Benchmark BemiDB vs Postgres

.gitignore

@@ -1,3 +1,5 @@
 /iceberg
 /iceberg-test
 .env
+/benchmark/tpch-kit
+/benchmark/data/*.tbl

Makefile

@@ -24,3 +24,12 @@ lint:
 
 outdated:
 	devbox run "cd src && go list -u -m -f '{{if and .Update (not .Indirect)}}{{.}}{{end}}' all"
+
+pg-init:
+	devbox run initdb
+
+pg-up:
+	devbox services start postgresql
+
+pg-down:
+	devbox services stop postgresql

benchmark/README.md

@@ -0,0 +1,74 @@
+# BemiDB Bechmark
+
+## Running the TPC-H Benchmark
+
+Set up a local PostgreSQL database:
+
+```sh
+# Install PostgreSQL
+make pg-init
+make pg-up
+
+# Create the database
+make sh
+createdb tpch
+
+# Load the tables' structure
+cd ./benchmark/data
+psql tpch -f ./structure.ddl
+
+# Download and unzip "TPC-H_generated_data.zip" from the latest release into the "benchmark/data" directory
+# And load the data
+for i in `ls *.tbl`; do
+  table=${i/.tbl/}
+  echo "Loading $table..."
+  sed 's/|$//' $i > /tmp/$i
+  psql tpch -q -c "TRUNCATE $table"
+  psql tpch -c "\\copy $table FROM '/tmp/$i' CSV DELIMITER '|'"
+done
+
+# Run the queries
+psql tpch -c "ANALYZE VERBOSE"
+time psql tpch < ../queries.sql
+```
+
+## Generating the TPC-H Data
+
+Install the TPC-H benchmark kit:
+
+```sh
+make sh
+cd benchmark
+git clone https://github.com/gregrahn/tpch-kit.git
+cd tpch-kit/dbgen
+make MACHINE=MACOS DATABASE=POSTGRESQL # Use MACHINE=LINUX for Linux
+cd -
+```
+
+Copy tables' structure DDL file:
+
+```sh
+export DSS_PATH="$(pwd)/data"
+export DSS_CONFIG=./tpch-kit/dbgen
+cp ./tpch-kit/dbgen/dss.ddl ./data/structure.ddl
+```
+
+Generate the data:
+
+```sh
+./tpch-kit/dbgen/dbgen -vf -s 0.1 # Generate ~100MB of data
+```
+
+Generate the queries:
+
+```sh
+mkdir /tmp/query-templates
+for i in `ls query-templates/*.sql`; do
+  tac $i | sed '2s/;//' | tac > /tmp/$i # Remove ";"
+done
+
+export DSS_QUERY=/tmp/query-templates
+cd ./tpch-kit/dbgen
+./qgen -v -s 0.1 | sed 's/limit -1//' | sed 's/day (3)/day/' > ../../queries.sql
+cd -
+```

benchmark/data/structure.ddl

@@ -0,0 +1,70 @@
+-- Sccsid:     @(#)dss.ddl	2.1.8.1
+CREATE TABLE NATION  ( N_NATIONKEY  INTEGER NOT NULL,
+                            N_NAME       CHAR(25) NOT NULL,
+                            N_REGIONKEY  INTEGER NOT NULL,
+                            N_COMMENT    VARCHAR(152));
+
+CREATE TABLE REGION  ( R_REGIONKEY  INTEGER NOT NULL,
+                            R_NAME       CHAR(25) NOT NULL,
+                            R_COMMENT    VARCHAR(152));
+
+CREATE TABLE PART  ( P_PARTKEY     INTEGER NOT NULL,
+                          P_NAME        VARCHAR(55) NOT NULL,
+                          P_MFGR        CHAR(25) NOT NULL,
+                          P_BRAND       CHAR(10) NOT NULL,
+                          P_TYPE        VARCHAR(25) NOT NULL,
+                          P_SIZE        INTEGER NOT NULL,
+                          P_CONTAINER   CHAR(10) NOT NULL,
+                          P_RETAILPRICE DECIMAL(15,2) NOT NULL,
+                          P_COMMENT     VARCHAR(23) NOT NULL );
+
+CREATE TABLE SUPPLIER ( S_SUPPKEY     INTEGER NOT NULL,
+                             S_NAME        CHAR(25) NOT NULL,
+                             S_ADDRESS     VARCHAR(40) NOT NULL,
+                             S_NATIONKEY   INTEGER NOT NULL,
+                             S_PHONE       CHAR(15) NOT NULL,
+                             S_ACCTBAL     DECIMAL(15,2) NOT NULL,
+                             S_COMMENT     VARCHAR(101) NOT NULL);
+
+CREATE TABLE PARTSUPP ( PS_PARTKEY     INTEGER NOT NULL,
+                             PS_SUPPKEY     INTEGER NOT NULL,
+                             PS_AVAILQTY    INTEGER NOT NULL,
+                             PS_SUPPLYCOST  DECIMAL(15,2)  NOT NULL,
+                             PS_COMMENT     VARCHAR(199) NOT NULL );
+
+CREATE TABLE CUSTOMER ( C_CUSTKEY     INTEGER NOT NULL,
+                             C_NAME        VARCHAR(25) NOT NULL,
+                             C_ADDRESS     VARCHAR(40) NOT NULL,
+                             C_NATIONKEY   INTEGER NOT NULL,
+                             C_PHONE       CHAR(15) NOT NULL,
+                             C_ACCTBAL     DECIMAL(15,2)   NOT NULL,
+                             C_MKTSEGMENT  CHAR(10) NOT NULL,
+                             C_COMMENT     VARCHAR(117) NOT NULL);
+
+CREATE TABLE ORDERS  ( O_ORDERKEY       INTEGER NOT NULL,
+                           O_CUSTKEY        INTEGER NOT NULL,
+                           O_ORDERSTATUS    CHAR(1) NOT NULL,
+                           O_TOTALPRICE     DECIMAL(15,2) NOT NULL,
+                           O_ORDERDATE      DATE NOT NULL,
+                           O_ORDERPRIORITY  CHAR(15) NOT NULL,  
+                           O_CLERK          CHAR(15) NOT NULL, 
+                           O_SHIPPRIORITY   INTEGER NOT NULL,
+                           O_COMMENT        VARCHAR(79) NOT NULL);
+
+CREATE TABLE LINEITEM ( L_ORDERKEY    INTEGER NOT NULL,
+                             L_PARTKEY     INTEGER NOT NULL,
+                             L_SUPPKEY     INTEGER NOT NULL,
+                             L_LINENUMBER  INTEGER NOT NULL,
+                             L_QUANTITY    DECIMAL(15,2) NOT NULL,
+                             L_EXTENDEDPRICE  DECIMAL(15,2) NOT NULL,
+                             L_DISCOUNT    DECIMAL(15,2) NOT NULL,
+                             L_TAX         DECIMAL(15,2) NOT NULL,
+                             L_RETURNFLAG  CHAR(1) NOT NULL,
+                             L_LINESTATUS  CHAR(1) NOT NULL,
+                             L_SHIPDATE    DATE NOT NULL,
+                             L_COMMITDATE  DATE NOT NULL,
+                             L_RECEIPTDATE DATE NOT NULL,
+                             L_SHIPINSTRUCT CHAR(25) NOT NULL,
+                             L_SHIPMODE     CHAR(10) NOT NULL,
+                             L_COMMENT      VARCHAR(44) NOT NULL);
+