Scrape meterics from system process on each node

4 files changed, 118 insertions, 62 deletions

diff --git a/app/telemetry/config/otel-config.yaml b/app/telemetry/config/otel-config.yaml
index e1d6d78..574d01c 100644
--- a/app/telemetry/config/otel-config.yaml
+++ b/app/telemetry/config/otel-config.yaml
@@ -14,9 +14,7 @@ receivers:
           scrape_interval: 5s
           static_configs:
             - targets:
-              - "10.42.2.21:3909"
-              - "10.42.2.22:3909"
-              - "10.42.2.23:3909"
+              - "localhost:3909"
 
 exporters:
   logging:
diff --git a/app/telemetry/deploy/telemetry-system.hcl b/app/telemetry/deploy/telemetry-system.hcl
index 9dd379d..af9acff 100644
--- a/app/telemetry/deploy/telemetry-system.hcl
+++ b/app/telemetry/deploy/telemetry-system.hcl
@@ -57,5 +57,64 @@ EOH
       }
     }
   }
+
+  group "collector" {
+    network {
+      port "otel_grpc" {
+        static = 4317
+      }
+      port "apm" {
+        static = 8200
+      }
+    }
+
+    task "otel" {
+      driver = "docker"
+      config {
+        image = "otel/opentelemetry-collector-contrib:0.44.0"
+        args = [
+          "--config=/etc/otel-config.yaml",
+        ]
+        network_mode = "host"
+        ports= [ "otel_grpc" ]
+        volumes = [
+          "secrets/otel-config.yaml:/etc/otel-config.yaml"
+        ]
+      }
+
+      template {
+        data = file("../config/otel-config.yaml")
+        destination = "secrets/otel-config.yaml"
+      }
+
+      resources {
+        memory = 200
+        cpu = 100
+      }
+    }
+
+    task "apm" {
+      driver = "docker"
+      config {
+        image = "docker.elastic.co/apm/apm-server:7.17.0"
+        network_mode = "host"
+        ports = [ "apm" ]
+        args = [ "--strict.perms=false" ]
+        volumes = [
+          "secrets/apm-config.yaml:/usr/share/apm-server/apm-server.yml:ro"
+        ]
+      }
+
+      template {
+        data = file("../config/apm-config.yaml")
+        destination = "secrets/apm-config.yaml"
+      }
+
+      resources {
+        memory = 200
+        cpu = 100
+      }
+    }
+  }
 }
   
diff --git a/app/telemetry/deploy/telemetry.hcl b/app/telemetry/deploy/telemetry.hcl
index 90cde54..c3edd4c 100644
--- a/app/telemetry/deploy/telemetry.hcl
+++ b/app/telemetry/deploy/telemetry.hcl
@@ -1,54 +1,14 @@
 job "telemetry" {
   datacenters = ["neptune"]
   type = "service"
-  
-  group "grafana" {
-    count = 1
 
-    constraint {
-      attribute = "${attr.unique.hostname}"
-      operator = "="
-      value = "carcajou"
-    }
+  group "kibana" {
+    count = 1
 
     network {
-      port "otel_grpc" {
-        static = 4317
-      }
       port "kibana" {
         static = 5601
       }
-      port "apm" {
-        static = 8200
-      }
-      port "grafana" {
-        static = 3333
-      }
-    }
-
-    task "otel" {
-      driver = "docker"
-      config {
-        image = "otel/opentelemetry-collector-contrib:0.44.0"
-        args = [
-          "--config=/etc/otel-config.yaml",
-        ]
-        network_mode = "host"
-        ports= [ "otel_grpc" ]
-        volumes = [
-          "secrets/otel-config.yaml:/etc/otel-config.yaml"
-        ]
-      }
-
-      template {
-        data = file("../config/otel-config.yaml")
-        destination = "secrets/otel-config.yaml"
-      }
-
-      resources {
-        memory = 200
-        cpu = 100
-      }
     }
 
     task "kibana" {
@@ -74,28 +34,43 @@ EOH
         memory = 1500
         cpu = 500
       }
-    }
 
-    task "apm" {
-      driver = "docker"
-      config {
-        image = "docker.elastic.co/apm/apm-server:7.17.0"
-        network_mode = "host"
-        ports = [ "apm" ]
-        args = [ "--strict.perms=false" ]
-        volumes = [
-          "secrets/apm-config.yaml:/usr/share/apm-server/apm-server.yml:ro"
+      service {
+        tags = [
+            "kibana",
+            "tricot kibana.home.adnab.me",
         ]
+        port = 5601
+        address_mode = "driver"
+        name = "kibana"
+        check {
+          type = "tcp"
+          port = 5601
+          address_mode = "driver"
+          interval = "60s"
+          timeout = "5s"
+          check_restart {
+            limit = 3
+            grace = "90s"
+            ignore_warnings = false
+          }
+        }
       }
+    }
+  }
+  
+  group "grafana" {
+    count = 1
 
-      template {
-        data = file("../config/apm-config.yaml")
-        destination = "secrets/apm-config.yaml"
-      }
+    constraint {
+      attribute = "${attr.unique.hostname}"
+      operator = "="
+      value = "carcajou"
+    }
 
-      resources {
-        memory = 200
-        cpu = 100
+    network {
+      port "grafana" {
+        static = 3333
       }
     }
 
diff --git a/doc/telemetry.md b/doc/telemetry.md
index ee8d0dd..1e405a5 100644
--- a/doc/telemetry.md
+++ b/doc/telemetry.md
@@ -1,3 +1,27 @@
+# create elasticsearch folders on all nodes
+
+```bash
+mkdir -p /mnt/ssd/telemetry/es_data/nodes
+chown 1000 /mnt/ssd/telemetry/es_data/nodes
+```
+
+# generate ca and tls certs for elasticsearch cluster
+
+start a `bash` in an elasticsearch image, such as `docker.elastic.co/elasticsearch/elasticsearch:7.17.0`: `docker run -ti docker.elastic.co/elasticsearch/elasticsearch:7.17.0 bash`
+
+generate a ca and node certs:
+
+```bash
+./bin/elasticsearch-certutil ca
+./bin/elasticsearch-certutil cert --ca elastic-stack-ca.p12
+```
+
+copy `elastic-certificates.p12` to `/mnt/ssd/telemetry/es_data` in all nodes, and chown it:
+
+```bash
+chown 1000 /mnt/ssd/telemetry/es_data/elastic-certificates.p12
+```
+
 # create elasticsearch passwords
 
 in elasticsearch container