Master to Prod

.ebextensions/003_add_grafana_repo.config

@@ -1,15 +1,38 @@
 commands:
-  01_add_grafana_repo:
+  01_download_alloy:
     command: |
-      sudo wget -q -O /tmp/grafana.key https://rpm.grafana.com/gpg.key
-      sudo rpm --import /tmp/grafana.key
-      echo -e '[grafana]\nname=grafana\nbaseurl=https://rpm.grafana.com\nrepo_gpgcheck=1\nenabled=1\ngpgcheck=1\ngpgkey=https://rpm.grafana.com/gpg.key\nsslverify=1\nsslcacert=/etc/pki/tls/certs/ca-bundle.crt' | sudo tee /etc/yum.repos.d/grafana.repo
+      echo "[INFO] Downloading Grafana Alloy v1.12.2..."
+      ALLOY_VERSION="1.12.2"
+      RPM_FILE="alloy-${ALLOY_VERSION}-1.amd64.rpm"
+      DOWNLOAD_URL="https://github.com/grafana/alloy/releases/download/v${ALLOY_VERSION}/${RPM_FILE}"
+
+      curl -L -o /tmp/alloy.rpm "$DOWNLOAD_URL"
+
+      if [ ! -s /tmp/alloy.rpm ]; then
+          echo "[ERROR] Alloy RPM download failed."
+          exit 1
+      fi
 
   02_install_alloy:
-    command: sudo yum install -y alloy
+    command: |
+      echo "[INFO] Installing Alloy..."
+      sudo rpm -Uvh /tmp/alloy.rpm || true
+
+  03_prepare_directories:
+    command: |
+      echo "[INFO] Creating Alloy directories..."
+      sudo mkdir -p /etc/alloy
+      sudo mkdir -p /etc/systemd/system/alloy.service.d
+
+  04_set_root_user:
+    command: |
+      echo "[INFO] Setting Alloy to run as root..."
+      echo "[Service]" | sudo tee /etc/systemd/system/alloy.service.d/override.conf
+      echo "User=root" | sudo tee -a /etc/systemd/system/alloy.service.d/override.conf
+      echo "Group=root" | sudo tee -a /etc/systemd/system/alloy.service.d/override.conf
 
-  03_install_unzip:
-    command: sudo yum install -y unzip
+  05_reload_systemd:
+    command: |
+      echo "[INFO] Reloading systemd..."
+      sudo systemctl daemon-reload
 
-  09_restart_alloy:
-    command: sudo systemctl restart alloy

.ebextensions/005_memory_optimization.config

@@ -0,0 +1,52 @@
+commands:
+  01_configure_vm_settings:
+    command: |
+      cat > /etc/sysctl.d/99-pdf-memory-optimization.conf << 'EOF'
+      # Limit page cache to approximately 100MB to maximize memory for PDF generation
+      # vm.vfs_cache_pressure controls the tendency to reclaim memory used for caching
+      # Default is 100. Higher values (200) = more aggressive cache reclamation
+      vm.vfs_cache_pressure = 200
+
+      # vm.min_free_kbytes ensures kernel keeps minimum free memory
+      # Set to ~50MB (51200 KB) to ensure some buffer
+      vm.min_free_kbytes = 51200
+
+      # vm.swappiness controls swap usage tendency
+      # Lower value (10) = prefer using RAM over swap
+      # This keeps PDF generation in RAM for better performance
+      vm.swappiness = 10
+
+      # vm.dirty_ratio limits percentage of RAM for dirty pages (pending disk writes)
+      # Set to 10% to prevent excessive buffering
+      vm.dirty_ratio = 10
+
+      # vm.dirty_background_ratio starts background writes earlier
+      # Set to 5% to flush cache to disk sooner
+      vm.dirty_background_ratio = 5
+
+      # vm.overcommit_memory controls memory allocation strategy
+      # 1 = Always allow overcommit (useful for Chrome which requests more than it uses)
+      vm.overcommit_memory = 1
+
+      # vm.overcommit_ratio percentage of RAM that can be overcommitted
+      # 80% allows some overcommit while preventing extreme cases
+      vm.overcommit_ratio = 80
+      EOF
+
+      # Apply the settings immediately
+      sysctl -p /etc/sysctl.d/99-pdf-memory-optimization.conf
+    ignoreErrors: false
+
+  02_configure_transparent_hugepages:
+    command: |
+      # Disable transparent huge pages for better memory predictability
+      echo never > /sys/kernel/mm/transparent_hugepage/enabled
+      echo never > /sys/kernel/mm/transparent_hugepage/defrag
+    ignoreErrors: true
+
+  03_drop_caches_on_startup:
+    command: |
+      # Clear existing caches on deployment to start fresh
+      sync
+      echo 3 > /proc/sys/vm/drop_caches
+    ignoreErrors: true

.ebextensions/swap.config

@@ -0,0 +1,14 @@
+commands:
+  01_create_swap:
+    command: |
+      if [ ! -f /swapfile ]; then
+        fallocate -l 4G /swapfile || dd if=/dev/zero of=/swapfile bs=1M count=4096
+        chmod 600 /swapfile
+        mkswap /swapfile
+        swapon /swapfile
+        echo '/swapfile none swap sw 0 0' >> /etc/fstab
+      fi
+  02_set_swappiness:
+    command: |
+      sysctl vm.swappiness=10
+      echo 'vm.swappiness=10' >> /etc/sysctl.conf

.platform/hooks/postdeploy/grafana-setup.sh

@@ -1,138 +1,170 @@
 #!/bin/bash
+
 set -e
 
-GRAFANA_APP_ENV=$(/opt/elasticbeanstalk/bin/get-config environment -k ENVIRONMENT)
-SERVER_REGION=$(/opt/elasticbeanstalk/bin/get-config environment -k SERVER_REGION)
 ALLOY_CONF_DIR="/etc/alloy"
+sudo mkdir -p "${ALLOY_CONF_DIR}"
+
+# ========= Load Environment Variables from EB =========
+GRAFANA_APP_ENV=$(/opt/elasticbeanstalk/bin/get-config environment -k ENVIRONMENT 2>/dev/null || true)
+SERVER_REGION=$(/opt/elasticbeanstalk/bin/get-config environment -k SERVER_REGION 2>/dev/null || true)
 
-# write endpoints.json (GRAFANA_APP_ENV will be expanded)
-sudo tee ${ALLOY_CONF_DIR}/endpoints.json > /dev/null <<EOF
+# Fallback
+GRAFANA_APP_ENV="${GRAFANA_APP_ENV:-TEST}"
+SERVER_REGION="${SERVER_REGION:-IN}"
+
+# ============= Create endpoints.json =============
+sudo tee "${ALLOY_CONF_DIR}/endpoints.json" > /dev/null <<EOF
 {
-      "environment": "${GRAFANA_APP_ENV}",
-      "server_region": "${SERVER_REGION}",
-      "company": "Walkover",
-      "product": "Giddh",
-      "service_name": "giddh-template",
-      "orgId": "14",
-      "logs": {
-        "url": "http://loghub.msg91.com:3100/loki/api/v1/push"
-      },
-      "metrics": {
-        "url": "http://loghub.msg91.com:9009/api/v1/push"
-      },
-      "tempo": {
-        "url": "http://loghub.msg91.com:4317"
-      },
-      "pyroscope": {
-         "url": "http://loghub.msg91.com:4040"
-       }
+  "environment": "${GRAFANA_APP_ENV}",
+  "server_region": "${SERVER_REGION}",
+  "company": "Walkover",
+  "product": "Giddh",
+  "service_name": "giddh-template",
+  "orgId": "14",
+  "logs": {
+    "url": "http://loghub.msg91.com:3100/loki/api/v1/push"
+  },
+  "metrics": {
+    "url": "http://loghub.msg91.com:9009/api/v1/push"
+  },
+  "tempo": {
+    "url": "http://loghub.msg91.com:4317"
+  },
+  "pyroscope": {
+    "url": "http://loghub.msg91.com:4040"
+  }
 }
 EOF
 
-sudo tee ${ALLOY_CONF_DIR}/config.alloy > /dev/null <<'EOF'
+# ============= Create config.alloy =============
+sudo tee "${ALLOY_CONF_DIR}/config.alloy" > /dev/null <<'EOF'
 local.file "endpoints" {
-      filename = "/etc/alloy/endpoints.json"
+  filename = "/etc/alloy/endpoints.json"
 }
 
-// loki config for logs
 local.file_match "logs" {
-      path_targets = [
-          {
-            "job"       = "nginx",
-            "namespace" = "/var/log/nginx",
-            "__path__"  = "/var/log/nginx/*.log",
-          },
-          {
-            "job"       = "application",
-            "namespace" = "/var/log/template-logs",
-            "__path__"  = "/var/log/template-logs/*.log",
-          },
-      ]
-      ignore_older_than = "24h"
-      sync_period       = "10s"
+  path_targets = [
+    {
+      job       = "nginx",
+      namespace = "/var/log/nginx",
+      __path__  = "/var/log/nginx/*.log",
+    },
+    {
+      job       = "application",
+      namespace = "/var/log/template-logs",
+      __path__  = "/var/log/template-logs/*.log",
+    },
+  ]
+  sync_period       = "10s"
 }
 
 loki.source.file "log_source_file" {
-      targets       = local.file_match.logs.targets
-      forward_to    = [loki.process.log_process.receiver]
-      tail_from_end = true
+  targets       = local.file_match.logs.targets
+  forward_to    = [loki.process.log_process.receiver]
+  tail_from_end = true
 }
 
 loki.process "log_process" {
-      forward_to = [loki.write.log_write.receiver]
-      stage.decolorize {}
-      stage.static_labels {
-          values = {
-            env           = json_path(local.file.endpoints.content, ".environment")[0],
-            server_region = json_path(local.file.endpoints.content, ".server_region")[0],
-            company       = json_path(local.file.endpoints.content, ".company")[0],
-            product       = json_path(local.file.endpoints.content, ".product")[0],
-            service_name  = json_path(local.file.endpoints.content, ".service_name")[0],
-            instance      = constants.hostname,
-          }
-      }
+  forward_to = [loki.write.log_write.receiver]
+
+  stage.decolorize {}
+
+  stage.static_labels {
+    values = {
+      env           = json_path(local.file.endpoints.content, ".environment")[0],
+      server_region = json_path(local.file.endpoints.content, ".server_region")[0],
+      company       = json_path(local.file.endpoints.content, ".company")[0],
+      product       = json_path(local.file.endpoints.content, ".product")[0],
+      service_name  = json_path(local.file.endpoints.content, ".service_name")[0],
+      instance      = constants.hostname,
+    }
+  }
 }
 
 loki.write "log_write" {
-      endpoint {
-        url = json_path(local.file.endpoints.content, ".logs.url")[0]
-        headers = {
-          "X-Scope-OrgID" = json_path(local.file.endpoints.content, ".orgId")[0],
-        }
-        retry_on_http_429 = true
-      }
+  endpoint {
+    url = json_path(local.file.endpoints.content, ".logs.url")[0]
+    headers = {
+      "X-Scope-OrgID" = json_path(local.file.endpoints.content, ".orgId")[0],
+    }
+    retry_on_http_429 = true
+  }
 }
 
-// prometheus config for system monitering
 prometheus.exporter.unix "metrics" {
-      disable_collectors = []
-      include_exporter_metrics = true
-
-      filesystem {
-        fs_types_exclude     = "^(autofs|binfmt_misc|bpf|cgroup2?|configfs|debugfs|devpts|devtmpfs|fusectl|hugetlbfs|iso9660|mqueue|nsfs|overlay|proc|procfs|pstore|rpc_pipefs|securityfs|selinuxfs|squashfs|sysfs|tracefs)$"
-        mount_points_exclude = "^/(dev|proc|run/credentials/.+|sys|var/lib/docker/.+)($|/)"
-        mount_timeout        = "5s"
-      }
-
-      netclass {
-        ignored_devices = "^(veth.*|cali.*|[a-f0-9]{15})$"
-      }
-
-      netdev {
-        device_exclude = "^(veth.*|cali.*|[a-f0-9]{15})$"
-      }
+  include_exporter_metrics = true
 }
 
 prometheus.scrape "metrics_scrape" {
-      scrape_interval = "15s"
-      targets         = prometheus.exporter.unix.metrics.targets
-      forward_to      = [prometheus.relabel.metrics_relabel.receiver]
+  scrape_interval = "15s"
+  targets         = prometheus.exporter.unix.metrics.targets
+  forward_to      = [prometheus.relabel.metrics_relabel.receiver]
+}
+
+prometheus.scrape "app_metrics_scrape" {
+  scrape_interval = "15s"
+  targets = [
+    {
+      __address__      = "127.0.0.1:5000",
+      __metrics_path__ = "/metrics",
+      job              = "giddh-template-app",
+    },
+  ]
+  forward_to = [prometheus.relabel.metrics_relabel.receiver]
 }
 
 prometheus.relabel "metrics_relabel" {
-      forward_to = [prometheus.remote_write.metrics_write.receiver]
+  forward_to = [prometheus.remote_write.metrics_write.receiver]
 }
 
 prometheus.remote_write "metrics_write" {
-      endpoint {
-        url     = json_path(local.file.endpoints.content, ".metrics.url")[0]
-        headers = {
-          "X-Scope-OrgID" = json_path(local.file.endpoints.content, ".orgId")[0],
-        }
-      }
+  endpoint {
+    url     = json_path(local.file.endpoints.content, ".metrics.url")[0]
+    headers = {
+      "X-Scope-OrgID" = json_path(local.file.endpoints.content, ".orgId")[0],
+    }
+  }
 
   external_labels = {
-      env           = json_path(local.file.endpoints.content, ".environment")[0],
-      server_region = json_path(local.file.endpoints.content, ".server_region")[0],
-      company       = json_path(local.file.endpoints.content, ".company")[0],
-      product       = json_path(local.file.endpoints.content, ".product")[0],
-      service_name  = json_path(local.file.endpoints.content, ".service_name")[0],
-      instance      = constants.hostname,
+    env           = json_path(local.file.endpoints.content, ".environment")[0],
+    server_region = json_path(local.file.endpoints.content, ".server_region")[0],
+    company       = json_path(local.file.endpoints.content, ".company")[0],
+    product       = json_path(local.file.endpoints.content, ".product")[0],
+    service_name  = json_path(local.file.endpoints.content, ".service_name")[0],
+    instance      = constants.hostname,
+  }
+}
+
+otelcol.receiver.otlp "trace" {
+  grpc { endpoint = "0.0.0.0:4317" }
+  http { endpoint = "0.0.0.0:4318" }
+  output {
+    traces = [otelcol.processor.batch.trace_batch.input]
+  }
+}
+otelcol.processor.batch "trace_batch" {
+  timeout = "10s"
+  output {
+    traces = [otelcol.exporter.otlp.trace_write.input]
+  }
+}
+otelcol.exporter.otlp "trace_write" {
+  client {
+    endpoint = json_path(local.file.endpoints.content, ".tempo.url")[0]
+    tls {
+      insecure = true
+    }
+    headers = {
+      "X-Scope-OrgID" = json_path(local.file.endpoints.content, ".orgId")[0],
+    }
+    compression = "none"
   }
 }
 EOF
 
 echo "[INFO] Restarting alloy service..."
 sudo systemctl daemon-reexec
 sudo systemctl restart alloy
-echo "[INFO] Grafana setup complete."
+
+echo "[INFO] Grafana Alloy configuration applied successfully."