]> git.proxmox.com Git - ceph.git/blob - ceph/src/spdk/dpdk/doc/guides/sample_app_ug/rxtx_callbacks.rst
import 15.2.0 Octopus source
[ceph.git] / ceph / src / spdk / dpdk / doc / guides / sample_app_ug / rxtx_callbacks.rst
1 .. SPDX-License-Identifier: BSD-3-Clause
2 Copyright(c) 2015 Intel Corporation.
3
4 RX/TX Callbacks Sample Application
5 ==================================
6
7 The RX/TX Callbacks sample application is a packet forwarding application that
8 demonstrates the use of user defined callbacks on received and transmitted
9 packets. The application performs a simple latency check, using callbacks, to
10 determine the time packets spend within the application.
11
12 In the sample application a user defined callback is applied to all received
13 packets to add a timestamp. A separate callback is applied to all packets
14 prior to transmission to calculate the elapsed time, in CPU cycles.
15
16
17 Compiling the Application
18 -------------------------
19
20 To compile the sample application see :doc:`compiling`.
21
22 The application is located in the ``rxtx_callbacks`` sub-directory.
23
24 The callbacks feature requires that the ``CONFIG_RTE_ETHDEV_RXTX_CALLBACKS``
25 setting is on in the ``config/common_`` config file that applies to the
26 target. This is generally on by default:
27
28 .. code-block:: console
29
30 CONFIG_RTE_ETHDEV_RXTX_CALLBACKS=y
31
32 Running the Application
33 -----------------------
34
35 To run the example in a ``linux`` environment:
36
37 .. code-block:: console
38
39 ./build/rxtx_callbacks -l 1 -n 4
40
41 Refer to *DPDK Getting Started Guide* for general information on running
42 applications and the Environment Abstraction Layer (EAL) options.
43
44
45
46 Explanation
47 -----------
48
49 The ``rxtx_callbacks`` application is mainly a simple forwarding application
50 based on the :doc:`skeleton`. See that section of the documentation for more
51 details of the forwarding part of the application.
52
53 The sections below explain the additional RX/TX callback code.
54
55
56 The Main Function
57 ~~~~~~~~~~~~~~~~~
58
59 The ``main()`` function performs the application initialization and calls the
60 execution threads for each lcore. This function is effectively identical to
61 the ``main()`` function explained in :doc:`skeleton`.
62
63 The ``lcore_main()`` function is also identical.
64
65 The main difference is in the user defined ``port_init()`` function where the
66 callbacks are added. This is explained in the next section:
67
68
69 The Port Initialization Function
70 ~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~
71
72 The main functional part of the port initialization is shown below with
73 comments:
74
75 .. code-block:: c
76
77 static inline int
78 port_init(uint16_t port, struct rte_mempool *mbuf_pool)
79 {
80 struct rte_eth_conf port_conf = port_conf_default;
81 const uint16_t rx_rings = 1, tx_rings = 1;
82 struct ether_addr addr;
83 int retval;
84 uint16_t q;
85
86 /* Configure the Ethernet device. */
87 retval = rte_eth_dev_configure(port, rx_rings, tx_rings, &port_conf);
88 if (retval != 0)
89 return retval;
90
91 /* Allocate and set up 1 RX queue per Ethernet port. */
92 for (q = 0; q < rx_rings; q++) {
93 retval = rte_eth_rx_queue_setup(port, q, RX_RING_SIZE,
94 rte_eth_dev_socket_id(port), NULL, mbuf_pool);
95 if (retval < 0)
96 return retval;
97 }
98
99 /* Allocate and set up 1 TX queue per Ethernet port. */
100 for (q = 0; q < tx_rings; q++) {
101 retval = rte_eth_tx_queue_setup(port, q, TX_RING_SIZE,
102 rte_eth_dev_socket_id(port), NULL);
103 if (retval < 0)
104 return retval;
105 }
106
107 /* Start the Ethernet port. */
108 retval = rte_eth_dev_start(port);
109 if (retval < 0)
110 return retval;
111
112 /* Enable RX in promiscuous mode for the Ethernet device. */
113 rte_eth_promiscuous_enable(port);
114
115
116 /* Add the callbacks for RX and TX.*/
117 rte_eth_add_rx_callback(port, 0, add_timestamps, NULL);
118 rte_eth_add_tx_callback(port, 0, calc_latency, NULL);
119
120 return 0;
121 }
122
123
124 The RX and TX callbacks are added to the ports/queues as function pointers:
125
126 .. code-block:: c
127
128 rte_eth_add_rx_callback(port, 0, add_timestamps, NULL);
129 rte_eth_add_tx_callback(port, 0, calc_latency, NULL);
130
131 More than one callback can be added and additional information can be passed
132 to callback function pointers as a ``void*``. In the examples above ``NULL``
133 is used.
134
135 The ``add_timestamps()`` and ``calc_latency()`` functions are explained below.
136
137
138 The add_timestamps() Callback
139 ~~~~~~~~~~~~~~~~~~~~~~~~~~~~~
140
141 The ``add_timestamps()`` callback is added to the RX port and is applied to
142 all packets received:
143
144 .. code-block:: c
145
146 static uint16_t
147 add_timestamps(uint16_t port __rte_unused, uint16_t qidx __rte_unused,
148 struct rte_mbuf **pkts, uint16_t nb_pkts, void *_ __rte_unused)
149 {
150 unsigned i;
151 uint64_t now = rte_rdtsc();
152
153 for (i = 0; i < nb_pkts; i++)
154 pkts[i]->udata64 = now;
155
156 return nb_pkts;
157 }
158
159 The DPDK function ``rte_rdtsc()`` is used to add a cycle count timestamp to
160 each packet (see the *cycles* section of the *DPDK API Documentation* for
161 details).
162
163
164 The calc_latency() Callback
165 ~~~~~~~~~~~~~~~~~~~~~~~~~~~
166
167 The ``calc_latency()`` callback is added to the TX port and is applied to all
168 packets prior to transmission:
169
170 .. code-block:: c
171
172 static uint16_t
173 calc_latency(uint16_t port __rte_unused, uint16_t qidx __rte_unused,
174 struct rte_mbuf **pkts, uint16_t nb_pkts, void *_ __rte_unused)
175 {
176 uint64_t cycles = 0;
177 uint64_t now = rte_rdtsc();
178 unsigned i;
179
180 for (i = 0; i < nb_pkts; i++)
181 cycles += now - pkts[i]->udata64;
182
183 latency_numbers.total_cycles += cycles;
184 latency_numbers.total_pkts += nb_pkts;
185
186 if (latency_numbers.total_pkts > (100 * 1000 * 1000ULL)) {
187 printf("Latency = %"PRIu64" cycles\n",
188 latency_numbers.total_cycles / latency_numbers.total_pkts);
189
190 latency_numbers.total_cycles = latency_numbers.total_pkts = 0;
191 }
192
193 return nb_pkts;
194 }
195
196 The ``calc_latency()`` function accumulates the total number of packets and
197 the total number of cycles used. Once more than 100 million packets have been
198 transmitted the average cycle count per packet is printed out and the counters
199 are reset.