From mboxrd@z Thu Jan 1 00:00:00 1970 Return-Path: Received: from mails.dpdk.org (mails.dpdk.org [217.70.189.124]) by inbox.dpdk.org (Postfix) with ESMTP id 138F4A00C3; Mon, 19 Sep 2022 12:19:31 +0200 (CEST) Received: from [217.70.189.124] (localhost [127.0.0.1]) by mails.dpdk.org (Postfix) with ESMTP id AA3D340E0F; Mon, 19 Sep 2022 12:19:30 +0200 (CEST) Received: from szxga02-in.huawei.com (szxga02-in.huawei.com [45.249.212.188]) by mails.dpdk.org (Postfix) with ESMTP id 365D240141 for ; Mon, 19 Sep 2022 12:19:28 +0200 (CEST) Received: from dggpeml500023.china.huawei.com (unknown [172.30.72.56]) by szxga02-in.huawei.com (SkyGuard) with ESMTP id 4MWLBs5Dn3zMn2m; Mon, 19 Sep 2022 18:14:45 +0800 (CST) Received: from fraeml712-chm.china.huawei.com (10.206.15.61) by dggpeml500023.china.huawei.com (7.185.36.114) with Microsoft SMTP Server (version=TLS1_2, cipher=TLS_ECDHE_RSA_WITH_AES_128_GCM_SHA256) id 15.1.2375.31; Mon, 19 Sep 2022 18:19:24 +0800 Received: from fraeml712-chm.china.huawei.com ([10.206.15.61]) by fraeml712-chm.china.huawei.com ([10.206.15.61]) with mapi id 15.01.2375.031; Mon, 19 Sep 2022 12:19:23 +0200 From: Konstantin Ananyev To: Kevin Laatz , "dev@dpdk.org" CC: "anatoly.burakov@intel.com" , Conor Walsh , David Hunt , Bruce Richardson , Nicolas Chautru , Fan Zhang , Ashish Gupta , Akhil Goyal , Fengchengwen , "Ray Kinsella" , Thomas Monjalon , Ferruh Yigit , Andrew Rybchenko , Jerin Jacob , Sachin Saxena , Hemant Agrawal , Ori Kam , "Honnappa Nagarahalli" , Konstantin Ananyev Subject: RE: [PATCH v7 1/4] eal: add lcore poll busyness telemetry Thread-Topic: [PATCH v7 1/4] eal: add lcore poll busyness telemetry Thread-Index: AQHYyBwnq1Rf9qaPr0irR9A4hv15eq3mcjuw Date: Mon, 19 Sep 2022 10:19:22 +0000 Message-ID: <9a6fec15f9684d21bb4730596cceacff@huawei.com> References: <24c49429394294cfbf0d9c506b205029bac77c8b.1657890378.git.anatoly.burakov@intel.com> <20220914092929.1159773-1-kevin.laatz@intel.com> <20220914092929.1159773-2-kevin.laatz@intel.com> In-Reply-To: <20220914092929.1159773-2-kevin.laatz@intel.com> Accept-Language: en-US Content-Language: en-US X-MS-Has-Attach: X-MS-TNEF-Correlator: x-originating-ip: [10.206.138.42] Content-Type: text/plain; charset="us-ascii" Content-Transfer-Encoding: quoted-printable MIME-Version: 1.0 X-CFilter-Loop: Reflected X-BeenThere: dev@dpdk.org X-Mailman-Version: 2.1.29 Precedence: list List-Id: DPDK patches and discussions List-Unsubscribe: , List-Archive: List-Post: List-Help: List-Subscribe: , Errors-To: dev-bounces@dpdk.org Hi everyone, >=20 > From: Anatoly Burakov >=20 > Currently, there is no way to measure lcore poll busyness in a passive wa= y, > without any modifications to the application. This patch adds a new EAL A= PI > that will be able to passively track core polling busyness. >=20 > The poll busyness is calculated by relying on the fact that most DPDK API= 's > will poll for work (packets, completions, eventdev events, etc). Empty > polls can be counted as "idle", while non-empty polls can be counted as > busy. To measure lcore poll 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 empt= y > bursts. The more empty bursts we encounter, the less cycles we spend in > "busy" state, and the less core poll busyness will be reported. >=20 > 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 DP= DK > are instrumented with lcore poll busyness timestamping calls: >=20 > - All major driver API's: > - ethdev > - cryptodev > - compressdev > - regexdev > - bbdev > - rawdev > - eventdev > - dmadev > - Some additional libraries: > - ring > - distributor >=20 > To avoid performance impact from having lcore telemetry support, a global > variable is exported by EAL, and a call to timestamping function is wrapp= ed > into a macro, so that whenever telemetry is disabled, it only takes one > additional branch and no function calls are performed. It is disabled at > compile time by default. >=20 > This patch also adds a telemetry endpoint to report lcore poll busyness, = as > well as telemetry endpoints to enable/disable lcore telemetry. A > documentation entry has been added to the howto guides to explain the usa= ge > of the new telemetry endpoints and API. As was already mentioned by other reviewers, it would be much better to let application itself decide when it is idle and when it is busy. With current approach even for constant polling run-to-completion model the= re are plenty of opportunities to get things wrong and provide misleading stat= istics. My special concern - inserting it into ring dequeue code. Ring is used for various different things, not only pass packets between th= reads (mempool, etc.). Blindly assuming that ring dequeue returns empty means idle cycles seams wr= ong to me. Which make me wonder should we really hard-code these calls into DPDK core = functions? If you still like to introduce such stats, might be better to implement it = via callback mechanism. As I remember nearly all our drivers (net, crypto, etc.) do support it. That way our generic code will remain unaffected, plus user will have abi= lity to enable/disable it on a per device basis. =20 Konstantin > Signed-off-by: Kevin Laatz > Signed-off-by: Conor Walsh > Signed-off-by: David Hunt > Signed-off-by: Anatoly Burakov >=20 > --- > v7: > * Rename funcs, vars, files to include "poll" where missing. >=20 > v5: > * Fix Windows build > * Make lcore_telemetry_free() an internal interface > * Minor cleanup >=20 > v4: > * Fix doc build > * Rename timestamp macro to RTE_LCORE_POLL_BUSYNESS_TIMESTAMP > * Make enable/disable read and write atomic > * Change rte_lcore_poll_busyness_enabled_set() param to bool > * Move mem alloc from enable/disable to init/cleanup > * Other minor fixes >=20 > v3: > * Fix missed renaming to poll busyness > * Fix clang compilation > * Fix arm compilation >=20 > 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 +- > .../common/eal_common_lcore_poll_telemetry.c | 303 ++++++++++++++++++ > lib/eal/common/meson.build | 1 + > lib/eal/freebsd/eal.c | 1 + > lib/eal/include/rte_lcore.h | 85 ++++- > lib/eal/linux/eal.c | 1 + > 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 | 6 +- > lib/regexdev/rte_regexdev.h | 5 +- > lib/ring/rte_ring_elem_pvt.h | 1 + > meson_options.txt | 2 + > 21 files changed, 475 insertions(+), 25 deletions(-) > create mode 100644 lib/eal/common/eal_common_lcore_poll_telemetry.c >=20 > 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_b= usyness')) > # 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 ae56a86394..86ac3b8a6e 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 >=20 > /* 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..d6a98d3f11 100644 > --- a/lib/bbdev/rte_bbdev.h > +++ b/lib/bbdev/rte_bbdev.h > @@ -28,6 +28,7 @@ extern "C" { > #include >=20 > #include > +#include >=20 > #include "rte_bbdev_op.h" >=20 > @@ -599,7 +600,9 @@ rte_bbdev_dequeue_enc_ops(uint16_t dev_id, uint16_t q= ueue_id, > { > struct rte_bbdev *dev =3D &rte_bbdev_devices[dev_id]; > struct rte_bbdev_queue_data *q_data =3D &dev->data->queues[queue_id]; > - return dev->dequeue_enc_ops(q_data, ops, num_ops); > + const uint16_t nb_ops =3D dev->dequeue_enc_ops(q_data, ops, num_ops); > + RTE_LCORE_POLL_BUSYNESS_TIMESTAMP(nb_ops); > + return nb_ops; > } >=20 > /** > @@ -631,7 +634,9 @@ rte_bbdev_dequeue_dec_ops(uint16_t dev_id, uint16_t q= ueue_id, > { > struct rte_bbdev *dev =3D &rte_bbdev_devices[dev_id]; > struct rte_bbdev_queue_data *q_data =3D &dev->data->queues[queue_id]; > - return dev->dequeue_dec_ops(q_data, ops, num_ops); > + const uint16_t nb_ops =3D dev->dequeue_dec_ops(q_data, ops, num_ops); > + RTE_LCORE_POLL_BUSYNESS_TIMESTAMP(nb_ops); > + return nb_ops; > } >=20 >=20 > @@ -662,7 +667,9 @@ rte_bbdev_dequeue_ldpc_enc_ops(uint16_t dev_id, uint1= 6_t queue_id, > { > struct rte_bbdev *dev =3D &rte_bbdev_devices[dev_id]; > struct rte_bbdev_queue_data *q_data =3D &dev->data->queues[queue_id]; > - return dev->dequeue_ldpc_enc_ops(q_data, ops, num_ops); > + const uint16_t nb_ops =3D dev->dequeue_ldpc_enc_ops(q_data, ops, num_op= s); > + RTE_LCORE_POLL_BUSYNESS_TIMESTAMP(nb_ops); > + return nb_ops; > } >=20 > /** > @@ -692,7 +699,9 @@ rte_bbdev_dequeue_ldpc_dec_ops(uint16_t dev_id, uint1= 6_t queue_id, > { > struct rte_bbdev *dev =3D &rte_bbdev_devices[dev_id]; > struct rte_bbdev_queue_data *q_data =3D &dev->data->queues[queue_id]; > - return dev->dequeue_ldpc_dec_ops(q_data, ops, num_ops); > + const uint16_t nb_ops =3D dev->dequeue_ldpc_dec_ops(q_data, ops, num_op= s); > + RTE_LCORE_POLL_BUSYNESS_TIMESTAMP(nb_ops); > + return nb_ops; > } >=20 > /** Definitions of device event types */ > diff --git a/lib/compressdev/rte_compressdev.c b/lib/compressdev/rte_comp= ressdev.c > index 22c438f2dd..fabc495a8e 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 =3D (*dev->dequeue_burst) > (dev->data->queue_pairs[qp_id], ops, nb_ops); >=20 > + RTE_LCORE_POLL_BUSYNESS_TIMESTAMP(nb_ops); > + > return nb_ops; > } >=20 > diff --git a/lib/cryptodev/rte_cryptodev.h b/lib/cryptodev/rte_cryptodev.= h > index 56f459c6a0..a5b1d7c594 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_POLL_BUSYNESS_TIMESTAMP(nb_ops); > return nb_ops; > } >=20 > diff --git a/lib/distributor/rte_distributor.c b/lib/distributor/rte_dist= ributor.c > index 3035b7a999..428157ec64 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, >=20 > while (rte_rdtsc() < t) > rte_pause(); > + /* this was an empty poll */ > + RTE_LCORE_POLL_BUSYNESS_TIMESTAMP(0); > } >=20 > /* > @@ -134,24 +136,29 @@ rte_distributor_get_pkt(struct rte_distributor *d, >=20 > if (unlikely(d->alg_type =3D=3D RTE_DIST_ALG_SINGLE)) { > if (return_count <=3D 1) { > + uint16_t cnt; > pkts[0] =3D 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 =3D (pkts[0] !=3D NULL) ? 1 : 0; > + RTE_LCORE_POLL_BUSYNESS_TIMESTAMP(cnt); > + return cnt; > + } > + return -EINVAL; > } >=20 > rte_distributor_request_pkt(d, worker_id, oldpkt, return_count); >=20 > - count =3D rte_distributor_poll_pkt(d, worker_id, pkts); > - while (count =3D=3D -1) { > + while ((count =3D rte_distributor_poll_pkt(d, worker_id, pkts)) =3D=3D = -1) { > uint64_t t =3D rte_rdtsc() + 100; >=20 > while (rte_rdtsc() < t) > rte_pause(); >=20 > - count =3D rte_distributor_poll_pkt(d, worker_id, pkts); > + /* this was an empty poll */ > + RTE_LCORE_POLL_BUSYNESS_TIMESTAMP(0); > } > + RTE_LCORE_POLL_BUSYNESS_TIMESTAMP(count); > return count; > } >=20 > diff --git a/lib/distributor/rte_distributor_single.c b/lib/distributor/r= te_distributor_single.c > index 2c77ac454a..4c916c0fd2 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_distribu= tor_single *d, > union rte_distributor_buffer_single *buf =3D &d->bufs[worker_id]; > int64_t req =3D (((int64_t)(uintptr_t)oldpkt) << RTE_DISTRIB_FLAG_BITS) > | RTE_DISTRIB_GET_BUF; > - RTE_WAIT_UNTIL_MASKED(&buf->bufptr64, RTE_DISTRIB_FLAGS_MASK, > - =3D=3D, 0, __ATOMIC_RELAXED); > + > + while ((__atomic_load_n(&buf->bufptr64, __ATOMIC_RELAXED) > + & RTE_DISTRIB_FLAGS_MASK) !=3D 0) { > + rte_pause(); > + /* this was an empty poll */ > + RTE_LCORE_POLL_BUSYNESS_TIMESTAMP(0); > + } >=20 > /* 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 =3D rte_distributor_poll_pkt_single(d, worker_id)) =3D=3D N= ULL) > + while ((ret =3D rte_distributor_poll_pkt_single(d, worker_id)) =3D=3D N= ULL) { > rte_pause(); > + /* this was an empty poll */ > + RTE_LCORE_POLL_BUSYNESS_TIMESTAMP(0); > + } > return ret; > } >=20 > diff --git a/lib/dmadev/rte_dmadev.h b/lib/dmadev/rte_dmadev.h > index e7f992b734..3e27e0fd2b 100644 > --- a/lib/dmadev/rte_dmadev.h > +++ b/lib/dmadev/rte_dmadev.h > @@ -149,6 +149,7 @@ > #include > #include > #include > +#include >=20 > #ifdef __cplusplus > extern "C" { > @@ -1027,7 +1028,7 @@ rte_dma_completed(int16_t dev_id, uint16_t vchan, c= onst uint16_t nb_cpls, > uint16_t *last_idx, bool *has_error) > { > struct rte_dma_fp_object *obj =3D &rte_dma_fp_objs[dev_id]; > - uint16_t idx; > + uint16_t idx, nb_ops; > bool err; >=20 > #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 =3D &err; >=20 > *has_error =3D false; > - return (*obj->completed)(obj->dev_private, vchan, nb_cpls, last_idx, > - has_error); > + nb_ops =3D (*obj->completed)(obj->dev_private, vchan, nb_cpls, last_idx= , > + has_error); > + RTE_LCORE_POLL_BUSYNESS_TIMESTAMP(nb_ops); > + return nb_ops; > } >=20 > /** > @@ -1090,7 +1093,7 @@ rte_dma_completed_status(int16_t dev_id, uint16_t v= chan, > enum rte_dma_status_code *status) > { > struct rte_dma_fp_object *obj =3D &rte_dma_fp_objs[dev_id]; > - uint16_t idx; > + uint16_t idx, nb_ops; >=20 > #ifdef RTE_DMADEV_DEBUG > if (!rte_dma_is_valid(dev_id) || nb_cpls =3D=3D 0 || status =3D=3D NULL= ) > @@ -1101,8 +1104,10 @@ rte_dma_completed_status(int16_t dev_id, uint16_t = vchan, > if (last_idx =3D=3D NULL) > last_idx =3D &idx; >=20 > - return (*obj->completed_status)(obj->dev_private, vchan, nb_cpls, > + nb_ops =3D (*obj->completed_status)(obj->dev_private, vchan, nb_cpls, > last_idx, status); > + RTE_LCORE_POLL_BUSYNESS_TIMESTAMP(nb_ops); > + return nb_ops; > } >=20 > /** > diff --git a/lib/eal/common/eal_common_lcore_poll_telemetry.c b/lib/eal/c= ommon/eal_common_lcore_poll_telemetry.c > new file mode 100644 > index 0000000000..d97996e85f > --- /dev/null > +++ b/lib/eal/common/eal_common_lcore_poll_telemetry.c > @@ -0,0 +1,303 @@ > +/* SPDX-License-Identifier: BSD-3-Clause > + * Copyright(c) 2022 Intel Corporation > + */ > + > +#include > +#include > +#include > + > +#include > +#include > +#include > +#include > + > +#ifdef RTE_LCORE_POLL_BUSYNESS > +#include > +#endif > + > +rte_atomic32_t __rte_lcore_poll_telemetry_enabled; > + > +#ifdef RTE_LCORE_POLL_BUSYNESS > + > +struct lcore_poll_telemetry { > + int poll_busyness; > + /**< Calculated poll busyness (gets set/returned by the API) */ > + int raw_poll_busyness; > + /**< Calculated poll 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_poll_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; > + > + RTE_LCORE_FOREACH(lcore_id) { > + struct lcore_poll_telemetry *td =3D &telemetry_data[lcore_id]; > + > + td->interval_ts =3D 0; > + td->last_poll_ts =3D 0; > + td->empty_cycles =3D 0; > + td->last_empty =3D true; > + td->contig_poll_cnt =3D 0; > + td->poll_busyness =3D LCORE_POLL_BUSYNESS_NOT_SET; > + td->raw_poll_busyness =3D 0; > + } > +} > + > +int rte_lcore_poll_busyness(unsigned int lcore_id) > +{ > + const uint64_t tsc_ms =3D rte_get_timer_hz() / MS_PER_S; > + /* if more than 1000 busyness periods have passed, this core is conside= red inactive */ > + const uint64_t active_thresh =3D RTE_LCORE_POLL_BUSYNESS_PERIOD_MS * ts= c_ms * 1000; > + struct lcore_poll_telemetry *tdata; > + > + if (lcore_id >=3D RTE_MAX_LCORE) > + return -EINVAL; > + tdata =3D &telemetry_data[lcore_id]; > + > + /* if the lcore is not active */ > + if (tdata->interval_ts =3D=3D 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 poll busyness */ > + return telemetry_data[lcore_id].poll_busyness; > +} > + > +int rte_lcore_poll_busyness_enabled(void) > +{ > + return rte_atomic32_read(&__rte_lcore_poll_telemetry_enabled); > +} > + > +void rte_lcore_poll_busyness_enabled_set(bool enable) > +{ > + int set =3D rte_atomic32_cmpset((volatile uint32_t *)&__rte_lcore_poll_= telemetry_enabled, > + (int)!enable, (int)enable); > + > + /* Reset counters on successful disable */ > + if (set && !enable) > + lcore_config_init(); > +} > + > +static inline int calc_raw_poll_busyness(const struct lcore_poll_telemet= ry *tdata, > + const uint64_t empty, const uint64_t total) > +{ > + /* > + * We don't want to use floating point math here, but we want for our p= oll > + * busyness to react smoothly to sudden changes, while still keeping th= e > + * accuracy and making sure that over time the average follows poll bus= yness > + * as measured just-in-time. Therefore, we will calculate the average p= oll > + * 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 =3D LCORE_POLL_BUSYNESS_MAX * 100; > + > + const int prev_raw_idle =3D max_raw_idle - tdata->raw_poll_busyness; > + > + /* calculate rate of idle cycles, times 100 */ > + const int cur_raw_idle =3D (int)((empty * max_raw_idle) / total); > + > + /* smoothen the idleness */ > + const int smoothened_idle =3D > + (cur_raw_idle + prev_raw_idle * (SMOOTH_COEFF - 1)) / SMOOTH_COEFF; > + > + /* convert idleness to poll busyness */ > + return max_raw_idle - smoothened_idle; > +} > + > +void __rte_lcore_poll_busyness_timestamp(uint16_t nb_rx) > +{ > + const unsigned int lcore_id =3D rte_lcore_id(); > + uint64_t interval_ts, empty_cycles, cur_tsc, last_poll_ts; > + struct lcore_poll_telemetry *tdata; > + const bool empty =3D nb_rx =3D=3D 0; > + uint64_t diff_int, diff_last; > + bool last_empty; > + > + /* This telemetry is not supported for unregistered non-EAL threads */ > + if (lcore_id >=3D RTE_MAX_LCORE) { > + RTE_LOG(DEBUG, EAL, > + "Lcore telemetry not supported on unregistered non-EAL thread %d", > + lcore_id); > + return; > + } > + > + tdata =3D &telemetry_data[lcore_id]; > + last_empty =3D tdata->last_empty; > + > + /* optimization: don't do anything if status hasn't changed */ > + if (last_empty =3D=3D empty && tdata->contig_poll_cnt++ < STATE_CHANGE_= OPT) > + return; > + /* status changed or we're waiting for too long, reset counter */ > + tdata->contig_poll_cnt =3D 0; > + > + cur_tsc =3D rte_rdtsc(); > + > + interval_ts =3D tdata->interval_ts; > + empty_cycles =3D tdata->empty_cycles; > + last_poll_ts =3D tdata->last_poll_ts; > + > + diff_int =3D cur_tsc - interval_ts; > + diff_last =3D cur_tsc - last_poll_ts; > + > + /* is this the first time we're here? */ > + if (interval_ts =3D=3D 0) { > + tdata->poll_busyness =3D LCORE_POLL_BUSYNESS_MIN; > + tdata->raw_poll_busyness =3D 0; > + tdata->interval_ts =3D cur_tsc; > + tdata->empty_cycles =3D 0; > + tdata->contig_poll_cnt =3D 0; > + goto end; > + } > + > + /* update the empty counter if we got an empty poll earlier */ > + if (last_empty) > + empty_cycles +=3D diff_last; > + > + /* have we passed the interval? */ > + uint64_t interval =3D ((rte_get_tsc_hz() / MS_PER_S) * RTE_LCORE_POLL_B= USYNESS_PERIOD_MS); > + if (diff_int > interval) { > + int raw_poll_busyness; > + > + /* get updated poll_busyness value */ > + raw_poll_busyness =3D calc_raw_poll_busyness(tdata, empty_cycles, diff= _int); > + > + /* set a new interval, reset empty counter */ > + tdata->interval_ts =3D cur_tsc; > + tdata->empty_cycles =3D 0; > + tdata->raw_poll_busyness =3D raw_poll_busyness; > + /* bring poll busyness back to 0..100 range, biased to round up */ > + tdata->poll_busyness =3D (raw_poll_busyness + 50) / 100; > + } else > + /* we may have updated empty counter */ > + tdata->empty_cycles =3D empty_cycles; > + > +end: > + /* update status for next poll */ > + tdata->last_poll_ts =3D cur_tsc; > + tdata->last_empty =3D 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(true); > + > + 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(false); > + > + rte_tel_data_start_dict(d); > + > + rte_tel_data_add_dict_int(d, "poll_busyness_enabled", 0); > + > + 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; > +} > + > +void > +eal_lcore_poll_telemetry_free(void) > +{ > + if (telemetry_data !=3D NULL) { > + free(telemetry_data); > + telemetry_data =3D NULL; > + } > +} > + > +RTE_INIT(lcore_init_poll_telemetry) > +{ > + telemetry_data =3D calloc(RTE_MAX_LCORE, sizeof(telemetry_data[0])); > + if (telemetry_data =3D=3D NULL) > + rte_panic("Could not init lcore telemetry data: Out of memory\n"); > + > + lcore_config_init(); > + > + rte_telemetry_register_cmd("/eal/lcore/poll_busyness", lcore_handle_pol= l_busyness, > + "return percentage poll busyness of cores"); > + > + rte_telemetry_register_cmd("/eal/lcore/poll_busyness_enable", lcore_pol= l_busyness_enable, > + "enable lcore poll busyness measurement"); > + > + rte_telemetry_register_cmd("/eal/lcore/poll_busyness_disable", lcore_po= ll_busyness_disable, > + "disable lcore poll busyness measurement"); > + > + rte_atomic32_set(&__rte_lcore_poll_telemetry_enabled, true); > +} > + > +#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(bool enable __rte_unused) > +{ > +} > + > +void __rte_lcore_poll_busyness_timestamp(uint16_t nb_rx __rte_unused) > +{ > +} > + > +void eal_lcore_poll_telemetry_free(void) > +{ > +} > + > +#endif > diff --git a/lib/eal/common/meson.build b/lib/eal/common/meson.build > index 917758cc65..e5741ce9f9 100644 > --- a/lib/eal/common/meson.build > +++ b/lib/eal/common/meson.build > @@ -17,6 +17,7 @@ sources +=3D files( > 'eal_common_hexdump.c', > 'eal_common_interrupts.c', > 'eal_common_launch.c', > + 'eal_common_lcore_poll_telemetry.c', > 'eal_common_lcore.c', > 'eal_common_log.c', > 'eal_common_mcfg.c', > diff --git a/lib/eal/freebsd/eal.c b/lib/eal/freebsd/eal.c > index 26fbc91b26..92c4af9c28 100644 > --- a/lib/eal/freebsd/eal.c > +++ b/lib/eal/freebsd/eal.c > @@ -895,6 +895,7 @@ rte_eal_cleanup(void) > rte_mp_channel_cleanup(); > rte_trace_save(); > eal_trace_fini(); > + eal_lcore_poll_telemetry_free(); > /* after this point, any DPDK pointers will become dangling */ > rte_eal_memory_detach(); > rte_eal_alarm_cleanup(); > diff --git a/lib/eal/include/rte_lcore.h b/lib/eal/include/rte_lcore.h > index b598e1b9ec..2191c2473a 100644 > --- a/lib/eal/include/rte_lcore.h > +++ b/lib/eal/include/rte_lcore.h > @@ -16,6 +16,7 @@ > #include > #include > #include > +#include >=20 > #ifdef __cplusplus > extern "C" { > @@ -415,9 +416,91 @@ rte_ctrl_thread_create(pthread_t *thread, const char= *name, > const pthread_attr_t *attr, > void *(*start_routine)(void *), void *arg); >=20 > +/** > + * @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 > + * - true if lcore telemetry is enabled > + * - false 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(bool enable); > + > +/** > + * @warning > + * @b EXPERIMENTAL: this API may change without prior notice. > + * > + * Lcore poll busyness timestamping function. > + * > + * @param nb_rx > + * Number of buffers processed by lcore. > + */ > +__rte_experimental > +void > +__rte_lcore_poll_busyness_timestamp(uint16_t nb_rx); > + > +/** @internal lcore telemetry enabled status */ > +extern rte_atomic32_t __rte_lcore_poll_telemetry_enabled; > + > +/** @internal free memory allocated for lcore telemetry */ > +void > +eal_lcore_poll_telemetry_free(void); > + > +/** > + * Call lcore poll busyness timestamp function. > + * > + * @param nb_rx > + * Number of buffers processed by lcore. > + */ > +#ifdef RTE_LCORE_POLL_BUSYNESS > +#define RTE_LCORE_POLL_BUSYNESS_TIMESTAMP(nb_rx) do { \ > + int enabled =3D (int)rte_atomic32_read(&__rte_lcore_poll_telemetry_enab= led); \ > + if (enabled) \ > + __rte_lcore_poll_busyness_timestamp(nb_rx); \ > +} while (0) > +#else > +#define RTE_LCORE_POLL_BUSYNESS_TIMESTAMP(nb_rx) do { } while (0) > +#endif > + > #ifdef __cplusplus > } > #endif >=20 > - > #endif /* _RTE_LCORE_H_ */ > diff --git a/lib/eal/linux/eal.c b/lib/eal/linux/eal.c > index 37d29643a5..5e81352a81 100644 > --- a/lib/eal/linux/eal.c > +++ b/lib/eal/linux/eal.c > @@ -1364,6 +1364,7 @@ rte_eal_cleanup(void) > rte_mp_channel_cleanup(); > rte_trace_save(); > eal_trace_fini(); > + eal_lcore_poll_telemetry_free(); > /* after this point, any DPDK pointers will become dangling */ > rte_eal_memory_detach(); > eal_mp_dev_hotplug_cleanup(); > diff --git a/lib/eal/meson.build b/lib/eal/meson.build > index 056beb9461..2fb90d446b 100644 > --- a/lib/eal/meson.build > +++ b/lib/eal/meson.build > @@ -25,6 +25,9 @@ subdir(arch_subdir) > deps +=3D ['kvargs'] > if not is_windows > deps +=3D ['telemetry'] > +else > + # core poll busyness telemetry depends on telemetry library > + dpdk_conf.set('RTE_LCORE_POLL_BUSYNESS', false) > endif > if dpdk_conf.has('RTE_USE_LIBBSD') > ext_deps +=3D libbsd > diff --git a/lib/eal/version.map b/lib/eal/version.map > index 1f293e768b..3275d1fac4 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_poll_busyness_timestamp; > + __rte_lcore_poll_telemetry_enabled; > + rte_lcore_poll_busyness; > + rte_lcore_poll_busyness_enabled; > + rte_lcore_poll_busyness_enabled_set; > }; >=20 > INTERNAL { > diff --git a/lib/ethdev/rte_ethdev.h b/lib/ethdev/rte_ethdev.h > index de9e970d4d..4c8113f31f 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_i= d, > #endif >=20 > rte_ethdev_trace_rx_burst(port_id, queue_id, (void **)rx_pkts, nb_rx); > + > + RTE_LCORE_POLL_BUSYNESS_TIMESTAMP(nb_rx); > return nb_rx; > } >=20 > diff --git a/lib/eventdev/rte_eventdev.h b/lib/eventdev/rte_eventdev.h > index 6a6f6ea4c1..a65b3c7c85 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 por= t_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; >=20 > fp_ops =3D &rte_event_fp_ops[dev_id]; > @@ -2175,10 +2176,13 @@ rte_event_dequeue_burst(uint8_t dev_id, uint8_t p= ort_id, struct rte_event ev[], > * requests nb_events as const one > */ > if (nb_events =3D=3D 1) > - return (fp_ops->dequeue)(port, ev, timeout_ticks); > + nb_evts =3D (fp_ops->dequeue)(port, ev, timeout_ticks); > else > - return (fp_ops->dequeue_burst)(port, ev, nb_events, > - timeout_ticks); > + nb_evts =3D (fp_ops->dequeue_burst)(port, ev, nb_events, > + timeout_ticks); > + > + RTE_LCORE_POLL_BUSYNESS_TIMESTAMP(nb_evts); > + return nb_evts; > } >=20 > #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..1cba53270a 100644 > --- a/lib/rawdev/rte_rawdev.c > +++ b/lib/rawdev/rte_rawdev.c > @@ -16,6 +16,7 @@ > #include > #include > #include > +#include >=20 > #include "rte_rawdev.h" > #include "rte_rawdev_pmd.h" > @@ -226,12 +227,15 @@ rte_rawdev_dequeue_buffers(uint16_t dev_id, > rte_rawdev_obj_t context) > { > struct rte_rawdev *dev; > + int nb_ops; >=20 > RTE_RAWDEV_VALID_DEVID_OR_ERR_RET(dev_id, -EINVAL); > dev =3D &rte_rawdevs[dev_id]; >=20 > RTE_FUNC_PTR_OR_ERR_RET(*dev->dev_ops->dequeue_bufs, -ENOTSUP); > - return (*dev->dev_ops->dequeue_bufs)(dev, buffers, count, context); > + nb_ops =3D (*dev->dev_ops->dequeue_bufs)(dev, buffers, count, context); > + RTE_LCORE_POLL_BUSYNESS_TIMESTAMP(nb_ops); > + return nb_ops; > } >=20 > int > diff --git a/lib/regexdev/rte_regexdev.h b/lib/regexdev/rte_regexdev.h > index 3bce8090f6..8caaed502f 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 =3D &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 =3D (*dev->dequeue)(dev, qp_id, ops, nb_ops); > + RTE_LCORE_POLL_BUSYNESS_TIMESTAMP(deq_ops); > + return deq_ops; > } >=20 > #ifdef __cplusplus > diff --git a/lib/ring/rte_ring_elem_pvt.h b/lib/ring/rte_ring_elem_pvt.h > index 83788c56e6..cf2370c238 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 !=3D NULL) > *available =3D entries - n; > + RTE_LCORE_POLL_BUSYNESS_TIMESTAMP(n); > return n; > } >=20 > diff --git a/meson_options.txt b/meson_options.txt > index 7c220ad68d..9b20a36fdb 100644 > --- a/meson_options.txt > +++ b/meson_options.txt > @@ -20,6 +20,8 @@ option('enable_driver_sdk', type: 'boolean', value: fal= se, 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: false, desc= ription: > + '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: > -- > 2.31.1