Xây dựng một Target Endpoint cho Prometheus

sudo apt update
sudo apt install python3-pip

pip3 install prometheus_client

import subprocess, re, socket, time
from prometheus_client import start_http_server, Gauge

instance = socket.gethostbyname(socket.gethostname())
node = socket.gethostname()

# Define your metrics
cpu_load_average_1minute = Gauge('pe_custom_node_cpu_load_average_1minute', 'Description of gauge', ['id', 'instance'])
cpu_load_average_5minute = Gauge('pve_custom_node_cpu_load_average_5minute', 'Description of gauge', ['id', 'instance'])
cpu_load_average_15minute = Gauge('pve_custom_node_cpu_load_average_15minute', 'Description of gauge', ['id', 'instance'])
current_logged_in_users = Gauge('pve_custom_current_logged_in_users', 'Description of gauge', ['id', 'instance'])

def cpu_load_average(node, instance):
    results = subprocess.check_output("w", shell=True, text=True).strip('\n').split('\n')
    match = re.search(r'(\d+) users', results[0])

    if match:
        users_count = match.group(1)
    else:
        users_count = 0

    load_averages = re.findall(r'\d+\.\d+', results[0])

    cpu_load_average_1minute.labels(id="node/%s" % node, instance=instance).set(load_averages[0])
    cpu_load_average_5minute.labels(id="node/%s" % node, instance=instance).set(load_averages[1])
    cpu_load_average_15minute.labels(id="node/%s" % node, instance=instance).set(load_averages[2])
    current_logged_in_users.labels(id="node/%s" % node, instance=instance).set(users_count)

if __name__ == '__main__':
    # Start up the server to expose the metrics.
    start_http_server(16490)
    # Generate some requests.
    while True:
        cpu_load_average(node, instance)
        time.sleep(1)

scrape_configs:
  - job_name: 'demo-endpoints'
    static_configs:
      - targets: ['192.168.100.201:16490']

shell> netstat -tlnp  | grep 16490
tcp        0      0 0.0.0.0:16490           0.0.0.0:*               LISTEN      1191446/python3

shell> curl http://192.168.100.201:16490/metrics
# HELP python_gc_objects_collected_total Objects collected during gc
# TYPE python_gc_objects_collected_total counter
python_gc_objects_collected_total{generation="0"} 408.0
python_gc_objects_collected_total{generation="1"} 207.0
python_gc_objects_collected_total{generation="2"} 0.0
# HELP python_gc_objects_uncollectable_total Uncollectable objects found during GC
# TYPE python_gc_objects_uncollectable_total counter
python_gc_objects_uncollectable_total{generation="0"} 0.0
python_gc_objects_uncollectable_total{generation="1"} 0.0
python_gc_objects_uncollectable_total{generation="2"} 0.0
# HELP python_gc_collections_total Number of times this generation was collected
# TYPE python_gc_collections_total counter
python_gc_collections_total{generation="0"} 39.0
python_gc_collections_total{generation="1"} 3.0
python_gc_collections_total{generation="2"} 0.0
# HELP python_info Python platform information
# TYPE python_info gauge
python_info{implementation="CPython",major="3",minor="11",patchlevel="2",version="3.11.2"} 1.0
# HELP process_virtual_memory_bytes Virtual memory size in bytes.
# TYPE process_virtual_memory_bytes gauge
process_virtual_memory_bytes 1.82583296e+08
# HELP process_resident_memory_bytes Resident memory size in bytes.
# TYPE process_resident_memory_bytes gauge
process_resident_memory_bytes 2.3199744e+07
# HELP process_start_time_seconds Start time of the process since unix epoch in seconds.
# TYPE process_start_time_seconds gauge
process_start_time_seconds 1.71478961504e+09
# HELP process_cpu_seconds_total Total user and system CPU time spent in seconds.
# TYPE process_cpu_seconds_total counter
process_cpu_seconds_total 0.13
# HELP process_open_fds Number of open file descriptors.
# TYPE process_open_fds gauge
process_open_fds 11.0
# HELP process_max_fds Maximum number of open file descriptors.
# TYPE process_max_fds gauge
process_max_fds 1.048576e+06
# HELP pe_custom_node_cpu_load_average_1minute Description of gauge
# TYPE pe_custom_node_cpu_load_average_1minute gauge
pe_custom_node_cpu_load_average_1minute{id="node/pve01",instance="10.10.10.1"} 1.74
# HELP pve_custom_node_cpu_load_average_5minute Description of gauge
# TYPE pve_custom_node_cpu_load_average_5minute gauge
pve_custom_node_cpu_load_average_5minute{id="node/pve01",instance="10.10.10.1"} 1.66
# HELP pve_custom_node_cpu_load_average_15minute Description of gauge
# TYPE pve_custom_node_cpu_load_average_15minute gauge
pve_custom_node_cpu_load_average_15minute{id="node/pve01",instance="10.10.10.1"} 1.61
# HELP pve_custom_current_logged_in_users Description of gauge
# TYPE pve_custom_current_logged_in_users gauge
pve_custom_current_logged_in_users{id="node/pve01",instance="10.10.10.1"} 8.0