chore(docs): update instructions to run TPC-H (#374)

Signed-off-by: Alex Chi <iskyzh@gmail.com>

Author: skyzh

.gitignore

@@ -1,3 +1,4 @@
 /target
 *.db
 .idea
+/tpch-dbgen

Makefile

@@ -1,4 +1,4 @@
-TPCH_DBGEN_PATH := target/tpch-dbgen
+TPCH_DBGEN_PATH := tpch-dbgen
 
 docs_check:
 	cargo doc --no-deps --document-private-items --all-features # TODO: docs check won't fail if there is warning, should be fixed later
@@ -37,4 +37,8 @@ tpch: $(TPCH_DBGEN_PATH)
 	make -C $(TPCH_DBGEN_PATH)
 	cd $(TPCH_DBGEN_PATH) && ./dbgen -f && mkdir -p tbl && mv *.tbl tbl
 
+tpch-10gb: $(TPCH_DBGEN_PATH)
+	make -C $(TPCH_DBGEN_PATH)
+	cd $(TPCH_DBGEN_PATH) && ./dbgen -f -s 10 && mkdir -p tbl && mv *.tbl tbl
+
 .PHONY: docs check fmt fmt_check clippy clippy_check build test docs_check clean tpch

docs/01-tpch.md

@@ -7,13 +7,19 @@ and run some simple queries in RisingLight.
 
 ### Use Make Recipe
 
-You may use the make recipe to download and generate TPC-H data.
+You may use the make recipe to download and generate TPC-H data (about 1GB in tbl format).
 
 ```
 make tpch
 ```
 
-The generated data will be placed under `target/tpch-dbgen/tbl` folder.
+If you want to run a larger query:
+
+```
+make tpch-10gb
+```
+
+The generated data will be placed under `tpch-dbgen/tbl` folder.
 
 ### Manual Generation
 
@@ -30,7 +36,7 @@ Then, enter the tpch-dbgen directory and type `make all`, and it will generate s
 Finally, type the following command and wait for several seconds:
 
 ```
-./dbgen -s 1
+./dbgen
 ```
 
 This command will generate the data we want, which contains a table called `LINEITEM` with a size of 700MB.
@@ -88,6 +94,16 @@ select sum(L_LINENUMBER) from LINEITEM;
 select count(L_ORDERKEY), sum(L_LINENUMBER) from LINEITEM where L_ORDERKEY > 2135527;
 ```
 
+Or run real TPC-H queries:
+
+```shell
+cargo run --release -- -f tests/sql/tpch/q1.sql
+cargo run --release -- -f tests/sql/tpch/q3.sql
+cargo run --release -- -f tests/sql/tpch/q5.sql
+cargo run --release -- -f tests/sql/tpch/q6.sql
+cargo run --release -- -f tests/sql/tpch/q10.sql
+```
+
 ## Clean Data
 
 All data of RisingLight is stored in `risinglight.secondary.db` folder. Simply remove it

tests/sql/tpch/import.sql

@@ -1,8 +1,8 @@
-COPY CUSTOMER FROM 'target/tpch-dbgen/tbl/customer.tbl' ( DELIMITER '|' );
-COPY NATION FROM 'target/tpch-dbgen/tbl/nation.tbl' ( DELIMITER '|' );
-COPY ORDERS FROM 'target/tpch-dbgen/tbl/orders.tbl' ( DELIMITER '|' );
-COPY PART FROM 'target/tpch-dbgen/tbl/part.tbl' ( DELIMITER '|' );
-COPY PARTSUPP FROM 'target/tpch-dbgen/tbl/partsupp.tbl' ( DELIMITER '|' );
-COPY REGION FROM 'target/tpch-dbgen/tbl/region.tbl' ( DELIMITER '|' );
-COPY SUPPLIER FROM 'target/tpch-dbgen/tbl/supplier.tbl' ( DELIMITER '|' );
-COPY LINEITEM FROM 'target/tpch-dbgen/tbl/lineitem.tbl' ( DELIMITER '|' );
+COPY CUSTOMER FROM 'tpch-dbgen/tbl/customer.tbl' ( DELIMITER '|' );
+COPY NATION FROM 'tpch-dbgen/tbl/nation.tbl' ( DELIMITER '|' );
+COPY ORDERS FROM 'tpch-dbgen/tbl/orders.tbl' ( DELIMITER '|' );
+COPY PART FROM 'tpch-dbgen/tbl/part.tbl' ( DELIMITER '|' );
+COPY PARTSUPP FROM 'tpch-dbgen/tbl/partsupp.tbl' ( DELIMITER '|' );
+COPY REGION FROM 'tpch-dbgen/tbl/region.tbl' ( DELIMITER '|' );
+COPY SUPPLIER FROM 'tpch-dbgen/tbl/supplier.tbl' ( DELIMITER '|' );
+COPY LINEITEM FROM 'tpch-dbgen/tbl/lineitem.tbl' ( DELIMITER '|' );

tests/sql/tpch/q1.sql

@@ -0,0 +1,21 @@
+select
+  l_returnflag,
+  l_linestatus,
+  sum(l_quantity) as sum_qty,
+  sum(l_extendedprice) as sum_base_price,
+  sum(l_extendedprice * (1 - l_discount)) as sum_disc_price,
+  sum(l_extendedprice * (1 - l_discount) * (1 + l_tax)) as sum_charge,
+  avg(l_quantity) as avg_qty,
+  avg(l_extendedprice) as avg_price,
+  avg(l_discount) as avg_disc,
+  count(*) as count_order
+from
+  lineitem
+where
+  l_shipdate <= date '1998-12-01' - interval '71' day
+group by
+  l_returnflag,
+  l_linestatus
+order by
+  l_returnflag,
+  l_linestatus;

tests/sql/tpch/q10.sql

@@ -0,0 +1,32 @@
+select
+        c_custkey,
+        c_name,
+        sum(l_extendedprice * (1 - l_discount)) as revenue,
+        c_acctbal,
+        n_name,
+        c_address,
+        c_phone,
+        c_comment
+from
+        customer,
+        orders,
+        lineitem,
+        nation
+where
+        c_custkey = o_custkey
+        and l_orderkey = o_orderkey
+        and o_orderdate >= date '1993-10-01'
+        and o_orderdate < date '1993-10-01' + interval '3' month
+        and l_returnflag = 'R'
+        and c_nationkey = n_nationkey
+group by
+        c_custkey,
+        c_name,
+        c_acctbal,
+        c_phone,
+        n_name,
+        c_address,
+        c_comment
+order by
+        revenue desc
+limit 20;

tests/sql/tpch/q3.sql

@@ -0,0 +1,23 @@
+select
+        l_orderkey,
+        sum(l_extendedprice * (1 - l_discount)) as revenue,
+        o_orderdate,
+        o_shippriority
+from
+        customer,
+        orders,
+        lineitem
+where
+        c_mktsegment = 'BUILDING'
+        and c_custkey = o_custkey
+        and l_orderkey = o_orderkey
+        and o_orderdate < date '1995-03-15'
+        and l_shipdate > date '1995-03-15'
+group by
+        l_orderkey,
+        o_orderdate,
+        o_shippriority
+order by
+        revenue desc,
+        o_orderdate
+limit 10;

tests/sql/tpch/q5.sql

@@ -0,0 +1,24 @@
+select
+        n_name,
+        sum(l_extendedprice * (1 - l_discount)) as revenue
+from
+        customer,
+        orders,
+        lineitem,
+        supplier,
+        nation,
+        region
+where
+        c_custkey = o_custkey
+        and l_orderkey = o_orderkey
+        and l_suppkey = s_suppkey
+        and c_nationkey = s_nationkey
+        and s_nationkey = n_nationkey
+        and n_regionkey = r_regionkey
+        and r_name = 'AFRICA'
+        and o_orderdate >= date '1994-01-01'
+        and o_orderdate < date '1994-01-01' + interval '1' year
+group by
+        n_name
+order by
+        revenue desc;

tests/sql/tpch/q6.sql

@@ -0,0 +1,9 @@
+select
+  sum(l_extendedprice * l_discount) as revenue
+from
+  lineitem
+where
+  l_shipdate >= date '1994-01-01'
+  and l_shipdate < date '1994-01-01' + interval '1' year
+  and l_discount between 0.08 - 0.01 and 0.08 + 0.01
+  and l_quantity < 24;