| 1 | plugin_name: go.d.plugin |
| 2 | modules: |
| 3 | - meta: |
| 4 | id: collector-go.d.plugin-docker |
| 5 | plugin_name: go.d.plugin |
| 6 | module_name: docker |
| 7 | alternative_monitored_instances: [] |
| 8 | monitored_instance: |
| 9 | name: Docker |
| 10 | link: https://www.docker.com/ |
| 11 | categories: |
| 12 | - data-collection.containers-and-vms |
| 13 | icon_filename: docker.svg |
| 14 | related_resources: |
| 15 | integrations: |
| 16 | list: [] |
| 17 | info_provided_to_referring_integrations: |
| 18 | description: "" |
| 19 | keywords: |
| 20 | - container |
| 21 | overview: |
| 22 | data_collection: |
| 23 | metrics_description: | |
| 24 | This collector monitors Docker containers state, health status and more. |
| 25 | method_description: | |
| 26 | It connects to the Docker instance via a TCP or UNIX socket and executes the following commands: |
| 27 | |
| 28 | - [System info](https://docs.docker.com/engine/api/v1.43/#tag/System/operation/SystemInfo). |
| 29 | - [List images](https://docs.docker.com/engine/api/v1.43/#tag/Image/operation/ImageList). |
| 30 | - [List containers](https://docs.docker.com/engine/api/v1.43/#tag/Container/operation/ContainerList). |
| 31 | supported_platforms: |
| 32 | include: [] |
| 33 | exclude: [] |
| 34 | multi_instance: true |
| 35 | additional_permissions: |
| 36 | description: Requires netdata user to be in the docker group. |
| 37 | default_behavior: |
| 38 | auto_detection: |
| 39 | description: | |
| 40 | It discovers instances running on localhost by attempting to connect to a known Docker UNIX socket: `/var/run/docker.sock`. |
| 41 | limits: |
| 42 | description: "" |
| 43 | performance_impact: |
| 44 | description: | |
| 45 | Enabling `collect_container_size` may result in high CPU usage depending on the version of Docker Engine. |
| 46 | setup: |
| 47 | prerequisites: |
| 48 | list: [] |
| 49 | configuration: |
| 50 | file: |
| 51 | name: go.d/docker.conf |
| 52 | options: |
| 53 | description: | |
| 54 | The following options can be defined globally: update_every, autodetection_retry. |
| 55 | folding: |
| 56 | title: Config options |
| 57 | enabled: true |
| 58 | list: |
| 59 | - name: update_every |
| 60 | description: Data collection interval (seconds). |
| 61 | default_value: 1 |
| 62 | required: false |
| 63 | group: Collection |
| 64 | - name: autodetection_retry |
| 65 | description: Autodetection retry interval (seconds). Set 0 to disable. |
| 66 | default_value: 0 |
| 67 | required: false |
| 68 | group: Collection |
| 69 | |
| 70 | - name: address |
| 71 | description: "Docker daemon address. For TCP sockets: `tcp://IP:PORT`." |
| 72 | default_value: unix:///var/run/docker.sock |
| 73 | required: true |
| 74 | group: Target |
| 75 | - name: timeout |
| 76 | description: Request timeout (seconds). |
| 77 | default_value: 2 |
| 78 | required: false |
| 79 | group: Target |
| 80 | |
| 81 | - name: container_selector |
| 82 | description: "Container selector. Defines which containers to monitor. Uses [simple patterns](https://github.com/netdata/netdata/tree/master/src/libnetdata/simple_pattern#readme)." |
| 83 | default_value: "*" |
| 84 | required: false |
| 85 | group: Filters |
| 86 | |
| 87 | - name: collect_container_size |
| 88 | description: Collect container writable layer size metrics. |
| 89 | default_value: no |
| 90 | required: false |
| 91 | group: Metrics Selection |
| 92 | |
| 93 | - name: vnode |
| 94 | description: Associates this data collection job with a [Virtual Node](https://learn.netdata.cloud/docs/netdata-agent/configuration/organize-systems-metrics-and-alerts#virtual-nodes). |
| 95 | default_value: "" |
| 96 | required: false |
| 97 | group: Virtual Node |
| 98 | examples: |
| 99 | folding: |
| 100 | enabled: true |
| 101 | title: Config |
| 102 | list: |
| 103 | - name: Basic |
| 104 | description: An example configuration. |
| 105 | folding: |
| 106 | enabled: false |
| 107 | config: | |
| 108 | jobs: |
| 109 | - name: local |
| 110 | address: 'unix:///var/run/docker.sock' |
| 111 | - name: Multi-instance |
| 112 | description: | |
| 113 | > **Note**: When you define multiple jobs, their names must be unique. |
| 114 | |
| 115 | Collecting metrics from local and remote instances. |
| 116 | config: | |
| 117 | jobs: |
| 118 | - name: local |
| 119 | address: 'unix:///var/run/docker.sock' |
| 120 | |
| 121 | - name: remote |
| 122 | address: 'tcp://203.0.113.10:2375' |
| 123 | troubleshooting: |
| 124 | problems: |
| 125 | list: [] |
| 126 | alerts: |
| 127 | - name: docker_container_unhealthy |
| 128 | metric: docker.container_health_status |
| 129 | info: ${label:container_name} docker container health status is unhealthy |
| 130 | link: https://github.com/netdata/netdata/blob/master/src/health/health.d/docker.conf |
| 131 | functions: |
| 132 | description: | |
| 133 | This collector exposes real-time functions for interactive troubleshooting in the Live tab. |
| 134 | list: |
| 135 | - id: container-ls |
| 136 | name: Containers |
| 137 | description: | |
| 138 | Retrieves container list data equivalent to `docker ps -a`. |
| 139 | |
| 140 | This function calls the Docker Container List API with `all=true` and returns both running and non-running containers in a table similar to Docker CLI output. |
| 141 | |
| 142 | Use cases: |
| 143 | - Quickly inspect all containers (running, exited, paused, dead) from Netdata |
| 144 | - Correlate container lifecycle with metric changes and alerts |
| 145 | - Verify exposed ports, image tags, and container names without shell access |
| 146 | parameters: [] |
| 147 | returns: |
| 148 | description: Container inventory from Docker Engine. Each row represents one container returned by `docker ps -a`. |
| 149 | columns: |
| 150 | - name: CONTAINER ID |
| 151 | type: string |
| 152 | unit: "" |
| 153 | description: Short container ID (12 characters). |
| 154 | - name: IMAGE |
| 155 | type: string |
| 156 | unit: "" |
| 157 | description: Container image reference. |
| 158 | - name: COMMAND |
| 159 | type: string |
| 160 | unit: "" |
| 161 | description: Container command as reported by Docker API. |
| 162 | - name: CREATED |
| 163 | type: string |
| 164 | unit: "" |
| 165 | description: Human-readable container creation age (for example, '5 days ago'). |
| 166 | - name: STATUS |
| 167 | type: string |
| 168 | unit: "" |
| 169 | description: Docker status string (for example, 'Up 3 weeks' or 'Exited (0) 4 weeks ago'). |
| 170 | - name: State (Raw) |
| 171 | type: string |
| 172 | unit: "" |
| 173 | visibility: hidden |
| 174 | description: Raw Docker state value (for example, running, exited, paused, restarting, dead). |
| 175 | - name: PORTS |
| 176 | type: string |
| 177 | unit: "" |
| 178 | description: Published or exposed ports summary. |
| 179 | - name: NAMES |
| 180 | type: string |
| 181 | unit: "" |
| 182 | description: Container name. |
| 183 | - name: Container ID (Full) |
| 184 | type: string |
| 185 | unit: "" |
| 186 | visibility: hidden |
| 187 | description: Full 64-character container ID. |
| 188 | - name: Created (Unix) |
| 189 | type: integer |
| 190 | unit: "seconds" |
| 191 | visibility: hidden |
| 192 | description: Container creation timestamp in Unix seconds. |
| 193 | performance: | |
| 194 | Executes a single Docker API request (`ContainerList` with `all=true`):<br/>• No per-container inspect requests are issued<br/>• Response size grows with total container count<br/>• Large histories with many stopped containers may return more rows |
| 195 | security: | |
| 196 | Exposes container metadata that may include sensitive details:<br/>• Container command text may include runtime arguments<br/>• Image names, ports, and container names are visible<br/>• Restrict access to authorized operators |
| 197 | availability: | |
| 198 | Available when:<br/>• Docker collector is initialized and connected<br/>• Docker API list-containers request succeeds<br/>• Returns HTTP 503 while collector is initializing<br/>• Returns HTTP 500 on Docker API errors<br/>• Returns HTTP 504 on timeout |
| 199 | require_cloud: true |
| 200 | metrics: |
| 201 | folding: |
| 202 | title: Metrics |
| 203 | enabled: false |
| 204 | description: "" |
| 205 | availability: [] |
| 206 | scopes: |
| 207 | - name: global |
| 208 | description: These metrics refer to the entire monitored application. |
| 209 | labels: [] |
| 210 | metrics: |
| 211 | - name: docker.containers_state |
| 212 | description: Total number of Docker containers in various states |
| 213 | unit: containers |
| 214 | chart_type: stacked |
| 215 | dimensions: |
| 216 | - name: running |
| 217 | - name: paused |
| 218 | - name: stopped |
| 219 | - name: docker.containers_health_status |
| 220 | description: Total number of Docker containers in various health states |
| 221 | unit: containers |
| 222 | chart_type: line |
| 223 | dimensions: |
| 224 | - name: healthy |
| 225 | - name: unhealthy |
| 226 | - name: not_running_unhealthy |
| 227 | - name: starting |
| 228 | - name: no_healthcheck |
| 229 | - name: docker.images |
| 230 | description: Total number of Docker images in various states |
| 231 | unit: images |
| 232 | chart_type: stacked |
| 233 | dimensions: |
| 234 | - name: active |
| 235 | - name: dangling |
| 236 | - name: docker.images_size |
| 237 | description: Total size of all Docker images |
| 238 | unit: bytes |
| 239 | chart_type: line |
| 240 | dimensions: |
| 241 | - name: size |
| 242 | - name: container |
| 243 | description: Metrics related to containers. Each container provides its own set of the following metrics. |
| 244 | labels: |
| 245 | - name: container_name |
| 246 | description: The container's name |
| 247 | - name: image |
| 248 | description: The image name the container uses |
| 249 | metrics: |
| 250 | - name: docker.container_state |
| 251 | description: Docker container state |
| 252 | unit: state |
| 253 | chart_type: line |
| 254 | dimensions: |
| 255 | - name: running |
| 256 | - name: paused |
| 257 | - name: exited |
| 258 | - name: created |
| 259 | - name: restarting |
| 260 | - name: removing |
| 261 | - name: dead |
| 262 | - name: docker.container_health_status |
| 263 | description: Docker container health status |
| 264 | unit: status |
| 265 | chart_type: line |
| 266 | dimensions: |
| 267 | - name: healthy |
| 268 | - name: unhealthy |
| 269 | - name: not_running_unhealthy |
| 270 | - name: starting |
| 271 | - name: no_healthcheck |
| 272 | - name: docker.container_writeable_layer_size |
| 273 | description: Docker container writable layer size |
| 274 | unit: size |
| 275 | chart_type: line |
| 276 | dimensions: |
| 277 | - name: writeable_layer |