
38| src/vat | VPP API test program |
39| @ref src/vlib | VPP application library |
40| @ref src/vlibapi | VPP API library |
41| @ref src/vlibmemory | VPP Memory management |
42| @ref src/vnet | VPP networking |
43| @ref src/vpp | VPP application |
44| @ref src/vpp-api | VPP application API bindings |
45| @ref src/vppinfra | VPP core library |
46| @ref src/vpp/api | Not-yet-relocated API bindings |
47| test | Unit tests and Python test harness |
49## Getting started
51In general anyone interested in building, developing or running VPP should
52consult the [VPP wiki](https://wiki.fd.io/view/VPP) for more complete
55In particular, readers are recommended to take a look at [Pulling, Building,
56Running, Hacking, Pushing](https://wiki.fd.io/view/VPP/Pulling,_Building,_Run
57ning,_Hacking_and_Pushing_VPP_Code) which provides extensive step-by-step
58coverage of the topic.
60For the impatient, some salient information is distilled below.
63### Quick-start: On an existing Linux host
65To install system dependencies, build VPP and then install it, simply run the
66build script. This should be performed a non-privileged user with `sudo`
67access from the project base directory:
71If you want a more fine-grained approach because you intend to do some
72development work, the `Makefile` in the root directory of the source tree
73provides several convenience shortcuts as `make` targets that may be of
74interest. To see the available targets run:
79### Quick-start: Vagrant
81The directory `extras/vagrant` contains a `VagrantFile` and supporting
82scripts to bootstrap a working VPP inside a Vagrant-managed Virtual Machine.
83This VM can then be used to test concepts with VPP or as a development
84platform to extend VPP. Some obvious caveats apply when using a VM for VPP
85since its performance will never match that of bare metal; if your work is
86timing or performance sensitive, consider using bare metal in addition or
87instead of the VM.
89For this to work you will need a working installation of Vagrant. Instructions
90for this can be found [on the Setting up Vagrant wiki page]
94## More information
96Several modules provide documentation, see @subpage user_doc for more
97end-user-oriented information. Also see @subpage dev_doc for developer notes.
99Visit the [VPP wiki](https://wiki.fd.io/view/VPP) for details on more
100advanced building strategies and other development notes.
103## Test Framework
105There is PyDoc generated documentation available for the VPP test framework.
106See @ref test_framework_doc for details.