Added Grafana

changelog.md

@@ -1,3 +1,4 @@
 # azhpc Change log
 
+* 01-Apr-2020 : Added Grafana and Telegraf 
 * 04-Feb-2020 : Added permission option to sasurl variable value. Append ",rw" for read write access. Default is read.

examples/grafana/config.json

@@ -0,0 +1,71 @@
+{
+    "location": "variables.location",
+    "resource_group": "variables.resource_group",
+    "install_from": "jumpbox",
+    "admin_user": "hpcadmin",
+    "vnet": {
+        "name": "hpcvnet",
+        "address_prefix": "10.2.0.0/20",
+        "subnets": {
+            "admin": "10.2.1.0/24"
+        }
+    },
+    "variables": {
+        "location": "<NOT-SET>",
+        "resource_group": "<NOT-SET>",
+        "vm_type": "<NOT-SET>",
+        "image": "OpenLogic:CentOS:7.7:latest",
+        "key_vault": "<NOT-SET>"
+    },
+    "resources": {
+        "jumpbox": {
+            "type": "vm",
+            "vm_type": "variables.vm_type",
+            "public_ip": true,
+            "image": "variables.image",
+            "subnet": "admin",
+            "tags": [
+            ]
+        },
+        "grafana": {
+            "type": "vm",
+            "vm_type": "variables.vm_type",
+            "accelerated_networking": true,
+            "public_ip": true,
+            "image": "variables.image",
+            "subnet": "admin",
+            "tags": [
+                "disable-selinux",
+                "grafana",
+                "telegraf"
+            ]
+        }
+    },
+    "install": [
+        {
+            "script": "disable-selinux.sh",
+            "tag": "disable-selinux",
+            "sudo": true
+        },
+        {
+            "script": "install-grafana.sh",
+            "tag": "grafana",
+            "sudo": true,
+            "args": [
+                "azhpc",
+                "secret.{{variables.key_vault}}.GrafanaPassword"
+             ],
+             "deps" : ["telegraf_dashboard.json"]
+        },
+        {
+            "script": "install-telegraf.sh",
+            "tag": "telegraf",
+            "sudo": true,
+            "args": [
+                "$(<hostlists/tags/grafana)",
+                "azhpc",
+                "secret.{{variables.key_vault}}.GrafanaPassword"
+             ] 
+        }
+    ]
+}

examples/grafana/readme.md

@@ -0,0 +1,35 @@
+# Deploy an initialize a Grafana server
+This example shows how deploy a [Grafana](https://grafana.com/grafana/) server and configure [Telegraf](https://www.influxdata.com/time-series-platform/telegraf/) on monitored machines.
+
+
+The configuration file requires the following variables to be set:
+
+| Variable                | Description                                  |
+|-------------------------|----------------------------------------------|
+| location                | The location of resources                    |
+| resource_group          | The resource group for the project           |
+| vm_type                 | Azure GPU VM full name (NC or ND series)     |
+| key_vault               | Keyvault to store the GrafanaPassword secret |
+
+> Note : Create an Azure Key Vault and store the Grafana Password in the secret named _GrafanaPassword_
+
+Once deployed:
+ - Add port 3000 to the NSG of the grafana server
+ - access the portal thru the URL : **http://[grafana server fqdn]:3000/**
+ - Authenticate with the **admin** user and the password stored into your KeyVault
+ - Access the dashboard thru the left meny **Dashboards/Manage** and then select "Telegraf : system dashboard"
+
+> Note : To monitor other VMs, just add the **telegraf** tag to your resources and its associated install script as specified the in the configuration file
+
+```json
+        {
+            "script": "install-telegraf.sh",
+            "tag": "telegraf",
+            "sudo": true,
+            "args": [
+                "<grafana server or ip address>",
+                "azhpc",
+                "secret.{{variables.key_vault}}.GrafanaPassword"
+             ] 
+        }
+```

scripts/install-grafana.sh

@@ -0,0 +1,112 @@
+#!/bin/bash
+DIR="$( cd "$( dirname "${BASH_SOURCE[0]}" )" && pwd )"
+GRAFANA_USER=${1-azhpc}
+GRAFANA_PWD=$2
+
+if [ -z "$GRAFANA_PWD" ]; then
+    echo "Grafana password parameter is required"
+    exit 1
+fi
+
+echo "#### Configuration repo for InfluxDB:"
+cat <<EOF | tee /etc/yum.repos.d/influxdb.repo
+[influxdb]
+name = InfluxDB Repository - RHEL \$releasever
+baseurl = https://repos.influxdata.com/centos/\$releasever/\$basearch/stable
+enabled = 1
+gpgcheck = 1
+gpgkey = https://repos.influxdata.com/influxdb.key
+EOF
+
+echo "#### Configuration repo for Grafana:"
+cat <<EOF | tee /etc/yum.repos.d/grafana.repo
+[grafana]
+name=grafana
+baseurl=https://packages.grafana.com/oss/rpm
+repo_gpgcheck=1
+enabled=1
+gpgcheck=1
+gpgkey=https://packages.grafana.com/gpg.key
+sslverify=1
+sslcacert=/etc/pki/tls/certs/ca-bundle.crt
+EOF
+
+echo "#### InfluxDB Installation:"
+yum -y install influxdb
+echo "#### Grafana Installation:"
+yum -y install grafana
+
+
+echo "#### Starting InfluxDB services:"
+systemctl daemon-reload
+systemctl start influxdb
+systemctl enable influxdb
+echo "#### Starting Grafana services:"
+systemctl start grafana-server
+systemctl enable grafana-server
+
+#echo "#### Opening InfluxDB firewalld port 80(83|86):"
+#sudo firewall-cmd --permanent --zone=public --add-port=8086/tcp
+#sudo firewall-cmd --permanent --zone=public --add-port=8083/tcp
+#echo "#### Opening Grafana firewalld port 3000:"
+#sudo firewall-cmd --permanent --zone=public --add-port=3000/tcp
+#echo "#### Reload firewall rules:"
+#sudo firewall-cmd --reload
+
+
+echo "#### Configuration of influxDB User and DB:"
+curl "http://localhost:8086/query" --data-urlencode "q=CREATE USER admindb WITH PASSWORD '$GRAFANA_PWD' WITH ALL PRIVILEGES"
+curl "http://localhost:8086/query" --data-urlencode "q=CREATE USER $GRAFANA_USER WITH PASSWORD '$GRAFANA_PWD'"
+curl "http://localhost:8086/query" --data-urlencode "q=CREATE DATABASE monitor"
+curl "http://localhost:8086/query" --data-urlencode "q=GRANT ALL ON monitor to $GRAFANA_USER"
+
+echo "Add the administrator"
+# https://grafana.com/docs/grafana/latest/administration/cli/
+grafana-cli admin reset-admin-password "$GRAFANA_PWD"
+
+echo "Create the datasource"
+# https://grafana.com/docs/grafana/latest/administration/provisioning/
+grafana_etc_root=/etc/grafana/provisioning
+dashboard_dir=/var/lib/grafana/dashboards
+cat <<EOF > $grafana_etc_root/datasources/azhpc.yml
+apiVersion: 1
+
+datasources:
+  - name: azhpc
+    type: influxdb
+    access: proxy
+    database: monitor
+    user: $GRAFANA_USER
+    password: "$GRAFANA_PWD"
+    url: http://localhost:8086
+    jsonData:
+      httpMode: GET
+EOF
+chown root:grafana $grafana_etc_root/datasources/azhpc.yml
+
+cat <<EOF > $grafana_etc_root/dashboards/azhpc.yml
+apiVersion: 1
+
+providers:
+- name: 'azhpc'
+  orgId: 1
+  folder: ''
+  folderUid: ''
+  type: file
+  disableDeletion: false
+  editable: true
+  allowUiUpdates: true
+  options:
+    path: $dashboard_dir
+EOF
+
+chown root:grafana $grafana_etc_root/dashboards/azhpc.yaml
+
+mkdir $dashboard_dir
+chown grafana:grafana $dashboard_dir
+
+cp $DIR/telegraf_dashboard.json $dashboard_dir
+
+systemctl stop grafana-server
+systemctl start grafana-server
+

scripts/install-telegraf.sh

@@ -0,0 +1,77 @@
+#!/bin/bash
+GRAFANA_SERVER=$1
+GRAFANA_USER=$2
+GRAFANA_PWD=$3
+
+if [ -z "$GRAFANA_SERVER" ]; then
+    echo "Grafana server parameter is required"
+    exit 1
+fi
+if [ -z "$GRAFANA_USER" ]; then
+    echo "Grafana user parameter is required"
+    exit 1
+fi
+if [ -z "$GRAFANA_PWD" ]; then
+    echo "Grafana password parameter is required"
+    exit 1
+fi
+
+echo "#### Configuration repo for InfluxDB:"
+cat <<EOF | tee /etc/yum.repos.d/influxdb.repo
+[influxdb]
+name = InfluxDB Repository - RHEL \$releasever
+baseurl = https://repos.influxdata.com/centos/\$releasever/\$basearch/stable
+enabled = 1
+gpgcheck = 1
+gpgkey = https://repos.influxdata.com/influxdb.key
+EOF
+
+echo "#### Telegraf Installation:"
+yum -y install telegraf
+
+echo "Push right config .... "
+# Update telegraph.conf
+cp /etc/telegraf/telegraf.conf /etc/telegraf/telegraf.conf.origin
+
+cat << EOF > /etc/telegraf/telegraf.conf
+[global_tags]
+[agent]
+  interval = "10s"
+  round_interval = true
+  metric_batch_size = 1000
+  metric_buffer_limit = 10000
+  collection_jitter = "0s"
+  flush_interval = "10s"
+  flush_jitter = "0s"
+  precision = ""
+  hostname = ""
+  omit_hostname = false
+
+[[outputs.influxdb]]
+  urls = ["http://$GRAFANA_SERVER:8086"]
+  database = "monitor"
+  username = "$GRAFANA_USER"
+  password = "$GRAFANA_PWD"
+
+[[inputs.cpu]]
+  percpu = true
+  totalcpu = true
+  collect_cpu_time = false
+  report_active = false
+
+[[inputs.disk]]
+  ignore_fs = ["tmpfs", "devtmpfs", "devfs", "iso9660", "overlay", "aufs", "squashfs"]
+
+[[inputs.diskio]]
+[[inputs.kernel]]
+[[inputs.mem]]
+[[inputs.processes]]
+[[inputs.swap]]
+[[inputs.system]]
+[[inputs.net]]
+EOF
+
+echo "#### Starting Telegraf services:"
+systemctl daemon-reload
+systemctl start telegraf
+systemctl enable telegraf