[RFC,v3,1/3] sched: add PIE based congestion management

Message ID 20210621073506.96017-2-wojciechx.liguzinski@intel.com (mailing list archive)
State Superseded, archived
Delegated to: Thomas Monjalon
Headers
Series Add PIE support for HQoS library |

Checks

Context Check Description
ci/checkpatch success coding style OK

Commit Message

Liguzinski, WojciechX June 21, 2021, 7:35 a.m. UTC
  Implement PIE based congestion management based on rfc8033

Signed-off-by: Liguzinski, WojciechX <wojciechx.liguzinski@intel.com>
---
 drivers/net/softnic/rte_eth_softnic_tm.c |   6 +-
 lib/sched/meson.build                    |  10 +-
 lib/sched/rte_pie.c                      |  78 +++++
 lib/sched/rte_pie.h                      | 388 +++++++++++++++++++++++
 lib/sched/rte_sched.c                    | 229 +++++++++----
 lib/sched/rte_sched.h                    |  53 +++-
 6 files changed, 673 insertions(+), 91 deletions(-)
 create mode 100644 lib/sched/rte_pie.c
 create mode 100644 lib/sched/rte_pie.h
  

Comments

Stephen Hemminger June 21, 2021, 6:17 p.m. UTC | #1
On Mon, 21 Jun 2021 08:35:04 +0100
"Liguzinski, WojciechX" <wojciechx.liguzinski@intel.com> wrote:

> +/**
> + * @brief Initialises run-time data
> + *
> + * @param pie [in,out] data pointer to PIE runtime data
> + *
> + * @return Operation status
> + * @retval 0 success
> + * @retval !0 error
> + */
> +int
> +rte_pie_rt_data_init(struct rte_pie *pie);

All the new code needs to be marked experimental.
Why return an error on the init() function, then you are going to
make application check the result and lead to lots more code.

Other places in DPDK use void for init functions.
  
Liguzinski, WojciechX June 22, 2021, 7:39 a.m. UTC | #2
> -----Original Message-----
> From: Stephen Hemminger <stephen@networkplumber.org> 
> Sent: Monday, June 21, 2021 8:18 PM
> To: Liguzinski, WojciechX <wojciechx.liguzinski@intel.com>
> Cc: dev@dpdk.org; Singh, Jasvinder <jasvinder.singh@intel.com>; Dumitrescu, Cristian <cristian.dumitrescu@intel.com>; Dharmappa, Savinay <savinay.dharmappa@intel.com>; Ajmera, Megha <megha.ajmera@intel.com>
> Subject: Re: [dpdk-dev] [RFC PATCH v3 1/3] sched: add PIE based congestion management
>
> On Mon, 21 Jun 2021 08:35:04 +0100
> "Liguzinski, WojciechX" <wojciechx.liguzinski@intel.com> wrote:
>
> > +/**
> > + * @brief Initialises run-time data
> > + *
> > + * @param pie [in,out] data pointer to PIE runtime data
> > + *
> > + * @return Operation status
> > + * @retval 0 success
> > + * @retval !0 error
> > + */
> > +int
> > +rte_pie_rt_data_init(struct rte_pie *pie);
>
> All the new code needs to be marked experimental.
> Why return an error on the init() function, then you are going to make application check the result and lead to lots more code.
>
> Other places in DPDK use void for init functions.

Thanks for comments.
I'll apply necessary updates to V4 of RFC patches.

BR,
Wojciech
  

Patch

diff --git a/drivers/net/softnic/rte_eth_softnic_tm.c b/drivers/net/softnic/rte_eth_softnic_tm.c
index 90baba15ce..5b6c4e6d4b 100644
--- a/drivers/net/softnic/rte_eth_softnic_tm.c
+++ b/drivers/net/softnic/rte_eth_softnic_tm.c
@@ -420,7 +420,7 @@  pmd_tm_node_type_get(struct rte_eth_dev *dev,
 	return 0;
 }
 
-#ifdef RTE_SCHED_RED
+#ifdef RTE_SCHED_AQM
 #define WRED_SUPPORTED						1
 #else
 #define WRED_SUPPORTED						0
@@ -2306,7 +2306,7 @@  tm_tc_wred_profile_get(struct rte_eth_dev *dev, uint32_t tc_id)
 	return NULL;
 }
 
-#ifdef RTE_SCHED_RED
+#ifdef RTE_SCHED_AQM
 
 static void
 wred_profiles_set(struct rte_eth_dev *dev, uint32_t subport_id)
@@ -2321,7 +2321,7 @@  wred_profiles_set(struct rte_eth_dev *dev, uint32_t subport_id)
 	for (tc_id = 0; tc_id < RTE_SCHED_TRAFFIC_CLASSES_PER_PIPE; tc_id++)
 		for (color = RTE_COLOR_GREEN; color < RTE_COLORS; color++) {
 			struct rte_red_params *dst =
-				&pp->red_params[tc_id][color];
+				&pp->wred_params[tc_id][color];
 			struct tm_wred_profile *src_wp =
 				tm_tc_wred_profile_get(dev, tc_id);
 			struct rte_tm_red_params *src =
diff --git a/lib/sched/meson.build b/lib/sched/meson.build
index b24f7b8775..e7ae9bcf19 100644
--- a/lib/sched/meson.build
+++ b/lib/sched/meson.build
@@ -1,11 +1,7 @@ 
 # SPDX-License-Identifier: BSD-3-Clause
 # Copyright(c) 2017 Intel Corporation
 
-sources = files('rte_sched.c', 'rte_red.c', 'rte_approx.c')
-headers = files(
-        'rte_approx.h',
-        'rte_red.h',
-        'rte_sched.h',
-        'rte_sched_common.h',
-)
+sources = files('rte_sched.c', 'rte_red.c', 'rte_approx.c', 'rte_pie.c')
+headers = files('rte_sched.h', 'rte_sched_common.h',
+		'rte_red.h', 'rte_approx.h', 'rte_pie.h')
 deps += ['mbuf', 'meter']
diff --git a/lib/sched/rte_pie.c b/lib/sched/rte_pie.c
new file mode 100644
index 0000000000..f538dda21d
--- /dev/null
+++ b/lib/sched/rte_pie.c
@@ -0,0 +1,78 @@ 
+/* SPDX-License-Identifier: BSD-3-Clause
+ * Copyright(c) 2020 Intel Corporation
+ */
+
+#include <stdlib.h>
+
+#include "rte_pie.h"
+#include <rte_common.h>
+#include <rte_cycles.h>
+
+#ifdef __INTEL_COMPILER
+#pragma warning(disable:2259) /* conversion may lose significant bits */
+#endif
+
+int
+rte_pie_rt_data_init(struct rte_pie *pie)
+{
+	if (pie == NULL)
+		return -1;
+
+	pie->active = 0;
+	pie->in_measurement = 0;
+	pie->departed_bytes_count = 0;
+	pie->start_measurement = 0;
+	pie->last_measurement = 0;
+	pie->qlen = 0;
+	pie->avg_dq_time = 0;
+	pie->burst_allowance = 0;
+	pie->qdelay_old = 0;
+	pie->drop_prob = 0;
+	pie->accu_prob = 0;
+
+	return 0;
+}
+
+int
+rte_pie_config_init(struct rte_pie_config *pie_cfg,
+	const uint16_t qdelay_ref,
+	const uint16_t dp_update_interval,
+	const uint16_t max_burst,
+	const uint16_t tailq_th)
+{
+	uint64_t tsc_hz = rte_get_tsc_hz();
+
+	if (pie_cfg == NULL)
+		return -1;
+
+	if (qdelay_ref <= 0) {
+		RTE_LOG(ERR, SCHED,
+			"%s: Incorrect value for qdelay_ref\n", __func__);
+		return -EINVAL;
+	}
+
+	if (dp_update_interval <= 0) {
+		RTE_LOG(ERR, SCHED,
+			"%s: Incorrect value for dp_update_interval\n", __func__);
+		return -EINVAL;
+	}
+
+	if (max_burst <= 0) {
+		RTE_LOG(ERR, SCHED,
+			"%s: Incorrect value for max_burst\n", __func__);
+		return -EINVAL;
+	}
+
+	if (tailq_th <= 0) {
+		RTE_LOG(ERR, SCHED,
+			"%s: Incorrect value for tailq_th\n", __func__);
+		return -EINVAL;
+	}
+
+	pie_cfg->qdelay_ref = (tsc_hz * qdelay_ref) / 1000;
+	pie_cfg->dp_update_interval = (tsc_hz * dp_update_interval) / 1000;
+	pie_cfg->max_burst = (tsc_hz * max_burst) / 1000;
+	pie_cfg->tailq_th = tailq_th;
+
+	return 0;
+}
diff --git a/lib/sched/rte_pie.h b/lib/sched/rte_pie.h
new file mode 100644
index 0000000000..9295f39c07
--- /dev/null
+++ b/lib/sched/rte_pie.h
@@ -0,0 +1,388 @@ 
+/* SPDX-License-Identifier: BSD-3-Clause
+ * Copyright(c) 2020 Intel Corporation
+ */
+
+#ifndef __RTE_PIE_H_INCLUDED__
+#define __RTE_PIE_H_INCLUDED__
+
+#ifdef __cplusplus
+extern "C" {
+#endif
+
+/**
+ * @file
+ * RTE Proportional Integral controller Enhanced (PIE)
+ *
+ *
+ ***/
+
+#include <stdint.h>
+
+#include <rte_random.h>
+#include <rte_debug.h>
+
+#define RTE_DQ_THRESHOLD   16384   /**< Queue length threshold (2^14)
+				     * to start measurement cycle (bytes)
+				     */
+#define RTE_DQ_WEIGHT      0.25    /**< Weight (RTE_DQ_THRESHOLD/2^16) to compute dequeue rate */
+#define RTE_ALPHA          0.125   /**< Weights in drop probability calculations */
+#define RTE_BETA           1.25    /**< Weights in drop probability calculations */
+#define RTE_RAND_MAX      ~0LLU    /**< Max value of the random number */
+
+
+/**
+ * PIE configuration parameters passed by user
+ *
+ */
+struct rte_pie_params {
+	uint16_t qdelay_ref;           /**< Latency Target (milliseconds) */
+	uint16_t dp_update_interval;   /**< Update interval for drop probability (milliseconds) */
+	uint16_t max_burst;            /**< Max Burst Allowance (milliseconds) */
+	uint16_t tailq_th;             /**< Tailq drop threshold (packet counts) */
+};
+
+/**
+ * PIE configuration parameters
+ *
+ */
+struct rte_pie_config {
+	uint64_t qdelay_ref;           /**< Latency Target (in CPU cycles.) */
+	uint64_t dp_update_interval;   /**< Update interval for drop probability (in CPU cycles) */
+	uint64_t max_burst;            /**< Max Burst Allowance (in CPU cycles.) */
+	uint16_t tailq_th;             /**< Tailq drop threshold (packet counts) */
+};
+
+/**
+ * RED run-time data
+ */
+struct rte_pie {
+	uint16_t active;               /**< Flag for activating/deactivating pie */
+	uint16_t in_measurement;       /**< Flag for activation of measurement cycle */
+	uint32_t departed_bytes_count; /**< Number of bytes departed in current measurement cycle */
+	uint64_t start_measurement;    /**< Time to start to measurement cycle (in cpu cycles) */
+	uint64_t last_measurement;     /**< Time of last measurement (in cpu cycles) */
+	uint64_t qlen;                 /**< Queue length (packets count) */
+	uint64_t qlen_bytes;           /**< Queue length (bytes count) */
+	uint64_t avg_dq_time;          /**< Time averaged dequeue rate (in cpu cycles) */
+	uint32_t burst_allowance;      /**< Current burst allowance (bytes) */
+	uint64_t qdelay_old;           /**< Old queue delay (bytes) */
+	double drop_prob;              /**< Current packet drop probability */
+	double accu_prob;              /**< Accumulated packet drop probability */
+};
+
+/**
+ * @brief Initialises run-time data
+ *
+ * @param pie [in,out] data pointer to PIE runtime data
+ *
+ * @return Operation status
+ * @retval 0 success
+ * @retval !0 error
+ */
+int
+rte_pie_rt_data_init(struct rte_pie *pie);
+
+/**
+ * @brief Configures a single PIE configuration parameter structure.
+ *
+ * @param pie_cfg [in,out] config pointer to a PIE configuration parameter structure
+ * @param qdelay_ref [in]  latency target(milliseconds)
+ * @param dp_update_interval [in] update interval for drop probability (milliseconds)
+ * @param max_burst [in] maximum burst allowance (milliseconds)
+ * @param tailq_th [in] tail drop threshold for the queue (number of packets)
+ *
+ * @return Operation status
+ * @retval 0 success
+ * @retval !0 error
+ */
+int
+rte_pie_config_init(struct rte_pie_config *pie_cfg,
+	const uint16_t qdelay_ref,
+	const uint16_t dp_update_interval,
+	const uint16_t max_burst,
+	const uint16_t tailq_th);
+
+/**
+ * @brief Decides packet enqueue when queue is empty
+ *
+ * Note: packet is never dropped in this particular case.
+ *
+ * @param pie_cfg [in] config pointer to a PIE configuration parameter structure
+ * @param pie [in, out] data pointer to PIE runtime data
+ * @param pkt_len [in] packet length in bytes
+ *
+ * @return Operation status
+ * @retval 0 enqueue the packet
+ * @retval !0 drop the packet
+ */
+static inline int
+rte_pie_enqueue_empty(const struct rte_pie_config *pie_cfg,
+	struct rte_pie *pie,
+	uint32_t pkt_len)
+{
+	RTE_ASSERT(pkt_len != NULL);
+
+	/* Update the PIE qlen parameter */
+	pie->qlen++;
+	pie->qlen_bytes += pkt_len;
+
+	/**
+	 * If the queue has been idle for a while, turn off PIE and Reset counters
+	 */
+	if ((pie->active == 1) &&
+		(pie->qlen < (pie_cfg->tailq_th * 0.1))) {
+		pie->active =  0;
+		pie->in_measurement = 0;
+	}
+
+	return 0;
+}
+
+/**
+ * @brief make a decision to drop or enqueue a packet based on probability
+ *        criteria
+ *
+ * @param pie_cfg [in] config pointer to a PIE configuration parameter structure
+ * @param pie [in, out] data pointer to PIE runtime data
+ * @param time [in] current time (measured in cpu cycles)
+ */
+static inline void
+_calc_drop_probability(const struct rte_pie_config *pie_cfg,
+	struct rte_pie *pie, uint64_t time)
+{
+	uint64_t qdelay_ref = pie_cfg->qdelay_ref;
+
+	/* Note: can be implemented using integer multiply.
+	 * DQ_THRESHOLD is power of 2 value.
+	 */
+	double current_qdelay = pie->qlen * (pie->avg_dq_time / RTE_DQ_THRESHOLD);
+
+	double p = RTE_ALPHA * (current_qdelay - qdelay_ref) +
+		RTE_BETA * (current_qdelay - pie->qdelay_old);
+
+	if (pie->drop_prob < 0.000001)
+		p = p * 0.00048828125;              /* (1/2048) = 0.00048828125 */
+	else if (pie->drop_prob < 0.00001)
+		p = p * 0.001953125;                /* (1/512) = 0.001953125  */
+	else if (pie->drop_prob < 0.0001)
+		p = p * 0.0078125;                  /* (1/128) = 0.0078125  */
+	else if (pie->drop_prob < 0.001)
+		p = p * 0.03125;                    /* (1/32) = 0.03125   */
+	else if (pie->drop_prob < 0.01)
+		p = p * 0.125;                      /* (1/8) = 0.125    */
+	else if (pie->drop_prob < 0.1)
+		p = p * 0.5;                        /* (1/2) = 0.5    */
+
+	if (pie->drop_prob >= 0.1 && p > 0.02)
+		p = 0.02;
+
+	pie->drop_prob += p;
+
+	double qdelay = qdelay_ref * 0.5;
+
+	/*  Exponentially decay drop prob when congestion goes away  */
+	if (current_qdelay < qdelay && pie->qdelay_old < qdelay)
+		pie->drop_prob *= 0.98;     /* 1 - 1/64 is sufficient */
+
+	/* Bound drop probability */
+	if (pie->drop_prob < 0)
+		pie->drop_prob = 0;
+	if (pie->drop_prob > 1)
+		pie->drop_prob = 1;
+
+	pie->qdelay_old = current_qdelay;
+	pie->last_measurement = time;
+
+	uint64_t burst_allowance = pie->burst_allowance - pie_cfg->dp_update_interval;
+
+	pie->burst_allowance = (burst_allowance > 0) ? burst_allowance : 0;
+}
+
+/**
+ * @brief make a decision to drop or enqueue a packet based on probability
+ *        criteria
+ *
+ * @param pie_cfg [in] config pointer to a PIE configuration parameter structure
+ * @param pie [in, out] data pointer to PIE runtime data
+ *
+ * @return operation status
+ * @retval 0 enqueue the packet
+ * @retval 1 drop the packet
+ */
+static inline int
+_rte_pie_drop(const struct rte_pie_config *pie_cfg,
+	struct rte_pie *pie)
+{
+	uint64_t rand_value;
+	double qdelay = pie_cfg->qdelay_ref * 0.5;
+
+	/* PIE is active but the queue is not congested: return 0 */
+	if (((pie->qdelay_old < qdelay) && (pie->drop_prob < 0.2)) ||
+		(pie->qlen <= (pie_cfg->tailq_th * 0.1)))
+		return 0;
+
+	if (pie->drop_prob == 0)
+		pie->accu_prob = 0;
+
+	/* For practical reasons, drop probability can be further scaled according
+	 * to packet size, but one needs to set a bound to avoid unnecessary bias
+	 * Random drop
+	 */
+	pie->accu_prob += pie->drop_prob;
+
+	if (pie->accu_prob < 0.85)
+		return 0;
+
+	if (pie->accu_prob >= 8.5)
+		return 1;
+
+	rand_value = rte_rand()/RTE_RAND_MAX;
+
+	if ((double)rand_value < pie->drop_prob) {
+		pie->accu_prob = 0;
+		return 1;
+	}
+
+	/* No drop */
+	return 0;
+}
+
+/**
+ * @brief Decides if new packet should be enqeued or dropped for non-empty queue
+ *
+ * @param pie_cfg [in] config pointer to a PIE configuration parameter structure
+ * @param pie [in,out] data pointer to PIE runtime data
+ * @param pkt_len [in] packet length in bytes
+ * @param time [in] current time (measured in cpu cycles)
+ *
+ * @return Operation status
+ * @retval 0 enqueue the packet
+ * @retval 1 drop the packet based on max threshold criterion
+ * @retval 2 drop the packet based on mark probability criterion
+ */
+static inline int
+rte_pie_enqueue_nonempty(const struct rte_pie_config *pie_cfg,
+	struct rte_pie *pie,
+	uint32_t pkt_len,
+	const uint64_t time)
+{
+	/* Check queue space against the tail drop threshold */
+	if (pie->qlen >= pie_cfg->tailq_th) {
+
+		pie->accu_prob = 0;
+		return 1;
+	}
+
+	if (pie->active) {
+		/* Update drop probability after certain interval */
+		if ((time - pie->last_measurement) >= pie_cfg->dp_update_interval)
+			_calc_drop_probability(pie_cfg, pie, time);
+
+		/* Decide whether packet to be dropped or enqueued */
+		if (_rte_pie_drop(pie_cfg, pie) && pie->burst_allowance == 0)
+			return 2;
+	}
+
+	/* When queue occupancy is over a certain threshold, turn on PIE */
+	if ((pie->active == 0) &&
+		(pie->qlen >= (pie_cfg->tailq_th * 0.1))) {
+		pie->active = 1;
+		pie->qdelay_old = 0;
+		pie->drop_prob = 0;
+		pie->in_measurement = 1;
+		pie->departed_bytes_count = 0;
+		pie->avg_dq_time = 0;
+		pie->last_measurement = time;
+		pie->burst_allowance = pie_cfg->max_burst;
+		pie->accu_prob = 0;
+		pie->start_measurement = time;
+	}
+
+	/* when queue has been idle for a while, turn off PIE and Reset counters */
+	if (pie->active == 1 &&
+		pie->qlen < (pie_cfg->tailq_th * 0.1)) {
+		pie->active =  0;
+		pie->in_measurement = 0;
+	}
+
+	/* Update PIE qlen parameter */
+	pie->qlen++;
+	pie->qlen_bytes += pkt_len;
+
+	/* No drop */
+	return 0;
+}
+
+/**
+ * @brief Decides if new packet should be enqeued or dropped
+ * Updates run time data and gives verdict whether to enqueue or drop the packet.
+ *
+ * @param pie_cfg [in] config pointer to a PIE configuration parameter structure
+ * @param pie [in,out] data pointer to PIE runtime data
+ * @param pkt_len [in] packet length in bytes
+ * @param time [in] current time stamp (measured in cpu cycles)
+ *
+ * @return Operation status
+ * @retval 0 enqueue the packet
+ * @retval 1 drop the packet based on drop probility criteria
+ */
+static inline int
+rte_pie_enqueue(const struct rte_pie_config *pie_cfg,
+	struct rte_pie *pie,
+	const unsigned int qlen,
+	uint32_t pkt_len,
+	const uint64_t time)
+{
+	RTE_ASSERT(pie_cfg != NULL);
+	RTE_ASSERT(pie != NULL);
+
+	if (qlen != 0)
+		return rte_pie_enqueue_nonempty(pie_cfg, pie, pkt_len, time);
+	else
+		return rte_pie_enqueue_empty(pie_cfg, pie, pkt_len);
+}
+
+/**
+ * @brief PIE rate estimation method
+ * Called on each packet departure.
+ *
+ * @param pie [in] data pointer to PIE runtime data
+ * @param pkt_len [in] packet length in bytes
+ * @param time [in] current time stamp in cpu cycles
+ */
+static inline void
+rte_pie_dequeue(struct rte_pie *pie,
+	uint32_t pkt_len,
+	uint64_t time)
+{
+	/* Dequeue rate estimation */
+	if (pie->in_measurement) {
+		pie->departed_bytes_count += pkt_len;
+
+		/* Start a new measurement cycle when enough packets */
+		if (pie->departed_bytes_count >= RTE_DQ_THRESHOLD) {
+			uint64_t dq_time = time - pie->start_measurement;
+
+			if (pie->avg_dq_time == 0)
+				pie->avg_dq_time = dq_time;
+			else
+				pie->avg_dq_time = dq_time * RTE_DQ_WEIGHT + pie->avg_dq_time
+					* (1 - RTE_DQ_WEIGHT);
+
+			pie->in_measurement = 0;
+		}
+	}
+
+	/* Start measurement cycle when enough data in the queue */
+	if ((pie->qlen_bytes >= RTE_DQ_THRESHOLD) && (pie->in_measurement == 0)) {
+		pie->in_measurement = 1;
+		pie->start_measurement = time;
+		pie->departed_bytes_count = 0;
+	}
+}
+
+#ifdef __cplusplus
+}
+#endif
+
+#endif /* __RTE_PIE_H_INCLUDED__ */
diff --git a/lib/sched/rte_sched.c b/lib/sched/rte_sched.c
index cd87e688e4..afda39caf5 100644
--- a/lib/sched/rte_sched.c
+++ b/lib/sched/rte_sched.c
@@ -89,8 +89,12 @@  struct rte_sched_queue {
 
 struct rte_sched_queue_extra {
 	struct rte_sched_queue_stats stats;
-#ifdef RTE_SCHED_RED
-	struct rte_red red;
+#ifdef RTE_SCHED_AQM
+	RTE_STD_C11
+	union {
+		struct rte_red red;
+		struct rte_pie pie;
+	};
 #endif
 };
 
@@ -183,8 +187,13 @@  struct rte_sched_subport {
 	/* Pipe queues size */
 	uint16_t qsize[RTE_SCHED_TRAFFIC_CLASSES_PER_PIPE];
 
-#ifdef RTE_SCHED_RED
-	struct rte_red_config red_config[RTE_SCHED_TRAFFIC_CLASSES_PER_PIPE][RTE_COLORS];
+	enum rte_sched_aqm_mode aqm;
+#ifdef RTE_SCHED_AQM
+	RTE_STD_C11
+	union {
+		struct rte_red_config wred_config[RTE_SCHED_TRAFFIC_CLASSES_PER_PIPE][RTE_COLORS];
+		struct rte_pie_config pie_config[RTE_SCHED_TRAFFIC_CLASSES_PER_PIPE];
+	};
 #endif
 
 	/* Scheduling loop detection */
@@ -1078,6 +1087,91 @@  rte_sched_free_memory(struct rte_sched_port *port, uint32_t n_subports)
 	rte_free(port);
 }
 
+#ifdef RTE_SCHED_AQM
+
+static int
+rte_sched_red_config(struct rte_sched_port *port,
+	struct rte_sched_subport *s,
+	struct rte_sched_subport_params *params,
+	uint32_t n_subports)
+{
+	uint32_t i;
+
+	for (i = 0; i < RTE_SCHED_TRAFFIC_CLASSES_PER_PIPE; i++) {
+
+		uint32_t j;
+
+		for (j = 0; j < RTE_COLORS; j++) {
+			/* if min/max are both zero, then RED is disabled */
+			if ((params->wred_params[i][j].min_th |
+				 params->wred_params[i][j].max_th) == 0) {
+				continue;
+			}
+
+			if (rte_red_config_init(&s->wred_config[i][j],
+				params->wred_params[i][j].wq_log2,
+				params->wred_params[i][j].min_th,
+				params->wred_params[i][j].max_th,
+				params->wred_params[i][j].maxp_inv) != 0) {
+				rte_sched_free_memory(port, n_subports);
+
+				RTE_LOG(NOTICE, SCHED,
+				"%s: RED configuration init fails\n", __func__);
+				return -EINVAL;
+			}
+		}
+	}
+	s->aqm = RTE_SCHED_AQM_WRED;
+	return 0;
+}
+
+static int
+rte_sched_pie_config(struct rte_sched_port *port,
+	struct rte_sched_subport *s,
+	struct rte_sched_subport_params *params,
+	uint32_t n_subports)
+{
+	uint32_t i;
+
+	for (i = 0; i < RTE_SCHED_TRAFFIC_CLASSES_PER_PIPE; i++) {
+		if (params->pie_params[i].tailq_th > params->qsize[i]) {
+			RTE_LOG(NOTICE, SCHED,
+			"%s: PIE tailq threshold incorrect\n", __func__);
+			return -EINVAL;
+		}
+
+		if (rte_pie_config_init(&s->pie_config[i],
+			params->pie_params[i].qdelay_ref,
+			params->pie_params[i].dp_update_interval,
+			params->pie_params[i].max_burst,
+			params->pie_params[i].tailq_th) != 0) {
+			rte_sched_free_memory(port, n_subports);
+
+			RTE_LOG(NOTICE, SCHED,
+			"%s: PIE configuration init fails\n", __func__);
+			return -EINVAL;
+			}
+	}
+	s->aqm = RTE_SCHED_AQM_PIE;
+	return 0;
+}
+
+static int
+rte_sched_aqm_config(struct rte_sched_port *port,
+	struct rte_sched_subport *s,
+	struct rte_sched_subport_params *params,
+	uint32_t n_subports)
+{
+	if (params->aqm == RTE_SCHED_AQM_WRED)
+		return rte_sched_red_config(port, s, params, n_subports);
+
+	else if (params->aqm == RTE_SCHED_AQM_PIE)
+		return rte_sched_pie_config(port, s, params, n_subports);
+
+	return -EINVAL;
+}
+#endif
+
 int
 rte_sched_subport_config(struct rte_sched_port *port,
 	uint32_t subport_id,
@@ -1169,30 +1263,11 @@  rte_sched_subport_config(struct rte_sched_port *port,
 		s->n_pipe_profiles = params->n_pipe_profiles;
 		s->n_max_pipe_profiles = params->n_max_pipe_profiles;
 
-#ifdef RTE_SCHED_RED
-		for (i = 0; i < RTE_SCHED_TRAFFIC_CLASSES_PER_PIPE; i++) {
-			uint32_t j;
-
-			for (j = 0; j < RTE_COLORS; j++) {
-			/* if min/max are both zero, then RED is disabled */
-				if ((params->red_params[i][j].min_th |
-				     params->red_params[i][j].max_th) == 0) {
-					continue;
-				}
-
-				if (rte_red_config_init(&s->red_config[i][j],
-				    params->red_params[i][j].wq_log2,
-				    params->red_params[i][j].min_th,
-				    params->red_params[i][j].max_th,
-				    params->red_params[i][j].maxp_inv) != 0) {
-					rte_sched_free_memory(port, n_subports);
-
-					RTE_LOG(NOTICE, SCHED,
-					"%s: RED configuration init fails\n",
-					__func__);
-					return -EINVAL;
-				}
-			}
+#ifdef RTE_SCHED_AQM
+		status = rte_sched_aqm_config(port, s, params, n_subports);
+		if (status) {
+			RTE_LOG(NOTICE, SCHED, "%s: AQM configuration fails\n", __func__);
+			return status;
 		}
 #endif
 
@@ -1714,29 +1789,20 @@  rte_sched_port_update_subport_stats(struct rte_sched_port *port,
 	subport->stats.n_bytes_tc[tc_index] += pkt_len;
 }
 
-#ifdef RTE_SCHED_RED
 static inline void
 rte_sched_port_update_subport_stats_on_drop(struct rte_sched_port *port,
 	struct rte_sched_subport *subport,
 	uint32_t qindex,
 	struct rte_mbuf *pkt,
-	uint32_t red)
-#else
-static inline void
-rte_sched_port_update_subport_stats_on_drop(struct rte_sched_port *port,
-	struct rte_sched_subport *subport,
-	uint32_t qindex,
-	struct rte_mbuf *pkt,
-	__rte_unused uint32_t red)
-#endif
+	__rte_unused uint32_t drops)
 {
 	uint32_t tc_index = rte_sched_port_pipe_tc(port, qindex);
 	uint32_t pkt_len = pkt->pkt_len;
 
 	subport->stats.n_pkts_tc_dropped[tc_index] += 1;
 	subport->stats.n_bytes_tc_dropped[tc_index] += pkt_len;
-#ifdef RTE_SCHED_RED
-	subport->stats.n_pkts_red_dropped[tc_index] += red;
+#ifdef RTE_SCHED_AQM
+	subport->stats.n_pkts_aqm_dropped[tc_index] += drops;
 #endif
 }
 
@@ -1752,58 +1818,61 @@  rte_sched_port_update_queue_stats(struct rte_sched_subport *subport,
 	qe->stats.n_bytes += pkt_len;
 }
 
-#ifdef RTE_SCHED_RED
-static inline void
-rte_sched_port_update_queue_stats_on_drop(struct rte_sched_subport *subport,
-	uint32_t qindex,
-	struct rte_mbuf *pkt,
-	uint32_t red)
-#else
 static inline void
 rte_sched_port_update_queue_stats_on_drop(struct rte_sched_subport *subport,
 	uint32_t qindex,
 	struct rte_mbuf *pkt,
-	__rte_unused uint32_t red)
-#endif
+	__rte_unused uint32_t drops)
 {
 	struct rte_sched_queue_extra *qe = subport->queue_extra + qindex;
 	uint32_t pkt_len = pkt->pkt_len;
 
 	qe->stats.n_pkts_dropped += 1;
 	qe->stats.n_bytes_dropped += pkt_len;
-#ifdef RTE_SCHED_RED
-	qe->stats.n_pkts_red_dropped += red;
+#ifdef RTE_SCHED_AQM
+	qe->stats.n_pkts_aqm_dropped += drops;
 #endif
 }
 
 #endif /* RTE_SCHED_COLLECT_STATS */
 
-#ifdef RTE_SCHED_RED
+#ifdef RTE_SCHED_AQM
 
 static inline int
-rte_sched_port_red_drop(struct rte_sched_port *port,
+rte_sched_port_aqm_drop(struct rte_sched_port *port,
 	struct rte_sched_subport *subport,
 	struct rte_mbuf *pkt,
 	uint32_t qindex,
 	uint16_t qlen)
 {
 	struct rte_sched_queue_extra *qe;
-	struct rte_red_config *red_cfg;
-	struct rte_red *red;
 	uint32_t tc_index;
-	enum rte_color color;
 
 	tc_index = rte_sched_port_pipe_tc(port, qindex);
-	color = rte_sched_port_pkt_read_color(pkt);
-	red_cfg = &subport->red_config[tc_index][color];
+	qe = subport->queue_extra + qindex;
 
-	if ((red_cfg->min_th | red_cfg->max_th) == 0)
-		return 0;
+	/* WRED */
+	if (subport->aqm == RTE_SCHED_AQM_WRED) {
+		struct rte_red_config *red_cfg;
+		struct rte_red *red;
+		enum rte_color color;
 
-	qe = subport->queue_extra + qindex;
-	red = &qe->red;
+		color = rte_sched_port_pkt_read_color(pkt);
+		red_cfg = &subport->wred_config[tc_index][color];
+
+		if ((red_cfg->min_th | red_cfg->max_th) == 0)
+			return 0;
 
-	return rte_red_enqueue(red_cfg, red, qlen, port->time);
+		red = &qe->red;
+
+		return rte_red_enqueue(red_cfg, red, qlen, port->time);
+	}
+
+	/* PIE */
+	struct rte_pie_config *pie_cfg = &subport->pie_config[tc_index];
+	struct rte_pie *pie = &qe->pie;
+
+	return rte_pie_enqueue(pie_cfg, pie, pkt->pkt_len, qlen, port->time_cpu_cycles);
 }
 
 static inline void
@@ -1811,14 +1880,29 @@  rte_sched_port_set_queue_empty_timestamp(struct rte_sched_port *port,
 	struct rte_sched_subport *subport, uint32_t qindex)
 {
 	struct rte_sched_queue_extra *qe = subport->queue_extra + qindex;
-	struct rte_red *red = &qe->red;
+	if (subport->aqm == RTE_SCHED_AQM_WRED) {
+		struct rte_red *red = &qe->red;
+
+		rte_red_mark_queue_empty(red, port->time);
+	}
+}
+
+static inline void
+rte_sched_port_pie_dequeue(struct rte_sched_subport *subport,
+uint32_t qindex, uint32_t pkt_len, uint64_t time) {
+	struct rte_sched_queue_extra *qe = subport->queue_extra + qindex;
+	struct rte_pie *pie = &qe->pie;
 
-	rte_red_mark_queue_empty(red, port->time);
+	/* Update queue length */
+	pie->qlen -= 1;
+	pie->qlen_bytes -= pkt_len;
+
+	rte_pie_dequeue(pie, pkt_len, time);
 }
 
 #else
 
-static inline int rte_sched_port_red_drop(struct rte_sched_port *port __rte_unused,
+static inline int rte_sched_port_aqm_drop(struct rte_sched_port *port __rte_unused,
 	struct rte_sched_subport *subport __rte_unused,
 	struct rte_mbuf *pkt __rte_unused,
 	uint32_t qindex __rte_unused,
@@ -1829,7 +1913,7 @@  static inline int rte_sched_port_red_drop(struct rte_sched_port *port __rte_unus
 
 #define rte_sched_port_set_queue_empty_timestamp(port, subport, qindex)
 
-#endif /* RTE_SCHED_RED */
+#endif /* RTE_SCHED_AQM */
 
 #ifdef RTE_SCHED_DEBUG
 
@@ -1925,7 +2009,7 @@  rte_sched_port_enqueue_qwa(struct rte_sched_port *port,
 	qlen = q->qw - q->qr;
 
 	/* Drop the packet (and update drop stats) when queue is full */
-	if (unlikely(rte_sched_port_red_drop(port, subport, pkt, qindex, qlen) ||
+	if (unlikely(rte_sched_port_aqm_drop(port, subport, pkt, qindex, qlen) ||
 		     (qlen >= qsize))) {
 		rte_pktmbuf_free(pkt);
 #ifdef RTE_SCHED_COLLECT_STATS
@@ -2398,6 +2482,7 @@  grinder_schedule(struct rte_sched_port *port,
 {
 	struct rte_sched_grinder *grinder = subport->grinder + pos;
 	struct rte_sched_queue *queue = grinder->queue[grinder->qpos];
+	uint32_t qindex = grinder->qindex[grinder->qpos];
 	struct rte_mbuf *pkt = grinder->pkt;
 	uint32_t pkt_len = pkt->pkt_len + port->frame_overhead;
 	uint32_t be_tc_active;
@@ -2417,15 +2502,19 @@  grinder_schedule(struct rte_sched_port *port,
 		(pkt_len * grinder->wrr_cost[grinder->qpos]) & be_tc_active;
 
 	if (queue->qr == queue->qw) {
-		uint32_t qindex = grinder->qindex[grinder->qpos];
-
 		rte_bitmap_clear(subport->bmp, qindex);
 		grinder->qmask &= ~(1 << grinder->qpos);
 		if (be_tc_active)
 			grinder->wrr_mask[grinder->qpos] = 0;
+
 		rte_sched_port_set_queue_empty_timestamp(port, subport, qindex);
 	}
 
+#ifdef RTE_SCHED_AQM
+	if (subport->aqm == RTE_SCHED_AQM_PIE)
+		rte_sched_port_pie_dequeue(subport, qindex, pkt_len, port->time_cpu_cycles);
+#endif
+
 	/* Reset pipe loop detection */
 	subport->pipe_loop = RTE_SCHED_PIPE_INVALID;
 	grinder->productive = 1;
diff --git a/lib/sched/rte_sched.h b/lib/sched/rte_sched.h
index c1a772b70c..a5fe6266cd 100644
--- a/lib/sched/rte_sched.h
+++ b/lib/sched/rte_sched.h
@@ -61,9 +61,10 @@  extern "C" {
 #include <rte_mbuf.h>
 #include <rte_meter.h>
 
-/** Random Early Detection (RED) */
-#ifdef RTE_SCHED_RED
+/** Active Queue Management */
+#ifdef RTE_SCHED_AQM
 #include "rte_red.h"
+#include "rte_pie.h"
 #endif
 
 /** Maximum number of queues per pipe.
@@ -110,6 +111,28 @@  extern "C" {
 #define RTE_SCHED_FRAME_OVERHEAD_DEFAULT      24
 #endif
 
+/**
+ * Active Queue Management (AQM) mode
+ *
+ * This is used for controlling the admission of packets into a packet queue or
+ * group of packet queues on congestion.
+ *
+ * The *Random Early Detection (RED)* algorithm works by proactively dropping
+ * more and more input packets as the queue occupancy builds up. When the queue
+ * is full or almost full, RED effectively works as *tail drop*. The *Weighted
+ * RED* algorithm uses a separate set of RED thresholds for each packet color.
+ *
+ * Similar to RED, Proportional Integral Controller Enhanced (PIE) randomly
+ * drops a packet at the onset of the congestion and tries to control the
+ * latency around the target value. The congestion detection, however, is based
+ * on the queueing latency instead of the queue length like RED. For more
+ * information, refer RFC8033.
+ */
+enum rte_sched_aqm_mode {
+	RTE_SCHED_AQM_WRED, /**< Weighted Random Early Detection (WRED) */
+	RTE_SCHED_AQM_PIE,  /**< Proportional Integral Controller Enhanced (PIE) */
+};
+
 /*
  * Pipe configuration parameters. The period and credits_per_period
  * parameters are measured in bytes, with one byte meaning the time
@@ -174,9 +197,17 @@  struct rte_sched_subport_params {
 	/** Max allowed profiles in the pipe profile table */
 	uint32_t n_max_pipe_profiles;
 
-#ifdef RTE_SCHED_RED
-	/** RED parameters */
-	struct rte_red_params red_params[RTE_SCHED_TRAFFIC_CLASSES_PER_PIPE][RTE_COLORS];
+#ifdef RTE_SCHED_AQM
+	/** Active Queue Management mode */
+	enum rte_sched_aqm_mode aqm;
+
+	RTE_STD_C11
+	union {
+		/** WRED parameters */
+		struct rte_red_params wred_params[RTE_SCHED_TRAFFIC_CLASSES_PER_PIPE][RTE_COLORS];
+		/** PIE parameters */
+		struct rte_pie_params pie_params[RTE_SCHED_TRAFFIC_CLASSES_PER_PIPE];
+	};
 #endif
 };
 
@@ -208,9 +239,9 @@  struct rte_sched_subport_stats {
 	/** Number of bytes dropped for each traffic class */
 	uint64_t n_bytes_tc_dropped[RTE_SCHED_TRAFFIC_CLASSES_PER_PIPE];
 
-#ifdef RTE_SCHED_RED
-	/** Number of packets dropped by red */
-	uint64_t n_pkts_red_dropped[RTE_SCHED_TRAFFIC_CLASSES_PER_PIPE];
+#ifdef RTE_SCHED_AQM
+	/** Number of packets dropped by active queue management scheme */
+	uint64_t n_pkts_aqm_dropped[RTE_SCHED_TRAFFIC_CLASSES_PER_PIPE];
 #endif
 };
 
@@ -222,9 +253,9 @@  struct rte_sched_queue_stats {
 	/** Packets dropped */
 	uint64_t n_pkts_dropped;
 
-#ifdef RTE_SCHED_RED
-	/** Packets dropped by RED */
-	uint64_t n_pkts_red_dropped;
+#ifdef RTE_SCHED_AQM
+	/** Packets dropped by active queue management scheme */
+	uint64_t n_pkts_aqm_dropped;
 #endif
 
 	/** Bytes successfully written */