Top Related Projects
Quick Overview
VPP (Vector Packet Processing) is an open-source, high-performance packet processing framework developed by FD.io (Fast Data - Input/Output). It provides a flexible and extensible platform for building network functions, including routers, switches, and network appliances, with a focus on performance and scalability.
Pros
- High performance: VPP utilizes vector processing techniques to achieve exceptional packet processing speeds
- Extensibility: Supports plugins and custom extensions for adding new features and protocols
- Hardware acceleration: Can leverage hardware offloading capabilities for improved performance
- Multi-platform support: Runs on various architectures, including x86, ARM, and PowerPC
Cons
- Steep learning curve: Requires in-depth knowledge of networking concepts and C programming
- Limited documentation: Some areas of the project may lack comprehensive documentation
- Complex configuration: Setting up and configuring VPP can be challenging for beginners
- Resource-intensive: May require significant system resources for optimal performance
Code Examples
- Creating a simple VPP plugin:
#include <vnet/vnet.h>
#include <vnet/plugin/plugin.h>
static clib_error_t *
my_init (vlib_main_t * vm)
{
return 0;
}
VLIB_INIT_FUNCTION (my_init);
VNET_PLUGIN_REGISTER () = {
.version = VPP_BUILD_VER,
.description = "My Custom Plugin",
};
- Registering a new CLI command:
static clib_error_t *
my_command_fn (vlib_main_t * vm,
unformat_input_t * input,
vlib_cli_command_t * cmd)
{
vlib_cli_output (vm, "Hello from my custom command!");
return 0;
}
VLIB_CLI_COMMAND (my_command, static) = {
.path = "my custom command",
.short_help = "Executes my custom command",
.function = my_command_fn,
};
- Adding a new graph node:
VLIB_REGISTER_NODE (my_node) = {
.name = "my-node",
.vector_size = sizeof (u32),
.format_trace = format_my_trace,
.type = VLIB_NODE_TYPE_INTERNAL,
.n_errors = ARRAY_LEN(my_error_strings),
.error_strings = my_error_strings,
.n_next_nodes = MY_N_NEXT,
.next_nodes = {
[MY_NEXT_DROP] = "error-drop",
},
};
Getting Started
To get started with VPP:
-
Clone the repository:
git clone https://github.com/FDio/vpp.git
-
Install dependencies:
cd vpp make install-dep
-
Build VPP:
make build
-
Install VPP:
make install
-
Start VPP:
sudo vpp
For more detailed instructions and configuration options, refer to the official VPP documentation.
Competitor Comparisons
Open vSwitch
Pros of OVS
- Mature and widely adopted in cloud environments
- Extensive feature set for network virtualization
- Strong integration with OpenStack and other cloud platforms
Cons of OVS
- Lower performance compared to VPP, especially for high-speed networking
- More complex configuration and management
- Less suitable for edge and telco use cases
Code Comparison
VPP (DPDK-based fast-path processing):
VLIB_NODE_FN (dpdk_input_node) (vlib_main_t * vm,
vlib_node_runtime_t * node,
vlib_frame_t * frame)
{
dpdk_main_t *dm = &dpdk_main;
uword n_rx_packets = 0;
// ... (packet processing logic)
}
OVS (Datapath implementation):
static int
ovs_vport_cmd_new(struct sk_buff *skb, struct genl_info *info)
{
struct nlattr **a = info->attrs;
struct ovs_vport_cmd_info cmd_info;
struct vport *vport;
// ... (vport creation logic)
}
The code snippets showcase different approaches to packet processing and virtual port management in VPP and OVS, respectively. VPP focuses on high-performance packet processing using DPDK, while OVS implements a more flexible datapath for various networking scenarios.
Data Plane Development Kit
Pros of DPDK
- Lower-level library offering more fine-grained control over packet processing
- Wider hardware support and compatibility
- More mature project with extensive documentation and community support
Cons of DPDK
- Requires more manual configuration and setup
- Steeper learning curve for developers
- Less out-of-the-box functionality compared to VPP
Code Comparison
DPDK example (packet reception):
struct rte_mbuf *pkts_burst[MAX_PKT_BURST];
unsigned int nb_rx = rte_eth_rx_burst(port_id, 0, pkts_burst, MAX_PKT_BURST);
VPP example (packet reception):
vlib_frame_t *frame;
u32 n_left_from, *from;
vlib_get_next_frame(vm, node, next_index, to_next, n_left_to_next);
Both DPDK and VPP are powerful networking frameworks, but they serve different purposes. DPDK is a lower-level library focused on efficient packet processing, while VPP provides a more comprehensive networking stack with additional features. DPDK offers more flexibility and hardware support, making it suitable for a wider range of applications. However, VPP provides a higher-level abstraction and more built-in functionality, which can lead to faster development for certain use cases.
The FRRouting Protocol Suite
Pros of FRRouting
- More comprehensive routing protocol support, including BGP, OSPF, IS-IS, and RIP
- Easier integration with existing network infrastructure
- Better suited for traditional network environments and legacy systems
Cons of FRRouting
- Lower performance compared to VPP's vector packet processing
- Less optimized for modern, high-speed networking hardware
- Limited support for advanced packet processing features
Code Comparison
FRRouting (BGP configuration example):
router bgp 65000
neighbor 192.168.1.1 remote-as 65001
network 10.0.0.0/8
VPP (Interface configuration example):
set interface ip address GigabitEthernet0/8/0 192.168.1.1/24
set interface state GigabitEthernet0/8/0 up
FRRouting focuses on routing protocols and network configuration, while VPP emphasizes high-performance packet processing and forwarding. FRRouting is more suitable for traditional networking scenarios, whereas VPP excels in modern, high-speed environments requiring advanced packet manipulation.
FRRouting offers a wider range of routing protocols and easier integration with existing networks. However, VPP provides superior performance and is better optimized for modern hardware. The choice between the two depends on specific use cases and network requirements.
Convert designs to code with AI
Introducing Visual Copilot: A new AI model to turn Figma designs to high quality code using your components.
Try Visual CopilotREADME
Vector Packet Processing
Introduction
The VPP platform is an extensible framework that provides out-of-the-box production quality switch/router functionality. It is the open source version of Cisco's Vector Packet Processing (VPP) technology: a high performance, packet-processing stack that can run on commodity CPUs.
The benefits of this implementation of VPP are its high performance, proven technology, its modularity and flexibility, and rich feature set.
For more information on VPP and its features please visit the FD.io website and What is VPP? pages.
Changes
Details of the changes leading up to this version of VPP can be found under doc/releasenotes.
Directory layout
Directory name | Description |
---|---|
build-data | Build metadata |
build-root | Build output directory |
docs | Sphinx Documentation |
dpdk | DPDK patches and build infrastructure |
extras/libmemif | Client library for memif |
src/examples | VPP example code |
src/plugins | VPP bundled plugins directory |
src/svm | Shared virtual memory allocation library |
src/tests | Standalone tests (not part of test harness) |
src/vat | VPP API test program |
src/vlib | VPP application library |
src/vlibapi | VPP API library |
src/vlibmemory | VPP Memory management |
src/vnet | VPP networking |
src/vpp | VPP application |
src/vpp-api | VPP application API bindings |
src/vppinfra | VPP core library |
src/vpp/api | Not-yet-relocated API bindings |
test | Unit tests and Python test harness |
Getting started
In general anyone interested in building, developing or running VPP should consult the VPP wiki for more complete documentation.
In particular, readers are recommended to take a look at [Pulling, Building, Running, Hacking, Pushing](https://wiki.fd.io/view/VPP/Pulling,_Building,_Run ning,_Hacking_and_Pushing_VPP_Code) which provides extensive step-by-step coverage of the topic.
For the impatient, some salient information is distilled below.
Quick-start: On an existing Linux host
To install system dependencies, build VPP and then install it, simply run the
build script. This should be performed a non-privileged user with sudo
access from the project base directory:
./extras/vagrant/build.sh
If you want a more fine-grained approach because you intend to do some
development work, the Makefile
in the root directory of the source tree
provides several convenience shortcuts as make
targets that may be of
interest. To see the available targets run:
make
Quick-start: Vagrant
The directory extras/vagrant
contains a VagrantFile
and supporting
scripts to bootstrap a working VPP inside a Vagrant-managed Virtual Machine.
This VM can then be used to test concepts with VPP or as a development
platform to extend VPP. Some obvious caveats apply when using a VM for VPP
since its performance will never match that of bare metal; if your work is
timing or performance sensitive, consider using bare metal in addition or
instead of the VM.
For this to work you will need a working installation of Vagrant. Instructions for this can be found [on the Setting up Vagrant wiki page] (https://wiki.fd.io/view/DEV/Setting_Up_Vagrant).
More information
Several modules provide documentation, see @subpage user_doc for more end-user-oriented information. Also see @subpage dev_doc for developer notes.
Visit the VPP wiki for details on more advanced building strategies and other development notes.
Top Related Projects
Convert designs to code with AI
Introducing Visual Copilot: A new AI model to turn Figma designs to high quality code using your components.
Try Visual Copilot