Configure procs retries (on failure)

.travis.yml

@@ -2,7 +2,7 @@ dist: trusty
 sudo: required
 language: go
 go:
-- "1.8"
+- "1.10"
 
 env:
   global:
@@ -14,6 +14,7 @@ env:
     - PROCTOR_REDIS_ADDRESS="localhost:6379"
     - PROCTOR_REDIS_MAX_ACTIVE_CONNECTIONS="10"
     - PROCTOR_KUBE_JOB_ACTIVE_DEADLINE_SECONDS="60"
+    - PROCTOR_KUBE_JOB_RETRIES="0"
     - PROCTOR_LOGS_STREAM_READ_BUFFER_SIZE="140"
     - PROCTOR_LOGS_STREAM_WRITE_BUFFER_SIZE="4096"
     - PROCTOR_KUBE_CLUSTER_HOST_NAME="localhost:8001"

CHANGELOG.md

@@ -1,5 +1,16 @@
-## Changelog
+# Changelog
+All notable changes to this project will be documented in this file.
 
-### v0.1.0
+## [WIP: v0.2.0] - 2018-10-10
+### Added
+  - Configurable kubernetes job retries (on failure)
+### Modified
+  - Changelog format
+  - CI golang version. Reason: [kubernetes client-go issue](https://github.com/kubernetes/client-go/issues/449)
+
+## v0.1.0 - 2018-10-08
+### Added
   - Add Authentication Headers: Email-Id and Access-Token
   - Add Job success and failure metrics
+
+[WIP: v0.2.0]: https://github.com/gojektech/proctor/compare/v0.1.0...v0.2.0

proctord/.env.test

@@ -5,6 +5,7 @@ export PROCTOR_DEFAULT_NAMESPACE="default"
 export PROCTOR_REDIS_ADDRESS="localhost:6379"
 export PROCTOR_REDIS_MAX_ACTIVE_CONNECTIONS="10"
 export PROCTOR_KUBE_JOB_ACTIVE_DEADLINE_SECONDS="60"
+export PROCTOR_KUBE_JOB_RETRIES="0"
 export PROCTOR_LOGS_STREAM_READ_BUFFER_SIZE="140"
 export PROCTOR_LOGS_STREAM_WRITE_BUFFER_SIZE="4096"
 export PROCTOR_KUBE_CLUSTER_HOST_NAME="localhost:8001"

proctord/README.md

@@ -47,6 +47,7 @@
   * If unset, service will execute jobs in the same kubernetes cluster where it is run
   * When set to "out-of-cluster", service will fetch kube config based on current-context from `.kube/config` file in home directory
 * If a job doesn't reach completion, it is terminated after `PROCTOR_KUBE_JOB_ACTIVE_DEADLINE_SECONDS`
+* `PROCTOR_KUBE_JOB_RETRIES` is the number of retries for a kubernetes job (on failure)
 * `PROCTOR_DEFAULT_NAMESPACE` is the namespace under which jobs will be run in kubernetes cluster. By default, K8s has namespace "default". If you set another value, please create namespace in K8s before deploying `proctord`
 * `PROCTOR_KUBE_CLUSTER_HOST_NAME` is address/ip address to api-server of kube cluster. It is used for fetching logs of a pod using https
 * `PROCTOR_KUBE_CA_CERT_ENCODED` is the CA cert file encoded in base64. This is used for establishing authority while talking to kubernetes api-server on a public https call

proctord/config/config.go

@@ -56,8 +56,13 @@ func KubePodsListWaitTime() int {
 }
 
 func KubeJobActiveDeadlineSeconds() *int64 {
-	tmp := viper.GetInt64("KUBE_JOB_ACTIVE_DEADLINE_SECONDS")
-	return &tmp
+	kubeJobActiveDeadlineSeconds := viper.GetInt64("KUBE_JOB_ACTIVE_DEADLINE_SECONDS")
+	return &kubeJobActiveDeadlineSeconds
+}
+
+func KubeJobRetries() *int32 {
+	kubeJobRetries := int32(viper.GetInt("KUBE_JOB_RETRIES"))
+	return &kubeJobRetries
 }
 
 func PostgresUser() string {

proctord/config/config_test.go

@@ -105,6 +105,15 @@ func TestKubeJobActiveDeadlineSeconds(t *testing.T) {
 	assert.Equal(t, &expectedValue, KubeJobActiveDeadlineSeconds())
 }
 
+func TestKubeJobRetries(t *testing.T) {
+	os.Setenv("PROCTOR_KUBE_JOB_RETRIES", "0")
+
+	viper.AutomaticEnv()
+
+	expectedValue := int32(0)
+	assert.Equal(t, &expectedValue, KubeJobRetries())
+}
+
 func TestPostgresUser(t *testing.T) {
 	os.Setenv("PROCTOR_POSTGRES_USER", "postgres")