Skip to content
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.

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

chore: bump hdfs version to 3.4.0 #98

Merged
merged 1 commit into from
Sep 20, 2024
Merged
Show file tree
Hide file tree
Changes from all commits
Commits
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
3 changes: 2 additions & 1 deletion demos/hbase-hdfs-load-cycling-data/distcp-cycling-data.yaml
Original file line number Diff line number Diff line change
Expand Up @@ -11,14 +11,15 @@ spec:
# We use 24.3.0 here which contains the distcp MapReduce components
# This is not included in the 24.7 images and will fail.
# See: https://github.com/stackabletech/docker-images/issues/793
image: docker.stackable.tech/stackable/hadoop:3.3.4-stackable24.3.0
image: docker.stackable.tech/stackable/hadoop:3.4.0-stackable24.11.0
env:
- name: HADOOP_USER_NAME
value: stackable
- name: HADOOP_CONF_DIR
value: "/stackable/conf/hdfs"
- name: HADOOP_CLASSPATH
value: "/stackable/hadoop/share/hadoop/tools/lib/*.jar"
# yamllint disable-line rule:line-length
command: ["bash", "-c", "bin/hdfs dfs -mkdir -p /data/raw && bin/hadoop distcp -D fs.s3a.aws.credentials.provider=org.apache.hadoop.fs.s3a.AnonymousAWSCredentialsProvider s3a://public-backup-nyc-tlc/cycling-tripdata/demo-cycling-tripdata.csv.gz hdfs://hdfs/data/raw"]
volumeMounts:
- name: config-volume-hdfs
Expand Down
Original file line number Diff line number Diff line change
Expand Up @@ -8,13 +8,15 @@ spec:
spec:
containers:
- name: load-ny-taxi-data
image: docker.stackable.tech/stackable/hadoop:3.3.4-stackable24.7.0
image: docker.stackable.tech/stackable/hadoop:3.4.0-stackable24.11.0
# yamllint disable rule:line-length
command: ["bash", "-c", "/stackable/hadoop/bin/hdfs dfs -mkdir -p /ny-taxi-data/raw \
&& cd /tmp \
&& for month in 2020-09; do \
curl -O https://repo.stackable.tech/repository/misc/ny-taxi-data/fhvhv_tripdata_$month.parquet \
&& /stackable/hadoop/bin/hdfs dfs -put fhvhv_tripdata_$month.parquet /ny-taxi-data/raw/; \
done"]
# yamllint enable rule:line-length
volumeMounts:
- name: hdfs-discovery-configmap
mountPath: /hdfs
Expand Down
Original file line number Diff line number Diff line change
Expand Up @@ -9,6 +9,7 @@ spec:
containers:
- name: load-ny-taxi-data
image: "bitnami/minio:2022-debian-10"
# yamllint disable-line rule:line-length
command: ["bash", "-c", "cd /tmp && for month in 2020-09 2020-10 2020-11 2020-12; do curl -O https://repo.stackable.tech/repository/misc/ny-taxi-data/fhvhv_tripdata_$month.parquet && mc --insecure alias set minio http://minio:9000/ $(cat /minio-s3-credentials/accessKey) $(cat /minio-s3-credentials/secretKey) && mc cp fhvhv_tripdata_$month.parquet minio/demo/ny-taxi-data/raw/ && mc mb --ignore-existing minio/prediction; done"]
volumeMounts:
- name: minio-s3-credentials
Expand Down
1 change: 1 addition & 0 deletions demos/trino-taxi-data/load-test-data.yaml
Original file line number Diff line number Diff line change
Expand Up @@ -9,6 +9,7 @@ spec:
containers:
- name: load-ny-taxi-data
image: "bitnami/minio:2024-debian-12"
# yamllint disable-line rule:line-length
command: ["bash", "-c", "cd /tmp && for month in 2020-01 2020-02 2020-03 2020-04 2020-05 2020-06 2020-07 2020-08 2020-09 2020-10 2020-11 2020-12 2021-01 2021-02 2021-03 2021-04 2021-05 2021-06 2021-07 2021-08 2021-09 2021-10 2021-11 2021-12 2022-01 2022-02 2022-03 2022-04; do curl -O https://repo.stackable.tech/repository/misc/ny-taxi-data/yellow_tripdata_$month.parquet && mc --insecure alias set minio http://minio:9000/ $(cat /minio-s3-credentials/accessKey) $(cat /minio-s3-credentials/secretKey) && mc cp yellow_tripdata_$month.parquet minio/demo/ny-taxi-data/raw/; done"]
volumeMounts:
- name: minio-s3-credentials
Expand Down
2 changes: 1 addition & 1 deletion stacks/dual-hive-hdfs-s3/hdfs.yaml
Original file line number Diff line number Diff line change
Expand Up @@ -25,7 +25,7 @@ metadata:
name: hdfs
spec:
image:
productVersion: 3.3.4
productVersion: 3.4.0
clusterConfig:
listenerClass: external-unstable
dfsReplication: 1
Expand Down
8 changes: 5 additions & 3 deletions stacks/end-to-end-security/hdfs.yaml
Original file line number Diff line number Diff line change
@@ -1,10 +1,11 @@
---
apiVersion: hdfs.stackable.tech/v1alpha1
kind: HdfsCluster
metadata:
name: hdfs
spec:
image:
productVersion: 3.3.4
productVersion: 3.4.0
clusterConfig:
zookeeperConfigMapName: hdfs-znode
authentication:
Expand All @@ -29,8 +30,9 @@ spec:
level: DEBUG
configOverrides: &configOverrides
core-site.xml:
# The idea is that the user "hive" can't do anything in hdfs, *but* it can impersonate other users
# (such as trino), that have the needed permissions
# The idea is that the user "hive" can't do anything in hdfs,
# *but* it can impersonate other users (such as trino),
# that have the needed permissions
hadoop.proxyuser.hive.users: "*"
hadoop.proxyuser.hive.hosts: "*"
roleGroups:
Expand Down
3 changes: 2 additions & 1 deletion stacks/hdfs-hbase/hdfs.yaml
Original file line number Diff line number Diff line change
@@ -1,10 +1,11 @@
---
apiVersion: hdfs.stackable.tech/v1alpha1
kind: HdfsCluster
metadata:
name: hdfs
spec:
image:
productVersion: 3.3.4
productVersion: 3.4.0
clusterConfig:
dfsReplication: 1
zookeeperConfigMapName: hdfs-znode
Expand Down
2 changes: 1 addition & 1 deletion stacks/jupyterhub-pyspark-hdfs/hdfs.yaml
Original file line number Diff line number Diff line change
Expand Up @@ -13,7 +13,7 @@ metadata:
name: hdfs
spec:
image:
productVersion: 3.3.4
productVersion: 3.4.0
clusterConfig:
dfsReplication: 1
zookeeperConfigMapName: hdfs-znode
Expand Down
2 changes: 1 addition & 1 deletion stacks/keycloak-opa-poc/hdfs.yaml
Original file line number Diff line number Diff line change
Expand Up @@ -5,7 +5,7 @@ metadata:
name: hdfs
spec:
image:
productVersion: 3.3.4
productVersion: 3.4.0
clusterConfig:
dfsReplication: 1
zookeeperConfigMapName: hdfs-znode
Expand Down