[v4,3/3] rxtx_callbacks: Add support for HW timestamp

Message ID 20190502121135.18775-4-barbette@kth.se
State Accepted
Delegated to: Ferruh Yigit
Headers show
Series
  • Add rte_eth_read_clock API
Related show

Checks

Context Check Description
ci/Intel-compilation success Compilation OK
ci/checkpatch success coding style OK

Commit Message

Tom Barbette May 2, 2019, 12:11 p.m.
Use rxtx callback to demonstrate a way to use rte_eth_read_clock to
convert the hardware timestamps to an amount of cycles.

This allows to get the amount of time the packet spent since its entry
in the device. While the regular latency only shows the latency from
when it entered the software stack.

Signed-off-by: Tom Barbette <barbette@kth.se>
---
 doc/guides/sample_app_ug/rxtx_callbacks.rst |  9 ++-
 examples/rxtx_callbacks/Makefile            |  3 +
 examples/rxtx_callbacks/main.c              | 87 ++++++++++++++++++++-
 examples/rxtx_callbacks/meson.build         |  3 +
 4 files changed, 97 insertions(+), 5 deletions(-)

Comments

Ferruh Yigit May 31, 2019, 7:46 a.m. | #1
On 5/2/2019 1:11 PM, Tom Barbette wrote:
> Use rxtx callback to demonstrate a way to use rte_eth_read_clock to
> convert the hardware timestamps to an amount of cycles.
> 
> This allows to get the amount of time the packet spent since its entry
> in the device. While the regular latency only shows the latency from
> when it entered the software stack.
> 
> Signed-off-by: Tom Barbette <barbette@kth.se>

Reviewed-by: Ferruh Yigit <ferruh.yigit@intel.com>
Thomas Monjalon June 13, 2019, 5:55 a.m. | #2
02/05/2019 21:11, Tom Barbette:
> +	if (hw_timestamping && ticks_per_cycle_mult  == 0) {
> +		uint64_t cycles_base = rte_rdtsc();
> +		uint64_t ticks_base;
> +		retval = rte_eth_read_clock(port, &ticks_base);
> +		if (retval != 0)
> +			return retval;
> +		rte_delay_ms(100);
> +		uint64_t cycles = rte_rdtsc();
> +		uint64_t ticks;
> +		rte_eth_read_clock(port, &ticks);
> +		uint64_t c_freq = cycles - cycles_base;
> +		uint64_t t_freq = ticks - ticks_base;
> +		double freq_mult = (double)c_freq / t_freq;
> +		printf("TSC Freq ~= %lu\nHW Freq ~= %lu\nRatio : %f\n",
> +				c_freq * 10, t_freq * 10, freq_mult);
> +		/* TSC will be faster than internal ticks so freq_mult is > 0
> +		 * We convert the multiplication to an integer shift & mult
> +		 */
> +		ticks_per_cycle_mult = (1 << TICKS_PER_CYCLE_SHIFT) / freq_mult;
> +	}

I see two issues in this code:
1/ statements are mixed with variable declarations
2/ %lu is used for 64-bit variables, which does not work on 32-bit system.

I am fixing item 2 when merging.
I hope item 1 won't be an issue for some old compilers.

Patch

diff --git a/doc/guides/sample_app_ug/rxtx_callbacks.rst b/doc/guides/sample_app_ug/rxtx_callbacks.rst
index 81463d28d..6b0c64461 100644
--- a/doc/guides/sample_app_ug/rxtx_callbacks.rst
+++ b/doc/guides/sample_app_ug/rxtx_callbacks.rst
@@ -13,6 +13,10 @@  In the sample application a user defined callback is applied to all received
 packets to add a timestamp. A separate callback is applied to all packets
 prior to transmission to calculate the elapsed time, in CPU cycles.
 
+If hardware timestamping is supported by the NIC, the sample application will
+also display the average latency since the packet was timestamped in hardware,
+on top of the latency since the packet was received and processed by the RX
+callback.
 
 Compiling the Application
 -------------------------
@@ -36,7 +40,10 @@  To run the example in a ``linux`` environment:
 
 .. code-block:: console
 
-    ./build/rxtx_callbacks -l 1 -n 4
+    ./build/rxtx_callbacks -l 1 -n 4 -- [-t]
+
+Use -t to enable hardware timestamping. If not supported by the NIC, an error
+will be displayed.
 
 Refer to *DPDK Getting Started Guide* for general information on running
 applications and the Environment Abstraction Layer (EAL) options.
diff --git a/examples/rxtx_callbacks/Makefile b/examples/rxtx_callbacks/Makefile
index b937d599b..0a4660681 100644
--- a/examples/rxtx_callbacks/Makefile
+++ b/examples/rxtx_callbacks/Makefile
@@ -50,6 +50,9 @@  include $(RTE_SDK)/mk/rte.vars.mk
 
 CFLAGS += $(WERROR_FLAGS)
 
+# rte_eth_read_clock is experimental
+CFLAGS += -DALLOW_EXPERIMENTAL_API
+
 # workaround for a gcc bug with noreturn attribute
 # http://gcc.gnu.org/bugzilla/show_bug.cgi?id=12603
 ifeq ($(CONFIG_RTE_TOOLCHAIN_GCC),y)
diff --git a/examples/rxtx_callbacks/main.c b/examples/rxtx_callbacks/main.c
index 2058be627..55aa82288 100644
--- a/examples/rxtx_callbacks/main.c
+++ b/examples/rxtx_callbacks/main.c
@@ -4,6 +4,7 @@ 
 
 #include <stdint.h>
 #include <inttypes.h>
+#include <getopt.h>
 #include <rte_eal.h>
 #include <rte_ethdev.h>
 #include <rte_cycles.h>
@@ -17,6 +18,9 @@ 
 #define MBUF_CACHE_SIZE 250
 #define BURST_SIZE 32
 
+static const char usage[] =
+	"%s EAL_ARGS -- [-t]\n";
+
 static const struct rte_eth_conf port_conf_default = {
 	.rxmode = {
 		.max_rx_pkt_len = ETHER_MAX_LEN,
@@ -25,9 +29,14 @@  static const struct rte_eth_conf port_conf_default = {
 
 static struct {
 	uint64_t total_cycles;
+	uint64_t total_queue_cycles;
 	uint64_t total_pkts;
 } latency_numbers;
 
+int hw_timestamping;
+
+#define TICKS_PER_CYCLE_SHIFT 16
+static uint64_t ticks_per_cycle_mult;
 
 static uint16_t
 add_timestamps(uint16_t port __rte_unused, uint16_t qidx __rte_unused,
@@ -43,22 +52,42 @@  add_timestamps(uint16_t port __rte_unused, uint16_t qidx __rte_unused,
 }
 
 static uint16_t
-calc_latency(uint16_t port __rte_unused, uint16_t qidx __rte_unused,
+calc_latency(uint16_t port, uint16_t qidx __rte_unused,
 		struct rte_mbuf **pkts, uint16_t nb_pkts, void *_ __rte_unused)
 {
 	uint64_t cycles = 0;
+	uint64_t queue_ticks = 0;
 	uint64_t now = rte_rdtsc();
+	uint64_t ticks;
 	unsigned i;
 
-	for (i = 0; i < nb_pkts; i++)
+	if (hw_timestamping)
+		rte_eth_read_clock(port, &ticks);
+
+	for (i = 0; i < nb_pkts; i++) {
 		cycles += now - pkts[i]->udata64;
+		if (hw_timestamping)
+			queue_ticks += ticks - pkts[i]->timestamp;
+	}
+
 	latency_numbers.total_cycles += cycles;
+	if (hw_timestamping)
+		latency_numbers.total_queue_cycles += (queue_ticks
+			* ticks_per_cycle_mult) >> TICKS_PER_CYCLE_SHIFT;
+
 	latency_numbers.total_pkts += nb_pkts;
 
 	if (latency_numbers.total_pkts > (100 * 1000 * 1000ULL)) {
 		printf("Latency = %"PRIu64" cycles\n",
 		latency_numbers.total_cycles / latency_numbers.total_pkts);
-		latency_numbers.total_cycles = latency_numbers.total_pkts = 0;
+		if (hw_timestamping) {
+			printf("Latency from HW = %"PRIu64" cycles\n",
+			   latency_numbers.total_queue_cycles
+			   / latency_numbers.total_pkts);
+		}
+		latency_numbers.total_cycles = 0;
+		latency_numbers.total_queue_cycles = 0;
+		latency_numbers.total_pkts = 0;
 	}
 	return nb_pkts;
 }
@@ -77,6 +106,7 @@  port_init(uint16_t port, struct rte_mempool *mbuf_pool)
 	int retval;
 	uint16_t q;
 	struct rte_eth_dev_info dev_info;
+	struct rte_eth_rxconf rxconf;
 	struct rte_eth_txconf txconf;
 
 	if (!rte_eth_dev_is_valid_port(port))
@@ -95,9 +125,20 @@  port_init(uint16_t port, struct rte_mempool *mbuf_pool)
 	if (retval != 0)
 		return retval;
 
+	rxconf = dev_info.default_rxconf;
+
+	if (hw_timestamping) {
+		if (!(dev_info.rx_offload_capa & DEV_RX_OFFLOAD_TIMESTAMP)) {
+			printf("\nERROR: Port %u does not support hardware timestamping\n"
+					, port);
+			return -1;
+		}
+		rxconf.offloads |= DEV_RX_OFFLOAD_TIMESTAMP;
+	}
+
 	for (q = 0; q < rx_rings; q++) {
 		retval = rte_eth_rx_queue_setup(port, q, nb_rxd,
-				rte_eth_dev_socket_id(port), NULL, mbuf_pool);
+			rte_eth_dev_socket_id(port), &rxconf, mbuf_pool);
 		if (retval < 0)
 			return retval;
 	}
@@ -115,6 +156,27 @@  port_init(uint16_t port, struct rte_mempool *mbuf_pool)
 	if (retval < 0)
 		return retval;
 
+	if (hw_timestamping && ticks_per_cycle_mult  == 0) {
+		uint64_t cycles_base = rte_rdtsc();
+		uint64_t ticks_base;
+		retval = rte_eth_read_clock(port, &ticks_base);
+		if (retval != 0)
+			return retval;
+		rte_delay_ms(100);
+		uint64_t cycles = rte_rdtsc();
+		uint64_t ticks;
+		rte_eth_read_clock(port, &ticks);
+		uint64_t c_freq = cycles - cycles_base;
+		uint64_t t_freq = ticks - ticks_base;
+		double freq_mult = (double)c_freq / t_freq;
+		printf("TSC Freq ~= %lu\nHW Freq ~= %lu\nRatio : %f\n",
+				c_freq * 10, t_freq * 10, freq_mult);
+		/* TSC will be faster than internal ticks so freq_mult is > 0
+		 * We convert the multiplication to an integer shift & mult
+		 */
+		ticks_per_cycle_mult = (1 << TICKS_PER_CYCLE_SHIFT) / freq_mult;
+	}
+
 	struct ether_addr addr;
 
 	rte_eth_macaddr_get(port, &addr);
@@ -177,6 +239,11 @@  main(int argc, char *argv[])
 	struct rte_mempool *mbuf_pool;
 	uint16_t nb_ports;
 	uint16_t portid;
+	struct option lgopts[] = {
+		{ NULL,  0, 0, 0 }
+	};
+	int opt, option_index;
+
 
 	/* init EAL */
 	int ret = rte_eal_init(argc, argv);
@@ -186,6 +253,18 @@  main(int argc, char *argv[])
 	argc -= ret;
 	argv += ret;
 
+	while ((opt = getopt_long(argc, argv, "t", lgopts, &option_index))
+			!= EOF)
+		switch (opt) {
+		case 't':
+			hw_timestamping = 1;
+			break;
+		default:
+			printf(usage, argv[0]);
+			return -1;
+		}
+	optind = 1; /* reset getopt lib */
+
 	nb_ports = rte_eth_dev_count_avail();
 	if (nb_ports < 2 || (nb_ports & 1))
 		rte_exit(EXIT_FAILURE, "Error: number of ports must be even\n");
diff --git a/examples/rxtx_callbacks/meson.build b/examples/rxtx_callbacks/meson.build
index c34e11e36..a7bf12dd3 100644
--- a/examples/rxtx_callbacks/meson.build
+++ b/examples/rxtx_callbacks/meson.build
@@ -6,6 +6,9 @@ 
 # To build this example as a standalone application with an already-installed
 # DPDK instance, use 'make'
 
+#rte_eth_read_clock is experimental
+allow_experimental_apis = true
+
 sources = files(
 	'main.c'
 )