[NSE-108] Add end-to-end test suite against TPC-DS (#109)

Close #108

.github/workflows/report_ram_log.yml

@@ -62,7 +62,7 @@ jobs:
       - name: Run Maven tests
         run: |
           cd core/
-          mvn test -B -DmembersOnlySuites=com.intel.oap.tpch -Dorg.slf4j.simpleLogger.log.org.apache.maven.cli.transfer.Slf4jMavenTransferListener=warn -DtagsToInclude=com.intel.oap.tags.CommentOnContextPR -Dexec.skip=true
+          mvn test -B -DmembersOnlySuites=com.intel.oap.tpc.h -Dorg.slf4j.simpleLogger.log.org.apache.maven.cli.transfer.Slf4jMavenTransferListener=warn -DtagsToInclude=com.intel.oap.tags.CommentOnContextPR -Dexec.skip=true
         env:
           MAVEN_OPTS: "-Xmx2048m"
           COMMENT_CONTENT_PATH: "/tmp/comment.md"

.github/workflows/tpch.yml

@@ -56,7 +56,7 @@ jobs:
       - name: Run Maven tests - BHJ
         run: |
           cd core/
-          mvn test -B -Dorg.slf4j.simpleLogger.log.org.apache.maven.cli.transfer.Slf4jMavenTransferListener=warn -DmembersOnlySuites=com.intel.oap.tpch -DtagsToInclude=com.intel.oap.tags.BroadcastHashJoinMode -DargLine="-Xmx1G -XX:MaxDirectMemorySize=500M -Dio.netty.allocator.numDirectArena=1"
+          mvn test -B -Dorg.slf4j.simpleLogger.log.org.apache.maven.cli.transfer.Slf4jMavenTransferListener=warn -DmembersOnlySuites=com.intel.oap.tpc.h -DtagsToInclude=com.intel.oap.tags.BroadcastHashJoinMode -DargLine="-Xmx1G -XX:MaxDirectMemorySize=500M -Dio.netty.allocator.numDirectArena=1"
         env:
           MALLOC_ARENA_MAX: "4"
           MAVEN_OPTS: "-Xmx1G"
@@ -66,7 +66,7 @@ jobs:
       - name: Run Maven tests - SMJ
         run: |
           cd core/
-          mvn test -B -Dorg.slf4j.simpleLogger.log.org.apache.maven.cli.transfer.Slf4jMavenTransferListener=warn -DmembersOnlySuites=com.intel.oap.tpch -DtagsToInclude=com.intel.oap.tags.SortMergeJoinMode -DargLine="-Xmx1G -XX:MaxDirectMemorySize=500M -Dio.netty.allocator.numDirectArena=1"
+          mvn test -B -Dorg.slf4j.simpleLogger.log.org.apache.maven.cli.transfer.Slf4jMavenTransferListener=warn -DmembersOnlySuites=com.intel.oap.tpc.h -DtagsToInclude=com.intel.oap.tags.SortMergeJoinMode -DargLine="-Xmx1G -XX:MaxDirectMemorySize=500M -Dio.netty.allocator.numDirectArena=1"
         env:
           MALLOC_ARENA_MAX: "4"
           MAVEN_OPTS: "-Xmx1G"
@@ -86,3 +86,4 @@ jobs:
         with:
           name: pr_event
           path: ${{steps.output-envs.outputs.event_path}}
+

core/pom.xml

@@ -226,9 +226,15 @@
       <scope>test</scope>
     </dependency>
     <dependency>
-      <groupId>io.prestosql.tpch</groupId>
+      <groupId>io.trino.tpch</groupId>
       <artifactId>tpch</artifactId>
-      <version>1.0</version>
+      <version>1.1</version>
+      <scope>test</scope>
+    </dependency>
+    <dependency>
+      <groupId>io.trino.tpcds</groupId>
+      <artifactId>tpcds</artifactId>
+      <version>1.4</version>
       <scope>test</scope>
     </dependency>
     <dependency>

core/src/test/java/com/intel/oap/tpch/MallocUtils.java → core/src/test/java/com/intel/oap/tpc/MallocUtils.java

@@ -15,7 +15,7 @@
  * limitations under the License.
  */
 
-package com.intel.oap.tpch;
+package com.intel.oap.tpc;
 
 import com.intel.oap.vectorized.JniUtils;
 
@@ -35,10 +35,10 @@ public class MallocUtils {
    * Visible for testing: Try turning back allocated native memory to OS. This might have no effect
    * when using Jemalloc.
    */
-  static native void mallocTrim();
+  public static native void mallocTrim();
 
   /**
    * Visible for testing: Print malloc statistics.
    */
-  static native void mallocStats();
+  public static native void mallocStats();
 }

core/src/test/resources/tpcds-queries-double/q1.sql

@@ -0,0 +1,19 @@
+WITH customer_total_return AS
+( SELECT
+    sr_customer_sk AS ctr_customer_sk,
+    sr_store_sk AS ctr_store_sk,
+    sum(sr_return_amt) AS ctr_total_return
+  FROM store_returns, date_dim
+  WHERE sr_returned_date_sk = d_date_sk AND d_year = 2000
+  GROUP BY sr_customer_sk, sr_store_sk)
+SELECT c_customer_id
+FROM customer_total_return ctr1, store, customer
+WHERE ctr1.ctr_total_return >
+  (SELECT avg(ctr_total_return) * 1.2
+  FROM customer_total_return ctr2
+  WHERE ctr1.ctr_store_sk = ctr2.ctr_store_sk)
+  AND s_store_sk = ctr1.ctr_store_sk
+  AND s_state = 'TN'
+  AND ctr1.ctr_customer_sk = c_customer_sk
+ORDER BY c_customer_id
+LIMIT 100

core/src/test/resources/tpcds-queries-double/q10.sql

@@ -0,0 +1,57 @@
+SELECT
+  cd_gender,
+  cd_marital_status,
+  cd_education_status,
+  count(*) cnt1,
+  cd_purchase_estimate,
+  count(*) cnt2,
+  cd_credit_rating,
+  count(*) cnt3,
+  cd_dep_count,
+  count(*) cnt4,
+  cd_dep_employed_count,
+  count(*) cnt5,
+  cd_dep_college_count,
+  count(*) cnt6
+FROM
+  customer c, customer_address ca, customer_demographics
+WHERE
+  c.c_current_addr_sk = ca.ca_address_sk AND
+    ca_county IN ('Rush County', 'Toole County', 'Jefferson County',
+                  'Dona Ana County', 'La Porte County') AND
+    cd_demo_sk = c.c_current_cdemo_sk AND
+    exists(SELECT *
+           FROM store_sales, date_dim
+           WHERE c.c_customer_sk = ss_customer_sk AND
+             ss_sold_date_sk = d_date_sk AND
+             d_year = 2002 AND
+             d_moy BETWEEN 1 AND 1 + 3) AND
+    (exists(SELECT *
+            FROM web_sales, date_dim
+            WHERE c.c_customer_sk = ws_bill_customer_sk AND
+              ws_sold_date_sk = d_date_sk AND
+              d_year = 2002 AND
+              d_moy BETWEEN 1 AND 1 + 3) OR
+      exists(SELECT *
+             FROM catalog_sales, date_dim
+             WHERE c.c_customer_sk = cs_ship_customer_sk AND
+               cs_sold_date_sk = d_date_sk AND
+               d_year = 2002 AND
+               d_moy BETWEEN 1 AND 1 + 3))
+GROUP BY cd_gender,
+  cd_marital_status,
+  cd_education_status,
+  cd_purchase_estimate,
+  cd_credit_rating,
+  cd_dep_count,
+  cd_dep_employed_count,
+  cd_dep_college_count
+ORDER BY cd_gender,
+  cd_marital_status,
+  cd_education_status,
+  cd_purchase_estimate,
+  cd_credit_rating,
+  cd_dep_count,
+  cd_dep_employed_count,
+  cd_dep_college_count
+LIMIT 100

core/src/test/resources/tpcds-queries-double/q11.sql

@@ -0,0 +1,68 @@
+WITH year_total AS (
+  SELECT
+    c_customer_id customer_id,
+    c_first_name customer_first_name,
+    c_last_name customer_last_name,
+    c_preferred_cust_flag customer_preferred_cust_flag,
+    c_birth_country customer_birth_country,
+    c_login customer_login,
+    c_email_address customer_email_address,
+    d_year dyear,
+    sum(ss_ext_list_price - ss_ext_discount_amt) year_total,
+    's' sale_type
+  FROM customer, store_sales, date_dim
+  WHERE c_customer_sk = ss_customer_sk
+    AND ss_sold_date_sk = d_date_sk
+  GROUP BY c_customer_id
+    , c_first_name
+    , c_last_name
+    , d_year
+    , c_preferred_cust_flag
+    , c_birth_country
+    , c_login
+    , c_email_address
+    , d_year
+  UNION ALL
+  SELECT
+    c_customer_id customer_id,
+    c_first_name customer_first_name,
+    c_last_name customer_last_name,
+    c_preferred_cust_flag customer_preferred_cust_flag,
+    c_birth_country customer_birth_country,
+    c_login customer_login,
+    c_email_address customer_email_address,
+    d_year dyear,
+    sum(ws_ext_list_price - ws_ext_discount_amt) year_total,
+    'w' sale_type
+  FROM customer, web_sales, date_dim
+  WHERE c_customer_sk = ws_bill_customer_sk
+    AND ws_sold_date_sk = d_date_sk
+  GROUP BY
+    c_customer_id, c_first_name, c_last_name, c_preferred_cust_flag, c_birth_country,
+    c_login, c_email_address, d_year)
+SELECT t_s_secyear.customer_preferred_cust_flag
+FROM year_total t_s_firstyear
+  , year_total t_s_secyear
+  , year_total t_w_firstyear
+  , year_total t_w_secyear
+WHERE t_s_secyear.customer_id = t_s_firstyear.customer_id
+  AND t_s_firstyear.customer_id = t_w_secyear.customer_id
+  AND t_s_firstyear.customer_id = t_w_firstyear.customer_id
+  AND t_s_firstyear.sale_type = 's'
+  AND t_w_firstyear.sale_type = 'w'
+  AND t_s_secyear.sale_type = 's'
+  AND t_w_secyear.sale_type = 'w'
+  AND t_s_firstyear.dyear = 2001
+  AND t_s_secyear.dyear = 2001 + 1
+  AND t_w_firstyear.dyear = 2001
+  AND t_w_secyear.dyear = 2001 + 1
+  AND t_s_firstyear.year_total > 0
+  AND t_w_firstyear.year_total > 0
+  AND CASE WHEN t_w_firstyear.year_total > 0
+  THEN t_w_secyear.year_total / t_w_firstyear.year_total
+      ELSE NULL END
+  > CASE WHEN t_s_firstyear.year_total > 0
+  THEN t_s_secyear.year_total / t_s_firstyear.year_total
+    ELSE NULL END
+ORDER BY t_s_secyear.customer_preferred_cust_flag
+LIMIT 100

core/src/test/resources/tpcds-queries-double/q12.sql

@@ -0,0 +1,22 @@
+SELECT
+  i_item_desc,
+  i_category,
+  i_class,
+  i_current_price,
+  sum(ws_ext_sales_price) AS itemrevenue,
+  sum(ws_ext_sales_price) * 100 / sum(sum(ws_ext_sales_price))
+  OVER
+  (PARTITION BY i_class) AS revenueratio
+FROM
+  web_sales, item, date_dim
+WHERE
+  ws_item_sk = i_item_sk
+    AND i_category IN ('Sports', 'Books', 'Home')
+    AND ws_sold_date_sk = d_date_sk
+    AND d_date BETWEEN cast('1999-02-22' AS DATE)
+  AND (cast('1999-02-22' AS DATE) + INTERVAL 30 days)
+GROUP BY
+  i_item_id, i_item_desc, i_category, i_class, i_current_price
+ORDER BY
+  i_category, i_class, i_item_id, i_item_desc, revenueratio
+LIMIT 100

core/src/test/resources/tpcds-queries-double/q13.sql

@@ -0,0 +1,49 @@
+SELECT
+  avg(ss_quantity),
+  avg(ss_ext_sales_price),
+  avg(ss_ext_wholesale_cost),
+  sum(ss_ext_wholesale_cost)
+FROM store_sales
+  , store
+  , customer_demographics
+  , household_demographics
+  , customer_address
+  , date_dim
+WHERE s_store_sk = ss_store_sk
+  AND ss_sold_date_sk = d_date_sk AND d_year = 2001
+  AND ((ss_hdemo_sk = hd_demo_sk
+  AND cd_demo_sk = ss_cdemo_sk
+  AND cd_marital_status = 'M'
+  AND cd_education_status = 'Advanced Degree'
+  AND ss_sales_price BETWEEN 100.00 AND 150.00
+  AND hd_dep_count = 3
+) OR
+  (ss_hdemo_sk = hd_demo_sk
+    AND cd_demo_sk = ss_cdemo_sk
+    AND cd_marital_status = 'S'
+    AND cd_education_status = 'College'
+    AND ss_sales_price BETWEEN 50.00 AND 100.00
+    AND hd_dep_count = 1
+  ) OR
+  (ss_hdemo_sk = hd_demo_sk
+    AND cd_demo_sk = ss_cdemo_sk
+    AND cd_marital_status = 'W'
+    AND cd_education_status = '2 yr Degree'
+    AND ss_sales_price BETWEEN 150.00 AND 200.00
+    AND hd_dep_count = 1
+  ))
+  AND ((ss_addr_sk = ca_address_sk
+  AND ca_country = 'United States'
+  AND ca_state IN ('TX', 'OH', 'TX')
+  AND ss_net_profit BETWEEN 100 AND 200
+) OR
+  (ss_addr_sk = ca_address_sk
+    AND ca_country = 'United States'
+    AND ca_state IN ('OR', 'NM', 'KY')
+    AND ss_net_profit BETWEEN 150 AND 300
+  ) OR
+  (ss_addr_sk = ca_address_sk
+    AND ca_country = 'United States'
+    AND ca_state IN ('VA', 'TX', 'MS')
+    AND ss_net_profit BETWEEN 50 AND 250
+  ))