PostgreSQL क्वेरी इंडेक्स स्कैन के साथ तेजी से चलती है, लेकिन इंजन हैश जॉइन चुनता है

मेरा अनुमान है कि आप डिफ़ॉल्ट random_page_cost = 4 . का उपयोग कर रहे हैं , जो बहुत अधिक है, जिससे अनुक्रमणिका स्कैन बहुत महंगा हो जाता है।

मैं इस स्क्रिप्ट के साथ 2 टेबल को फिर से बनाने की कोशिश करता हूं:

CREATE TABLE replays_game (
    id integer NOT NULL,
    PRIMARY KEY (id)
);

CREATE TABLE replays_playeringame (
    player_id integer NOT NULL,
    game_id integer NOT NULL,
    PRIMARY KEY (player_id, game_id),
    CONSTRAINT replays_playeringame_game_fkey
        FOREIGN KEY (game_id) REFERENCES replays_game (id)
);

CREATE INDEX ix_replays_playeringame_game_id
    ON replays_playeringame (game_id);

-- 150k games
INSERT INTO replays_game
SELECT generate_series(1, 150000);

-- ~150k players, ~2 games each
INSERT INTO replays_playeringame
select trunc(random() * 149999 + 1), generate_series(1, 150000);

INSERT INTO replays_playeringame
SELECT *
FROM
    (
        SELECT
            trunc(random() * 149999 + 1) as player_id,
            generate_series(1, 150000) as game_id
    ) AS t
WHERE
    NOT EXISTS (
        SELECT 1
        FROM replays_playeringame
        WHERE
            t.player_id = replays_playeringame.player_id
            AND t.game_id = replays_playeringame.game_id
    )
;

-- the heavy player with 3000 games
INSERT INTO replays_playeringame
select 999999, generate_series(1, 3000);

4 के डिफ़ॉल्ट मान के साथ:

game=# set random_page_cost = 4;
SET
game=# explain analyse SELECT "replays_game".*
FROM "replays_game"
INNER JOIN "replays_playeringame" ON "replays_game"."id" = "replays_playeringame"."game_id"
WHERE "replays_playeringame"."player_id" = 999999;
                                                                     QUERY PLAN                                                                      
-----------------------------------------------------------------------------------------------------------------------------------------------------
 Hash Join  (cost=1483.54..4802.54 rows=3000 width=4) (actual time=3.640..110.212 rows=3000 loops=1)
   Hash Cond: (replays_game.id = replays_playeringame.game_id)
   ->  Seq Scan on replays_game  (cost=0.00..2164.00 rows=150000 width=4) (actual time=0.012..34.261 rows=150000 loops=1)
   ->  Hash  (cost=1446.04..1446.04 rows=3000 width=4) (actual time=3.598..3.598 rows=3000 loops=1)
         Buckets: 1024  Batches: 1  Memory Usage: 106kB
         ->  Bitmap Heap Scan on replays_playeringame  (cost=67.54..1446.04 rows=3000 width=4) (actual time=0.586..2.041 rows=3000 loops=1)
               Recheck Cond: (player_id = 999999)
               ->  Bitmap Index Scan on replays_playeringame_pkey  (cost=0.00..66.79 rows=3000 width=0) (actual time=0.560..0.560 rows=3000 loops=1)
                     Index Cond: (player_id = 999999)
 Total runtime: 110.621 ms

इसे 2 पर कम करने के बाद:

game=# set random_page_cost = 2;
SET
game=# explain analyse SELECT "replays_game".*
FROM "replays_game"
INNER JOIN "replays_playeringame" ON "replays_game"."id" = "replays_playeringame"."game_id"
WHERE "replays_playeringame"."player_id" = 999999;
                                                                  QUERY PLAN                                                                   
-----------------------------------------------------------------------------------------------------------------------------------------------
 Nested Loop  (cost=45.52..4444.86 rows=3000 width=4) (actual time=0.418..27.741 rows=3000 loops=1)
   ->  Bitmap Heap Scan on replays_playeringame  (cost=45.52..1424.02 rows=3000 width=4) (actual time=0.406..1.502 rows=3000 loops=1)
         Recheck Cond: (player_id = 999999)
         ->  Bitmap Index Scan on replays_playeringame_pkey  (cost=0.00..44.77 rows=3000 width=0) (actual time=0.388..0.388 rows=3000 loops=1)
               Index Cond: (player_id = 999999)
   ->  Index Scan using replays_game_pkey on replays_game  (cost=0.00..0.99 rows=1 width=4) (actual time=0.006..0.006 rows=1 loops=3000)
         Index Cond: (id = replays_playeringame.game_id)
 Total runtime: 28.542 ms
(8 rows)

अगर SSD का उपयोग करते हैं, तो मैं इसे और कम करके 1.1 कर दूंगा।

आपके अंतिम प्रश्न के लिए, मुझे सच में लगता है कि आपको पोस्टग्रेस्क्ल के साथ रहना चाहिए। मेरे पास postgresql और mssql के साथ अनुभव है, और मुझे बाद के प्रयासों के साथ-साथ पूर्व के आधे प्रदर्शन के लिए तीन गुना प्रयास करने की आवश्यकता है।