From: Jiawei Wang <jiaweiw@nvidia.com>
To: <viacheslavo@nvidia.com>, <orika@nvidia.com>,
<thomas@monjalon.net>, <andrew.rybchenko@oktetlabs.ru>,
Aman Singh <aman.deep.singh@intel.com>,
Yuying Zhang <yuying.zhang@intel.com>,
Ferruh Yigit <ferruh.yigit@amd.com>
Cc: <dev@dpdk.org>, <rasland@nvidia.com>
Subject: [PATCH v5 1/2] ethdev: introduce the Tx map API for aggregated ports
Date: Tue, 14 Feb 2023 17:48:35 +0200 [thread overview]
Message-ID: <20230214154836.9681-2-jiaweiw@nvidia.com> (raw)
In-Reply-To: <20230214154836.9681-1-jiaweiw@nvidia.com>
When multiple ports are aggregated into a single DPDK port,
(example: Linux bonding, DPDK bonding, failsafe, etc.),
we want to know which port use for Tx via a queue.
This patch introduces the new ethdev API
rte_eth_dev_map_aggr_tx_affinity(), it's used to map a Tx queue
with an aggregated port of the DPDK port (specified with port_id),
The affinity is the number of the aggregated port.
Value 0 means no affinity and traffic could be routed to any
aggregated port, this is the default current behavior.
The maximum number of affinity is given by rte_eth_dev_count_aggr_ports().
Add the trace point for ethdev rte_eth_dev_count_aggr_ports()
and rte_eth_dev_map_aggr_tx_affinity() functions.
Add the testpmd command line:
testpmd> port config (port_id) txq (queue_id) affinity (value)
For example, there're two physical ports connected to
a single DPDK port (port id 0), and affinity 1 stood for
the first physical port and affinity 2 stood for the second
physical port.
Use the below commands to config tx phy affinity for per Tx Queue:
port config 0 txq 0 affinity 1
port config 0 txq 1 affinity 1
port config 0 txq 2 affinity 2
port config 0 txq 3 affinity 2
These commands config the Tx Queue index 0 and Tx Queue index 1 with
phy affinity 1, uses Tx Queue 0 or Tx Queue 1 send packets,
these packets will be sent from the first physical port, and similar
with the second physical port if sending packets with Tx Queue 2
or Tx Queue 3.
Signed-off-by: Jiawei Wang <jiaweiw@nvidia.com>
---
app/test-pmd/cmdline.c | 96 +++++++++++++++++++++
doc/guides/rel_notes/release_23_03.rst | 7 ++
doc/guides/testpmd_app_ug/testpmd_funcs.rst | 14 +++
lib/ethdev/ethdev_driver.h | 39 +++++++++
lib/ethdev/ethdev_trace.h | 17 ++++
lib/ethdev/ethdev_trace_points.c | 6 ++
lib/ethdev/rte_ethdev.c | 49 +++++++++++
lib/ethdev/rte_ethdev.h | 46 ++++++++++
lib/ethdev/version.map | 2 +
9 files changed, 276 insertions(+)
diff --git a/app/test-pmd/cmdline.c b/app/test-pmd/cmdline.c
index bb7ff2b449..36c798ac45 100644
--- a/app/test-pmd/cmdline.c
+++ b/app/test-pmd/cmdline.c
@@ -776,6 +776,10 @@ static void cmd_help_long_parsed(void *parsed_result,
"port cleanup (port_id) txq (queue_id) (free_cnt)\n"
" Cleanup txq mbufs for a specific Tx queue\n\n"
+
+ "port config (port_id) txq (queue_id) affinity (value)\n"
+ " Map a Tx queue with an aggregated port "
+ "of the DPDK port\n\n"
);
}
@@ -12636,6 +12640,97 @@ static cmdline_parse_inst_t cmd_show_port_flow_transfer_proxy = {
}
};
+/* *** configure port txq affinity value *** */
+struct cmd_config_tx_affinity_map {
+ cmdline_fixed_string_t port;
+ cmdline_fixed_string_t config;
+ portid_t portid;
+ cmdline_fixed_string_t txq;
+ uint16_t qid;
+ cmdline_fixed_string_t affinity;
+ uint8_t value;
+};
+
+static void
+cmd_config_tx_affinity_map_parsed(void *parsed_result,
+ __rte_unused struct cmdline *cl,
+ __rte_unused void *data)
+{
+ struct cmd_config_tx_affinity_map *res = parsed_result;
+ int ret;
+
+ if (port_id_is_invalid(res->portid, ENABLED_WARN))
+ return;
+
+ if (res->portid == (portid_t)RTE_PORT_ALL) {
+ printf("Invalid port id\n");
+ return;
+ }
+
+ if (strcmp(res->txq, "txq")) {
+ printf("Unknown parameter\n");
+ return;
+ }
+ if (tx_queue_id_is_invalid(res->qid))
+ return;
+
+ ret = rte_eth_dev_count_aggr_ports(res->portid);
+ if (ret < 0) {
+ printf("Failed to count the aggregated ports: (%s)\n",
+ strerror(-ret));
+ return;
+ }
+ if (ret == 0) {
+ printf("Number of aggregated ports is 0 which is invalid for affinity mapping\n");
+ return;
+ }
+ if (ret < res->value) {
+ printf("The affinity value %u is Invalid, exceeds the "
+ "number of aggregated ports\n", res->value);
+ return;
+ }
+
+ rte_eth_dev_map_aggr_tx_affinity(res->portid, res->qid, res->value);
+}
+
+cmdline_parse_token_string_t cmd_config_tx_affinity_map_port =
+ TOKEN_STRING_INITIALIZER(struct cmd_config_tx_affinity_map,
+ port, "port");
+cmdline_parse_token_string_t cmd_config_tx_affinity_map_config =
+ TOKEN_STRING_INITIALIZER(struct cmd_config_tx_affinity_map,
+ config, "config");
+cmdline_parse_token_num_t cmd_config_tx_affinity_map_portid =
+ TOKEN_NUM_INITIALIZER(struct cmd_config_tx_affinity_map,
+ portid, RTE_UINT16);
+cmdline_parse_token_string_t cmd_config_tx_affinity_map_txq =
+ TOKEN_STRING_INITIALIZER(struct cmd_config_tx_affinity_map,
+ txq, "txq");
+cmdline_parse_token_num_t cmd_config_tx_affinity_map_qid =
+ TOKEN_NUM_INITIALIZER(struct cmd_config_tx_affinity_map,
+ qid, RTE_UINT16);
+cmdline_parse_token_string_t cmd_config_tx_affinity_map_affinity =
+ TOKEN_STRING_INITIALIZER(struct cmd_config_tx_affinity_map,
+ affinity, "affinity");
+cmdline_parse_token_num_t cmd_config_tx_affinity_map_value =
+ TOKEN_NUM_INITIALIZER(struct cmd_config_tx_affinity_map,
+ value, RTE_UINT8);
+
+static cmdline_parse_inst_t cmd_config_tx_affinity_map = {
+ .f = cmd_config_tx_affinity_map_parsed,
+ .data = (void *)0,
+ .help_str = "port config <port_id> txq <queue_id> affinity <value>",
+ .tokens = {
+ (void *)&cmd_config_tx_affinity_map_port,
+ (void *)&cmd_config_tx_affinity_map_config,
+ (void *)&cmd_config_tx_affinity_map_portid,
+ (void *)&cmd_config_tx_affinity_map_txq,
+ (void *)&cmd_config_tx_affinity_map_qid,
+ (void *)&cmd_config_tx_affinity_map_affinity,
+ (void *)&cmd_config_tx_affinity_map_value,
+ NULL,
+ },
+};
+
/* ******************************************************************************** */
/* list of instructions */
@@ -12869,6 +12964,7 @@ static cmdline_parse_ctx_t builtin_ctx[] = {
(cmdline_parse_inst_t *)&cmd_show_port_cman_capa,
(cmdline_parse_inst_t *)&cmd_show_port_cman_config,
(cmdline_parse_inst_t *)&cmd_set_port_cman_config,
+ (cmdline_parse_inst_t *)&cmd_config_tx_affinity_map,
NULL,
};
diff --git a/doc/guides/rel_notes/release_23_03.rst b/doc/guides/rel_notes/release_23_03.rst
index ab998a5357..becf6fed91 100644
--- a/doc/guides/rel_notes/release_23_03.rst
+++ b/doc/guides/rel_notes/release_23_03.rst
@@ -68,6 +68,13 @@ New Features
* Applications can register a callback at startup via
``rte_lcore_register_usage_cb()`` to provide lcore usage information.
+* **Added support for Tx queue mapping with an aggregated port.**
+
+ * Introduced new function ``rte_eth_dev_count_aggr_ports()``
+ to get the number of aggregated ports.
+ * Introduced new function ``rte_eth_dev_map_aggr_tx_affinity()``
+ to map a Tx queue with an aggregated port of the DPDK port.
+
* **Added rte_flow support for matching IPv6 routing extension header fields.**
Added ``ipv6_routing_ext`` items in rte_flow to match IPv6 routing extension
diff --git a/doc/guides/testpmd_app_ug/testpmd_funcs.rst b/doc/guides/testpmd_app_ug/testpmd_funcs.rst
index 357adb09d7..1d3c372601 100644
--- a/doc/guides/testpmd_app_ug/testpmd_funcs.rst
+++ b/doc/guides/testpmd_app_ug/testpmd_funcs.rst
@@ -1612,6 +1612,20 @@ Enable or disable a per queue Tx offloading only on a specific Tx queue::
This command should be run when the port is stopped, or else it will fail.
+config per queue Tx affinity mapping
+~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~
+
+Map a Tx queue with an aggregated port of the DPDK port (specified with port_id)::
+
+ testpmd> port (port_id) txq (queue_id) affinity (value)
+
+* ``affinity``: the number of the aggregated port.
+ When multiple ports are aggregated into a single one,
+ it allows to choose which port to use for Tx via a queue.
+
+This command should be run when the port is stopped, otherwise it fails.
+
+
Config VXLAN Encap outer layers
~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~
diff --git a/lib/ethdev/ethdev_driver.h b/lib/ethdev/ethdev_driver.h
index 6a550cfc83..b7fdc454a8 100644
--- a/lib/ethdev/ethdev_driver.h
+++ b/lib/ethdev/ethdev_driver.h
@@ -1171,6 +1171,40 @@ typedef int (*eth_tx_descriptor_dump_t)(const struct rte_eth_dev *dev,
uint16_t queue_id, uint16_t offset,
uint16_t num, FILE *file);
+/**
+ * @internal
+ * Get the number of aggregated ports.
+ *
+ * @param port_id
+ * The port identifier of the Ethernet device.
+ *
+ * @return
+ * Negative errno value on error, 0 or positive on success.
+ *
+ * @retval >=0
+ * The number of aggregated port if success.
+ * @retval -ENOTSUP
+ * Get aggregated ports API is not supported.
+ */
+typedef int (*eth_count_aggr_ports_t)(uint16_t port_id);
+
+/**
+ * @internal
+ * Map a Tx queue with an aggregated port of the DPDK port.
+ *
+ * @param port_id
+ * The identifier of the port used in rte_eth_tx_burst().
+ * @param tx_queue_id
+ * The index of the transmit queue used in rte_eth_tx_burst().
+ * @param affinity
+ * The number of the aggregated port.
+ *
+ * @return
+ * Negative on error, 0 on success.
+ */
+typedef int (*eth_map_aggr_tx_affinity_t)(uint16_t port_id, uint16_t tx_queue_id,
+ uint8_t affinity);
+
/**
* @internal A structure containing the functions exported by an Ethernet driver.
*/
@@ -1403,6 +1437,11 @@ struct eth_dev_ops {
eth_cman_config_set_t cman_config_set;
/** Retrieve congestion management configuration */
eth_cman_config_get_t cman_config_get;
+
+ /** Get the number of aggregated ports */
+ eth_count_aggr_ports_t count_aggr_ports;
+ /** Map a Tx queue with an aggregated port of the DPDK port */
+ eth_map_aggr_tx_affinity_t map_aggr_tx_affinity;
};
/**
diff --git a/lib/ethdev/ethdev_trace.h b/lib/ethdev/ethdev_trace.h
index 9fae22c490..4e210d099b 100644
--- a/lib/ethdev/ethdev_trace.h
+++ b/lib/ethdev/ethdev_trace.h
@@ -1385,6 +1385,23 @@ RTE_TRACE_POINT(
rte_trace_point_emit_int(ret);
)
+RTE_TRACE_POINT(
+ rte_eth_trace_count_aggr_ports,
+ RTE_TRACE_POINT_ARGS(uint16_t port_id, int ret),
+ rte_trace_point_emit_u16(port_id);
+ rte_trace_point_emit_int(ret);
+)
+
+RTE_TRACE_POINT(
+ rte_eth_trace_map_aggr_tx_affinity,
+ RTE_TRACE_POINT_ARGS(uint16_t port_id, uint16_t tx_queue_id,
+ uint8_t affinity, int ret),
+ rte_trace_point_emit_u16(port_id);
+ rte_trace_point_emit_u16(tx_queue_id);
+ rte_trace_point_emit_u8(affinity);
+ rte_trace_point_emit_int(ret);
+)
+
RTE_TRACE_POINT(
rte_flow_trace_dynf_metadata_register,
RTE_TRACE_POINT_ARGS(int offset, uint64_t flag),
diff --git a/lib/ethdev/ethdev_trace_points.c b/lib/ethdev/ethdev_trace_points.c
index 34d12e2859..61010cae56 100644
--- a/lib/ethdev/ethdev_trace_points.c
+++ b/lib/ethdev/ethdev_trace_points.c
@@ -475,6 +475,12 @@ RTE_TRACE_POINT_REGISTER(rte_eth_trace_cman_config_set,
RTE_TRACE_POINT_REGISTER(rte_eth_trace_cman_config_get,
lib.ethdev.cman_config_get)
+RTE_TRACE_POINT_REGISTER(rte_eth_trace_count_aggr_ports,
+ lib.ethdev.count_aggr_ports)
+
+RTE_TRACE_POINT_REGISTER(rte_eth_trace_map_aggr_tx_affinity,
+ lib.ethdev.map_aggr_tx_affinity)
+
RTE_TRACE_POINT_REGISTER(rte_flow_trace_copy,
lib.ethdev.flow.copy)
diff --git a/lib/ethdev/rte_ethdev.c b/lib/ethdev/rte_ethdev.c
index dc0a4eb12c..1d5b3a16b2 100644
--- a/lib/ethdev/rte_ethdev.c
+++ b/lib/ethdev/rte_ethdev.c
@@ -6915,6 +6915,55 @@ rte_eth_buffer_split_get_supported_hdr_ptypes(uint16_t port_id, uint32_t *ptypes
return j;
}
+int rte_eth_dev_count_aggr_ports(uint16_t port_id)
+{
+ struct rte_eth_dev *dev;
+ int ret;
+
+ RTE_ETH_VALID_PORTID_OR_ERR_RET(port_id, -ENODEV);
+ dev = &rte_eth_devices[port_id];
+
+ if (*dev->dev_ops->count_aggr_ports == NULL)
+ return -ENOTSUP;
+ ret = eth_err(port_id, (*dev->dev_ops->count_aggr_ports)(port_id));
+
+ rte_eth_trace_count_aggr_ports(port_id, ret);
+
+ return ret;
+}
+
+int rte_eth_dev_map_aggr_tx_affinity(uint16_t port_id, uint16_t tx_queue_id,
+ uint8_t affinity)
+{
+ struct rte_eth_dev *dev;
+ int ret;
+
+ RTE_ETH_VALID_PORTID_OR_ERR_RET(port_id, -ENODEV);
+ dev = &rte_eth_devices[port_id];
+
+ if (tx_queue_id >= dev->data->nb_tx_queues) {
+ RTE_ETHDEV_LOG(ERR, "Invalid Tx queue_id=%u\n", tx_queue_id);
+ return -EINVAL;
+ }
+
+ if (*dev->dev_ops->map_aggr_tx_affinity == NULL)
+ return -ENOTSUP;
+
+ if (dev->data->dev_started) {
+ RTE_ETHDEV_LOG(ERR,
+ "Port %u must be stopped to allow configuration\n",
+ port_id);
+ return -EBUSY;
+ }
+
+ ret = eth_err(port_id, (*dev->dev_ops->map_aggr_tx_affinity)(port_id,
+ tx_queue_id, affinity));
+
+ rte_eth_trace_map_aggr_tx_affinity(port_id, tx_queue_id, affinity, ret);
+
+ return ret;
+}
+
RTE_LOG_REGISTER_DEFAULT(rte_eth_dev_logtype, INFO);
RTE_INIT(ethdev_init_telemetry)
diff --git a/lib/ethdev/rte_ethdev.h b/lib/ethdev/rte_ethdev.h
index c129ca1eaf..07b8250eb8 100644
--- a/lib/ethdev/rte_ethdev.h
+++ b/lib/ethdev/rte_ethdev.h
@@ -2589,6 +2589,52 @@ int rte_eth_hairpin_bind(uint16_t tx_port, uint16_t rx_port);
__rte_experimental
int rte_eth_hairpin_unbind(uint16_t tx_port, uint16_t rx_port);
+/**
+ * @warning
+ * @b EXPERIMENTAL: this API may change without prior notice.
+ *
+ * Get the number of aggregated ports.
+ *
+ * @param port_id
+ * The port identifier of the Ethernet device.
+ * @return
+ * - (>=0) the number of aggregated port if success.
+ * - (-ENOTSUP) if not supported.
+ */
+__rte_experimental
+int rte_eth_dev_count_aggr_ports(uint16_t port_id);
+
+/**
+ * @warning
+ * @b EXPERIMENTAL: this API may change without prior notice.
+ *
+ * Map a Tx queue with an aggregated port of the DPDK port (specified with port_id).
+ * When multiple ports are aggregated into a single one,
+ * it allows to choose which port to use for Tx via a queue.
+ *
+ * The application should use rte_eth_dev_map_aggr_tx_affinity()
+ * after rte_eth_dev_configure(), rte_eth_tx_queue_setup(), and
+ * before rte_eth_dev_start().
+ *
+ * @param port_id
+ * The identifier of the port used in rte_eth_tx_burst().
+ * @param tx_queue_id
+ * The index of the transmit queue used in rte_eth_tx_burst().
+ * The value must be in the range [0, nb_tx_queue - 1] previously supplied
+ * to rte_eth_dev_configure().
+ * @param affinity
+ * The number of the aggregated port.
+ * Value 0 means no affinity and traffic could be routed to any aggregated port.
+ * The first aggregated port is number 1 and so on.
+ * The maximum number is given by rte_eth_dev_count_aggr_ports().
+ *
+ * @return
+ * Zero if successful. Non-zero otherwise.
+ */
+__rte_experimental
+int rte_eth_dev_map_aggr_tx_affinity(uint16_t port_id, uint16_t tx_queue_id,
+ uint8_t affinity);
+
/**
* Return the NUMA socket to which an Ethernet device is connected
*
diff --git a/lib/ethdev/version.map b/lib/ethdev/version.map
index dbc2bffe64..685aa71e51 100644
--- a/lib/ethdev/version.map
+++ b/lib/ethdev/version.map
@@ -300,6 +300,8 @@ EXPERIMENTAL {
rte_mtr_meter_profile_get;
# added in 23.03
+ rte_eth_dev_count_aggr_ports;
+ rte_eth_dev_map_aggr_tx_affinity;
rte_flow_async_create_by_index;
};
--
2.18.1
next prev parent reply other threads:[~2023-02-14 15:49 UTC|newest]
Thread overview: 40+ messages / expand[flat|nested] mbox.gz Atom feed top
[not found] <20221221102934.13822-1-jiaweiw@nvidia.com/>
2023-02-03 5:07 ` [PATCH v3 0/2] add new PHY affinity in the flow item and Tx queue API Jiawei Wang
2023-02-03 5:07 ` [PATCH v3 1/2] ethdev: introduce the PHY affinity field in " Jiawei Wang
2023-02-03 5:07 ` [PATCH v3 2/2] ethdev: add PHY affinity match item Jiawei Wang
2023-02-03 13:33 ` [PATCH v4 0/2] add new PHY affinity in the flow item and Tx queue API Jiawei Wang
2023-02-03 13:33 ` [PATCH v4 1/2] ethdev: introduce the PHY affinity field in " Jiawei Wang
2023-02-06 15:29 ` Jiawei(Jonny) Wang
2023-02-07 9:40 ` Ori Kam
2023-02-09 19:44 ` Ferruh Yigit
2023-02-10 14:06 ` Jiawei(Jonny) Wang
2023-02-14 9:38 ` Jiawei(Jonny) Wang
2023-02-14 10:01 ` Ferruh Yigit
2023-02-03 13:33 ` [PATCH v4 2/2] ethdev: add PHY affinity match item Jiawei Wang
2023-02-14 15:48 ` [PATCH v5 0/2] Added support for Tx queue mapping with an aggregated port Jiawei Wang
2023-02-14 15:48 ` Jiawei Wang [this message]
2023-02-15 11:41 ` [PATCH v5 1/2] ethdev: introduce the Tx map API for aggregated ports Jiawei(Jonny) Wang
2023-02-16 17:42 ` Thomas Monjalon
2023-02-17 6:45 ` Jiawei(Jonny) Wang
2023-02-16 17:58 ` Ferruh Yigit
2023-02-17 6:44 ` Jiawei(Jonny) Wang
2023-02-17 8:24 ` Andrew Rybchenko
2023-02-17 9:50 ` Jiawei(Jonny) Wang
2023-02-14 15:48 ` [PATCH v5 2/2] ethdev: add Aggregated affinity match item Jiawei Wang
2023-02-16 17:46 ` Thomas Monjalon
2023-02-17 6:45 ` Jiawei(Jonny) Wang
2023-02-17 10:50 ` [PATCH v6 0/2] Add Tx queue mapping of aggregated ports Jiawei Wang
2023-02-17 10:50 ` [PATCH v6 1/2] ethdev: add " Jiawei Wang
2023-02-17 12:53 ` Ferruh Yigit
2023-02-17 12:56 ` Andrew Rybchenko
2023-02-17 12:59 ` Ferruh Yigit
2023-02-17 13:05 ` Jiawei(Jonny) Wang
2023-02-17 13:41 ` Jiawei(Jonny) Wang
2023-02-17 15:03 ` Andrew Rybchenko
2023-02-17 15:32 ` Ferruh Yigit
2023-02-17 10:50 ` [PATCH v6 2/2] ethdev: add flow matching of aggregated port Jiawei Wang
2023-02-17 13:01 ` [PATCH v6 0/2] Add Tx queue mapping of aggregated ports Ferruh Yigit
2023-02-17 13:07 ` Jiawei(Jonny) Wang
2023-02-17 15:47 ` [PATCH v7 " Jiawei Wang
2023-02-17 15:47 ` [PATCH v7 1/2] ethdev: add " Jiawei Wang
2023-02-17 15:47 ` [PATCH v7 2/2] ethdev: add flow matching of aggregated port Jiawei Wang
2023-02-17 16:45 ` [PATCH v7 0/2] Add Tx queue mapping of aggregated ports Ferruh Yigit
Reply instructions:
You may reply publicly to this message via plain-text email
using any one of the following methods:
* Save the following mbox file, import it into your mail client,
and reply-to-all from there: mbox
Avoid top-posting and favor interleaved quoting:
https://en.wikipedia.org/wiki/Posting_style#Interleaved_style
* Reply using the --to, --cc, and --in-reply-to
switches of git-send-email(1):
git send-email \
--in-reply-to=20230214154836.9681-2-jiaweiw@nvidia.com \
--to=jiaweiw@nvidia.com \
--cc=aman.deep.singh@intel.com \
--cc=andrew.rybchenko@oktetlabs.ru \
--cc=dev@dpdk.org \
--cc=ferruh.yigit@amd.com \
--cc=orika@nvidia.com \
--cc=rasland@nvidia.com \
--cc=thomas@monjalon.net \
--cc=viacheslavo@nvidia.com \
--cc=yuying.zhang@intel.com \
/path/to/YOUR_REPLY
https://kernel.org/pub/software/scm/git/docs/git-send-email.html
* If your mail client supports setting the In-Reply-To header
via mailto: links, try the mailto: link
Be sure your reply has a Subject: header at the top and a blank line
before the message body.
This is a public inbox, see mirroring instructions
for how to clone and mirror all data and code used for this inbox;
as well as URLs for NNTP newsgroup(s).