otel: update breaking changing apis

cmd/api/main.go

@@ -54,7 +54,7 @@ func main() {
 	logging.SetupLogger(buildinfo.GitCommit, config.Log.Debug, config.Log.Human)
 
 	// Validator instrumentation configuration.
-	if err := metrics.SetupInstrumentation(":" + config.Metrics.Port); err != nil {
+	if err := metrics.SetupInstrumentation(":"+config.Metrics.Port, "tableland:api"); err != nil {
 		log.Fatal().
 			Err(err).
 			Str("port", config.Metrics.Port).
@@ -108,9 +108,10 @@ func main() {
 		log.Fatal().Err(err).Msg("creating executors db")
 	}
 	executorsDB.SetMaxOpenConns(1)
+	attrs := append([]attribute.KeyValue{attribute.String("name", "executors")}, metrics.BaseAttrs...)
 	if err := otelsql.RegisterDBStatsMetrics(
 		executorsDB,
-		otelsql.WithAttributes(attribute.String("name", "executors"))); err != nil {
+		otelsql.WithAttributes(attrs...)); err != nil {
 		log.Fatal().Err(err).Msg("registering executors db stats")
 	}
 

cmd/healthbot/counterprobe/metrics.go

@@ -4,14 +4,15 @@ import (
 	"context"
 	"fmt"
 
+	"github.com/textileio/go-tableland/pkg/metrics"
 	"go.opentelemetry.io/otel/attribute"
 	"go.opentelemetry.io/otel/metric/global"
 	"go.opentelemetry.io/otel/metric/instrument"
 )
 
 func (cp *CounterProbe) initMetrics(chainName string) error {
 	meter := global.MeterProvider().Meter("tableland")
-	cp.mBaseLabels = []attribute.KeyValue{attribute.String("chain_name", chainName)}
+	cp.mBaseLabels = append([]attribute.KeyValue{attribute.String("chain_name", chainName)}, metrics.BaseAttrs...)
 
 	latencyHistogram, err := meter.SyncInt64().Histogram(metricPrefix + ".latency")
 	if err != nil {

cmd/healthbot/main.go

@@ -18,7 +18,7 @@ import (
 func main() {
 	cfg := setupConfig()
 	logging.SetupLogger(buildinfo.GitCommit, cfg.Log.Debug, cfg.Log.Human)
-	if err := metrics.SetupInstrumentation(":" + cfg.Metrics.Port); err != nil {
+	if err := metrics.SetupInstrumentation(":"+cfg.Metrics.Port, "tableland:healthbot"); err != nil {
 		log.Fatal().Err(err).Str("port", cfg.Metrics.Port).Msg("could not setup instrumentation")
 	}
 

docker/deployed/docker-compose.healthbot.yml

@@ -4,8 +4,6 @@ services:
       context: ..
       dockerfile: ./cmd/healthbot/Dockerfile
     platform: linux/${PLATFORM}
-    environment:
-      - OTEL_SERVICE_NAME=tableland:healthbot # this is just to the unknown_service from the metrics label
     env_file:
       - ${PWD}/${ENVIRONMENT}/healthbot/.env_healthbot
     volumes:

docker/docker-compose.yml

@@ -6,7 +6,6 @@ services:
       dockerfile: ./cmd/api/Dockerfile
     platform: linux/${PLATFORM}
     environment:
-      - OTEL_SERVICE_NAME=tableland:api # this is just to the unknown_service from the metrics label
       - BOOTSTRAP_BACKUP_URL=${BOOTSTRAP_BACKUP_URL}
     env_file:
       - ${PWD}/${ENVIRONMENT}/api/.env_validator

docker/observability/grafana/provisioning/dashboards/validator-dashboard.json

@@ -664,6 +664,68 @@
       "title": "Last Hash Calculation Elapsed Time",
       "type": "stat"
     },
+    {
+      "datasource": {
+        "type": "prometheus",
+        "uid": "P1809F7CD0C75ACF3"
+      },
+      "fieldConfig": {
+        "defaults": {
+          "color": {
+            "mode": "thresholds"
+          },
+          "mappings": [],
+          "thresholds": {
+            "mode": "absolute",
+            "steps": [
+              {
+                "color": "green",
+                "value": null
+              }
+            ]
+          },
+          "unit": "ms"
+        },
+        "overrides": []
+      },
+      "gridPos": {
+        "h": 5,
+        "w": 4,
+        "x": 10,
+        "y": 15
+      },
+      "id": 85,
+      "options": {
+        "colorMode": "value",
+        "graphMode": "area",
+        "justifyMode": "auto",
+        "orientation": "auto",
+        "reduceOptions": {
+          "calcs": [
+            "lastNotNull"
+          ],
+          "fields": "",
+          "values": false
+        },
+        "textMode": "auto"
+      },
+      "pluginVersion": "9.0.1",
+      "targets": [
+        {
+          "datasource": {
+            "type": "prometheus",
+            "uid": "P1809F7CD0C75ACF3"
+          },
+          "editorMode": "code",
+          "expr": "runtime_uptime",
+          "legendFormat": "{{job}}",
+          "range": true,
+          "refId": "A"
+        }
+      ],
+      "title": "Uptime",
+      "type": "stat"
+    },
     {
       "collapsed": false,
       "datasource": {
@@ -2515,9 +2577,9 @@
           },
           "editorMode": "code",
           "exemplar": true,
-          "expr": "process_runtime_go_mem_heap_inuse{job=\"validator\"}",
+          "expr": "process_runtime_go_mem_heap_inuse",
           "interval": "",
-          "legendFormat": "Heap in use",
+          "legendFormat": "{{job}}",
           "range": true,
           "refId": "A"
         }
@@ -2608,9 +2670,9 @@
           },
           "editorMode": "code",
           "exemplar": true,
-          "expr": "process_runtime_go_goroutines{job=\"validator\"}",
+          "expr": "process_runtime_go_goroutines",
           "interval": "",
-          "legendFormat": "goroutines",
+          "legendFormat": "{{job}}",
           "range": true,
           "refId": "A"
         }
@@ -2701,9 +2763,9 @@
           },
           "editorMode": "code",
           "exemplar": true,
-          "expr": "rate(process_runtime_go_gc_count{job=\"validator\"}[5m])",
+          "expr": "rate(process_runtime_go_gc_count[5m])",
           "interval": "",
-          "legendFormat": "gc/s",
+          "legendFormat": "{{job}}",
           "range": true,
           "refId": "A"
         }
@@ -2794,9 +2856,9 @@
           },
           "editorMode": "code",
           "exemplar": true,
-          "expr": "avg_over_time(process_runtime_go_mem_live_objects{job=\"validator\"}[5m])",
+          "expr": "avg_over_time(process_runtime_go_mem_live_objects[5m])",
           "interval": "",
-          "legendFormat": "objects",
+          "legendFormat": "{{job}}",
           "range": true,
           "refId": "A"
         }
@@ -2813,13 +2875,13 @@
     "list": []
   },
   "time": {
-    "from": "now-6h",
+    "from": "now-5m",
     "to": "now"
   },
   "timepicker": {},
   "timezone": "",
   "title": "Validator",
   "uid": "2Le7qt_7z",
-  "version": 13,
+  "version": 18,
   "weekStart": ""
 }

go.mod

@@ -12,10 +12,11 @@ require (
 	github.com/gorilla/mux v1.8.0
 	github.com/hetiansu5/urlquery v1.2.7
 	github.com/json-iterator/go v1.1.12
-	github.com/klauspost/compress v1.15.10
+	github.com/klauspost/compress v1.15.11
 	github.com/mattn/go-sqlite3 v1.14.15
 	github.com/omeid/uconfig v1.2.0
 	github.com/pkg/errors v0.9.1
+	github.com/prometheus/client_golang v1.13.0
 	github.com/rs/zerolog v1.28.0
 	github.com/sethvargo/go-limiter v0.7.2
 	github.com/spf13/cobra v1.5.0
@@ -24,11 +25,10 @@ require (
 	github.com/tablelandnetwork/sqlparser v0.0.0-20220923130758-1b39431a2fea
 	github.com/textileio/cli v1.0.2
 	go.opentelemetry.io/contrib/instrumentation/net/http/otelhttp v0.32.0
-	go.opentelemetry.io/contrib/instrumentation/runtime v0.36.0
 	go.opentelemetry.io/otel v1.10.0
-	go.opentelemetry.io/otel/exporters/prometheus v0.31.0
-	go.opentelemetry.io/otel/metric v0.32.0
-	go.opentelemetry.io/otel/sdk/metric v0.31.0
+	go.opentelemetry.io/otel/exporters/prometheus v0.32.2
+	go.opentelemetry.io/otel/metric v0.32.2
+	go.opentelemetry.io/otel/sdk/metric v0.32.2
 	go.uber.org/atomic v1.10.0
 	golang.org/x/sync v0.0.0-20220601150217-0de741cfad7f
 )
@@ -77,10 +77,9 @@ require (
 	github.com/olekukonko/tablewriter v0.0.5 // indirect
 	github.com/pelletier/go-toml v1.9.3 // indirect
 	github.com/pmezard/go-difflib v1.0.0 // indirect
-	github.com/prometheus/client_golang v1.12.2 // indirect
 	github.com/prometheus/client_model v0.2.0 // indirect
-	github.com/prometheus/common v0.32.1 // indirect
-	github.com/prometheus/procfs v0.7.3 // indirect
+	github.com/prometheus/common v0.37.0 // indirect
+	github.com/prometheus/procfs v0.8.0 // indirect
 	github.com/prometheus/tsdb v0.7.1 // indirect
 	github.com/relvacode/iso8601 v1.1.0 // indirect
 	github.com/rjeczalik/notify v0.9.1 // indirect
@@ -97,21 +96,21 @@ require (
 	github.com/tklauser/go-sysconf v0.3.5 // indirect
 	github.com/tklauser/numcpus v0.2.2 // indirect
 	go.opencensus.io v0.23.0 // indirect
-	go.opentelemetry.io/otel/sdk v1.9.0 // indirect
+	go.opentelemetry.io/otel/sdk v1.10.0 // indirect
 	go.opentelemetry.io/otel/trace v1.10.0 // indirect
 	go.uber.org/multierr v1.6.0 // indirect
 	go.uber.org/zap v1.19.0 // indirect
 	golang.org/x/crypto v0.0.0-20211215165025-cf75a172585e // indirect
 	golang.org/x/net v0.0.0-20220607020251-c690dde0001d // indirect
 	golang.org/x/oauth2 v0.0.0-20220608161450-d0670ef3b1eb // indirect
-	golang.org/x/sys v0.0.0-20220610221304-9f5ed59c137d // indirect
+	golang.org/x/sys v0.0.0-20220919091848-fb04ddd9f9c8 // indirect
 	golang.org/x/text v0.3.7 // indirect
 	golang.org/x/xerrors v0.0.0-20220609144429-65e65417b02f // indirect
 	google.golang.org/api v0.84.0 // indirect
 	google.golang.org/appengine v1.6.7 // indirect
 	google.golang.org/genproto v0.0.0-20220617124728-180714bec0ad // indirect
 	google.golang.org/grpc v1.47.0 // indirect
-	google.golang.org/protobuf v1.28.0 // indirect
+	google.golang.org/protobuf v1.28.1 // indirect
 	gopkg.in/ini.v1 v1.62.0 // indirect
 	gopkg.in/natefinch/npipe.v2 v2.0.0-20160621034901-c1b8fa8bdcce // indirect
 	gopkg.in/yaml.v2 v2.4.0 // indirect