From 56ff4c5cfdfc7fd84a10bd1d69418109e25c2560 Mon Sep 17 00:00:00 2001
From: Alex Auvolat <alex@adnab.me>
Date: Tue, 20 Sep 2022 17:13:46 +0200
Subject: Prod-like telemetry into staging

---
 .../deploy/telemetry-system.hcl                    | 182 +++++++++++++++++++++
 .../bad.telemetry-elastic/deploy/telemetry.hcl     | 181 ++++++++++++++++++++
 2 files changed, 363 insertions(+)
 create mode 100644 experimental/bad.telemetry-elastic/deploy/telemetry-system.hcl
 create mode 100644 experimental/bad.telemetry-elastic/deploy/telemetry.hcl

(limited to 'experimental/bad.telemetry-elastic/deploy')

diff --git a/experimental/bad.telemetry-elastic/deploy/telemetry-system.hcl b/experimental/bad.telemetry-elastic/deploy/telemetry-system.hcl
new file mode 100644
index 0000000..3e26c2e
--- /dev/null
+++ b/experimental/bad.telemetry-elastic/deploy/telemetry-system.hcl
@@ -0,0 +1,182 @@
+job "telemetry-system" {
+  datacenters = ["neptune"]
+  type = "system"
+
+  group "elasticsearch" {
+    network {
+      port "elastic" {
+        static = 9200
+      }
+      port "elastic_internal" {
+        static = 9300
+      }
+    }
+
+    task "elastic" {
+      driver = "docker"
+      config {
+        image = "docker.elastic.co/elasticsearch/elasticsearch:8.2.0"
+        network_mode = "host"
+        volumes = [
+          "/mnt/ssd/telemetry/es_data:/usr/share/elasticsearch/data",
+          "secrets/elastic-certificates.p12:/usr/share/elasticsearch/config/elastic-certificates.p12",
+        ]
+        ports = [ "elastic", "elastic_internal" ]
+        sysctl = {
+          #"vm.max_map_count" = "262144",
+        }
+        ulimit = {
+          memlock = "9223372036854775807:9223372036854775807", 
+        }
+      }
+
+      user = "1000"
+
+      resources {
+        memory = 1500
+        cpu = 500
+      }
+
+      template {
+        data = "{{ key \"secrets/telemetry/elasticsearch/elastic-certificates.p12\" }}"
+        destination = "secrets/elastic-certificates.p12"
+      }
+
+      template {
+        data = <<EOH
+node.name={{ env "attr.unique.hostname" }}
+http.port=9200
+transport.port=9300
+cluster.name=es-deuxfleurs
+cluster.initial_master_nodes=carcajou,caribou,cariacou
+discovery.seed_hosts=carcajou,caribou,cariacou
+bootstrap.memory_lock=true
+xpack.security.enabled=true
+xpack.security.authc.api_key.enabled=true
+xpack.security.transport.ssl.enabled=true
+xpack.security.transport.ssl.verification_mode=certificate
+xpack.security.transport.ssl.client_authentication=required
+xpack.security.transport.ssl.keystore.path=/usr/share/elasticsearch/config/elastic-certificates.p12
+xpack.security.transport.ssl.truststore.path=/usr/share/elasticsearch/config/elastic-certificates.p12
+cluster.routing.allocation.disk.watermark.high=75%
+cluster.routing.allocation.disk.watermark.low=65%
+ES_JAVA_OPTS=-Xms512M -Xmx512M
+EOH
+        destination = "secrets/env"
+        env = true
+      }
+    }
+  }
+
+  group "collector" {
+    network {
+      port "otel_grpc" {
+        static = 4317
+      }
+      port "apm" {
+        static = 8200
+      }
+      port "node_exporter" {
+        static = 9100
+      }
+    }
+
+    task "otel" {
+      driver = "docker"
+      config {
+        image = "otel/opentelemetry-collector-contrib:0.46.0"
+        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 = 100
+        cpu = 100
+      }
+    }
+
+    task "apm" {
+      driver = "docker"
+      config {
+        image = "docker.elastic.co/apm/apm-server:8.2.0"
+        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 = 100
+        cpu = 100
+      }
+    }
+
+/*
+    task "node_exporter" {
+      driver = "docker"
+      config {
+        image = "quay.io/prometheus/node-exporter:v1.1.2"
+        network_mode = "host"
+        ports = [ "node_exporter" ]
+        volumes = [
+          "/:/host:ro,rslave"
+        ]
+        args = [ "--path.rootfs=/host" ]
+      }
+
+      resources {
+        cpu = 50
+        memory = 40
+      }
+    }
+*/
+
+    task "filebeat" {
+      driver = "docker"
+      config {
+        image = "docker.elastic.co/beats/filebeat:8.2.0"
+        network_mode = "host"
+        volumes = [
+          "/mnt/ssd/telemetry/filebeat:/usr/share/filebeat/data",
+          "secrets/filebeat.yml:/usr/share/filebeat/filebeat.yml",
+          "/var/run/docker.sock:/var/run/docker.sock",
+          "/var/lib/docker/containers/:/var/lib/docker/containers/:ro",
+          "/var/log/:/var/log/:ro",
+        ]
+        args = [ "--strict.perms=false" ]
+        privileged = true
+      }
+      user = "root"
+
+
+      template {
+        data = file("../config/filebeat.yml")
+        destination = "secrets/filebeat.yml"
+      }
+
+      resources {
+        memory = 100
+        cpu = 100
+      }
+    }
+  }
+}
+  
diff --git a/experimental/bad.telemetry-elastic/deploy/telemetry.hcl b/experimental/bad.telemetry-elastic/deploy/telemetry.hcl
new file mode 100644
index 0000000..21685a1
--- /dev/null
+++ b/experimental/bad.telemetry-elastic/deploy/telemetry.hcl
@@ -0,0 +1,181 @@
+job "telemetry" {
+  datacenters = ["neptune"]
+  type = "service"
+
+  group "kibana" {
+    count = 1
+
+    network {
+      port "kibana" {
+        static = 5601
+      }
+    }
+
+    task "kibana" {
+      driver = "docker"
+      config {
+        image = "docker.elastic.co/kibana/kibana:8.2.0"
+        network_mode = "host"
+        ports = [ "kibana" ]
+      }
+
+      template {
+        data = <<EOH
+SERVER_NAME={{ env "attr.unique.hostname" }}
+ELASTICSEARCH_HOSTS=http://localhost:9200
+ELASTICSEARCH_USERNAME=kibana_system
+ELASTICSEARCH_PASSWORD={{ key "secrets/telemetry/elastic_passwords/kibana_system" }}
+SERVER_PUBLICBASEURL=https://kibana.home.adnab.me
+EOH
+        destination = "secrets/env"
+        env = true
+      }
+
+      resources {
+        memory = 1000
+        cpu = 500
+      }
+
+      service {
+        tags = [
+            "kibana",
+            "tricot kibana.staging.deuxfleurs.org",
+        ]
+        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
+
+    network {
+      port "grafana" {
+        static = 3333
+      }
+    }
+
+    task "restore-db" {
+      lifecycle {
+        hook = "prestart"
+        sidecar = false
+      }
+
+      driver = "docker"
+      config {
+        image = "litestream/litestream:0.3.7"
+        args = [
+          "restore", "-config", "/etc/litestream.yml", "/ephemeral/grafana.db"
+        ]
+        volumes = [
+          "../alloc/data:/ephemeral",
+          "secrets/litestream.yml:/etc/litestream.yml"
+        ]
+      }
+      user = "472"
+
+      template {
+        data = file("../config/grafana-litestream.yml")
+        destination = "secrets/litestream.yml"
+      }
+
+      resources {
+        memory = 200
+        cpu = 1000
+      }
+    }
+
+    task "grafana" {
+      driver = "docker"
+      config {
+        image = "grafana/grafana:8.4.3"
+        network_mode = "host"
+        ports = [ "grafana" ]
+        volumes = [
+          "../alloc/data:/var/lib/grafana",
+          "secrets/elastic.yaml:/etc/grafana/provisioning/datasources/elastic.yaml"
+        ]
+      }
+
+      template {
+        data = file("../config/grafana/provisioning/datasources/elastic.yaml")
+        destination = "secrets/elastic.yaml"
+      }
+
+      template {
+        data = <<EOH
+GF_INSTALL_PLUGINS=grafana-clock-panel,grafana-simple-json-datasource,grafana-piechart-panel,grafana-worldmap-panel,grafana-polystat-panel
+GF_SERVER_HTTP_PORT=3333
+EOH
+        destination = "secrets/env"
+        env = true
+      }
+
+      resources {
+        memory = 500
+        cpu = 100
+      }
+
+      service {
+        tags = [
+            "grafana",
+            "tricot grafana.staging.deuxfleurs.org",
+        ]
+        port = 3333
+        address_mode = "driver"
+        name = "grafana"
+        check {
+          type = "tcp"
+          port = 3333
+          address_mode = "driver"
+          interval = "60s"
+          timeout = "5s"
+          check_restart {
+            limit = 3
+            grace = "90s"
+            ignore_warnings = false
+          }
+        }
+      }
+    }
+
+    task "replicate-db" {
+      driver = "docker"
+      config {
+        image = "litestream/litestream:0.3.7"
+        args = [
+          "replicate", "-config", "/etc/litestream.yml"
+        ]
+        volumes = [
+          "../alloc/data:/ephemeral",
+          "secrets/litestream.yml:/etc/litestream.yml"
+        ]
+      }
+      user = "472"
+
+      template {
+        data = file("../config/grafana-litestream.yml")
+        destination = "secrets/litestream.yml"
+      }
+
+      resources {
+        memory = 200
+        cpu = 100
+      }
+    }
+  }
+}
-- 
cgit v1.2.3