Skip to content

fix(docs): Update getting-started script pre-26.3.0 #802

New issue

Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.

Sign up for GitHub

By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.

Already on GitHub? Sign in to your account

Merged
adwk67 merged 3 commits into from
Mar 11, 2026
Merged

fix(docs): Update getting-started script pre-26.3.0 #802

Show file tree
Hide file tree
Changes from all commits
Commits
Show all changes
3 commits
Select commit Hold shift + click to select a range
521569f
wait for nodes and crds, change to FQDN names as per integration test
adwk67 Mar 10, 2026
589bbdb
corrected docs, improved wait condition
adwk67 Mar 11, 2026
bb339ec
Merge branch 'main' into fix/getting-started-pre-26.3.0
adwk67 Mar 11, 2026
File filter

Filter by extension

Filter by extension
Conversations
Failed to load comments.
Loading
Jump to
Jump to file
Failed to load files.
Loading
Diff view
Diff view
61 changes: 34 additions & 27 deletions docs/modules/druid/examples/getting_started/getting_started.sh
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -20,6 +20,9 @@ then
exit 1
fi

echo "Waiting for node(s) to be ready..."
kubectl wait node --all --for=condition=Ready --timeout=120s

cd "$(dirname "$0")"

case "$1" in
Expand Down Expand Up @@ -52,6 +55,9 @@ exit 1
;;
esac

# TODO: Remove once https://github.com/stackabletech/issues/issues/828 has been implemented (see that issue for details).
until kubectl get crd druidclusters.druid.stackable.tech >/dev/null 2>&1; do echo "Waiting for CRDs to be installed" && sleep 1; done

echo "Installing ZooKeeper from zookeeper.yaml"
# tag::install-zookeeper[]
kubectl apply -f zookeeper.yaml
Expand Down Expand Up @@ -89,9 +95,9 @@ done

echo "Awaiting HDFS rollout finish"
# tag::watch-hdfs-rollout[]
kubectl rollout status --watch statefulset/simple-hdfs-datanode-default --timeout=300s
kubectl rollout status --watch statefulset/simple-hdfs-journalnode-default --timeout=300s
kubectl rollout status --watch statefulset/simple-hdfs-namenode-default --timeout=300s
kubectl rollout status --watch statefulset/simple-hdfs-datanode-default --timeout=600s
kubectl rollout status --watch statefulset/simple-hdfs-journalnode-default --timeout=600s
kubectl rollout status --watch statefulset/simple-hdfs-namenode-default --timeout=600s
# end::watch-hdfs-rollout[]

echo "Installing PostgreSQL for Druid"
Expand Down Expand Up @@ -125,39 +131,36 @@ done

echo "Awaiting Druid rollout finish"
# tag::watch-druid-rollout[]
kubectl rollout status --watch statefulset/simple-druid-broker-default --timeout=300s
kubectl rollout status --watch statefulset/simple-druid-coordinator-default --timeout=300s
kubectl rollout status --watch statefulset/simple-druid-historical-default --timeout=300s
kubectl rollout status --watch statefulset/simple-druid-middlemanager-default --timeout=300s
kubectl rollout status --watch statefulset/simple-druid-router-default --timeout=300s
kubectl rollout status --watch statefulset/simple-druid-broker-default --timeout=600s
kubectl rollout status --watch statefulset/simple-druid-coordinator-default --timeout=600s
kubectl rollout status --watch statefulset/simple-druid-historical-default --timeout=600s
kubectl rollout status --watch statefulset/simple-druid-middlemanager-default --timeout=600s
kubectl rollout status --watch statefulset/simple-druid-router-default --timeout=600s
# end::watch-druid-rollout[]

echo "Starting port-forwarding of port 9088"
# shellcheck disable=2069 # we want all output to be blackholed
# tag::port-forwarding[]
kubectl port-forward svc/simple-druid-router 9088 > /dev/null 2>&1 &
# end::port-forwarding[]
PORT_FORWARD_PID=$!
# shellcheck disable=2064 # we want the PID evaluated now, not at the time the trap is
trap "kill $PORT_FORWARD_PID" EXIT
sleep 5
COORDINATOR="simple-druid-coordinator-default-headless.default.svc.cluster.local"
BROKER="simple-druid-broker-default-headless.default.svc.cluster.local"

submit_job() {
# tag::submit-job[]
curl -s -k -X 'POST' -H 'Content-Type:application/json' -d @ingestion_spec.json https://localhost:9088/druid/indexer/v1/task
# end::submit-job[]
# tag::submit-job[]
kubectl exec simple-druid-coordinator-default-0 -i -- \
curl -s -k -X POST -H 'Content-Type:application/json' --data-binary @- \
"https://${COORDINATOR}:8281/druid/indexer/v1/task" < ingestion_spec.json
# end::submit-job[]
}

echo "Submitting job"
task_id=$(submit_job | sed -e 's/.*":"\([^"]\+\).*/\1/g')

request_job_status() {
curl -s -k "https://localhost:9088/druid/indexer/v1/task/${task_id}/status" | sed -e 's/.*statusCode":"\([^"]\+\).*/\1/g'
kubectl exec simple-druid-coordinator-default-0 -- \
curl -s -k "https://${COORDINATOR}:8281/druid/indexer/v1/task/${task_id}/status" \
| sed -e 's/.*statusCode":"\([^"]\+\).*/\1/g'
}

while [ "$(request_job_status)" == "RUNNING" ]; do
echo "Task still running..."
sleep 5
sleep 10
done

task_status=$(request_job_status)
Expand All @@ -170,18 +173,22 @@ else
fi

segment_load_status() {
curl -s -k https://localhost:9088/druid/coordinator/v1/loadstatus | sed -e 's/.*wikipedia":\([0-9\.]\+\).*/\1/g'
kubectl exec simple-druid-coordinator-default-0 -- \
curl -s -k "https://${COORDINATOR}:8281/druid/coordinator/v1/loadstatus" \
| sed -e 's/.*wikipedia":\([0-9\.]\+\).*/\1/g'
}

while [ "$(segment_load_status)" != "100.0" ]; do
echo "Segments still loading..."
sleep 5
sleep 10
done

query_data() {
# tag::query-data[]
curl -s -k -X 'POST' -H 'Content-Type:application/json' -d @query.json https://localhost:9088/druid/v2/sql
# end::query-data[]
# tag::query-data[]
kubectl exec simple-druid-broker-default-0 -i -- \
curl -s -k -X POST -H 'Content-Type:application/json' --data-binary @- \
"https://${BROKER}:8282/druid/v2/sql" < query.json
# end::query-data[]
}

echo "Querying data..."
Expand Down
61 changes: 34 additions & 27 deletions docs/modules/druid/examples/getting_started/getting_started.sh.j2
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -20,6 +20,9 @@ then
exit 1
fi

echo "Waiting for node(s) to be ready..."
kubectl wait node --all --for=condition=Ready --timeout=120s

cd "$(dirname "$0")"

case "$1" in
Expand Down Expand Up @@ -52,6 +55,9 @@ exit 1
;;
esac

# TODO: Remove once https://github.com/stackabletech/issues/issues/828 has been implemented (see that issue for details).
until kubectl get crd druidclusters.druid.stackable.tech >/dev/null 2>&1; do echo "Waiting for CRDs to be installed" && sleep 1; done

echo "Installing ZooKeeper from zookeeper.yaml"
# tag::install-zookeeper[]
kubectl apply -f zookeeper.yaml
Expand Down Expand Up @@ -89,9 +95,9 @@ done

echo "Awaiting HDFS rollout finish"
# tag::watch-hdfs-rollout[]
kubectl rollout status --watch statefulset/simple-hdfs-datanode-default --timeout=300s
kubectl rollout status --watch statefulset/simple-hdfs-journalnode-default --timeout=300s
kubectl rollout status --watch statefulset/simple-hdfs-namenode-default --timeout=300s
kubectl rollout status --watch statefulset/simple-hdfs-datanode-default --timeout=600s
kubectl rollout status --watch statefulset/simple-hdfs-journalnode-default --timeout=600s
kubectl rollout status --watch statefulset/simple-hdfs-namenode-default --timeout=600s
# end::watch-hdfs-rollout[]

echo "Installing PostgreSQL for Druid"
Expand Down Expand Up @@ -125,39 +131,36 @@ done

echo "Awaiting Druid rollout finish"
# tag::watch-druid-rollout[]
kubectl rollout status --watch statefulset/simple-druid-broker-default --timeout=300s
kubectl rollout status --watch statefulset/simple-druid-coordinator-default --timeout=300s
kubectl rollout status --watch statefulset/simple-druid-historical-default --timeout=300s
kubectl rollout status --watch statefulset/simple-druid-middlemanager-default --timeout=300s
kubectl rollout status --watch statefulset/simple-druid-router-default --timeout=300s
kubectl rollout status --watch statefulset/simple-druid-broker-default --timeout=600s
kubectl rollout status --watch statefulset/simple-druid-coordinator-default --timeout=600s
kubectl rollout status --watch statefulset/simple-druid-historical-default --timeout=600s
kubectl rollout status --watch statefulset/simple-druid-middlemanager-default --timeout=600s
kubectl rollout status --watch statefulset/simple-druid-router-default --timeout=600s
# end::watch-druid-rollout[]

echo "Starting port-forwarding of port 9088"
# shellcheck disable=2069 # we want all output to be blackholed
# tag::port-forwarding[]
kubectl port-forward svc/simple-druid-router 9088 > /dev/null 2>&1 &
# end::port-forwarding[]
PORT_FORWARD_PID=$!
# shellcheck disable=2064 # we want the PID evaluated now, not at the time the trap is
trap "kill $PORT_FORWARD_PID" EXIT
sleep 5
COORDINATOR="simple-druid-coordinator-default-headless.default.svc.cluster.local"
BROKER="simple-druid-broker-default-headless.default.svc.cluster.local"

submit_job() {
# tag::submit-job[]
curl -s -k -X 'POST' -H 'Content-Type:application/json' -d @ingestion_spec.json https://localhost:9088/druid/indexer/v1/task
# end::submit-job[]
# tag::submit-job[]
kubectl exec simple-druid-coordinator-default-0 -i -- \
curl -s -k -X POST -H 'Content-Type:application/json' --data-binary @- \
"https://${COORDINATOR}:8281/druid/indexer/v1/task" < ingestion_spec.json
# end::submit-job[]
}

echo "Submitting job"
task_id=$(submit_job | sed -e 's/.*":"\([^"]\+\).*/\1/g')

request_job_status() {
curl -s -k "https://localhost:9088/druid/indexer/v1/task/${task_id}/status" | sed -e 's/.*statusCode":"\([^"]\+\).*/\1/g'
kubectl exec simple-druid-coordinator-default-0 -- \
curl -s -k "https://${COORDINATOR}:8281/druid/indexer/v1/task/${task_id}/status" \
| sed -e 's/.*statusCode":"\([^"]\+\).*/\1/g'
}

while [ "$(request_job_status)" == "RUNNING" ]; do
echo "Task still running..."
sleep 5
sleep 10
done

task_status=$(request_job_status)
Expand All @@ -170,18 +173,22 @@ else
fi

segment_load_status() {
curl -s -k https://localhost:9088/druid/coordinator/v1/loadstatus | sed -e 's/.*wikipedia":\([0-9\.]\+\).*/\1/g'
kubectl exec simple-druid-coordinator-default-0 -- \
curl -s -k "https://${COORDINATOR}:8281/druid/coordinator/v1/loadstatus" \
| sed -e 's/.*wikipedia":\([0-9\.]\+\).*/\1/g'
}

while [ "$(segment_load_status)" != "100.0" ]; do
echo "Segments still loading..."
sleep 5
sleep 10
done

query_data() {
# tag::query-data[]
curl -s -k -X 'POST' -H 'Content-Type:application/json' -d @query.json https://localhost:9088/druid/v2/sql
# end::query-data[]
# tag::query-data[]
kubectl exec simple-druid-broker-default-0 -i -- \
curl -s -k -X POST -H 'Content-Type:application/json' --data-binary @- \
"https://${BROKER}:8282/druid/v2/sql" < query.json
# end::query-data[]
}

echo "Querying data..."
Expand Down
12 changes: 5 additions & 7 deletions docs/modules/druid/pages/getting_started/first_steps.adoc
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -106,20 +106,18 @@ simple-hdfs-namenode-default 2/2 6m
simple-zk-server-default 3/3 7m
----

Ideally you use `stackablectl stacklet list` to find out the address the Druid router is reachable at and use that address.
=== Ingest example data

As an alternative, you can create a port-forward for the Druid Router:
Next, ingest some example data using the web interface.
You can either use `stackablectl stacklet list` to find out the address the Druid router is reachable at and use that address, or you can create a port-forward for the Druid Router:

[source,bash]
----
include::example$getting_started/getting_started.sh[tag=port-forwarding]
kubectl port-forward svc/simple-druid-router 9088 > /dev/null 2>&1 &
----

=== Ingest example data

Next, ingest some example data using the web interface.
If you prefer to use the command line instead, follow the instructions in the collapsed section below.


[#ingest-cmd-line]
.Alternative: Using the command line
[%collapsible]
Expand Down
Loading