[Flow] Add new discovery.file component (#4404)

CHANGELOG.md

@@ -78,6 +78,7 @@ Main (unreleased)
 
 - New Grafana Agent Flow components:
 
+  - `discovery.file` discovers scrape targets from files. (@spartan0x117)
   - `discovery.kubelet` collect scrape targets from the Kubelet API. (@gcampbell12)
   - `module.http` runs a Grafana Agent Flow module loaded from a remote HTTP endpoint. (@spartan0x117)
   - `otelcol.processor.attributes` accepts telemetry data from other `otelcol`

component/all/all.go

@@ -8,6 +8,7 @@ import (
 	_ "github.com/grafana/agent/component/discovery/digitalocean"                   // Import discovery.digitalocean
 	_ "github.com/grafana/agent/component/discovery/dns"                            // Import discovery.dns
 	_ "github.com/grafana/agent/component/discovery/docker"                         // Import discovery.docker
+	_ "github.com/grafana/agent/component/discovery/file"                           // Import discovery.file
 	_ "github.com/grafana/agent/component/discovery/gce"                            // Import discovery.gce
 	_ "github.com/grafana/agent/component/discovery/http"                           // Import discovery.http
 	_ "github.com/grafana/agent/component/discovery/kubelet"                        // Import discovery.kubelet

component/discovery/file/file.go

@@ -0,0 +1,50 @@
+package file
+
+import (
+	"time"
+
+	"github.com/grafana/agent/component"
+	"github.com/grafana/agent/component/discovery"
+	"github.com/prometheus/common/model"
+	prom_discovery "github.com/prometheus/prometheus/discovery/file"
+)
+
+func init() {
+	component.Register(component.Registration{
+		Name:    "discovery.file",
+		Args:    Arguments{},
+		Exports: discovery.Exports{},
+
+		Build: func(opts component.Options, args component.Arguments) (component.Component, error) {
+			return New(opts, args.(Arguments))
+		},
+	})
+}
+
+type Arguments struct {
+	Files           []string      `river:"files,attr"`
+	RefreshInterval time.Duration `river:"refresh_interval,attr,optional"`
+}
+
+var DefaultArguments = Arguments{
+	RefreshInterval: 5 * time.Minute,
+}
+
+// SetToDefault implements river.Defaulter.
+func (a *Arguments) SetToDefault() {
+	*a = DefaultArguments
+}
+
+func (a *Arguments) Convert() *prom_discovery.SDConfig {
+	return &prom_discovery.SDConfig{
+		Files:           a.Files,
+		RefreshInterval: model.Duration(a.RefreshInterval),
+	}
+}
+
+func New(opts component.Options, args Arguments) (*discovery.Component, error) {
+	return discovery.New(opts, args, func(args component.Arguments) (discovery.Discoverer, error) {
+		newArgs := args.(Arguments)
+		return prom_discovery.NewDiscovery(newArgs.Convert(), opts.Logger), nil
+	})
+}

component/discovery/file/file_test.go

@@ -0,0 +1,43 @@
+package file
+
+import (
+	"testing"
+	"time"
+
+	"github.com/grafana/agent/pkg/river"
+	"github.com/prometheus/common/model"
+	"github.com/stretchr/testify/require"
+)
+
+func TestUnmarshal(t *testing.T) {
+	cfg := `
+	refresh_interval = "10m"
+	files = ["file1", "file2"]`
+
+	var args Arguments
+	err := river.Unmarshal([]byte(cfg), &args)
+	require.NoError(t, err)
+	require.Equal(t, 2, len(args.Files))
+	require.Equal(t, 10*time.Minute, args.RefreshInterval)
+}
+
+func TestUnmarshal_Defaults(t *testing.T) {
+	cfg := `files = ["file1"]`
+
+	var args Arguments
+	err := river.Unmarshal([]byte(cfg), &args)
+	require.NoError(t, err)
+	require.Equal(t, 1, len(args.Files))
+	require.Equal(t, 5*time.Minute, args.RefreshInterval)
+}
+
+func TestConvert(t *testing.T) {
+	args := Arguments{
+		Files:           []string{"file1", "file2"},
+		RefreshInterval: 10 * time.Minute,
+	}
+
+	promSDConfig := args.Convert()
+	require.Equal(t, 2, len(promSDConfig.Files))
+	require.Equal(t, model.Duration(10*time.Minute), promSDConfig.RefreshInterval)
+}

docs/sources/flow/reference/components/discovery.file.md

@@ -0,0 +1,168 @@
+---
+title: discovery.file
+---
+
+# discovery.file
+
+> **NOTE:** In `v0.35.0` of the Grafana Agent, the `discovery.file` component was renamed to [local.file_match][],
+> and `discovery.file` was repurposed to discover scrape targets from one or more files.
+>
+> <br>
+>
+> If you are trying to discover files on the local filesystem rather than scrape
+> targets within a set of files, you should use [local.file_match][] instead.
+
+[local.file_match]: {{< relref "./local.file_match.md" >}}
+
+`discovery.file` discovers targets from a set of files, similar to the [Prometheus file_sd_config](https://prometheus.io/docs/prometheus/latest/configuration/configuration/#file_sd_config).
+
+## Usage
+
+```river
+discovery.file "LABEL" {
+  files = [FILE_PATH_1, FILE_PATH_2, ...]
+}
+```
+
+## Arguments
+
+The following arguments are supported:
+
+Name               | Type                | Description                                | Default | Required
+------------------ | ------------------- | ------------------------------------------ |---------| --------
+`files`            | `list(string)`      | Files to read and discover targets from.   |         | yes 
+`refresh_interval` | `duration`          | How often to sync targets.                 | "5m"    | no
+
+The last path segment of each element in `files` may contain a single * that matches any character sequence, e.g. `my/path/tg_*.json`.
+
+## Exported fields
+
+The following fields are exported and can be referenced by other components:
+
+Name      | Type                | Description
+--------- | ------------------- | -----------
+`targets` | `list(map(string))` | The set of targets discovered from the filesystem.
+
+Each target includes the following labels:
+
+* `__meta_filepath`: The absolute path to the file the target was discovered from.
+
+## Component health
+
+`discovery.file` is only reported as unhealthy when given an invalid
+configuration. In those cases, exported fields retain their last healthy
+values.
+
+## Debug information
+
+`discovery.file` does not expose any component-specific debug information.
+
+### Debug metrics
+
+`discovery.file` does not expose any component-specific debug metrics.
+
+## Examples
+
+### Example target files
+```json
+[
+  {
+    "targets": [ "127.0.0.1:9091", "127.0.0.1:9092" ],
+    "labels": {
+      "environment": "dev"
+    }
+  },
+  {
+    "targets": [ "127.0.0.1:9093" ],
+    "labels": {
+      "environment": "prod"
+    }
+  }
+]
+```
+
+```yaml
+- targets:
+  - 127.0.0.1:9999
+  - 127.0.0.1:10101
+  labels:
+    job: worker
+- targets:
+  - 127.0.0.1:9090
+  labels:
+    job: prometheus
+```
+
+### Basic file discovery
+
+This example discovers targets from a single file, scrapes them, and writes metrics
+to a Prometheus remote write endpoint.
+
+```river
+discovery.file "example" {
+  files = ["/tmp/example.json"]
+}
+
+prometheus.scrape "default" {
+  targets    = discovery.file.example.targets
+  forward_to = [prometheus.remote_write.demo.receiver]
+}
+
+prometheus.remote_write "demo" {
+  endpoint {
+    url = PROMETHEUS_REMOTE_WRITE_URL
+
+    basic_auth {
+      username = USERNAME
+      password = PASSWORD
+    }
+  }
+}
+```
+
+Replace the following:
+  - `PROMETHEUS_REMOTE_WRITE_URL`: The URL of the Prometheus remote_write-compatible server to send metrics to.
+  - `USERNAME`: The username to use for authentication to the remote_write API.
+  - `PASSWORD`: The password to use for authentication to the remote_write API.
+
+### File discovery with retained file path label
+
+This example discovers targets from a wildcard file path, scrapes them, and writes metrics
+to a Prometheus remote write endpoint.
+
+It also uses a relabeling rule to retain the file path as a label on each target.
+
+```river
+discovery.file "example" {
+  files = ["/tmp/example_*.yaml"]
+}
+
+discovery.relabel "keep_filepath" {
+  targets = discovery.file.example.targets
+  rule {
+    source_labels = ["__meta_filepath"]
+    target_label = "filepath"
+  }
+}
+
+prometheus.scrape "default" {
+  targets    = discovery.relabel.keep_filepath.output
+  forward_to = [prometheus.remote_write.demo.receiver]
+}
+
+prometheus.remote_write "demo" {
+  endpoint {
+    url = PROMETHEUS_REMOTE_WRITE_URL
+
+    basic_auth {
+      username = USERNAME
+      password = PASSWORD
+    }
+  }
+}
+```
+
+Replace the following:
+  - `PROMETHEUS_REMOTE_WRITE_URL`: The URL of the Prometheus remote_write-compatible server to send metrics to.
+  - `USERNAME`: The username to use for authentication to the remote_write API.
+  - `PASSWORD`: The password to use for authentication to the remote_write API.