Configuration

collector_branch_name:           # Unique identifier for this collector
  name: metric_namespace         # Metric prefix (defaults to branch name)
  desc: "Collector description"  # Human-readable description
  query: |                       # SQL query to execute
    SELECT column1, column2
    FROM table

  # Execution Control
  ttl: 10                        # Cache time-to-live in seconds
  timeout: 0.1                   # Query timeout in seconds
  fatal: false                   # If true, failure fails entire scrape
  skip: false                    # If true, collector is disabled

  # Version Compatibility
  min_version: 100000            # Minimum PostgreSQL version (inclusive)
  max_version: 999999            # Maximum PostgreSQL version (exclusive)

  # Execution Tags
  tags: [cluster, primary]       # Conditions for execution

  # Predicate Queries (optional)
  predicate_queries:
    - name: "check_function"
      predicate_query: |
        SELECT EXISTS (...)

  # Metric Definitions
  metrics:
    - column_name:
        usage: GAUGE             # GAUGE, COUNTER, HISTOGRAM, LABEL, or DISCARD
        rename: metric_name      # Optional: rename the metric
        description: "Help text" # Metric description
        default: 0               # Default value if NULL
        scale: 1000              # Scale factor for the value
        bucket: [1, 10, 100]     # Bucket upper bounds for HISTOGRAM columns (strictly increasing, +Inf appended)

pg_stat_database:  # Must be unique
  name: pg_db      # Actual metric namespace

query: |
  SELECT 
    datname,
    numbackends,
    xact_commit,
    xact_rollback,
    blks_read,
    blks_hit
  FROM pg_stat_database
  WHERE datname NOT IN ('template0', 'template1')

pg_xact_age:
  name: pg_xact_age
  desc: "Open transaction age distribution histogram"
  query: |
    SELECT datname,
           greatest(0, extract(epoch FROM now() - xact_start)) AS seconds
    FROM pg_stat_activity
    WHERE pid <> pg_backend_pid() AND backend_type = 'client backend'
      AND datname IS NOT NULL AND xact_start IS NOT NULL;
  ttl: 10
  tags: [cluster]
  metrics:
    - datname: {usage: LABEL, description: "Database name"}
    - seconds:
        usage: HISTOGRAM
        bucket: [1, 3, 10, 30, 100, 300, 1000, 3000, 10000, 30000, 100000]
        description: "Open transaction age snapshot in seconds"

# Fast queries - minimal caching
pg_stat_activity:
  ttl: 1  # Cache for 1 second

# Expensive queries - longer caching
pg_table_bloat:
  ttl: 3600  # Cache for 1 hour

timeout: 0.1   # 100ms default
timeout: 1.0   # 1 second for complex queries
timeout: -1    # Disable timeout (not recommended)

min_version: 100000  # PostgreSQL 10.0+
max_version: 140000  # Below PostgreSQL 14.0

pg_exporter --tag="production,critical"

expensive_metrics:
  tags: [critical]  # Only runs with 'critical' tag

predicate_queries:
  - name: "Check pg_stat_statements"
    predicate_query: |
      SELECT EXISTS (
        SELECT 1 FROM pg_extension 
        WHERE extname = 'pg_stat_statements'
      )

metrics:
  - numbackends:
      usage: GAUGE
      description: "Number of backends connected"

metrics:
  - checkpoint_write_time:
      usage: COUNTER
      rename: write_time        # Rename metric
      scale: 0.001              # Convert ms to seconds
      default: 0                # Use 0 if NULL
      description: "Checkpoint write time in seconds"

pg_connections:
  desc: "Current database connections"
  query: |
    SELECT 
      count(*) as total,
      count(*) FILTER (WHERE state = 'active') as active,
      count(*) FILTER (WHERE state = 'idle') as idle,
      count(*) FILTER (WHERE state = 'idle in transaction') as idle_in_transaction
    FROM pg_stat_activity
    WHERE pid != pg_backend_pid()
  ttl: 1
  metrics:
    - total: {usage: GAUGE, description: "Total connections"}
    - active: {usage: GAUGE, description: "Active connections"}
    - idle: {usage: GAUGE, description: "Idle connections"}
    - idle_in_transaction: {usage: GAUGE, description: "Idle in transaction"}

pg_table_stats:
  desc: "Table statistics"
  query: |
    SELECT 
      schemaname,
      tablename,
      n_tup_ins,
      n_tup_upd,
      n_tup_del,
      n_live_tup,
      n_dead_tup
    FROM pg_stat_user_tables
  ttl: 10
  metrics:
    - schemaname: {usage: LABEL}
    - tablename: {usage: LABEL}
    - n_tup_ins: {usage: COUNTER, description: "Tuples inserted"}
    - n_tup_upd: {usage: COUNTER, description: "Tuples updated"}
    - n_tup_del: {usage: COUNTER, description: "Tuples deleted"}
    - n_live_tup: {usage: GAUGE, description: "Live tuples"}
    - n_dead_tup: {usage: GAUGE, description: "Dead tuples"}

pg_wal_stats:
  desc: "WAL statistics (PG 14+)"
  min_version: 140000
  query: |
    SELECT 
      wal_records,
      wal_bytes,
      wal_buffers_full,
      wal_write_time,
      wal_sync_time
    FROM pg_stat_wal
  ttl: 10
  tags: [cluster]
  metrics:
    - wal_records: {usage: COUNTER}
    - wal_bytes: {usage: COUNTER}
    - wal_buffers_full: {usage: COUNTER}
    - wal_write_time: {usage: COUNTER, scale: 0.001}
    - wal_sync_time: {usage: COUNTER, scale: 0.001}

pg_stat_statements_metrics:
  desc: "Query performance statistics"
  tags: [extension:pg_stat_statements]
  query: |
    SELECT 
      sum(calls) as total_calls,
      sum(total_exec_time) as total_time,
      sum(mean_exec_time * calls) / sum(calls) as mean_time
    FROM pg_stat_statements
  ttl: 60
  metrics:
    - total_calls: {usage: COUNTER}
    - total_time: {usage: COUNTER, scale: 0.001}
    - mean_time: {usage: GAUGE, scale: 0.001}

# /etc/pg_exporter/custom_metrics.yml
app_metrics:
  desc: "Application-specific metrics"
  query: |
    SELECT 
      (SELECT count(*) FROM users WHERE active = true) as active_users,
      (SELECT count(*) FROM orders WHERE created_at > NOW() - '1 hour'::interval) as recent_orders,
      (SELECT avg(processing_time) FROM jobs WHERE completed_at > NOW() - '5 minutes'::interval) as avg_job_time
  ttl: 30
  metrics:
    - active_users: {usage: GAUGE, description: "Currently active users"}
    - recent_orders: {usage: GAUGE, description: "Orders in last hour"}
    - avg_job_time: {usage: GAUGE, description: "Average job processing time"}

pg_exporter --explain --config=/etc/pg_exporter/

partition_metrics:
  desc: "Partitioned table metrics"
  predicate_queries:
    - name: "Check if partitioning is used"
      predicate_query: |
        SELECT EXISTS (
          SELECT 1 FROM pg_class 
          WHERE relkind = 'p' LIMIT 1
        )
  query: |
    SELECT 
      parent.relname as parent_table,
      count(*) as partition_count,
      sum(pg_relation_size(child.oid)) as total_size
    FROM pg_inherits
    JOIN pg_class parent ON parent.oid = pg_inherits.inhparent
    JOIN pg_class child ON child.oid = pg_inherits.inhrelid
    WHERE parent.relkind = 'p'
    GROUP BY parent.relname
  ttl: 300
  metrics:
    - parent_table: {usage: LABEL}
    - partition_count: {usage: GAUGE}
    - total_size: {usage: GAUGE}

# View collector statistics (hit / error / skip counters and durations)
curl http://localhost:9630/stat

# Per-collector duration and error counters, by datname/query
curl -s http://localhost:9630/metrics | grep -E 'pg_exporter_query_scrape_(duration|error_count)'

# Dry run - shows parsed configuration
pg_exporter --dry-run

# Explain - shows planned queries
pg_exporter --explain

pg_exporter --log.level=debug