- Notifications
You must be signed in to change notification settings - Fork1k
feat: expose agent metrics via Prometheus endpoint#7011
New issue
Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.
By clicking “Sign up for GitHub”, you agree to ourterms of service andprivacy statement. We’ll occasionally send you account related emails.
Already on GitHub?Sign in to your account
Merged
Uh oh!
There was an error while loading.Please reload this page.
Merged
Changes fromall commits
Commits
Show all changes
16 commits Select commitHold shift + click to select a range
8d4e67d WIP
mtojekda729e6 Merge branch 'main' into 6724-metrics
mtojek9ad09b2 WIP
mtojek440657c WIP
mtojek8764f89 Agents
mtojek663b5d5 fix
mtojek63aff5e 1min
mtojek3905481 fix
mtojekf8d6f46 WIP
mtojekd487a77 Test
mtojek7acbaf0 docs
mtojek7418779 fmt
mtojek3a8e4e6 Add timer to measure the metrics collection
mtojekb5d0581 Use CachedGaugeVec
mtojeke4d708b Unit tests
mtojeke0669f0 Address PR comments
mtojekFile filter
Filter by extension
Conversations
Failed to load comments.
Loading
Uh oh!
There was an error while loading.Please reload this page.
Jump to
Jump to file
Failed to load files.
Loading
Uh oh!
There was an error while loading.Please reload this page.
Diff view
Diff view
There are no files selected for viewing
9 changes: 9 additions & 0 deletionscli/server.go
This file contains hidden or bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.Learn more about bidirectional Unicode characters
95 changes: 95 additions & 0 deletionscoderd/prometheusmetrics/collector.go
This file contains hidden or bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.Learn more about bidirectional Unicode characters
| Original file line number | Diff line number | Diff line change | ||||
|---|---|---|---|---|---|---|
| @@ -0,0 +1,95 @@ | ||||||
| package prometheusmetrics | ||||||
| import ( | ||||||
| "sync" | ||||||
| "github.com/prometheus/client_golang/prometheus" | ||||||
| ) | ||||||
| // CachedGaugeVec is a wrapper for the prometheus.GaugeVec which allows | ||||||
| // for staging changes in the metrics vector. Calling "WithLabelValues(...)" | ||||||
| // will update the internal gauge value, but it will not be returned by | ||||||
| // "Collect(...)" until the "Commit()" method is called. The "Commit()" method | ||||||
| // resets the internal gauge and applies all staged changes to it. | ||||||
| // | ||||||
| // The Use of CachedGaugeVec is recommended for use cases when there is a risk | ||||||
| // that the Prometheus collector receives incomplete metrics, collected | ||||||
| // in the middle of metrics recalculation, between "Reset()" and the last | ||||||
| // "WithLabelValues()" call. | ||||||
| type CachedGaugeVec struct { | ||||||
| m sync.Mutex | ||||||
| gaugeVec *prometheus.GaugeVec | ||||||
| records []vectorRecord | ||||||
| } | ||||||
Comment on lines +19 to +24 There was a problem hiding this comment. Choose a reason for hiding this commentThe reason will be displayed to describe this comment to others.Learn more. Can you doc the usage? And the why? Eg:
Or something... There was a problem hiding this comment. Choose a reason for hiding this commentThe reason will be displayed to describe this comment to others.Learn more. Added 👍 | ||||||
| var _ prometheus.Collector = new(CachedGaugeVec) | ||||||
| type VectorOperation int | ||||||
| const ( | ||||||
| VectorOperationAdd VectorOperation = iota | ||||||
| VectorOperationSet | ||||||
| ) | ||||||
| type vectorRecord struct { | ||||||
| operation VectorOperation | ||||||
| value float64 | ||||||
| labelValues []string | ||||||
| } | ||||||
| func NewCachedGaugeVec(gaugeVec *prometheus.GaugeVec) *CachedGaugeVec { | ||||||
| return &CachedGaugeVec{ | ||||||
| gaugeVec: gaugeVec, | ||||||
| } | ||||||
| } | ||||||
| func (v *CachedGaugeVec) Describe(desc chan<- *prometheus.Desc) { | ||||||
| v.gaugeVec.Describe(desc) | ||||||
| } | ||||||
| func (v *CachedGaugeVec) Collect(ch chan<- prometheus.Metric) { | ||||||
| v.m.Lock() | ||||||
| defer v.m.Unlock() | ||||||
| v.gaugeVec.Collect(ch) | ||||||
| } | ||||||
| func (v *CachedGaugeVec) WithLabelValues(operation VectorOperation, value float64, labelValues ...string) { | ||||||
| switch operation { | ||||||
| case VectorOperationAdd: | ||||||
| case VectorOperationSet: | ||||||
| default: | ||||||
Comment on lines +59 to +62 There was a problem hiding this comment. Choose a reason for hiding this commentThe reason will be displayed to describe this comment to others.Learn more. I usually prefer this. But it does not matter. switchoperation {caseVectorOperationAdd,VectorOperationSet:default:} There was a problem hiding this comment. Choose a reason for hiding this commentThe reason will be displayed to describe this comment to others.Learn more. | ||||||
| panic("unsupported vector operation") | ||||||
| } | ||||||
| v.m.Lock() | ||||||
| defer v.m.Unlock() | ||||||
| v.records = append(v.records, vectorRecord{ | ||||||
| operation: operation, | ||||||
| value: value, | ||||||
| labelValues: labelValues, | ||||||
| }) | ||||||
| } | ||||||
| // Commit will set the internal value as the cached value to return from "Collect()". | ||||||
| // The internal metric value is completely reset, so the caller should expect | ||||||
| // the gauge to be empty for the next 'WithLabelValues' values. | ||||||
| func (v *CachedGaugeVec) Commit() { | ||||||
There was a problem hiding this comment. Choose a reason for hiding this commentThe reason will be displayed to describe this comment to others.Learn more. // Commit will set the internal value as the cached value to return from 'Collect'. Suggested change
There was a problem hiding this comment. Choose a reason for hiding this commentThe reason will be displayed to describe this comment to others.Learn more. Comment added. | ||||||
| v.m.Lock() | ||||||
| defer v.m.Unlock() | ||||||
| v.gaugeVec.Reset() | ||||||
| for _, record := range v.records { | ||||||
| g := v.gaugeVec.WithLabelValues(record.labelValues...) | ||||||
| switch record.operation { | ||||||
| case VectorOperationAdd: | ||||||
| g.Add(record.value) | ||||||
| case VectorOperationSet: | ||||||
| g.Set(record.value) | ||||||
| } | ||||||
| } | ||||||
| v.records = nil | ||||||
| } | ||||||
140 changes: 140 additions & 0 deletionscoderd/prometheusmetrics/collector_test.go
This file contains hidden or bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.Learn more about bidirectional Unicode characters
| Original file line number | Diff line number | Diff line change |
|---|---|---|
| @@ -0,0 +1,140 @@ | ||
| package prometheusmetrics_test | ||
| import ( | ||
| "sort" | ||
| "testing" | ||
| "github.com/prometheus/client_golang/prometheus" | ||
| dto "github.com/prometheus/client_model/go" | ||
| "github.com/stretchr/testify/assert" | ||
| "github.com/stretchr/testify/require" | ||
| "github.com/coder/coder/coderd/prometheusmetrics" | ||
| ) | ||
| func TestCollector_Add(t *testing.T) { | ||
| t.Parallel() | ||
| // given | ||
| agentsGauge := prometheusmetrics.NewCachedGaugeVec(prometheus.NewGaugeVec(prometheus.GaugeOpts{ | ||
| Namespace: "coderd", | ||
| Subsystem: "agents", | ||
| Name: "up", | ||
| Help: "The number of active agents per workspace.", | ||
| }, []string{"username", "workspace_name"})) | ||
| // when | ||
| agentsGauge.WithLabelValues(prometheusmetrics.VectorOperationAdd, 7, "first user", "my workspace") | ||
| agentsGauge.WithLabelValues(prometheusmetrics.VectorOperationAdd, 23, "second user", "your workspace") | ||
| agentsGauge.WithLabelValues(prometheusmetrics.VectorOperationAdd, 1, "first user", "my workspace") | ||
| agentsGauge.WithLabelValues(prometheusmetrics.VectorOperationAdd, 25, "second user", "your workspace") | ||
| agentsGauge.Commit() | ||
| // then | ||
| ch := make(chan prometheus.Metric, 2) | ||
| agentsGauge.Collect(ch) | ||
| metrics := collectAndSortMetrics(t, agentsGauge, 2) | ||
| assert.Equal(t, "first user", metrics[0].Label[0].GetValue()) // Username | ||
| assert.Equal(t, "my workspace", metrics[0].Label[1].GetValue()) // Workspace name | ||
| assert.Equal(t, 8, int(metrics[0].Gauge.GetValue())) // Metric value | ||
| assert.Equal(t, "second user", metrics[1].Label[0].GetValue()) // Username | ||
| assert.Equal(t, "your workspace", metrics[1].Label[1].GetValue()) // Workspace name | ||
| assert.Equal(t, 48, int(metrics[1].Gauge.GetValue())) // Metric value | ||
| } | ||
| func TestCollector_Set(t *testing.T) { | ||
| t.Parallel() | ||
| // given | ||
| agentsGauge := prometheusmetrics.NewCachedGaugeVec(prometheus.NewGaugeVec(prometheus.GaugeOpts{ | ||
| Namespace: "coderd", | ||
| Subsystem: "agents", | ||
| Name: "up", | ||
| Help: "The number of active agents per workspace.", | ||
| }, []string{"username", "workspace_name"})) | ||
| // when | ||
| agentsGauge.WithLabelValues(prometheusmetrics.VectorOperationSet, 3, "first user", "my workspace") | ||
| agentsGauge.WithLabelValues(prometheusmetrics.VectorOperationSet, 4, "second user", "your workspace") | ||
| agentsGauge.WithLabelValues(prometheusmetrics.VectorOperationSet, 5, "first user", "my workspace") | ||
| agentsGauge.WithLabelValues(prometheusmetrics.VectorOperationSet, 6, "second user", "your workspace") | ||
| agentsGauge.Commit() | ||
| // then | ||
| ch := make(chan prometheus.Metric, 2) | ||
| agentsGauge.Collect(ch) | ||
| metrics := collectAndSortMetrics(t, agentsGauge, 2) | ||
| assert.Equal(t, "first user", metrics[0].Label[0].GetValue()) // Username | ||
| assert.Equal(t, "my workspace", metrics[0].Label[1].GetValue()) // Workspace name | ||
| assert.Equal(t, 5, int(metrics[0].Gauge.GetValue())) // Metric value | ||
| assert.Equal(t, "second user", metrics[1].Label[0].GetValue()) // Username | ||
| assert.Equal(t, "your workspace", metrics[1].Label[1].GetValue()) // Workspace name | ||
| assert.Equal(t, 6, int(metrics[1].Gauge.GetValue())) // Metric value | ||
| } | ||
| func TestCollector_Set_Add(t *testing.T) { | ||
| t.Parallel() | ||
| // given | ||
| agentsGauge := prometheusmetrics.NewCachedGaugeVec(prometheus.NewGaugeVec(prometheus.GaugeOpts{ | ||
| Namespace: "coderd", | ||
| Subsystem: "agents", | ||
| Name: "up", | ||
| Help: "The number of active agents per workspace.", | ||
| }, []string{"username", "workspace_name"})) | ||
| // when | ||
| agentsGauge.WithLabelValues(prometheusmetrics.VectorOperationAdd, 9, "first user", "my workspace") | ||
| agentsGauge.WithLabelValues(prometheusmetrics.VectorOperationAdd, 8, "second user", "your workspace") | ||
| agentsGauge.WithLabelValues(prometheusmetrics.VectorOperationAdd, 7, "first user", "my workspace") | ||
| agentsGauge.WithLabelValues(prometheusmetrics.VectorOperationAdd, 6, "second user", "your workspace") | ||
| agentsGauge.WithLabelValues(prometheusmetrics.VectorOperationSet, 5, "first user", "my workspace") | ||
| agentsGauge.WithLabelValues(prometheusmetrics.VectorOperationSet, 4, "second user", "your workspace") | ||
| agentsGauge.WithLabelValues(prometheusmetrics.VectorOperationAdd, 3, "first user", "my workspace") | ||
| agentsGauge.WithLabelValues(prometheusmetrics.VectorOperationAdd, 2, "second user", "your workspace") | ||
| agentsGauge.Commit() | ||
| // then | ||
| ch := make(chan prometheus.Metric, 2) | ||
| agentsGauge.Collect(ch) | ||
| metrics := collectAndSortMetrics(t, agentsGauge, 2) | ||
| assert.Equal(t, "first user", metrics[0].Label[0].GetValue()) // Username | ||
| assert.Equal(t, "my workspace", metrics[0].Label[1].GetValue()) // Workspace name | ||
| assert.Equal(t, 8, int(metrics[0].Gauge.GetValue())) // Metric value | ||
| assert.Equal(t, "second user", metrics[1].Label[0].GetValue()) // Username | ||
| assert.Equal(t, "your workspace", metrics[1].Label[1].GetValue()) // Workspace name | ||
| assert.Equal(t, 6, int(metrics[1].Gauge.GetValue())) // Metric value | ||
| } | ||
| func collectAndSortMetrics(t *testing.T, collector prometheus.Collector, count int) []dto.Metric { | ||
| ch := make(chan prometheus.Metric, count) | ||
| defer close(ch) | ||
| var metrics []dto.Metric | ||
| collector.Collect(ch) | ||
| for i := 0; i < count; i++ { | ||
| m := <-ch | ||
| var metric dto.Metric | ||
| err := m.Write(&metric) | ||
| require.NoError(t, err) | ||
| metrics = append(metrics, metric) | ||
| } | ||
| // Ensure always the same order of metrics | ||
| sort.Slice(metrics, func(i, j int) bool { | ||
| return sort.StringsAreSorted([]string{metrics[i].Label[0].GetValue(), metrics[j].Label[1].GetValue()}) | ||
| }) | ||
| return metrics | ||
| } |
Oops, something went wrong.
Uh oh!
There was an error while loading.Please reload this page.
Add this suggestion to a batch that can be applied as a single commit.This suggestion is invalid because no changes were made to the code.Suggestions cannot be applied while the pull request is closed.Suggestions cannot be applied while viewing a subset of changes.Only one suggestion per line can be applied in a batch.Add this suggestion to a batch that can be applied as a single commit.Applying suggestions on deleted lines is not supported.You must change the existing code in this line in order to create a valid suggestion.Outdated suggestions cannot be applied.This suggestion has been applied or marked resolved.Suggestions cannot be applied from pending reviews.Suggestions cannot be applied on multi-line comments.Suggestions cannot be applied while the pull request is queued to merge.Suggestion cannot be applied right now. Please check back later.