Hologres:Analyze table statistics

-- Monitor trends for all internal tables in an instance, including storage size, number of files, read/write counts, and number of rows.
SELECT
  db_name,
  schema_name,
  table_name,
  collect_time :: date AS collect_date,
  hot_storage_size,
  cold_storage_size,
  hot_file_count,
  cold_file_count,
  read_sql_count_1d,
  write_sql_count_1d,
  row_count
FROM
  hologres.hg_table_info
WHERE
  collect_time > (current_date - interval '1 week')::timestamptz -- For the last week
  AND type ='TABLE'
  ORDER  BY  collect_date desc ;

-- Check access patterns for the top 10 tables by storage size.
SELECT
  db_name,
  schema_name,
  table_name,
  hot_storage_size + cold_storage_size AS total_storage_size,
  row_count,
  sum(read_sql_count_1d) AS total_read_count,
  sum(write_sql_count_1d) AS total_write_count
FROM
  hologres.hg_table_info
WHERE
  collect_time > (current_date - interval '1 week')::timestamptz -- For the last week
  AND type = 'TABLE'
  AND (
    cold_storage_size IS NOT NULL
    OR hot_storage_size IS NOT NULL
  )
GROUP BY db_name,schema_name,table_name,total_storage_size,row_count
ORDER BY total_storage_size DESC
LIMIT 10;

-- Analyze access, storage, and data volume trends over the last week for the top 10 tables by storage (based on yesterday's statistics).
WITH top10_table AS (SELECT
  db_name,
  schema_name,
  table_name,
  hot_storage_size + cold_storage_size AS total_storage_size
FROM
  hologres.hg_table_info
WHERE
  collect_time >= (current_date - interval '1 day')::timestamptz -- Yesterday
  AND collect_time < current_date
  AND type = 'TABLE'
  AND ( cold_storage_size IS NOT NULL OR hot_storage_size IS NOT NULL )
ORDER BY total_storage_size DESC
LIMIT 10
)
SELECT
  base.db_name,
  base.schema_name,
  base.table_name,
  base.hot_storage_size + cold_storage_size AS total_storage_size,
  base.row_count,
  base.read_sql_count_1d,
  base.write_sql_count_1d,
  base.collect_time :: date AS collect_date
FROM
  hologres.hg_table_info AS base
LEFT JOIN
  top10_table
ON
  base.db_name = top10_table.db_name
  AND base.schema_name = top10_table.schema_name
  AND base.table_name = top10_table.table_name
WHERE
  collect_time > (current_date - interval '1 week')::timestamptz -- For the last week
  AND type = 'TABLE'
  AND ( cold_storage_size IS NOT NULL OR hot_storage_size IS NOT NULL )
ORDER BY total_storage_size DESC , collect_date DESC;

-- Analyze access, storage, and data volume trends over the last week for the 10 tables that use the least storage (based on yesterday's statistics).
WITH top10_table AS (SELECT
  db_name,
  schema_name,
  table_name,
  hot_storage_size + cold_storage_size AS total_storage_size
FROM
  hologres.hg_table_info
WHERE
  collect_time >= (current_date - interval '1 day')::timestamptz -- Yesterday
  AND collect_time < current_date
  AND type = 'TABLE'
ORDER BY total_storage_size ASC LIMIT 10
)
SELECT
  base.db_name,
  base.schema_name,
  base.table_name,
  base.hot_storage_size + cold_storage_size AS total_storage_size,
  base.row_count,
  base.read_sql_count_1d,
  base.write_sql_count_1d,
  base.collect_time :: date AS collect_date
FROM
  hologres.hg_table_info AS base
RIGHT JOIN
  top10_table
ON
  base.db_name = top10_table.db_name
  AND base.schema_name = top10_table.schema_name
  AND base.table_name = top10_table.table_name
WHERE
  collect_time > (current_date - interval '1 week')::timestamptz -- For the last week
  AND type = 'TABLE'
ORDER BY total_storage_size ASC  , collect_date DESC ;

-- View the number of files and storage size for each table, and sort by average file size.
-- The table group shows the shard count only for the current database. For other databases, this value is null.
SELECT
  db_name,
  schema_name,
  table_name,
  cold_storage_size + hot_storage_size AS total_storage_size,
  cold_file_count + hot_file_count AS total_file_count,
  (cold_storage_size + hot_storage_size) / (cold_file_count + hot_file_count) AS avg_file_size,
  tmp_table_info.table_meta ->> 'table_group' AS table_group,
  tg_info.shard_count
FROM
  hologres.hg_table_info tmp_table_info
  LEFT JOIN (
    SELECT
      tablegroup_name,
      property_value AS shard_count
    FROM
      hologres.hg_table_group_properties
    WHERE
      property_key = 'shard_count'
  ) tg_info ON tmp_table_info.table_meta ->> 'table_group' = tg_info.tablegroup_name
WHERE
  collect_time > (current_date - interval '1 day')::timestamptz
  AND type = 'TABLE'
  AND (
    cold_storage_size IS NOT NULL
    OR hot_storage_size IS NOT NULL
  )
  AND (
    cold_file_count IS NOT NULL
    OR hot_file_count IS NOT NULL
  )
  AND cold_file_count + hot_file_count <> 0
ORDER BY avg_file_size;

-- View the last modification time and the total change in the number of rows from the last modification.
-- If the instance contains many tables, filter the CTE tmp_table_info to prevent long query times from fetching excessive data.
WITH tmp_table_info AS (
  SELECT
    db_name,
    schema_name,
    table_name,
    row_count,
    collect_time,
    last_modify_time
  FROM
    hologres.hg_table_info
  WHERE
    last_modify_time IS NOT NULL
    AND type = 'TABLE'
    -- Add filters for tmp_table_info here.
    -- For example: collect_time > (current_date - interval '14 day'):: timestamptz
    -- For example: table_name like ''
    -- For example: type = 'PARTITION'
)
SELECT
  end_data.db_name AS db_name,
  end_data.schema_name AS schema_name,
  end_data.table_name AS table_name,
  (end_data.row_count - start_data.row_count) AS modify_row_count,
  end_data.row_count AS current_rows,
  end_data.last_modify_time AS last_modify_time
FROM
  (
    SELECT
      db_name,
      schema_name,
      table_name,
      row_count,
      last_modify_time
    FROM
      tmp_table_info
    WHERE
      collect_time > (current_date - interval '1 day')::timestamptz -- Query the last modification time of the table recorded yesterday.
  ) end_data
  LEFT JOIN (
    SELECT
      db_name,
      schema_name,
      table_name,
      row_count,
      collect_time
    FROM
      tmp_table_info
  ) start_data ON (
    end_data.db_name = start_data.db_name
    AND end_data.schema_name = start_data.schema_name
    AND end_data.table_name = start_data.table_name
    AND end_data.last_modify_time::date = (start_data.collect_time + interval '1 day')::date
  );