मैं निम्न क्वेरीPostgreSQL: निचली सीमा, धीमी क्वेरी
SELECT translation.id
FROM "TRANSLATION" translation
INNER JOIN "UNIT" unit
ON translation.fk_id_unit = unit.id
INNER JOIN "DOCUMENT" document
ON unit.fk_id_document = document.id
WHERE document.fk_id_job = 3665
ORDER BY translation.id asc
LIMIT 50
यह भयानक 110 सेकंड के लिए चलाता है।
तालिका आकार:
+----------------+-------------+
| Table | Records |
+----------------+-------------+
| TRANSLATION | 6,906,679 |
| UNIT | 6,906,679 |
| DOCUMENT | 42,321 |
+----------------+-------------+
हालांकि, जब मैं 50 से 1000 करने के लिए LIMIT
पैरामीटर बदलने के लिए, क्वेरी 2 सेकंड में खत्म।
यहाँ धीमी गति से एक
Limit (cost=0.00..146071.52 rows=50 width=8) (actual time=111916.180..111917.626 rows=50 loops=1)
-> Nested Loop (cost=0.00..50748166.14 rows=17371 width=8) (actual time=111916.179..111917.624 rows=50 loops=1)
Join Filter: (unit.fk_id_document = document.id)
-> Nested Loop (cost=0.00..39720545.91 rows=5655119 width=16) (actual time=0.051..15292.943 rows=5624514 loops=1)
-> Index Scan using "TRANSLATION_pkey" on "TRANSLATION" translation (cost=0.00..7052806.78 rows=5655119 width=16) (actual time=0.039..1887.757 rows=5624514 loops=1)
-> Index Scan using "UNIT_pkey" on "UNIT" unit (cost=0.00..5.76 rows=1 width=16) (actual time=0.002..0.002 rows=1 loops=5624514)
Index Cond: (unit.id = translation.fk_id_translation_unit)
-> Materialize (cost=0.00..138.51 rows=130 width=8) (actual time=0.000..0.006 rows=119 loops=5624514)
-> Index Scan using "DOCUMENT_idx_job" on "DOCUMENT" document (cost=0.00..137.86 rows=130 width=8) (actual time=0.025..0.184 rows=119 loops=1)
Index Cond: (fk_id_job = 3665)
के लिए और तेजी से एक
Limit (cost=523198.17..523200.67 rows=1000 width=8) (actual time=2274.830..2274.988 rows=1000 loops=1)
-> Sort (cost=523198.17..523241.60 rows=17371 width=8) (actual time=2274.829..2274.895 rows=1000 loops=1)
Sort Key: translation.id
Sort Method: top-N heapsort Memory: 95kB
-> Nested Loop (cost=139.48..522245.74 rows=17371 width=8) (actual time=0.095..2252.710 rows=97915 loops=1)
-> Hash Join (cost=139.48..420861.93 rows=17551 width=8) (actual time=0.079..2005.238 rows=97915 loops=1)
Hash Cond: (unit.fk_id_document = document.id)
-> Seq Scan on "UNIT" unit (cost=0.00..399120.41 rows=5713741 width=16) (actual time=0.008..1200.547 rows=6908070 loops=1)
-> Hash (cost=137.86..137.86 rows=130 width=8) (actual time=0.065..0.065 rows=119 loops=1)
Buckets: 1024 Batches: 1 Memory Usage: 5kB
-> Index Scan using "DOCUMENT_idx_job" on "DOCUMENT" document (cost=0.00..137.86 rows=130 width=8) (actual time=0.009..0.041 rows=119 loops=1)
Index Cond: (fk_id_job = 3665)
-> Index Scan using "TRANSLATION_idx_unit" on "TRANSLATION" translation (cost=0.00..5.76 rows=1 width=16) (actual time=0.002..0.002 rows=1 loops=97915)
Index Cond: (translation.fk_id_translation_unit = unit.id)
जाहिर निष्पादन की योजना बहुत अलग हैं और एक प्रश्न में दूसरा एक परिणाम 50 बार के लिए क्वेरी योजना है तेज़।
मैं सभी क्वेरी में शामिल क्षेत्रों सूचक है और मैं सिर्फ प्रश्नों को चलाने से पहले सभी टेबल पर ANALYZE
भाग गया।
किसी को देख सकते हैं क्या पहली क्वेरी के साथ गलत क्या है?
अद्यतन: टेबल परिभाषाओं
CREATE TABLE "public"."TRANSLATION" (
"id" BIGINT NOT NULL,
"fk_id_translation_unit" BIGINT NOT NULL,
"translation" TEXT NOT NULL,
"fk_id_language" INTEGER NOT NULL,
"relevance" INTEGER,
CONSTRAINT "TRANSLATION_pkey" PRIMARY KEY("id"),
CONSTRAINT "TRANSLATION_fk" FOREIGN KEY ("fk_id_translation_unit")
REFERENCES "public"."UNIT"("id")
ON DELETE CASCADE
ON UPDATE NO ACTION
DEFERRABLE
INITIALLY DEFERRED,
CONSTRAINT "TRANSLATION_fk1" FOREIGN KEY ("fk_id_language")
REFERENCES "public"."LANGUAGE"("id")
ON DELETE NO ACTION
ON UPDATE NO ACTION
NOT DEFERRABLE
) WITHOUT OIDS;
CREATE INDEX "TRANSLATION_idx_unit" ON "public"."TRANSLATION"
USING btree ("fk_id_translation_unit");
CREATE INDEX "TRANSLATION_language_idx" ON "public"."TRANSLATION"
USING hash ("translation");
CREATE TABLE "public"."UNIT" (
"id" BIGINT NOT NULL,
"text" TEXT NOT NULL,
"fk_id_language" INTEGER NOT NULL,
"fk_id_document" BIGINT NOT NULL,
"word_count" INTEGER DEFAULT 0,
CONSTRAINT "UNIT_pkey" PRIMARY KEY("id"),
CONSTRAINT "UNIT_fk" FOREIGN KEY ("fk_id_document")
REFERENCES "public"."DOCUMENT"("id")
ON DELETE CASCADE
ON UPDATE NO ACTION
NOT DEFERRABLE,
CONSTRAINT "UNIT_fk1" FOREIGN KEY ("fk_id_language")
REFERENCES "public"."LANGUAGE"("id")
ON DELETE NO ACTION
ON UPDATE NO ACTION
NOT DEFERRABLE
) WITHOUT OIDS;
CREATE INDEX "UNIT_idx_document" ON "public"."UNIT"
USING btree ("fk_id_document");
CREATE INDEX "UNIT_text_idx" ON "public"."UNIT"
USING hash ("text");
CREATE TABLE "public"."DOCUMENT" (
"id" BIGINT NOT NULL,
"fk_id_job" BIGINT,
CONSTRAINT "DOCUMENT_pkey" PRIMARY KEY("id"),
CONSTRAINT "DOCUMENT_fk" FOREIGN KEY ("fk_id_job")
REFERENCES "public"."JOB"("id")
ON DELETE SET NULL
ON UPDATE NO ACTION
NOT DEFERRABLE
) WITHOUT OIDS;
अद्यतन: डेटाबेस मानकों
shared_buffers = 2048MB
effective_cache_size = 4096MB
work_mem = 32MB
Total memory: 32GB
CPU: Intel Xeon X3470 @ 2.93 GHz, 8MB cache
क्या आप तालिका परिभाषा पोस्ट कर सकते हैं? –
@JohnTotetWoo – twoflower
अपडेट किया गया है क्या आपका इंस्टॉल बिल्कुल ट्यून किया गया है? Shared_buffers, effect_cache_size, work_mem, और आपके सिस्टम चश्मा के लिए सेटिंग्स क्या हैं? – eevar