From mboxrd@z Thu Jan 1 00:00:00 1970
Return-Path: <dev-bounces@dpdk.org>
Received: from dpdk.org (dpdk.org [92.243.14.124])
by inbox.dpdk.org (Postfix) with ESMTP id 40700A00C2;
Fri, 24 Apr 2020 17:30:01 +0200 (CEST)
Received: from [92.243.14.124] (localhost [127.0.0.1])
by dpdk.org (Postfix) with ESMTP id D53B71D177;
Fri, 24 Apr 2020 17:29:59 +0200 (CEST)
Received: from mail-pf1-f196.google.com (mail-pf1-f196.google.com
[209.85.210.196]) by dpdk.org (Postfix) with ESMTP id 05C551D164
for <dev@dpdk.org>; Fri, 24 Apr 2020 17:29:57 +0200 (CEST)
Received: by mail-pf1-f196.google.com with SMTP id x2so1244408pfx.7
for <dev@dpdk.org>; Fri, 24 Apr 2020 08:29:57 -0700 (PDT)
DKIM-Signature: v=1; a=rsa-sha256; c=relaxed/relaxed;
d=networkplumber-org.20150623.gappssmtp.com; s=20150623;
h=date:from:to:cc:subject:message-id:in-reply-to:references
:mime-version:content-transfer-encoding;
bh=/0p10XPHhLLZfWiI6+bg/WwShRKOgZAA8rLTs+K7Yfg=;
b=zDo1IgGok/hqQ3qYTqYT1GvQkuO6gs0XMPWUbe5RjcfuiJr+YEgjg1+1tobcqDe8rR
vwyTBAa6SBcUl1KxJ9ipqSb1xliiJiG5W1wjUn6OHZUUt3BJXspi4V8v9eVpqspxwLA9
Pqio9p50xAHjPDNIRNwcaqHuuwpKPOUpKZ0ddWaJgTUU9LJQSTIRJtYxMtEazFLA31Rn
SyYrO/BTTjGCaiixOCzLASUV8PbnukbX8Sgahb4nbkQbEQWsB0IUrnjNBqd+wJRr3O/q
ITJc1uKMqmJyIEwsveqB5shDSh3BUEqWTGmNmQM7J8Q6y3lB3aW8kJEd+MjY+fx0Nnma
5cvw==
X-Google-DKIM-Signature: v=1; a=rsa-sha256; c=relaxed/relaxed;
d=1e100.net; s=20161025;
h=x-gm-message-state:date:from:to:cc:subject:message-id:in-reply-to
:references:mime-version:content-transfer-encoding;
bh=/0p10XPHhLLZfWiI6+bg/WwShRKOgZAA8rLTs+K7Yfg=;
b=AC25EvWnOhsLukC6CWikT1YUjw4OvQqRsaa67jqYxX0VSf0I+X8IMDLwTkLLe1Iets
HYnHv+T6771qjxrc8zzPStjwGRx0bkgiOn7fsQQ4zW0o6Q9EhIVs+u+sIiqPfzCtRuvM
Ofx6uWgI0sATZYtxgH+msZtISkdzqd1NktC51ipeUh0x0YcTfHokiXfZqHIKkG9CALmH
1tcptC08k/dChYq3invGG2gPkrEaNhrw8eISYgMKt0z5vnp1YtnmDofw2L2sht2pjYYY
MKslSfm4DG4GUqu2gpj/gS8JEO72xiPAruDiv98kMfWzoZ7CNEJbuOJ+83yIhcSAGbcx
O8gg==
X-Gm-Message-State: AGi0PubEXepF2snHplDb78KzT7elI/j/JpjEkZCq0p2k2HO2w2FV3Kc0
90JyKS/tu6+eY84KkY1RoG1kzw==
X-Google-Smtp-Source: APiQypLnSkb4yIfzidxtEM6naEwQH46gFLJnhDIGfgbacxh1sZHHbMiEbvyqwI5oaBfIj1pscyPxRw==
X-Received: by 2002:a63:c34e:: with SMTP id e14mr10040071pgd.212.1587742196781;
Fri, 24 Apr 2020 08:29:56 -0700 (PDT)
Received: from hermes.lan (204-195-22-127.wavecable.com. [204.195.22.127])
by smtp.gmail.com with ESMTPSA id f21sm6160916pfn.71.2020.04.24.08.29.55
(version=TLS1_3 cipher=TLS_AES_256_GCM_SHA384 bits=256/256);
Fri, 24 Apr 2020 08:29:56 -0700 (PDT)
Date: Fri, 24 Apr 2020 08:29:53 -0700
From: Stephen Hemminger <stephen@networkplumber.org>
To: Ciara Power <ciara.power@intel.com>
Cc: dev@dpdk.org, kevin.laatz@intel.com, reshma.pattan@intel.com,
jerinjacobk@gmail.com, david.marchand@redhat.com, keith.wiles@intel.com,
mb@smartsharesystems.com, thomas@monjalon.net
Message-ID: <20200424082953.4b52ab9e@hermes.lan>
In-Reply-To: <20200424124159.45989-3-ciara.power@intel.com>
References: <20200319171907.60891-1-ciara.power@intel.com>
<20200424124159.45989-1-ciara.power@intel.com>
<20200424124159.45989-3-ciara.power@intel.com>
MIME-Version: 1.0
Content-Type: text/plain; charset=US-ASCII
Content-Transfer-Encoding: 7bit
Subject: Re: [dpdk-dev] [PATCH v4 02/18] telemetry: move code to metrics for
later reuse
X-BeenThere: dev@dpdk.org
X-Mailman-Version: 2.1.15
Precedence: list
List-Id: DPDK patches and discussions <dev.dpdk.org>
List-Unsubscribe: <https://mails.dpdk.org/options/dev>,
<mailto:dev-request@dpdk.org?subject=unsubscribe>
List-Archive: <http://mails.dpdk.org/archives/dev/>
List-Post: <mailto:dev@dpdk.org>
List-Help: <mailto:dev-request@dpdk.org?subject=help>
List-Subscribe: <https://mails.dpdk.org/listinfo/dev>,
<mailto:dev-request@dpdk.org?subject=subscribe>
Errors-To: dev-bounces@dpdk.org
Sender: "dev" <dev-bounces@dpdk.org>
On Fri, 24 Apr 2020 13:41:43 +0100
Ciara Power <ciara.power@intel.com> wrote:
> This commit moves some of the telemetry library code to a new file in
> the metrics library. No modifications are made to the moved code,
> except what is needed to allow it to compile and run. The additional
> code in metrics is built only when the Jansson library is present.
> Telemetry functions as normal, using the functions from the
> metrics_telemetry file. This move will enable code be reused by the new
> version of telemetry in a later commit, to support backward
> compatibility with the existing telemetry usage.
>
> Signed-off-by: Ciara Power <ciara.power@intel.com>
Minor comments, none of these are show stoppers.
> diff --git a/lib/librte_metrics/rte_metrics.c b/lib/librte_metrics/rte_metrics.c
> index df5e32c59f..9b38d7787c 100644
> --- a/lib/librte_metrics/rte_metrics.c
> +++ b/lib/librte_metrics/rte_metrics.c
> @@ -13,7 +13,6 @@
> #include <rte_memzone.h>
> #include <rte_spinlock.h>
>
> -#define RTE_METRICS_MAX_METRICS 256
> #define RTE_METRICS_MEMZONE_NAME "RTE_METRICS"
>
> /**
> diff --git a/lib/librte_metrics/rte_metrics.h b/lib/librte_metrics/rte_metrics.h
> index 77bffe08e4..466ca98c31 100644
> --- a/lib/librte_metrics/rte_metrics.h
> +++ b/lib/librte_metrics/rte_metrics.h
> @@ -32,6 +32,7 @@ extern "C" {
>
> /** Maximum length of metric name (including null-terminator) */
> #define RTE_METRICS_MAX_NAME_LEN 64
> +#define RTE_METRICS_MAX_METRICS 256
Exposing max metrics to API/ABI does limit you in the future.
> diff --git a/lib/librte_metrics/rte_metrics_telemetry.c b/lib/librte_metrics/rte_metrics_telemetry.c
> new file mode 100644
> index 0000000000..a6b2616714
> --- /dev/null
> +++ b/lib/librte_metrics/rte_metrics_telemetry.c
> @@ -0,0 +1,719 @@
...
> +static int32_t
> +rte_metrics_tel_is_port_active(int port_id)
portid should be uint16_t like rte_ethdev
return bool rather than int
> +{
> + int ret;
> +
> + ret = rte_eth_find_next(port_id);
> + if (ret == port_id)
> + return 1;
> +
> + METRICS_LOG_ERR("port_id: %d is invalid, not active",
> + port_id);
> +
> + return 0;
> +}
> +
> +static int32_t
> +rte_metrics_tel_reg_port_ethdev_to_metrics(uint16_t port_id)
> +{
> + int ret, num_xstats, ret_val, i;
> + struct rte_eth_xstat *eth_xstats = NULL;
> + struct rte_eth_xstat_name *eth_xstats_names = NULL;
You don't need to initialize all variables, and it is actually
bad practice with modern compilers since it breaks checking
for using values before set.
> +
> + if (!rte_eth_dev_is_valid_port(port_id)) {
> + METRICS_LOG_ERR("port_id: %d is invalid", port_id);
> + return -EINVAL;
> + }
Validity of port_id is already checked by rte_eth_xstats_get
> + num_xstats = rte_eth_xstats_get(port_id, NULL, 0);
> + if (num_xstats < 0) {
> + METRICS_LOG_ERR("rte_eth_xstats_get(%u) failed: %d",
> + port_id, num_xstats);
> + return -EPERM;
> + }
> +
> + eth_xstats = malloc(sizeof(struct rte_eth_xstat) * num_xstats);
> + if (eth_xstats == NULL) {
> + METRICS_LOG_ERR("Failed to malloc memory for xstats");
> + return -ENOMEM;
> + }
> +
> + ret = rte_eth_xstats_get(port_id, eth_xstats, num_xstats);
> + const char *xstats_names[num_xstats];
Please don't put declarations in the middle of the code.
You should malloc the names as well
> + eth_xstats_names = malloc(sizeof(struct rte_eth_xstat_name)
> + * num_xstats);
> + if (ret < 0 || ret > num_xstats) {
> + METRICS_LOG_ERR("rte_eth_xstats_get(%u) len%i failed: %d",
> + port_id, num_xstats, ret);
> + ret_val = -EPERM;
> + goto free_xstats;
> + }
> +
> + if (eth_xstats_names == NULL) {
> + METRICS_LOG_ERR("Failed to malloc memory for xstats_names");
> + ret_val = -ENOMEM;
> + goto free_xstats;
> + }
> +
> + ret = rte_eth_xstats_get_names(port_id, eth_xstats_names, num_xstats);
> + if (ret < 0 || ret > num_xstats) {
> + METRICS_LOG_ERR("rte_eth_xstats_get_names(%u) len%i failed: %d",
> + port_id, num_xstats, ret);
> + ret_val = -EPERM;
> + goto free_xstats;
> + }
> +
> + for (i = 0; i < num_xstats; i++)
> + xstats_names[i] = eth_xstats_names[eth_xstats[i].id].name;
> +
> + ret_val = rte_metrics_reg_names(xstats_names, num_xstats);
> + if (ret_val < 0) {
> + METRICS_LOG_ERR("rte_metrics_reg_names failed - metrics may already be registered");
> + ret_val = -1;
> + goto free_xstats;
> + }
> +
> + goto free_xstats;
> +
> +free_xstats:
> + free(eth_xstats);
> + free(eth_xstats_names);
> + return ret_val;
> +}
> +
> +int32_t
> +rte_metrics_tel_reg_all_ethdev(int *metrics_register_done, int *reg_index_list)
> +{
> + struct driver_index {
> + const void *dev_ops;
> + int reg_index;
> + } drv_idx[RTE_MAX_ETHPORTS] = { {0} };
> + int nb_drv_idx = 0;
> + uint16_t pid;
> + int ret;
> +
> + RTE_ETH_FOREACH_DEV(pid) {
> + int i;
> + /* Different device types have different numbers of stats, so
> + * first check if the stats for this type of device have
> + * already been registered
> + */
> + for (i = 0; i < nb_drv_idx; i++) {
> + if (rte_eth_devices[pid].dev_ops ==
> + drv_idx[i].dev_ops) {
> + reg_index_list[pid] = drv_idx[i].reg_index;
> + break;
> + }
> + }
> + if (i < nb_drv_idx)
> + continue; /* we found a match, go to next port */
> +
> + /* No match, register a new set of xstats for this port */
> + ret = rte_metrics_tel_reg_port_ethdev_to_metrics(pid);
> + if (ret < 0) {
> + METRICS_LOG_ERR("Failed to register ethdev metrics");
> + return -1;
> + }
> + reg_index_list[pid] = ret;
> + drv_idx[nb_drv_idx].dev_ops = rte_eth_devices[pid].dev_ops;
> + drv_idx[nb_drv_idx].reg_index = ret;
> + nb_drv_idx++;
> + }
> +
> + *metrics_register_done = 1;
> + return 0;
> +}
> +
> +static int32_t
> +rte_metrics_tel_update_metrics_ethdev(uint16_t port_id, int reg_start_index)
> +{
> + int ret, num_xstats, i;
> + struct rte_eth_xstat *eth_xstats;
> +
> + if (!rte_eth_dev_is_valid_port(port_id)) {
> + METRICS_LOG_ERR("port_id: %d is invalid", port_id);
> + return -EINVAL;
> + }
> +
> + ret = rte_metrics_tel_is_port_active(port_id);
> + if (ret < 1)
> + return -EINVAL;
> +
> + num_xstats = rte_eth_xstats_get(port_id, NULL, 0);
> + if (num_xstats < 0) {
> + METRICS_LOG_ERR("rte_eth_xstats_get(%u) failed: %d", port_id,
> + num_xstats);
> + return -EPERM;
> + }
The number of metrics on a port should not change (as long as it has
not been hot plugged). So you could optimize by knowing number of
stats from last query.
> + eth_xstats = malloc(sizeof(struct rte_eth_xstat) * num_xstats);
> + if (eth_xstats == NULL) {
> + METRICS_LOG_ERR("Failed to malloc memory for xstats");
> + return -ENOMEM;
> + }
> +
> + ret = rte_eth_xstats_get(port_id, eth_xstats, num_xstats);
> + if (ret < 0 || ret > num_xstats) {
> + free(eth_xstats);
> + METRICS_LOG_ERR("rte_eth_xstats_get(%u) len%i failed: %d",
> + port_id, num_xstats, ret);
> + return -EPERM;
> + }
> +
> + uint64_t xstats_values[num_xstats];
> + for (i = 0; i < num_xstats; i++)
> + xstats_values[i] = eth_xstats[i].value;
> +
> + ret = rte_metrics_update_values(port_id, reg_start_index, xstats_values,
> + num_xstats);
> + if (ret < 0) {
> + METRICS_LOG_ERR("Could not update metrics values");
> + free(eth_xstats);
> + return -EPERM;
> + }
> +
> + free(eth_xstats);
> + return 0;
> +}
> +
> +static int
> +rte_metrics_tel_get_metrics(uint32_t port_id, struct rte_metric_value
> + *metrics, struct rte_metric_name *names, int num_metrics)
Don't break awkwardly in the function declaration.
> +{
> + int ret, num_values;
> +
> + if (num_metrics < 0) {
if you don't want negative, make it unsigned.
> + METRICS_LOG_ERR("Invalid metrics count");
> + return -EINVAL;
> + } else if (num_metrics == 0) {
else after return non needed.
> + METRICS_LOG_ERR("No metrics to display (none have been registered)");
> + return -EPERM;
> + }
> +
> + if (metrics == NULL) {
> + METRICS_LOG_ERR("Metrics must be initialised.");
> + return -EINVAL;
> + }
> +
> + if (names == NULL) {
> + METRICS_LOG_ERR("Names must be initialised.");
> + return -EINVAL;
> + }
> +
> + ret = rte_metrics_get_names(names, num_metrics);
> + if (ret < 0 || ret > num_metrics) {
> + METRICS_LOG_ERR("Cannot get metrics names");
> + return -EPERM;
> + }
> +
> + num_values = rte_metrics_get_values(port_id, NULL, 0);
> + ret = rte_metrics_get_values(port_id, metrics, num_values);
> + if (ret < 0 || ret > num_values) {
> + METRICS_LOG_ERR("Cannot get metrics values");
> + return -EPERM;
> + }
> +
> + return 0;
> +}