[dpdk-dev] [v1] ethdev: support Tx queue used count

[Ferruh Yigit]

On 1/11/2024 3:17 PM, jerinj at marvell.com wrote:
> From: Jerin Jacob <jerinj at marvell.com>
> 
> Introduce a new API to retrieve the number of used descriptors
> in a Tx queue. Applications can leverage this API in the fast path to
> inspect the Tx queue occupancy and take appropriate actions based on the
> available free descriptors.
> 
> A notable use case could be implementing Random Early Discard (RED)
> in software based on Tx queue occupancy.
> 
> Signed-off-by: Jerin Jacob <jerinj at marvell.com>
> ---
>  doc/guides/nics/features.rst         | 10 ++++
>  doc/guides/nics/features/default.ini |  1 +
>  lib/ethdev/ethdev_driver.h           |  2 +
>  lib/ethdev/ethdev_private.c          |  1 +
>  lib/ethdev/ethdev_trace_points.c     |  3 ++
>  lib/ethdev/rte_ethdev.h              | 74 ++++++++++++++++++++++++++++
>  lib/ethdev/rte_ethdev_core.h         |  7 ++-
>  lib/ethdev/rte_ethdev_trace_fp.h     |  8 +++
>  lib/ethdev/version.map               |  3 ++
>  9 files changed, 108 insertions(+), 1 deletion(-)
> 

As we are adding a new API and dev_ops, is a driver implementation and
testpmd/example implementation planned for this release?


> rfc..v1:
> - Updated API similar to rte_eth_rx_queue_count() where it returns
> "used" count instead of "free" count
> 
> diff --git a/doc/guides/nics/features.rst b/doc/guides/nics/features.rst
> index f7d9980849..0d5a8733fc 100644
> --- a/doc/guides/nics/features.rst
> +++ b/doc/guides/nics/features.rst
> @@ -962,6 +962,16 @@ management (see :doc:`../prog_guide/power_man` for more details).
>  
>  * **[implements] eth_dev_ops**: ``get_monitor_addr``
>  
> +.. _nic_features_tx_queue_used_count:
> +
> +Tx queue count
> +--------------
> +
> +Supports to get the number of used descriptors of a Tx queue.
> +
> +* **[implements] eth_dev_ops**: ``tx_queue_count``.
> +* **[related] API**: ``rte_eth_tx_queue_count()``.
> +
>

Can you please keep the order same with 'default.ini' file,
I recognized there is already some mismatch in order but we can fix them
later.

>  .. _nic_features_other:
>  
>  Other dev ops not represented by a Feature
> diff --git a/doc/guides/nics/features/default.ini b/doc/guides/nics/features/default.ini
> index 806cb033ff..3ef6d45c0e 100644
> --- a/doc/guides/nics/features/default.ini
> +++ b/doc/guides/nics/features/default.ini
> @@ -59,6 +59,7 @@ Packet type parsing  =
>  Timesync             =
>  Rx descriptor status =
>  Tx descriptor status =
> +Tx queue count       =
>

Existing Rx queue count is not documented, if we are documenting this,
can you please add "Rx queue count" in a separate patch?

>  Basic stats          =
>  Extended stats       =
>  Stats per queue      =
> diff --git a/lib/ethdev/ethdev_driver.h b/lib/ethdev/ethdev_driver.h
> index b482cd12bb..f05f68a67c 100644
> --- a/lib/ethdev/ethdev_driver.h
> +++ b/lib/ethdev/ethdev_driver.h
> @@ -58,6 +58,8 @@ struct rte_eth_dev {
>  	eth_rx_queue_count_t rx_queue_count;
>  	/** Check the status of a Rx descriptor */
>  	eth_rx_descriptor_status_t rx_descriptor_status;
> +	/** Get the number of used Tx descriptors */
> +	eth_tx_queue_count_t tx_queue_count;
>  	/** Check the status of a Tx descriptor */
>  	eth_tx_descriptor_status_t tx_descriptor_status;
>  	/** Pointer to PMD transmit mbufs reuse function */
> diff --git a/lib/ethdev/ethdev_private.c b/lib/ethdev/ethdev_private.c
> index a656df293c..626524558a 100644
> --- a/lib/ethdev/ethdev_private.c
> +++ b/lib/ethdev/ethdev_private.c
> @@ -273,6 +273,7 @@ eth_dev_fp_ops_setup(struct rte_eth_fp_ops *fpo,
>  	fpo->tx_pkt_prepare = dev->tx_pkt_prepare;
>  	fpo->rx_queue_count = dev->rx_queue_count;
>  	fpo->rx_descriptor_status = dev->rx_descriptor_status;
> +	fpo->tx_queue_count = dev->tx_queue_count;
>  	fpo->tx_descriptor_status = dev->tx_descriptor_status;
>  	fpo->recycle_tx_mbufs_reuse = dev->recycle_tx_mbufs_reuse;
>  	fpo->recycle_rx_descriptors_refill = dev->recycle_rx_descriptors_refill;
> diff --git a/lib/ethdev/ethdev_trace_points.c b/lib/ethdev/ethdev_trace_points.c
> index 91f71d868b..e618414392 100644
> --- a/lib/ethdev/ethdev_trace_points.c
> +++ b/lib/ethdev/ethdev_trace_points.c
> @@ -481,6 +481,9 @@ RTE_TRACE_POINT_REGISTER(rte_eth_trace_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_eth_trace_tx_queue_count,
> +	lib.ethdev.tx_queue_count)
> +

Can you please group this with 'tx_burst' & 'call_tx_callbacks' above?

>  RTE_TRACE_POINT_REGISTER(rte_flow_trace_copy,
>  	lib.ethdev.flow.copy)
>  
> diff --git a/lib/ethdev/rte_ethdev.h b/lib/ethdev/rte_ethdev.h
> index 21e3a21903..af59da9652 100644
> --- a/lib/ethdev/rte_ethdev.h
> +++ b/lib/ethdev/rte_ethdev.h
> @@ -6803,6 +6803,80 @@ rte_eth_recycle_mbufs(uint16_t rx_port_id, uint16_t rx_queue_id,
>  __rte_experimental
>  int rte_eth_buffer_split_get_supported_hdr_ptypes(uint16_t port_id, uint32_t *ptypes, int num);
>  
> +/**
> + * @warning
> + * @b EXPERIMENTAL: this API may change, or be removed, without prior notice
> + *
> + * Get the number of used descriptors of a Tx queue
> + *
> + * This function retrieves the number of used descriptors of a transmit queue.
> + * Applications can use this API in the fast path to inspect Tx queue occupancy and take
> + * appropriate actions based on the available free descriptors.
> + * An example action could be implementing the Random Early Discard (RED).
>

Above is good, but do you think does it help to mention that intended
usacase is QoS, to address the risk Bruce mentioned?


> + *
> + * Since it's a fast-path function, no check is performed on port_id and
> + * tx_queue_id. The caller must therefore ensure that the port is enabled
> + * and the queue is configured and running.
> + *
> + * @param port_id
> + *   The port identifier of the device.
> + * @param tx_queue_id
> + *   The index of the transmit queue.
> + *   The value must be in the range [0, nb_tx_queue - 1] previously supplied
> + *   to rte_eth_dev_configure().
> + * @return
> + *  The number of used descriptors in the specific queue, or:
> + *   - (-ENODEV) if *port_id* is invalid. Enabled only when RTE_ETHDEV_DEBUG_TX is enabled
> + *   - (-EINVAL) if *queue_id* is invalid. Enabled only when RTE_ETHDEV_DEBUG_TX is enabled
> + *   - (-ENOTSUP) if the device does not support this function.
> + *
> + * @note This function is designed for fast-path use.
> + */
> +__rte_experimental
> +static inline int
> +rte_eth_tx_queue_count(uint16_t port_id, uint16_t tx_queue_id)
> +{
> +	struct rte_eth_fp_ops *fops;
> +	void *qd;
> +	int rc;
> +
> +#ifdef RTE_ETHDEV_DEBUG_TX
> +	if (port_id >= RTE_MAX_ETHPORTS || !rte_eth_dev_is_valid_port(port_id)) {
> +		RTE_ETHDEV_LOG_LINE(ERR, "Invalid port_id=%u", port_id);
> +		rc = -ENODEV;
> +		rte_eth_trace_tx_queue_count(port_id, tx_queue_id, rc);
> +		return rc;
> +	}
> +
> +	rc = -EINVAL;
> +	if (tx_queue_id >= RTE_MAX_QUEUES_PER_PORT) {
> +		RTE_ETHDEV_LOG_LINE(ERR, "Invalid Tx queue_id=%u for port_id=%u",
> +				    tx_queue_id, port_id);
> +		rte_eth_trace_tx_queue_count(port_id, tx_queue_id, rc);
> +		return rc;
> +	}
> +#endif
> +
> +	/* Fetch pointer to Tx queue data */
> +	fops = &rte_eth_fp_ops[port_id];
> +	qd = fops->txq.data[tx_queue_id];
> +
> +#ifdef RTE_ETHDEV_DEBUG_TX
> +	if (qd == NULL) {
> +		RTE_ETHDEV_LOG_LINE(ERR, "Invalid Tx queue_id=%u for port_id=%u",
> +				    tx_queue_id, port_id);
> +		rte_eth_trace_tx_queue_count(port_id, tx_queue_id, rc);
> +		return rc;
> +	}
> +#endif
> +	if (fops->tx_queue_count == NULL)
> +		return -ENOTSUP;
> +
> +	rc = fops->tx_queue_count(qd);
>

Can you please put an empty line here to have a separate block for trace
code?

> +	rte_eth_trace_tx_queue_count(port_id, tx_queue_id, rc);
> +
> +	return rc;
> +}
>  #ifdef __cplusplus
>  }
>  #endif
> diff --git a/lib/ethdev/rte_ethdev_core.h b/lib/ethdev/rte_ethdev_core.h
> index 4bfaf79c6c..d3f09f390d 100644
> --- a/lib/ethdev/rte_ethdev_core.h
> +++ b/lib/ethdev/rte_ethdev_core.h
> @@ -60,6 +60,9 @@ typedef uint16_t (*eth_recycle_tx_mbufs_reuse_t)(void *txq,
>  /** @internal Refill Rx descriptors with the recycling mbufs */
>  typedef void (*eth_recycle_rx_descriptors_refill_t)(void *rxq, uint16_t nb);
>  
> +/** @internal Get number of used descriptors on a transmit queue. */
> +typedef int (*eth_tx_queue_count_t)(void *txq);
> +

Can you please move it above 'tx_descriptor_status', to keep same order
kept in many other locations:
rx_queue_count
rx_descriptor_status
tx_queue_count
tx_descriptor_status


>  /**
>   * @internal
>   * Structure used to hold opaque pointers to internal ethdev Rx/Tx
> @@ -116,7 +119,9 @@ struct rte_eth_fp_ops {
>  	eth_tx_descriptor_status_t tx_descriptor_status;
>  	/** Copy used mbufs from Tx mbuf ring into Rx. */
>  	eth_recycle_tx_mbufs_reuse_t recycle_tx_mbufs_reuse;
> -	uintptr_t reserved2[2];
> +	/** Get the number of used Tx descriptors. */
> +	eth_tx_queue_count_t tx_queue_count;
>

Similarly, can you please move it above 'tx_descriptor_status'?


> +	uintptr_t reserved2[1];
>  	/**@}*/
>  
>  } __rte_cache_aligned;
> diff --git a/lib/ethdev/rte_ethdev_trace_fp.h b/lib/ethdev/rte_ethdev_trace_fp.h
> index 186271c9ff..c98c488433 100644
> --- a/lib/ethdev/rte_ethdev_trace_fp.h
> +++ b/lib/ethdev/rte_ethdev_trace_fp.h
> @@ -73,6 +73,14 @@ RTE_TRACE_POINT_FP(
>  	rte_trace_point_emit_u64(count);
>  )
>  
> +RTE_TRACE_POINT_FP(
> +	rte_eth_trace_tx_queue_count,
> +	RTE_TRACE_POINT_ARGS(uint16_t port_id, uint16_t tx_queue_id, int rc),
> +	rte_trace_point_emit_u16(port_id);
> +	rte_trace_point_emit_u16(tx_queue_id);
> +	rte_trace_point_emit_int(rc);
> +)
> +

Existing 'rx_queue_count' is missing tracepoints, for consistency, can
you please add that too in a separate patch?


>  #ifdef __cplusplus
>  }
>  #endif
> diff --git a/lib/ethdev/version.map b/lib/ethdev/version.map
> index 5c4917c020..e03830902a 100644
> --- a/lib/ethdev/version.map
> +++ b/lib/ethdev/version.map
> @@ -316,6 +316,9 @@ EXPERIMENTAL {
>  	rte_eth_recycle_rx_queue_info_get;
>  	rte_flow_group_set_miss_actions;
>  	rte_flow_calc_table_hash;
> +
> +	# added in 24.03
> +	rte_eth_tx_queue_count;
>  };
>  
>  INTERNAL {