From patchwork Thu Apr 7 14:51:52 2022 Content-Type: text/plain; charset="utf-8" MIME-Version: 1.0 Content-Transfer-Encoding: 7bit X-Patchwork-Submitter: "Danilewicz, MarcinX" X-Patchwork-Id: 109426 X-Patchwork-Delegate: thomas@monjalon.net Return-Path: X-Original-To: patchwork@inbox.dpdk.org Delivered-To: patchwork@inbox.dpdk.org Received: from mails.dpdk.org (mails.dpdk.org [217.70.189.124]) by inbox.dpdk.org (Postfix) with ESMTP id E8E02A0505; Thu, 7 Apr 2022 16:52:01 +0200 (CEST) Received: from [217.70.189.124] (localhost [127.0.0.1]) by mails.dpdk.org (Postfix) with ESMTP id 95DC44068F; Thu, 7 Apr 2022 16:52:01 +0200 (CEST) Received: from mga03.intel.com (mga03.intel.com [134.134.136.65]) by mails.dpdk.org (Postfix) with ESMTP id 610A240689 for ; Thu, 7 Apr 2022 16:52:00 +0200 (CEST) DKIM-Signature: v=1; a=rsa-sha256; c=relaxed/simple; d=intel.com; i=@intel.com; q=dns/txt; s=Intel; t=1649343120; x=1680879120; h=from:to:cc:subject:date:message-id:mime-version: content-transfer-encoding; bh=i9QKKfKcgd5SXW9HooavtYVJLNRoOYZwLnzVE6+E6kY=; b=nSrSpz2uxxhxTfvxaHvKi6A6/Gwpam+sv3mHEVJLoRMvOxYmFhcrvt6H jZwFzJ6gu7WvbJZLDiWWx04MFJ7gKx/QCol41/XF0bg3jpWX8jmXswBXb oMNDnxCiAGQFAiEnrAOZ3cPwS6e/D7ezgJwD/tRbYSYVutnZ+O6qjY76a mx3RmeB0zlaMBGLurGj+cbBCAvRa+/p+XzAHWuih4mH6chMncCjEFcAkF lSwO3kya5R05b7Ho8KQuDnKt0wTMbV/pwH3gxrfMvAGTDNC4lP2gqOBO1 2eHedzj4YCFif6Ez7+6qYULHvx8mnwerXl9QmH/nmNCAFG77PqqgcYFab A==; X-IronPort-AV: E=McAfee;i="6400,9594,10309"; a="261335854" X-IronPort-AV: E=Sophos;i="5.90,242,1643702400"; d="scan'208";a="261335854" Received: from orsmga002.jf.intel.com ([10.7.209.21]) by orsmga103.jf.intel.com with ESMTP/TLS/ECDHE-RSA-AES256-GCM-SHA384; 07 Apr 2022 07:51:59 -0700 X-ExtLoop1: 1 X-IronPort-AV: E=Sophos;i="5.90,242,1643702400"; d="scan'208";a="524391898" Received: from silpixa00400629.ir.intel.com ([10.237.213.88]) by orsmga002.jf.intel.com with ESMTP; 07 Apr 2022 07:51:57 -0700 From: Marcin Danilewicz To: dev@dpdk.org Cc: Megha Ajmera Subject: [dpdk][PATCH 1/2] sched: enable/disable TC OV at runtime Date: Thu, 7 Apr 2022 14:51:52 +0000 Message-Id: <20220407145153.238969-1-marcinx.danilewicz@intel.com> X-Mailer: git-send-email 2.25.1 MIME-Version: 1.0 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 From: Megha Ajmera Added new API to enable or disable TC over subscription for best effort traffic class at subport level. By default TC OV is disabled for subport. Signed-off-by: Megha Ajmera diff --git a/lib/sched/rte_sched.c b/lib/sched/rte_sched.c index ec74bee939..1d05089d00 100644 --- a/lib/sched/rte_sched.c +++ b/lib/sched/rte_sched.c @@ -155,6 +155,7 @@ struct rte_sched_subport { uint64_t tc_credits[RTE_SCHED_TRAFFIC_CLASSES_PER_PIPE]; /* TC oversubscription */ + uint8_t is_tc_ov_enabled; uint64_t tc_ov_wm; uint64_t tc_ov_wm_min; uint64_t tc_ov_wm_max; @@ -1165,6 +1166,45 @@ rte_sched_cman_config(struct rte_sched_port *port, } #endif +int +rte_sched_subport_tc_ov_config(struct rte_sched_port *port, + uint32_t subport_id, + bool tc_ov_enable) +{ + struct rte_sched_subport *s; + struct rte_sched_subport_profile *profile; + + if (port == NULL) { + RTE_LOG(ERR, SCHED, + "%s: Incorrect value for parameter port\n", __func__); + return -EINVAL; + } + + if (subport_id >= port->n_subports_per_port) { + RTE_LOG(ERR, SCHED, + "%s: Incorrect value for parameter subport id\n", __func__); + return -EINVAL; + } + + s = port->subports[subport_id]; + s->is_tc_ov_enabled = tc_ov_enable; + + if (s->is_tc_ov_enabled) { + /* TC oversubscription */ + s->tc_ov_wm_min = port->mtu; + s->tc_ov_period_id = 0; + s->tc_ov = 0; + s->tc_ov_n = 0; + s->tc_ov_rate = 0; + + profile = port->subport_profiles + s->profile; + s->tc_ov_wm_max = rte_sched_time_ms_to_bytes(profile->tc_period, + s->pipe_tc_be_rate_max); + s->tc_ov_wm = s->tc_ov_wm_max; + } + return 0; +} + int rte_sched_subport_config(struct rte_sched_port *port, uint32_t subport_id, @@ -1317,12 +1357,8 @@ rte_sched_subport_config(struct rte_sched_port *port, for (i = 0; i < RTE_SCHED_PORT_N_GRINDERS; i++) s->grinder_base_bmp_pos[i] = RTE_SCHED_PIPE_INVALID; - /* TC oversubscription */ - s->tc_ov_wm_min = port->mtu; - s->tc_ov_period_id = 0; - s->tc_ov = 0; - s->tc_ov_n = 0; - s->tc_ov_rate = 0; + /* TC over-subscription is disabled by default */ + s->is_tc_ov_enabled = 0; } { @@ -1342,9 +1378,6 @@ rte_sched_subport_config(struct rte_sched_port *port, else profile->tc_credits_per_period[i] = 0; - s->tc_ov_wm_max = rte_sched_time_ms_to_bytes(profile->tc_period, - s->pipe_tc_be_rate_max); - s->tc_ov_wm = s->tc_ov_wm_max; s->profile = subport_profile_id; } @@ -1417,17 +1450,20 @@ rte_sched_pipe_config(struct rte_sched_port *port, double pipe_tc_be_rate = (double) params->tc_credits_per_period[RTE_SCHED_TRAFFIC_CLASS_BE] / (double) params->tc_period; - uint32_t tc_be_ov = s->tc_ov; - /* Unplug pipe from its subport */ - s->tc_ov_n -= params->tc_ov_weight; - s->tc_ov_rate -= pipe_tc_be_rate; - s->tc_ov = s->tc_ov_rate > subport_tc_be_rate; + if (s->is_tc_ov_enabled) { + uint32_t tc_be_ov = s->tc_ov; - if (s->tc_ov != tc_be_ov) { - RTE_LOG(DEBUG, SCHED, - "Subport %u Best-effort TC oversubscription is OFF (%.4lf >= %.4lf)\n", - subport_id, subport_tc_be_rate, s->tc_ov_rate); + /* Unplug pipe from its subport */ + s->tc_ov_n -= params->tc_ov_weight; + s->tc_ov_rate -= pipe_tc_be_rate; + s->tc_ov = s->tc_ov_rate > subport_tc_be_rate; + + if (s->tc_ov != tc_be_ov) { + RTE_LOG(DEBUG, SCHED, + "Subport %u Best-effort TC oversubscription is OFF (%.4lf >= %.4lf)\n", + subport_id, subport_tc_be_rate, s->tc_ov_rate); + } } /* Reset the pipe */ @@ -1460,19 +1496,22 @@ rte_sched_pipe_config(struct rte_sched_port *port, double pipe_tc_be_rate = (double) params->tc_credits_per_period[RTE_SCHED_TRAFFIC_CLASS_BE] / (double) params->tc_period; - uint32_t tc_be_ov = s->tc_ov; - s->tc_ov_n += params->tc_ov_weight; - s->tc_ov_rate += pipe_tc_be_rate; - s->tc_ov = s->tc_ov_rate > subport_tc_be_rate; + if (s->is_tc_ov_enabled) { + uint32_t tc_be_ov = s->tc_ov; - if (s->tc_ov != tc_be_ov) { - RTE_LOG(DEBUG, SCHED, - "Subport %u Best effort TC oversubscription is ON (%.4lf < %.4lf)\n", - subport_id, subport_tc_be_rate, s->tc_ov_rate); + s->tc_ov_n += params->tc_ov_weight; + s->tc_ov_rate += pipe_tc_be_rate; + s->tc_ov = s->tc_ov_rate > subport_tc_be_rate; + + if (s->tc_ov != tc_be_ov) { + RTE_LOG(DEBUG, SCHED, + "Subport %u Best effort TC oversubscription is ON (%.4lf < %.4lf)\n", + subport_id, subport_tc_be_rate, s->tc_ov_rate); + } + p->tc_ov_period_id = s->tc_ov_period_id; + p->tc_ov_credits = s->tc_ov_wm; } - p->tc_ov_period_id = s->tc_ov_period_id; - p->tc_ov_credits = s->tc_ov_wm; } return 0; @@ -2318,6 +2357,45 @@ grinder_credits_update(struct rte_sched_port *port, pipe->tb_credits = RTE_MIN(pipe->tb_credits, params->tb_size); pipe->tb_time += n_periods * params->tb_period; + /* Subport TCs */ + if (unlikely(port->time >= subport->tc_time)) { + for (i = 0; i < RTE_SCHED_TRAFFIC_CLASSES_PER_PIPE; i++) + subport->tc_credits[i] = sp->tc_credits_per_period[i]; + + subport->tc_time = port->time + sp->tc_period; + } + + /* Pipe TCs */ + if (unlikely(port->time >= pipe->tc_time)) { + for (i = 0; i < RTE_SCHED_TRAFFIC_CLASSES_PER_PIPE; i++) + pipe->tc_credits[i] = params->tc_credits_per_period[i]; + pipe->tc_time = port->time + params->tc_period; + } +} + +static inline void +grinder_credits_update_with_tc_ov(struct rte_sched_port *port, + struct rte_sched_subport *subport, uint32_t pos) +{ + struct rte_sched_grinder *grinder = subport->grinder + pos; + struct rte_sched_pipe *pipe = grinder->pipe; + struct rte_sched_pipe_profile *params = grinder->pipe_params; + struct rte_sched_subport_profile *sp = grinder->subport_params; + uint64_t n_periods; + uint32_t i; + + /* Subport TB */ + n_periods = (port->time - subport->tb_time) / sp->tb_period; + subport->tb_credits += n_periods * sp->tb_credits_per_period; + subport->tb_credits = RTE_MIN(subport->tb_credits, sp->tb_size); + subport->tb_time += n_periods * sp->tb_period; + + /* Pipe TB */ + n_periods = (port->time - pipe->tb_time) / params->tb_period; + pipe->tb_credits += n_periods * params->tb_credits_per_period; + pipe->tb_credits = RTE_MIN(pipe->tb_credits, params->tb_size); + pipe->tb_time += n_periods * params->tb_period; + /* Subport TCs */ if (unlikely(port->time >= subport->tc_time)) { subport->tc_ov_wm = @@ -2348,6 +2426,39 @@ grinder_credits_update(struct rte_sched_port *port, static inline int grinder_credits_check(struct rte_sched_port *port, struct rte_sched_subport *subport, uint32_t pos) +{ + struct rte_sched_grinder *grinder = subport->grinder + pos; + struct rte_sched_pipe *pipe = grinder->pipe; + struct rte_mbuf *pkt = grinder->pkt; + uint32_t tc_index = grinder->tc_index; + uint64_t pkt_len = pkt->pkt_len + port->frame_overhead; + uint64_t subport_tb_credits = subport->tb_credits; + uint64_t subport_tc_credits = subport->tc_credits[tc_index]; + uint64_t pipe_tb_credits = pipe->tb_credits; + uint64_t pipe_tc_credits = pipe->tc_credits[tc_index]; + int enough_credits; + + /* Check pipe and subport credits */ + enough_credits = (pkt_len <= subport_tb_credits) && + (pkt_len <= subport_tc_credits) && + (pkt_len <= pipe_tb_credits) && + (pkt_len <= pipe_tc_credits); + + if (!enough_credits) + return 0; + + /* Update pipe and subport credits */ + subport->tb_credits -= pkt_len; + subport->tc_credits[tc_index] -= pkt_len; + pipe->tb_credits -= pkt_len; + pipe->tc_credits[tc_index] -= pkt_len; + + return 1; +} + +static inline int +grinder_credits_check_with_tc_ov(struct rte_sched_port *port, + struct rte_sched_subport *subport, uint32_t pos) { struct rte_sched_grinder *grinder = subport->grinder + pos; struct rte_sched_pipe *pipe = grinder->pipe; @@ -2403,8 +2514,13 @@ grinder_schedule(struct rte_sched_port *port, uint32_t pkt_len = pkt->pkt_len + port->frame_overhead; uint32_t be_tc_active; - if (!grinder_credits_check(port, subport, pos)) - return 0; + if (unlikely(subport->is_tc_ov_enabled)) { + if (!grinder_credits_check_with_tc_ov(port, subport, pos)) + return 0; + } else { + if (!grinder_credits_check(port, subport, pos)) + return 0; + } /* Advance port time */ port->time += pkt_len; @@ -2770,7 +2886,11 @@ grinder_handle(struct rte_sched_port *port, subport->profile; grinder_prefetch_tc_queue_arrays(subport, pos); - grinder_credits_update(port, subport, pos); + + if (unlikely(subport->is_tc_ov_enabled)) + grinder_credits_update_with_tc_ov(port, subport, pos); + else + grinder_credits_update(port, subport, pos); grinder->state = e_GRINDER_PREFETCH_MBUF; return 0; diff --git a/lib/sched/rte_sched.h b/lib/sched/rte_sched.h index 5ece64e527..94febe1d94 100644 --- a/lib/sched/rte_sched.h +++ b/lib/sched/rte_sched.h @@ -579,6 +579,24 @@ rte_sched_port_enqueue(struct rte_sched_port *port, struct rte_mbuf **pkts, uint int rte_sched_port_dequeue(struct rte_sched_port *port, struct rte_mbuf **pkts, uint32_t n_pkts); +/** + * Hierarchical scheduler subport TC OV enable/disable config. + * Note that this function is safe to use at runtime + * to enable/disable TC OV for subport. + * + * @param port + * Handle to port scheduler instance + * @param subport_id + * Subport ID + * @param tc_ov_enable + * Boolean flag to enable/disable TC OV + * @return + * 0 upon success, error code otherwise + */ +__rte_experimental +int +rte_sched_subport_tc_ov_config(struct rte_sched_port *port, uint32_t subport_id, bool tc_ov_enable); + #ifdef __cplusplus } #endif diff --git a/lib/sched/version.map b/lib/sched/version.map index d22c07fc9f..c6e994d8df 100644 --- a/lib/sched/version.map +++ b/lib/sched/version.map @@ -34,4 +34,7 @@ EXPERIMENTAL { # added in 21.11 rte_pie_rt_data_init; rte_pie_config_init; + + # added in 22.03 + rte_sched_subport_tc_ov_config; };