feat: expose metrics for the git commit (#1249)

new `HostOperatorCommitGaugeVec` and `HostOperatorShortCommitGaugeVec` metrics
to reflect the current git commit and short commit of the host-operator

the metrics are named `sandbox_host_operator_commit` and `sandbox_host_operator_short_commit`
and the relevant label is `commit`

also, update the tests to assert the value of the metric.

also, deprecated the `HostOperatorVersionGaugeVec` metric (will be removed
in a future release, once Grafana is updated to support the new metrics)

Signed-off-by: Xavier Coulon <xcoulon@redhat.com>

* update govulncheck exclusions

Signed-off-by: Xavier Coulon <xcoulon@redhat.com>

* apply coderabbitai suggestion

Signed-off-by: Xavier Coulon <xcoulon@redhat.com>

* test

Signed-off-by: Xavier Coulon <xcoulon@redhat.com>

* update govulncheck exclusions

Signed-off-by: Xavier Coulon <xcoulon@redhat.com>

---------

Signed-off-by: Xavier Coulon <xcoulon@redhat.com>

Author: xcoulon

README.adoc

@@ -99,4 +99,4 @@ If you are still confused by the e2e location, execution and branch pairing, see
 *** 2. create a branch with the same name within your fork of https://github.com/codeready-toolchain/toolchain-e2e[toolchain-e2e] repo and put all necessary changes there
 *** 3. push all changes into both forks of the repositories https://github.com/codeready-toolchain/toolchain-e2e[toolchain-e2e] and https://github.com/codeready-toolchain/host-operator[host-operator]
 *** 4. create a PR for https://github.com/codeready-toolchain/host-operator[host-operator]
-*** 5. create a PR for https://github.com/codeready-toolchain/toolchain-e2e[toolchain-e2e]
+*** 5. create a PR for https://github.com/codeready-toolchain/toolchain-e2e[toolchain-e2e]

pkg/metrics/metrics.go

@@ -55,8 +55,12 @@ var (
 	UserSignupsPerActivationAndDomainGaugeVec *prometheus.GaugeVec
 	// MasterUserRecordGaugeVec reflects the current number of MasterUserRecords, labelled with their email address domain (`internal` vs `external`)
 	MasterUserRecordGaugeVec *prometheus.GaugeVec
-	// HostOperatorVersionGaugeVec reflects the current version of the host-operator (via the `version` label)
-	HostOperatorVersionGaugeVec *prometheus.GaugeVec
+	// HostOperatorVersionGaugeVec reflects the current short commit used to identify the version of the host-operator (via the `commit` label)
+	HostOperatorVersionGaugeVec *prometheus.GaugeVec // DEPRECATED: use HostOperatorShortCommitGaugeVec instead
+	// HostOperatorShortCommitGaugeVec reflects the current short git commit of the host-operator (via the `commit` label)
+	HostOperatorShortCommitGaugeVec *prometheus.GaugeVec
+	// HostOperatorCommitGaugeVec reflects the current full git commit of the host-operator (via the `commit` label)
+	HostOperatorCommitGaugeVec *prometheus.GaugeVec
 	// ToolchainStatusGaugeVec reflects the current status of the toolchainstatus, labelled with the status
 	ToolchainStatusGaugeVec *prometheus.GaugeVec
 )
@@ -100,7 +104,9 @@ func initMetrics() {
 	SpaceGaugeVec = newGaugeVec("spaces_current", "Current number of Spaces (per member cluster)", "cluster_name")
 	UserSignupsPerActivationAndDomainGaugeVec = newGaugeVec("users_per_activations_and_domain", "Number of UserSignups per activations and domain", []string{"activations", "domain"}...)
 	MasterUserRecordGaugeVec = newGaugeVec("master_user_records", "Number of MasterUserRecords per email address domain ('internal' vs 'external')", "domain")
-	HostOperatorVersionGaugeVec = newGaugeVec("host_operator_version", "Current version of the host operator", "commit")
+	HostOperatorVersionGaugeVec = newGaugeVec("host_operator_version", "Short commit used to identify the version of the host operator", "commit")
+	HostOperatorCommitGaugeVec = newGaugeVec("host_operator_commit", "Full commit used to identify the version of the host operator", "commit")
+	HostOperatorShortCommitGaugeVec = newGaugeVec("host_operator_short_commit", "Short commit used to identify the version of the host operator", "commit")
 	ToolchainStatusGaugeVec = newGaugeVec("toolchain_status", "Current status of the toolchain components", "component")
 	// Histograms
 	UserSignupProvisionTimeHistogram = newHistogram("user_signup_provision_time", "UserSignup provision time in seconds")
@@ -199,8 +205,9 @@ func RegisterCustomMetrics() []prometheus.Collector {
 		collectors = append(collectors, v)
 	}
 
-	// expose the HostOperatorVersionGaugeVec metric (static ie, 1 value per build/deployment)
-	HostOperatorVersionGaugeVec.WithLabelValues(version.Commit[0:7]).Set(1)
+	HostOperatorVersionGaugeVec.WithLabelValues(version.Commit[0:7]).Set(1)                 // the HostOperatorVersionGaugeVec is set to `1`, Grafana will display the 'commit' label as the version for the instant record
+	HostOperatorCommitGaugeVec.WithLabelValues(version.Commit).SetToCurrentTime()           // automatically set the value to the current time, so that the highest value is the current commit
+	HostOperatorShortCommitGaugeVec.WithLabelValues(version.Commit[0:7]).SetToCurrentTime() // automatically set the value to the current time, so that the highest value is the current commit
 
 	logger.Info("custom metrics registered")
 	return collectors

pkg/metrics/metrics_test.go

@@ -6,6 +6,7 @@ import (
 	"strconv"
 	"sync"
 	"testing"
+	"time"
 
 	toolchainv1alpha1 "github.com/codeready-toolchain/api/api/v1alpha1"
 	"github.com/codeready-toolchain/host-operator/pkg/metrics"
@@ -16,6 +17,8 @@ import (
 	"github.com/codeready-toolchain/toolchain-common/pkg/test/space"
 	"github.com/codeready-toolchain/toolchain-common/pkg/test/usersignup"
 
+	promtestutil "github.com/prometheus/client_golang/prometheus/testutil"
+	"github.com/stretchr/testify/assert"
 	"github.com/stretchr/testify/require"
 	runtimeclient "sigs.k8s.io/controller-runtime/pkg/client"
 	logf "sigs.k8s.io/controller-runtime/pkg/log"
@@ -40,6 +43,32 @@ func TestResetMetrics(t *testing.T) {
 	metricscommontest.AssertAllHistogramBucketsAreEmpty(t, metrics.UserSignupProvisionTimeHistogram)
 }
 
+func TestGitCommitGauge(t *testing.T) {
+	t.Run("HostOperatorCommitGaugeVec", func(t *testing.T) {
+		// given
+		metrics.Reset()
+		defer metrics.Reset()
+		now := time.Now()
+
+		// when
+		metrics.HostOperatorCommitGaugeVec.WithLabelValues("commit-1234567890").SetToCurrentTime()
+
+		// then
+		assert.InDelta(t, float64(now.Unix()), promtestutil.ToFloat64(metrics.HostOperatorCommitGaugeVec.WithLabelValues("commit-1234567890")), float64(time.Minute.Seconds()))
+	})
+	t.Run("HostOperatorShortCommitGaugeVec", func(t *testing.T) {
+		// given
+		metrics.Reset()
+		defer metrics.Reset()
+		now := time.Now()
+
+		// when
+		metrics.HostOperatorShortCommitGaugeVec.WithLabelValues("hash-1234567890").SetToCurrentTime()
+
+		// then
+		assert.InDelta(t, float64(now.Unix()), promtestutil.ToFloat64(metrics.HostOperatorShortCommitGaugeVec.WithLabelValues("hash-1234567890")), float64(time.Minute.Seconds()))
+	})
+}
 func TestIncrementMasterUserRecordCount(t *testing.T) {
 	// given
 	metrics.Reset()