Adding upstream version 1.44.3.upstream/1.44.3upstream

Signed-off-by: Daniel Baumann <daniel.baumann@progress-linux.org>

5 files changed, 511 insertions, 0 deletions

diff --git a/collectors/python.d.plugin/traefik/Makefile.inc b/collectors/python.d.plugin/traefik/Makefile.inc
new file mode 100644
index 00000000..926d56dd
--- /dev/null
+++ b/collectors/python.d.plugin/traefik/Makefile.inc
@@ -0,0 +1,13 @@
+# SPDX-License-Identifier: GPL-3.0-or-later
+
+# THIS IS NOT A COMPLETE Makefile
+# IT IS INCLUDED BY ITS PARENT'S Makefile.am
+# IT IS REQUIRED TO REFERENCE ALL FILES RELATIVE TO THE PARENT
+
+# install these files
+dist_python_DATA       += traefik/traefik.chart.py
+dist_pythonconfig_DATA += traefik/traefik.conf
+
+# do not install these files, but include them in the distribution
+dist_noinst_DATA       += traefik/README.md traefik/Makefile.inc
+
diff --git a/collectors/python.d.plugin/traefik/README.md b/collectors/python.d.plugin/traefik/README.md
new file mode 100644
index 00000000..40ed24f0
--- /dev/null
+++ b/collectors/python.d.plugin/traefik/README.md
@@ -0,0 +1,98 @@
+<!--
+title: "Traefik monitoring with Netdata"
+custom_edit_url: "https://github.com/netdata/netdata/edit/master/collectors/python.d.plugin/traefik/README.md"
+sidebar_label: "traefik-python.d.plugin"
+learn_status: "Published"
+learn_topic_type: "References"
+learn_rel_path: "Integrations/Monitor/Webapps"
+-->
+
+# Traefik collector
+
+Uses the `health` API to provide statistics.
+
+It produces:
+
+1. **Responses** by statuses
+
+    - success (1xx, 2xx, 304)
+    - error (5xx)
+    - redirect (3xx except 304)
+    - bad (4xx)
+    - other (all other responses)
+
+2. **Responses** by codes
+
+    - 2xx (successful)
+    - 5xx (internal server errors)
+    - 3xx (redirect)
+    - 4xx (bad)
+    - 1xx (informational)
+    - other (non-standart responses)
+
+3. **Detailed Response Codes** requests/s (number of responses for each response code family individually)
+
+4. **Requests**/s
+
+    - request statistics
+
+5. **Total response time**
+
+    - sum of all response time
+
+6. **Average response time**
+
+7. **Average response time per iteration**
+
+8. **Uptime**
+
+    - Traefik server uptime
+
+## Configuration
+
+Edit the `python.d/traefik.conf` configuration file using `edit-config` from the
+Netdata [config directory](https://github.com/netdata/netdata/blob/master/docs/configure/nodes.md), which is typically
+at `/etc/netdata`.
+
+```bash
+cd /etc/netdata   # Replace this path with your Netdata config directory, if different
+sudo ./edit-config python.d/traefik.conf
+```
+
+Needs only `url` to server's `health`
+
+Here is an example for local server:
+
+```yaml
+update_every: 1
+priority: 60000
+
+local:
+  url: 'http://localhost:8080/health'
+```
+
+Without configuration, module attempts to connect to `http://localhost:8080/health`.
+
+
+
+
+### Troubleshooting
+
+To troubleshoot issues with the `traefik` module, run the `python.d.plugin` with the debug option enabled. The 
+output will give you the output of the data collection job or error messages on why the collector isn't working.
+
+First, navigate to your plugins directory, usually they are located under `/usr/libexec/netdata/plugins.d/`. If that's 
+not the case on your system, open `netdata.conf` and look for the setting `plugins directory`. Once you're in the 
+plugin's directory, switch to the `netdata` user.
+
+```bash
+cd /usr/libexec/netdata/plugins.d/
+sudo su -s /bin/bash netdata
+```
+
+Now you can manually run the `traefik` module in debug mode:
+
+```bash
+./python.d.plugin traefik debug trace
+```
+
diff --git a/collectors/python.d.plugin/traefik/metadata.yaml b/collectors/python.d.plugin/traefik/metadata.yaml
new file mode 100644
index 00000000..dcfb098a
--- /dev/null
+++ b/collectors/python.d.plugin/traefik/metadata.yaml
@@ -0,0 +1,125 @@
+# This collector will not appear in documentation, as the go version is preferred,
+# https://github.com/netdata/go.d.plugin/blob/master/modules/traefik/README.md
+#
+# meta:
+#   plugin_name: python.d.plugin
+#   module_name: traefik
+#   monitored_instance:
+#     name: python.d traefik
+#     link: ''
+#     categories: []
+#     icon_filename: ''
+#   related_resources:
+#     integrations:
+#       list: []
+#   info_provided_to_referring_integrations:
+#     description: ''
+#   keywords: []
+#   most_popular: false
+# overview:
+#   data_collection:
+#     metrics_description: ''
+#     method_description: ''
+#   supported_platforms:
+#     include: []
+#     exclude: []
+#   multi_instance: true
+#   additional_permissions:
+#     description: ''
+#   default_behavior:
+#     auto_detection:
+#       description: ''
+#     limits:
+#       description: ''
+#     performance_impact:
+#       description: ''
+# setup:
+#   prerequisites:
+#     list: []
+#   configuration:
+#     file:
+#       name: ''
+#       description: ''
+#     options:
+#       description: ''
+#       folding:
+#         title: ''
+#         enabled: true
+#       list: []
+#     examples:
+#       folding:
+#         enabled: true
+#         title: ''
+#       list: []
+# troubleshooting:
+#   problems:
+#     list: []
+# alerts: []
+# metrics:
+#   folding:
+#     title: Metrics
+#     enabled: false
+#   description: ""
+#   availability: []
+#   scopes:
+#   - name: global
+#     description: ""
+#     labels: []
+#     metrics:
+#     - name: traefik.response_statuses
+#       description: Response statuses
+#       unit: "requests/s"
+#       chart_type: stacked
+#       dimensions:
+#       - name: success
+#       - name: error
+#       - name: redirect
+#       - name: bad
+#       - name: other
+#     - name: traefik.response_codes
+#       description: Responses by codes
+#       unit: "requests/s"
+#       chart_type: stacked
+#       dimensions:
+#       - name: 2xx
+#       - name: 5xx
+#       - name: 3xx
+#       - name: 4xx
+#       - name: 1xx
+#       - name: other
+#     - name: traefik.detailed_response_codes
+#       description: Detailed response codes
+#       unit: "requests/s"
+#       chart_type: stacked
+#       dimensions:
+#       - name: a dimension for each response code family
+#     - name: traefik.requests
+#       description: Requests
+#       unit: "requests/s"
+#       chart_type: line
+#       dimensions:
+#       - name: requests
+#     - name: traefik.total_response_time
+#       description: Total response time
+#       unit: "seconds"
+#       chart_type: line
+#       dimensions:
+#       - name: response
+#     - name: traefik.average_response_time
+#       description: Average response time
+#       unit: "milliseconds"
+#       chart_type: line
+#       dimensions:
+#       - name: response
+#     - name: traefik.average_response_time_per_iteration
+#       description: Average response time per iteration
+#       unit: "milliseconds"
+#       chart_type: line
+#       dimensions:
+#       - name: response
+#     - name: traefik.uptime
+#       description: Uptime
+#       unit: "seconds"
+#       chart_type: line
+#       dimensions:
+#       - name: uptime
diff --git a/collectors/python.d.plugin/traefik/traefik.chart.py b/collectors/python.d.plugin/traefik/traefik.chart.py
new file mode 100644
index 00000000..5a498467
--- /dev/null
+++ b/collectors/python.d.plugin/traefik/traefik.chart.py
@@ -0,0 +1,198 @@
+# -*- coding: utf-8 -*-
+# Description: traefik netdata python.d module
+# Author: Alexandre Menezes (@ale_menezes)
+# SPDX-License-Identifier: GPL-3.0-or-later
+
+from collections import defaultdict
+from json import loads
+
+from bases.FrameworkServices.UrlService import UrlService
+
+ORDER = [
+    'response_statuses',
+    'response_codes',
+    'detailed_response_codes',
+    'requests',
+    'total_response_time',
+    'average_response_time',
+    'average_response_time_per_iteration',
+    'uptime'
+]
+
+CHARTS = {
+    'response_statuses': {
+        'options': [None, 'Response statuses', 'requests/s', 'responses', 'traefik.response_statuses', 'stacked'],
+        'lines': [
+            ['successful_requests', 'success', 'incremental'],
+            ['server_errors', 'error', 'incremental'],
+            ['redirects', 'redirect', 'incremental'],
+            ['bad_requests', 'bad', 'incremental'],
+            ['other_requests', 'other', 'incremental']
+        ]
+    },
+    'response_codes': {
+        'options': [None, 'Responses by codes', 'requests/s', 'responses', 'traefik.response_codes', 'stacked'],
+        'lines': [
+            ['2xx', None, 'incremental'],
+            ['5xx', None, 'incremental'],
+            ['3xx', None, 'incremental'],
+            ['4xx', None, 'incremental'],
+            ['1xx', None, 'incremental'],
+            ['other', None, 'incremental']
+        ]
+    },
+    'detailed_response_codes': {
+        'options': [None, 'Detailed response codes', 'requests/s', 'responses', 'traefik.detailed_response_codes',
+                    'stacked'],
+        'lines': []
+    },
+    'requests': {
+        'options': [None, 'Requests', 'requests/s', 'requests', 'traefik.requests', 'line'],
+        'lines': [
+            ['total_count', 'requests', 'incremental']
+        ]
+    },
+    'total_response_time': {
+        'options': [None, 'Total response time', 'seconds', 'timings', 'traefik.total_response_time', 'line'],
+        'lines': [
+            ['total_response_time_sec', 'response', 'absolute', 1, 10000]
+        ]
+    },
+    'average_response_time': {
+        'options': [None, 'Average response time', 'milliseconds', 'timings', 'traefik.average_response_time', 'line'],
+        'lines': [
+            ['average_response_time_sec', 'response', 'absolute', 1, 1000]
+        ]
+    },
+    'average_response_time_per_iteration': {
+        'options': [None, 'Average response time per iteration', 'milliseconds', 'timings',
+                    'traefik.average_response_time_per_iteration', 'line'],
+        'lines': [
+            ['average_response_time_per_iteration_sec', 'response', 'incremental', 1, 10000]
+        ]
+    },
+    'uptime': {
+        'options': [None, 'Uptime', 'seconds', 'uptime', 'traefik.uptime', 'line'],
+        'lines': [
+            ['uptime_sec', 'uptime', 'absolute']
+        ]
+    }
+}
+
+HEALTH_STATS = [
+    'uptime_sec',
+    'average_response_time_sec',
+    'total_response_time_sec',
+    'total_count',
+    'total_status_code_count'
+]
+
+
+class Service(UrlService):
+    def __init__(self, configuration=None, name=None):
+        UrlService.__init__(self, configuration=configuration, name=name)
+        self.url = self.configuration.get('url', 'http://localhost:8080/health')
+        self.order = ORDER
+        self.definitions = CHARTS
+        self.last_total_response_time = 0
+        self.last_total_count = 0
+        self.data = {
+            'successful_requests': 0,
+            'redirects': 0,
+            'bad_requests': 0,
+            'server_errors': 0,
+            'other_requests': 0,
+            '1xx': 0,
+            '2xx': 0,
+            '3xx': 0,
+            '4xx': 0,
+            '5xx': 0,
+            'other': 0,
+            'average_response_time_per_iteration_sec': 0,
+        }
+
+    def _get_data(self):
+        data = self._get_raw_data()
+
+        if not data:
+            return None
+
+        data = loads(data)
+
+        self.get_data_per_code_status(raw_data=data)
+
+        self.get_data_per_code_family(raw_data=data)
+
+        self.get_data_per_code(raw_data=data)
+
+        self.data.update(fetch_data_(raw_data=data, metrics=HEALTH_STATS))
+
+        self.data['average_response_time_sec'] *= 1000000
+        self.data['total_response_time_sec'] *= 10000
+        if data['total_count'] != self.last_total_count:
+            self.data['average_response_time_per_iteration_sec'] = \
+                (data['total_response_time_sec'] - self.last_total_response_time) * \
+                1000000 / (data['total_count'] - self.last_total_count)
+        else:
+            self.data['average_response_time_per_iteration_sec'] = 0
+        self.last_total_response_time = data['total_response_time_sec']
+        self.last_total_count = data['total_count']
+
+        return self.data or None
+
+    def get_data_per_code_status(self, raw_data):
+        data = defaultdict(int)
+        for code, value in raw_data['total_status_code_count'].items():
+            code_prefix = code[0]
+            if code_prefix == '1' or code_prefix == '2' or code == '304':
+                data['successful_requests'] += value
+            elif code_prefix == '3':
+                data['redirects'] += value
+            elif code_prefix == '4':
+                data['bad_requests'] += value
+            elif code_prefix == '5':
+                data['server_errors'] += value
+            else:
+                data['other_requests'] += value
+        self.data.update(data)
+
+    def get_data_per_code_family(self, raw_data):
+        data = defaultdict(int)
+        for code, value in raw_data['total_status_code_count'].items():
+            code_prefix = code[0]
+            if code_prefix == '1':
+                data['1xx'] += value
+            elif code_prefix == '2':
+                data['2xx'] += value
+            elif code_prefix == '3':
+                data['3xx'] += value
+            elif code_prefix == '4':
+                data['4xx'] += value
+            elif code_prefix == '5':
+                data['5xx'] += value
+            else:
+                data['other'] += value
+        self.data.update(data)
+
+    def get_data_per_code(self, raw_data):
+        for code, value in raw_data['total_status_code_count'].items():
+            if self.charts:
+                if code not in self.data:
+                    self.charts['detailed_response_codes'].add_dimension([code, code, 'incremental'])
+                self.data[code] = value
+
+
+def fetch_data_(raw_data, metrics):
+    data = dict()
+
+    for metric in metrics:
+        value = raw_data
+        metrics_list = metric.split('.')
+        try:
+            for m in metrics_list:
+                value = value[m]
+        except KeyError:
+            continue
+        data['_'.join(metrics_list)] = value
+
+    return data
diff --git a/collectors/python.d.plugin/traefik/traefik.conf b/collectors/python.d.plugin/traefik/traefik.conf
new file mode 100644
index 00000000..e3f182d3
--- /dev/null
+++ b/collectors/python.d.plugin/traefik/traefik.conf
@@ -0,0 +1,77 @@
+# netdata python.d.plugin configuration for traefik health data API
+#
+# This file is in YaML format. Generally the format is:
+#
+# name: value
+#
+# There are 2 sections:
+#  - global variables
+#  - one or more JOBS
+#
+# JOBS allow you to collect values from multiple sources.
+# Each source will have its own set of charts.
+#
+# JOB parameters have to be indented (using spaces only, example below).
+
+# ----------------------------------------------------------------------
+# Global Variables
+# These variables set the defaults for all JOBs, however each JOB
+# may define its own, overriding the defaults.
+
+# update_every sets the default data collection frequency.
+# If unset, the python.d.plugin default is used.
+# update_every: 1
+
+# priority controls the order of charts at the netdata dashboard.
+# Lower numbers move the charts towards the top of the page.
+# If unset, the default for python.d.plugin is used.
+# priority: 60000
+
+# penalty indicates whether to apply penalty to update_every in case of failures.
+# Penalty will increase every 5 failed updates in a row. Maximum penalty is 10 minutes.
+# penalty: yes
+
+# autodetection_retry sets the job re-check interval in seconds.
+# The job is not deleted if check fails.
+# Attempts to start the job are made once every autodetection_retry.
+# This feature is disabled by default.
+# autodetection_retry: 0
+
+# ----------------------------------------------------------------------
+# JOBS (data collection sources)
+#
+# The default JOBS share the same *name*. JOBS with the same name
+# are mutually exclusive. Only one of them will be allowed running at
+# any time. This allows autodetection to try several alternatives and
+# pick the one that works.
+#
+# Any number of jobs is supported.
+#
+# All python.d.plugin JOBS (for all its modules) support a set of
+# predefined parameters. These are:
+#
+# job_name:
+#     name: myname            # the JOB's name as it will appear at the
+#                             # dashboard (by default is the job_name)
+#                             # JOBs sharing a name are mutually exclusive
+#     update_every: 1         # the JOB's data collection frequency
+#     priority: 60000         # the JOB's order on the dashboard
+#     penalty: yes            # the JOB's penalty
+#     autodetection_retry: 0  # the JOB's re-check interval in seconds
+#
+# Additionally to the above, traefik plugin also supports the following:
+#
+#     url: '<scheme>://<host>:<port>/<health_page_api>'
+#     # http://localhost:8080/health
+#
+# if the URL is password protected, the following are supported:
+#
+#     user: 'username'
+#     pass: 'password'
+#
+# ----------------------------------------------------------------------
+# AUTO-DETECTION JOBS
+# only one of them will run (they have the same name)
+#
+local:
+ url: 'http://localhost:8080/health'