summaryrefslogtreecommitdiffstats
path: root/monitor
diff options
context:
space:
mode:
authorRutuja Surve <rutuja.r.surve@gmail.com>2018-02-21 13:17:53 +0000
committerRutuja Surve <rutuja.r.surve@gmail.com>2018-03-30 20:01:42 +0100
commit4b89af12f547bd8eebc01572e1b9a02f89c5fa7c (patch)
treee57d298aa778b79fed5a03ee88334526aa4f7fc0 /monitor
parent5053b1c137d1d22678a416abbaf4dd4cce3e5285 (diff)
Barometer automated installation script for jump server
and compute/controller nodes JIRA: BOTTLENECK-182 Install barometer for collecting OVS and collectd statistics as docker containers on all nodes Change-Id: I8ae7e2bcbe95ab6e1224e08828c822d50367f616 Signed-off-by: Rutuja Surve <rutuja.r.surve@gmail.com>
Diffstat (limited to 'monitor')
-rw-r--r--monitor/automated-dashboard-datasource.py4
-rw-r--r--monitor/barometer-collectd.conf174
-rw-r--r--monitor/barometer-install-script.sh5
-rw-r--r--monitor/barometer_automated_client_install.py36
-rw-r--r--monitor/barometer_client.conf174
-rw-r--r--monitor/barometer_install_client.sh5
-rw-r--r--monitor/client_ip_configure.py27
-rw-r--r--monitor/custom-query-dashboard.json2
-rw-r--r--monitor/monitoring.sh12
-rw-r--r--monitor/prototype_dashboard_collapsible.json2040
-rw-r--r--monitor/server_ip_configure.py27
11 files changed, 2504 insertions, 2 deletions
diff --git a/monitor/automated-dashboard-datasource.py b/monitor/automated-dashboard-datasource.py
index 1e1b42f7..69f3ebe6 100644
--- a/monitor/automated-dashboard-datasource.py
+++ b/monitor/automated-dashboard-datasource.py
@@ -63,7 +63,9 @@ def post(url, data):
ip_address = socket.gethostbyname(socket.gethostname())
+_create_data_source(ip_address, 3000)
_create_dashboard(ip_address, 3000, '/var/lib/grafana/' +
'dashboards/' +
'prometheus-system_rev1.json')
-_create_data_source(ip_address, 3000)
+_create_dashboard(ip_address, 3000,
+ 'prototype_dashboard_collapsible.json')
diff --git a/monitor/barometer-collectd.conf b/monitor/barometer-collectd.conf
new file mode 100644
index 00000000..ecb1261c
--- /dev/null
+++ b/monitor/barometer-collectd.conf
@@ -0,0 +1,174 @@
+#
+# Config file for collectd(1).
+# Please read collectd.conf(5) for a list of options.
+# http://collectd.org/
+#
+
+##############################################################################
+# Global #
+#----------------------------------------------------------------------------#
+# Global settings for the daemon. #
+##############################################################################
+
+#Hostname "localhost"
+#FQDNLookup true
+#BaseDir "${prefix}/var/lib/collectd"
+#PIDFile "${prefix}/var/run/collectd.pid"
+#PluginDir "${exec_prefix}/lib/collectd"
+#TypesDB "/opt/collectd/share/collectd/types.db"
+
+#----------------------------------------------------------------------------#
+# When enabled, plugins are loaded automatically with the default options #
+# when an appropriate <Plugin ...> block is encountered. #
+# Disabled by default. #
+#----------------------------------------------------------------------------#
+#AutoLoadPlugin false
+
+#----------------------------------------------------------------------------#
+# When enabled, internal statistics are collected, using "collectd" as the #
+# plugin name. #
+# Disabled by default. #
+#----------------------------------------------------------------------------#
+#CollectInternalStats false
+
+#----------------------------------------------------------------------------#
+# Interval at which to query values. This may be overwritten on a per-plugin #
+# base by using the 'Interval' option of the LoadPlugin block: #
+# <LoadPlugin foo> #
+# Interval 60 #
+# </LoadPlugin> #
+#----------------------------------------------------------------------------#
+#Interval 10
+
+#MaxReadInterval 86400
+#Timeout 2
+#ReadThreads 5
+#WriteThreads 5
+
+# Limit the size of the write queue. Default is no limit. Setting up a limit is
+# recommended for servers handling a high volume of traffic.
+#WriteQueueLimitHigh 1000000
+#WriteQueueLimitLow 800000
+
+##############################################################################
+# Logging #
+#----------------------------------------------------------------------------#
+# Plugins which provide logging functions should be loaded first, so log #
+# messages generated when loading or configuring other plugins can be #
+# accessed. #
+##############################################################################
+
+LoadPlugin syslog
+#LoadPlugin logfile
+#LoadPlugin log_logstash
+
+#<Plugin logfile>
+# LogLevel info
+# File STDOUT
+# Timestamp true
+# PrintSeverity false
+#</Plugin>
+
+#<Plugin log_logstash>
+# LogLevel info
+# File "${prefix}/var/log/collectd.json.log"
+#</Plugin>
+
+#<Plugin syslog>
+# LogLevel info
+#</Plugin>
+
+##############################################################################
+# LoadPlugin section #
+#----------------------------------------------------------------------------#
+# Lines beginning with a single `#' belong to plugins which have been built #
+# but are disabled by default. #
+# #
+# Lines beginning with `##' belong to plugins which have not been built due #
+# to missing dependencies or because they have been deactivated explicitly. #
+##############################################################################
+
+##LoadPlugin barometer
+LoadPlugin cpu
+LoadPlugin interface
+LoadPlugin load
+LoadPlugin memory
+LoadPlugin network
+LoadPlugin ovs_events
+LoadPlugin ovs_stats
+LoadPlugin rrdtool
+LoadPlugin write_http
+
+##############################################################################
+# Plugin configuration #
+#----------------------------------------------------------------------------#
+# In this section configuration stubs for each plugin are provided. A desc- #
+# ription of those options is available in the collectd.conf(5) manual page. #
+##############################################################################
+
+#<Plugin "barometer">
+# Device "/dev/i2c-0";
+# Oversampling 512
+# PressureOffset 0.0
+# TemperatureOffset 0.0
+# Normalization 2
+# Altitude 238.0
+# TemperatureSensor "myserver/onewire-F10FCA000800/temperature"
+#</Plugin>
+
+#<Plugin cpu>
+# ReportByCpu true
+# ReportByState true
+# ValuesPercentage false
+# ReportNumCpu false
+# ReportGuestState false
+# SubtractGuestState true
+#</Plugin>
+
+#<Plugin interface>
+# Interface "eth0"
+# IgnoreSelected false
+# ReportInactive true
+# UniqueName false
+#</Plugin>
+
+#<Plugin memcached>
+# <Instance "local">
+# #Host "memcache.example.com"
+# Address "127.0.0.1"
+# Port "11211"
+# </Instance>
+#</Plugin>
+
+#<Plugin memory>
+# ValuesAbsolute true
+# ValuesPercentage false
+#</Plugin>
+
+<Plugin network>
+ Listen "192.168.121.2" "25826"
+</Plugin>
+
+<Plugin ovs_events>
+ Port "6640"
+ Address "127.0.0.1"
+ Socket "/var/run/openvswitch/db.sock"
+ Interfaces "br0" "veth0"
+ SendNotification true
+ DispatchValues false
+</Plugin>
+
+<Plugin ovs_stats>
+ Port "6640"
+ Address "127.0.0.1"
+ Socket "/var/run/openvswitch/db.sock"
+ Bridges "br0" "br_ext"
+</Plugin>
+
+<Plugin write_http>
+ <Node "collectd_exporter">
+ URL "http://192.168.121.2:9103/collectd-post"
+ Format "JSON"
+ StoreRates false
+ </Node>
+</Plugin>
diff --git a/monitor/barometer-install-script.sh b/monitor/barometer-install-script.sh
new file mode 100644
index 00000000..9dc20093
--- /dev/null
+++ b/monitor/barometer-install-script.sh
@@ -0,0 +1,5 @@
+docker pull opnfv/barometer
+sudo docker run --name bottlenecks-barometer-server -tid --net=host -v `pwd`/../src/collectd_sample_configs:/opt/collectd/etc/collectd.conf.d \
+-v /home/opnfv/bottlenecks/monitor/barometer-collectd.conf:/src/barometer/src/collectd/collectd/src/collectd.conf \
+-v /etc/barometer-config/barometer_client_collectd.conf:/opt/collectd/etc/collectd.conf \
+-v /var/run:/var/run -v /tmp:/tmp --privileged opnfv/barometer /run_collectd.sh
diff --git a/monitor/barometer_automated_client_install.py b/monitor/barometer_automated_client_install.py
new file mode 100644
index 00000000..7bbfa701
--- /dev/null
+++ b/monitor/barometer_automated_client_install.py
@@ -0,0 +1,36 @@
+##############################################################################
+# Copyright (c) 2018 Huawei Tech and others.
+#
+# All rights reserved. This program and the accompanying materials
+# are made available under the terms of the Apache License, Version 2.0
+# which accompanies this distribution, and is available at
+# http://www.apache.org/licenses/LICENSE-2.0
+##############################################################################
+
+import logging
+import sys
+import yaml
+sys.path.insert(0, '/home/opnfv/bottlenecks/utils/infra_setup/passwordless_SSH/')
+import ssh
+
+logger = logging.getLogger(__name__)
+with open('/tmp/pod.yaml') as f:
+ dataMap = yaml.safe_load(f)
+ for x in dataMap:
+ for y in dataMap[x]:
+ if (y['role']=='Controller') or (y['role']=='Compute'):
+ ip = str(y['ip'])
+ user = str(y['user'])
+ pwd = str(y['password'])
+ ssh_d = ssh.SSH(user, host= ip, password= pwd)
+ status, stdout, stderr = ssh_d.execute("cd /etc && mkdir barometer-config")
+ if status:
+ raise Exception("Command failed with non-zero status.")
+ logger.info(stdout.splitlines())
+ with open("/home/opnfv/bottlenecks/monitor/barometer_client.conf") as stdin_file:
+ ssh_d.run("cat > /etc/barometer-config/barometer_client_collectd.conf", stdin=stdin_file)
+
+ with open("/home/opnfv/bottlenecks/monitor/barometer_install_client.sh") as stdin_file:
+ ssh_d.run("cat > /etc/barometer-config/install.sh", stdin=stdin_file)
+
+ ssh_d.run("cd /etc/barometer-config/ && bash ./install.sh")
diff --git a/monitor/barometer_client.conf b/monitor/barometer_client.conf
new file mode 100644
index 00000000..fc29e72c
--- /dev/null
+++ b/monitor/barometer_client.conf
@@ -0,0 +1,174 @@
+#
+# Config file for collectd(1).
+# Please read collectd.conf(5) for a list of options.
+# http://collectd.org/
+#
+
+##############################################################################
+# Global #
+#----------------------------------------------------------------------------#
+# Global settings for the daemon. #
+##############################################################################
+
+#Hostname "localhost"
+#FQDNLookup true
+#BaseDir "${prefix}/var/lib/collectd"
+#PIDFile "${prefix}/var/run/collectd.pid"
+#PluginDir "${exec_prefix}/lib/collectd"
+#TypesDB "/opt/collectd/share/collectd/types.db"
+
+#----------------------------------------------------------------------------#
+# When enabled, plugins are loaded automatically with the default options #
+# when an appropriate <Plugin ...> block is encountered. #
+# Disabled by default. #
+#----------------------------------------------------------------------------#
+#AutoLoadPlugin false
+
+#----------------------------------------------------------------------------#
+# When enabled, internal statistics are collected, using "collectd" as the #
+# plugin name. #
+# Disabled by default. #
+#----------------------------------------------------------------------------#
+#CollectInternalStats false
+
+#----------------------------------------------------------------------------#
+# Interval at which to query values. This may be overwritten on a per-plugin #
+# base by using the 'Interval' option of the LoadPlugin block: #
+# <LoadPlugin foo> #
+# Interval 60 #
+# </LoadPlugin> #
+#----------------------------------------------------------------------------#
+#Interval 10
+
+#MaxReadInterval 86400
+#Timeout 2
+#ReadThreads 5
+#WriteThreads 5
+
+# Limit the size of the write queue. Default is no limit. Setting up a limit is
+# recommended for servers handling a high volume of traffic.
+#WriteQueueLimitHigh 1000000
+#WriteQueueLimitLow 800000
+
+##############################################################################
+# Logging #
+#----------------------------------------------------------------------------#
+# Plugins which provide logging functions should be loaded first, so log #
+# messages generated when loading or configuring other plugins can be #
+# accessed. #
+##############################################################################
+
+LoadPlugin syslog
+#LoadPlugin logfile
+#LoadPlugin log_logstash
+
+#<Plugin logfile>
+# LogLevel info
+# File STDOUT
+# Timestamp true
+# PrintSeverity false
+#</Plugin>
+
+#<Plugin log_logstash>
+# LogLevel info
+# File "${prefix}/var/log/collectd.json.log"
+#</Plugin>
+
+#<Plugin syslog>
+# LogLevel info
+#</Plugin>
+
+##############################################################################
+# LoadPlugin section #
+#----------------------------------------------------------------------------#
+# Lines beginning with a single `#' belong to plugins which have been built #
+# but are disabled by default. #
+# #
+# Lines beginning with `##' belong to plugins which have not been built due #
+# to missing dependencies or because they have been deactivated explicitly. #
+##############################################################################
+
+##LoadPlugin barometer
+LoadPlugin cpu
+LoadPlugin interface
+LoadPlugin load
+LoadPlugin memory
+LoadPlugin network
+LoadPlugin ovs_events
+LoadPlugin ovs_stats
+LoadPlugin rrdtool
+LoadPlugin write_http
+
+##############################################################################
+# Plugin configuration #
+#----------------------------------------------------------------------------#
+# In this section configuration stubs for each plugin are provided. A desc- #
+# ription of those options is available in the collectd.conf(5) manual page. #
+##############################################################################
+
+#<Plugin "barometer">
+# Device "/dev/i2c-0";
+# Oversampling 512
+# PressureOffset 0.0
+# TemperatureOffset 0.0
+# Normalization 2
+# Altitude 238.0
+# TemperatureSensor "myserver/onewire-F10FCA000800/temperature"
+#</Plugin>
+
+#<Plugin cpu>
+# ReportByCpu true
+# ReportByState true
+# ValuesPercentage false
+# ReportNumCpu false
+# ReportGuestState false
+# SubtractGuestState true
+#</Plugin>
+
+#<Plugin interface>
+# Interface "eth0"
+# IgnoreSelected false
+# ReportInactive true
+# UniqueName false
+#</Plugin>
+
+#<Plugin memcached>
+# <Instance "local">
+# #Host "memcache.example.com"
+# Address "127.0.0.1"
+# Port "11211"
+# </Instance>
+#</Plugin>
+
+#<Plugin memory>
+# ValuesAbsolute true
+# ValuesPercentage false
+#</Plugin>
+
+<Plugin network>
+ Server "192.168.121.2" "25826"
+</Plugin>
+
+<Plugin ovs_events>
+ Port "6640"
+ Address "127.0.0.1"
+ Socket "/var/run/openvswitch/db.sock"
+ Interfaces "br0" "veth0"
+ SendNotification true
+ DispatchValues false
+</Plugin>
+
+<Plugin ovs_stats>
+ Port "6640"
+ Address "127.0.0.1"
+ Socket "/var/run/openvswitch/db.sock"
+ Bridges "br0" "br_ext"
+</Plugin>
+
+<Plugin write_http>
+ <Node "collectd_exporter">
+ URL "http://192.168.121.2:9103/collectd-post"
+ Format "JSON"
+ StoreRates false
+ </Node>
+</Plugin>
diff --git a/monitor/barometer_install_client.sh b/monitor/barometer_install_client.sh
new file mode 100644
index 00000000..d75adf1a
--- /dev/null
+++ b/monitor/barometer_install_client.sh
@@ -0,0 +1,5 @@
+docker pull opnfv/barometer
+sudo docker run --name bottlenecks-barometer-client -tid --net=host -v `pwd`/../src/collectd_sample_configs:/opt/collectd/etc/collectd.conf.d \
+-v /etc/barometer-config/barometer_client_collectd.conf:/src/barometer/src/collectd/collectd/src/collectd.conf \
+-v /etc/barometer-config/barometer_client_collectd.conf:/opt/collectd/etc/collectd.conf \
+-v /var/run:/var/run -v /tmp:/tmp --privileged opnfv/barometer /run_collectd.sh
diff --git a/monitor/client_ip_configure.py b/monitor/client_ip_configure.py
new file mode 100644
index 00000000..9bfb12ce
--- /dev/null
+++ b/monitor/client_ip_configure.py
@@ -0,0 +1,27 @@
+##############################################################################
+# Copyright (c) 2018 Huawei Tech and others.
+#
+# All rights reserved. This program and the accompanying materials
+# are made available under the terms of the Apache License, Version 2.0
+# which accompanies this distribution, and is available at
+# http://www.apache.org/licenses/LICENSE-2.0
+##############################################################################
+import fileinput
+import re
+import logging
+import socket
+import requests
+from oslo_serialization import jsonutils
+
+logger = logging.getLogger(__name__)
+ip_address = socket.gethostbyname(socket.gethostname())
+
+for line in fileinput.input(inplace=1):
+ ip = " Server \"" + str(ip_address) +"\" \"25826\""
+ line = re.sub(r'.*Server.*25826.*', r''+str(ip), line.rstrip())
+ print(line)
+
+for line in fileinput.input(inplace=1):
+ ip = " URL \"http://"+str(ip_address)+":9103/collectd-post\""
+ line = re.sub(r'.*URL.*collectd-post.*', r''+str(ip), line.rstrip())
+ print(line)
diff --git a/monitor/custom-query-dashboard.json b/monitor/custom-query-dashboard.json
index 8ee83570..7f2e53a3 100644
--- a/monitor/custom-query-dashboard.json
+++ b/monitor/custom-query-dashboard.json
@@ -17,7 +17,7 @@
"targets": [
{
"hide": false,
- "expr": "Pre-existing Query",
+ "expr": "Sample Prometheus Query",
"step": 1800,
"legendFormat": "",
"intervalFactor": 2,
diff --git a/monitor/monitoring.sh b/monitor/monitoring.sh
index 16cb3086..01c1edc3 100644
--- a/monitor/monitoring.sh
+++ b/monitor/monitoring.sh
@@ -60,11 +60,23 @@ sudo docker run \
--name=cadvisor \
google/cadvisor:v0.25.0 \ -storage_driver=Prometheus
+# Configure IP Address in barometer client configuration
+python client_ip_configure.py barometer_client.conf
+
+# Configure IP Address in barometer server configuration
+python server_ip_configure.py barometer-collectd.conf
+
# Automate Collectd Client
python automate_collectd_client.py
# Automate Cadvisor Client
python automate_cadvisor_client.py
+# Automate Barometer installation for jump server
+bash ./barometer-install-script.sh
+
+# Automate Barometer installation for compute/controller nodes
+python barometer_automated_client_install.py
+
# Automate Prometheus Datasource and Grafana Dashboard creation
python automated-dashboard-datasource.py
diff --git a/monitor/prototype_dashboard_collapsible.json b/monitor/prototype_dashboard_collapsible.json
new file mode 100644
index 00000000..aca25234
--- /dev/null
+++ b/monitor/prototype_dashboard_collapsible.json
@@ -0,0 +1,2040 @@
+{
+ "annotations": {
+ "list": []
+ },
+ "description": "A simple overview of the most important Docker host and container metrics. (Barometer/Prometheus)",
+ "editable": true,
+ "gnetId": 893,
+ "graphTooltip": 1,
+ "hideControls": false,
+ "id": 13,
+ "links": [],
+ "refresh": "15m",
+ "rows": [
+ {
+ "collapse": false,
+ "height": 193,
+ "panels": [
+ {
+ "content": "<img src=\"http://prometheus.io/assets/prometheus_logo_grey.svg\" alt=\"Prometheus logo\" style=\"height: 40px;\">\n<span style=\"font-family: 'Open Sans', 'Helvetica Neue', Helvetica; font-size: 25px;vertical-align: text-top;color: #bbbfc2;margin-left: 10px;\">Prometheus</span>\n\n<p style=\"margin-top: 10px;\">You're using Prometheus, an open-source systems monitoring and alerting toolkit originally built at SoundCloud. For more information, check out the <a href=\"http://www.grafana.org/\">Grafana</a> and <a href=\"http://prometheus.io/\">Prometheus</a> projects.</p>",
+ "editable": true,
+ "error": false,
+ "id": 91,
+ "links": [],
+ "mode": "html",
+ "span": 6,
+ "style": {},
+ "title": "",
+ "transparent": true,
+ "type": "text"
+ },
+ {
+ "content": "#### Samples Ingested\nThis graph displays the count of samples ingested by the Prometheus server, as measured over the last 5 minutes, per time series in the range vector. When troubleshooting an issue on IRC or Github, this is often the first stat requested by the Prometheus team. ",
+ "editable": true,
+ "error": false,
+ "id": 92,
+ "links": [],
+ "mode": "markdown",
+ "span": 6,
+ "style": {},
+ "title": "",
+ "transparent": true,
+ "type": "text"
+ }
+ ],
+ "repeat": null,
+ "repeatIteration": null,
+ "repeatRowId": null,
+ "showTitle": false,
+ "title": "Prometheus Information",
+ "titleSize": "h6"
+ },
+ {
+ "collapse": true,
+ "height": 239,
+ "panels": [
+ {
+ "cacheTimeout": null,
+ "colorBackground": false,
+ "colorValue": false,
+ "colors": [
+ "rgba(245, 54, 54, 0.9)",
+ "rgba(237, 129, 40, 0.89)",
+ "rgba(50, 172, 45, 0.97)"
+ ],
+ "datasource": "automated-ds",
+ "decimals": 0,
+ "editable": true,
+ "error": false,
+ "format": "s",
+ "gauge": {
+ "maxValue": 100,
+ "minValue": 0,
+ "show": false,
+ "thresholdLabels": false,
+ "thresholdMarkers": true
+ },
+ "height": "",
+ "id": 24,
+ "interval": null,
+ "links": [],
+ "mappingType": 1,
+ "mappingTypes": [
+ {
+ "name": "value to text",
+ "value": 1
+ },
+ {
+ "name": "range to text",
+ "value": 2
+ }
+ ],
+ "maxDataPoints": 100,
+ "nullPointMode": "connected",
+ "nullText": null,
+ "postfix": "",
+ "postfixFontSize": "30%",
+ "prefix": "",
+ "prefixFontSize": "20%",
+ "rangeMaps": [
+ {
+ "from": "null",
+ "text": "N/A",
+ "to": "null"
+ }
+ ],
+ "span": 3,
+ "sparkline": {
+ "fillColor": "rgba(31, 118, 189, 0.18)",
+ "full": false,
+ "lineColor": "rgb(31, 120, 193)",
+ "show": false
+ },
+ "tableColumn": "",
+ "targets": [
+ {
+ "expr": "time() - node_boot_time{instance=~\"$server:.*\"}",
+ "hide": false,
+ "intervalFactor": 2,
+ "legendFormat": "",
+ "refId": "A",
+ "step": 1800
+ }
+ ],
+ "thresholds": "",
+ "title": "Uptime",
+ "type": "singlestat",
+ "valueFontSize": "80%",
+ "valueMaps": [
+ {
+ "op": "=",
+ "text": "N/A",
+ "value": "null"
+ }
+ ],
+ "valueName": "current"
+ },
+ {
+ "cacheTimeout": null,
+ "colorBackground": false,
+ "colorValue": false,
+ "colors": [
+ "rgba(245, 54, 54, 0.9)",
+ "rgba(237, 129, 40, 0.89)",
+ "rgba(50, 172, 45, 0.97)"
+ ],
+ "datasource": "automated-ds",
+ "editable": true,
+ "error": false,
+ "format": "none",
+ "gauge": {
+ "maxValue": 100,
+ "minValue": 0,
+ "show": false,
+ "thresholdLabels": false,
+ "thresholdMarkers": true
+ },
+ "id": 31,
+ "interval": null,
+ "links": [],
+ "mappingType": 1,
+ "mappingTypes": [
+ {
+ "name": "value to text",
+ "value": 1
+ },
+ {
+ "name": "range to text",
+ "value": 2
+ }
+ ],
+ "maxDataPoints": 100,
+ "nullPointMode": "connected",
+ "nullText": null,
+ "postfix": "",
+ "postfixFontSize": "50%",
+ "prefix": "",
+ "prefixFontSize": "50%",
+ "rangeMaps": [
+ {
+ "from": "null",
+ "text": "N/A",
+ "to": "null"
+ }
+ ],
+ "span": 3,
+ "sparkline": {
+ "fillColor": "rgba(31, 118, 189, 0.18)",
+ "full": false,
+ "lineColor": "rgb(31, 120, 193)",
+ "show": false
+ },
+ "tableColumn": "",
+ "targets": [
+ {
+ "expr": "count(rate(container_last_seen{name=~\".+\"}[$interval]))",
+ "intervalFactor": 2,
+ "refId": "A",
+ "step": 1800
+ }
+ ],
+ "thresholds": "",
+ "title": "Containers",
+ "type": "singlestat",
+ "valueFontSize": "120%",
+ "valueMaps": [
+ {
+ "op": "=",
+ "text": "N/A",
+ "value": "null"
+ }
+ ],
+ "valueName": "current"
+ },
+ {
+ "cacheTimeout": null,
+ "colorBackground": false,
+ "colorValue": false,
+ "colors": [
+ "rgba(50, 172, 45, 0.97)",
+ "rgba(237, 129, 40, 0.89)",
+ "rgba(245, 54, 54, 0.9)"
+ ],
+ "datasource": "automated-ds",
+ "decimals": 1,
+ "editable": true,
+ "error": false,
+ "format": "percentunit",
+ "gauge": {
+ "maxValue": 1,
+ "minValue": 0,
+ "show": true,
+ "thresholdLabels": false,
+ "thresholdMarkers": true
+ },
+ "id": 26,
+ "interval": null,
+ "links": [],
+ "mappingType": 1,
+ "mappingTypes": [
+ {
+ "name": "value to text",
+ "value": 1
+ },
+ {
+ "name": "range to text",
+ "value": 2
+ }
+ ],
+ "maxDataPoints": 100,
+ "nullPointMode": "connected",
+ "nullText": null,
+ "postfix": "",
+ "postfixFontSize": "50%",
+ "prefix": "",
+ "prefixFontSize": "50%",
+ "rangeMaps": [
+ {
+ "from": "null",
+ "text": "N/A",
+ "to": "null"
+ }
+ ],
+ "span": 3,
+ "sparkline": {
+ "fillColor": "rgba(31, 118, 189, 0.18)",
+ "full": false,
+ "lineColor": "rgb(31, 120, 193)",
+ "show": false
+ },
+ "tableColumn": "",
+ "targets": [
+ {
+ "expr": "min((node_filesystem_size{fstype=~\"xfs|ext4\",instance=~\"$server:.*\"} - node_filesystem_free{fstype=~\"xfs|ext4\",instance=~\"$server:.*\"} )/ node_filesystem_size{fstype=~\"xfs|ext4\",instance=~\"$server:.*\"})",
+ "hide": false,
+ "intervalFactor": 2,
+ "refId": "A",
+ "step": 1800
+ }
+ ],
+ "thresholds": "0.75, 0.90",
+ "title": "Disk space",
+ "type": "singlestat",
+ "valueFontSize": "80%",
+ "valueMaps": [
+ {
+ "op": "=",
+ "text": "N/A",
+ "value": "null"
+ }
+ ],
+ "valueName": "current"
+ },
+ {
+ "cacheTimeout": null,
+ "colorBackground": false,
+ "colorValue": false,
+ "colors": [
+ "rgba(50, 172, 45, 0.97)",
+ "rgba(237, 129, 40, 0.89)",
+ "rgba(245, 54, 54, 0.9)"
+ ],
+ "datasource": "automated-ds",
+ "decimals": 0,
+ "editable": true,
+ "error": false,
+ "format": "percent",
+ "gauge": {
+ "maxValue": 100,
+ "minValue": 0,
+ "show": true,
+ "thresholdLabels": false,
+ "thresholdMarkers": true
+ },
+ "id": 25,
+ "interval": null,
+ "links": [],
+ "mappingType": 1,
+ "mappingTypes": [
+ {
+ "name": "value to text",
+ "value": 1
+ },
+ {
+ "name": "range to text",
+ "value": 2
+ }
+ ],
+ "maxDataPoints": 100,
+ "nullPointMode": "connected",
+ "nullText": null,
+ "postfix": "",
+ "postfixFontSize": "50%",
+ "prefix": "",
+ "prefixFontSize": "50%",
+ "rangeMaps": [
+ {
+ "from": "null",
+ "text": "N/A",
+ "to": "null"
+ }
+ ],
+ "span": 3,
+ "sparkline": {
+ "fillColor": "rgba(31, 118, 189, 0.18)",
+ "full": false,
+ "lineColor": "rgb(31, 120, 193)",
+ "show": false
+ },
+ "tableColumn": "",
+ "targets": [
+ {
+ "expr": "((node_memory_MemTotal{instance=~\"$server:.*\"} - node_memory_MemAvailable{instance=~\"$server:.*\"}) / node_memory_MemTotal{instance=~\"$server:.*\"}) * 100",
+ "intervalFactor": 2,
+ "refId": "A",
+ "step": 1800
+ }
+ ],
+ "thresholds": "70, 90",
+ "title": "Memory",
+ "type": "singlestat",
+ "valueFontSize": "80%",
+ "valueMaps": [
+ {
+ "op": "=",
+ "text": "N/A",
+ "value": "null"
+ }
+ ],
+ "valueName": "current"
+ }
+ ],
+ "repeat": null,
+ "repeatIteration": null,
+ "repeatRowId": null,
+ "showTitle": false,
+ "title": "Container, Disk, Memory Statistics",
+ "titleSize": "h6"
+ },
+ {
+ "collapse": true,
+ "height": 218,
+ "panels": [
+ {
+ "aliasColors": {
+ "SENT": "#BF1B00"
+ },
+ "bars": false,
+ "dashLength": 10,
+ "dashes": false,
+ "datasource": "automated-ds",
+ "editable": true,
+ "error": false,
+ "fill": 1,
+ "grid": {},
+ "id": 19,
+ "legend": {
+ "avg": false,
+ "current": false,
+ "max": false,
+ "min": false,
+ "show": false,
+ "total": false,
+ "values": false
+ },
+ "lines": true,
+ "linewidth": 1,
+ "links": [],
+ "nullPointMode": "null as zero",
+ "percentage": false,
+ "pointradius": 1,
+ "points": false,
+ "renderer": "flot",
+ "seriesOverrides": [],
+ "spaceLength": 10,
+ "span": 3,
+ "stack": false,
+ "steppedLine": false,
+ "targets": [
+ {
+ "expr": "sum(rate(container_network_receive_bytes_total{id=\"/\"}[$interval])) by (id)",
+ "intervalFactor": 2,
+ "legendFormat": "RECEIVED",
+ "refId": "A",
+ "step": 600
+ },
+ {
+ "expr": "- sum(rate(container_network_transmit_bytes_total{id=\"/\"}[$interval])) by (id)",
+ "hide": false,
+ "intervalFactor": 2,
+ "legendFormat": "SENT",
+ "refId": "B",
+ "step": 600
+ }
+ ],
+ "thresholds": [],
+ "timeFrom": null,
+ "timeShift": null,
+ "title": "Network Traffic",
+ "tooltip": {
+ "msResolution": true,
+ "shared": true,
+ "sort": 0,
+ "value_type": "cumulative"
+ },
+ "transparent": false,
+ "type": "graph",
+ "xaxis": {
+ "buckets": null,
+ "mode": "time",
+ "name": null,
+ "show": false,
+ "values": []
+ },
+ "yaxes": [
+ {
+ "format": "bytes",
+ "label": null,
+ "logBase": 1,
+ "max": null,
+ "min": null,
+ "show": true
+ },
+ {
+ "format": "short",
+ "label": null,
+ "logBase": 1,
+ "max": null,
+ "min": null,
+ "show": false
+ }
+ ]
+ },
+ {
+ "aliasColors": {
+ "{id=\"/\",instance=\"cadvisor:8080\",job=\"prometheus\"}": "#BA43A9"
+ },
+ "bars": false,
+ "dashLength": 10,
+ "dashes": false,
+ "datasource": "automated-ds",
+ "editable": true,
+ "error": false,
+ "fill": 1,
+ "grid": {},
+ "id": 5,
+ "legend": {
+ "avg": false,
+ "current": false,
+ "max": false,
+ "min": false,
+ "show": false,
+ "total": false,
+ "values": false
+ },
+ "lines": true,
+ "linewidth": 1,
+ "links": [],
+ "nullPointMode": "null as zero",
+ "percentage": false,
+ "pointradius": 5,
+ "points": false,
+ "renderer": "flot",
+ "seriesOverrides": [],
+ "spaceLength": 10,
+ "span": 3,
+ "stack": true,
+ "steppedLine": false,
+ "targets": [
+ {
+ "expr": "sum(rate(container_cpu_system_seconds_total[1m]))",
+ "hide": true,
+ "intervalFactor": 2,
+ "legendFormat": "a",
+ "refId": "B",
+ "step": 120
+ },
+ {
+ "expr": "sum(rate(container_cpu_system_seconds_total{name=~\".+\"}[1m]))",
+ "hide": true,
+ "interval": "",
+ "intervalFactor": 2,
+ "legendFormat": "nur container",
+ "refId": "F",
+ "step": 10
+ },
+ {
+ "expr": "sum(rate(container_cpu_system_seconds_total{id=\"/\"}[1m]))",
+ "hide": true,
+ "interval": "",
+ "intervalFactor": 2,
+ "legendFormat": "nur docker host",
+ "metric": "",
+ "refId": "A",
+ "step": 20
+ },
+ {
+ "expr": "sum(rate(process_cpu_seconds_total[$interval])) * 100",
+ "hide": false,
+ "interval": "",
+ "intervalFactor": 2,
+ "legendFormat": "host",
+ "metric": "",
+ "refId": "C",
+ "step": 600
+ },
+ {
+ "expr": "sum(rate(container_cpu_system_seconds_total{name=~\".+\"}[1m])) + sum(rate(container_cpu_system_seconds_total{id=\"/\"}[1m])) + sum(rate(process_cpu_seconds_total[1m]))",
+ "hide": true,
+ "intervalFactor": 2,
+ "legendFormat": "",
+ "refId": "D",
+ "step": 120
+ }
+ ],
+ "thresholds": [],
+ "timeFrom": null,
+ "timeShift": null,
+ "title": "CPU Usage",
+ "tooltip": {
+ "msResolution": true,
+ "shared": true,
+ "sort": 0,
+ "value_type": "cumulative"
+ },
+ "type": "graph",
+ "xaxis": {
+ "buckets": null,
+ "mode": "time",
+ "name": null,
+ "show": false,
+ "values": []
+ },
+ "yaxes": [
+ {
+ "format": "percent",
+ "label": "",
+ "logBase": 1,
+ "max": null,
+ "min": null,
+ "show": true
+ },
+ {
+ "format": "short",
+ "label": null,
+ "logBase": 1,
+ "max": null,
+ "min": null,
+ "show": false
+ }
+ ]
+ },
+ {
+ "alert": {
+ "conditions": [
+ {
+ "evaluator": {
+ "params": [
+ 1.25
+ ],
+ "type": "gt"
+ },
+ "query": {
+ "params": [
+ "A",
+ "5m",
+ "now"
+ ]
+ },
+ "reducer": {
+ "params": [],
+ "type": "avg"
+ },
+ "type": "query"
+ }
+ ],
+ "executionErrorState": "alerting",
+ "frequency": "60s",
+ "handler": 1,
+ "name": "Panel Title alert",
+ "noDataState": "keep_state",
+ "notifications": [
+ {
+ "id": 1
+ }
+ ]
+ },
+ "aliasColors": {},
+ "bars": false,
+ "dashLength": 10,
+ "dashes": false,
+ "datasource": "automated-ds",
+ "decimals": 0,
+ "editable": true,
+ "error": false,
+ "fill": 1,
+ "id": 28,
+ "legend": {
+ "avg": false,
+ "current": false,
+ "max": false,
+ "min": false,
+ "show": false,
+ "total": false,
+ "values": false
+ },
+ "lines": true,
+ "linewidth": 1,
+ "links": [],
+ "nullPointMode": "connected",
+ "percentage": false,
+ "pointradius": 5,
+ "points": false,
+ "renderer": "flot",
+ "seriesOverrides": [],
+ "spaceLength": 10,
+ "span": 3,
+ "stack": false,
+ "steppedLine": false,
+ "targets": [
+ {
+ "expr": "node_load1{instance=~\"$server:.*\"} / count by(job, instance)(count by(job, instance, cpu)(node_cpu{instance=~\"$server:.*\"}))",
+ "intervalFactor": 2,
+ "refId": "A",
+ "step": 600
+ }
+ ],
+ "thresholds": [
+ {
+ "colorMode": "critical",
+ "fill": true,
+ "line": true,
+ "op": "gt",
+ "value": 1.25
+ }
+ ],
+ "timeFrom": null,
+ "timeShift": null,
+ "title": "Load",
+ "tooltip": {
+ "msResolution": false,
+ "shared": true,
+ "sort": 0,
+ "value_type": "individual"
+ },
+ "type": "graph",
+ "xaxis": {
+ "buckets": null,
+ "mode": "time",
+ "name": null,
+ "show": false,
+ "values": []
+ },
+ "yaxes": [
+ {
+ "format": "percentunit",
+ "label": null,
+ "logBase": 1,
+ "max": "1.50",
+ "min": null,
+ "show": true
+ },
+ {
+ "format": "short",
+ "label": null,
+ "logBase": 1,
+ "max": null,
+ "min": null,
+ "show": false
+ }
+ ]
+ },
+ {
+ "alert": {
+ "conditions": [
+ {
+ "evaluator": {
+ "params": [
+ 850000000000
+ ],
+ "type": "gt"
+ },
+ "query": {
+ "params": [
+ "A",
+ "5m",
+ "now"
+ ]
+ },
+ "reducer": {
+ "params": [],
+ "type": "avg"
+ },
+ "type": "query"
+ }
+ ],
+ "executionErrorState": "alerting",
+ "frequency": "60s",
+ "handler": 1,
+ "name": "Free/Used Disk Space alert",
+ "noDataState": "keep_state",
+ "notifications": [
+ {
+ "id": 1
+ }
+ ]
+ },
+ "aliasColors": {
+ "Belegete Festplatte": "#BF1B00",
+ "Free Disk Space": "#7EB26D",
+ "Used Disk Space": "#7EB26D",
+ "{}": "#BF1B00"
+ },
+ "bars": false,
+ "dashLength": 10,
+ "dashes": false,
+ "datasource": "automated-ds",
+ "editable": true,
+ "error": false,
+ "fill": 1,
+ "grid": {},
+ "id": 13,
+ "legend": {
+ "avg": false,
+ "current": false,
+ "max": false,
+ "min": false,
+ "show": false,
+ "total": false,
+ "values": false
+ },
+ "lines": true,
+ "linewidth": 1,
+ "links": [],
+ "nullPointMode": "null as zero",
+ "percentage": false,
+ "pointradius": 5,
+ "points": false,
+ "renderer": "flot",
+ "seriesOverrides": [
+ {
+ "alias": "Used Disk Space",
+ "yaxis": 1
+ }
+ ],
+ "spaceLength": 10,
+ "span": 3,
+ "stack": true,
+ "steppedLine": false,
+ "targets": [
+ {
+ "expr": "node_filesystem_size{fstype=\"aufs\"} - node_filesystem_free{fstype=\"aufs\"}",
+ "hide": false,
+ "intervalFactor": 2,
+ "legendFormat": "Used Disk Space",
+ "refId": "A",
+ "step": 600
+ }
+ ],
+ "thresholds": [
+ {
+ "colorMode": "critical",
+ "fill": true,
+ "line": true,
+ "op": "gt",
+ "value": 850000000000
+ }
+ ],
+ "timeFrom": null,
+ "timeShift": null,
+ "title": "Used Disk Space",
+ "tooltip": {
+ "msResolution": true,
+ "shared": true,
+ "sort": 0,
+ "value_type": "individual"
+ },
+ "type": "graph",
+ "xaxis": {
+ "buckets": null,
+ "mode": "time",
+ "name": null,
+ "show": false,
+ "values": []
+ },
+ "yaxes": [
+ {
+ "format": "bytes",
+ "label": "",
+ "logBase": 1,
+ "max": 1000000000000,
+ "min": 0,
+ "show": true
+ },
+ {
+ "format": "short",
+ "label": null,
+ "logBase": 1,
+ "max": null,
+ "min": null,
+ "show": false
+ }
+ ]
+ }
+ ],
+ "repeat": null,
+ "repeatIteration": null,
+ "repeatRowId": null,
+ "showTitle": false,
+ "title": "Network, CPU, Load Statistics",
+ "titleSize": "h6"
+ },
+ {
+ "collapse": true,
+ "height": 249,
+ "panels": [
+ {
+ "aliasColors": {},
+ "bars": false,
+ "dashLength": 10,
+ "dashes": false,
+ "datasource": "automated-ds",
+ "editable": true,
+ "error": false,
+ "fill": 5,
+ "grid": {},
+ "id": 1,
+ "legend": {
+ "alignAsTable": true,
+ "avg": false,
+ "current": false,
+ "max": false,
+ "min": false,
+ "rightSide": true,
+ "show": true,
+ "total": false,
+ "values": false
+ },
+ "lines": true,
+ "linewidth": 1,
+ "links": [],
+ "nullPointMode": "null as zero",
+ "percentage": false,
+ "pointradius": 5,
+ "points": false,
+ "renderer": "flot",
+ "seriesOverrides": [],
+ "spaceLength": 10,
+ "span": 8,
+ "stack": true,
+ "steppedLine": false,
+ "targets": [
+ {
+ "expr": "sum(rate(container_cpu_usage_seconds_total{name=~\".+\"}[$interval])) by (name) * 100",
+ "hide": false,
+ "interval": "",
+ "intervalFactor": 2,
+ "legendFormat": "{{name}}",
+ "metric": "",
+ "refId": "F",
+ "step": 240
+ }
+ ],
+ "thresholds": [],
+ "timeFrom": null,
+ "timeShift": null,
+ "title": "CPU Usage per Container",
+ "tooltip": {
+ "msResolution": true,
+ "shared": true,
+ "sort": 0,
+ "value_type": "individual"
+ },
+ "type": "graph",
+ "xaxis": {
+ "buckets": null,
+ "mode": "time",
+ "name": null,
+ "show": true,
+ "values": []
+ },
+ "yaxes": [
+ {
+ "format": "percent",
+ "label": "",
+ "logBase": 1,
+ "max": null,
+ "show": true
+ },
+ {
+ "format": "short",
+ "label": null,
+ "logBase": 1,
+ "max": null,
+ "min": null,
+ "show": false
+ }
+ ]
+ },
+ {
+ "aliasColors": {
+ "IN on /sda": "#7EB26D",
+ "OUT on /sda": "#890F02"
+ },
+ "bars": false,
+ "dashLength": 10,
+ "dashes": false,
+ "datasource": "automated-ds",
+ "editable": true,
+ "error": false,
+ "fill": 1,
+ "grid": {},
+ "id": 3,
+ "legend": {
+ "avg": false,
+ "current": false,
+ "max": false,
+ "min": false,
+ "show": false,
+ "total": false,
+ "values": false
+ },
+ "lines": true,
+ "linewidth": 1,
+ "links": [],
+ "nullPointMode": "null as zero",
+ "percentage": false,
+ "pointradius": 5,
+ "points": false,
+ "renderer": "flot",
+ "seriesOverrides": [],
+ "spaceLength": 10,
+ "span": 2,
+ "stack": false,
+ "steppedLine": false,
+ "targets": [
+ {
+ "expr": "-sum(rate(node_disk_bytes_read[$interval])) by (device)",
+ "hide": false,
+ "intervalFactor": 2,
+ "legendFormat": "OUT on /{{device}}",
+ "metric": "node_disk_bytes_read",
+ "refId": "A",
+ "step": 600
+ },
+ {
+ "expr": "sum(rate(node_disk_bytes_written[$interval])) by (device)",
+ "intervalFactor": 2,
+ "legendFormat": "IN on /{{device}}",
+ "metric": "",
+ "refId": "B",
+ "step": 600
+ }
+ ],
+ "thresholds": [],
+ "timeFrom": null,
+ "timeShift": null,
+ "title": "Disk I/O",
+ "tooltip": {
+ "msResolution": true,
+ "shared": true,
+ "sort": 0,
+ "value_type": "cumulative"
+ },
+ "type": "graph",
+ "xaxis": {
+ "buckets": null,
+ "mode": "time",
+ "name": null,
+ "show": false,
+ "values": []
+ },
+ "yaxes": [
+ {
+ "format": "Bps",
+ "label": null,
+ "logBase": 1,
+ "max": null,
+ "min": null,
+ "show": true
+ },
+ {
+ "format": "short",
+ "label": null,
+ "logBase": 1,
+ "max": null,
+ "min": null,
+ "show": false
+ }
+ ]
+ },
+ {
+ "aliasColors": {
+ "Available Memory": "#7EB26D",
+ "Unavailable Memory": "#7EB26D"
+ },
+ "bars": false,
+ "dashLength": 10,
+ "dashes": false,
+ "datasource": "automated-ds",
+ "editable": true,
+ "error": false,
+ "fill": 1,
+ "grid": {},
+ "id": 38,
+ "legend": {
+ "avg": false,
+ "current": false,
+ "max": false,
+ "min": false,
+ "show": false,
+ "total": false,
+ "values": false
+ },
+ "lines": true,
+ "linewidth": 1,
+ "links": [],
+ "nullPointMode": "null as zero",
+ "percentage": false,
+ "pointradius": 5,
+ "points": false,
+ "renderer": "flot",
+ "seriesOverrides": [],
+ "spaceLength": 10,
+ "span": 2,
+ "stack": true,
+ "steppedLine": false,
+ "targets": [
+ {
+ "expr": "container_memory_rss{name=~\".+\"}",
+ "hide": true,
+ "intervalFactor": 2,
+ "legendFormat": "{{__name__}}",
+ "refId": "D",
+ "step": 20
+ },
+ {
+ "expr": "sum(container_memory_rss{name=~\".+\"})",
+ "hide": true,
+ "intervalFactor": 2,
+ "legendFormat": "{{__name__}}",
+ "refId": "A",
+ "step": 20
+ },
+ {
+ "expr": "container_memory_usage_bytes{name=~\".+\"}",
+ "hide": true,
+ "intervalFactor": 2,
+ "legendFormat": "{{name}}",
+ "refId": "B",
+ "step": 20
+ },
+ {
+ "expr": "container_memory_rss{id=\"/\"}",
+ "hide": true,
+ "intervalFactor": 2,
+ "legendFormat": "{{__name__}}",
+ "refId": "C",
+ "step": 20
+ },
+ {
+ "expr": "sum(container_memory_rss)",
+ "hide": true,
+ "intervalFactor": 2,
+ "legendFormat": "{{__name__}}",
+ "refId": "E",
+ "step": 20
+ },
+ {
+ "expr": "node_memory_Buffers",
+ "hide": true,
+ "intervalFactor": 2,
+ "legendFormat": "node_memory_Dirty",
+ "refId": "N",
+ "step": 30
+ },
+ {
+ "expr": "node_memory_MemFree",
+ "hide": true,
+ "intervalFactor": 2,
+ "legendFormat": "{{__name__}}",
+ "refId": "F",
+ "step": 20
+ },
+ {
+ "expr": "node_memory_MemAvailable",
+ "hide": true,
+ "intervalFactor": 2,
+ "legendFormat": "Available Memory",
+ "refId": "H",
+ "step": 20
+ },
+ {
+ "expr": "node_memory_MemTotal - node_memory_MemAvailable",
+ "hide": false,
+ "intervalFactor": 2,
+ "legendFormat": "Unavailable Memory",
+ "refId": "G",
+ "step": 600
+ },
+ {
+ "expr": "node_memory_Inactive",
+ "hide": true,
+ "intervalFactor": 2,
+ "legendFormat": "{{__name__}}",
+ "refId": "I",
+ "step": 30
+ },
+ {
+ "expr": "node_memory_KernelStack",
+ "hide": true,
+ "intervalFactor": 2,
+ "legendFormat": "{{__name__}}",
+ "refId": "J",
+ "step": 30
+ },
+ {
+ "expr": "node_memory_Active",
+ "hide": true,
+ "intervalFactor": 2,
+ "legendFormat": "{{__name__}}",
+ "refId": "K",
+ "step": 30
+ },
+ {
+ "expr": "node_memory_MemTotal - (node_memory_Active + node_memory_MemFree + node_memory_Inactive)",
+ "hide": true,
+ "intervalFactor": 2,
+ "legendFormat": "Unknown",
+ "refId": "L",
+ "step": 40
+ },
+ {
+ "expr": "node_memory_MemFree + node_memory_Inactive ",
+ "hide": true,
+ "intervalFactor": 2,
+ "legendFormat": "{{__name__}}",
+ "refId": "M",
+ "step": 30
+ },
+ {
+ "expr": "container_memory_rss{name=~\".+\"}",
+ "hide": true,
+ "intervalFactor": 2,
+ "legendFormat": "{{__name__}}",
+ "refId": "O",
+ "step": 30
+ },
+ {
+ "expr": "node_memory_Inactive + node_memory_MemFree + node_memory_MemAvailable",
+ "hide": true,
+ "intervalFactor": 2,
+ "legendFormat": "",
+ "refId": "P",
+ "step": 40
+ }
+ ],
+ "thresholds": [
+ {
+ "colorMode": "critical",
+ "fill": true,
+ "line": true,
+ "op": "gt",
+ "value": 10000000000
+ }
+ ],
+ "timeFrom": null,
+ "timeShift": null,
+ "title": "Available Memory",
+ "tooltip": {
+ "msResolution": true,
+ "shared": true,
+ "sort": 0,
+ "value_type": "individual"
+ },
+ "type": "graph",
+ "xaxis": {
+ "buckets": null,
+ "mode": "time",
+ "name": null,
+ "show": false,
+ "values": []
+ },
+ "yaxes": [
+ {
+ "format": "bytes",
+ "label": "",
+ "logBase": 1,
+ "max": 16000000000,
+ "min": 0,
+ "show": true
+ },
+ {
+ "format": "short",
+ "label": null,
+ "logBase": 1,
+ "max": null,
+ "min": null,
+ "show": false
+ }
+ ]
+ }
+ ],
+ "repeat": null,
+ "repeatIteration": null,
+ "repeatRowId": null,
+ "showTitle": false,
+ "title": "Container-wise CPU usage, Disk I/O, Memory Available",
+ "titleSize": "h6"
+ },
+ {
+ "collapse": true,
+ "height": 251,
+ "panels": [
+ {
+ "aliasColors": {},
+ "bars": false,
+ "dashLength": 10,
+ "dashes": false,
+ "datasource": "automated-ds",
+ "editable": true,
+ "error": false,
+ "fill": 1,
+ "grid": {},
+ "id": 8,
+ "legend": {
+ "alignAsTable": true,
+ "avg": false,
+ "current": false,
+ "max": false,
+ "min": false,
+ "rightSide": true,
+ "show": true,
+ "total": false,
+ "values": false
+ },
+ "lines": true,
+ "linewidth": 2,
+ "links": [],
+ "nullPointMode": "null as zero",
+ "percentage": false,
+ "pointradius": 5,
+ "points": false,
+ "renderer": "flot",
+ "seriesOverrides": [],
+ "spaceLength": 10,
+ "span": 6,
+ "stack": false,
+ "steppedLine": false,
+ "targets": [
+ {
+ "expr": "sum(rate(container_network_receive_bytes_total{name=~\".+\"}[$interval])) by (name)",
+ "intervalFactor": 2,
+ "legendFormat": "{{name}}",
+ "refId": "A",
+ "step": 240
+ },
+ {
+ "expr": "- rate(container_network_transmit_bytes_total{name=~\".+\"}[$interval])",
+ "hide": true,
+ "intervalFactor": 2,
+ "legendFormat": "{{name}}",
+ "refId": "B",
+ "step": 10
+ }
+ ],
+ "thresholds": [],
+ "timeFrom": null,
+ "timeShift": null,
+ "title": "Received Network Traffic per Container",
+ "tooltip": {
+ "msResolution": true,
+ "shared": true,
+ "sort": 0,
+ "value_type": "cumulative"
+ },
+ "transparent": false,
+ "type": "graph",
+ "xaxis": {
+ "buckets": null,
+ "mode": "time",
+ "name": null,
+ "show": true,
+ "values": []
+ },
+ "yaxes": [
+ {
+ "format": "Bps",
+ "label": null,
+ "logBase": 1,
+ "max": null,
+ "min": null,
+ "show": true
+ },
+ {
+ "format": "short",
+ "label": null,
+ "logBase": 1,
+ "max": null,
+ "min": null,
+ "show": true
+ }
+ ]
+ },
+ {
+ "aliasColors": {},
+ "bars": false,
+ "dashLength": 10,
+ "dashes": false,
+ "datasource": "automated-ds",
+ "editable": true,
+ "error": false,
+ "fill": 1,
+ "grid": {},
+ "id": 9,
+ "legend": {
+ "alignAsTable": true,
+ "avg": false,
+ "current": false,
+ "hideEmpty": false,
+ "hideZero": false,
+ "max": false,
+ "min": false,
+ "rightSide": true,
+ "show": true,
+ "total": false,
+ "values": false
+ },
+ "lines": true,
+ "linewidth": 2,
+ "links": [],
+ "nullPointMode": "null as zero",
+ "percentage": false,
+ "pointradius": 5,
+ "points": false,
+ "renderer": "flot",
+ "seriesOverrides": [],
+ "spaceLength": 10,
+ "span": 6,
+ "stack": false,
+ "steppedLine": false,
+ "targets": [
+ {
+ "expr": "sum(rate(container_network_transmit_bytes_total{name=~\".+\"}[$interval])) by (name)",
+ "intervalFactor": 2,
+ "legendFormat": "{{name}}",
+ "refId": "A",
+ "step": 240
+ },
+ {
+ "expr": "rate(container_network_transmit_bytes_total{id=\"/\"}[$interval])",
+ "hide": true,
+ "intervalFactor": 2,
+ "legendFormat": "",
+ "refId": "B",
+ "step": 10
+ }
+ ],
+ "thresholds": [],
+ "timeFrom": null,
+ "timeShift": null,
+ "title": "Sent Network Traffic per Container",
+ "tooltip": {
+ "msResolution": true,
+ "shared": true,
+ "sort": 0,
+ "value_type": "cumulative"
+ },
+ "transparent": false,
+ "type": "graph",
+ "xaxis": {
+ "buckets": null,
+ "mode": "time",
+ "name": null,
+ "show": true,
+ "values": []
+ },
+ "yaxes": [
+ {
+ "format": "Bps",
+ "label": "",
+ "logBase": 1,
+ "max": null,
+ "min": null,
+ "show": true
+ },
+ {
+ "format": "short",
+ "label": "",
+ "logBase": 10,
+ "max": 8,
+ "min": 0,
+ "show": false
+ }
+ ]
+ }
+ ],
+ "repeat": null,
+ "repeatIteration": null,
+ "repeatRowId": null,
+ "showTitle": false,
+ "title": "Network Traffic",
+ "titleSize": "h6"
+ },
+ {
+ "collapse": true,
+ "height": 250,
+ "panels": [
+ {
+ "aliasColors": {},
+ "bars": false,
+ "dashLength": 10,
+ "dashes": false,
+ "datasource": "automated-ds",
+ "editable": true,
+ "error": false,
+ "fill": 3,
+ "grid": {},
+ "id": 10,
+ "legend": {
+ "alignAsTable": true,
+ "avg": false,
+ "current": false,
+ "max": false,
+ "min": false,
+ "rightSide": true,
+ "show": true,
+ "total": false,
+ "values": false
+ },
+ "lines": true,
+ "linewidth": 2,
+ "links": [],
+ "nullPointMode": "null as zero",
+ "percentage": false,
+ "pointradius": 5,
+ "points": false,
+ "renderer": "flot",
+ "seriesOverrides": [],
+ "spaceLength": 10,
+ "span": 6,
+ "stack": true,
+ "steppedLine": false,
+ "targets": [
+ {
+ "expr": "sum(container_memory_rss{name=~\".+\"}) by (name)",
+ "hide": false,
+ "intervalFactor": 2,
+ "legendFormat": "{{name}}",
+ "refId": "A",
+ "step": 240
+ },
+ {
+ "expr": "container_memory_usage_bytes{name=~\".+\"}",
+ "hide": true,
+ "intervalFactor": 2,
+ "legendFormat": "{{name}}",
+ "refId": "B",
+ "step": 240
+ }
+ ],
+ "thresholds": [],
+ "timeFrom": null,
+ "timeShift": null,
+ "title": "Memory Usage per Container",
+ "tooltip": {
+ "msResolution": true,
+ "shared": true,
+ "sort": 0,
+ "value_type": "individual"
+ },
+ "type": "graph",
+ "xaxis": {
+ "buckets": null,
+ "mode": "time",
+ "name": null,
+ "show": true,
+ "values": []
+ },
+ "yaxes": [
+ {
+ "format": "bytes",
+ "label": "",
+ "logBase": 1,
+ "max": null,
+ "min": null,
+ "show": true
+ },
+ {
+ "format": "short",
+ "label": null,
+ "logBase": 1,
+ "max": null,
+ "min": null,
+ "show": true
+ }
+ ]
+ },
+ {
+ "aliasColors": {},
+ "bars": false,
+ "dashLength": 10,
+ "dashes": false,
+ "datasource": "automated-ds",
+ "editable": true,
+ "error": false,
+ "fill": 3,
+ "grid": {},
+ "id": 34,
+ "legend": {
+ "alignAsTable": true,
+ "avg": false,
+ "current": false,
+ "max": false,
+ "min": false,
+ "rightSide": true,
+ "show": true,
+ "total": false,
+ "values": false
+ },
+ "lines": true,
+ "linewidth": 2,
+ "links": [],
+ "nullPointMode": "null as zero",
+ "percentage": false,
+ "pointradius": 5,
+ "points": false,
+ "renderer": "flot",
+ "seriesOverrides": [],
+ "spaceLength": 10,
+ "span": 6,
+ "stack": true,
+ "steppedLine": false,
+ "targets": [
+ {
+ "expr": "sum(container_memory_swap{name=~\".+\"}) by (name)",
+ "hide": false,
+ "intervalFactor": 2,
+ "legendFormat": "{{name}}",
+ "refId": "A",
+ "step": 240
+ },
+ {
+ "expr": "container_memory_usage_bytes{name=~\".+\"}",
+ "hide": true,
+ "intervalFactor": 2,
+ "legendFormat": "{{name}}",
+ "refId": "B",
+ "step": 240
+ }
+ ],
+ "thresholds": [],
+ "timeFrom": null,
+ "timeShift": null,
+ "title": "Memory Swap per Container",
+ "tooltip": {
+ "msResolution": true,
+ "shared": true,
+ "sort": 0,
+ "value_type": "individual"
+ },
+ "type": "graph",
+ "xaxis": {
+ "buckets": null,
+ "mode": "time",
+ "name": null,
+ "show": true,
+ "values": []
+ },
+ "yaxes": [
+ {
+ "format": "bytes",
+ "label": "",
+ "logBase": 1,
+ "max": null,
+ "min": null,
+ "show": true
+ },
+ {
+ "format": "short",
+ "label": null,
+ "logBase": 1,
+ "max": null,
+ "min": null,
+ "show": true
+ }
+ ]
+ }
+ ],
+ "repeat": null,
+ "repeatIteration": null,
+ "repeatRowId": null,
+ "showTitle": false,
+ "title": "Container Memory Statistics",
+ "titleSize": "h6"
+ },
+ {
+ "collapse": true,
+ "height": 97,
+ "panels": [
+ {
+ "columns": [
+ {
+ "text": "Current",
+ "value": "current"
+ }
+ ],
+ "editable": true,
+ "error": false,
+ "fontSize": "100%",
+ "id": 37,
+ "links": [],
+ "pageSize": null,
+ "scroll": true,
+ "showHeader": true,
+ "sort": {
+ "col": 0,
+ "desc": true
+ },
+ "span": 4,
+ "styles": [
+ {
+ "colorMode": null,
+ "colors": [
+ "rgba(245, 54, 54, 0.9)",
+ "rgba(237, 129, 40, 0.89)",
+ "rgba(50, 172, 45, 0.97)"
+ ],
+ "decimals": 2,
+ "pattern": "/.*/",
+ "thresholds": [
+ "10000000",
+ " 25000000"
+ ],
+ "type": "number",
+ "unit": "decbytes"
+ }
+ ],
+ "targets": [
+ {
+ "expr": "sum(container_spec_memory_limit_bytes{name=~\".+\"} - container_memory_usage_bytes{name=~\".+\"}) by (name) ",
+ "hide": true,
+ "intervalFactor": 2,
+ "legendFormat": "{{name}}",
+ "metric": "",
+ "refId": "A",
+ "step": 240
+ },
+ {
+ "expr": "sum(container_spec_memory_limit_bytes{name=~\".+\"}) by (name) ",
+ "hide": true,
+ "intervalFactor": 2,
+ "legendFormat": "{{name}}",
+ "refId": "B",
+ "step": 240
+ },
+ {
+ "expr": "container_memory_usage_bytes{name=~\".+\"}",
+ "hide": false,
+ "intervalFactor": 2,
+ "legendFormat": "{{name}}",
+ "refId": "C",
+ "step": 240
+ }
+ ],
+ "title": "Usage memory",
+ "transform": "timeseries_aggregations",
+ "type": "table"
+ },
+ {
+ "columns": [
+ {
+ "text": "Current",
+ "value": "current"
+ }
+ ],
+ "editable": true,
+ "error": false,
+ "fontSize": "100%",
+ "id": 35,
+ "links": [],
+ "pageSize": null,
+ "scroll": true,
+ "showHeader": true,
+ "sort": {
+ "col": 1,
+ "desc": true
+ },
+ "span": 4,
+ "styles": [
+ {
+ "colorMode": "cell",
+ "colors": [
+ "rgba(50, 172, 45, 0.97)",
+ "rgba(237, 129, 40, 0.89)",
+ "rgba(245, 54, 54, 0.9)"
+ ],
+ "decimals": 2,
+ "pattern": "/.*/",
+ "thresholds": [
+ "80",
+ "90"
+ ],
+ "type": "number",
+ "unit": "percent"
+ }
+ ],
+ "targets": [
+ {
+ "expr": "sum(100 - ((container_spec_memory_limit_bytes{name=~\".+\"} - container_memory_usage_bytes{name=~\".+\"}) * 100 / container_spec_memory_limit_bytes{name=~\".+\"}) ) by (name) ",
+ "intervalFactor": 2,
+ "legendFormat": "{{name}}",
+ "metric": "",
+ "refId": "A",
+ "step": 240
+ },
+ {
+ "expr": "sum(container_spec_memory_limit_bytes{name=~\".+\"}) by (name) ",
+ "hide": true,
+ "intervalFactor": 2,
+ "legendFormat": "{{name}}",
+ "refId": "B",
+ "step": 240
+ },
+ {
+ "expr": "container_memory_usage_bytes{name=~\".+\"}",
+ "hide": true,
+ "intervalFactor": 2,
+ "legendFormat": "{{name}}",
+ "refId": "C",
+ "step": 240
+ }
+ ],
+ "title": "Remaining memory",
+ "transform": "timeseries_aggregations",
+ "type": "table"
+ },
+ {
+ "columns": [
+ {
+ "text": "Current",
+ "value": "current"
+ }
+ ],
+ "editable": true,
+ "error": false,
+ "fontSize": "100%",
+ "id": 36,
+ "links": [],
+ "pageSize": null,
+ "scroll": true,
+ "showHeader": true,
+ "sort": {
+ "col": 0,
+ "desc": true
+ },
+ "span": 4,
+ "styles": [
+ {
+ "colorMode": null,
+ "colors": [
+ "rgba(245, 54, 54, 0.9)",
+ "rgba(237, 129, 40, 0.89)",
+ "rgba(50, 172, 45, 0.97)"
+ ],
+ "decimals": 2,
+ "pattern": "/.*/",
+ "thresholds": [
+ "10000000",
+ " 25000000"
+ ],
+ "type": "number",
+ "unit": "decbytes"
+ }
+ ],
+ "targets": [
+ {
+ "expr": "sum(container_spec_memory_limit_bytes{name=~\".+\"} - container_memory_usage_bytes{name=~\".+\"}) by (name) ",
+ "hide": true,
+ "intervalFactor": 2,
+ "legendFormat": "{{name}}",
+ "metric": "",
+ "refId": "A",
+ "step": 240
+ },
+ {
+ "expr": "sum(container_spec_memory_limit_bytes{name=~\".+\"}) by (name) ",
+ "hide": false,
+ "intervalFactor": 2,
+ "legendFormat": "{{name}}",
+ "refId": "B",
+ "step": 240
+ },
+ {
+ "expr": "container_memory_usage_bytes{name=~\".+\"}",
+ "hide": true,
+ "intervalFactor": 2,
+ "legendFormat": "{{name}}",
+ "refId": "C",
+ "step": 240
+ }
+ ],
+ "title": "Limit memory",
+ "transform": "timeseries_aggregations",
+ "type": "table"
+ }
+ ],
+ "repeat": null,
+ "repeatIteration": null,
+ "repeatRowId": null,
+ "showTitle": false,
+ "title": "Memory Usage",
+ "titleSize": "h6"
+ }
+ ],
+ "schemaVersion": 14,
+ "style": "dark",
+ "tags": [],
+ "templating": {
+ "list": [
+ {
+ "allValue": ".+",
+ "current": {
+ "text": "All",
+ "value": "$__all"
+ },
+ "datasource": "automated-ds",
+ "hide": 0,
+ "includeAll": true,
+ "label": "Container Group",
+ "multi": true,
+ "name": "containergroup",
+ "options": [],
+ "query": "label_values(container_group)",
+ "refresh": 1,
+ "regex": "",
+ "sort": 0,
+ "tagValuesQuery": null,
+ "tags": [],
+ "tagsQuery": null,
+ "type": "query",
+ "useTags": false
+ },
+ {
+ "auto": true,
+ "auto_count": 50,
+ "auto_min": "50s",
+ "current": {
+ "text": "auto",
+ "value": "$__auto_interval"
+ },
+ "datasource": null,
+ "hide": 0,
+ "includeAll": false,
+ "label": "Interval",
+ "multi": false,
+ "name": "interval",
+ "options": [
+ {
+ "selected": true,
+ "text": "auto",
+ "value": "$__auto_interval"
+ },
+ {
+ "selected": false,
+ "text": "30s",
+ "value": "30s"
+ },
+ {
+ "selected": false,
+ "text": "1m",
+ "value": "1m"
+ },
+ {
+ "selected": false,
+ "text": "2m",
+ "value": "2m"
+ },
+ {
+ "selected": false,
+ "text": "3m",
+ "value": "3m"
+ },
+ {
+ "selected": false,
+ "text": "5m",
+ "value": "5m"
+ },
+ {
+ "selected": false,
+ "text": "7m",
+ "value": "7m"
+ },
+ {
+ "selected": false,
+ "text": "10m",
+ "value": "10m"
+ },
+ {
+ "selected": false,
+ "text": "30m",
+ "value": "30m"
+ },
+ {
+ "selected": false,
+ "text": "1h",
+ "value": "1h"
+ },
+ {
+ "selected": false,
+ "text": "6h",
+ "value": "6h"
+ },
+ {
+ "selected": false,
+ "text": "12h",
+ "value": "12h"
+ },
+ {
+ "selected": false,
+ "text": "1d",
+ "value": "1d"
+ },
+ {
+ "selected": false,
+ "text": "7d",
+ "value": "7d"
+ },
+ {
+ "selected": false,
+ "text": "14d",
+ "value": "14d"
+ },
+ {
+ "selected": false,
+ "text": "30d",
+ "value": "30d"
+ }
+ ],
+ "query": "30s,1m,2m,3m,5m,7m,10m,30m,1h,6h,12h,1d,7d,14d,30d",
+ "refresh": 2,
+ "type": "interval"
+ },
+ {
+ "allValue": null,
+ "current": {
+ "text": "192.168.121.2",
+ "value": "192.168.121.2"
+ },
+ "datasource": "automated-ds",
+ "hide": 0,
+ "includeAll": false,
+ "label": "Node",
+ "multi": true,
+ "name": "server",
+ "options": [],
+ "query": "label_values(node_boot_time, instance)",
+ "refresh": 1,
+ "regex": "/([^:]+):.*/",
+ "sort": 0,
+ "tagValuesQuery": null,
+ "tags": [],
+ "tagsQuery": null,
+ "type": "query",
+ "useTags": false
+ }
+ ]
+ },
+ "time": {
+ "from": "now-24h",
+ "to": "now"
+ },
+ "timepicker": {
+ "refresh_intervals": [
+ "5s",
+ "10s",
+ "30s",
+ "1m",
+ "5m",
+ "15m",
+ "30m",
+ "1h",
+ "2h",
+ "1d"
+ ],
+ "time_options": [
+ "5m",
+ "15m",
+ "1h",
+ "6h",
+ "12h",
+ "24h",
+ "2d",
+ "7d",
+ "30d"
+ ]
+ },
+ "timezone": "browser",
+ "title": "Monitoring docker using Prometheus",
+ "version": 3
+}
diff --git a/monitor/server_ip_configure.py b/monitor/server_ip_configure.py
new file mode 100644
index 00000000..4e8d630a
--- /dev/null
+++ b/monitor/server_ip_configure.py
@@ -0,0 +1,27 @@
+##############################################################################
+# Copyright (c) 2018 Huawei Tech and others.
+#
+# All rights reserved. This program and the accompanying materials
+# are made available under the terms of the Apache License, Version 2.0
+# which accompanies this distribution, and is available at
+# http://www.apache.org/licenses/LICENSE-2.0
+##############################################################################
+import fileinput
+import re
+import logging
+import socket
+import requests
+from oslo_serialization import jsonutils
+
+logger = logging.getLogger(__name__)
+ip_address = socket.gethostbyname(socket.gethostname())
+
+for line in fileinput.input(inplace=1):
+ ip = " Listen \"" + str(ip_address) +"\" \"25826\""
+ line = re.sub(r'.*Listen.*25826.*', r''+str(ip), line.rstrip())
+ print(line)
+
+for line in fileinput.input(inplace=1):
+ ip = " URL \"http://"+str(ip_address)+":9103/collectd-post\""
+ line = re.sub(r'.*URL.*collectd-post.*', r''+str(ip), line.rstrip())
+ print(line)