Lots of work on stats, including an awesome Ansible-NAS Grafana dashboard

files/grafana/provisioning/dashboards/ansible-nas.yml

@@ -0,0 +1,24 @@
+apiVersion: 1
+
+providers:
+  # <string> an unique provider name
+- name: 'Ansible-NAS Dashboards'
+  # <int> org id. will default to orgId 1 if not specified
+  orgId: 1
+  # <string, required> name of the dashboard folder. Required
+  folder: 'Ansible-NAS'
+  # <string> folder UID. will be automatically generated if not specified
+  folderUid: ''
+  # <string, required> provider type. Required
+  type: file
+  # <bool> disable dashboard deletion
+  disableDeletion: false
+  # <bool> enable dashboard editing
+  editable: true
+  # <int> how often Grafana will scan for changed dashboards
+  updateIntervalSeconds: 60
+  # <bool> allow updating provisioned dashboards from the UI
+  allowUiUpdates: false
+  options:
+    # <string, required> path to dashboard files on disk. Required
+    path: /var/lib/grafana/dashboards/ansible-nas

tasks/stats.yml

@@ -16,9 +16,11 @@
   with_items:
     - "{{ grafana_data_directory }}"
     - "{{ grafana_data_directory }}/data"
+    - "{{ grafana_data_directory }}/data/dashboards/ansible-nas"
     - "{{ grafana_data_directory }}/config/"
     - "{{ grafana_data_directory }}/config/provisioning"
     - "{{ grafana_data_directory }}/config/provisioning/datasources"
+    - "{{ grafana_data_directory }}/config/provisioning/dashboards"
 
 - name: InfluxDB
   docker_container:
@@ -34,6 +36,18 @@
       INFLUXDB_LOGGING_LEVEL: "error"
     memory: 1g
 
+- name: hddtemp
+  docker_container:
+    name: hddtemp
+    image: drewster727/hddtemp-docker
+    pull: true
+    privileged: true
+    restart_policy: unless-stopped
+    env:
+      HDDTEMP_ARGS: "-q -d -F /dev/sd*"
+      TZ: "{{ ansible_nas_timezone }}"
+    memory: 128m
+
 - name: Template telegraf.conf
   template:
     src: telegraf/telegraf.conf
@@ -44,9 +58,26 @@
     name: telegraf
     image: telegraf
     pull: true
+    links:
+      - hddtemp:hddtemp
+    privileged: true
+    ipc_mode: host
     volumes:
       - "{{ telegraf_data_directory }}/telegraf.conf:/etc/telegraf/telegraf.conf:ro"
       - "/var/run/docker.sock:/var/run/docker.sock:ro"
+      - "/:/hostfs:ro"
+      - "/etc:/hostfs/etc:ro"
+      - "/proc:/hostfs/proc:ro"
+      - "/sys:/hostfs/sys:ro"
+      - "/var:/hostfs/var:ro"
+      - "/run:/hostfs/run:ro"
+    env:
+      HOST_ETC: "/hostfs/etc"
+      HOST_PROC: "/hostfs/proc"
+      HOST_SYS: "/hostfs/sys"
+      HOST_VAR: "/hostfs/var"
+      HOST_RUN: "/hostfs/run"
+      HOST_MOUNT_PREFIX: "/hostfs"
     restart_policy: unless-stopped
     memory: 1g
 
@@ -55,6 +86,16 @@
     src: grafana/provisioning/datasources/ansible-nas.yml
     dest: "{{ grafana_data_directory }}/config/provisioning/datasources/ansible-nas.yml"
 
+- name: Copy Ansible-NAS Dashboard Provisioner
+  copy:
+    src: grafana/provisioning/dashboards/ansible-nas.yml
+    dest: "{{ grafana_data_directory }}/config/provisioning/dashboards/ansible-nas.yml"
+
+- name: Copy Ansible-NAS Dashboard
+  copy:
+    src: grafana/dashboards/ansible-nas/ansible-nas-overview.json
+    dest: "{{ grafana_data_directory }}/data/dashboards/ansible-nas/ansible-nas-overview.json"
+
 - name: Grafana
   docker_container:
     name: grafana

templates/telegraf/telegraf.conf

@@ -271,17 +271,17 @@
   # insecure_skip_verify = false
 
 
-# # Monitor disks' temperatures using hddtemp
-# [[inputs.hddtemp]]
-#   ## By default, telegraf gathers temps data from all disks detected by the
-#   ## hddtemp.
-#   ##
-#   ## Only collect temps from the selected disks.
-#   ##
-#   ## A * as the device name will return the temperature values of all disks.
-#   ##
-#   # address = "127.0.0.1:7634"
-#   # devices = ["sda", "*"]
+# Monitor disks' temperatures using hddtemp
+[[inputs.hddtemp]]
+  ## By default, telegraf gathers temps data from all disks detected by the
+  ## hddtemp.
+  ##
+  ## Only collect temps from the selected disks.
+  ##
+  ## A * as the device name will return the temperature values of all disks.
+  ##
+  address = "hddtemp:7634"
+  devices = ["*"]
 
 # Read metrics about network interface usage
 [[inputs.net]]
@@ -309,7 +309,7 @@
   # remove_numbers = true
 
 
-# # Read metrics from storage devices supporting S.M.A.R.T.
+# Read metrics from storage devices supporting S.M.A.R.T.
 # [[inputs.smart]]
 #   ## Optionally specify the path to the smartctl executable
 #   # path = "/usr/bin/smartctl"
@@ -418,5 +418,5 @@
   # kstatMetrics = ["abdstats", "arcstats", "dnodestats", "dbufcachestats",
   #   "dmu_tx", "fm", "vdev_mirror_stats", "zfetchstats", "zil"]
   ## By default, don't gather zpool stats
-  # poolMetrics = false
+  poolMetrics = true