DEV Community

Cover image for Apache Flink SQL Client on Docker
Francesco Tisiot
Francesco Tisiot

Posted on • Originally published at aiven.io

Apache Flink SQL Client on Docker

#apachekafka #apacheflink #streaming #datapipelines

Apache Flink is an open source framework for data processing both in stream and batch mode. It supports a variety of different data platforms, including Apache Kafka and any JDBC database. Flink's superpowers come in a variety of languages: from the more traditional Java and Scala, all the way to Python. And for Python there is pyFlink that you can use with the best Machine Learning libraries available.

However, in the data world, one of the most commonly known languages is SQL. From data analysts, to scientist and engineers, SQL is usually part of the toolkit of any data practitioner. SQL provides an abstraction to data access and manipulation that goes beyond technologies and trends. You can use it to query your data no matter what the underlying tech is (with minor dialect differences).

With Apache Flink, you can define whole data pipelines in pure SQL using its SQL Client. This blog post will get you set up with a local docker-based platform for Apache Flink, including an SQL client.

Set up Apache Flink Locally with Docker Compose

As mentioned above, Apache Flink is a very interesting technology and worth trying out. When evaluating a new tool, running it locally is a two-edged sword. On the one hand, you get the benefit of understanding its inner mechanism better. On the other, you also get the pain of the setup phase.

To skip the setup pain, try Docker. It offers tools as pre-packaged solutions portable in any guest OS with minimal effort.

When looking around for content around Flink's SQL client I found a demo on Apache Flink's website, which is quite good but not for casual experimentation. That's why I've created a lighter tutorial. This article, with its related Github repository, takes the minimal building blocks and provides a basic Flink functionality, expecting any data pipeline source or target to be available outside the containers. Before starting, make sure that both docker and docker-compose are installed.

The whole code is contained in the aiven/flink-sql-cli-docker repository, which we can clone with the following call in our terminal:

git clone https://github.com/aiven/flink-sql-cli-docker.git
Enter fullscreen mode Exit fullscreen mode

Now let's open the flink-sql-cli-docker folder and start the docker compose:

cd flink-sql-cli-docker
docker-compose up -d
Enter fullscreen mode Exit fullscreen mode

This will start 3 Apache Flink nodes in the background: a jobmanager, a taskmanager and the sql-client. We can review the details of the cluster like this:

docker-compose ps
Enter fullscreen mode Exit fullscreen mode

This should show the three containers being in Up state:

Name                             Command               State                Ports              
--------------------------------------------------------------------------------------------------------------
flink-sql-cli-docker_jobmanager_1    /docker-entrypoint.sh jobm ...   Up      6123/tcp, 0.0.0.0:8081->8081/tcp
flink-sql-cli-docker_sql-client_1    /docker-entrypoint.sh            Up      6123/tcp, 8081/tcp              
flink-sql-cli-docker_taskmanager_1   /docker-entrypoint.sh task ...   Up      6123/tcp, 8081/tcp
Enter fullscreen mode Exit fullscreen mode

Flink's web UI is now available at localhost:8081. This is a useful tool for browsing information about Flink's status and the data pipelines we're going to create.

Flink Web UI

Notes about setting up Docker-Compose

In docker-compose.yml we map settings subfolder to the jobmanager docker container /settings folder. This way, settings files can be passed between host and guest, which is helpful if specific host generated files (e.g. Keystores) are needed for authentication.

The data subfolder is also mapped to the taskmanager and jobmanager containers. This is purely because I needed to provide the SQL example below, but could be useful in cases where we want to test Apache Flink behaviour against files in a local file system. The data subfolder contains a test.csv file with made-up data that we'll use to test Apache Flink.

Unleashing the power of SQL

If we want to play with Flink's SQL, we need to enter the sql-client container. We can do that by executing the following command in the terminal:

docker exec -it flink-sql-cli-docker_sql-client_1 /bin/bash
Enter fullscreen mode Exit fullscreen mode

Now we're in, and we can start the Flink's SQL client with

./sql-client.sh
Enter fullscreen mode Exit fullscreen mode

There we are! We have a fully functional SQL client that we can use to create data pipelines attaching to a variety of data sources and targets. As a little demo example we can query the test.csv file within the flink-sql-cli-docker/data folder by defining the associated Flink table within the SQL Client:

create table
  people_job (
    id INT,
    name STRING,
    job STRING,
    salary BIGINT
  )
  WITH (
    'connector' = 'filesystem',
    'path' = 'file:///data/test.csv',
    'format' = 'csv',
    'csv.ignore-parse-errors' = 'true'
    );
Enter fullscreen mode Exit fullscreen mode

And we can query the table:

select * from people_job;
Enter fullscreen mode Exit fullscreen mode

With the following results:

+/-                        id                      name                       job                    salary
  +                         1                       Ugo           Football Player                    200000
  +                         2                     Carlo    Crocodile domesticator                     30000
  +                         3                     Maria         Software Engineer                    210000
  +                         4                    Sandro               UX Designer                     70000
  +                         5                   Melissa         Software Engineer                     95000
Enter fullscreen mode Exit fullscreen mode

Exit Flink's table view by pressing Q.

Create a Data Target: PostgreSQL

Let's assume that we want to push the aggregated average salary and people count by job to a PostgreSQL table. If you don't have a PostgreSQL instance, you can quickly create it with the following Aiven's CLI command a new terminal window:

avn service create pg-flink   \
  -t pg                       \
  --cloud google-europe-west3 \
  --plan startup-4
Enter fullscreen mode Exit fullscreen mode

This creates a PostgreSQL instance (-t pg), in google-europe-west3 with a startup-4 plan. Let's wait for the service to be ready:

avn service wait pg-flink
Enter fullscreen mode Exit fullscreen mode

Let's create a target table job_details that we'll use to push data from Flink. From the same terminal window we can execute the following:

avn service cli pg-flink
Enter fullscreen mode Exit fullscreen mode

and then

create table job_summary (
  job VARCHAR PRIMARY KEY,
  avg_salary BIGINT,
  nr_people BIGINT
  );
Enter fullscreen mode Exit fullscreen mode

Create the SQL pipeline

Now it's time to retrieve the connection parameters to PostgreSQL with the following command in a new terminal window:

avn service get pg-flink \
  --format '{service_uri_params}'
Enter fullscreen mode Exit fullscreen mode

The output should be similar to the following:

{
  'dbname': 'defaultdb',
  'host': '<hostname>.aivencloud.com',
  'password': '<password>',
  'port': '13039',
  'sslmode': 'require',
  'user': 'avnadmin'
}
Enter fullscreen mode Exit fullscreen mode

Take note of the host, port, user, dbname and password details above and use them to create a Flink table pointing to PostgreSQL. Paste the following SQL into Flink's SQL Cli.

create table
  job_summary_flink(
    job STRING,
    avg_salary BIGINT,
    nr_people BIGINT,
    PRIMARY KEY (job) NOT ENFORCED
  )
  WITH (
    'connector' = 'jdbc',
    'url' = 'jdbc:postgresql://<host>:<port>/<dbname>?sslmode=require',
    'table-name' = 'job_summary',
    'username' = '<username>',
    'password' = '<password>'
    );
Enter fullscreen mode Exit fullscreen mode

Now let's create the SQL pipeline with the following command in Flink SQL Client:

insert into job_summary_flink
  select job,
    avg(salary),
    count(*)
  from people_job
  group by job;
Enter fullscreen mode Exit fullscreen mode

We should see an output from the SQL Client like this:

[INFO] Submitting SQL update statement to the cluster...
[INFO] Table update statement has been successfully submitted to the cluster:
Job ID: b2d8b019c6c6e3dc5fe63902a14c13a9
Enter fullscreen mode Exit fullscreen mode

And we can now check that Flink's table has been correctly populated with the following SQL from Flink's CLI:

select * from job_summary_flink;
Enter fullscreen mode Exit fullscreen mode

which results in

+/-                       job                avg_salary                 nr_people
  +               UX Designer                     70000                         1
  +    Crocodile domesticator                     30000                         1
  +           Football Player                    200000                         1
  +         Software Engineer                    152500                         2
Enter fullscreen mode Exit fullscreen mode

And also checking we can obtain the same result from PostgreSQL with the following command in the PostgreSQL client terminal window:

select * from job_summary;
Enter fullscreen mode Exit fullscreen mode

Resulting

         job           | avg_salary | nr_people
------------------------+------------+-----------
UX Designer            |      70000 |         1
Crocodile domesticator |      30000 |         1
Football Player        |     200000 |         1
Software Engineer      |     152500 |         2
(4 rows)
Enter fullscreen mode Exit fullscreen mode

Wrapping up

This blog post provides a way to get Apache Flink's SQL Client as a set of Docker containers. It expects additional data sources or targets to be available outside the container and can be used to start the learning journey into Flink. The sql pipeline example shows an integration between a local csv file and PostgreSQL. Check out this space, we'll publish more example of streaming pipelines in the future using Apache Flink in conjunction with other Aiven managed data structures!

Some additional resources:

Stay tuned for more content about Apache Flink in conjunctions with other Aiven's data services.

Top comments (0)

Read next

congcong profile image

GBASE数据库 | GBase 8c Compatibility Analysis with Distributed Databases

Cong Li -

peter_truchly_4fce0874fd5 profile image

Old-School Graphics in C# / .Net 8, Part 2: Fireworks and Advanced Vector Extensions (AVX, SSE)

Peter Truchly -

austin6799 profile image

5 Free GIS Software Options: Map the World

Austin -

mnboy profile image

Why Read/Write in Hash Maps Has O(1) Time Complexity⁉️🚀

Moein Salari -