分布式 PostgreSQL 集群(Citus)官方示例 - 时间序列数据

-- declaratively partitioned table
CREATE TABLE github_events (
  event_id bigint,
  event_type text,
  event_public boolean,
  repo_id bigint,
  payload jsonb,
  repo jsonb,
  actor jsonb,
  org jsonb,
  created_at timestamp
) PARTITION BY RANGE (created_at);

SELECT create_distributed_table('github_events', 'repo_id');

SELECT create_time_partitions(
  table_name         := 'github_events',
  partition_interval := '1 month',
  end_at             := now() + '12 months'
);

-- set two monthly cron jobs:
-- 1. ensure we have partitions for the next 12 months
SELECT cron.schedule('create-partitions', '0 0 1 * *', $$
  SELECT create_time_partitions(
      table_name         := 'github_events',
      partition_interval := '1 month',
      end_at             := now() + '12 months'
  )
$$);
-- 2. (optional) ensure we never have more than one year of data
SELECT cron.schedule('drop-partitions', '0 0 1 * *', $$
  CALL drop_old_time_partitions(
      'github_events',
      now() - interval '12 months' /* older_than */
  );
$$);

wget http://examples.citusdata.com/github_archive/github_events-2015-01-01-{0..5}.csv.gz
gzip -c -d github_events-2015-01-01-*.gz >> github_events.csv

-- our new table, same structure as the example in
-- the previous section
CREATE TABLE github_columnar_events ( LIKE github_events )
PARTITION BY RANGE (created_at);
-- create partitions to hold two hours of data each
SELECT create_time_partitions(
  table_name         := 'github_columnar_events',
  partition_interval := '2 hours',
  start_from         := '2015-01-01 00:00:00',
  end_at             := '2015-01-01 08:00:00'
);
-- fill with sample data
-- (note that this data requires the database to have UTF8 encoding)
\COPY github_columnar_events FROM 'github_events.csv' WITH (format CSV)
-- list the partitions, and confirm they're
-- using row-based storage (heap access method)
SELECT partition, access_method
  FROM time_partitions
 WHERE parent_table = 'github_columnar_events'::regclass;

-- convert older partitions to use columnar storage
CALL alter_old_partitions_set_access_method(
  'github_columnar_events',
  '2015-01-01 06:00:00' /* older_than */,
  'columnar'
);
-- the old partitions are now columnar, while the
-- latest uses row storage and can be updated
SELECT partition, access_method
  FROM time_partitions
 WHERE parent_table = 'github_columnar_events'::regclass;

VACUUM VERBOSE github_columnar_events;

INFO:  statistics for "github_columnar_events_p2015_01_01_0000":
storage id: 10000000003
total file size: 4481024, total data size: 4444425
compression rate: 8.31x
total row count: 15129, stripe count: 1, average rows per stripe: 15129
chunk count: 18, containing data for dropped columns: 0, zstd compressed: 18
INFO:  statistics for "github_columnar_events_p2015_01_01_0200":
storage id: 10000000004
total file size: 3579904, total data size: 3548221
compression rate: 8.26x
total row count: 12714, stripe count: 1, average rows per stripe: 12714
chunk count: 18, containing data for dropped columns: 0, zstd compressed: 18
INFO:  statistics for "github_columnar_events_p2015_01_01_0400":
storage id: 10000000005
total file size: 2949120, total data size: 2917407
compression rate: 8.51x
total row count: 11756, stripe count: 1, average rows per stripe: 11756
chunk count: 18, containing data for dropped columns: 0, zstd compressed: 18

SELECT COUNT(DISTINCT repo_id)
  FROM github_columnar_events;

-- a monthly cron job
SELECT cron.schedule('compress-partitions', '0 0 1 * *', $$
  CALL alter_old_partitions_set_access_method(
    'github_columnar_events',
    now() - interval '6 months' /* older_than */,
    'columnar'
  );
$$);