Skip to content

[#10788] improvement(deps): upgrade Hadoop from 2.10.2 to 3.3.6 and remove hadoop2 dependency line #10789

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

Open
geyanggang wants to merge 3 commits into
base: main
Choose a base branch
from
Open

[#10788] improvement(deps): upgrade Hadoop from 2.10.2 to 3.3.6 and remove hadoop2 dependency line #10789

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
cc42fc1
improvement(deps): upgrade Hadoop from 2.10.2 to 3.3.6 and remove had…
geyanggang Apr 15, 2026
fa70c78
fix: add missing hadoop-hdfs-client dependencies for Hadoop 3.3.6(pro…
geyanggang Apr 16, 2026
c7b3584
fix(hudi) : set to avoid Hudi 0.15.0 + Hadoop 3 incompatibility
geyanggang Apr 16, 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
1 change: 1 addition & 0 deletions authorizations/authorization-chain/build.gradle.kts
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -104,6 +104,7 @@ dependencies {
exclude("javax.servlet", "servlet-api")
exclude("io.netty")
}
testImplementation(libs.hadoop3.hdfs.client)
}

tasks {
Expand Down
1 change: 1 addition & 0 deletions authorizations/authorization-ranger/build.gradle.kts
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -105,6 +105,7 @@ dependencies {
exclude("javax.servlet", "servlet-api")
exclude("io.netty")
}
testImplementation(libs.hadoop3.hdfs.client)
testImplementation("org.apache.iceberg:iceberg-spark-runtime-${sparkMajorVersion}_$scalaVersion:$icebergVersion")
testImplementation("org.apache.paimon:paimon-spark-$sparkMajorVersion:$paimonVersion")
}
Expand Down
31 changes: 17 additions & 14 deletions catalogs/catalog-hive/build.gradle.kts
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -49,12 +49,17 @@ dependencies {
implementation(libs.commons.io)
implementation(libs.commons.lang3)
implementation(libs.guava)
implementation(libs.hadoop2.auth) {
implementation(libs.hadoop3.auth) {
exclude("*")
}
implementation(libs.hadoop2.common) {
implementation(libs.hadoop3.common) {
exclude("*")
}
// Hadoop 3.x runtime requirements (stripped by exclude("*") above)
implementation(libs.hadoop3.shaded.guava)
implementation(libs.hadoop3.shaded.protobuf)
implementation("org.apache.commons:commons-configuration2:2.8.0")
implementation(libs.re2j)
implementation(libs.htrace.core4)
implementation(libs.slf4j.api)
implementation(libs.woodstox.core)
Expand Down Expand Up @@ -89,14 +94,20 @@ dependencies {
testImplementation(libs.bundles.jersey)
testImplementation(libs.bundles.jetty)
testImplementation(libs.bundles.log4j)
testImplementation(libs.hadoop2.aws)
testImplementation(libs.hadoop2.common) {
testImplementation(libs.hadoop3.aws)
testImplementation(libs.hadoop3.common) {
exclude("*")
}
testImplementation(libs.hadoop2.hdfs)
testImplementation(libs.hadoop2.mapreduce.client.core) {
testImplementation(libs.hadoop3.hdfs)
testImplementation(libs.hadoop3.hdfs.client)
testImplementation(libs.hadoop3.mapreduce.client.core) {
exclude("*")
}
// Hadoop 3.x runtime requirements (stripped by exclude("*") above)
testImplementation(libs.hadoop3.shaded.guava)
testImplementation(libs.hadoop3.shaded.protobuf)
testImplementation("org.apache.commons:commons-configuration2:2.8.0")
testImplementation(libs.re2j)
testImplementation(libs.hadoop3.abs)
testImplementation(libs.hadoop3.gcs)
testImplementation(libs.hive2.common) {
Expand All @@ -112,14 +123,6 @@ dependencies {
testImplementation(libs.testcontainers.localstack)
testImplementation(libs.testcontainers.mysql)

// You need this to run test CatalogHiveABSIT as it required hadoop3 environment introduced by hadoop3.abs
// (The protocol `abfss` was first introduced in Hadoop 3.2.0), However, as the there already exists
// hadoop2.common in the test classpath, If we added the following dependencies directly, it will
// cause the conflict between hadoop2 and hadoop3, resulting test failures, so we comment the
// following line temporarily, if you want to run the test, please uncomment it.
// In the future, we may need to refactor the test to avoid the conflict.
// testImplementation(libs.hadoop3.common)

testRuntimeOnly(libs.junit.jupiter.engine)
}

Expand Down
21 changes: 16 additions & 5 deletions catalogs/catalog-lakehouse-hudi/build.gradle.kts
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -48,12 +48,17 @@ dependencies {
implementation(libs.commons.io)
implementation(libs.commons.lang3)
implementation(libs.guava)
implementation(libs.hadoop2.auth) {
implementation(libs.hadoop3.auth) {
exclude("*")
}
implementation(libs.hadoop2.common) {
implementation(libs.hadoop3.common) {
exclude("*")
}
// Hadoop 3.x runtime requirements (stripped by exclude("*") above)
implementation(libs.hadoop3.shaded.guava)
implementation(libs.hadoop3.shaded.protobuf)
implementation("org.apache.commons:commons-configuration2:2.8.0")
implementation(libs.re2j)
implementation(libs.htrace.core4)
implementation(libs.slf4j.api)
implementation(libs.woodstox.core)
Expand Down Expand Up @@ -113,13 +118,19 @@ dependencies {
testImplementation(libs.datanucleus.jdo)
testImplementation(libs.datanucleus.rdbms)
testImplementation(libs.derby)
testImplementation(libs.hadoop2.auth) {
testImplementation(libs.hadoop3.auth) {
exclude("*")
}
testImplementation(libs.hadoop2.hdfs)
testImplementation(libs.hadoop2.mapreduce.client.core) {
testImplementation(libs.hadoop3.hdfs)
testImplementation(libs.hadoop3.hdfs.client)
testImplementation(libs.hadoop3.mapreduce.client.core) {
exclude("*")
}
// Hadoop 3.x runtime requirements (stripped by exclude("*") above)
testImplementation(libs.hadoop3.shaded.guava)
testImplementation(libs.hadoop3.shaded.protobuf)
testImplementation("org.apache.commons:commons-configuration2:2.8.0")
testImplementation(libs.re2j)
testImplementation(libs.htrace.core4)
testImplementation(libs.junit.jupiter.api)
testImplementation(libs.mysql.driver)
Expand Down
4 changes: 4 additions & 0 deletions ...t/java/org/apache/gravitino/catalog/lakehouse/hudi/integration/test/HudiCatalogHMSIT.java
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -469,6 +469,10 @@ private static void createHudiTables() {
"org.apache.spark.sql.hudi.catalog.HoodieCatalog")
.config("spark.kryo.registrator", "org.apache.spark.HoodieSparkKryoRegistrar")
.config("dfs.replication", "1")
// Disable Hudi metadata table to avoid NoSuchMethodError caused by Hudi 0.15.0's
// shaded HBase code (HoodieHFileReader) being incompatible with hadoop-hdfs-client
// 3.3.6. See: https://github.com/apache/hudi/issues/5765
.config("hoodie.metadata.enable", "false")
.enableHiveSupport()
.getOrCreate();

Expand Down
8 changes: 4 additions & 4 deletions catalogs/catalog-lakehouse-paimon/build.gradle.kts
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -103,7 +103,7 @@ dependencies {
}
implementation(libs.commons.lang3)
implementation(libs.guava)
implementation(libs.hadoop2.common) {
implementation(libs.hadoop3.common) {
exclude("com.github.spotbugs")
exclude("com.sun.jersey")
exclude("javax.servlet")
Expand All @@ -113,16 +113,16 @@ dependencies {
exclude("org.apache.zookeeper")
exclude("org.mortbay.jetty")
}
implementation(libs.hadoop2.hdfs) {
implementation(libs.hadoop3.hdfs) {
exclude("*")
}
implementation(libs.hadoop2.hdfs.client) {
implementation(libs.hadoop3.hdfs.client) {
exclude("com.sun.jersey")
exclude("javax.servlet")
exclude("org.fusesource.leveldbjni")
exclude("org.mortbay.jetty")
}
implementation(libs.hadoop2.mapreduce.client.core) {
implementation(libs.hadoop3.mapreduce.client.core) {
exclude("*")
}

Expand Down
11 changes: 8 additions & 3 deletions catalogs/hive-metastore-common/build.gradle.kts
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -55,15 +55,20 @@ dependencies {
testImplementation(libs.datanucleus.jdo)
testImplementation(libs.datanucleus.rdbms)
testImplementation(libs.derby)
testImplementation(libs.hadoop2.auth) {
testImplementation(libs.hadoop3.auth) {
exclude("*")
}
testImplementation(libs.hadoop2.common) {
testImplementation(libs.hadoop3.common) {
exclude("*")
}
testImplementation(libs.hadoop2.mapreduce.client.core) {
testImplementation(libs.hadoop3.mapreduce.client.core) {
exclude("*")
}
// Hadoop 3.x runtime requirements (stripped by exclude("*") above)
testImplementation(libs.hadoop3.shaded.guava)
testImplementation(libs.hadoop3.shaded.protobuf)
testImplementation("org.apache.commons:commons-configuration2:2.8.0")
testImplementation(libs.re2j)
testImplementation(libs.hive2.exec) {
artifact {
classifier = "core"
Expand Down
4 changes: 2 additions & 2 deletions catalogs/hive-metastore2-libs/build.gradle.kts
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -29,7 +29,7 @@ plugins {
// Guava and Logback are excluded because they are provided by the Gravitino runtime classpath.

dependencies {
implementation(libs.hadoop2.common) {
implementation(libs.hadoop3.common) {
exclude(group = "ch.qos.logback")
exclude(group = "com.fasterxml.jackson.core")
exclude(group = "com.github.spotbugs")
Expand All @@ -43,7 +43,7 @@ dependencies {
exclude(group = "org.eclipse.jetty.orbit", module = "javax.servlet")
exclude(group = "org.slf4j")
}
implementation(libs.hadoop2.mapreduce.client.core) {
implementation(libs.hadoop3.mapreduce.client.core) {
exclude(group = "com.github.spotbugs")
exclude(group = "com.google.code.findbugs")
exclude(group = "com.google.guava")
Expand Down
2 changes: 1 addition & 1 deletion catalogs/hive-metastore3-libs/build.gradle.kts
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -29,7 +29,7 @@ plugins {
// Guava and Logback are excluded because they are provided by the Gravitino runtime classpath.

dependencies {
implementation(libs.hadoop2.common) {
implementation(libs.hadoop3.common) {
exclude(group = "ch.qos.logback")
exclude(group = "com.fasterxml.jackson.core")
exclude(group = "com.github.spotbugs")
Expand Down
1 change: 1 addition & 0 deletions clients/filesystem-hadoop3/build.gradle.kts
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -68,6 +68,7 @@ dependencies {
exclude("javax.servlet", "servlet-api")
exclude("io.netty")
}
testImplementation(libs.hadoop3.hdfs.client)
testImplementation(libs.httpclient5)
testImplementation(libs.javax.jaxb.api) {
exclude("*")
Expand Down
12 changes: 9 additions & 3 deletions flink-connector/flink/build.gradle.kts
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -129,10 +129,10 @@ dependencies {
exclude("org.slf4j")
}

testImplementation(libs.hadoop2.common) {
testImplementation(libs.hadoop3.common) {
exclude("*")
}
testImplementation(libs.hadoop2.hdfs) {
testImplementation(libs.hadoop3.hdfs) {
exclude("com.sun.jersey")
exclude("commons-cli", "commons-cli")
exclude("commons-io", "commons-io")
Expand All @@ -141,9 +141,15 @@ dependencies {
exclude("javax.servlet", "servlet-api")
exclude("org.mortbay.jetty")
}
testImplementation(libs.hadoop2.mapreduce.client.core) {
testImplementation(libs.hadoop3.hdfs.client)
testImplementation(libs.hadoop3.mapreduce.client.core) {
exclude("*")
}
// Hadoop 3.x runtime requirements (stripped by exclude("*") above)
testImplementation(libs.hadoop3.shaded.guava)
testImplementation(libs.hadoop3.shaded.protobuf)
testImplementation("org.apache.commons:commons-configuration2:2.8.0")
testImplementation(libs.re2j)
testImplementation(libs.hive2.common) {
exclude("org.eclipse.jetty.aggregate", "jetty-all")
exclude("org.eclipse.jetty.orbit", "javax.servlet")
Expand Down
21 changes: 10 additions & 11 deletions gradle/libs.versions.toml
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -38,12 +38,11 @@ airlift-json = "237"
airlift-resolver = "1.6"
hive2 = "2.3.9"
hive3 = "3.1.3"
hadoop2 = "2.10.2"
hadoop3 = "3.3.1"
hadoop3 = "3.3.6"
hadoop3-gcs = "1.9.4-hadoop3"
hadoop3-abs = "3.3.1"
hadoop3-aliyun = "3.3.1"
hadoop-minikdc = "3.3.1"
hadoop3-abs = "3.3.6"
hadoop3-aliyun = "3.3.6"
hadoop-minikdc = "3.3.6"
htrace-core4 = "4.1.0-incubating"
httpclient = "4.4.1"
httpclient5 = "5.4.4"
Expand Down Expand Up @@ -197,22 +196,22 @@ hive2-common = { group = "org.apache.hive", name = "hive-common", version.ref =
hive2-jdbc = { group = "org.apache.hive", name = "hive-jdbc", version.ref = "hive2"}
hive3-metastore = { group = "org.apache.hive", name = "hive-metastore", version.ref = "hive3"}
hive3-common = { group = "org.apache.hive", name = "hive-common", version.ref = "hive3"}
hadoop2-auth = { group = "org.apache.hadoop", name = "hadoop-auth", version.ref = "hadoop2" }
hadoop2-hdfs = { group = "org.apache.hadoop", name = "hadoop-hdfs", version.ref = "hadoop2" }
hadoop2-hdfs-client = { group = "org.apache.hadoop", name = "hadoop-hdfs-client", version.ref = "hadoop2" }
hadoop2-common = { group = "org.apache.hadoop", name = "hadoop-common", version.ref = "hadoop2"}
hadoop2-mapreduce-client-core = { group = "org.apache.hadoop", name = "hadoop-mapreduce-client-core", version.ref = "hadoop2"}
hadoop2-aws = { group = "org.apache.hadoop", name = "hadoop-aws", version.ref = "hadoop2"}
hadoop3-aws = { group = "org.apache.hadoop", name = "hadoop-aws", version.ref = "hadoop3"}
hadoop3-auth = { group = "org.apache.hadoop", name = "hadoop-auth", version.ref = "hadoop3" }
hadoop3-hdfs = { group = "org.apache.hadoop", name = "hadoop-hdfs", version.ref = "hadoop3" }
hadoop3-hdfs-client = { group = "org.apache.hadoop", name = "hadoop-hdfs-client", version.ref = "hadoop3" }
hadoop3-common = { group = "org.apache.hadoop", name = "hadoop-common", version.ref = "hadoop3"}
hadoop3-client = { group = "org.apache.hadoop", name = "hadoop-client", version.ref = "hadoop3"}
hadoop3-client-api = { group = "org.apache.hadoop", name = "hadoop-client-api", version.ref = "hadoop3"}
hadoop3-client-runtime = { group = "org.apache.hadoop", name = "hadoop-client-runtime", version.ref = "hadoop3"}
hadoop3-mapreduce-client-core = { group = "org.apache.hadoop", name = "hadoop-mapreduce-client-core", version.ref = "hadoop3"}
hadoop3-minicluster = { group = "org.apache.hadoop", name = "hadoop-minicluster", version.ref = "hadoop-minikdc"}
hadoop3-gcs = { group = "com.google.cloud.bigdataoss", name = "gcs-connector", version.ref = "hadoop3-gcs"}
hadoop3-oss = { group = "org.apache.hadoop", name = "hadoop-aliyun", version.ref = "hadoop3-aliyun"}
hadoop3-abs = { group = "org.apache.hadoop", name = "hadoop-azure", version.ref = "hadoop3-abs"}
hadoop3-shaded-guava = { group = "org.apache.hadoop.thirdparty", name = "hadoop-shaded-guava", version = "1.1.1" }
hadoop3-shaded-protobuf = { group = "org.apache.hadoop.thirdparty", name = "hadoop-shaded-protobuf_3_7", version = "1.1.1" }
re2j = { group = "com.google.re2j", name = "re2j", version = "1.7" }
htrace-core4 = { group = "org.apache.htrace", name = "htrace-core4", version.ref = "htrace-core4" }
airlift-json = { group = "io.airlift", name = "json", version.ref = "airlift-json"}
airlift-resolver = { group = "io.airlift.resolver", name = "resolver", version.ref = "airlift-resolver"}
Expand Down
12 changes: 9 additions & 3 deletions trino-connector/integration-test/build.gradle.kts
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -41,13 +41,19 @@ dependencies {
testImplementation(libs.bundles.jetty)
testImplementation(libs.bundles.log4j)
testImplementation(libs.commons.cli)
testImplementation(libs.hadoop2.common) {
testImplementation(libs.hadoop3.common) {
exclude("*")
}
testImplementation(libs.hadoop2.hdfs)
testImplementation(libs.hadoop2.mapreduce.client.core) {
testImplementation(libs.hadoop3.hdfs)
testImplementation(libs.hadoop3.hdfs.client)
testImplementation(libs.hadoop3.mapreduce.client.core) {
exclude("*")
}
// Hadoop 3.x runtime requirements (stripped by exclude("*") above)
testImplementation(libs.hadoop3.shaded.guava)
testImplementation(libs.hadoop3.shaded.protobuf)
testImplementation("org.apache.commons:commons-configuration2:2.8.0")
testImplementation(libs.re2j)
testImplementation(libs.hive2.common) {
exclude("org.eclipse.jetty.aggregate", "jetty-all")
exclude("org.eclipse.jetty.orbit", "javax.servlet")
Expand Down
Loading