collector_config.yaml

collector_name: mssql_standard

metrics:
  - metric_name: mssql_local_time_seconds
    type: gauge
    help: 'Local time in seconds since epoch (Unix time).'
    values: [unix_time]
    query: |
      SELECT DATEDIFF(second, '19700101', GETUTCDATE()) AS unix_time
  - metric_name: mssql_connections
    type: gauge
    help: 'Number of active connections.'
    key_labels:
      - db
    values: [count]
    query: |
      SELECT DB_NAME(sp.dbid) AS db, COUNT(sp.spid) AS count
      FROM sys.sysprocesses sp
      GROUP BY DB_NAME(sp.dbid)
  #
  # Collected from sys.dm_os_performance_counters
  #
  - metric_name: mssql_deadlocks_total
    type: counter
    help: 'Number of lock requests that resulted in a deadlock.'
    values: [cntr_value]
    query: |
      SELECT cntr_value
      FROM sys.dm_os_performance_counters WITH (NOLOCK)
      WHERE counter_name = 'Number of Deadlocks/sec' AND instance_name = '_Total'
  - metric_name: mssql_user_errors_total
    type: counter
    help: 'Number of user errors.'
    values: [cntr_value]
    query: |
      SELECT cntr_value
      FROM sys.dm_os_performance_counters WITH (NOLOCK)
      WHERE counter_name = 'Errors/sec' AND instance_name = 'User Errors'
  - metric_name: mssql_kill_connection_errors_total
    type: counter
    help: 'Number of severe errors that caused SQL Server to kill the connection.'
    values: [cntr_value]
    query: |
      SELECT cntr_value
      FROM sys.dm_os_performance_counters WITH (NOLOCK)
      WHERE counter_name = 'Errors/sec' AND instance_name = 'Kill Connection Errors'
  - metric_name: mssql_page_life_expectancy_seconds
    type: gauge
    help: 'The minimum number of seconds a page will stay in the buffer pool on this node without references.'
    values: [cntr_value]
    query: |
      SELECT top(1) cntr_value
      FROM sys.dm_os_performance_counters WITH (NOLOCK)
      WHERE counter_name = 'Page life expectancy'
  - metric_name: mssql_batch_requests_total
    type: counter
    help: 'Number of command batches received.'
    values: [cntr_value]
    query: |
      SELECT cntr_value
      FROM sys.dm_os_performance_counters WITH (NOLOCK)
      WHERE counter_name = 'Batch Requests/sec'
  - metric_name: mssql_log_growths_total
    type: counter
    help: 'Number of times the transaction log has been expanded, per database.'
    key_labels:
      - db
    values: [cntr_value]
    query: |
      SELECT rtrim(instance_name) AS db, cntr_value
      FROM sys.dm_os_performance_counters WITH (NOLOCK)
      WHERE counter_name = 'Log Growths' AND instance_name <> '_Total'
  - metric_name: mssql_buffer_cache_hit_ratio
    type: gauge
    help: 'Ratio of requests that hit the buffer cache'
    values: [BufferCacheHitRatio]
    query: |
      SELECT (a.cntr_value * 1.0 / b.cntr_value) * 100.0 as BufferCacheHitRatio
      FROM sys.dm_os_performance_counters  a
      JOIN  (SELECT cntr_value, OBJECT_NAME 
          FROM sys.dm_os_performance_counters  
          WHERE counter_name = 'Buffer cache hit ratio base'
              AND OBJECT_NAME = 'SQLServer:Buffer Manager') b ON  a.OBJECT_NAME = b.OBJECT_NAME
      WHERE a.counter_name = 'Buffer cache hit ratio'
      AND a.OBJECT_NAME = 'SQLServer:Buffer Manager'

  - metric_name: mssql_checkpoint_pages_sec
    type: gauge
    help: 'Checkpoint Pages Per Second'
    values: [cntr_value]
    query: |
      SELECT cntr_value
      FROM sys.dm_os_performance_counters
      WHERE [counter_name] = 'Checkpoint pages/sec'
  #
  # Collected from sys.dm_io_virtual_file_stats
  #
  - metric_name: mssql_io_stall_seconds_total
    type: counter
    help: 'Stall time in seconds per database and I/O operation.'
    key_labels:
      - db
    value_label: operation
    values:
      - read
      - write
    query_ref: mssql_io_stall

  #
  # Collected from sys.dm_os_process_memory
  #
  - metric_name: mssql_resident_memory_bytes
    type: gauge
    help: 'SQL Server resident memory size (AKA working set).'
    values: [resident_memory_bytes]
    query_ref: mssql_process_memory

  - metric_name: mssql_virtual_memory_bytes
    type: gauge
    help: 'SQL Server committed virtual memory size.'
    values: [virtual_memory_bytes]
    query_ref: mssql_process_memory

  - metric_name: mssql_memory_utilization_percentage
    type: gauge
    help: 'The percentage of committed memory that is in the working set.'
    values: [memory_utilization_percentage]
    query_ref: mssql_process_memory

  - metric_name: mssql_page_fault_count_total
    type: counter
    help: 'The number of page faults that were incurred by the SQL Server process.'
    values: [page_fault_count]
    query_ref: mssql_process_memory

  #
  # Collected from sys.dm_os_sys_memory
  #
  - metric_name: mssql_os_memory
    type: gauge
    help: 'OS physical memory, used and available.'
    value_label: 'state'
    values: [used, available]
    query: |
      SELECT
        (total_physical_memory_kb - available_physical_memory_kb) * 1024 AS used,
        available_physical_memory_kb * 1024 AS available
      FROM sys.dm_os_sys_memory
  - metric_name: mssql_os_page_file
    type: gauge
    help: 'OS page file, used and available.'
    value_label: 'state'
    values: [used, available]
    query: |
      SELECT
        (total_page_file_kb - available_page_file_kb) * 1024 AS used,
        available_page_file_kb * 1024 AS available
      FROM sys.dm_os_sys_memory
queries:
  # Populates `mssql_io_stall` and `mssql_io_stall_total`
  - query_name: mssql_io_stall
    query: |
      SELECT
        cast(DB_Name(a.database_id) as varchar) AS [db],
        sum(io_stall_read_ms) / 1000.0 AS [read],
        sum(io_stall_write_ms) / 1000.0 AS [write]
      FROM
        sys.dm_io_virtual_file_stats(null, null) a
      INNER JOIN sys.master_files b ON a.database_id = b.database_id AND a.file_id = b.file_id
      GROUP BY a.database_id
  # Populates `mssql_resident_memory_bytes`, `mssql_virtual_memory_bytes`, `mssql_memory_utilization_percentage` and
  # `mssql_page_fault_count`.
  - query_name: mssql_process_memory
    query: |
      SELECT
        physical_memory_in_use_kb * 1024 AS resident_memory_bytes,
        virtual_address_space_committed_kb * 1024 AS virtual_memory_bytes,
        memory_utilization_percentage,
        page_fault_count
      FROM sys.dm_os_process_memory