PostgreSQL
 sql >> Base de données >  >> RDS >> PostgreSQL

Requête agrégée sur une table de plus de 50 millions de lignes dans PostgreSQL

Première étape :effectuer une pré-agrégation dans la sous-requête :

EXPLAIN
SELECT cal.theday, act.action_name, SUM(sub.the_count)
FROM generate_series(current_date - interval '1 week', now(), interval '1 
day') as cal(theday) -- calendar pseudo-table
CROSS JOIN (VALUES
        ('page_open')
        , ('product_add') , ('product_buy') , ('product_event')
        , ('product_favourite') , ('product_open') , ('product_share') , ('session_start')
        ) AS act(action_name)
LEFT JOIN (
        SELECT es.action_name, date_trunc('day',es.date_update) as theday
                , COUNT(DISTINCT es.id ) AS the_count
        FROM event_statistics as es
        WHERE es.client_id = (SELECT c.id FROM clients AS c
                        WHERE c.client_name = 'client name')
        AND (es.date_update BETWEEN (current_date - interval '1 week') AND now())
        GROUP BY 1,2
        ) sub ON cal.theday = sub.theday AND act.action_name = sub.action_name
GROUP BY act.action_name,cal.theday
ORDER BY act.action_name,cal.theday
        ;

Étape suivante :placez VALUES dans un CTE et faites-y également référence dans la sous-requête agrégée. (le gain dépend du nombre de noms d'action pouvant être ignorés)

EXPLAIN
WITH act(action_name) AS (VALUES
        ('page_open')
        , ('product_add') , ('product_buy') , ('product_event')
        , ('product_favourite') , ('product_open') , ('product_share') , ('session_start')
        )
SELECT cal.theday, act.action_name, SUM(sub.the_count)
FROM generate_series(current_date - interval '1 week', now(), interval '1day') AS cal(theday)
CROSS JOIN act
LEFT JOIN (
        SELECT es.action_name, date_trunc('day',es.date_update) AS theday
                , COUNT(DISTINCT es.id ) AS the_count
        FROM event_statistics AS es
        WHERE es.date_update BETWEEN (current_date - interval '1 week') AND now()
        AND EXISTS (SELECT * FROM clients cli  WHERE cli.id= es.client_id AND cli.client_name = 'client name')
        AND EXISTS (SELECT * FROM act WHERE act.action_name = es.action_name)
        GROUP BY 1,2
        ) sub ON cal.theday = sub.theday AND act.action_name = sub.action_name
GROUP BY act.action_name,cal.theday
ORDER BY act.action_name,cal.theday
        ;

MISE À JOUR :l'utilisation d'une table physique (temp) se traduira par de meilleures estimations.

    -- Final attempt: materialize the carthesian product (timeseries*action_name)
    -- into a temp table
CREATE TEMP TABLE grid AS
(SELECT act.action_name, cal.theday
FROM generate_series(current_date - interval '1 week', now(), interval '1 day')
    AS cal(theday)
CROSS JOIN
    (VALUES ('page_open')
        , ('product_add') , ('product_buy') , ('product_event')
        , ('product_favourite') , ('product_open') , ('product_share') , ('session_start')
        ) act(action_name)
    );
CREATE UNIQUE INDEX ON grid(action_name, theday);

    -- Index will force statistics to be collected
    -- ,and will generate better estimates for the numbers of rows
CREATE INDEX iii ON event_statistics (action_name, date_update ) ;
VACUUM ANALYZE grid;
VACUUM ANALYZE event_statistics;

EXPLAIN
SELECT grid.action_name, grid.theday, SUM(sub.the_count) AS the_count
FROM grid
LEFT JOIN (
        SELECT es.action_name, date_trunc('day',es.date_update) AS theday
                , COUNT(*) AS the_count
        FROM event_statistics AS es
        WHERE es.date_update BETWEEN (current_date - interval '1 week') AND now()
        AND EXISTS (SELECT * FROM clients cli  WHERE cli.id= es.client_id AND cli.client_name = 'client name')
        -- AND EXISTS (SELECT * FROM grid WHERE grid.action_name = es.action_name)
        GROUP BY 1,2
        ORDER BY 1,2 --nonsense!
        ) sub ON grid.theday = sub.theday AND grid.action_name = sub.action_name
GROUP BY grid.action_name,grid.theday
ORDER BY grid.action_name,grid.theday
        ;

Mise à jour #3 (désolé, je crée des index sur la ou les tables de base ici, vous devrez les modifier. J'ai également supprimé les colonnes sur l'horodatage)

    -- attempt#4:
    -- - materialize the carthesian product (timeseries*action_name)
    -- - sanitize date interval -logic

CREATE TEMP TABLE grid AS
(SELECT act.action_name, cal.theday::date
FROM generate_series(current_date - interval '1 week', now(), interval '1 day')
    AS cal(theday)
CROSS JOIN
    (VALUES ('page_open')
        , ('product_add') , ('product_buy') , ('product_event')
        , ('product_favourite') , ('product_open') , ('product_share') , ('session_start')
        ) act(action_name)
    );

    -- Index will force statistics to be collected
    -- ,and will generate better estimates for the numbers of rows
-- CREATE UNIQUE INDEX ON grid(action_name, theday);
-- CREATE INDEX iii ON event_statistics (action_name, date_update ) ;
CREATE UNIQUE INDEX ON grid(theday, action_name);
CREATE INDEX iii ON event_statistics (date_update, action_name) ;
VACUUM ANALYZE grid;
VACUUM ANALYZE event_statistics;

EXPLAIN
SELECT gr.action_name, gr.theday
            , COUNT(*) AS the_count
FROM grid gr
LEFT JOIN event_statistics AS es
    ON es.action_name = gr.action_name
    AND date_trunc('day',es.date_update)::date = gr.theday
    AND es.date_update BETWEEN (current_date - interval '1 week') AND current_date
JOIN clients cli  ON cli.id= es.client_id AND cli.client_name = 'client name'
GROUP BY gr.action_name,gr.theday
ORDER BY 1,2
        ;
                                                                        QUERY PLAN                                                                        
----------------------------------------------------------------------------------------------------------------------------------------------------------
 GroupAggregate  (cost=8.33..8.35 rows=1 width=17)
   Group Key: gr.action_name, gr.theday
   ->  Sort  (cost=8.33..8.34 rows=1 width=17)
         Sort Key: gr.action_name, gr.theday
         ->  Nested Loop  (cost=1.40..8.33 rows=1 width=17)
               ->  Nested Loop  (cost=1.31..7.78 rows=1 width=40)
                     Join Filter: (es.client_id = cli.id)
                     ->  Index Scan using clients_client_name_key on clients cli  (cost=0.09..2.30 rows=1 width=4)
                           Index Cond: (client_name = 'client name'::text)
                     ->  Bitmap Heap Scan on event_statistics es  (cost=1.22..5.45 rows=5 width=44)
                           Recheck Cond: ((date_update >= (('now'::cstring)::date - '7 days'::interval)) AND (date_update <= ('now'::cstring)::date))
                           ->  Bitmap Index Scan on iii  (cost=0.00..1.22 rows=5 width=0)
                                 Index Cond: ((date_update >= (('now'::cstring)::date - '7 days'::interval)) AND (date_update <= ('now'::cstring)::date))
               ->  Index Only Scan using grid_theday_action_name_idx on grid gr  (cost=0.09..0.54 rows=1 width=17)
                     Index Cond: ((theday = (date_trunc('day'::text, es.date_update))::date) AND (action_name = es.action_name))
(15 rows)