Mysql查詢優化

Question

我有一張近700萬行的表。這裏的表結構

`CREATE TABLE `ERS_SALES_TRANSACTIONS` (
    `saleId` int(12) NOT NULL AUTO_INCREMENT, 
    `ERS_COMPANY_CODE` int(3) DEFAULT NULL, 
    `SALE_SECTION` varchar(128) DEFAULT NULL, 
    `SALE_DATE` date DEFAULT NULL, 
    `SALE_STOCKAGE_EXACT` int(4) DEFAULT NULL, 
    `SALE_NET_AMOUNT` decimal(11,2) DEFAULT NULL, 
    `SALE_ABSOLUTE_CDATE` date DEFAULT NULL, 
    PRIMARY KEY (`saleId`), 
    KEY `index_location` (`ERS_COMPANY_CODE`), 
    KEY `idx-erscode-salesec` (`SALE_SECTION`,`ERS_COMPANY_CODE`) USING BTREE, 
    KEY `idx-saledate-section` (`SALE_DATE`,`SALE_SECTION`) USING BTREE 
    KEY `idx_quick_sales_transactions` (`ERS_COMPANY_CODE`,`SALE_SECTION`,`SALE_DATE`,`SALE_STOCKAGE_EXACT`,`SALE_NET_AMOUNT`) 
) ENGINE=InnoDB; 

這個查詢是花了超過7秒執行，有沒有什麼辦法來加速呢？

SELECT 
    A.SALE_SECTION, 
    SUM(IF(A.SALE_DATE BETWEEN '2016-01-16' AND '2016-04-30' 
      AND A.SALE_STOCKAGE_EXACT BETWEEN 0 AND 90, A.SALE_NET_AMOUNT, 0)) AS fs1_pd1_sale, 
    SUM(IF(A.SALE_DATE BETWEEN '2016-01-16' AND '2016-04-30' 
      AND A.SALE_STOCKAGE_EXACT BETWEEN 91 AND 180, A.SALE_NET_AMOUNT, 0)) AS fs2_pd1_sale, 
    SUM(IF(A.SALE_DATE BETWEEN '2016-01-16' AND '2016-04-30' 
      AND A.SALE_STOCKAGE_EXACT BETWEEN 181 AND 365, A.SALE_NET_AMOUNT, 0)) AS os1_pd1_sale, 
    SUM(IF(A.SALE_DATE BETWEEN '2016-01-16' AND '2016-04-30' 
      AND A.SALE_STOCKAGE_EXACT BETWEEN 366 AND 9999, A.SALE_NET_AMOUNT, 0)) AS os2_pd1_sale, 
    SUM(IF(A.SALE_DATE BETWEEN '2016-01-16' AND '2016-04-30', A.SALE_NET_AMOUNT, 0)) AS TOTAL_PD1_SALE, 
    SUM(IF(A.SALE_DATE BETWEEN '2016-04-01' AND '2016-04-30' 
      AND A.SALE_STOCKAGE_EXACT BETWEEN 0 AND 90, A.SALE_NET_AMOUNT, 0)) AS fs1_pd2_sale, 
    SUM(IF(A.SALE_DATE BETWEEN '2016-04-01' AND '2016-04-30' 
      AND A.SALE_STOCKAGE_EXACT BETWEEN 91 AND 180, A.SALE_NET_AMOUNT, 0)) AS fs2_pd2_sale, 
    SUM(IF(A.SALE_DATE BETWEEN '2016-04-01' AND '2016-04-30' 
      AND A.SALE_STOCKAGE_EXACT BETWEEN 181 AND 365, A.SALE_NET_AMOUNT, 0)) AS os1_pd2_sale, 
    SUM(IF(A.SALE_DATE BETWEEN '2016-04-01' AND '2016-04-30' 
      AND A.SALE_STOCKAGE_EXACT BETWEEN 366 AND 9999, A.SALE_NET_AMOUNT, 0)) AS os2_pd2_sale, 
    SUM(IF(A.SALE_DATE BETWEEN '2016-04-01' AND '2016-04-30', A.SALE_NET_AMOUNT, 0)) AS TOTAL_PD2_SALE, 
    SUM(IF(A.SALE_DATE BETWEEN '2016-05-01' AND '2016-05-31' 
      AND A.SALE_ABSOLUTE_CDATE BETWEEN '2016-03-01' AND '2016-05-31', A.SALE_NET_AMOUNT, 0)) AS fs1_achived_sale, 
    SUM(IF(A.SALE_DATE BETWEEN '2016-05-01' AND '2016-05-31' 
      AND A.SALE_ABSOLUTE_CDATE BETWEEN '2015-12-01' AND '2016-02-29', A.SALE_NET_AMOUNT, 0)) AS fs2_achived_sale, 
    SUM(IF(A.SALE_DATE BETWEEN '2016-05-01' AND '2016-05-31' 
      AND A.SALE_ABSOLUTE_CDATE BETWEEN '2015-06-01' AND '2015-11-30', A.SALE_NET_AMOUNT, 0)) AS os1_achived_sale, 
    SUM(IF(A.SALE_DATE BETWEEN '2016-05-01' AND '2016-05-31' 
      AND A.SALE_ABSOLUTE_CDATE BETWEEN '2006-12-26' AND '2015-05-31', A.SALE_NET_AMOUNT, 0)) AS os2_achived_sale, 
    SUM(IF(A.SALE_DATE BETWEEN '2016-05-01' AND '2016-05-31', A.SALE_NET_AMOUNT, 0)) AS Total_ACHIVED_SALE 
    FROM ERS_SALES_TRANSACTIONS A WHERE A.ERS_COMPANY_CODE = 48 GROUP BY A.SALE_SECTION 

這裏的解釋查詢

{ 
"data": 
[ 
    { 
     "id": 1, 
     "select_type": "SIMPLE", 
     "table": "A", 
     "type": "ref", 
     "possible_keys": "index_location,idx-erscode-salesec,idx-saledate-section", 
     "key": "index_location", 
     "key_len": "5", 
     "ref": "const", 
     "rows": 1411944, 
     "Extra": "Using where; Using temporary; Using filesort" 
    } 
] 
} 

加入複合索引之後，時間減少到4.03秒。下面是該計劃

{ 
"data": 
[ 
    { 
     "id": 1, 
     "select_type": "SIMPLE", 
     "table": "A", 
     "type": "ref", 
     "possible_keys": "index_location,idx-erscode-salesec,idx-saledate-section,idx_quick_sales_transactions", 
     "key_len": "5", 
     "key": "idx_quick_sales_transactions", 
     "ref": "const", 
     "rows": 1306058, 
     "Extra": "Using where" 
    } 
] 

}

Answer 1

我不同意吉米B在這裏。在我看來，你的查詢看起來很完美。

根據公司48有多少條記錄，應該按順序讀取整個表（當它的數量是所有表記錄的50％時）或者應該使用ERS_COMPANY_CODE上的索引（當它不是那麼多時，比例只有所有記錄的1％）。

由於DBMS決定使用ERS_COMPANY_CODE上的索引，所以後者應該是這種情況。

您可以嘗試通過創建組合索引來進一步加快查詢速度。至少做到這一點(ERS_COMPANY_CODE , SALE_SECTION)，以便讓GROUP BY更快。甚至可以添加所有字段，因此可以從索引收集所有數據，並且不必再訪問表本身。

CREATE INDEX idx_quick_sales_transactions ON ERS_SALES_TRANSACTIONS 
    (ERS_COMPANY_CODE, SALE_SECTION, SALE_DATE, SALE_STOCKAGE_EXACT, SALE_NET_AMOUNT); 

Answer 2

SELECT 
    sales.SALE_SECTION, 
    SUM(fs1_pd1.SALE_NET_AMOUNT) AS fs1_pd1_sale, 
    SUM(fs2_pd1.SALE_NET_AMOUNT) AS fs2_pd1_sale, 
... 
FROM ERS_SALES_TRANSACTIONS sales 

LEFT OUTER JOIN ERS_SALES_TRANSACTIONS fs1_pd1 ON sales.ERS_COMPANY_CODE = fs1_pd1.ERS_COMPANY_CODE AND sales.SALE_SECTION = fs1_pd1.SALE_SECTION 
    AND fs1_pd1.SALE_DATE BETWEEN '2016-01-16' AND '2016-04-30' 
    AND fs1_pd1.SALE_STOCKAGE_EXACT BETWEEN 0 AND 90 

LEFT OUTER JOIN ERS_SALES_TRANSACTIONS fs2_pd1 ON sales.ERS_COMPANY_CODE = fs2_pd1.ERS_COMPANY_CODE AND sales.SALE_SECTION = fs2_pd1.SALE_SECTION 
    AND fs2_pd1.SALE_DATE BETWEEN '2016-01-16' AND '2016-04-30' 
    AND fs2_pd1.SALE_STOCKAGE_EXACT BETWEEN 91 AND 180 
... 
    WHERE sales.ERS_COMPANY_CODE = 48 
    GROUP BY sales.SALE_SECTION 

這種方式，優化器可以使用多個索引進行查詢。

但是，我建議，首先嚐試複合索引@Thorsten Kettner建議，因爲這樣可以達到相同的效果，但複雜程度要低得多。

Answer 3

我不知道是否有辦法加快速度。但是，你可以嘗試使用索引。我會推薦一個ERS_SALES_TRANSACTIONS(ERS_COMPANY_CODE, SALE_SECTION, SALE_DATE, SALE_NET_AMOUNT)。

這是查詢的覆蓋索引，這意味着用於查詢的所有列位於索引中 - 因此數據庫引擎不需要訪問原始數據頁面。

但是，性能仍然取決於與特定公司代碼匹配的行數。特別是，用於聚合的文件排序的性能。