[v2,1/3] eal: add lcore poll busyness telemetry

Message ID 20220824162442.631456-2-kevin.laatz@intel.com (mailing list archive)
State Superseded, archived
Headers
Series Add lcore poll busyness telemetry |

Checks

Context Check Description
ci/checkpatch warning coding style issues

Commit Message

Kevin Laatz Aug. 24, 2022, 4:24 p.m. UTC
  From: Anatoly Burakov <anatoly.burakov@intel.com>

Currently, there is no way to measure lcore busyness in a passive way,
without any modifications to the application. This patch adds a new EAL
API that will be able to passively track core busyness.

The busyness is calculated by relying on the fact that most DPDK API's
will poll for packets. Empty polls can be counted as "idle", while
non-empty polls can be counted as busy. To measure lcore busyness, we
simply call the telemetry timestamping function with the number of polls
a particular code section has processed, and count the number of cycles
we've spent processing empty bursts. The more empty bursts we encounter,
the less cycles we spend in "busy" state, and the less core busyness
will be reported.

In order for all of the above to work without modifications to the
application, the library code needs to be instrumented with calls to
the lcore telemetry busyness timestamping function. The following parts
of DPDK are instrumented with lcore telemetry calls:

- All major driver API's:
  - ethdev
  - cryptodev
  - compressdev
  - regexdev
  - bbdev
  - rawdev
  - eventdev
  - dmadev
- Some additional libraries:
  - ring
  - distributor

To avoid performance impact from having lcore telemetry support, a
global variable is exported by EAL, and a call to timestamping function
is wrapped into a macro, so that whenever telemetry is disabled, it only
takes one additional branch and no function calls are performed. It is
also possible to disable it at compile time by commenting out
RTE_LCORE_BUSYNESS from build config.

This patch also adds a telemetry endpoint to report lcore busyness, as
well as telemetry endpoints to enable/disable lcore telemetry.

Signed-off-by: Kevin Laatz <kevin.laatz@intel.com>
Signed-off-by: Conor Walsh <conor.walsh@intel.com>
Signed-off-by: David Hunt <david.hunt@intel.com>
Signed-off-by: Anatoly Burakov <anatoly.burakov@intel.com>

---
v2:
  * Use rte_get_tsc_hz() to adjust the telemetry period
  * Rename to reflect polling busyness vs general busyness
  * Fix segfault when calling telemetry timestamp from an unregistered
    non-EAL thread.
  * Minor cleanup
---
 config/meson.build                          |   1 +
 config/rte_config.h                         |   1 +
 lib/bbdev/rte_bbdev.h                       |  17 +-
 lib/compressdev/rte_compressdev.c           |   2 +
 lib/cryptodev/rte_cryptodev.h               |   2 +
 lib/distributor/rte_distributor.c           |  21 +-
 lib/distributor/rte_distributor_single.c    |  14 +-
 lib/dmadev/rte_dmadev.h                     |  15 +-
 lib/eal/common/eal_common_lcore_telemetry.c | 293 ++++++++++++++++++++
 lib/eal/common/meson.build                  |   1 +
 lib/eal/include/rte_lcore.h                 |  80 ++++++
 lib/eal/meson.build                         |   3 +
 lib/eal/version.map                         |   7 +
 lib/ethdev/rte_ethdev.h                     |   2 +
 lib/eventdev/rte_eventdev.h                 |  10 +-
 lib/rawdev/rte_rawdev.c                     |   5 +-
 lib/regexdev/rte_regexdev.h                 |   5 +-
 lib/ring/rte_ring_elem_pvt.h                |   1 +
 meson_options.txt                           |   2 +
 19 files changed, 458 insertions(+), 24 deletions(-)
 create mode 100644 lib/eal/common/eal_common_lcore_telemetry.c
  

Patch

diff --git a/config/meson.build b/config/meson.build
index 7f7b6c92fd..d5954a059c 100644
--- a/config/meson.build
+++ b/config/meson.build
@@ -297,6 +297,7 @@  endforeach
 dpdk_conf.set('RTE_MAX_ETHPORTS', get_option('max_ethports'))
 dpdk_conf.set('RTE_LIBEAL_USE_HPET', get_option('use_hpet'))
 dpdk_conf.set('RTE_ENABLE_TRACE_FP', get_option('enable_trace_fp'))
+dpdk_conf.set('RTE_LCORE_POLL_BUSYNESS', get_option('enable_lcore_poll_busyness'))
 # values which have defaults which may be overridden
 dpdk_conf.set('RTE_MAX_VFIO_GROUPS', 64)
 dpdk_conf.set('RTE_DRIVER_MEMPOOL_BUCKET_SIZE_KB', 64)
diff --git a/config/rte_config.h b/config/rte_config.h
index 46549cb062..498702c9c7 100644
--- a/config/rte_config.h
+++ b/config/rte_config.h
@@ -39,6 +39,7 @@ 
 #define RTE_LOG_DP_LEVEL RTE_LOG_INFO
 #define RTE_BACKTRACE 1
 #define RTE_MAX_VFIO_CONTAINERS 64
+#define RTE_LCORE_POLL_BUSYNESS_PERIOD_MS 2
 
 /* bsd module defines */
 #define RTE_CONTIGMEM_MAX_NUM_BUFS 64
diff --git a/lib/bbdev/rte_bbdev.h b/lib/bbdev/rte_bbdev.h
index b88c88167e..d6ed176cce 100644
--- a/lib/bbdev/rte_bbdev.h
+++ b/lib/bbdev/rte_bbdev.h
@@ -28,6 +28,7 @@  extern "C" {
 #include <stdbool.h>
 
 #include <rte_cpuflags.h>
+#include <rte_lcore.h>
 
 #include "rte_bbdev_op.h"
 
@@ -599,7 +600,9 @@  rte_bbdev_dequeue_enc_ops(uint16_t dev_id, uint16_t queue_id,
 {
 	struct rte_bbdev *dev = &rte_bbdev_devices[dev_id];
 	struct rte_bbdev_queue_data *q_data = &dev->data->queues[queue_id];
-	return dev->dequeue_enc_ops(q_data, ops, num_ops);
+	const uint16_t nb_ops = dev->dequeue_enc_ops(q_data, ops, num_ops);
+	RTE_LCORE_TELEMETRY_TIMESTAMP(nb_ops);
+	return nb_ops;
 }
 
 /**
@@ -631,7 +634,9 @@  rte_bbdev_dequeue_dec_ops(uint16_t dev_id, uint16_t queue_id,
 {
 	struct rte_bbdev *dev = &rte_bbdev_devices[dev_id];
 	struct rte_bbdev_queue_data *q_data = &dev->data->queues[queue_id];
-	return dev->dequeue_dec_ops(q_data, ops, num_ops);
+	const uint16_t nb_ops = dev->dequeue_dec_ops(q_data, ops, num_ops);
+	RTE_LCORE_TELEMETRY_TIMESTAMP(nb_ops);
+	return nb_ops;
 }
 
 
@@ -662,7 +667,9 @@  rte_bbdev_dequeue_ldpc_enc_ops(uint16_t dev_id, uint16_t queue_id,
 {
 	struct rte_bbdev *dev = &rte_bbdev_devices[dev_id];
 	struct rte_bbdev_queue_data *q_data = &dev->data->queues[queue_id];
-	return dev->dequeue_ldpc_enc_ops(q_data, ops, num_ops);
+	const uint16_t nb_ops = dev->dequeue_ldpc_enc_ops(q_data, ops, num_ops);
+	RTE_LCORE_TELEMETRY_TIMESTAMP(nb_ops);
+	return nb_ops;
 }
 
 /**
@@ -692,7 +699,9 @@  rte_bbdev_dequeue_ldpc_dec_ops(uint16_t dev_id, uint16_t queue_id,
 {
 	struct rte_bbdev *dev = &rte_bbdev_devices[dev_id];
 	struct rte_bbdev_queue_data *q_data = &dev->data->queues[queue_id];
-	return dev->dequeue_ldpc_dec_ops(q_data, ops, num_ops);
+	const uint16_t nb_ops = dev->dequeue_ldpc_dec_ops(q_data, ops, num_ops);
+	RTE_LCORE_TELEMETRY_TIMESTAMP(nb_ops);
+	return nb_ops;
 }
 
 /** Definitions of device event types */
diff --git a/lib/compressdev/rte_compressdev.c b/lib/compressdev/rte_compressdev.c
index 22c438f2dd..912cee9a16 100644
--- a/lib/compressdev/rte_compressdev.c
+++ b/lib/compressdev/rte_compressdev.c
@@ -580,6 +580,8 @@  rte_compressdev_dequeue_burst(uint8_t dev_id, uint16_t qp_id,
 	nb_ops = (*dev->dequeue_burst)
 			(dev->data->queue_pairs[qp_id], ops, nb_ops);
 
+	RTE_LCORE_TELEMETRY_TIMESTAMP(nb_ops);
+
 	return nb_ops;
 }
 
diff --git a/lib/cryptodev/rte_cryptodev.h b/lib/cryptodev/rte_cryptodev.h
index 56f459c6a0..072874020d 100644
--- a/lib/cryptodev/rte_cryptodev.h
+++ b/lib/cryptodev/rte_cryptodev.h
@@ -1915,6 +1915,8 @@  rte_cryptodev_dequeue_burst(uint8_t dev_id, uint16_t qp_id,
 		rte_rcu_qsbr_thread_offline(list->qsbr, 0);
 	}
 #endif
+
+	RTE_LCORE_TELEMETRY_TIMESTAMP(nb_ops);
 	return nb_ops;
 }
 
diff --git a/lib/distributor/rte_distributor.c b/lib/distributor/rte_distributor.c
index 3035b7a999..35b0d8d36b 100644
--- a/lib/distributor/rte_distributor.c
+++ b/lib/distributor/rte_distributor.c
@@ -56,6 +56,8 @@  rte_distributor_request_pkt(struct rte_distributor *d,
 
 		while (rte_rdtsc() < t)
 			rte_pause();
+		/* this was an empty poll */
+		RTE_LCORE_TELEMETRY_TIMESTAMP(0);
 	}
 
 	/*
@@ -134,24 +136,29 @@  rte_distributor_get_pkt(struct rte_distributor *d,
 
 	if (unlikely(d->alg_type == RTE_DIST_ALG_SINGLE)) {
 		if (return_count <= 1) {
+			uint16_t cnt;
 			pkts[0] = rte_distributor_get_pkt_single(d->d_single,
-				worker_id, return_count ? oldpkt[0] : NULL);
-			return (pkts[0]) ? 1 : 0;
-		} else
-			return -EINVAL;
+								 worker_id,
+								 return_count ? oldpkt[0] : NULL);
+			cnt = (pkts[0] != NULL) ? 1 : 0;
+			RTE_LCORE_TELEMETRY_TIMESTAMP(cnt);
+			return cnt;
+		}
+		return -EINVAL;
 	}
 
 	rte_distributor_request_pkt(d, worker_id, oldpkt, return_count);
 
-	count = rte_distributor_poll_pkt(d, worker_id, pkts);
-	while (count == -1) {
+	while ((count = rte_distributor_poll_pkt(d, worker_id, pkts)) == -1) {
 		uint64_t t = rte_rdtsc() + 100;
 
 		while (rte_rdtsc() < t)
 			rte_pause();
 
-		count = rte_distributor_poll_pkt(d, worker_id, pkts);
+		/* this was an empty poll */
+		RTE_LCORE_TELEMETRY_TIMESTAMP(0);
 	}
+	RTE_LCORE_TELEMETRY_TIMESTAMP(count);
 	return count;
 }
 
diff --git a/lib/distributor/rte_distributor_single.c b/lib/distributor/rte_distributor_single.c
index 2c77ac454a..dc58791bf4 100644
--- a/lib/distributor/rte_distributor_single.c
+++ b/lib/distributor/rte_distributor_single.c
@@ -31,8 +31,13 @@  rte_distributor_request_pkt_single(struct rte_distributor_single *d,
 	union rte_distributor_buffer_single *buf = &d->bufs[worker_id];
 	int64_t req = (((int64_t)(uintptr_t)oldpkt) << RTE_DISTRIB_FLAG_BITS)
 			| RTE_DISTRIB_GET_BUF;
-	RTE_WAIT_UNTIL_MASKED(&buf->bufptr64, RTE_DISTRIB_FLAGS_MASK,
-		==, 0, __ATOMIC_RELAXED);
+
+	while (!(__atomic_load_n(&buf->bufptr64, __ATOMIC_RELAXED)
+			& RTE_DISTRIB_FLAGS_MASK) == 0) {
+		rte_pause();
+		/* this was an empty poll */
+		RTE_LCORE_TELEMETRY_TIMESTAMP(0);
+	}
 
 	/* Sync with distributor on GET_BUF flag. */
 	__atomic_store_n(&(buf->bufptr64), req, __ATOMIC_RELEASE);
@@ -59,8 +64,11 @@  rte_distributor_get_pkt_single(struct rte_distributor_single *d,
 {
 	struct rte_mbuf *ret;
 	rte_distributor_request_pkt_single(d, worker_id, oldpkt);
-	while ((ret = rte_distributor_poll_pkt_single(d, worker_id)) == NULL)
+	while ((ret = rte_distributor_poll_pkt_single(d, worker_id)) == NULL) {
 		rte_pause();
+		/* this was an empty poll */
+		RTE_LCORE_TELEMETRY_TIMESTAMP(0);
+	}
 	return ret;
 }
 
diff --git a/lib/dmadev/rte_dmadev.h b/lib/dmadev/rte_dmadev.h
index e7f992b734..98176a6a7a 100644
--- a/lib/dmadev/rte_dmadev.h
+++ b/lib/dmadev/rte_dmadev.h
@@ -149,6 +149,7 @@ 
 #include <rte_bitops.h>
 #include <rte_common.h>
 #include <rte_compat.h>
+#include <rte_lcore.h>
 
 #ifdef __cplusplus
 extern "C" {
@@ -1027,7 +1028,7 @@  rte_dma_completed(int16_t dev_id, uint16_t vchan, const uint16_t nb_cpls,
 		  uint16_t *last_idx, bool *has_error)
 {
 	struct rte_dma_fp_object *obj = &rte_dma_fp_objs[dev_id];
-	uint16_t idx;
+	uint16_t idx, nb_ops;
 	bool err;
 
 #ifdef RTE_DMADEV_DEBUG
@@ -1050,8 +1051,10 @@  rte_dma_completed(int16_t dev_id, uint16_t vchan, const uint16_t nb_cpls,
 		has_error = &err;
 
 	*has_error = false;
-	return (*obj->completed)(obj->dev_private, vchan, nb_cpls, last_idx,
-				 has_error);
+	nb_ops = (*obj->completed)(obj->dev_private, vchan, nb_cpls, last_idx,
+				   has_error);
+	RTE_LCORE_TELEMETRY_TIMESTAMP(nb_ops);
+	return nb_ops;
 }
 
 /**
@@ -1090,7 +1093,7 @@  rte_dma_completed_status(int16_t dev_id, uint16_t vchan,
 			 enum rte_dma_status_code *status)
 {
 	struct rte_dma_fp_object *obj = &rte_dma_fp_objs[dev_id];
-	uint16_t idx;
+	uint16_t idx, nb_ops;
 
 #ifdef RTE_DMADEV_DEBUG
 	if (!rte_dma_is_valid(dev_id) || nb_cpls == 0 || status == NULL)
@@ -1101,8 +1104,10 @@  rte_dma_completed_status(int16_t dev_id, uint16_t vchan,
 	if (last_idx == NULL)
 		last_idx = &idx;
 
-	return (*obj->completed_status)(obj->dev_private, vchan, nb_cpls,
+	nb_ops = (*obj->completed_status)(obj->dev_private, vchan, nb_cpls,
 					last_idx, status);
+	RTE_LCORE_TELEMETRY_TIMESTAMP(nb_ops);
+	return nb_ops;
 }
 
 /**
diff --git a/lib/eal/common/eal_common_lcore_telemetry.c b/lib/eal/common/eal_common_lcore_telemetry.c
new file mode 100644
index 0000000000..e6b58788c8
--- /dev/null
+++ b/lib/eal/common/eal_common_lcore_telemetry.c
@@ -0,0 +1,293 @@ 
+/* SPDX-License-Identifier: BSD-3-Clause
+ * Copyright(c) 2010-2014 Intel Corporation
+ */
+
+#include <unistd.h>
+#include <limits.h>
+#include <string.h>
+
+#include <rte_common.h>
+#include <rte_cycles.h>
+#include <rte_errno.h>
+#include <rte_lcore.h>
+
+#ifdef RTE_LCORE_POLL_BUSYNESS
+#include <rte_telemetry.h>
+#endif
+
+int __rte_lcore_telemetry_enabled;
+
+#ifdef RTE_LCORE_POLL_BUSYNESS
+
+struct lcore_telemetry {
+	int busyness;
+	/**< Calculated busyness (gets set/returned by the API) */
+	int raw_busyness;
+	/**< Calculated busyness times 100. */
+	uint64_t interval_ts;
+	/**< when previous telemetry interval started */
+	uint64_t empty_cycles;
+	/**< empty cycle count since last interval */
+	uint64_t last_poll_ts;
+	/**< last poll timestamp */
+	bool last_empty;
+	/**< if last poll was empty */
+	unsigned int contig_poll_cnt;
+	/**< contiguous (always empty/non empty) poll counter */
+} __rte_cache_aligned;
+
+static struct lcore_telemetry *telemetry_data;
+
+#define LCORE_POLL_BUSYNESS_MAX 100
+#define LCORE_POLL_BUSYNESS_NOT_SET -1
+#define LCORE_POLL_BUSYNESS_MIN 0
+
+#define SMOOTH_COEFF 5
+#define STATE_CHANGE_OPT 32
+
+static void lcore_config_init(void)
+{
+	int lcore_id;
+
+	telemetry_data = calloc(RTE_MAX_LCORE, sizeof(telemetry_data[0]));
+	if (telemetry_data == NULL)
+		rte_panic("Could not init lcore telemetry data: Out of memory\n");
+
+	RTE_LCORE_FOREACH(lcore_id) {
+		struct lcore_telemetry *td = &telemetry_data[lcore_id];
+
+		td->interval_ts = 0;
+		td->last_poll_ts = 0;
+		td->empty_cycles = 0;
+		td->last_empty = true;
+		td->contig_poll_cnt = 0;
+		td->busyness = LCORE_POLL_BUSYNESS_NOT_SET;
+		td->raw_busyness = 0;
+	}
+}
+
+int rte_lcore_poll_busyness(unsigned int lcore_id)
+{
+	const uint64_t active_thresh = rte_get_tsc_hz() * RTE_LCORE_POLL_BUSYNESS_PERIOD_MS;
+	struct lcore_telemetry *tdata;
+
+	if (lcore_id >= RTE_MAX_LCORE)
+		return -EINVAL;
+	tdata = &telemetry_data[lcore_id];
+
+	/* if the lcore is not active */
+	if (tdata->interval_ts == 0)
+		return LCORE_POLL_BUSYNESS_NOT_SET;
+	/* if the core hasn't been active in a while */
+	else if ((rte_rdtsc() - tdata->interval_ts) > active_thresh)
+		return LCORE_POLL_BUSYNESS_NOT_SET;
+
+	/* this core is active, report its busyness */
+	return telemetry_data[lcore_id].busyness;
+}
+
+int rte_lcore_poll_busyness_enabled(void)
+{
+	return __rte_lcore_telemetry_enabled;
+}
+
+void rte_lcore_poll_busyness_enabled_set(int enable)
+{
+	__rte_lcore_telemetry_enabled = !!enable;
+
+	if (!enable)
+		lcore_config_init();
+}
+
+static inline int calc_raw_busyness(const struct lcore_telemetry *tdata,
+				    const uint64_t empty, const uint64_t total)
+{
+	/*
+	 * we don't want to use floating point math here, but we want for our
+	 * busyness to react smoothly to sudden changes, while still keeping the
+	 * accuracy and making sure that over time the average follows busyness
+	 * as measured just-in-time. therefore, we will calculate the average
+	 * busyness using integer math, but shift the decimal point two places
+	 * to the right, so that 100.0 becomes 10000. this allows us to report
+	 * integer values (0..100) while still allowing ourselves to follow the
+	 * just-in-time measurements when we calculate our averages.
+	 */
+	const int max_raw_idle = LCORE_POLL_BUSYNESS_MAX * 100;
+
+	/*
+	 * at upper end of the busyness scale, going up from 90->100 will take
+	 * longer than going from 10->20 because of the averaging. to address
+	 * this, we invert the scale when doing calculations: that is, we
+	 * effectively calculate average *idle* cycle percentage, not average
+	 * *busy* cycle percentage. this means that the scale is naturally
+	 * biased towards fast scaling up, and slow scaling down.
+	 */
+	const int prev_raw_idle = max_raw_idle - tdata->raw_busyness;
+
+	/* calculate rate of idle cycles, times 100 */
+	const int cur_raw_idle = (int)((empty * max_raw_idle) / total);
+
+	/* smoothen the idleness */
+	const int smoothened_idle =
+			(cur_raw_idle + prev_raw_idle * (SMOOTH_COEFF - 1)) / SMOOTH_COEFF;
+
+	/* convert idleness back to busyness */
+	return max_raw_idle - smoothened_idle;
+}
+
+void __rte_lcore_telemetry_timestamp(uint16_t nb_rx)
+{
+	const unsigned int lcore_id = rte_lcore_id();
+	uint64_t interval_ts, empty_cycles, cur_tsc, last_poll_ts;
+	struct lcore_telemetry *tdata;
+	const bool empty = nb_rx == 0;
+	uint64_t diff_int, diff_last;
+	bool last_empty;
+
+	/* This telemetry is not supported for unregistered non-EAL threads */
+	if (lcore_id >= RTE_MAX_LCORE)
+		return;
+
+	tdata = &telemetry_data[lcore_id];
+	last_empty = tdata->last_empty;
+
+	/* optimization: don't do anything if status hasn't changed */
+	if (last_empty == empty && tdata->contig_poll_cnt++ < STATE_CHANGE_OPT)
+		return;
+	/* status changed or we're waiting for too long, reset counter */
+	tdata->contig_poll_cnt = 0;
+
+	cur_tsc = rte_rdtsc();
+
+	interval_ts = tdata->interval_ts;
+	empty_cycles = tdata->empty_cycles;
+	last_poll_ts = tdata->last_poll_ts;
+
+	diff_int = cur_tsc - interval_ts;
+	diff_last = cur_tsc - last_poll_ts;
+
+	/* is this the first time we're here? */
+	if (interval_ts == 0) {
+		tdata->busyness = LCORE_POLL_BUSYNESS_MIN;
+		tdata->raw_busyness = 0;
+		tdata->interval_ts = cur_tsc;
+		tdata->empty_cycles = 0;
+		tdata->contig_poll_cnt = 0;
+		goto end;
+	}
+
+	/* update the empty counter if we got an empty poll earlier */
+	if (last_empty)
+		empty_cycles += diff_last;
+
+	/* have we passed the interval? */
+	uint64_t interval = ((rte_get_tsc_hz() / MS_PER_S) * RTE_LCORE_POLL_BUSYNESS_PERIOD_MS);
+	if (diff_int > interval) {
+		int raw_busyness;
+
+		/* get updated busyness value */
+		raw_busyness = calc_raw_busyness(tdata, empty_cycles, diff_int);
+
+		/* set a new interval, reset empty counter */
+		tdata->interval_ts = cur_tsc;
+		tdata->empty_cycles = 0;
+		tdata->raw_busyness = raw_busyness;
+		/* bring busyness back to 0..100 range, biased to round up */
+		tdata->busyness = (raw_busyness + 50) / 100;
+	} else
+		/* we may have updated empty counter */
+		tdata->empty_cycles = empty_cycles;
+
+end:
+	/* update status for next poll */
+	tdata->last_poll_ts = cur_tsc;
+	tdata->last_empty = empty;
+}
+
+static int
+lcore_poll_busyness_enable(const char *cmd __rte_unused,
+		      const char *params __rte_unused,
+		      struct rte_tel_data *d)
+{
+	rte_lcore_poll_busyness_enabled_set(1);
+
+	rte_tel_data_start_dict(d);
+
+	rte_tel_data_add_dict_int(d, "poll_busyness_enabled", 1);
+
+	return 0;
+}
+
+static int
+lcore_poll_busyness_disable(const char *cmd __rte_unused,
+		       const char *params __rte_unused,
+		       struct rte_tel_data *d)
+{
+	rte_lcore_poll_busyness_enabled_set(0);
+
+	rte_tel_data_start_dict(d);
+
+	rte_tel_data_add_dict_int(d, "poll_busyness_enabled", 0);
+
+	if (telemetry_data != NULL)
+		free(telemetry_data);
+
+	return 0;
+}
+
+static int
+lcore_handle_poll_busyness(const char *cmd __rte_unused,
+		      const char *params __rte_unused, struct rte_tel_data *d)
+{
+	char corenum[64];
+	int i;
+
+	rte_tel_data_start_dict(d);
+
+	RTE_LCORE_FOREACH(i) {
+		if (!rte_lcore_is_enabled(i))
+			continue;
+		snprintf(corenum, sizeof(corenum), "%d", i);
+		rte_tel_data_add_dict_int(d, corenum, rte_lcore_poll_busyness(i));
+	}
+
+	return 0;
+}
+
+RTE_INIT(lcore_init_telemetry)
+{
+	__rte_lcore_telemetry_enabled = true;
+
+	lcore_config_init();
+
+	rte_telemetry_register_cmd("/eal/lcore/busyness", lcore_handle_poll_busyness,
+				   "return percentage poll busyness of cores");
+
+	rte_telemetry_register_cmd("/eal/lcore/busyness_enable", lcore_poll_busyness_enable,
+				   "enable lcore poll busyness measurement");
+
+	rte_telemetry_register_cmd("/eal/lcore/busyness_disable", lcore_poll_busyness_disable,
+				   "disable lcore poll busyness measurement");
+}
+
+#else
+
+int rte_lcore_poll_busyness(unsigned int lcore_id __rte_unused)
+{
+	return -ENOTSUP;
+}
+
+int rte_lcore_poll_busyness_enabled(void)
+{
+	return -ENOTSUP;
+}
+
+void rte_lcore_poll_busyness_enabled_set(int enable __rte_unused)
+{
+}
+
+void __rte_lcore_telemetry_timestamp(uint16_t nb_rx __rte_unused)
+{
+}
+
+#endif
diff --git a/lib/eal/common/meson.build b/lib/eal/common/meson.build
index 917758cc65..a743e66a7d 100644
--- a/lib/eal/common/meson.build
+++ b/lib/eal/common/meson.build
@@ -17,6 +17,7 @@  sources += files(
         'eal_common_hexdump.c',
         'eal_common_interrupts.c',
         'eal_common_launch.c',
+        'eal_common_lcore_telemetry.c',
         'eal_common_lcore.c',
         'eal_common_log.c',
         'eal_common_mcfg.c',
diff --git a/lib/eal/include/rte_lcore.h b/lib/eal/include/rte_lcore.h
index b598e1b9ec..75c1f874cb 100644
--- a/lib/eal/include/rte_lcore.h
+++ b/lib/eal/include/rte_lcore.h
@@ -415,6 +415,86 @@  rte_ctrl_thread_create(pthread_t *thread, const char *name,
 		const pthread_attr_t *attr,
 		void *(*start_routine)(void *), void *arg);
 
+/**
+ * @warning
+ * @b EXPERIMENTAL: this API may change without prior notice.
+ *
+ * Read poll busyness value corresponding to an lcore.
+ *
+ * @param lcore_id
+ *   Lcore to read poll busyness value for.
+ * @return
+ *   - value between 0 and 100 on success
+ *   - -1 if lcore is not active
+ *   - -EINVAL if lcore is invalid
+ *   - -ENOMEM if not enough memory available
+ *   - -ENOTSUP if not supported
+ */
+__rte_experimental
+int
+rte_lcore_poll_busyness(unsigned int lcore_id);
+
+/**
+ * @warning
+ * @b EXPERIMENTAL: this API may change without prior notice.
+ *
+ * Check if lcore poll busyness telemetry is enabled.
+ *
+ * @return
+ *   - 1 if lcore telemetry is enabled
+ *   - 0 if lcore telemetry is disabled
+ *   - -ENOTSUP if not lcore telemetry supported
+ */
+__rte_experimental
+int
+rte_lcore_poll_busyness_enabled(void);
+
+/**
+ * @warning
+ * @b EXPERIMENTAL: this API may change without prior notice.
+ *
+ * Enable or disable poll busyness telemetry.
+ *
+ * @param enable
+ *   1 to enable, 0 to disable
+ */
+__rte_experimental
+void
+rte_lcore_poll_busyness_enabled_set(int enable);
+
+/**
+ * @warning
+ * @b EXPERIMENTAL: this API may change without prior notice.
+ *
+ * Lcore telemetry timestamping function.
+ *
+ * @param nb_rx
+ *   Number of buffers processed by lcore.
+ */
+__rte_experimental
+void
+__rte_lcore_telemetry_timestamp(uint16_t nb_rx);
+
+/** @internal lcore telemetry enabled status */
+extern int __rte_lcore_telemetry_enabled;
+
+/**
+ * Call lcore telemetry timestamp function.
+ *
+ * @param nb_rx
+ *   Number of buffers processed by lcore.
+ */
+#ifdef RTE_LCORE_POLL_BUSYNESS
+#define RTE_LCORE_TELEMETRY_TIMESTAMP(nb_rx)                    \
+	do {                                                    \
+		if (__rte_lcore_telemetry_enabled)              \
+			__rte_lcore_telemetry_timestamp(nb_rx); \
+	} while (0)
+#else
+#define RTE_LCORE_TELEMETRY_TIMESTAMP(nb_rx) \
+	while (0)
+#endif
+
 #ifdef __cplusplus
 }
 #endif
diff --git a/lib/eal/meson.build b/lib/eal/meson.build
index 056beb9461..7199aa03c2 100644
--- a/lib/eal/meson.build
+++ b/lib/eal/meson.build
@@ -25,6 +25,9 @@  subdir(arch_subdir)
 deps += ['kvargs']
 if not is_windows
     deps += ['telemetry']
+else
+	# core busyness telemetry depends on telemetry library
+	dpdk_conf.set('RTE_LCORE_BUSYNESS', false)
 endif
 if dpdk_conf.has('RTE_USE_LIBBSD')
     ext_deps += libbsd
diff --git a/lib/eal/version.map b/lib/eal/version.map
index c2a2cebf69..8a4af7e937 100644
--- a/lib/eal/version.map
+++ b/lib/eal/version.map
@@ -424,6 +424,13 @@  EXPERIMENTAL {
 	rte_thread_self;
 	rte_thread_set_affinity_by_id;
 	rte_thread_set_priority;
+
+	# added in 22.11
+	__rte_lcore_telemetry_timestamp;
+	__rte_lcore_telemetry_enabled;
+	rte_lcore_poll_busyness;
+	rte_lcore_poll_busyness_enabled;
+	rte_lcore_poll_busyness_enabled_set;
 };
 
 INTERNAL {
diff --git a/lib/ethdev/rte_ethdev.h b/lib/ethdev/rte_ethdev.h
index de9e970d4d..1caecd5a11 100644
--- a/lib/ethdev/rte_ethdev.h
+++ b/lib/ethdev/rte_ethdev.h
@@ -5675,6 +5675,8 @@  rte_eth_rx_burst(uint16_t port_id, uint16_t queue_id,
 #endif
 
 	rte_ethdev_trace_rx_burst(port_id, queue_id, (void **)rx_pkts, nb_rx);
+
+	RTE_LCORE_TELEMETRY_TIMESTAMP(nb_rx);
 	return nb_rx;
 }
 
diff --git a/lib/eventdev/rte_eventdev.h b/lib/eventdev/rte_eventdev.h
index 6a6f6ea4c1..a1d42d9214 100644
--- a/lib/eventdev/rte_eventdev.h
+++ b/lib/eventdev/rte_eventdev.h
@@ -2153,6 +2153,7 @@  rte_event_dequeue_burst(uint8_t dev_id, uint8_t port_id, struct rte_event ev[],
 			uint16_t nb_events, uint64_t timeout_ticks)
 {
 	const struct rte_event_fp_ops *fp_ops;
+	uint16_t nb_evts;
 	void *port;
 
 	fp_ops = &rte_event_fp_ops[dev_id];
@@ -2175,10 +2176,13 @@  rte_event_dequeue_burst(uint8_t dev_id, uint8_t port_id, struct rte_event ev[],
 	 * requests nb_events as const one
 	 */
 	if (nb_events == 1)
-		return (fp_ops->dequeue)(port, ev, timeout_ticks);
+		nb_evts = (fp_ops->dequeue)(port, ev, timeout_ticks);
 	else
-		return (fp_ops->dequeue_burst)(port, ev, nb_events,
-					       timeout_ticks);
+		nb_evts = (fp_ops->dequeue_burst)(port, ev, nb_events,
+					timeout_ticks);
+
+	RTE_LCORE_TELEMETRY_TIMESTAMP(nb_evts);
+	return nb_evts;
 }
 
 #define RTE_EVENT_DEV_MAINT_OP_FLUSH          (1 << 0)
diff --git a/lib/rawdev/rte_rawdev.c b/lib/rawdev/rte_rawdev.c
index 2f0a4f132e..27163e87cb 100644
--- a/lib/rawdev/rte_rawdev.c
+++ b/lib/rawdev/rte_rawdev.c
@@ -226,12 +226,15 @@  rte_rawdev_dequeue_buffers(uint16_t dev_id,
 			   rte_rawdev_obj_t context)
 {
 	struct rte_rawdev *dev;
+	int nb_ops;
 
 	RTE_RAWDEV_VALID_DEVID_OR_ERR_RET(dev_id, -EINVAL);
 	dev = &rte_rawdevs[dev_id];
 
 	RTE_FUNC_PTR_OR_ERR_RET(*dev->dev_ops->dequeue_bufs, -ENOTSUP);
-	return (*dev->dev_ops->dequeue_bufs)(dev, buffers, count, context);
+	nb_ops = (*dev->dev_ops->dequeue_bufs)(dev, buffers, count, context);
+	RTE_LCORE_TELEMETRY_TIMESTAMP(nb_ops);
+	return nb_ops;
 }
 
 int
diff --git a/lib/regexdev/rte_regexdev.h b/lib/regexdev/rte_regexdev.h
index 3bce8090f6..781055b4eb 100644
--- a/lib/regexdev/rte_regexdev.h
+++ b/lib/regexdev/rte_regexdev.h
@@ -1530,6 +1530,7 @@  rte_regexdev_dequeue_burst(uint8_t dev_id, uint16_t qp_id,
 			   struct rte_regex_ops **ops, uint16_t nb_ops)
 {
 	struct rte_regexdev *dev = &rte_regex_devices[dev_id];
+	uint16_t deq_ops;
 #ifdef RTE_LIBRTE_REGEXDEV_DEBUG
 	RTE_REGEXDEV_VALID_DEV_ID_OR_ERR_RET(dev_id, -EINVAL);
 	RTE_FUNC_PTR_OR_ERR_RET(*dev->dequeue, -ENOTSUP);
@@ -1538,7 +1539,9 @@  rte_regexdev_dequeue_burst(uint8_t dev_id, uint16_t qp_id,
 		return -EINVAL;
 	}
 #endif
-	return (*dev->dequeue)(dev, qp_id, ops, nb_ops);
+	deq_ops = (*dev->dequeue)(dev, qp_id, ops, nb_ops);
+	RTE_LCORE_TELEMETRY_TIMESTAMP(deq_ops);
+	return deq_ops;
 }
 
 #ifdef __cplusplus
diff --git a/lib/ring/rte_ring_elem_pvt.h b/lib/ring/rte_ring_elem_pvt.h
index 83788c56e6..6db09d4291 100644
--- a/lib/ring/rte_ring_elem_pvt.h
+++ b/lib/ring/rte_ring_elem_pvt.h
@@ -379,6 +379,7 @@  __rte_ring_do_dequeue_elem(struct rte_ring *r, void *obj_table,
 end:
 	if (available != NULL)
 		*available = entries - n;
+	RTE_LCORE_TELEMETRY_TIMESTAMP(n);
 	return n;
 }
 
diff --git a/meson_options.txt b/meson_options.txt
index 7c220ad68d..725b851f69 100644
--- a/meson_options.txt
+++ b/meson_options.txt
@@ -20,6 +20,8 @@  option('enable_driver_sdk', type: 'boolean', value: false, description:
        'Install headers to build drivers.')
 option('enable_kmods', type: 'boolean', value: false, description:
        'build kernel modules')
+option('enable_lcore_poll_busyness', type: 'boolean', value: true, description:
+       'enable collection of lcore poll busyness telemetry')
 option('examples', type: 'string', value: '', description:
        'Comma-separated list of examples to build by default')
 option('flexran_sdk', type: 'string', value: '', description: