Azure Data Explorer Star Schema Benchmark versus Clickhouse

In this article I will start a Start Schema Benchmark, also known as SSB, on Azure Data Explorer and Clickhouse respectively to measure and compare the performance.

What is Star Schema Benchmark(SSB)

Star Schema Benchmark, aka SSB, is designed to measure performance of database products in support of data warehousing application. It is developed based on TPC-H benchmark but with a curated schema version. Simply speaking, SSB benchmarking schema is easier for developer to verify the performance of major commercial databases with a concise schema and queries.

TPC-H Schema

SSB Schema

If you are interested in the details of Star Schema Benchmark, please visit the Paper for more details.

Why Azure Data Explorer

Azure Data Explorer is a fast, fully managed data analytics service for real-time analysis on large volumes of data streaming from applications, websites, IoT devices, and more. In modern analytical scenarios, we need to have a fast and accurate insight from terabytes of data, in addition, from data lakehouse perspective, storage and compute should be decoupled and scaled respectively to achieve cost-effectiveness. Azure Data Explorer acts an important role in Azure Analytics Stack to support users to achieve cost-effective queries and storage by leveraging fully managed PaaS data service, without maintenance overhead.

Preparation

Environment

ADX Cluster:

3 nodes; Standard_E8d_v5, 8 cores, 64 GB memory for each node
3 nodes; Standard_E4d_v5, 4 cores, 32 GB memory for each node

Clickhouse Cluster:

3 nodes; Standard E8ds v5, 8 cores, 64 GB memory for each node

Generate Data

Compile SSB-Benchmark

git clone https://github.com/vadimtk/ssb-dbgen.git
cd ssb-dbgen
make clean
make

Generate SSB data files and we target to create the flat table data file size of 1TB, and we set the scale as 446 to achieve it
```
nohup ./dbgen -s 446 -T a 2>1 &
```

Create table schema in Clickhouse

CREATE DATABASE ssb;

CREATE TABLE ssb.customer on Cluster benchmark
(
C_CUSTKEY       UInt32,
C_NAME          String,
C_ADDRESS       String,
C_CITY          LowCardinality(String),
C_NATION        LowCardinality(String),
C_REGION        LowCardinality(String),
C_PHONE         String,
C_MKTSEGMENT    LowCardinality(String)
)
ENGINE = MergeTree ORDER BY (C_CUSTKEY);

## Create Distributed Table in Clickhouse cluster
CREATE TABLE ssb.dist_customer ON CLUSTER benchmark as ssb.customer engine = Distributed(benchmark, ssb, customer, rand());

CREATE TABLE ssb.lineorder on Cluster benchmark
(
LO_ORDERKEY             UInt32,
LO_LINENUMBER           UInt8,
LO_CUSTKEY              UInt32,
LO_PARTKEY              UInt32,
LO_SUPPKEY              UInt32,
LO_ORDERDATE            Date,
LO_ORDERPRIORITY        LowCardinality(String),
LO_SHIPPRIORITY         UInt8,
LO_QUANTITY             UInt8,
LO_EXTENDEDPRICE        UInt32,
LO_ORDTOTALPRICE        UInt32,
LO_DISCOUNT             UInt8,
LO_REVENUE              UInt32,
LO_SUPPLYCOST           UInt32,
LO_TAX                  UInt8,
LO_COMMITDATE           Date,
LO_SHIPMODE             LowCardinality(String)
)
ENGINE = MergeTree PARTITION BY toYear(LO_ORDERDATE) ORDER BY (LO_ORDERDATE, LO_ORDERKEY);

CREATE TABLE ssb.dist_lineorder ON CLUSTER benchmark as ssb.lineorder engine = Distributed(benchmark, ssb, lineorder, rand());

CREATE TABLE ssb.part on Cluster benchmark
(
P_PARTKEY       UInt32,
P_NAME          String,
P_MFGR          LowCardinality(String),
P_CATEGORY      LowCardinality(String),
P_BRAND         LowCardinality(String),
P_COLOR         LowCardinality(String),
P_TYPE          LowCardinality(String),
P_SIZE          UInt8,
P_CONTAINER     LowCardinality(String)
)
ENGINE = MergeTree ORDER BY P_PARTKEY;

CREATE TABLE ssb.dist_part ON CLUSTER benchmark as ssb.part engine = Distributed(benchmark, ssb, part, rand());

CREATE TABLE ssb.supplier on Cluster benchmark
(
S_SUPPKEY       UInt32,
S_NAME          String,
S_ADDRESS       String,
S_CITY          LowCardinality(String),
S_NATION        LowCardinality(String),
S_REGION        LowCardinality(String),
S_PHONE         String
)
ENGINE = MergeTree ORDER BY S_SUPPKEY;

CREATE TABLE ssb.dist_supplier ON CLUSTER benchmark as ssb.supplier engine = Distributed(benchmark, ssb, supplier, rand());


CREATE TABLE dates
(
D_DATEKEY          Date,
D_DATE             String,
D_DAYOFWEEK        String,
D_MONTH            String,
D_YEAR             UInt8,
D_YEARMONTHNUM     UInt8,
D_YEARMONTH        String,
D_DAYNUMINWEEK     UInt8,
D_DAYNUMINMONTH    UInt8,
D_DAYNUMINYEAR     UInt8,
D_MONTHNUMINYEAR   UInt8,
D_WEEKNUMINYEAR    UInt8,
D_SELLINGSEASON    String,
D_LASTDAYINWEEKFL  UInt8,
D_LASTDAYINMONTHFL UInt8,
D_HOLIDAYFL        UInt8,
D_WEEKDAYFL        UInt8
)
ENGINE = MergeTree ORDER BY (D_DATEKEY);

CREATE TABLE ssb.dist_dates ON CLUSTER benchmark as ssb.dates engine = Distributed(benchmark, ssb, dates, rand());

Load data into Clickhouse

 clickhouse-client --query "INSERT INTO ssb.customer FORMAT CSV" < customer.tbl
 clickhouse-client --query "INSERT INTO ssb.part FORMAT CSV" < part.tbl
 clickhouse-client --query "INSERT INTO ssb.supplier FORMAT CSV" < supplier.tbl
 clickhouse-client --query "INSERT INTO ssb.lineorder FORMAT CSV" < lineorder.tbl
 clickhouse-client --query "INSERT INTO ssb.dates FORMAT CSV" < dates.tbl

Create a flat lineorder fact table for benchmark

SET max_memory_usage = 17179869184;
   
CREATE TABLE ssb.lineorder_flat on Cluster benchmark
ENGINE = MergeTree
PARTITION BY toYear(LO_ORDERDATE)
ORDER BY (LO_ORDERDATE, LO_ORDERKEY) AS
SELECT
l.LO_ORDERKEY AS LO_ORDERKEY,
l.LO_LINENUMBER AS LO_LINENUMBER,
l.LO_CUSTKEY AS LO_CUSTKEY,
l.LO_PARTKEY AS LO_PARTKEY,
l.LO_SUPPKEY AS LO_SUPPKEY,
l.LO_ORDERDATE AS LO_ORDERDATE,
l.LO_ORDERPRIORITY AS LO_ORDERPRIORITY,
l.LO_SHIPPRIORITY AS LO_SHIPPRIORITY,
l.LO_QUANTITY AS LO_QUANTITY,
l.LO_EXTENDEDPRICE AS LO_EXTENDEDPRICE,
l.LO_ORDTOTALPRICE AS LO_ORDTOTALPRICE,
l.LO_DISCOUNT AS LO_DISCOUNT,
l.LO_REVENUE AS LO_REVENUE,
l.LO_SUPPLYCOST AS LO_SUPPLYCOST,
l.LO_TAX AS LO_TAX,
l.LO_COMMITDATE AS LO_COMMITDATE,
l.LO_SHIPMODE AS LO_SHIPMODE,
c.C_NAME AS C_NAME,
c.C_ADDRESS AS C_ADDRESS,
c.C_CITY AS C_CITY,
c.C_NATION AS C_NATION,
c.C_REGION AS C_REGION,
c.C_PHONE AS C_PHONE,
c.C_MKTSEGMENT AS C_MKTSEGMENT,
s.S_NAME AS S_NAME,
s.S_ADDRESS AS S_ADDRESS,
s.S_CITY AS S_CITY,
s.S_NATION AS S_NATION,
s.S_REGION AS S_REGION,
s.S_PHONE AS S_PHONE,
p.P_NAME AS P_NAME,
p.P_MFGR AS P_MFGR,
p.P_CATEGORY AS P_CATEGORY,
p.P_BRAND AS P_BRAND,
p.P_COLOR AS P_COLOR,
p.P_TYPE AS P_TYPE,
p.P_SIZE AS P_SIZE,
p.P_CONTAINER AS P_CONTAINER
FROM ssb.lineorder AS l
INNER JOIN ssb.customer AS c ON c.C_CUSTKEY = l.LO_CUSTKEY
INNER JOIN ssb.supplier AS s ON s.S_SUPPKEY = l.LO_SUPPKEY
INNER JOIN ssb.part AS p ON p.P_PARTKEY = l.LO_PARTKEY
;

CREATE TABLE ssb.dist_lineorder_flat ON CLUSTER benchmark as ssb.lineorder_flat engine = Distributed(benchmark, ssb, lineorder_flat, rand());

Unload data into csv files

clickhouse-client --query "SELECT * from ssb.lineorder_flat" --format CSV > lineorder_flat.csv
clickhouse-client --query "SELECT * from ssb.lineorder" --format CSV > lineorder.csv
clickhouse-client --query "SELECT * from ssb.customer" --format CSV > customer.csv
clickhouse-client --query "SELECT * from ssb.part" --format CSV > part.csv
clickhouse-client --query "SELECT * from ssb.supplier" --format CSV > supplier.csv
clickhouse-client --query "SELECT * from ssb.dates" --format CSV > dates.csv

Truncate table data for data backfill into shards in Clickhouse cluster

truncate table lineorder_flat;
truncate table lineorder;
truncate table customer;
truncate table part;
truncate table supplier;
truncate table dates;

Load data back to Distributed table in multiple shards in Clickhouse cluster

 clickhouse-client --query "INSERT INTO ssb.dist_customer FORMAT CSV" < customer.csv
 clickhouse-client --query "INSERT INTO ssb.dist_part FORMAT CSV" < part.csv
 clickhouse-client --query "INSERT INTO ssb.dist_supplier FORMAT CSV" < supplier.csv
 clickhouse-client --query "INSERT INTO ssb.dist_lineorder FORMAT CSV" < lineorder.csv
 clickhouse-client --query "INSERT INTO ssb.dist_lineorder_flat FORMAT CSV" < lineorder_flat.csv
 clickhouse-client --query "INSERT INTO ssb.dist_dates FORMAT CSV" < dates.csv

Split the fact tables (lineorder/lineorder_flat) data file into multiple segments less than 4GB, which is the limit file size for Azure Data Explorer Lightingest

For scale factor 100, the total line number of lineorder is 600,038,145, we will evenly distribute into multiple files.
```
split -d -l 35000000 lineorder.csv lineorder_part_
split -d -l 10020000 /data3/clickouse/data/lineorder_flat.csv lineorder_flat_part_
```

Upload segment files to ADLS Gen2 for ADX data ingestion

az storage fs directory upload -f ssb --account-name <storage account> -s lineorder/* -d 100G/lineorder/csv/ --recursive
az storage fs directory upload -f ssb --account-name <storage account> -s lineorder_flat/* -d 100G/lineorder_flat/csv/ --recursive

3. Use Light Ingest to ingest segment data into Azure Data Explorer

Please refer to below official document to create ADX cluster and database for preparation https://docs.microsoft.com/en-us/azure/data-explorer/create-cluster-database-portal

Please refer to below official document to ingest data into ADX cluster

4. Create table schema and partitioning/roworder policy

Table customer

.create table customer (C_CUSTKEY: long, C_NAME: string, C_ADDRESS: string, C_CITY: string, C_NATION: string, C_REGION: string, C_PHONE: string, C_MKTSEGMENT: string)

Table dates

.create table dates (D_DATEKEY: datetime, D_DATE: string, D_DAYOFWEEK: string, D_MONTH: string, D_YEAR: int, D_YEARMONTHNUM: long, D_YEARMONTH: string, D_DAYNUMINWEEK: int, D_DAYNUMINMONTH: int, D_DAYNUMINYEAR: int, D_MONTHNUMINYEAR: int, D_WEEKNUMINYEAR: int, D_SELLINGSEASON: string, D_LASTDAYINWEEKFL: int, D_LASTDAYINMONTHFL: int, D_HOLIDAYFL: int, D_WEEKDAYFL: int)

Table part

.create table dates (D_DATEKEY: datetime, D_DATE: string, D_DAYOFWEEK: string, D_MONTH: string, D_YEAR: int, D_YEARMONTHNUM: long, D_YEARMONTH: string, D_DAYNUMINWEEK: int, D_DAYNUMINMONTH: int, D_DAYNUMINYEAR: int, D_MONTHNUMINYEAR: int, D_WEEKNUMINYEAR: int, D_SELLINGSEASON: string, D_LASTDAYINWEEKFL: int, D_LASTDAYINMONTHFL: int, D_HOLIDAYFL: int, D_WEEKDAYFL: int)

Table supplier

.create table supplier (S_SUPPKEY: long, S_NAME: string, S_ADDRESS: string, S_CITY: string, S_NATION: string, S_REGION: string, S_PHONE: string)

Table lineorder_daily_partition

.create table lineorder_daily_partition (LO_ORDERKEY: long, LO_LINENUMBER: int, LO_CUSTKEY: long, LO_PARTKEY: long, LO_SUPPKEY: long, LO_ORDERDATE: datetime, LO_ORDERPRIORITY: string, LO_SHIPPRIORITY: int, LO_QUANTITY: int, LO_EXTENDEDPRICE: long, LO_ORDTOTALPRICE: long, LO_DISCOUNT: int, LO_REVENUE: long, LO_SUPPLYCOST: long, LO_TAX: int, LO_COMMITDATE: datetime, LO_SHIPMODE: string) with (docstring = "Created based on lineorder")

Table lineorder_flat

.create table lineorder_flat (LO_ORDERKEY: long, LO_LINENUMBER: int, LO_CUSTKEY: long, LO_PARTKEY: long, LO_SUPPKEY: long, LO_ORDERDATE: datetime, LO_ORDERPRIORITY: string, LO_SHIPPRIORITY: int, LO_QUANTITY: int, LO_EXTENDEDPRICE: long, LO_ORDTOTALPRICE: long, LO_DISCOUNT: int, LO_REVENUE: long, LO_SUPPLYCOST: long, LO_TAX: int, LO_COMMITDATE: datetime, LO_SHIPMODE: string, C_NAME: string, C_ADDRESS: string, C_CITY: string, C_NATION: string, C_REGION: string, C_PHONE: string, C_MKTSEGMENT: string, S_NAME: string, S_ADDRESS: string, S_CITY: string, S_NATION: string, S_REGION: string, S_PHONE: string, P_NAME: string, P_MFGR: string, P_CATEGORY: string, P_BRAND: string, P_COLOR: string, P_TYPE: string, P_SIZE: int, P_CONTAINER: string)

Partitioning Policy

.alter table lineorder_flat policy partitioning ```
{
  "PartitionKeys": [
    {
      "ColumnName": "LO_ORDERDATE",
      "Kind": "UniformRange",
      "Properties": {
        "Reference": "1992-01-01T00:00:00",
        "RangeSize": "365.00:00:00",
        "OverrideCreationTime": false
      }
    }
  ]
}```

Roworder Policy

.alter table lineorder_flat policy roworder (LO_ORDERDATE asc, LO_ORDERKEY asc);

Run Queries

Clickhouse

Before running SSB queries in Clickhouse, it will be better to reset the cache to reduce the performance impact by system cache

Reset the OS PageCache

sync; echo 1 > /proc/sys/vm/drop_caches

Reset mark-cache in Clickhouse using DROP MARK CACHE

SYSTEM DROP MARK CACHE

If you encounters the error below

Double-distributed IN/JOIN subqueries is denied (distributed_product_mode = 'deny'). You may rewrite query to use local tables in subqueries, or use GLOBAL keyword, or set distributed_product_mode to suitable value.

Set distributed product mode to global to enable multi-join benchmark in Clickhouse

SET distributed_product_mode = 'global';

We could also leverate the Clickbench script to run the script in batch automatically. For more information pleases refer to Clickbench Script

We need to modify the 2 scripts - run.sh and queries.sql

queries.sql

SELECT sum(LO_EXTENDEDPRICE * LO_DISCOUNT) AS revenue FROM ssb.dist_lineorder_flat WHERE toYear(LO_ORDERDATE) = 1993  AND LO_DISCOUNT BETWEEN 1 AND 3  AND LO_QUANTITY < 25;
SELECT SUM(LO_EXTENDEDPRICE * LO_DISCOUNT) AS revenue FROM ssb.dist_lineorder_flat WHERE toYYYYMM(LO_ORDERDATE) = 199401 AND LO_DISCOUNT BETWEEN 4 AND 6 AND LO_QUANTITY BETWEEN 26 AND 35;
SELECT SUM(LO_EXTENDEDPRICE * LO_DISCOUNT) AS revenue FROM ssb.dist_lineorder_flat WHERE toISOWeek(LO_ORDERDATE) = 6 AND toYear(LO_ORDERDATE) = 1994  AND LO_DISCOUNT BETWEEN 5 AND 7 AND LO_QUANTITY BETWEEN 26 AND 35;
SELECT SUM(LO_REVENUE), toYear(LO_ORDERDATE) AS year, P_BRAND FROM ssb.dist_lineorder_flat WHERE P_CATEGORY = 'MFGR#12' AND S_REGION = 'AMERICA' GROUP BY year, P_BRAND ORDER BY year, P_BRAND;
SELECT SUM(LO_REVENUE), toYear(LO_ORDERDATE) AS year, P_BRAND FROM ssb.dist_lineorder_flat WHERE P_BRAND >= 'MFGR#2221' AND P_BRAND <= 'MFGR#2228' AND S_REGION = 'ASIA' GROUP BY year, P_BRAND ORDER BY year, P_BRAND;
SELECT SUM(LO_REVENUE), toYear(LO_ORDERDATE) AS year, P_BRAND FROM ssb.dist_lineorder_flat WHERE P_BRAND = 'MFGR#2239' AND S_REGION = 'EUROPE'GROUP BY year, P_BRAND ORDER BY year, P_BRAND;
SELECT C_NATION, S_NATION, toYear(LO_ORDERDATE) AS year, SUM(LO_REVENUE) AS revenue FROM ssb.dist_lineorder_flat WHERE C_REGION = 'ASIA' AND S_REGION = 'ASIA' AND year >= 1992 AND year <= 1997 GROUP BY C_NATION, S_NATION, year ORDER BY year ASC, revenue DESC;
SELECT C_CITY, S_CITY, toYear(LO_ORDERDATE) AS year, SUM(LO_REVENUE) AS revenue FROM ssb.dist_lineorder_flat WHERE C_NATION = 'UNITED STATES' AND S_NATION = 'UNITED STATES' AND year >= 1992 AND year <= 1997 GROUP BY C_CITY, S_CITY, year ORDER BY year ASC, revenue DESC;
SELECT C_CITY, S_CITY, toYear(LO_ORDERDATE) AS year, SUM(LO_REVENUE) AS revenue FROM ssb.dist_lineorder_flat WHERE (C_CITY = 'UNITED KI1' OR C_CITY = 'UNITED KI5') AND (S_CITY = 'UNITED KI1' OR S_CITY = 'UNITED KI5') AND year >= 1992 AND year <= 1997 GROUP BY C_CITY, S_CITY, year ORDER BY year ASC, revenue DESC;
SELECT C_CITY, S_CITY, toYear(LO_ORDERDATE) AS year, SUM(LO_REVENUE) AS revenue FROM ssb.dist_lineorder_flat WHERE (C_CITY = 'UNITED KI1' OR C_CITY = 'UNITED KI5') AND (S_CITY = 'UNITED KI1' OR S_CITY = 'UNITED KI5') AND toYYYYMM(LO_ORDERDATE) = 199712 GROUP BY C_CITY, S_CITY, year ORDER BY year ASC, revenue DESC;
SELECT toYear(LO_ORDERDATE) AS year, C_NATION, SUM(LO_REVENUE - LO_SUPPLYCOST) AS profit FROM ssb.dist_lineorder_flat WHERE C_REGION = 'AMERICA' AND S_REGION = 'AMERICA' AND (P_MFGR = 'MFGR#1' OR P_MFGR = 'MFGR#2') GROUP BY year, C_NATION ORDER BY year ASC, C_NATION ASC;
SELECT toYear(LO_ORDERDATE) AS year, S_NATION, P_CATEGORY, SUM(LO_REVENUE - LO_SUPPLYCOST) AS profit FROM ssb.dist_lineorder_flat WHERE C_REGION = 'AMERICA' AND S_REGION = 'AMERICA' AND (year = 1997 OR year = 1998) AND (P_MFGR = 'MFGR#1' OR P_MFGR = 'MFGR#2') GROUP BY year, S_NATION, P_CATEGORY ORDER BY year ASC, S_NATION ASC, P_CATEGORY ASC;
SELECT toYear(LO_ORDERDATE) AS year, S_CITY, P_BRAND, SUM(LO_REVENUE - LO_SUPPLYCOST) AS profit FROM ssb.dist_lineorder_flat WHERE S_NATION = 'UNITED STATES' AND (year = 1997 OR year = 1998) AND P_CATEGORY = 'MFGR#14' GROUP BY year, S_CITY, P_BRAND ORDER BY year ASC, S_CITY ASC, P_BRAND ASC;

run.sh

#!/bin/bash

TRIES=3
QUERY_NUM=1
cat queries.sql | while read query; do
    [ -z "$HOST" ] && sync
    [ -z "$HOST" ] && echo 3 | sudo tee /proc/sys/vm/drop_caches >/dev/null

    echo -n "["
    for i in $(seq 1 $TRIES); do
        RES=$(clickhouse-client --password "mypassword" --time --format=Null --query="$query" --progress 0 2>&1 ||:)
        [[ "$?" == "0" ]] && echo -n "${RES}" || echo -n "null"
        [[ "$i" != $TRIES ]] && echo -n ", "

        echo "${QUERY_NUM},${i},${RES}" >> result.csv
    done
    echo "],"

    QUERY_NUM=$((QUERY_NUM + 1))
done

Once we have modified the files, we could simply run the run.sh to execute the queries, each query will run 3 times consecutively

$ ./run.sh

[0.764, 0.266, 0.257],
[0.060, 0.053, 0.063],
[0.030, 0.031, 0.033],
[7.804, 1.936, 1.937],
[6.677, 1.805, 1.744],
[6.711, 1.659, 1.654],
[6.487, 2.391, 2.352],
[7.312, 1.962, 1.952],
[5.610, 1.428, 1.458],
[0.041, 0.035, 0.033],
[9.967, 3.247, 3.235],
[2.478, 0.894, 0.920],
[2.773, 0.763, 0.752],

Q1.1

Flat table

SELECT sum(LO_EXTENDEDPRICE * LO_DISCOUNT) AS revenue
FROM dist_lineorder_flat
WHERE toYear(LO_ORDERDATE) = 1993
  AND LO_DISCOUNT BETWEEN 1 AND 3
  AND LO_QUANTITY < 25;

Multi table join

SELECT sum(LO_EXTENDEDPRICE*LO_DISCOUNT) AS revenue
FROM dist_lineorder
LEFT JOIN dist_dates ON LO_ORDERDATE = D_DATEKEY
WHERE toYear(LO_ORDERDATE) = 1993
  AND LO_DISCOUNT BETWEEN 1 AND 3
  AND LO_QUANTITY < 25;

Q1.2

Flat table

SELECT SUM(LO_EXTENDEDPRICE * LO_DISCOUNT) AS revenue
FROM dist_lineorder_flat
WHERE toYYYYMM(LO_ORDERDATE) = 199401 AND LO_DISCOUNT BETWEEN 4 AND 6 AND LO_QUANTITY BETWEEN 26 AND 35;

Multi table join

SELECT SUM(LO_EXTENDEDPRICE*LO_DISCOUNT) AS revenue
FROM dist_lineorder
LEFT JOIN dist_dates ON LO_ORDERDATE = D_DATEKEY
WHERE toYYYYMM(LO_ORDERDATE) = 199401
  AND LO_DISCOUNT between 4 AND 6
  AND LO_QUANTITY between 26 AND 35;

Q1.3

Flat table

SELECT SUM(LO_EXTENDEDPRICE * LO_DISCOUNT) AS revenue
FROM dist_lineorder_flat
WHERE toISOWeek(LO_ORDERDATE) = 6 AND toYear(LO_ORDERDATE) = 1994
  AND LO_DISCOUNT BETWEEN 5 AND 7 AND LO_QUANTITY BETWEEN 26 AND 35;

Multi table join

SELECT SUM(LO_EXTENDEDPRICE*LO_DISCOUNT) AS revenue
FROM dist_lineorder
LEFT JOIN dist_dates ON LO_ORDERDATE = D_DATEKEY
WHERE toISOWeek(LO_ORDERDATE) = 6 AND toYear(LO_ORDERDATE) = 1994
  AND LO_DISCOUNT BETWEEN 5 AND 7 AND LO_QUANTITY BETWEEN 26 AND 35;

Q2.1

Flat table

SELECT
    SUM(LO_REVENUE),
    toYear(LO_ORDERDATE) AS year,
    P_BRAND
FROM dist_lineorder_flat
WHERE P_CATEGORY = 'MFGR#12' AND S_REGION = 'AMERICA'
GROUP BY
    year,
    P_BRAND
ORDER BY
    year,
    P_BRAND;

Multi table join

SELECT SUM(LO_REVENUE) AS lo_revenue, D_YEAR, P_BRAND
FROM dist_lineorder
LEFT JOIN dist_dates ON LO_ORDERDATE= D_DATEKEY
LEFT JOIN dist_part ON LO_PARTKEY = P_PARTKEY
LEFT JOIN dist_supplier ON LO_SUPPKEY = S_SUPPKEY
WHERE P_CATEGORY = 'MFGR#12' AND S_REGION = 'AMERICA'
GROUP BY D_YEAR, P_BRAND
ORDER BY D_YEAR, P_BRAND;

Q2.2

Flat table

SELECT
    SUM(LO_REVENUE),
    toYear(LO_ORDERDATE) AS year,
    P_BRAND
FROM dist_lineorder_flat
WHERE P_BRAND >= 'MFGR#2221' AND P_BRAND <= 'MFGR#2228' AND S_REGION = 'ASIA'
GROUP BY
    year,
    P_BRAND
ORDER BY
    year,
    P_BRAND;

Multi table join

SELECT SUM(LO_REVENUE) AS lo_revenue, D_YEAR, P_BRAND
FROM dist_lineorder
LEFT JOIN dist_dates ON LO_ORDERDATE= D_DATEKEY
LEFT JOIN dist_part ON LO_PARTKEY = P_PARTKEY
LEFT JOIN dist_supplier ON LO_SUPPKEY = S_SUPPKEY
WHERE P_BRAND >= 'MFGR#2221' AND P_BRAND <= 'MFGR#2228' AND S_REGION = 'ASIA'
GROUP BY D_YEAR, P_BRAND
ORDER BY D_YEAR, P_BRAND;

Q2.3

Flat table

SELECT
    SUM(LO_REVENUE),
    toYear(LO_ORDERDATE) AS year,
    P_BRAND
FROM dist_lineorder_flat
WHERE P_BRAND = 'MFGR#2239' AND S_REGION = 'EUROPE'
GROUP BY
    year,
    P_BRAND
ORDER BY
    year,
    P_BRAND;

Multi table join

SELECT SUM(LO_REVENUE) AS lo_revenue, D_YEAR, P_BRAND
FROM dist_lineorder
LEFT JOIN dist_dates ON LO_ORDERDATE= D_DATEKEY
LEFT JOIN dist_part ON LO_PARTKEY = P_PARTKEY
LEFT JOIN dist_supplier ON LO_SUPPKEY = S_SUPPKEY
WHERE P_BRAND = 'MFGR#2239' AND S_REGION = 'EUROPE'
GROUP BY D_YEAR, P_BRAND
ORDER BY D_YEAR, P_BRAND;

Q3.1

Flat table

SELECT
    C_NATION,
    S_NATION,
    toYear(LO_ORDERDATE) AS year,
    SUM(LO_REVENUE) AS revenue
FROM dist_lineorder_flat
WHERE C_REGION = 'ASIA' AND S_REGION = 'ASIA' AND year >= 1992 AND year <= 1997
GROUP BY
    C_NATION,
    S_NATION,
    year
ORDER BY
    year ASC,
    revenue DESC;

Multi table join

SELECT SUM(LO_REVENUE) AS lo_revenue, toYear(LO_ORDERDATE) AS year, C_NATION, S_NATION
FROM dist_lineorder
LEFT JOIN dist_dates ON LO_ORDERDATE= D_DATEKEY
LEFT JOIN dist_customer ON LO_PARTKEY = C_CUSTKEY
LEFT JOIN dist_supplier ON LO_SUPPKEY = S_SUPPKEY
WHERE C_REGION = 'ASIA' AND S_REGION = 'ASIA' AND year >= 1992 AND year <= 1997
GROUP BY C_NATION, S_NATION, year
ORDER BY year ASc, lo_revenue DESC;

Q3.2

Flat table

SELECT
    C_CITY,
    S_CITY,
    toYear(LO_ORDERDATE) AS year,
    SUM(LO_REVENUE) AS revenue
FROM dist_lineorder_flat
WHERE C_NATION = 'UNITED STATES' AND S_NATION = 'UNITED STATES' AND year >= 1992 AND year <= 1997
GROUP BY
    C_CITY,
    S_CITY,
    year
ORDER BY
    year ASC,
    revenue DESC;

Multi table join

SELECT SUM(LO_REVENUE) AS lo_revenue, toYear(LO_ORDERDATE) AS year, C_CITY, S_CITY
FROM dist_lineorder
LEFT JOIN dist_dates ON LO_ORDERDATE= D_DATEKEY
LEFT JOIN dist_customer ON LO_PARTKEY = C_CUSTKEY
LEFT JOIN dist_supplier ON LO_SUPPKEY = S_SUPPKEY
WHERE C_NATION = 'UNITED STATES' AND S_NATION = 'UNITED STATES' AND year >= 1992 AND year <= 1997
GROUP BY C_CITY, S_CITY, year
ORDER BY year ASc, lo_revenue DESC;

Q3.3

Flat table

SELECT
    C_CITY,
    S_CITY,
    toYear(LO_ORDERDATE) AS year,
    SUM(LO_REVENUE) AS revenue
FROM dist_lineorder_flat
WHERE (C_CITY = 'UNITED KI1' OR C_CITY = 'UNITED KI5') AND (S_CITY = 'UNITED KI1' OR S_CITY = 'UNITED KI5') AND year >= 1992 AND year <= 1997
GROUP BY
    C_CITY,
    S_CITY,
    year
ORDER BY
    year ASC,
    revenue DESC;

Multi table join

SELECT SUM(LO_REVENUE) AS lo_revenue, toYear(LO_ORDERDATE) AS year, C_CITY, S_CITY
FROM dist_lineorder
LEFT JOIN dist_dates ON LO_ORDERDATE= D_DATEKEY
LEFT JOIN dist_customer ON LO_PARTKEY = C_CUSTKEY
LEFT JOIN dist_supplier ON LO_SUPPKEY = S_SUPPKEY
WHERE (C_CITY ='UNITED KI1' or C_CITY ='UNITED KI5')
  AND (S_CITY='UNITED KI1' or S_CITY='UNITED KI5')
  AND year >= 1992 AND year <= 1997
GROUP BY C_CITY, S_CITY, year
ORDER BY year ASc, lo_revenue DESC;

Q3.4

Flat table

SELECT
    C_CITY,
    S_CITY,
    toYear(LO_ORDERDATE) AS year,
    SUM(LO_REVENUE) AS revenue
FROM dist_lineorder_flat
WHERE (C_CITY = 'UNITED KI1' OR C_CITY = 'UNITED KI5') AND (S_CITY = 'UNITED KI1' OR S_CITY = 'UNITED KI5') AND toYYYYMM(LO_ORDERDATE) = 199712
GROUP BY
    C_CITY,
    S_CITY,
    year
ORDER BY
    year ASC,
    revenue DESC;

Multi table join

SELECT SUM(LO_REVENUE) AS lo_revenue, toYear(LO_ORDERDATE) AS year, C_CITY, S_CITY
FROM dist_lineorder
LEFT JOIN dist_dates ON LO_ORDERDATE= D_DATEKEY
LEFT JOIN dist_customer ON LO_PARTKEY = C_CUSTKEY
LEFT JOIN dist_supplier ON LO_SUPPKEY = S_SUPPKEY
WHERE (C_CITY ='UNITED KI1' or C_CITY ='UNITED KI5')
  AND (S_CITY='UNITED KI1' or S_CITY='UNITED KI5')
  AND D_YEARMONTH == 'Dec1997'
GROUP BY C_CITY, S_CITY, year
ORDER BY year ASc, lo_revenue DESC;

Q4.1

Flat table

SELECT
    toYear(LO_ORDERDATE) AS year,
    C_NATION,
    SUM(LO_REVENUE - LO_SUPPLYCOST) AS profit
FROM lineorder_flat
WHERE C_REGION = 'AMERICA' AND S_REGION = 'AMERICA' AND (P_MFGR = 'MFGR#1' OR P_MFGR = 'MFGR#2')
GROUP BY
    year,
    C_NATION
ORDER BY
    year ASC,
    C_NATION ASC;

Multi table join

SELECT (SUM(LO_REVENUE ) - SUM(LO_SUPPLYCOST)) AS profit, toYear(LO_ORDERDATE) AS year, C_NATION
FROM dist_lineorder
LEFT JOIN dist_dates ON LO_ORDERDATE= D_DATEKEY
LEFT JOIN dist_customer ON LO_PARTKEY = C_CUSTKEY
LEFT JOIN dist_supplier ON LO_SUPPKEY = S_SUPPKEY
LEFT JOIN dist_part ON LO_PARTKEY = P_PARTKEY
WHERE C_REGION = 'AMERICA' AND S_REGION= 'AMERICA'
  AND (P_MFGR = 'MFGR#1' or P_MFGR = 'MFGR#2')
GROUP BY year, C_NATION
ORDER BY year ASc, C_NATION ASC;

Q4.2

Flat table

SELECT
    toYear(LO_ORDERDATE) AS year,
    S_NATION,
    P_CATEGORY,
    SUM(LO_REVENUE - LO_SUPPLYCOST) AS profit
FROM dist_lineorder_flat
WHERE C_REGION = 'AMERICA' AND S_REGION = 'AMERICA' AND (year = 1997 OR year = 1998) AND (P_MFGR = 'MFGR#1' OR P_MFGR = 'MFGR#2')
GROUP BY
    year,
    S_NATION,
    P_CATEGORY
ORDER BY
    year ASC,
    S_NATION ASC,
    P_CATEGORY ASC;

Multi table join

SELECT (SUM(LO_REVENUE ) - SUM(LO_SUPPLYCOST)) AS profit, toYear(LO_ORDERDATE) AS year, S_NATION, P_CATEGORY
FROM dist_lineorder
    LEFT JOIN dist_dates ON LO_ORDERDATE= D_DATEKEY
    LEFT JOIN dist_customer ON LO_PARTKEY = C_CUSTKEY
    LEFT JOIN dist_supplier ON LO_SUPPKEY = S_SUPPKEY
    LEFT JOIN dist_part ON LO_PARTKEY = P_PARTKEY
WHERE C_REGION = 'AMERICA' AND S_REGION = 'AMERICA' AND (year = 1997 OR year = 1998) AND (P_MFGR = 'MFGR#1' OR P_MFGR = 'MFGR#2')
GROUP BY
    year,
    S_NATION,
    P_CATEGORY
ORDER BY
    year ASC,
    S_NATION ASC,
    P_CATEGORY ASC;

Q4.3

Flat table

SELECT
    toYear(LO_ORDERDATE) AS year,
    S_CITY,
    P_BRAND,
    SUM(LO_REVENUE - LO_SUPPLYCOST) AS profit
FROM dist_lineorder_flat
WHERE S_NATION = 'UNITED STATES' AND (year = 1997 OR year = 1998) AND P_CATEGORY = 'MFGR#14'
GROUP BY
    year,
    S_CITY,
    P_BRAND
ORDER BY
    year ASC,
    S_CITY ASC,
    P_BRAND ASC;

Multi table join

SELECT
    toYear(LO_ORDERDATE) AS year,
    S_CITY,
    P_BRAND,
    (SUM(LO_REVENUE ) - SUM(LO_SUPPLYCOST)) AS profit
FROM dist_lineorder
    LEFT JOIN dist_dates ON LO_ORDERDATE= D_DATEKEY
    LEFT JOIN dist_customer ON LO_PARTKEY = C_CUSTKEY
    LEFT JOIN dist_supplier ON LO_SUPPKEY = S_SUPPKEY
    LEFT JOIN dist_part ON LO_PARTKEY = P_PARTKEY
WHERE S_NATION = 'UNITED STATES' AND (year = 1997 OR year = 1998) AND P_CATEGORY = 'MFGR#14'
GROUP BY
    year,
    S_CITY,
    P_BRAND
ORDER BY
    year ASC,
    S_CITY ASC,
    P_BRAND ASC;