Merge pull request #6 from Staffbase/add-prom-metrics

add metrics

go.mod

@@ -6,20 +6,29 @@ require (
 	github.com/alecthomas/kong v0.8.0
 	github.com/go-chi/chi/v5 v5.0.10
 	github.com/go-chi/render v1.0.3
+	github.com/prometheus/client_golang v1.16.0
 	github.com/stretchr/testify v1.8.1
 	go.uber.org/zap v1.24.0
 	gopkg.in/yaml.v2 v2.4.0
 )
 
 require (
 	github.com/ajg/form v1.5.1 // indirect
+	github.com/beorn7/perks v1.0.1 // indirect
+	github.com/cespare/xxhash/v2 v2.2.0 // indirect
 	github.com/davecgh/go-spew v1.1.1 // indirect
-	github.com/kr/pretty v0.3.0 // indirect
+	github.com/golang/protobuf v1.5.3 // indirect
+	github.com/kr/text v0.2.0 // indirect
+	github.com/matttproud/golang_protobuf_extensions v1.0.4 // indirect
 	github.com/pkg/errors v0.9.1 // indirect
 	github.com/pmezard/go-difflib v1.0.0 // indirect
+	github.com/prometheus/client_model v0.3.0 // indirect
+	github.com/prometheus/common v0.42.0 // indirect
+	github.com/prometheus/procfs v0.10.1 // indirect
 	github.com/rogpeppe/go-internal v1.10.0 // indirect
 	go.uber.org/atomic v1.11.0 // indirect
 	go.uber.org/multierr v1.11.0 // indirect
-	gopkg.in/check.v1 v1.0.0-20201130134442-10cb98267c6c // indirect
+	golang.org/x/sys v0.8.0 // indirect
+	google.golang.org/protobuf v1.30.0 // indirect
 	gopkg.in/yaml.v3 v3.0.1 // indirect
 )

go.sum

@@ -5,6 +5,10 @@ github.com/alecthomas/kong v0.8.0 h1:ryDCzutfIqJPnNn0omnrgHLbAggDQM2VWHikE1xqK7s
 github.com/alecthomas/kong v0.8.0/go.mod h1:n1iCIO2xS46oE8ZfYCNDqdR0b0wZNrXAIAqro/2132U=
 github.com/alecthomas/repr v0.1.0 h1:ENn2e1+J3k09gyj2shc0dHr/yjaWSHRlrJ4DPMevDqE=
 github.com/benbjohnson/clock v1.1.0 h1:Q92kusRqC1XV2MjkWETPvjJVqKetz1OzxZB7mHJLju8=
+github.com/beorn7/perks v1.0.1 h1:VlbKKnNfV8bJzeqoa4cOKqO6bYr3WgKZxO8Z16+hsOM=
+github.com/beorn7/perks v1.0.1/go.mod h1:G2ZrVWU2WbWT9wwq4/hrbKbnv/1ERSJQ0ibhJ6rlkpw=
+github.com/cespare/xxhash/v2 v2.2.0 h1:DC2CZ1Ep5Y4k3ZQ899DldepgrayRUGE6BBZ/cd9Cj44=
+github.com/cespare/xxhash/v2 v2.2.0/go.mod h1:VGX0DQ3Q6kWi7AoAeZDth3/j3BFtOZR5XLFGgcrjCOs=
 github.com/creack/pty v1.1.9/go.mod h1:oKZEueFk5CKHvIhNR5MUki03XCEU+Q6VDXinZuGJ33E=
 github.com/davecgh/go-spew v1.1.0/go.mod h1:J7Y8YcW2NihsgmVo/mv3lAwl/skON4iLHjSsI+c5H38=
 github.com/davecgh/go-spew v1.1.1 h1:vj9j/u1bqnvCEfJOwUhtlOARqs3+rkHYY13jYWTU97c=
@@ -13,20 +17,31 @@ github.com/go-chi/chi/v5 v5.0.10 h1:rLz5avzKpjqxrYwXNfmjkrYYXOyLJd37pz53UFHC6vk=
 github.com/go-chi/chi/v5 v5.0.10/go.mod h1:DslCQbL2OYiznFReuXYUmQ2hGd1aDpCnlMNITLSKoi8=
 github.com/go-chi/render v1.0.3 h1:AsXqd2a1/INaIfUSKq3G5uA8weYx20FOsM7uSoCyyt4=
 github.com/go-chi/render v1.0.3/go.mod h1:/gr3hVkmYR0YlEy3LxCuVRFzEu9Ruok+gFqbIofjao0=
+github.com/golang/protobuf v1.2.0/go.mod h1:6lQm79b+lXiMfvg/cZm0SGofjICqVBUtrP5yJMmIC1U=
+github.com/golang/protobuf v1.3.5/go.mod h1:6O5/vntMXwX2lRkT1hjjk0nAC1IDOTvTlVgjlRvqsdk=
+github.com/golang/protobuf v1.5.0/go.mod h1:FsONVRAS9T7sI+LIUmWTfcYkHO4aIWwzhcaSAoJOfIk=
+github.com/golang/protobuf v1.5.3 h1:KhyjKVUg7Usr/dYsdSqoFveMYd5ko72D+zANwlG1mmg=
+github.com/golang/protobuf v1.5.3/go.mod h1:XVQd3VNwM+JqD3oG2Ue2ip4fOMUkwXdXDdiuN0vRsmY=
+github.com/google/go-cmp v0.5.5/go.mod h1:v8dTdLbMG2kIc/vJvl+f65V22dbkXbowE6jgT/gNBxE=
+github.com/google/go-cmp v0.5.9 h1:O2Tfq5qg4qc4AmwVlvv0oLiVAGB7enBSJ2x2DqQFi38=
 github.com/hexops/gotextdiff v1.0.3 h1:gitA9+qJrrTCsiCl7+kh75nPqQt1cx4ZkudSTLoUqJM=
-github.com/kr/pretty v0.1.0/go.mod h1:dAy3ld7l9f0ibDNOQOHHMYYIIbhfbHSm3C4ZsoJORNo=
-github.com/kr/pretty v0.2.1/go.mod h1:ipq/a2n7PKx3OHsz4KJII5eveXtPO4qwEXGdVfWzfnI=
-github.com/kr/pretty v0.3.0 h1:WgNl7dwNpEZ6jJ9k1snq4pZsg7DOEN8hP9Xw0Tsjwk0=
-github.com/kr/pretty v0.3.0/go.mod h1:640gp4NfQd8pI5XOwp5fnNeVWj67G7CFk/SaSQn7NBk=
-github.com/kr/pty v1.1.1/go.mod h1:pFQYn66WHrOpPYNljwOMqo10TkYh1fy3cYio2l3bCsQ=
-github.com/kr/text v0.1.0/go.mod h1:4Jbv+DJW3UT/LiOwJeYQe1efqtUx/iVham/4vfdArNI=
+github.com/kr/pretty v0.3.1 h1:flRD4NNwYAUpkphVc1HcthR4KEIFJ65n8Mw5qdRn3LE=
 github.com/kr/text v0.2.0 h1:5Nx0Ya0ZqY2ygV366QzturHI13Jq95ApcVaJBhpS+AY=
 github.com/kr/text v0.2.0/go.mod h1:eLer722TekiGuMkidMxC/pM04lWEeraHUUmBw8l2grE=
+github.com/matttproud/golang_protobuf_extensions v1.0.4 h1:mmDVorXM7PCGKw94cs5zkfA9PSy5pEvNWRP0ET0TIVo=
+github.com/matttproud/golang_protobuf_extensions v1.0.4/go.mod h1:BSXmuO+STAnVfrANrmjBb36TMTDstsz7MSK+HVaYKv4=
 github.com/pkg/errors v0.9.1 h1:FEBLx1zS214owpjy7qsBeixbURkuhQAwrK5UwLGTwt4=
 github.com/pkg/errors v0.9.1/go.mod h1:bwawxfHBFNV+L2hUp1rHADufV3IMtnDRdf1r5NINEl0=
 github.com/pmezard/go-difflib v1.0.0 h1:4DBwDE0NGyQoBHbLQYPwSUPoCMWR5BEzIk/f1lZbAQM=
 github.com/pmezard/go-difflib v1.0.0/go.mod h1:iKH77koFhYxTK1pcRnkKkqfTogsbg7gZNVY4sRDYZ/4=
-github.com/rogpeppe/go-internal v1.6.1/go.mod h1:xXDCJY+GAPziupqXw64V24skbSoqbTEfhy4qGm1nDQc=
+github.com/prometheus/client_golang v1.16.0 h1:yk/hx9hDbrGHovbci4BY+pRMfSuuat626eFsHb7tmT8=
+github.com/prometheus/client_golang v1.16.0/go.mod h1:Zsulrv/L9oM40tJ7T815tM89lFEugiJ9HzIqaAx4LKc=
+github.com/prometheus/client_model v0.3.0 h1:UBgGFHqYdG/TPFD1B1ogZywDqEkwp3fBMvqdiQ7Xew4=
+github.com/prometheus/client_model v0.3.0/go.mod h1:LDGWKZIo7rky3hgvBe+caln+Dr3dPggB5dvjtD7w9+w=
+github.com/prometheus/common v0.42.0 h1:EKsfXEYo4JpWMHH5cg+KOUWeuJSov1Id8zGR8eeI1YM=
+github.com/prometheus/common v0.42.0/go.mod h1:xBwqVerjNdUDjgODMpudtOMwlOwf2SaTr1yjz4b7Zbc=
+github.com/prometheus/procfs v0.10.1 h1:kYK1Va/YMlutzCGazswoHKo//tZVlFpKYh+PymziUAg=
+github.com/prometheus/procfs v0.10.1/go.mod h1:nwNm2aOCAYw8uTR/9bWRREkZFxAUcWzPHWJq+XBB/FM=
 github.com/rogpeppe/go-internal v1.10.0 h1:TMyTOH3F/DB16zRVcYyreMH6GnZZrwQVAoYjRBZyWFQ=
 github.com/rogpeppe/go-internal v1.10.0/go.mod h1:UQnix2H7Ngw/k4C5ijL5+65zddjncjaFoBhdsK/akog=
 github.com/stretchr/objx v0.1.0/go.mod h1:HFkY916IF+rwdDfMAkV7OtwuqBVzrE8GR6GFx+wExME=
@@ -43,11 +58,16 @@ go.uber.org/multierr v1.11.0 h1:blXXJkSxSSfBVBlC76pxqeO+LN3aDfLQo+309xJstO0=
 go.uber.org/multierr v1.11.0/go.mod h1:20+QtiLqy0Nd6FdQB9TLXag12DsQkrbs3htMFfDN80Y=
 go.uber.org/zap v1.24.0 h1:FiJd5l1UOLj0wCgbSE0rwwXHzEdAZS6hiiSnxJN/D60=
 go.uber.org/zap v1.24.0/go.mod h1:2kMP+WWQ8aoFoedH3T2sq6iJ2yDWpHbP0f6MQbS9Gkg=
+golang.org/x/sync v0.0.0-20181221193216-37e7f081c4d4/go.mod h1:RxMgew5VJxzue5/jJTE5uejpjVlOe/izrB70Jof72aM=
+golang.org/x/sys v0.8.0 h1:EBmGv8NaZBZTWvrbjNoL6HVt+IVy3QDQpJs7VRIw3tU=
+golang.org/x/sys v0.8.0/go.mod h1:oPkhp1MJrh7nUepCBck5+mAzfO9JrbApNNgaTdGDITg=
+golang.org/x/xerrors v0.0.0-20191204190536-9bdfabe68543/go.mod h1:I/5z698sn9Ka8TeJc9MKroUUfqBBauWjQqLJ2OPfmY0=
+google.golang.org/protobuf v1.26.0-rc.1/go.mod h1:jlhhOSvTdKEhbULTjvd4ARK9grFBp09yW+WbY/TyQbw=
+google.golang.org/protobuf v1.26.0/go.mod h1:9q0QmTI4eRPtz6boOQmLYwt+qCgq0jsYwAQnmE0givc=
+google.golang.org/protobuf v1.30.0 h1:kPPoIgf3TsEvrm0PFe15JQ+570QVxYzEvvHqChK+cng=
+google.golang.org/protobuf v1.30.0/go.mod h1:HV8QOd/L58Z+nl8r43ehVNZIU/HEI6OcFqwMG9pJV4I=
 gopkg.in/check.v1 v0.0.0-20161208181325-20d25e280405/go.mod h1:Co6ibVJAznAaIkqp8huTwlJQCZ016jof/cbN4VW5Yz0=
-gopkg.in/check.v1 v1.0.0-20180628173108-788fd7840127/go.mod h1:Co6ibVJAznAaIkqp8huTwlJQCZ016jof/cbN4VW5Yz0=
 gopkg.in/check.v1 v1.0.0-20201130134442-10cb98267c6c h1:Hei/4ADfdWqJk1ZMxUNpqntNwaWcugrBjAiHlqqRiVk=
-gopkg.in/check.v1 v1.0.0-20201130134442-10cb98267c6c/go.mod h1:JHkPIbrfpd72SG/EVd6muEfDQjcINNoR0C8j2r3qZ4Q=
-gopkg.in/errgo.v2 v2.1.0/go.mod h1:hNsd1EY+bozCKY1Ytp96fpM3vjJbqLJn88ws8XvfDNI=
 gopkg.in/yaml.v2 v2.4.0 h1:D8xgwECY7CYvx+Y2n4sBz93Jn9JRvxdiyyo8CTfuKaY=
 gopkg.in/yaml.v2 v2.4.0/go.mod h1:RDklbk79AGWmwhnvt/jBztapEOGDOx6ZbXqjP6csGnQ=
 gopkg.in/yaml.v3 v3.0.0-20200313102051-9f266ea9e77c/go.mod h1:K4uyk7z7BCEPqu6E+C64Yfv1cQ7kz7rIZviUmN+EgEM=

main.go

@@ -22,6 +22,7 @@ import (
 	"github.com/Staffbase/spark-submit/pkg/spark"
 	"github.com/alecthomas/kong"
 	"github.com/go-chi/chi/v5"
+	"github.com/prometheus/client_golang/prometheus/promhttp"
 	"go.uber.org/zap"
 	"go.uber.org/zap/zapcore"
 )
@@ -52,6 +53,7 @@ func (cmd *mainCmd) Run() {
 	}
 	r := chi.NewRouter()
 	r.Get("/health", handlers.HandleHealth)
+	r.Handle("/metrics", promhttp.Handler())
 	r.Post("/", handlers.HandleSubmit(s))
 	r.Get("/", handlers.HandleStatus(s))
 	r.Delete("/", handlers.HandleKill(s))

pkg/spark/spark.go

@@ -23,6 +23,8 @@ import (
 	"strings"
 	"time"
 
+	"github.com/prometheus/client_golang/prometheus"
+	"github.com/prometheus/client_golang/prometheus/promauto"
 	"go.uber.org/zap"
 	"go.uber.org/zap/zapio"
 	"gopkg.in/yaml.v2"
@@ -118,14 +120,43 @@ func (s *Spark) submitArgs(presetName string) ([]string, error) {
 	return args, nil
 }
 
+var submitCounter = promauto.NewCounterVec(prometheus.CounterOpts{
+	Name: "spark_exec_total",
+	Help: "The total number of spark-submit runs",
+}, []string{"preset", "status"})
+
+var retryCounter = promauto.NewCounterVec(prometheus.CounterOpts{
+	Name: "retry_total",
+	Help: "The total number of retries",
+}, []string{"preset"})
+
 func (s *Spark) Submit(presetName string) error {
 	args, err := s.submitArgs(presetName)
 	if err != nil {
 		return fmt.Errorf("couldn't build submit args, %w", err)
 	}
 
 	zap.L().Info("submit with args", zap.Any("args", args))
-	go s.exec(args)
+	cmd := exec.Command(s.binaryPath, args...)
+	zap.L().Info("spark-submit", zap.Strings("args", args))
+	if s.debug {
+		writer := &zapio.Writer{Log: zap.L(), Level: zap.DebugLevel}
+		cmd.Stderr = writer
+		cmd.Stdout = writer
+		defer writer.Close()
+	}
+
+	go func() {
+		if err := retry(10, 1*time.Second, 2, 5*time.Minute, func() error {
+			retryCounter.WithLabelValues(presetName).Inc()
+			return cmd.Run()
+		}); err != nil {
+			zap.L().Error("spark submit failed with retries", zap.Error(err))
+			submitCounter.WithLabelValues(presetName, "failure").Inc()
+		}
+		submitCounter.WithLabelValues(presetName, "success").Inc()
+	}()
+
 	return nil
 }
 
@@ -137,7 +168,19 @@ func (s *Spark) buildArgs(kind string, namespace, name string) []string {
 }
 
 func (s *Spark) Kill(namespace, name string) {
-	s.exec(s.buildArgs("kill", namespace, name))
+	args := s.buildArgs("kill", namespace, name)
+	cmd := exec.Command(s.binaryPath, args...)
+	zap.L().Info("spark-submit", zap.Strings("args", args))
+	if s.debug {
+		writer := &zapio.Writer{Log: zap.L(), Level: zap.DebugLevel}
+		cmd.Stderr = writer
+		cmd.Stdout = writer
+		defer writer.Close()
+	}
+
+	if err := cmd.Run(); err != nil {
+		zap.L().Error("killing spark app failed", zap.Error(err))
+	}
 }
 
 func (s *Spark) Status(namespace, name string) string {
@@ -154,23 +197,6 @@ func (s *Spark) Status(namespace, name string) string {
 	return buffer.String()
 }
 
-func (s *Spark) exec(args []string) {
-	cmd := exec.Command(s.binaryPath, args...)
-	zap.L().Info("spark-submit", zap.Strings("args", args))
-	if s.debug {
-		writer := &zapio.Writer{Log: zap.L(), Level: zap.DebugLevel}
-		cmd.Stderr = writer
-		cmd.Stdout = writer
-		defer writer.Close()
-	}
-
-	if err := retry(10, 1*time.Second, 2, 5*time.Minute, func() error {
-		return cmd.Run()
-	}); err != nil {
-		zap.L().Error("spark submit failed with retries", zap.Error(err))
-	}
-}
-
 func retry(retries int, initialDelay time.Duration, mult int, maxWait time.Duration, fn func() error) error {
 	delay := initialDelay
 	for try := 0; try < retries; try++ {