ideallove

docker run -d \
--name nvidia_smi_exporter \
--restart unless-stopped \
--device /dev/nvidiactl:/dev/nvidiactl \
--device /dev/nvidia0:/dev/nvidia0 \
-v /usr/lib/x86_64-linux-gnu/libnvidia-ml.so:/usr/lib/x86_64-linux-gnu/libnvidia-ml.so \
-v /usr/lib/x86_64-linux-gnu/libnvidia-ml.so.1:/usr/lib/x86_64-linux-gnu/libnvidia-ml.so.1 \
-v /usr/bin/nvidia-smi:/usr/bin/nvidia-smi \
-p 9835:9835 \
utkuozdemir/nvidia_gpu_exporter:1.2.0

# Create persistent volume for your data
docker volume create prometheus-data

# my global config
global:
  scrape_interval: 15s # Set the scrape interval to every 15 seconds. Default is every 1 minute.
  evaluation_interval: 15s # Evaluate rules every 15 seconds. The default is every 1 minute.
  # scrape_timeout is set to the global default (10s).
# Alertmanager configuration
alerting:
  alertmanagers:
    - static_configs:
        - targets:
          # - alertmanager:9093
# Load rules once and periodically evaluate them according to the global 'evaluation_interval'.
rule_files:
  # - "first_rules.yml"
  # - "second_rules.yml"
# A scrape configuration containing exactly one endpoint to scrape:
# Here it's Prometheus itself.
scrape_configs:
  # The job name is added as a label `job=<job_name>` to any timeseries scraped from this config.
  - job_name: "prometheus"
    # metrics_path defaults to '/metrics'
    # scheme defaults to 'http'.
    static_configs:
      - targets: ["localhost:9090"]
  - job_name: "GPU"
    static_configs:
      - targets: ["172.17.0.1:9835"] 

# Start Prometheus container
docker run -d \
    -p 9090:9090 \
    -v /root/monitor/prometheus.yml:/etc/prometheus/prometheus.yml \
    -v prometheus-data:/prometheus \
    prom/prometheus

# create a persistent volume for your data
docker volume create grafana-storage

# start grafana
docker run -d -p 3000:3000 --name=grafana \
  --volume grafana-storage:/var/lib/grafana \
  grafana/grafana-enterprise