41. Distributor Sample Application
The distributor sample application is a simple example of packet distribution to cores using the Data Plane Development Kit (DPDK). It also makes use of Intel Speed Select Technology - Base Frequency (Intel SST-BF) to pin the distributor to the higher frequency core if available.
The distributor application performs the distribution of packets that are received on an RX_PORT to different cores. When processed by the cores, the destination port of a packet is the port from the enabled port mask adjacent to the one on which the packet was received, that is, if the first four ports are enabled (port mask 0xf), ports 0 and 1 RX/TX into each other, and ports 2 and 3 RX/TX into each other.
This application can be used to benchmark performance using the traffic generator as shown in the figure below.
41.2. Compiling the Application
To compile the sample application see Compiling the Sample Applications.
The application is located in the
41.3. Running the Application
The application has a number of command line options:
./<build-dir>/examples/dpdk-distributor [EAL options] -- -p PORTMASK [-c]
- -p PORTMASK: Hexadecimal bitmask of ports to configure
- -c: Combines the RX core with distribution core
To run the application in linux environment with 10 lcores, 4 ports, issue the command:
$ ./<build-dir>/examples/dpdk-distributor -l 1-9,22 -n 4 -- -p f
Refer to the DPDK Getting Started Guide for general information on running applications and the Environment Abstraction Layer (EAL) options.
The distributor application consists of four types of threads: a receive
lcore_rx()), a distributor thread (
lcore_dist()), a set of
worker threads (
lcore_worker()), and a transmit thread(
How these threads work together is shown in Fig. 41.2 below.
main() function launches threads of these four types. Each thread
has a while loop which will be doing processing and which is terminated
only upon SIGINT or ctrl+C.
The receive thread receives the packets using
rte_eth_rx_burst() and will
enqueue them to an rte_ring. The distributor thread will dequeue the packets
from the ring and assign them to workers (using
This assignment is based on the tag (or flow ID) of the packet - indicated by
the hash field in the mbuf. For IP traffic, this field is automatically filled
by the NIC with the “usr” hash value for the packet, which works as a per-flow
tag. The distributor thread communicates with the worker threads using a
cache-line swapping mechanism, passing up to 8 mbuf pointers at a time
(one cache line) to each worker.
More than one worker thread can exist as part of the application, and these worker threads do simple packet processing by requesting packets from the distributor, doing a simple XOR operation on the input port mbuf field (to indicate the output port which will be used later for packet transmission) and then finally returning the packets back to the distributor thread.
The distributor thread will then call the distributor api
rte_distributor_returned_pkts() to get the processed packets, and will enqueue
them to another rte_ring for transfer to the TX thread for transmission on the
output port. The transmit thread will dequeue the packets from the ring and
transmit them on the output port specified in packet mbuf.
Users who wish to terminate the running of the application have to press ctrl+C (or send SIGINT to the app). Upon this signal, a signal handler provided in the application will terminate all running threads gracefully and print final statistics to the user.
41.5. Intel SST-BF Support
In DPDK 19.05, support was added to the power management library for Intel-SST-BF, a technology that allows some cores to run at a higher frequency than others. An application note for Intel SST-BF is available, and is entitled Intel Speed Select Technology – Base Frequency - Enhancing Performance
The distributor application was also enhanced to be aware of these higher frequency SST-BF cores, and when starting the application, if high frequency SST-BF cores are present in the core mask, the application will identify these cores and pin the workloads appropriately. The distributor core is usually the bottleneck, so this is given first choice of the high frequency SST-BF cores, followed by the rx core and the tx core.
41.6. Debug Logging Support
Debug logging is provided as part of the application; the user needs to uncomment the line “#define DEBUG” defined in start of the application in main.c to enable debug logs.
The main function will print statistics on the console every second. These statistics include the number of packets enqueued and dequeued at each stage in the application, and also key statistics per worker, including how many packets of each burst size (1-8) were sent to each worker thread.
41.8. Application Initialization
Command line parsing is done in the same way as it is done in the L2 Forwarding Sample Application. See Command Line Arguments.
Mbuf pool initialization is done in the same way as it is done in the L2 Forwarding Sample Application. See Mbuf Pool Initialization.
Driver Initialization is done in same way as it is done in the L2 Forwarding Sample Application. See Driver Initialization.
RX queue initialization is done in the same way as it is done in the L2 Forwarding Sample Application. See RX Queue Initialization.
TX queue initialization is done in the same way as it is done in the L2 Forwarding Sample Application. See TX Queue Initialization.