This is an automated email from the ASF dual-hosted git repository.
xushiyan pushed a commit to branch asf-site
in repository https://gitbox.apache.org/repos/asf/hudi.git
The following commit(s) were added to refs/heads/asf-site by this push:
new 698c319ce9bd docs: set `--master` to `local[2]` for the
spark-shell/pyspark/spark-sql in quickstart examples (#14187)
698c319ce9bd is described below
commit 698c319ce9bd3ea6b4449a4d08f22d49c855ada6
Author: Ranga Reddy <[email protected]>
AuthorDate: Mon Nov 3 23:02:41 2025 +0530
docs: set `--master` to `local[2]` for the spark-shell/pyspark/spark-sql in
quickstart examples (#14187)
---
website/docs/quick-start-guide.md | 29 ++++----
.../version-0.14.0/quick-start-guide.md | 57 +++++++++++++---
.../version-0.14.1/quick-start-guide.md | 57 +++++++++++++---
.../version-0.15.0/quick-start-guide.md | 77 ++++++++++++++--------
.../version-1.0.0/quick-start-guide.md | 29 ++++----
.../version-1.0.1/quick-start-guide.md | 29 ++++----
.../version-1.0.2/quick-start-guide.md | 29 ++++----
7 files changed, 216 insertions(+), 91 deletions(-)
diff --git a/website/docs/quick-start-guide.md
b/website/docs/quick-start-guide.md
index 9a91fa3e17fa..345ef2b25f38 100644
--- a/website/docs/quick-start-guide.md
+++ b/website/docs/quick-start-guide.md
@@ -58,11 +58,12 @@ From the extracted directory run spark-shell with Hudi:
```shell
# For Spark versions: 3.3 - 3.5
export SPARK_VERSION=3.5 # or 3.4, 3.3
-spark-shell --packages
org.apache.hudi:hudi-spark$SPARK_VERSION-bundle_2.12:1.0.2 \
---conf 'spark.serializer=org.apache.spark.serializer.KryoSerializer' \
---conf
'spark.sql.catalog.spark_catalog=org.apache.spark.sql.hudi.catalog.HoodieCatalog'
\
---conf
'spark.sql.extensions=org.apache.spark.sql.hudi.HoodieSparkSessionExtension' \
---conf 'spark.kryo.registrator=org.apache.spark.HoodieSparkKryoRegistrar'
+spark-shell --master "local[2]" \
+ --packages org.apache.hudi:hudi-spark$SPARK_VERSION-bundle_2.12:1.0.2 \
+ --conf 'spark.serializer=org.apache.spark.serializer.KryoSerializer' \
+ --conf
'spark.sql.catalog.spark_catalog=org.apache.spark.sql.hudi.catalog.HoodieCatalog'
\
+ --conf
'spark.sql.extensions=org.apache.spark.sql.hudi.HoodieSparkSessionExtension' \
+ --conf 'spark.kryo.registrator=org.apache.spark.HoodieSparkKryoRegistrar'
```
</TabItem>
@@ -74,7 +75,12 @@ From the extracted directory run pyspark with Hudi:
# For Spark versions: 3.3 - 3.5
export PYSPARK_PYTHON=$(which python3)
export SPARK_VERSION=3.5 # or 3.4, 3.3
-pyspark --packages org.apache.hudi:hudi-spark$SPARK_VERSION-bundle_2.12:1.0.2
--conf 'spark.serializer=org.apache.spark.serializer.KryoSerializer' --conf
'spark.sql.catalog.spark_catalog=org.apache.spark.sql.hudi.catalog.HoodieCatalog'
--conf
'spark.sql.extensions=org.apache.spark.sql.hudi.HoodieSparkSessionExtension'
--conf 'spark.kryo.registrator=org.apache.spark.HoodieSparkKryoRegistrar'
+pyspark --master "local[2]" \
+ --packages org.apache.hudi:hudi-spark$SPARK_VERSION-bundle_2.12:1.0.2 \
+ --conf 'spark.serializer=org.apache.spark.serializer.KryoSerializer' \
+ --conf
'spark.sql.catalog.spark_catalog=org.apache.spark.sql.hudi.catalog.HoodieCatalog'
\
+ --conf
'spark.sql.extensions=org.apache.spark.sql.hudi.HoodieSparkSessionExtension' \
+ --conf 'spark.kryo.registrator=org.apache.spark.HoodieSparkKryoRegistrar'
```
</TabItem>
@@ -86,11 +92,12 @@ From the extracted directory run Spark SQL with Hudi:
```shell
# For Spark versions: 3.3 - 3.5
export SPARK_VERSION=3.5 # or 3.4, 3.3
-spark-sql --packages
org.apache.hudi:hudi-spark$SPARK_VERSION-bundle_2.12:1.0.2 \
---conf 'spark.serializer=org.apache.spark.serializer.KryoSerializer' \
---conf
'spark.sql.extensions=org.apache.spark.sql.hudi.HoodieSparkSessionExtension' \
---conf
'spark.sql.catalog.spark_catalog=org.apache.spark.sql.hudi.catalog.HoodieCatalog'
\
---conf 'spark.kryo.registrator=org.apache.spark.HoodieSparkKryoRegistrar'
+spark-sql --master "local[2]" \
+ --packages org.apache.hudi:hudi-spark$SPARK_VERSION-bundle_2.12:1.0.2 \
+ --conf 'spark.serializer=org.apache.spark.serializer.KryoSerializer' \
+ --conf
'spark.sql.extensions=org.apache.spark.sql.hudi.HoodieSparkSessionExtension' \
+ --conf
'spark.sql.catalog.spark_catalog=org.apache.spark.sql.hudi.catalog.HoodieCatalog'
\
+ --conf 'spark.kryo.registrator=org.apache.spark.HoodieSparkKryoRegistrar'
```
</TabItem>
</Tabs>
diff --git a/website/versioned_docs/version-0.14.0/quick-start-guide.md
b/website/versioned_docs/version-0.14.0/quick-start-guide.md
index 32c89b2afe07..da053f0a3a1e 100644
--- a/website/versioned_docs/version-0.14.0/quick-start-guide.md
+++ b/website/versioned_docs/version-0.14.0/quick-start-guide.md
@@ -54,16 +54,29 @@ From the extracted directory run spark-shell with Hudi:
```shell
# For Spark versions: 3.2 - 3.4
export SPARK_VERSION=3.4
-spark-shell --packages
org.apache.hudi:hudi-spark$SPARK_VERSION-bundle_2.12:0.14.0 --conf
'spark.serializer=org.apache.spark.serializer.KryoSerializer' --conf
'spark.sql.catalog.spark_catalog=org.apache.spark.sql.hudi.catalog.HoodieCatalog'
--conf
'spark.sql.extensions=org.apache.spark.sql.hudi.HoodieSparkSessionExtension'
--conf 'spark.kryo.registrator=org.apache.spark.HoodieSparkKryoRegistrar'
+spark-shell --master "local[2]" \
+ --packages org.apache.hudi:hudi-spark$SPARK_VERSION-bundle_2.12:0.14.0 \
+ --conf 'spark.serializer=org.apache.spark.serializer.KryoSerializer' \
+ --conf
'spark.sql.catalog.spark_catalog=org.apache.spark.sql.hudi.catalog.HoodieCatalog'
\
+ --conf
'spark.sql.extensions=org.apache.spark.sql.hudi.HoodieSparkSessionExtension' \
+ --conf 'spark.kryo.registrator=org.apache.spark.HoodieSparkKryoRegistrar'
```
```shell
# For Spark versions: 3.0 - 3.1
export SPARK_VERSION=3.1
-spark-shell --packages
org.apache.hudi:hudi-spark$SPARK_VERSION-bundle_2.12:0.14.0 --conf
'spark.serializer=org.apache.spark.serializer.KryoSerializer' --conf
'spark.sql.extensions=org.apache.spark.sql.hudi.HoodieSparkSessionExtension'
--conf 'spark.kryo.registrator=org.apache.spark.HoodieSparkKryoRegistrar'
+spark-shell --master "local[2]" \
+ --packages org.apache.hudi:hudi-spark$SPARK_VERSION-bundle_2.12:0.14.0 \
+ --conf 'spark.serializer=org.apache.spark.serializer.KryoSerializer' \
+ --conf
'spark.sql.extensions=org.apache.spark.sql.hudi.HoodieSparkSessionExtension' \
+ --conf 'spark.kryo.registrator=org.apache.spark.HoodieSparkKryoRegistrar'
```
```shell
# For Spark version: 2.4
-spark-shell --packages org.apache.hudi:hudi-spark2.4-bundle_2.11:0.14.0 --conf
'spark.serializer=org.apache.spark.serializer.KryoSerializer' --conf
'spark.sql.extensions=org.apache.spark.sql.hudi.HoodieSparkSessionExtension'
--conf 'spark.kryo.registrator=org.apache.spark.HoodieSparkKryoRegistrar'
+spark-shell --master "local[2]" \
+ --packages org.apache.hudi:hudi-spark2.4-bundle_2.11:0.14.0 \
+ --conf 'spark.serializer=org.apache.spark.serializer.KryoSerializer' \
+ --conf
'spark.sql.extensions=org.apache.spark.sql.hudi.HoodieSparkSessionExtension' \
+ --conf 'spark.kryo.registrator=org.apache.spark.HoodieSparkKryoRegistrar'
```
</TabItem>
@@ -75,18 +88,31 @@ From the extracted directory run pyspark with Hudi:
# For Spark versions: 3.2 - 3.4
export PYSPARK_PYTHON=$(which python3)
export SPARK_VERSION=3.4
-pyspark --packages org.apache.hudi:hudi-spark$SPARK_VERSION-bundle_2.12:0.14.0
--conf 'spark.serializer=org.apache.spark.serializer.KryoSerializer' --conf
'spark.sql.catalog.spark_catalog=org.apache.spark.sql.hudi.catalog.HoodieCatalog'
--conf
'spark.sql.extensions=org.apache.spark.sql.hudi.HoodieSparkSessionExtension'
--conf 'spark.kryo.registrator=org.apache.spark.HoodieSparkKryoRegistrar'
+pyspark --master "local[2]" \
+ --packages org.apache.hudi:hudi-spark$SPARK_VERSION-bundle_2.12:0.14.0 \
+ --conf 'spark.serializer=org.apache.spark.serializer.KryoSerializer' \
+ --conf
'spark.sql.catalog.spark_catalog=org.apache.spark.sql.hudi.catalog.HoodieCatalog'
\
+ --conf
'spark.sql.extensions=org.apache.spark.sql.hudi.HoodieSparkSessionExtension' \
+ --conf 'spark.kryo.registrator=org.apache.spark.HoodieSparkKryoRegistrar'
```
```shell
# For Spark versions: 3.0 - 3.1
export PYSPARK_PYTHON=$(which python3)
export SPARK_VERSION=3.1
-pyspark --packages org.apache.hudi:hudi-spark$SPARK_VERSION-bundle_2.12:0.14.0
--conf 'spark.serializer=org.apache.spark.serializer.KryoSerializer' --conf
'spark.sql.extensions=org.apache.spark.sql.hudi.HoodieSparkSessionExtension'
--conf 'spark.kryo.registrator=org.apache.spark.HoodieSparkKryoRegistrar'
+pyspark --master "local[2]" \
+ --packages org.apache.hudi:hudi-spark$SPARK_VERSION-bundle_2.12:0.14.0 \
+ --conf 'spark.serializer=org.apache.spark.serializer.KryoSerializer' \
+ --conf
'spark.sql.extensions=org.apache.spark.sql.hudi.HoodieSparkSessionExtension' \
+ --conf 'spark.kryo.registrator=org.apache.spark.HoodieSparkKryoRegistrar'
```
```shell
# For Spark version: 2.4
export PYSPARK_PYTHON=$(which python3)
-pyspark --packages org.apache.hudi:hudi-spark2.4-bundle_2.11:0.14.0 --conf
'spark.serializer=org.apache.spark.serializer.KryoSerializer' --conf
'spark.sql.extensions=org.apache.spark.sql.hudi.HoodieSparkSessionExtension'
--conf 'spark.kryo.registrator=org.apache.spark.HoodieSparkKryoRegistrar'
+pyspark --master "local[2]" \
+ --packages org.apache.hudi:hudi-spark2.4-bundle_2.11:0.14.0 \
+ --conf 'spark.serializer=org.apache.spark.serializer.KryoSerializer' \
+ --conf
'spark.sql.extensions=org.apache.spark.sql.hudi.HoodieSparkSessionExtension' \
+ --conf 'spark.kryo.registrator=org.apache.spark.HoodieSparkKryoRegistrar'
```
</TabItem>
@@ -98,16 +124,29 @@ From the extracted directory run Spark SQL with Hudi:
```shell
# For Spark versions: 3.2 - 3.4
export SPARK_VERSION=3.4
-spark-sql --packages
org.apache.hudi:hudi-spark$SPARK_VERSION-bundle_2.12:0.14.0 --conf
'spark.serializer=org.apache.spark.serializer.KryoSerializer' --conf
'spark.sql.extensions=org.apache.spark.sql.hudi.HoodieSparkSessionExtension'
--conf
'spark.sql.catalog.spark_catalog=org.apache.spark.sql.hudi.catalog.HoodieCatalog'
--conf 'spark.kryo.registrator=org.apache.spark.HoodieSparkKryoRegistrar'
+spark-sql --master "local[2]" \
+ --packages org.apache.hudi:hudi-spark$SPARK_VERSION-bundle_2.12:0.14.0 \
+ --conf 'spark.serializer=org.apache.spark.serializer.KryoSerializer' \
+ --conf
'spark.sql.extensions=org.apache.spark.sql.hudi.HoodieSparkSessionExtension' \
+ --conf
'spark.sql.catalog.spark_catalog=org.apache.spark.sql.hudi.catalog.HoodieCatalog'
\
+ --conf 'spark.kryo.registrator=org.apache.spark.HoodieSparkKryoRegistrar'
```
```shell
# For Spark versions: 3.0 - 3.1
export SPARK_VERSION=3.1
-spark-sql --packages
org.apache.hudi:hudi-spark$SPARK_VERSION-bundle_2.12:0.14.0 --conf
'spark.serializer=org.apache.spark.serializer.KryoSerializer' --conf
'spark.sql.extensions=org.apache.spark.sql.hudi.HoodieSparkSessionExtension'
--conf 'spark.kryo.registrator=org.apache.spark.HoodieSparkKryoRegistrar'
+spark-sql --master "local[2]" \
+ --packages org.apache.hudi:hudi-spark$SPARK_VERSION-bundle_2.12:0.14.0 \
+ --conf 'spark.serializer=org.apache.spark.serializer.KryoSerializer' \
+ --conf
'spark.sql.extensions=org.apache.spark.sql.hudi.HoodieSparkSessionExtension' \
+ --conf 'spark.kryo.registrator=org.apache.spark.HoodieSparkKryoRegistrar'
```
```shell
# For Spark version: 2.4
-spark-sql --packages org.apache.hudi:hudi-spark2.4-bundle_2.11:0.14.0 --conf
'spark.serializer=org.apache.spark.serializer.KryoSerializer' --conf
'spark.sql.extensions=org.apache.spark.sql.hudi.HoodieSparkSessionExtension'
--conf 'spark.kryo.registrator=org.apache.spark.HoodieSparkKryoRegistrar'
+spark-sql --master "local[2]" \
+ --packages org.apache.hudi:hudi-spark2.4-bundle_2.11:0.14.0 \
+ --conf 'spark.serializer=org.apache.spark.serializer.KryoSerializer' \
+ --conf
'spark.sql.extensions=org.apache.spark.sql.hudi.HoodieSparkSessionExtension' \
+ --conf 'spark.kryo.registrator=org.apache.spark.HoodieSparkKryoRegistrar'
```
</TabItem>
diff --git a/website/versioned_docs/version-0.14.1/quick-start-guide.md
b/website/versioned_docs/version-0.14.1/quick-start-guide.md
index 3c78608036fa..cacffc673837 100644
--- a/website/versioned_docs/version-0.14.1/quick-start-guide.md
+++ b/website/versioned_docs/version-0.14.1/quick-start-guide.md
@@ -54,16 +54,29 @@ From the extracted directory run spark-shell with Hudi:
```shell
# For Spark versions: 3.2 - 3.4
export SPARK_VERSION=3.4
-spark-shell --packages
org.apache.hudi:hudi-spark$SPARK_VERSION-bundle_2.12:0.14.1 --conf
'spark.serializer=org.apache.spark.serializer.KryoSerializer' --conf
'spark.sql.catalog.spark_catalog=org.apache.spark.sql.hudi.catalog.HoodieCatalog'
--conf
'spark.sql.extensions=org.apache.spark.sql.hudi.HoodieSparkSessionExtension'
--conf 'spark.kryo.registrator=org.apache.spark.HoodieSparkKryoRegistrar'
+spark-shell --master "local[2]" \
+ --packages org.apache.hudi:hudi-spark$SPARK_VERSION-bundle_2.12:0.14.1 \
+ --conf 'spark.serializer=org.apache.spark.serializer.KryoSerializer' \
+ --conf
'spark.sql.catalog.spark_catalog=org.apache.spark.sql.hudi.catalog.HoodieCatalog'
\
+ --conf
'spark.sql.extensions=org.apache.spark.sql.hudi.HoodieSparkSessionExtension' \
+ --conf 'spark.kryo.registrator=org.apache.spark.HoodieSparkKryoRegistrar'
```
```shell
# For Spark versions: 3.0 - 3.1
export SPARK_VERSION=3.1
-spark-shell --packages
org.apache.hudi:hudi-spark$SPARK_VERSION-bundle_2.12:0.14.1 --conf
'spark.serializer=org.apache.spark.serializer.KryoSerializer' --conf
'spark.sql.extensions=org.apache.spark.sql.hudi.HoodieSparkSessionExtension'
--conf 'spark.kryo.registrator=org.apache.spark.HoodieSparkKryoRegistrar'
+spark-shell --master "local[2]" \
+ --packages org.apache.hudi:hudi-spark$SPARK_VERSION-bundle_2.12:0.14.1 \
+ --conf 'spark.serializer=org.apache.spark.serializer.KryoSerializer' \
+ --conf
'spark.sql.extensions=org.apache.spark.sql.hudi.HoodieSparkSessionExtension' \
+ --conf 'spark.kryo.registrator=org.apache.spark.HoodieSparkKryoRegistrar'
```
```shell
# For Spark version: 2.4
-spark-shell --packages org.apache.hudi:hudi-spark2.4-bundle_2.11:0.14.1 --conf
'spark.serializer=org.apache.spark.serializer.KryoSerializer' --conf
'spark.sql.extensions=org.apache.spark.sql.hudi.HoodieSparkSessionExtension'
--conf 'spark.kryo.registrator=org.apache.spark.HoodieSparkKryoRegistrar'
+spark-shell --master "local[2]" \
+ --packages org.apache.hudi:hudi-spark2.4-bundle_2.11:0.14.1 \
+ --conf 'spark.serializer=org.apache.spark.serializer.KryoSerializer' \
+ --conf
'spark.sql.extensions=org.apache.spark.sql.hudi.HoodieSparkSessionExtension' \
+ --conf 'spark.kryo.registrator=org.apache.spark.HoodieSparkKryoRegistrar'
```
</TabItem>
@@ -75,18 +88,31 @@ From the extracted directory run pyspark with Hudi:
# For Spark versions: 3.2 - 3.4
export PYSPARK_PYTHON=$(which python3)
export SPARK_VERSION=3.4
-pyspark --packages org.apache.hudi:hudi-spark$SPARK_VERSION-bundle_2.12:0.14.1
--conf 'spark.serializer=org.apache.spark.serializer.KryoSerializer' --conf
'spark.sql.catalog.spark_catalog=org.apache.spark.sql.hudi.catalog.HoodieCatalog'
--conf
'spark.sql.extensions=org.apache.spark.sql.hudi.HoodieSparkSessionExtension'
--conf 'spark.kryo.registrator=org.apache.spark.HoodieSparkKryoRegistrar'
+pyspark --master "local[2]" \
+ --packages org.apache.hudi:hudi-spark$SPARK_VERSION-bundle_2.12:0.14.1 \
+ --conf 'spark.serializer=org.apache.spark.serializer.KryoSerializer' \
+ --conf
'spark.sql.catalog.spark_catalog=org.apache.spark.sql.hudi.catalog.HoodieCatalog'
\
+ --conf
'spark.sql.extensions=org.apache.spark.sql.hudi.HoodieSparkSessionExtension' \
+ --conf 'spark.kryo.registrator=org.apache.spark.HoodieSparkKryoRegistrar'
```
```shell
# For Spark versions: 3.0 - 3.1
export PYSPARK_PYTHON=$(which python3)
export SPARK_VERSION=3.1
-pyspark --packages org.apache.hudi:hudi-spark$SPARK_VERSION-bundle_2.12:0.14.1
--conf 'spark.serializer=org.apache.spark.serializer.KryoSerializer' --conf
'spark.sql.extensions=org.apache.spark.sql.hudi.HoodieSparkSessionExtension'
--conf 'spark.kryo.registrator=org.apache.spark.HoodieSparkKryoRegistrar'
+pyspark --master "local[2]" \
+ --packages org.apache.hudi:hudi-spark$SPARK_VERSION-bundle_2.12:0.14.1 \
+ --conf 'spark.serializer=org.apache.spark.serializer.KryoSerializer' \
+ --conf
'spark.sql.extensions=org.apache.spark.sql.hudi.HoodieSparkSessionExtension' \
+ --conf 'spark.kryo.registrator=org.apache.spark.HoodieSparkKryoRegistrar'
```
```shell
# For Spark version: 2.4
export PYSPARK_PYTHON=$(which python3)
-pyspark --packages org.apache.hudi:hudi-spark2.4-bundle_2.11:0.14.1 --conf
'spark.serializer=org.apache.spark.serializer.KryoSerializer' --conf
'spark.sql.extensions=org.apache.spark.sql.hudi.HoodieSparkSessionExtension'
--conf 'spark.kryo.registrator=org.apache.spark.HoodieSparkKryoRegistrar'
+pyspark --master "local[2]" \
+ --packages org.apache.hudi:hudi-spark2.4-bundle_2.11:0.14.1 \
+ --conf 'spark.serializer=org.apache.spark.serializer.KryoSerializer' \
+ --conf
'spark.sql.extensions=org.apache.spark.sql.hudi.HoodieSparkSessionExtension' \
+ --conf 'spark.kryo.registrator=org.apache.spark.HoodieSparkKryoRegistrar'
```
</TabItem>
@@ -98,16 +124,29 @@ From the extracted directory run Spark SQL with Hudi:
```shell
# For Spark versions: 3.2 - 3.4
export SPARK_VERSION=3.4
-spark-sql --packages
org.apache.hudi:hudi-spark$SPARK_VERSION-bundle_2.12:0.14.1 --conf
'spark.serializer=org.apache.spark.serializer.KryoSerializer' --conf
'spark.sql.extensions=org.apache.spark.sql.hudi.HoodieSparkSessionExtension'
--conf
'spark.sql.catalog.spark_catalog=org.apache.spark.sql.hudi.catalog.HoodieCatalog'
--conf 'spark.kryo.registrator=org.apache.spark.HoodieSparkKryoRegistrar'
+spark-sql --master "local[2]" \
+ --packages org.apache.hudi:hudi-spark$SPARK_VERSION-bundle_2.12:0.14.1 \
+ --conf 'spark.serializer=org.apache.spark.serializer.KryoSerializer' \
+ --conf
'spark.sql.extensions=org.apache.spark.sql.hudi.HoodieSparkSessionExtension' \
+ --conf
'spark.sql.catalog.spark_catalog=org.apache.spark.sql.hudi.catalog.HoodieCatalog'
\
+ --conf 'spark.kryo.registrator=org.apache.spark.HoodieSparkKryoRegistrar'
```
```shell
# For Spark versions: 3.0 - 3.1
export SPARK_VERSION=3.1
-spark-sql --packages
org.apache.hudi:hudi-spark$SPARK_VERSION-bundle_2.12:0.14.1 --conf
'spark.serializer=org.apache.spark.serializer.KryoSerializer' --conf
'spark.sql.extensions=org.apache.spark.sql.hudi.HoodieSparkSessionExtension'
--conf 'spark.kryo.registrator=org.apache.spark.HoodieSparkKryoRegistrar'
+spark-sql --master "local[2]" \
+ --packages org.apache.hudi:hudi-spark$SPARK_VERSION-bundle_2.12:0.14.1 \
+ --conf 'spark.serializer=org.apache.spark.serializer.KryoSerializer' \
+ --conf
'spark.sql.extensions=org.apache.spark.sql.hudi.HoodieSparkSessionExtension' \
+ --conf 'spark.kryo.registrator=org.apache.spark.HoodieSparkKryoRegistrar'
```
```shell
# For Spark version: 2.4
-spark-sql --packages org.apache.hudi:hudi-spark2.4-bundle_2.11:0.14.1 --conf
'spark.serializer=org.apache.spark.serializer.KryoSerializer' --conf
'spark.sql.extensions=org.apache.spark.sql.hudi.HoodieSparkSessionExtension'
--conf 'spark.kryo.registrator=org.apache.spark.HoodieSparkKryoRegistrar'
+spark-sql --master "local[2]" \
+ --packages org.apache.hudi:hudi-spark2.4-bundle_2.11:0.14.1 \
+ --conf 'spark.serializer=org.apache.spark.serializer.KryoSerializer' \
+ --conf
'spark.sql.extensions=org.apache.spark.sql.hudi.HoodieSparkSessionExtension' \
+ --conf 'spark.kryo.registrator=org.apache.spark.HoodieSparkKryoRegistrar'
```
</TabItem>
diff --git a/website/versioned_docs/version-0.15.0/quick-start-guide.md
b/website/versioned_docs/version-0.15.0/quick-start-guide.md
index d7ea0f80eb55..dbaf3d8a8158 100644
--- a/website/versioned_docs/version-0.15.0/quick-start-guide.md
+++ b/website/versioned_docs/version-0.15.0/quick-start-guide.md
@@ -56,26 +56,29 @@ From the extracted directory run spark-shell with Hudi:
```shell
# For Spark versions: 3.2 - 3.5
export SPARK_VERSION=3.5 # or 3.4, 3.3, 3.2
-spark-shell --packages
org.apache.hudi:hudi-spark$SPARK_VERSION-bundle_2.12:0.15.0 \
---conf 'spark.serializer=org.apache.spark.serializer.KryoSerializer' \
---conf
'spark.sql.catalog.spark_catalog=org.apache.spark.sql.hudi.catalog.HoodieCatalog'
\
---conf
'spark.sql.extensions=org.apache.spark.sql.hudi.HoodieSparkSessionExtension' \
---conf 'spark.kryo.registrator=org.apache.spark.HoodieSparkKryoRegistrar'
+spark-shell --master "local[2]" \
+ --packages org.apache.hudi:hudi-spark$SPARK_VERSION-bundle_2.12:0.15.0 \
+ --conf 'spark.serializer=org.apache.spark.serializer.KryoSerializer' \
+ --conf
'spark.sql.catalog.spark_catalog=org.apache.spark.sql.hudi.catalog.HoodieCatalog'
\
+ --conf
'spark.sql.extensions=org.apache.spark.sql.hudi.HoodieSparkSessionExtension' \
+ --conf 'spark.kryo.registrator=org.apache.spark.HoodieSparkKryoRegistrar'
```
```shell
# For Spark versions: 3.0 - 3.1
export SPARK_VERSION=3.1 # or 3.0
-spark-shell --packages
org.apache.hudi:hudi-spark$SPARK_VERSION-bundle_2.12:0.15.0 \
---conf 'spark.serializer=org.apache.spark.serializer.KryoSerializer' \
---conf
'spark.sql.extensions=org.apache.spark.sql.hudi.HoodieSparkSessionExtension' \
---conf 'spark.kryo.registrator=org.apache.spark.HoodieSparkKryoRegistrar'
+spark-shell --master "local[2]" \
+ --packages org.apache.hudi:hudi-spark$SPARK_VERSION-bundle_2.12:0.15.0 \
+ --conf 'spark.serializer=org.apache.spark.serializer.KryoSerializer' \
+ --conf
'spark.sql.extensions=org.apache.spark.sql.hudi.HoodieSparkSessionExtension' \
+ --conf 'spark.kryo.registrator=org.apache.spark.HoodieSparkKryoRegistrar'
```
```shell
# For Spark version: 2.4
-spark-shell --packages org.apache.hudi:hudi-spark2.4-bundle_2.11:0.15.0 \
---conf 'spark.serializer=org.apache.spark.serializer.KryoSerializer' \
---conf
'spark.sql.extensions=org.apache.spark.sql.hudi.HoodieSparkSessionExtension' \
---conf 'spark.kryo.registrator=org.apache.spark.HoodieSparkKryoRegistrar'
+spark-shell --master "local[2]" \
+ --packages org.apache.hudi:hudi-spark2.4-bundle_2.11:0.15.0 \
+ --conf 'spark.serializer=org.apache.spark.serializer.KryoSerializer' \
+ --conf
'spark.sql.extensions=org.apache.spark.sql.hudi.HoodieSparkSessionExtension' \
+ --conf 'spark.kryo.registrator=org.apache.spark.HoodieSparkKryoRegistrar'
```
</TabItem>
@@ -87,18 +90,31 @@ From the extracted directory run pyspark with Hudi:
# For Spark versions: 3.2 - 3.5
export PYSPARK_PYTHON=$(which python3)
export SPARK_VERSION=3.5 # or 3.4, 3.3, 3.2
-pyspark --packages org.apache.hudi:hudi-spark$SPARK_VERSION-bundle_2.12:0.15.0
--conf 'spark.serializer=org.apache.spark.serializer.KryoSerializer' --conf
'spark.sql.catalog.spark_catalog=org.apache.spark.sql.hudi.catalog.HoodieCatalog'
--conf
'spark.sql.extensions=org.apache.spark.sql.hudi.HoodieSparkSessionExtension'
--conf 'spark.kryo.registrator=org.apache.spark.HoodieSparkKryoRegistrar'
+pyspark --master "local[2]" \
+ --packages org.apache.hudi:hudi-spark$SPARK_VERSION-bundle_2.12:0.15.0 \
+ --conf 'spark.serializer=org.apache.spark.serializer.KryoSerializer' \
+ --conf
'spark.sql.catalog.spark_catalog=org.apache.spark.sql.hudi.catalog.HoodieCatalog'
\
+ --conf
'spark.sql.extensions=org.apache.spark.sql.hudi.HoodieSparkSessionExtension' \
+ --conf 'spark.kryo.registrator=org.apache.spark.HoodieSparkKryoRegistrar'
```
```shell
# For Spark versions: 3.0 - 3.1
export PYSPARK_PYTHON=$(which python3)
export SPARK_VERSION=3.1 # or 3.0
-pyspark --packages org.apache.hudi:hudi-spark$SPARK_VERSION-bundle_2.12:0.15.0
--conf 'spark.serializer=org.apache.spark.serializer.KryoSerializer' --conf
'spark.sql.extensions=org.apache.spark.sql.hudi.HoodieSparkSessionExtension'
--conf 'spark.kryo.registrator=org.apache.spark.HoodieSparkKryoRegistrar'
+pyspark --master "local[2]" \
+ --packages org.apache.hudi:hudi-spark$SPARK_VERSION-bundle_2.12:0.15.0 \
+ --conf 'spark.serializer=org.apache.spark.serializer.KryoSerializer' \
+ --conf
'spark.sql.extensions=org.apache.spark.sql.hudi.HoodieSparkSessionExtension' \
+ --conf 'spark.kryo.registrator=org.apache.spark.HoodieSparkKryoRegistrar'
```
```shell
# For Spark version: 2.4
export PYSPARK_PYTHON=$(which python3)
-pyspark --packages org.apache.hudi:hudi-spark2.4-bundle_2.11:0.15.0 --conf
'spark.serializer=org.apache.spark.serializer.KryoSerializer' --conf
'spark.sql.extensions=org.apache.spark.sql.hudi.HoodieSparkSessionExtension'
--conf 'spark.kryo.registrator=org.apache.spark.HoodieSparkKryoRegistrar'
+pyspark --master "local[2]" \
+ --packages org.apache.hudi:hudi-spark2.4-bundle_2.11:0.15.0 \
+ --conf 'spark.serializer=org.apache.spark.serializer.KryoSerializer' \
+ --conf
'spark.sql.extensions=org.apache.spark.sql.hudi.HoodieSparkSessionExtension' \
+ --conf 'spark.kryo.registrator=org.apache.spark.HoodieSparkKryoRegistrar'
```
</TabItem>
@@ -110,26 +126,29 @@ From the extracted directory run Spark SQL with Hudi:
```shell
# For Spark versions: 3.2 - 3.5
export SPARK_VERSION=3.5 # or 3.4, 3.3, 3.2
-spark-sql --packages
org.apache.hudi:hudi-spark$SPARK_VERSION-bundle_2.12:0.15.0 \
---conf 'spark.serializer=org.apache.spark.serializer.KryoSerializer' \
---conf
'spark.sql.extensions=org.apache.spark.sql.hudi.HoodieSparkSessionExtension' \
---conf
'spark.sql.catalog.spark_catalog=org.apache.spark.sql.hudi.catalog.HoodieCatalog'
\
---conf 'spark.kryo.registrator=org.apache.spark.HoodieSparkKryoRegistrar'
+spark-sql --master "local[2]" \
+ --packages org.apache.hudi:hudi-spark$SPARK_VERSION-bundle_2.12:0.15.0 \
+ --conf 'spark.serializer=org.apache.spark.serializer.KryoSerializer' \
+ --conf
'spark.sql.extensions=org.apache.spark.sql.hudi.HoodieSparkSessionExtension' \
+ --conf
'spark.sql.catalog.spark_catalog=org.apache.spark.sql.hudi.catalog.HoodieCatalog'
\
+ --conf 'spark.kryo.registrator=org.apache.spark.HoodieSparkKryoRegistrar'
```
```shell
# For Spark versions: 3.0 - 3.1
export SPARK_VERSION=3.1 # or 3.0
-spark-sql --packages
org.apache.hudi:hudi-spark$SPARK_VERSION-bundle_2.12:0.15.0 \
---conf 'spark.serializer=org.apache.spark.serializer.KryoSerializer' \
---conf
'spark.sql.extensions=org.apache.spark.sql.hudi.HoodieSparkSessionExtension' \
---conf 'spark.kryo.registrator=org.apache.spark.HoodieSparkKryoRegistrar'
+spark-sql --master "local[2]" \
+ --packages org.apache.hudi:hudi-spark$SPARK_VERSION-bundle_2.12:0.15.0 \
+ --conf 'spark.serializer=org.apache.spark.serializer.KryoSerializer' \
+ --conf
'spark.sql.extensions=org.apache.spark.sql.hudi.HoodieSparkSessionExtension' \
+ --conf 'spark.kryo.registrator=org.apache.spark.HoodieSparkKryoRegistrar'
```
```shell
# For Spark version: 2.4
-spark-sql --packages org.apache.hudi:hudi-spark2.4-bundle_2.11:0.15.0 \
---conf 'spark.serializer=org.apache.spark.serializer.KryoSerializer' \
---conf
'spark.sql.extensions=org.apache.spark.sql.hudi.HoodieSparkSessionExtension' \
---conf 'spark.kryo.registrator=org.apache.spark.HoodieSparkKryoRegistrar'
+spark-sql --master "local[2]" \
+ --packages org.apache.hudi:hudi-spark2.4-bundle_2.11:0.15.0 \
+ --conf 'spark.serializer=org.apache.spark.serializer.KryoSerializer' \
+ --conf
'spark.sql.extensions=org.apache.spark.sql.hudi.HoodieSparkSessionExtension' \
+ --conf 'spark.kryo.registrator=org.apache.spark.HoodieSparkKryoRegistrar'
```
</TabItem>
diff --git a/website/versioned_docs/version-1.0.0/quick-start-guide.md
b/website/versioned_docs/version-1.0.0/quick-start-guide.md
index 550d0476b0cc..c0543b6bcc2e 100644
--- a/website/versioned_docs/version-1.0.0/quick-start-guide.md
+++ b/website/versioned_docs/version-1.0.0/quick-start-guide.md
@@ -58,11 +58,12 @@ From the extracted directory run spark-shell with Hudi:
```shell
# For Spark versions: 3.3 - 3.5
export SPARK_VERSION=3.5 # or 3.4, 3.3
-spark-shell --packages
org.apache.hudi:hudi-spark$SPARK_VERSION-bundle_2.12:1.0.0 \
---conf 'spark.serializer=org.apache.spark.serializer.KryoSerializer' \
---conf
'spark.sql.catalog.spark_catalog=org.apache.spark.sql.hudi.catalog.HoodieCatalog'
\
---conf
'spark.sql.extensions=org.apache.spark.sql.hudi.HoodieSparkSessionExtension' \
---conf 'spark.kryo.registrator=org.apache.spark.HoodieSparkKryoRegistrar'
+spark-shell --master "local[2]" \
+ --packages org.apache.hudi:hudi-spark$SPARK_VERSION-bundle_2.12:1.0.0 \
+ --conf 'spark.serializer=org.apache.spark.serializer.KryoSerializer' \
+ --conf
'spark.sql.catalog.spark_catalog=org.apache.spark.sql.hudi.catalog.HoodieCatalog'
\
+ --conf
'spark.sql.extensions=org.apache.spark.sql.hudi.HoodieSparkSessionExtension' \
+ --conf 'spark.kryo.registrator=org.apache.spark.HoodieSparkKryoRegistrar'
```
</TabItem>
@@ -74,7 +75,12 @@ From the extracted directory run pyspark with Hudi:
# For Spark versions: 3.3 - 3.5
export PYSPARK_PYTHON=$(which python3)
export SPARK_VERSION=3.5 # or 3.4, 3.3
-pyspark --packages org.apache.hudi:hudi-spark$SPARK_VERSION-bundle_2.12:1.0.0
--conf 'spark.serializer=org.apache.spark.serializer.KryoSerializer' --conf
'spark.sql.catalog.spark_catalog=org.apache.spark.sql.hudi.catalog.HoodieCatalog'
--conf
'spark.sql.extensions=org.apache.spark.sql.hudi.HoodieSparkSessionExtension'
--conf 'spark.kryo.registrator=org.apache.spark.HoodieSparkKryoRegistrar'
+pyspark --master "local[2]" \
+ --packages org.apache.hudi:hudi-spark$SPARK_VERSION-bundle_2.12:1.0.0 \
+ --conf 'spark.serializer=org.apache.spark.serializer.KryoSerializer' \
+ --conf
'spark.sql.catalog.spark_catalog=org.apache.spark.sql.hudi.catalog.HoodieCatalog'
\
+ --conf
'spark.sql.extensions=org.apache.spark.sql.hudi.HoodieSparkSessionExtension' \
+ --conf 'spark.kryo.registrator=org.apache.spark.HoodieSparkKryoRegistrar'
```
</TabItem>
@@ -86,11 +92,12 @@ From the extracted directory run Spark SQL with Hudi:
```shell
# For Spark versions: 3.3 - 3.5
export SPARK_VERSION=3.5 # or 3.4, 3.3
-spark-sql --packages
org.apache.hudi:hudi-spark$SPARK_VERSION-bundle_2.12:1.0.0 \
---conf 'spark.serializer=org.apache.spark.serializer.KryoSerializer' \
---conf
'spark.sql.extensions=org.apache.spark.sql.hudi.HoodieSparkSessionExtension' \
---conf
'spark.sql.catalog.spark_catalog=org.apache.spark.sql.hudi.catalog.HoodieCatalog'
\
---conf 'spark.kryo.registrator=org.apache.spark.HoodieSparkKryoRegistrar'
+spark-sql --master "local[2]" \
+ --packages org.apache.hudi:hudi-spark$SPARK_VERSION-bundle_2.12:1.0.0 \
+ --conf 'spark.serializer=org.apache.spark.serializer.KryoSerializer' \
+ --conf
'spark.sql.extensions=org.apache.spark.sql.hudi.HoodieSparkSessionExtension' \
+ --conf
'spark.sql.catalog.spark_catalog=org.apache.spark.sql.hudi.catalog.HoodieCatalog'
\
+ --conf 'spark.kryo.registrator=org.apache.spark.HoodieSparkKryoRegistrar'
```
</TabItem>
</Tabs>
diff --git a/website/versioned_docs/version-1.0.1/quick-start-guide.md
b/website/versioned_docs/version-1.0.1/quick-start-guide.md
index 32f01287593a..5266ad2d4524 100644
--- a/website/versioned_docs/version-1.0.1/quick-start-guide.md
+++ b/website/versioned_docs/version-1.0.1/quick-start-guide.md
@@ -58,11 +58,12 @@ From the extracted directory run spark-shell with Hudi:
```shell
# For Spark versions: 3.3 - 3.5
export SPARK_VERSION=3.5 # or 3.4, 3.3
-spark-shell --packages
org.apache.hudi:hudi-spark$SPARK_VERSION-bundle_2.12:1.0.1 \
---conf 'spark.serializer=org.apache.spark.serializer.KryoSerializer' \
---conf
'spark.sql.catalog.spark_catalog=org.apache.spark.sql.hudi.catalog.HoodieCatalog'
\
---conf
'spark.sql.extensions=org.apache.spark.sql.hudi.HoodieSparkSessionExtension' \
---conf 'spark.kryo.registrator=org.apache.spark.HoodieSparkKryoRegistrar'
+spark-shell --master "local[2]" \
+ --packages org.apache.hudi:hudi-spark$SPARK_VERSION-bundle_2.12:1.0.1 \
+ --conf 'spark.serializer=org.apache.spark.serializer.KryoSerializer' \
+ --conf
'spark.sql.catalog.spark_catalog=org.apache.spark.sql.hudi.catalog.HoodieCatalog'
\
+ --conf
'spark.sql.extensions=org.apache.spark.sql.hudi.HoodieSparkSessionExtension' \
+ --conf 'spark.kryo.registrator=org.apache.spark.HoodieSparkKryoRegistrar'
```
</TabItem>
@@ -74,7 +75,12 @@ From the extracted directory run pyspark with Hudi:
# For Spark versions: 3.3 - 3.5
export PYSPARK_PYTHON=$(which python3)
export SPARK_VERSION=3.5 # or 3.4, 3.3
-pyspark --packages org.apache.hudi:hudi-spark$SPARK_VERSION-bundle_2.12:1.0.1
--conf 'spark.serializer=org.apache.spark.serializer.KryoSerializer' --conf
'spark.sql.catalog.spark_catalog=org.apache.spark.sql.hudi.catalog.HoodieCatalog'
--conf
'spark.sql.extensions=org.apache.spark.sql.hudi.HoodieSparkSessionExtension'
--conf 'spark.kryo.registrator=org.apache.spark.HoodieSparkKryoRegistrar'
+pyspark --master "local[2]" \
+ --packages org.apache.hudi:hudi-spark$SPARK_VERSION-bundle_2.12:1.0.1 \
+ --conf 'spark.serializer=org.apache.spark.serializer.KryoSerializer' \
+ --conf
'spark.sql.catalog.spark_catalog=org.apache.spark.sql.hudi.catalog.HoodieCatalog'
\
+ --conf
'spark.sql.extensions=org.apache.spark.sql.hudi.HoodieSparkSessionExtension' \
+ --conf 'spark.kryo.registrator=org.apache.spark.HoodieSparkKryoRegistrar'
```
</TabItem>
@@ -86,11 +92,12 @@ From the extracted directory run Spark SQL with Hudi:
```shell
# For Spark versions: 3.3 - 3.5
export SPARK_VERSION=3.5 # or 3.4, 3.3
-spark-sql --packages
org.apache.hudi:hudi-spark$SPARK_VERSION-bundle_2.12:1.0.1 \
---conf 'spark.serializer=org.apache.spark.serializer.KryoSerializer' \
---conf
'spark.sql.extensions=org.apache.spark.sql.hudi.HoodieSparkSessionExtension' \
---conf
'spark.sql.catalog.spark_catalog=org.apache.spark.sql.hudi.catalog.HoodieCatalog'
\
---conf 'spark.kryo.registrator=org.apache.spark.HoodieSparkKryoRegistrar'
+spark-sql --master "local[2]" \
+ --packages org.apache.hudi:hudi-spark$SPARK_VERSION-bundle_2.12:1.0.1 \
+ --conf 'spark.serializer=org.apache.spark.serializer.KryoSerializer' \
+ --conf
'spark.sql.extensions=org.apache.spark.sql.hudi.HoodieSparkSessionExtension' \
+ --conf
'spark.sql.catalog.spark_catalog=org.apache.spark.sql.hudi.catalog.HoodieCatalog'
\
+ --conf 'spark.kryo.registrator=org.apache.spark.HoodieSparkKryoRegistrar'
```
</TabItem>
</Tabs>
diff --git a/website/versioned_docs/version-1.0.2/quick-start-guide.md
b/website/versioned_docs/version-1.0.2/quick-start-guide.md
index 4a3f53ed8cbc..247ac626b911 100644
--- a/website/versioned_docs/version-1.0.2/quick-start-guide.md
+++ b/website/versioned_docs/version-1.0.2/quick-start-guide.md
@@ -58,11 +58,12 @@ From the extracted directory run spark-shell with Hudi:
```shell
# For Spark versions: 3.3 - 3.5
export SPARK_VERSION=3.5 # or 3.4, 3.3
-spark-shell --packages
org.apache.hudi:hudi-spark$SPARK_VERSION-bundle_2.12:1.0.2 \
---conf 'spark.serializer=org.apache.spark.serializer.KryoSerializer' \
---conf
'spark.sql.catalog.spark_catalog=org.apache.spark.sql.hudi.catalog.HoodieCatalog'
\
---conf
'spark.sql.extensions=org.apache.spark.sql.hudi.HoodieSparkSessionExtension' \
---conf 'spark.kryo.registrator=org.apache.spark.HoodieSparkKryoRegistrar'
+spark-shell --master "local[2]" \
+ --packages org.apache.hudi:hudi-spark$SPARK_VERSION-bundle_2.12:1.0.2 \
+ --conf 'spark.serializer=org.apache.spark.serializer.KryoSerializer' \
+ --conf
'spark.sql.catalog.spark_catalog=org.apache.spark.sql.hudi.catalog.HoodieCatalog'
\
+ --conf
'spark.sql.extensions=org.apache.spark.sql.hudi.HoodieSparkSessionExtension' \
+ --conf 'spark.kryo.registrator=org.apache.spark.HoodieSparkKryoRegistrar'
```
</TabItem>
@@ -74,7 +75,12 @@ From the extracted directory run pyspark with Hudi:
# For Spark versions: 3.3 - 3.5
export PYSPARK_PYTHON=$(which python3)
export SPARK_VERSION=3.5 # or 3.4, 3.3
-pyspark --packages org.apache.hudi:hudi-spark$SPARK_VERSION-bundle_2.12:1.0.2
--conf 'spark.serializer=org.apache.spark.serializer.KryoSerializer' --conf
'spark.sql.catalog.spark_catalog=org.apache.spark.sql.hudi.catalog.HoodieCatalog'
--conf
'spark.sql.extensions=org.apache.spark.sql.hudi.HoodieSparkSessionExtension'
--conf 'spark.kryo.registrator=org.apache.spark.HoodieSparkKryoRegistrar'
+pyspark --master "local[2]" \
+ --packages org.apache.hudi:hudi-spark$SPARK_VERSION-bundle_2.12:1.0.2 \
+ --conf 'spark.serializer=org.apache.spark.serializer.KryoSerializer' \
+ --conf
'spark.sql.catalog.spark_catalog=org.apache.spark.sql.hudi.catalog.HoodieCatalog'
\
+ --conf
'spark.sql.extensions=org.apache.spark.sql.hudi.HoodieSparkSessionExtension' \
+ --conf 'spark.kryo.registrator=org.apache.spark.HoodieSparkKryoRegistrar'
```
</TabItem>
@@ -86,11 +92,12 @@ From the extracted directory run Spark SQL with Hudi:
```shell
# For Spark versions: 3.3 - 3.5
export SPARK_VERSION=3.5 # or 3.4, 3.3
-spark-sql --packages
org.apache.hudi:hudi-spark$SPARK_VERSION-bundle_2.12:1.0.2 \
---conf 'spark.serializer=org.apache.spark.serializer.KryoSerializer' \
---conf
'spark.sql.extensions=org.apache.spark.sql.hudi.HoodieSparkSessionExtension' \
---conf
'spark.sql.catalog.spark_catalog=org.apache.spark.sql.hudi.catalog.HoodieCatalog'
\
---conf 'spark.kryo.registrator=org.apache.spark.HoodieSparkKryoRegistrar'
+spark-sql --master "local[2]" \
+ --packages org.apache.hudi:hudi-spark$SPARK_VERSION-bundle_2.12:1.0.2 \
+ --conf 'spark.serializer=org.apache.spark.serializer.KryoSerializer' \
+ --conf
'spark.sql.extensions=org.apache.spark.sql.hudi.HoodieSparkSessionExtension' \
+ --conf
'spark.sql.catalog.spark_catalog=org.apache.spark.sql.hudi.catalog.HoodieCatalog'
\
+ --conf 'spark.kryo.registrator=org.apache.spark.HoodieSparkKryoRegistrar'
```
</TabItem>
</Tabs>