[HCP Observability] Init OTELSink in Telemetry (#17162)

* Move hcp client to subpackage hcpclient (#16800) * [HCP Observability] New MetricsClient (#17100) * Client configured with TLS using HCP config and retry/throttle * Add tests and godoc for metrics client * close body after request * run go mod tidy * Remove one abstraction to use the config from deps * Address PR feedback * remove clone * Extract CloudConfig and mock for future PR * Switch to hclog.FromContext * [HCP Observability] New MetricsClient (#17100) * Client configured with TLS using HCP config and retry/throttle * Add tests and godoc for metrics client * close body after request * run go mod tidy * Remove one abstraction to use the config from deps * Address PR feedback * remove clone * Extract CloudConfig and mock for future PR * Switch to hclog.FromContext * [HCP Observability] New MetricsClient (#17100) * Client configured with TLS using HCP config and retry/throttle * Add tests and godoc for metrics client * close body after request * run go mod tidy * Remove one abstraction to use the config from deps * Address PR feedback * remove clone * Extract CloudConfig and mock for future PR * Switch to hclog.FromContext * Client configured with TLS using HCP config and retry/throttle * run go mod tidy * Remove one abstraction to use the config from deps * Address PR feedback * Client configured with TLS using HCP config and retry/throttle * run go mod tidy * Create new OTELExporter which uses the MetricsClient Add transform because the conversion is in an /internal package * Fix lint error * early return when there are no metrics * Add NewOTELExporter() function * Downgrade to metrics SDK version: v1.15.0-rc.1 * Fix imports * fix small nits with comments and url.URL * Fix tests by asserting actual error for context cancellation, fix parallel, and make mock more versatile * Cleanup error handling and clarify empty metrics case * Fix input/expected naming in otel_transform_test.go * add comment for metric tracking * Add a general isEmpty method * Add clear error types * update to latest version 1.15.0 of OTEL * Client configured with TLS using HCP config and retry/throttle * run go mod tidy * Remove one abstraction to use the config from deps * Address PR feedback * Initialize OTELSink with sync.Map for all the instrument stores. * Moved PeriodicReader init to NewOtelReader function. This allows us to use a ManualReader for tests. * Switch to mutex instead of sync.Map to avoid type assertion * Add gauge store * Clarify comments * return concrete sink type * Fix lint errors * Move gauge store to be within sink * Use context.TODO,rebase and clenaup opts handling * Rebase onto otl exporter to downgrade metrics API to v1.15.0-rc.1 * Fix imports * Update to latest stable version by rebasing on cc-4933, fix import, remove mutex init, fix opts error messages and use logger from ctx * Add lots of documentation to the OTELSink * Fix gauge store comment and check ok * Add select and ctx.Done() check to gauge callback * use require.Equal for attributes * Fixed import naming * Remove float64 calls and add a NewGaugeStore method * Change name Store to Set in gaugeStore, add concurrency tests in both OTELSink and gauge store * Generate 100 gauge operations * Seperate the labels into goroutines in sink test * Generate kv store for the test case keys to avoid using uuid * Added a race test with 300 samples for OTELSink * [HCP Observability] OTELExporter (#17128) * Client configured with TLS using HCP config and retry/throttle * run go mod tidy * Remove one abstraction to use the config from deps * Address PR feedback * Client configured with TLS using HCP config and retry/throttle * run go mod tidy * Create new OTELExporter which uses the MetricsClient Add transform because the conversion is in an /internal package * Fix lint error * early return when there are no metrics * Add NewOTELExporter() function * Downgrade to metrics SDK version: v1.15.0-rc.1 * Fix imports * fix small nits with comments and url.URL * Fix tests by asserting actual error for context cancellation, fix parallel, and make mock more versatile * Cleanup error handling and clarify empty metrics case * Fix input/expected naming in otel_transform_test.go * add comment for metric tracking * Add a general isEmpty method * Add clear error types * update to latest version 1.15.0 of OTEL * Do not pass in waitgroup and use error channel instead. * Using SHA 7dea2225a218872e86d2f580e82c089b321617b0 to avoid build failures in otel * Rebase onto otl exporter to downgrade metrics API to v1.15.0-rc.1 * Initialize OTELSink with sync.Map for all the instrument stores. * Added telemetry agent to client and init sink in deps * Fixed client * Initalize sink in deps * init sink in telemetry library * Init deps before telemetry * Use concrete telemetry.OtelSink type * add /v1/metrics * Avoid returning err for telemetry init * move sink init within the IsCloudEnabled() * Use HCPSinkOpts in deps instead * update golden test for configuration file * Switch to using extra sinks in the telemetry library * keep name MetricsConfig * fix log in verifyCCMRegistration * Set logger in context * pass around MetricSink in deps * Fix imports * Rebased onto otel sink pr * Fix URL in test * [HCP Observability] OTELSink (#17159) * Client configured with TLS using HCP config and retry/throttle * run go mod tidy * Remove one abstraction to use the config from deps * Address PR feedback * Client configured with TLS using HCP config and retry/throttle * run go mod tidy * Create new OTELExporter which uses the MetricsClient Add transform because the conversion is in an /internal package * Fix lint error * early return when there are no metrics * Add NewOTELExporter() function * Downgrade to metrics SDK version: v1.15.0-rc.1 * Fix imports * fix small nits with comments and url.URL * Fix tests by asserting actual error for context cancellation, fix parallel, and make mock more versatile * Cleanup error handling and clarify empty metrics case * Fix input/expected naming in otel_transform_test.go * add comment for metric tracking * Add a general isEmpty method * Add clear error types * update to latest version 1.15.0 of OTEL * Client configured with TLS using HCP config and retry/throttle * run go mod tidy * Remove one abstraction to use the config from deps * Address PR feedback * Initialize OTELSink with sync.Map for all the instrument stores. * Moved PeriodicReader init to NewOtelReader function. This allows us to use a ManualReader for tests. * Switch to mutex instead of sync.Map to avoid type assertion * Add gauge store * Clarify comments * return concrete sink type * Fix lint errors * Move gauge store to be within sink * Use context.TODO,rebase and clenaup opts handling * Rebase onto otl exporter to downgrade metrics API to v1.15.0-rc.1 * Fix imports * Update to latest stable version by rebasing on cc-4933, fix import, remove mutex init, fix opts error messages and use logger from ctx * Add lots of documentation to the OTELSink * Fix gauge store comment and check ok * Add select and ctx.Done() check to gauge callback * use require.Equal for attributes * Fixed import naming * Remove float64 calls and add a NewGaugeStore method * Change name Store to Set in gaugeStore, add concurrency tests in both OTELSink and gauge store * Generate 100 gauge operations * Seperate the labels into goroutines in sink test * Generate kv store for the test case keys to avoid using uuid * Added a race test with 300 samples for OTELSink * Do not pass in waitgroup and use error channel instead. * Using SHA 7dea2225a218872e86d2f580e82c089b321617b0 to avoid build failures in otel * Fix nits * pass extraSinks as function param instead * Add default interval as package export * remove verifyCCM func * Add clusterID * Fix import and add t.Parallel() for missing tests * Kick Vercel CI * Remove scheme from endpoint path, and fix error logging * return metrics.MetricSink for sink method * Update SDK
hashicorp · May 29, 2023 · 68e6e21 · 68e6e21
1 parent fb92de5
commit 68e6e21
Show file tree

Hide file tree

Showing 14 changed files with 427 additions and 34 deletions.
diff --git a/agent/hcp/client/client.go b/agent/hcp/client/client.go
@@ -12,23 +12,44 @@ import (
 	httptransport "github.com/go-openapi/runtime/client"
 	"github.com/go-openapi/strfmt"
 
-	"github.com/hashicorp/consul/agent/hcp/config"
-	"github.com/hashicorp/consul/version"
+	hcptelemetry "github.com/hashicorp/hcp-sdk-go/clients/cloud-consul-telemetry-gateway/preview/2023-04-14/client/consul_telemetry_service"
 	hcpgnm "github.com/hashicorp/hcp-sdk-go/clients/cloud-global-network-manager-service/preview/2022-02-15/client/global_network_manager_service"
 	gnmmod "github.com/hashicorp/hcp-sdk-go/clients/cloud-global-network-manager-service/preview/2022-02-15/models"
 	"github.com/hashicorp/hcp-sdk-go/httpclient"
 	"github.com/hashicorp/hcp-sdk-go/resource"
+
+	"github.com/hashicorp/consul/agent/hcp/config"
+	"github.com/hashicorp/consul/version"
 )
 
+// metricsGatewayPath is the default path for metrics export request on the Telemetry Gateway.
+const metricsGatewayPath = "/v1/metrics"
+
 // Client interface exposes HCP operations that can be invoked by Consul
 //
 //go:generate mockery --name Client --with-expecter --inpackage
 type Client interface {
 	FetchBootstrap(ctx context.Context) (*BootstrapConfig, error)
+	FetchTelemetryConfig(ctx context.Context) (*TelemetryConfig, error)
 	PushServerStatus(ctx context.Context, status *ServerStatus) error
 	DiscoverServers(ctx context.Context) ([]string, error)
 }
 
+// MetricsConfig holds metrics specific configuration for the TelemetryConfig.
+// The endpoint field overrides the TelemetryConfig endpoint.
+type MetricsConfig struct {
+	Filters  []string
+	Endpoint string
+}
+
+// TelemetryConfig contains configuration for telemetry data forwarded by Consul servers
+// to the HCP Telemetry gateway.
+type TelemetryConfig struct {
+	Endpoint      string
+	Labels        map[string]string
+	MetricsConfig *MetricsConfig
+}
+
 type BootstrapConfig struct {
 	Name            string
 	BootstrapExpect int
@@ -44,6 +65,7 @@ type hcpClient struct {
 	hc       *httptransport.Runtime
 	cfg      config.CloudConfig
 	gnm      hcpgnm.ClientService
+	tgw      hcptelemetry.ClientService
 	resource resource.Resource
 }
 
@@ -64,6 +86,8 @@ func NewClient(cfg config.CloudConfig) (Client, error) {
 	}
 
 	client.gnm = hcpgnm.New(client.hc, nil)
+	client.tgw = hcptelemetry.New(client.hc, nil)
+
 	return client, nil
 }
 
@@ -79,6 +103,29 @@ func httpClient(c config.CloudConfig) (*httptransport.Runtime, error) {
 	})
 }
 
+// FetchTelemetryConfig obtains telemetry configuration from the Telemetry Gateway.
+func (c *hcpClient) FetchTelemetryConfig(ctx context.Context) (*TelemetryConfig, error) {
+	params := hcptelemetry.NewAgentTelemetryConfigParamsWithContext(ctx).
+		WithLocationOrganizationID(c.resource.Organization).
+		WithLocationProjectID(c.resource.Project).
+		WithClusterID(c.resource.ID)
+
+	resp, err := c.tgw.AgentTelemetryConfig(params, nil)
+	if err != nil {
+		return nil, err
+	}
+
+	payloadConfig := resp.Payload.TelemetryConfig
+	return &TelemetryConfig{
+		Endpoint: payloadConfig.Endpoint,
+		Labels:   payloadConfig.Labels,
+		MetricsConfig: &MetricsConfig{
+			Filters:  payloadConfig.Metrics.IncludeList,
+			Endpoint: payloadConfig.Metrics.Endpoint,
+		},
+	}, nil
+}
+
 func (c *hcpClient) FetchBootstrap(ctx context.Context) (*BootstrapConfig, error) {
 	version := version.GetHumanVersion()
 	params := hcpgnm.NewAgentBootstrapConfigParamsWithContext(ctx).
@@ -233,3 +280,19 @@ func (c *hcpClient) DiscoverServers(ctx context.Context) ([]string, error) {
 
 	return servers, nil
 }
+
+// Enabled verifies if telemetry is enabled by ensuring a valid endpoint has been retrieved.
+// It returns full metrics endpoint and true if a valid endpoint was obtained.
+func (t *TelemetryConfig) Enabled() (string, bool) {
+	endpoint := t.Endpoint
+	if override := t.MetricsConfig.Endpoint; override != "" {
+		endpoint = override
+	}
+
+	if endpoint == "" {
+		return "", false
+	}
+
+	// The endpoint from Telemetry Gateway is a domain without scheme, and without the metrics path, so they must be added.
+	return endpoint + metricsGatewayPath, true
+}
diff --git a/agent/hcp/client/client_test.go b/agent/hcp/client/client_test.go
@@ -0,0 +1,75 @@
+package client
+
+import (
+	"context"
+	"testing"
+
+	"github.com/stretchr/testify/mock"
+	"github.com/stretchr/testify/require"
+)
+
+func TestFetchTelemetryConfig(t *testing.T) {
+	t.Parallel()
+	for name, test := range map[string]struct {
+		metricsEndpoint string
+		expect          func(*MockClient)
+		disabled        bool
+	}{
+		"success": {
+			expect: func(mockClient *MockClient) {
+				mockClient.EXPECT().FetchTelemetryConfig(mock.Anything).Return(&TelemetryConfig{
+					Endpoint: "https://test.com",
+					MetricsConfig: &MetricsConfig{
+						Endpoint: "",
+					},
+				}, nil)
+			},
+			metricsEndpoint: "https://test.com/v1/metrics",
+		},
+		"overrideMetricsEndpoint": {
+			expect: func(mockClient *MockClient) {
+				mockClient.EXPECT().FetchTelemetryConfig(mock.Anything).Return(&TelemetryConfig{
+					Endpoint: "https://test.com",
+					MetricsConfig: &MetricsConfig{
+						Endpoint: "https://test.com",
+					},
+				}, nil)
+			},
+			metricsEndpoint: "https://test.com/v1/metrics",
+		},
+		"disabledWithEmptyEndpoint": {
+			expect: func(mockClient *MockClient) {
+				mockClient.EXPECT().FetchTelemetryConfig(mock.Anything).Return(&TelemetryConfig{
+					Endpoint: "",
+					MetricsConfig: &MetricsConfig{
+						Endpoint: "",
+					},
+				}, nil)
+			},
+			disabled: true,
+		},
+	} {
+		test := test
+		t.Run(name, func(t *testing.T) {
+			t.Parallel()
+
+			mock := NewMockClient(t)
+			test.expect(mock)
+
+			telemetryCfg, err := mock.FetchTelemetryConfig(context.Background())
+			require.NoError(t, err)
+
+			if test.disabled {
+				endpoint, ok := telemetryCfg.Enabled()
+				require.False(t, ok)
+				require.Empty(t, endpoint)
+				return
+			}
+
+			endpoint, ok := telemetryCfg.Enabled()
+
+			require.True(t, ok)
+			require.Equal(t, test.metricsEndpoint, endpoint)
+		})
+	}
+}
diff --git a/agent/hcp/client/mock_Client.go b/agent/hcp/client/mock_Client.go
diff --git a/agent/hcp/config/config.go b/agent/hcp/config/config.go
@@ -46,6 +46,6 @@ func (c *CloudConfig) HCPConfig(opts ...hcpcfg.HCPConfigOption) (hcpcfg.HCPConfi
 	if c.ScadaAddress != "" {
 		opts = append(opts, hcpcfg.WithSCADA(c.ScadaAddress, c.TLSConfig))
 	}
-	opts = append(opts, hcpcfg.FromEnv())
+	opts = append(opts, hcpcfg.FromEnv(), hcpcfg.WithoutBrowserLogin())
 	return hcpcfg.NewHCPConfig(opts...)
 }