From mboxrd@z Thu Jan 1 00:00:00 1970 Return-Path: Received: from dpdk.org (dpdk.org [92.243.14.124]) by inbox.dpdk.org (Postfix) with ESMTP id BDCC4A0350; Wed, 24 Jun 2020 17:20:07 +0200 (CEST) Received: from [92.243.14.124] (localhost [127.0.0.1]) by dpdk.org (Postfix) with ESMTP id 445511D9F5; Wed, 24 Jun 2020 17:20:07 +0200 (CEST) Received: from mga02.intel.com (mga02.intel.com [134.134.136.20]) by dpdk.org (Postfix) with ESMTP id 913C31BECF for ; Wed, 24 Jun 2020 17:20:05 +0200 (CEST) IronPort-SDR: 0H2T2KnJZKwsHQZAfJasZWPIwRT2y2MfBCb3VMYeQQbT6GMPEy1W2xfXmwqJXuekERldALozJZ 0mNGdRBJTPAw== X-IronPort-AV: E=McAfee;i="6000,8403,9662"; a="132941970" X-IronPort-AV: E=Sophos;i="5.75,275,1589266800"; d="scan'208";a="132941970" X-Amp-Result: SKIPPED(no attachment in message) X-Amp-File-Uploaded: False Received: from orsmga004.jf.intel.com ([10.7.209.38]) by orsmga101.jf.intel.com with ESMTP/TLS/ECDHE-RSA-AES256-GCM-SHA384; 24 Jun 2020 08:20:04 -0700 IronPort-SDR: Qz7MEj1H/zld4GBogfmElktIdzwIp2XP0jGuLgZBsr1PNRqUSmhmoQFX7kCoZjAwZenxbMnBkh aObTNutFnxqg== X-IronPort-AV: E=Sophos;i="5.75,275,1589266800"; d="scan'208";a="423403355" Received: from bricha3-mobl.ger.corp.intel.com ([10.252.2.40]) by orsmga004-auth.jf.intel.com with ESMTP/TLS/ECDHE-RSA-AES256-SHA; 24 Jun 2020 08:20:02 -0700 Date: Wed, 24 Jun 2020 16:19:59 +0100 From: Bruce Richardson To: Ciara Power Cc: kevin.laatz@intel.com, thomas@monjalon.net, ferruh.yigit@intel.com, arybchenko@solarflare.com, dev@dpdk.org, keith.wiles@intel.com Message-ID: <20200624151959.GC1132@bricha3-MOBL.ger.corp.intel.com> References: <20200612105344.15383-1-ciara.power@intel.com> <20200624134824.16210-1-ciara.power@intel.com> <20200624134824.16210-3-ciara.power@intel.com> MIME-Version: 1.0 Content-Type: text/plain; charset=us-ascii Content-Disposition: inline In-Reply-To: <20200624134824.16210-3-ciara.power@intel.com> Subject: Re: [dpdk-dev] [PATCH v2 2/2] ethdev: add basic stats for telemetry X-BeenThere: dev@dpdk.org X-Mailman-Version: 2.1.15 Precedence: list List-Id: DPDK patches and discussions List-Unsubscribe: , List-Archive: List-Post: List-Help: List-Subscribe: , Errors-To: dev-bounces@dpdk.org Sender: "dev" On Wed, Jun 24, 2020 at 02:48:24PM +0100, Ciara Power wrote: > The ethdev library now registers a telemetry command for basic ethdev > statistics. > > An example usage is shown below: > > Connecting to /var/run/dpdk/rte/dpdk_telemetry.v2 > {"version": "DPDK 20.08.0-rc0", "pid": 14119, "max_output_len": 16384} > --> /ethdev/stats,0 > {"/ethdev/stats": {"ipackets": 0, "opackets": 0, "ibytes": 0, "obytes": \ > 0, "imissed": 0, "ierrors": 0, "oerrors": 0, "rx_nombuf": 0, \ > "q_ipackets": [0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0], \ > "q_opackets": [0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0], \ > "q_ibytes": [0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0], \ > "q_obytes": [0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0], \ > "q_errors": [0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0]}} > > Signed-off-by: Ciara Power > One comment inline below, otherwise: Acked-by: Bruce Richardson > --- > v2: > - Updated to use memory management APIs. > --- > lib/librte_ethdev/rte_ethdev.c | 53 ++++++++++++++++++++++++++++++++++ > 1 file changed, 53 insertions(+) > > diff --git a/lib/librte_ethdev/rte_ethdev.c b/lib/librte_ethdev/rte_ethdev.c > index 8e10a6fc3..23de93b50 100644 > --- a/lib/librte_ethdev/rte_ethdev.c > +++ b/lib/librte_ethdev/rte_ethdev.c > @@ -5215,6 +5215,57 @@ handle_port_list(const char *cmd __rte_unused, > return 0; > } > > +static void > +add_port_queue_stats(struct rte_tel_data *d, uint64_t *q_stats, > + const char *stat_name) > +{ > + int q; > + struct rte_tel_data *q_data = rte_tel_data_alloc(); > + rte_tel_data_start_array(q_data, RTE_TEL_U64_VAL); > + for (q = 0; q < RTE_ETHDEV_QUEUE_STAT_CNTRS; q++) > + rte_tel_data_add_array_u64(q_data, q_stats[q]); > + rte_tel_data_add_dict_container(d, stat_name, q_data, 0); > +} > + > +#define ADD_DICT_STAT(stats, s) rte_tel_data_add_dict_u64(d, #s, stats.s) > + > +static int > +handle_port_stats(const char *cmd __rte_unused, > + const char *params, > + struct rte_tel_data *d) > +{ > + struct rte_eth_stats stats; > + int port_id, ret; > + > + if (params == NULL || strlen(params) == 0 || !isdigit(*params)) > + return -1; > + > + port_id = atoi(params); > + if (!rte_eth_dev_is_valid_port(port_id)) > + return -1; > + > + ret = rte_eth_stats_get(port_id, &stats); > + if (ret < 0) > + return -1; > + > + rte_tel_data_start_dict(d); > + ADD_DICT_STAT(stats, ipackets); > + ADD_DICT_STAT(stats, opackets); > + ADD_DICT_STAT(stats, ibytes); > + ADD_DICT_STAT(stats, obytes); > + ADD_DICT_STAT(stats, imissed); > + ADD_DICT_STAT(stats, ierrors); > + ADD_DICT_STAT(stats, oerrors); > + ADD_DICT_STAT(stats, rx_nombuf); > + add_port_queue_stats(d, stats.q_ipackets, "q_ipackets"); > + add_port_queue_stats(d, stats.q_opackets, "q_opackets"); > + add_port_queue_stats(d, stats.q_ibytes, "q_ibytes"); > + add_port_queue_stats(d, stats.q_obytes, "q_obytes"); > + add_port_queue_stats(d, stats.q_errors, "q_errors"); > + > + return 0; > +} > + > static int > handle_port_xstats(const char *cmd __rte_unused, > const char *params, > @@ -5302,6 +5353,8 @@ RTE_INIT(ethdev_init_log) > rte_log_set_level(rte_eth_dev_logtype, RTE_LOG_INFO); > rte_telemetry_register_cmd("/ethdev/list", handle_port_list, > "Returns list of available ethdev ports. Takes no parameters"); > + rte_telemetry_register_cmd("/ethdev/stats", handle_port_stats, > + "Returns the basic stats for a port. Parameters: int port_id"); I think "common stats" or "standard stats" may be better than calling them "basic stats" since the main advantage of them is that they are common/standard across all drivers and are not NIC-specific. > rte_telemetry_register_cmd("/ethdev/xstats", handle_port_xstats, > "Returns the extended stats for a port. Parameters: int port_id"); > rte_telemetry_register_cmd("/ethdev/link_status", > -- > 2.17.1 >