プロジェクション

CREATE TABLE nyc_taxi.trips_with_projection AS nyc_taxi.trips;
INSERT INTO nyc_taxi.trips_with_projection SELECT * FROM nyc_taxi.trips;

ALTER TABLE nyc_taxi.trips_with_projection
ADD PROJECTION prj_tip_amount
(
    SELECT *
    ORDER BY tip_amount, dateDiff('minutes', pickup_datetime, dropoff_datetime)
)

ALTER TABLE nyc.trips_with_projection MATERIALIZE PROJECTION prj_tip_amount

SELECT query, projections 
FROM system.query_log 
WHERE query_id='<query_id>'

   ┌─query─────────────────────────────────────────────────────────────────────────┬─projections──────────────────────┐
   │ SELECT                                                                       ↴│ ['default.trips.prj_tip_amount'] │
   │↳  tip_amount,                                                                ↴│                                  │
   │↳  trip_id,                                                                   ↴│                                  │
   │↳  dateDiff('minutes', pickup_datetime, dropoff_datetime) AS trip_duration_min↴│                                  │
   │↳FROM trips WHERE tip_amount > 200 AND trip_duration_min > 0                   │                                  │
   └───────────────────────────────────────────────────────────────────────────────┴──────────────────────────────────┘

CREATE TABLE uk.uk_price_paid_with_projections AS uk_price_paid;
INSERT INTO uk.uk_price_paid_with_projections SELECT * FROM uk.uk_price_paid;

ALTER TABLE uk.uk_price_paid_with_projections
  (ADD PROJECTION prj_obj_town_price
  (
    SELECT *
    ORDER BY
        town,
        price
  ))

ALTER TABLE uk.uk_price_paid_with_projections
  (MATERIALIZE PROJECTION prj_obj_town_price)
SETTINGS mutations_sync = 1

ALTER TABLE uk.uk_price_paid_with_projections
  (ADD PROJECTION prj_gby_county
  (
    SELECT
        county,
        avg(price)
    GROUP BY county
  ))

ALTER TABLE uk.uk_price_paid_with_projections
  (MATERIALIZE PROJECTION prj_gby_county)
SETTINGS mutations_sync = 1

SELECT
  tables,
  query,
  query_duration_ms::String ||  ' ms' AS query_duration,
        formatReadableQuantity(read_rows) AS read_rows,
  projections
FROM clusterAllReplicas(default, system.query_log)
WHERE (type = 'QueryFinish') AND (tables = ['default.uk_price_paid_with_projections'])
ORDER BY initial_query_start_time DESC
  LIMIT 2
FORMAT Vertical

Row 1:
──────
tables:         ['uk.uk_price_paid_with_projections']
query:          SELECT
    county,
    avg(price)
FROM uk_price_paid_with_projections
GROUP BY county
ORDER BY avg(price) DESC
LIMIT 3
query_duration: 5 ms
read_rows:      132.00
projections:    ['uk.uk_price_paid_with_projections.prj_gby_county']

Row 2:
──────
tables:         ['uk.uk_price_paid_with_projections']
query:          SELECT
  county,
  price
FROM uk_price_paid_with_projections
WHERE town = 'LONDON'
ORDER BY price DESC
LIMIT 3
SETTINGS log_queries=1
query_duration: 11 ms
read_rows:      2.29 million
projections:    ['uk.uk_price_paid_with_projections.prj_obj_town_price']

2 rows in set. Elapsed: 0.006 sec.

CREATE TABLE uk.uk_price_paid_with_projections_v2 AS uk.uk_price_paid;
INSERT INTO uk.uk_price_paid_with_projections_v2 SELECT * FROM uk.uk_price_paid;

ALTER TABLE uk.uk_price_paid_with_projections_v2
    ADD COLUMN year UInt16 MATERIALIZED toYear(date)

ALTER TABLE uk.uk_price_paid_with_projections_v2
    ADD PROJECTION projection_by_year_district_town
    (
        SELECT
            year,
            district,
            town,
            avg(price),
            sum(price),
            count()
        GROUP BY
            year,
            district,
            town
    )

ALTER TABLE uk.uk_price_paid_with_projections_v2
    MATERIALIZE PROJECTION projection_by_year_district_town
SETTINGS mutations_sync = 1

CREATE TABLE page_views
(
    id UInt64,
    event_date Date,
    user_id UInt32,
    url String,
    region String,
    PROJECTION region_proj
    (
        SELECT _part_offset ORDER BY region
    ),
    PROJECTION user_id_proj
    (
        SELECT _part_offset ORDER BY user_id
    )
)
ENGINE = MergeTree
ORDER BY (event_date, id)
SETTINGS
  index_granularity = 1, -- granuleあたり1行
  max_bytes_to_merge_at_max_space_in_pool = 1; -- mergeを無効化

INSERT INTO page_views VALUES (
1, '2025-07-01', 101, 'https://example.com/page1', 'europe');
INSERT INTO page_views VALUES (
2, '2025-07-01', 102, 'https://example.com/page2', 'us_west');
INSERT INTO page_views VALUES (
3, '2025-07-02', 106, 'https://example.com/page3', 'us_west');
INSERT INTO page_views VALUES (
4, '2025-07-02', 107, 'https://example.com/page4', 'us_west');
INSERT INTO page_views VALUES (
5, '2025-07-03', 104, 'https://example.com/page5', 'asia');

EXPLAIN projections=1
SELECT * FROM page_views WHERE region = 'us_west' AND user_id = 107;

    ┌─explain────────────────────────────────────────────────────────────────────────────────┐
 1. │ Expression ((Project names + Projection))                                              │
 2. │   Expression                                                                           │                                                                        
 3. │     ReadFromMergeTree (default.page_views)                                             │
 4. │     Projections:                                                                       │
 5. │       Name: region_proj                                                                │
 6. │         Description: Projection has been analyzed and is used for part-level filtering │
 7. │         Condition: (region in ['us_west', 'us_west'])                                  │
 8. │         Search Algorithm: binary search                                                │
 9. │         Parts: 3                                                                       │
10. │         Marks: 3                                                                       │
11. │         Ranges: 3                                                                      │
12. │         Rows: 3                                                                        │
13. │         Filtered Parts: 2                                                              │
14. │       Name: user_id_proj                                                               │
15. │         Description: Projection has been analyzed and is used for part-level filtering │
16. │         Condition: (user_id in [107, 107])                                             │
17. │         Search Algorithm: binary search                                                │
18. │         Parts: 1                                                                       │
19. │         Marks: 1                                                                       │
20. │         Ranges: 1                                                                      │
21. │         Rows: 1                                                                        │
22. │         Filtered Parts: 2                                                              │
    └────────────────────────────────────────────────────────────────────────────────────────┘