feat(import) add script for multiple hbase snapshot imports

.release-please-manifest.json

@@ -1,3 +1,3 @@
 {
-  ".": "2.18.1"
+  ".": "2.18.3"
 }

CHANGELOG.md

@@ -1,5 +1,21 @@
 # Changelog
 
+## [2.18.3](https://github.com/googleapis/java-bigtable-hbase/compare/v2.18.2...v2.18.3) (2026-04-30)
+
+
+### Bug Fixes
+
+* do not split near empty ranges ([#4604](https://github.com/googleapis/java-bigtable-hbase/issues/4604)) ([c37ca95](https://github.com/googleapis/java-bigtable-hbase/commit/c37ca951f4cd1164b47c2e66f04ac6423651f592))
+
+## [2.18.2](https://github.com/googleapis/java-bigtable-hbase/compare/v2.18.1...v2.18.2) (2026-04-29)
+
+
+### Bug Fixes
+
+* expose max attempt ([#4593](https://github.com/googleapis/java-bigtable-hbase/issues/4593)) ([6c37093](https://github.com/googleapis/java-bigtable-hbase/commit/6c370939695b0692be5b173536998f197a81c144))
+* raise maxInboundMessageSize ([#4601](https://github.com/googleapis/java-bigtable-hbase/issues/4601)) ([e165006](https://github.com/googleapis/java-bigtable-hbase/commit/e16500656c6651b34bc3773b63929b47a1cf8743))
+* remove batch endpoint ([#4592](https://github.com/googleapis/java-bigtable-hbase/issues/4592)) ([1316f4e](https://github.com/googleapis/java-bigtable-hbase/commit/1316f4e54de98a4f0fd1f6d226f59551b6a62337))
+
 ## [2.18.1](https://github.com/googleapis/java-bigtable-hbase/compare/v2.18.0...v2.18.1) (2026-04-13)
 
 

bigtable-client-core-parent/bigtable-hbase-integration-tests-common/pom.xml

@@ -19,7 +19,7 @@ limitations under the License.
   <parent>
     <groupId>com.google.cloud.bigtable</groupId>
     <artifactId>bigtable-client-core-parent</artifactId>
-    <version>2.18.2-SNAPSHOT</version> <!-- {x-version-update:bigtable-client-parent:current} -->
+    <version>2.18.4-SNAPSHOT</version> <!-- {x-version-update:bigtable-client-parent:current} -->
   </parent>
 
   <artifactId>bigtable-hbase-integration-tests-common</artifactId>

bigtable-client-core-parent/bigtable-hbase/pom.xml

@@ -20,7 +20,7 @@ limitations under the License.
   <parent>
     <groupId>com.google.cloud.bigtable</groupId>
     <artifactId>bigtable-client-core-parent</artifactId>
-    <version>2.18.2-SNAPSHOT</version> <!-- {x-version-update:bigtable-client-parent:current} -->
+    <version>2.18.4-SNAPSHOT</version> <!-- {x-version-update:bigtable-client-parent:current} -->
   </parent>
 
   <artifactId>bigtable-hbase</artifactId>
@@ -85,7 +85,7 @@ limitations under the License.
     <dependency>
       <groupId>com.google.cloud.bigtable</groupId>
       <artifactId>bigtable-internal-test-helper</artifactId>
-      <version>2.18.2-SNAPSHOT</version> <!-- {x-version-update:bigtable-client-parent:current} -->
+      <version>2.18.4-SNAPSHOT</version> <!-- {x-version-update:bigtable-client-parent:current} -->
       <scope>test</scope>
     </dependency>
     <dependency>
@@ -149,7 +149,7 @@ limitations under the License.
       <plugin>
         <groupId>com.google.cloud.bigtable.test</groupId>
         <artifactId>bigtable-build-helper</artifactId>
-        <version>2.18.2-SNAPSHOT</version> <!-- {x-version-update:bigtable-client-parent:current} -->
+        <version>2.18.4-SNAPSHOT</version> <!-- {x-version-update:bigtable-client-parent:current} -->
 
         <executions>
           <execution>

bigtable-client-core-parent/bigtable-hbase/src/main/java/com/google/cloud/bigtable/hbase/BigtableHBaseVersion.java

@@ -34,7 +34,7 @@ public class BigtableHBaseVersion {
   private static final AtomicBoolean wasInitialized = new AtomicBoolean(false);
 
   // {x-version-update-start:bigtable-client-parent:current}
-  public static final String VERSION = "2.18.2-SNAPSHOT";
+  public static final String VERSION = "2.18.4-SNAPSHOT";
   // {x-version-update-end}
 
   /**

bigtable-client-core-parent/bigtable-hbase/src/main/java/com/google/cloud/bigtable/hbase/wrappers/veneer/BigtableHBaseVeneerSettings.java

@@ -491,6 +491,20 @@ private void configureConnection(
     final InstantiatingGrpcChannelProvider.Builder channelProvider =
         ((InstantiatingGrpcChannelProvider) stubSettings.getTransportChannelProvider()).toBuilder();
 
+    // Raise the gRPC inbound message size to 500MB. This is ok because maxInboundMessageSize
+    // doesn't pre-allocate the memory. It's only used to validate the message size from the
+    // gRPC header. When processing the data, the memory is always dynamically allocated.
+    // Bigtable server also enforces a 256MB limit.
+    ApiFunction<ManagedChannelBuilder, ManagedChannelBuilder> channelConfigurator =
+        channelProvider.getChannelConfigurator();
+    channelProvider.setChannelConfigurator(
+        cb -> {
+          if (channelConfigurator != null) {
+            cb = channelConfigurator.apply(cb);
+          }
+          return cb.maxInboundMessageSize(1024 * 1024 * 500);
+        });
+
     if (configuration.getBoolean(BIGTABLE_USE_PLAINTEXT_NEGOTIATION, false)) {
       // Make sure to avoid clobbering the old Configurator
       @SuppressWarnings("rawtypes")

bigtable-client-core-parent/pom.xml

@@ -20,7 +20,7 @@ limitations under the License.
   <parent>
     <groupId>com.google.cloud.bigtable</groupId>
     <artifactId>bigtable-client-parent</artifactId>
-    <version>2.18.2-SNAPSHOT</version> <!-- {x-version-update:bigtable-client-parent:current} -->
+    <version>2.18.4-SNAPSHOT</version> <!-- {x-version-update:bigtable-client-parent:current} -->
   </parent>
 
   <artifactId>bigtable-client-core-parent</artifactId>

bigtable-dataflow-parent/bigtable-beam-import/SNAPSHOT_IMPORT_USAGE.md

@@ -0,0 +1,65 @@
+# HBase Snapshot Import Helper Script Usage
+
+This document describes the environment variables used by the `run-snapshot-import.sh` script to automate HBase snapshot imports into Cloud Bigtable using Dataflow.
+
+## Environment Variables
+
+The script relies on the following environment variables. You should set them before executing the script.
+
+| Variable | Description | Example / Suggested Value |
+| :--- | :--- | :--- |
+| `PROJECT_ID` | The Google Cloud Project ID where the Bigtable instance and Dataflow jobs reside. | `your-project-id` |
+| `INSTANCE_ID` | The Bigtable Instance ID to import data into. | `your-instance-id` |
+| `BUCKET` | The GCS bucket name used for Dataflow staging, temp files, and default snapshot source path. | `your-gcs-bucket` |
+| `REGION` | The GCP region to run the Dataflow jobs in. | `us-central1` |
+| `TABLE_NAME` | The target Bigtable table name. | `your-table-name` |
+| `SNAPSHOT_NAME` | The name of the HBase snapshot to import. | `your-snapshot-name` |
+| `SNAPSHOT_SOURCE_DIR` | The GCS path where the HBase snapshot export is located. | `gs://your-gcs-bucket/snapshots` |
+| `SERVICE_ACCOUNT` | The service account email to run the Dataflow jobs. | `your-service-account@developer.gserviceaccount.com` |
+| `NUM_SHARDS` | The number of shards to split the import into for parallel processing. | `20` |
+| `MAX_INFLIGHT_RPCS` | Maximum number of inflight RPCs for Bigtable client. | `100` |
+| `BULK_MUTATION_CLOSE_TIMEOUT_MINUTES` | Timeout in minutes for closing bulk mutations. | `30` |
+| `NETWORK` | VPC Network name for Dataflow workers. | `your-network` |
+| `SUBNETWORK` | VPC Subnetwork name for Dataflow workers. | `regions/us-central1/subnetworks/your-subnetwork` |
+
+## Usage
+
+### Run a specific shard range
+```bash
+./run-snapshot-import.sh <start_shard> <end_shard>
+```
+Example: `./run-snapshot-import.sh 0 5`
+
+### Run all shards (Auto-parallel mode)
+```bash
+./run-snapshot-import.sh --all
+```
+This mode will first run the restore step, and then launch background processes for all shards in parallel groups of 4 by default.
+
+## Advanced Usage
+
+### Manual Parallel Execution
+
+To run shards in parallel groups (e.g., assuming 20 shards total), you can run multiple instances of this script.
+
+> [!IMPORTANT]
+> Because concurrent shards cannot delete or overwrite the restored snapshot directory simultaneously, **no shard** performs the restore step during a sharded run. You MUST run the restore step explicitly first!
+
+Example for manual parallel execution:
+```bash
+# 1. Run the blocking restore step first!
+./run-snapshot-import.sh --restore-only
+
+# 2. Once the restore is complete, launch shards in parallel:
+./run-snapshot-import.sh 0 3 &
+./run-snapshot-import.sh 4 7 &
+./run-snapshot-import.sh 8 11 &
+./run-snapshot-import.sh 12 15 &
+./run-snapshot-import.sh 16 19 &
+```
+
+## Troubleshooting
+
+### JDK Compatibility
+
+If you are running on a newer, unsupported JDK version (e.g. JDK 25+) and hit ByteBuddy errors, you can simply set the `JVM_OPTS` variable to `"-Dnet.bytebuddy.experimental=true"` in the Configurations section of the `run-snapshot-import.sh` script.

bigtable-dataflow-parent/bigtable-beam-import/pom.xml

@@ -18,7 +18,7 @@ limitations under the License.
   <parent>
     <groupId>com.google.cloud.bigtable</groupId>
     <artifactId>bigtable-dataflow-parent</artifactId>
-    <version>2.18.2-SNAPSHOT</version> <!-- {x-version-update:bigtable-client-parent:current} -->
+    <version>2.18.4-SNAPSHOT</version> <!-- {x-version-update:bigtable-client-parent:current} -->
   </parent>
   <modelVersion>4.0.0</modelVersion>
 
@@ -39,6 +39,33 @@ limitations under the License.
         <type>pom</type>
         <scope>import</scope>
       </dependency>
+
+      <!-- Version alignment -->
+      <!-- Mark all annotations as provided. They don't affect the runtime of the pipeline so
+      there is no need to try to version align them -->
+      <dependency>
+        <groupId>org.checkerframework</groupId>
+        <artifactId>checker-qual</artifactId>
+        <version>3.31.0</version>
+        <scope>provided</scope>
+      </dependency>
+      <dependency>
+        <groupId>com.google.errorprone</groupId>
+        <artifactId>error_prone_annotations</artifactId>
+        <version>2.18.0</version>
+        <scope>provided</scope>
+      </dependency>
+      <dependency>
+        <groupId>org.codehaus.mojo</groupId>
+        <artifactId>animal-sniffer-annotations</artifactId>
+        <version>1.22</version>
+        <scope>provided</scope>
+      </dependency>
+      <dependency>
+        <groupId>jakarta.annotation</groupId>
+        <artifactId>jakarta.annotation-api</artifactId>
+        <scope>provided</scope>
+      </dependency>
     </dependencies>
   </dependencyManagement>
 
@@ -83,8 +110,9 @@ limitations under the License.
     <dependency>
       <groupId>${project.groupId}</groupId>
       <artifactId>bigtable-hbase-beam</artifactId>
-      <version>2.18.2-SNAPSHOT</version> <!-- {x-version-update:bigtable-client-parent:current} -->
+      <version>2.18.4-SNAPSHOT</version> <!-- {x-version-update:bigtable-client-parent:current} -->
       <exclusions>
+        <!-- Exclude hbase-shaded-client to prevent reintroducing the dnsjava SPI / LiteralByteString conflict (NoClassDefFoundError) -->
         <exclusion>
           <groupId>org.apache.hbase</groupId>
           <artifactId>hbase-shaded-client</artifactId>
@@ -104,6 +132,7 @@ limitations under the License.
     </dependency>
 
 
+    <!-- Use hbase-shaded-mapreduce (instead of hbase-shaded-client) to defeat the dnsjava SPI / LiteralByteString conflict (NoClassDefFoundError on JDK 21+) -->
     <dependency>
       <groupId>org.apache.hbase</groupId>
       <artifactId>hbase-shaded-mapreduce</artifactId>
@@ -118,6 +147,10 @@ limitations under the License.
           <groupId>org.apache.hadoop</groupId>
           <artifactId>hadoop-hdfs-client</artifactId>
         </exclusion>
+        <exclusion>
+          <groupId>org.apache.hbase</groupId>
+          <artifactId>hbase-shaded-client</artifactId>
+        </exclusion>
       </exclusions>
     </dependency>
     <dependency>
@@ -134,7 +167,11 @@ limitations under the License.
       <artifactId>beam-runners-direct-java</artifactId>
       <scope>test</scope>
     </dependency>
-
+    <dependency>
+      <groupId>com.google.cloud</groupId>
+      <artifactId>google-cloud-bigtable-emulator-core</artifactId>
+      <scope>test</scope>
+    </dependency>
     <dependency>
       <groupId>org.apache.hbase</groupId>
       <artifactId>hbase-shaded-testing-util</artifactId>
@@ -148,15 +185,10 @@ limitations under the License.
       </exclusions>
     </dependency>
 
-    <dependency>
-      <groupId>com.google.cloud</groupId>
-      <artifactId>google-cloud-bigtable-emulator-core</artifactId>
-      <scope>test</scope>
-    </dependency>
     <dependency>
       <groupId>com.google.cloud.bigtable</groupId>
       <artifactId>bigtable-internal-test-helper</artifactId>
-      <version>2.18.2-SNAPSHOT</version> <!-- {x-version-update:bigtable-client-parent:current} -->
+      <version>2.18.4-SNAPSHOT</version> <!-- {x-version-update:bigtable-client-parent:current} -->
       <scope>test</scope>
     </dependency>
 
@@ -186,7 +218,7 @@ limitations under the License.
     </dependency>
     <dependency>
       <groupId>org.mockito</groupId>
-      <artifactId>mockito-core</artifactId>
+      <artifactId>mockito-inline</artifactId>
       <version>${mockito.version}</version>
       <scope>test</scope>
     </dependency>
@@ -221,6 +253,14 @@ limitations under the License.
 
 
     <plugins>
+      <plugin>
+        <groupId>org.apache.maven.plugins</groupId>
+        <artifactId>maven-compiler-plugin</artifactId>
+        <configuration>
+          <fork>true</fork>
+        </configuration>
+      </plugin>
+
       <plugin>
         <artifactId>maven-jar-plugin</artifactId>
         <configuration>
@@ -287,12 +327,13 @@ limitations under the License.
 	      <filter>
 		  <artifact>*:*</artifact>
 		  <excludes>
+		      <!-- Exclude InetAddressResolverProvider to prevent the dnsjava SPI / LiteralByteString conflict (NoClassDefFoundError on JDK 21+) -->
+		      <exclude>META-INF/services/java.net.spi.InetAddressResolverProvider</exclude>
 		      <exclude>META-INF/*.SF</exclude>
 		      <exclude>META-INF/*.DSA</exclude>
 		      <exclude>META-INF/*.RSA</exclude>
           <exclude>META-INF/**/pom.properties</exclude>
           <exclude>META-INF/**/pom.xml</exclude>
-          <exclude>META-INF/MANIFEST.MF</exclude>
           <exclude>META-INF/LICENSE</exclude>
           <exclude>META-INF/NOTICE.txt</exclude>
           <exclude>META-INF/NOTICE</exclude>