Deploy promethetus server
Browse files- Dockerfile +21 -0
- turing_cloud.yml +41 -0
Dockerfile
ADDED
|
@@ -0,0 +1,21 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
FROM prom/prometheus:latest
|
| 2 |
+
|
| 3 |
+
# Create a non-root user to run the application and set permissions
|
| 4 |
+
RUN useradd -m -u 1000 turinguser
|
| 5 |
+
|
| 6 |
+
# Create directories and set permissions
|
| 7 |
+
RUN mkdir -p /app/models && chown -R turinguser:turinguser /app /app/models
|
| 8 |
+
|
| 9 |
+
# Switch to the non-root user
|
| 10 |
+
USER turinguser
|
| 11 |
+
|
| 12 |
+
WORKDIR /app
|
| 13 |
+
|
| 14 |
+
# Copy your Prometheus config and set ownership
|
| 15 |
+
COPY --chown=turinguser turing_cloud.yml .
|
| 16 |
+
|
| 17 |
+
# Expose Prometheus port
|
| 18 |
+
EXPOSE 9090
|
| 19 |
+
|
| 20 |
+
# Run Prometheus with your custom config
|
| 21 |
+
CMD [ "/bin/prometheus", "--config.file=/app/turing_cloud.yml" ]
|
turing_cloud.yml
ADDED
|
@@ -0,0 +1,41 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
# my global config
|
| 2 |
+
global:
|
| 3 |
+
scrape_interval: 15s # Kept your faster 15s interval (better resolution)
|
| 4 |
+
evaluation_interval: 15s # Evaluate rules every 15s
|
| 5 |
+
scrape_timeout: 10s # Global default
|
| 6 |
+
|
| 7 |
+
# --- GRAFANA CLOUD CONNECTION ---
|
| 8 |
+
# This sends your metrics to the cloud.
|
| 9 |
+
# It sits at the top level, indented securely under no other block.
|
| 10 |
+
remote_write:
|
| 11 |
+
- url: https://prometheus-prod-65-prod-eu-west-2.grafana.net/api/prom/push
|
| 12 |
+
basic_auth:
|
| 13 |
+
username: 2894335
|
| 14 |
+
password: glc_eyJvIjoiMTYzMjA0NSIsIm4iOiJzdGFjay0xNDg1MDUxLWFsbG95LXR1cmluZ19hcGkiLCJrIjoiRjJvajQ5N2EwWWJpcTA2aFNXZ3FYMzIxIiwibSI6eyJyIjoicHJvZC1ldS13ZXN0LTIifX0=
|
| 15 |
+
|
| 16 |
+
# Alertmanager configuration
|
| 17 |
+
alerting:
|
| 18 |
+
alertmanagers:
|
| 19 |
+
- static_configs:
|
| 20 |
+
- targets:
|
| 21 |
+
# - alertmanager:9093
|
| 22 |
+
|
| 23 |
+
# Load rules once and periodically evaluate them
|
| 24 |
+
rule_files:
|
| 25 |
+
# - "first_rules.yml"
|
| 26 |
+
# - "second_rules.yml"
|
| 27 |
+
|
| 28 |
+
# --- SCRAPE CONFIGURATIONS ---
|
| 29 |
+
scrape_configs:
|
| 30 |
+
# JOB 1: Your Application (Turing API)
|
| 31 |
+
- job_name: "turing"
|
| 32 |
+
static_configs:
|
| 33 |
+
- targets: ["https://turing-team-turing-space.hf.space"]
|
| 34 |
+
labels:
|
| 35 |
+
app: "turing_api"
|
| 36 |
+
|
| 37 |
+
# JOB 2: Prometheus Internal Metrics (Recommended)
|
| 38 |
+
# It is good practice to let Prometheus monitor itself.
|
| 39 |
+
- job_name: "prometheus"
|
| 40 |
+
static_configs:
|
| 41 |
+
- targets: ["https://turing-team-turing-promethetus-server.hf.space"]
|