Vignesh/kvm monitor integration

.gitignore

@@ -3,3 +3,7 @@ env/
 __pycache__/
 *.py[cod]
 *$py.class
+.idea/
+venv/
+
+logs/

README.md

@@ -10,6 +10,32 @@ Make sure you have the following installed on your system:
 - InfluxDB
 - [InfluxDB Python Client](https://github.com/influxdata/influxdb-client-python)
 
+## VM Preparation
+
+Install `kvmtop`
+```commandline
+wget https://github.com/cha87de/kvmtop/releases/download/2.1.3/kvmtop_2.1.3_linux_amd64.deb
+sudo dpkg -i kvmtop_2.1.3_linux_amd64.deb
+```
+Try kvmtop it may fail with error saying missing package libncurses5.so
+To fix it add below lines to `/etc/apt/sources.list` 
+```commandline
+deb http://security.ubuntu.com/ubuntu focal-security main
+deb http://archive.ubuntu.com/ubuntu/ focal main restricted universe multiverse
+deb http://archive.ubuntu.com/ubuntu/ focal-updates main restricted universe multiverse
+deb http://security.ubuntu.com/ubuntu/ focal-security main restricted universe multiverse
+```
+And execute below commands:
+```commandline
+sudo apt update
+sudo apt upgrade
+sudo apt-get install libncurses5 libncurses5:i386
+```
+It will resolve this issue, try `kvmtop` command in terminal and verify everything working as expected
+
+Note: If you got stuck with the above error then, remove `libncurses5:i386` and install only `libncurses5` (Sample Error message: E: Unable to locate package libncurses5:i386)
+
+
 ## Usage
 
 1. Set up your InfluxDB configuration by creating a `.env` file with the following variables:
@@ -19,10 +45,22 @@ Make sure you have the following installed on your system:
     INFLUX_TOKEN="your-influxdb-token"
     INFLUX_ORG="your-influxdb-organization"
     INFLUX_BUCKET="your-influxdb-bucket"
+    ROOT_PASS="user-passof-ubuntu-terminal"
+    DISK_PATH="disk-path-to-be-monitored"
     ```
 2. Run the script:
 
     ```bash
-    python main.py
+    python system_monitor.py
     ```
 
+## Configure systemd service
+1. Pull latest changes to the machine.
+2. Update and validate `libmon.service` file in the Libmon directory
+3. Copy the directory to `sudo cp libmon.service /etc/systemd/system/libmon.service`
+4. Enable the service by `sudo systemctl enable libmon.service`
+5. Start the service by `sudo systemctl start libmon.service`
+6. Validate the process status by `sudo systemctl status libmon.service  and tail -f /home/dev/Libmon/logs/system_monitor.log`.
+
+
+

config/modules_config.json

@@ -1,8 +1,10 @@
 {
     "modules": [
-        {"name": "uptime", "interval_seconds": 600},
-        {"name": "disk", "interval_seconds": 600},
-        {"name": "partition", "interval_seconds": 3600},
-        {"name": "sensors", "interval_seconds": 60}
+        {"name": "uptime", "interval_seconds": 30},
+        {"name": "disk", "interval_seconds": 30},
+        {"name": "partition", "interval_seconds": 30},
+        {"name": "sensors", "interval_seconds": 30},
+        {"name": "kvm_monitor", "interval_seconds": 30},
+        {"name": "network", "interval_seconds": 30}
     ]
 }

connection.py

@@ -0,0 +1,29 @@
+import os
+import influxdb_client
+
+from dotenv import load_dotenv
+from influxdb_client.client.write_api import SYNCHRONOUS
+
+load_dotenv()
+
+INFLUX_URL = os.getenv("INFLUX_URL")
+INFLUX_TOKEN = os.getenv("INFLUX_TOKEN")
+INFLUX_ORG = os.getenv("INFLUX_ORG")
+INFLUX_BUCKET = os.getenv("INFLUX_BUCKET")
+
+client = influxdb_client.InfluxDBClient(url=INFLUX_URL, token=INFLUX_TOKEN, org=INFLUX_ORG, verify_ssl=False)
+write_api = client.write_api(write_options=SYNCHRONOUS)
+
+
+def create_influxdb_point(measurement, data):
+    point = influxdb_client.Point(measurement)
+    for key, value in data.items():
+        if key == 'host':
+            # hotfix for dot in hostname
+            point = point.tag(key, value.split('.')[0])
+        if key == 'vm_name':
+            point = point.tag(key, value)
+        else:
+            point = point.field(key, value)
+
+    return point

launch.sh

@@ -0,0 +1,32 @@
+#!/bin/bash
+
+# Name of the process to check (without path)
+PROCESS_NAME="system_monitor.py"
+
+# Directory of your Python virtual environment
+VENV_DIR="/path/to/your/venv"
+
+# Directory where your Python script is located
+SCRIPT_DIR="/path/to/your/script"
+
+# Name of your Python script
+SCRIPT_NAME="your_script.py"
+
+# Check if the process is running
+if ! pgrep -f "$PROCESS_NAME" > /dev/null
+then
+    echo "Process $PROCESS_NAME is not running. Starting it..."
+
+    # Activate virtual environment
+    source "$VENV_DIR/bin/activate"
+
+    # Change directory to the script location
+    cd "$SCRIPT_DIR"
+
+    # Launch the Python script
+    nohup python "$SCRIPT_NAME" &
+
+    echo "Process $PROCESS_NAME started."
+else
+    echo "Process $PROCESS_NAME is already running."
+fi

modules/__init__.py

@@ -0,0 +1,20 @@
+import logging
+import os
+
+MONITORING_INTERVAL = 30
+
+if not os.path.exists('./logs'):
+    os.makedirs('logs')
+
+# Configure logging
+logging.basicConfig(
+    level=logging.DEBUG,
+    format='%(asctime)s - %(name)s - %(levelname)s - %(message)s',
+    handlers=[
+        logging.FileHandler("./logs/system_monitor.log"),
+        logging.StreamHandler()
+    ]
+)
+
+# Create a logger instance
+logger = logging.getLogger(__name__)

modules/disk.py

@@ -1,7 +1,11 @@
 import os
 import socket
 import subprocess
-import json
+
+import ujson
+
+from modules import logger
+
 
 def get_nvme_disk_names():
     try:
@@ -12,20 +16,37 @@ def get_nvme_disk_names():
         return nvme_disks
 
     except subprocess.CalledProcessError as e:
-        print(f"Error: {e}")
+        logger.debug(f"Error: {e}")
         return []
 
 
+def get_disk_stats(disk_path):
+    try:
+        output = subprocess.check_output(
+            args=['sudo', '-S', 'smartctl', '-j', '-a', disk_path],
+            input=f'{os.getenv("ROOT_PASS")}\n',
+            universal_newlines=True
+        )
+        if output and output.startswith('{ "'):
+            data = ujson.loads(output)
+            return data
+    except subprocess.CalledProcessError as e:
+        logger.debug(f"Command failed with exit status {e.returncode}")
+        if e.output and e.output.startswith('{\n'):
+            data = ujson.loads(e.output)
+            return data
+    except Exception as e:
+        logger.debug(str(e))
+    return {}
+
+
 def get_smartctl_data(disk_path):
 
     if disk_path is None:
-        print("DISK_PATH environment variable is not set.")
+        logger.debug("DISK_PATH environment variable is not set.")
         return None
 
-    command_output = subprocess.check_output(['smartctl', '-j', '-a', disk_path]).decode('utf-8')
-
-    # Parse JSON output
-    smart_data = json.loads(command_output)
+    smart_data = get_disk_stats(disk_path)
 
     # Extract relevant values from the JSON data
     hostname = socket.gethostname()
@@ -57,18 +78,23 @@ def get_smartctl_data(disk_path):
         "media_and_data_integrity_errors": int(media_and_data_integrity_errors)
     }
 
+
 def collect_data():
-    if os.getenv("STORAGE_SERVER"):
-        disks = get_nvme_disk_names()
-        disk_data = []
-        for disk in disks:
-            disk_data.append(get_smartctl_data(f"/dev/{disk}"))
+    try:
+        if os.getenv("STORAGE_SERVER"):
+            disks = get_nvme_disk_names()
+            disk_data = []
+            for disk in disks:
+                disk_data.append(get_smartctl_data(f"/dev/{disk}"))
 
-        return disk_data
+            return disk_data
 
-    disk_path = os.getenv("DISK_PATH")
-    return get_smartctl_data(disk_path)
+        disk_path = os.getenv("DISK_PATH")
+        return get_smartctl_data(disk_path)
+    except Exception as e:
+        logger.debug(str(e))
+    return {}
 
 
 if __name__=="__main__":
-    print(collect_data())
+    logger.debug(collect_data())