Merge prometheus.write.queue into main.

CHANGELOG.md

@@ -22,9 +22,12 @@ Main (unreleased)
 - Add support to `loki.source.syslog` for the RFC3164 format ("BSD syslog"). (@sushain97)
 
 - Add support to `loki.source.api` to be able to extract the tenant from the HTTP `X-Scope-OrgID` header (@QuentinBisson)
-- 
+
 - (_Experimental_) Add a `loki.secretfilter` component to redact secrets from collected logs.
 
+- (_Experimental_) Add a `prometheus.write.queue` component to add an alternative to `prometheus.remote_write`
+  which allowing the writing of metrics  to a prometheus endpoint. (@mattdurham)
+
 ### Enhancements
 
 - The `mimir.rules.kubernetes` component now supports adding extra label matchers

Makefile

@@ -141,7 +141,7 @@ lint: alloylint
 # final command runs tests for all other submodules.
 test:
 	$(GO_ENV) go test $(GO_FLAGS) -race $(shell go list ./... | grep -v /integration-tests/)
-	$(GO_ENV) go test $(GO_FLAGS) ./internal/static/integrations/node_exporter ./internal/static/logs ./internal/component/otelcol/processor/tail_sampling ./internal/component/loki/source/file ./internal/component/loki/source/docker
+	$(GO_ENV) go test $(GO_FLAGS) ./internal/static/integrations/node_exporter ./internal/static/logs ./internal/component/otelcol/processor/tail_sampling ./internal/component/loki/source/file ./internal/component/loki/source/docker ./internal/component/prometheus/write/queue/serialization  ./internal/component/prometheus/write/queue/network
 	$(GO_ENV) find . -name go.mod -not -path "./go.mod" -execdir go test -race ./... \;
 
 test-packages:

docs/sources/reference/compatibility/_index.md

@@ -175,6 +175,7 @@ The following components, grouped by namespace, _export_ Prometheus `MetricsRece
 {{< collapse title="prometheus" >}}
 - [prometheus.relabel](../components/prometheus/prometheus.relabel)
 - [prometheus.remote_write](../components/prometheus/prometheus.remote_write)
+- [prometheus.write.queue](../components/prometheus/prometheus.write.queue)
 {{< /collapse >}}
 
 <!-- END GENERATED SECTION: EXPORTERS OF Prometheus `MetricsReceiver` -->

docs/sources/reference/components/prometheus/prometheus.write.queue.md

@@ -0,0 +1,280 @@
+---
+canonical: https://grafana.com/docs/alloy/latest/reference/components/prometheus/prometheus.write.queue/
+description: Learn about prometheus.write.queue
+title: prometheus.write.queue
+---
+
+
+<span class="badge docs-labels__stage docs-labels__item">Experimental</span>
+
+# prometheus.write.queue
+
+`prometheus.write.queue` collects metrics sent from other components into a
+Write-Ahead Log (WAL) and forwards them over the network to a series of
+user-supplied endpoints. Metrics are sent over the network using the
+[Prometheus Remote Write protocol][remote_write-spec].
+
+You can specify multiple `prometheus.write.queue` components by giving them different labels.
+
+You should consider everything here extremely experimental and highly subject to change.
+[remote_write-spec]: https://prometheus.io/docs/specs/remote_write_spec/
+
+
+
+## Usage
+
+```alloy
+prometheus.write.queue "LABEL" {
+  endpoint "default "{
+    url = REMOTE_WRITE_URL
+
+    ...
+  }
+
+  ...
+}
+```
+
+## Arguments
+
+The following arguments are supported:
+
+Name | Type | Description | Default | Required
+---- | ---- | ----------- | ------- | --------
+`ttl` | `time` | `duration` | How long the samples can be queued for before they are discarded. | `2h` | no
+
+## Blocks
+
+The following blocks are supported inside the definition of
+`prometheus.write.queue`:
+
+Hierarchy | Block | Description | Required
+--------- | ----- | ----------- | --------
+persistence | [persistence][] | Configuration for persistence | no
+endpoint | [endpoint][] | Location to send metrics to. | no
+endpoint > basic_auth | [basic_auth][] | Configure basic_auth for authenticating to the endpoint. | no
+
+The `>` symbol indicates deeper levels of nesting. For example, `endpoint >
+basic_auth` refers to a `basic_auth` block defined inside an
+`endpoint` block.
+
+[endpoint]: #endpoint-block
+[basic_auth]: #basic_auth-block
+[persistence]: #persistence-block
+
+### persistence block
+
+The `persistence` block describes how often and at what limits to write to disk. Persistence settings
+are shared for each `endpoint`.
+
+The following arguments are supported:
+
+Name | Type | Description                                                                   | Default | Required
+---- | ---- |-------------------------------------------------------------------------------|---------| --------
+`max_signals_to_batch` | `uint` | The maximum number of signals before they are batched to disk.                | `10000` | no
+`batch_interval` | `duration` | How often to batch signals to disk if `max_signals_to_batch` is not reached. | `5s`     | no
+
+
+### endpoint block
+
+The `endpoint` block describes a single location to send metrics to. Multiple
+`endpoint` blocks can be provided to send metrics to multiple locations. Each
+`endpoint` will have its own WAL folder.
+
+The following arguments are supported:
+
+Name | Type | Description                                                      | Default | Required
+---- | ---- |------------------------------------------------------------------| ------ | --------
+`url` | `string` | Full URL to send metrics to.                                     | | yes
+`write_timeout` | `duration` | Timeout for requests made to the URL.                            | `"30s"` | no
+`retry_backoff` | `duration` | How often to wait between retries.                               | `1s` | no
+`max_retry_attempts` | Maximum number of retries before dropping the batch. | `0`                                                              | no
+`batch_count` | `uint` | How many series to queue in each queue.                          | `1000` | no
+`flush_interval` | `duration` | How often to wait until sending if `batch_count` is not trigger. | `1s` | no
+`parallelism` | `uint` | How many parallel batches to write.                              | 10 | no
+`external_labels` | `map(string)` | Labels to add to metrics sent over the network.                  | | no
+
+### basic_auth block
+
+{{< docs/shared lookup="reference/components/basic-auth-block.md" source="alloy" version="<ALLOY_VERSION>" >}}
+
+
+## Exported fields
+
+The following fields are exported and can be referenced by other components:
+
+Name | Type | Description
+---- | ---- | -----------
+`receiver` | `MetricsReceiver` | A value that other components can use to send metrics to.
+
+## Component health
+
+`prometheus.write.queue` is only reported as unhealthy if given an invalid
+configuration. In those cases, exported fields are kept at their last healthy
+values.
+
+## Debug information
+
+`prometheus.write.queue` does not expose any component-specific debug
+information.
+
+## Debug metrics
+
+The following metrics are provided for backward compatibility.
+They generally behave the same, but there are likely edge cases where they differ.
+
+* `prometheus_remote_write_wal_storage_created_series_total` (counter): Total number of created
+  series appended to the WAL.
+* `prometheus_remote_write_wal_storage_removed_series_total` (counter): Total number of series
+  removed from the WAL.
+* `prometheus_remote_write_wal_samples_appended_total` (counter): Total number of samples
+  appended to the WAL.
+* `prometheus_remote_write_wal_exemplars_appended_total` (counter): Total number of exemplars
+  appended to the WAL.
+* `prometheus_remote_storage_samples_total` (counter): Total number of samples
+  sent to remote storage.
+* `prometheus_remote_storage_exemplars_total` (counter): Total number of
+  exemplars sent to remote storage.
+* `prometheus_remote_storage_metadata_total` (counter): Total number of
+  metadata entries sent to remote storage.
+* `prometheus_remote_storage_samples_failed_total` (counter): Total number of
+  samples that failed to send to remote storage due to non-recoverable errors.
+* `prometheus_remote_storage_exemplars_failed_total` (counter): Total number of
+  exemplars that failed to send to remote storage due to non-recoverable errors.
+* `prometheus_remote_storage_metadata_failed_total` (counter): Total number of
+  metadata entries that failed to send to remote storage due to
+  non-recoverable errors.
+* `prometheus_remote_storage_samples_retries_total` (counter): Total number of
+  samples that failed to send to remote storage but were retried due to
+  recoverable errors.
+* `prometheus_remote_storage_exemplars_retried_total` (counter): Total number of
+  exemplars that failed to send to remote storage but were retried due to
+  recoverable errors.
+* `prometheus_remote_storage_metadata_retried_total` (counter): Total number of
+  metadata entries that failed to send to remote storage but were retried due
+  to recoverable errors.
+* `prometheus_remote_storage_samples_dropped_total` (counter): Total number of
+  samples which were dropped after being read from the WAL before being sent to
+  remote_write because of an unknown reference ID.
+* `prometheus_remote_storage_exemplars_dropped_total` (counter): Total number
+  of exemplars that were dropped after being read from the WAL before being
+  sent to remote_write because of an unknown reference ID.
+* `prometheus_remote_storage_enqueue_retries_total` (counter): Total number of
+  times enqueue has failed because a shard's queue was full.
+* `prometheus_remote_storage_sent_batch_duration_seconds` (histogram): Duration
+  of send calls to remote storage.
+* `prometheus_remote_storage_queue_highest_sent_timestamp_seconds` (gauge):
+  Unix timestamp of the latest WAL sample successfully sent by a queue.
+* `prometheus_remote_storage_samples_pending` (gauge): The number of samples
+  pending in shards to be sent to remote storage.
+* `prometheus_remote_storage_exemplars_pending` (gauge): The number of
+  exemplars pending in shards to be sent to remote storage.
+* `prometheus_remote_storage_samples_in_total` (counter): Samples read into
+  remote storage.
+* `prometheus_remote_storage_exemplars_in_total` (counter): Exemplars read into
+  remote storage.
+
+Metrics that are new to `prometheus.write.queue`. These are highly subject to change.
+
+* `alloy_queue_series_serializer_incoming_signals` (counter): Total number of series written to serialization.
+* `alloy_queue_metadata_serializer_incoming_signals` (counter): Total number of metadata written to serialization.
+* `alloy_queue_series_serializer_incoming_timestamp_seconds` (gauge): Highest timestamp of incoming series.
+* `alloy_queue_series_serializer_errors` (gauge): Number of errors for series written to serializer.
+* `alloy_queue_metadata_serializer_errors` (gauge): Number of errors for metadata written to serializer.
+* `alloy_queue_series_network_timestamp_seconds` (gauge): Highest timestamp written to an endpoint.
+* `alloy_queue_series_network_sent` (counter): Number of series sent successfully.
+* `alloy_queue_metadata_network_sent` (counter): Number of metadata sent successfully.
+* `alloy_queue_network_series_failed` (counter): Number of series failed.
+* `alloy_queue_network_metadata_failed` (counter): Number of metadata failed.
+* `alloy_queue_network_series_retried` (counter): Number of series retried due to network issues.
+* `alloy_queue_network_metadata_retried` (counter): Number of metadata retried due to network issues.
+* `alloy_queue_network_series_retried_429` (counter): Number of series retried due to status code 429.
+* `alloy_queue_network_metadata_retried_429` (counter): Number of metadata retried due to status code 429.
+* `alloy_queue_network_series_retried_5xx` (counter): Number of series retried due to status code 5xx.
+* `alloy_queue_network_metadata_retried_5xx` (counter): Number of metadata retried due to status code 5xx.
+* `alloy_queue_network_series_network_duration_seconds` (histogram): Duration writing series to endpoint.
+* `alloy_queue_network_metadata_network_duration_seconds` (histogram): Duration writing metadata to endpoint.
+* `alloy_queue_network_series_network_errors` (counter): Number of errors writing series to network.
+* `alloy_queue_network_metadata_network_errors` (counter): Number of errors writing metadata to network.
+
+## Examples
+
+The following examples show you how to create `prometheus.write.queue` components that send metrics to different destinations.
+
+### Send metrics to a local Mimir instance
+
+You can create a `prometheus.write.queue` component that sends your metrics to a local Mimir instance:
+
+```alloy
+prometheus.write.queue "staging" {
+  // Send metrics to a locally running Mimir.
+  endpoint "mimir" {
+    url = "http://mimir:9009/api/v1/push"
+
+    basic_auth {
+      username = "example-user"
+      password = "example-password"
+    }
+  }
+}
+
+// Configure a prometheus.scrape component to send metrics to
+// prometheus.write.queue component.
+prometheus.scrape "demo" {
+  targets = [
+    // Collect metrics from the default HTTP listen address.
+    {"__address__" = "127.0.0.1:12345"},
+  ]
+  forward_to = [prometheus.write.queue.staging.receiver]
+}
+
+```
+
+## Technical details
+
+`prometheus.write.queue` uses [snappy][] for compression.
+`prometheus.write.queue` sends native histograms by default.
+Any labels that start with `__` will be removed before sending to the endpoint.
+
+### Data retention
+
+Data is written to disk in blocks utilizing [snappy][] compression. These blocks are read on startup and resent if they are still within the TTL. 
+Any data that has not been written to disk, or that is in the network queues is lost if {{< param "PRODUCT_NAME" >}} is restarted.
+
+### Retries
+
+`prometheus.write.queue`  will retry sending data if the following errors or HTTP status codes are returned:
+
+ * Network errors. 
+ * HTTP 429 errors. 
+ * HTTP 5XX errors.
+
+`prometheus.write.queue`  will  not retry sending data if any other unsuccessful status codes are returned. 
+
+### Memory
+
+`prometheus.write.queue` is meant to be memory efficient.
+You can adjust the `max_signals_to_batch`, `parallelism`, and `batch_size` to control how much memory is used.
+A higher `max_signals_to_batch` allows for more efficient disk compression.
+A higher `parallelism` allows more parallel writes, and `batch_size` allows more data sent at one time.
+This can allow greater throughput at the cost of more memory on both {{< param "PRODUCT_NAME" >}} and the endpoint.
+The defaults are suitable for most common usages. 
+
+<!-- START GENERATED COMPATIBLE COMPONENTS -->
+
+## Compatible components
+
+`prometheus.write.queue` has exports that can be consumed by the following components:
+
+- Components that consume [Prometheus `MetricsReceiver`](../../../compatibility/#prometheus-metricsreceiver-consumers)
+
+{{< admonition type="note" >}}
+Connecting some components may not be sensible or components may require further configuration to make the connection work correctly.
+Refer to the linked documentation for more details.
+{{< /admonition >}}
+
+<!-- END GENERATED COMPATIBLE COMPONENTS -->
+
+[snappy]: https://en.wikipedia.org/wiki/Snappy_(compression)
+[Stop]: ../../../../set-up/run/
+[run]: ../../../cli/run/

go.mod

@@ -809,10 +809,8 @@ require (
 	k8s.io/kube-openapi v0.0.0-20240620174524-b456828f718b // indirect
 	sigs.k8s.io/json v0.0.0-20221116044647-bc3834ca7abd // indirect
 	sigs.k8s.io/structured-merge-diff/v4 v4.4.1 // indirect
-
-)
-
-require (
+	github.com/gammazero/deque v0.2.1 // indirect
+	github.com/vladopajic/go-actor v0.9.0 // indirect
 	github.com/aws/aws-sdk-go-v2/service/iam v1.33.1 // indirect
 	github.com/checkpoint-restore/go-criu/v6 v6.3.0 // indirect
 	github.com/containerd/platforms v0.2.1 // indirect

go.sum

@@ -885,6 +885,8 @@ github.com/fxamacker/cbor/v2 v2.7.0 h1:iM5WgngdRBanHcxugY4JySA0nk1wZorNOpTgCMedv
 github.com/fxamacker/cbor/v2 v2.7.0/go.mod h1:pxXPTn3joSm21Gbwsv0w9OSA2y1HFR9qXEeXQVeNoDQ=
 github.com/gabriel-vasile/mimetype v1.4.2 h1:w5qFW6JKBz9Y393Y4q372O9A7cUSequkh1Q7OhCmWKU=
 github.com/gabriel-vasile/mimetype v1.4.2/go.mod h1:zApsH/mKG4w07erKIaJPFiX0Tsq9BFQgN3qGY5GnNgA=
+github.com/gammazero/deque v0.2.1 h1:qSdsbG6pgp6nL7A0+K/B7s12mcCY/5l5SIUpMOl+dC0=
+github.com/gammazero/deque v0.2.1/go.mod h1:LFroj8x4cMYCukHJDbxFCkT+r9AndaJnFMuZDV34tuU=
 github.com/gavv/monotime v0.0.0-20190418164738-30dba4353424 h1:Vh7rylVZRZCj6W41lRlP17xPk4Nq260H4Xo/DDYmEZk=
 github.com/gavv/monotime v0.0.0-20190418164738-30dba4353424/go.mod h1:vmp8DIyckQMXOPl0AQVHt+7n5h7Gb7hS6CUydiV8QeA=
 github.com/ghodss/yaml v0.0.0-20150909031657-73d445a93680/go.mod h1:4dBDuWmgqj2HViK6kFavaiC9ZROes6MMH2rRYeMEF04=
@@ -2443,6 +2445,8 @@ github.com/vishvananda/netns v0.0.0-20200728191858-db3c7e526aae/go.mod h1:DD4vA1
 github.com/vishvananda/netns v0.0.4 h1:Oeaw1EM2JMxD51g9uhtC0D7erkIjgmj8+JZc26m1YX8=
 github.com/vishvananda/netns v0.0.4/go.mod h1:SpkAiCQRtJ6TvvxPnOSyH3BMl6unz3xZlaprSwhNNJM=
 github.com/vjeantet/grok v1.0.0/go.mod h1:/FWYEVYekkm+2VjcFmO9PufDU5FgXHUz9oy2EGqmQBo=
+github.com/vladopajic/go-actor v0.9.0 h1:fFj5RDGo4YZ6XCx2BWCThx/efOGRwokTpsc3CWHVEIU=
+github.com/vladopajic/go-actor v0.9.0/go.mod h1:CKVRXStfjEIi7K74SyFQv/KfM8a/Po57bxmbBGv9YwE=
 github.com/vmihailenco/msgpack/v4 v4.3.13 h1:A2wsiTbvp63ilDaWmsk2wjx6xZdxQOvpiNlKBGKKXKI=
 github.com/vmihailenco/msgpack/v4 v4.3.13/go.mod h1:gborTTJjAo/GWTqqRjrLCn9pgNN+NXzzngzBKDPIqw4=
 github.com/vmihailenco/tagparser v0.1.2 h1:gnjoVuB/kljJ5wICEEOpx98oXMWPLj22G67Vbd1qPqc=

internal/component/all/all.go

@@ -137,6 +137,7 @@ import (
 	_ "github.com/grafana/alloy/internal/component/prometheus/relabel"                       // Import prometheus.relabel
 	_ "github.com/grafana/alloy/internal/component/prometheus/remotewrite"                   // Import prometheus.remote_write
 	_ "github.com/grafana/alloy/internal/component/prometheus/scrape"                        // Import prometheus.scrape
+	_ "github.com/grafana/alloy/internal/component/prometheus/write/queue"                   // Import prometheus.write.queue
 	_ "github.com/grafana/alloy/internal/component/pyroscope/ebpf"                           // Import pyroscope.ebpf
 	_ "github.com/grafana/alloy/internal/component/pyroscope/java"                           // Import pyroscope.java
 	_ "github.com/grafana/alloy/internal/component/pyroscope/scrape"                         // Import pyroscope.scrape

internal/component/faro/receiver/internal/payload/payload.go

@@ -396,14 +396,14 @@ func (a App) KeyVal() *KeyVal {
 
 // Browser holds metadata about a client's browser
 type Browser struct {
-	Name           string `json:"name,omitempty"`
-	Version        string `json:"version,omitempty"`
-	OS             string `json:"os,omitempty"`
-	Mobile         bool   `json:"mobile,omitempty"`
-	UserAgent      string `json:"userAgent,omitempty"`
-	Language       string `json:"language,omitempty"`
+	Name      string `json:"name,omitempty"`
+	Version   string `json:"version,omitempty"`
+	OS        string `json:"os,omitempty"`
+	Mobile    bool   `json:"mobile,omitempty"`
+	UserAgent string `json:"userAgent,omitempty"`
+	Language  string `json:"language,omitempty"`
 	// TODO: properly serialize brands
-	// Brands json.RawMessage `json:"brands,omitempty"` 
+	// Brands json.RawMessage `json:"brands,omitempty"`
 	ViewportWidth  string `json:"viewportWidth,omitempty"`
 	ViewportHeight string `json:"viewportHeight,omitempty"`
 }

internal/component/faro/receiver/internal/payload/payload_test.go

@@ -54,13 +54,13 @@ func TestUnmarshalPayloadJSON(t *testing.T) {
 			URL: "https://example.com/page",
 		},
 		Browser: Browser{
-			Name:    "chrome",
-			Version: "88.12.1",
-			OS:      "linux",
-			Mobile:  false,
-			UserAgent: "Mozilla/5.0 (X11; Linux x86_64; rv:128.0) Gecko/20100101 Firefox/128.0",
-			Language: "en-US",
-			ViewportWidth: "1920",
+			Name:           "chrome",
+			Version:        "88.12.1",
+			OS:             "linux",
+			Mobile:         false,
+			UserAgent:      "Mozilla/5.0 (X11; Linux x86_64; rv:128.0) Gecko/20100101 Firefox/128.0",
+			Language:       "en-US",
+			ViewportWidth:  "1920",
 			ViewportHeight: "1080",
 		},
 		View: View{