[Improvement] Improve docs for relasing 0.7.0

amoro-core/src/main/java/org/apache/amoro/table/TableProperties.java

@@ -29,15 +29,12 @@ public class TableProperties {
 
   private TableProperties() {}
 
-  public static final String SELF_OPTIMIZING_MIN_PLAN_INTERVAL =
-      "self-optimizing.min-plan-interval";
-  public static final long SELF_OPTIMIZING_MIN_PLAN_INTERVAL_DEFAULT = 60000;
-
   public static final String TABLE_PARTITION_PROPERTIES = "table.partition-properties";
 
   public static final String BASE_TABLE_MAX_TRANSACTION_ID = "base.table.max-transaction-id";
 
   public static final String PARTITION_OPTIMIZED_SEQUENCE = "max-txId";
+
   public static final String PARTITION_BASE_OPTIMIZED_TIME = "base-op-time";
 
   public static final String LOCATION = "location";
@@ -118,6 +115,10 @@ private TableProperties() {}
       "self-optimizing.full.rewrite-all-files";
   public static final boolean SELF_OPTIMIZING_FULL_REWRITE_ALL_FILES_DEFAULT = true;
 
+  public static final String SELF_OPTIMIZING_MIN_PLAN_INTERVAL =
+      "self-optimizing.min-plan-interval";
+  public static final long SELF_OPTIMIZING_MIN_PLAN_INTERVAL_DEFAULT = 60000;
+
   /** deprecated table optimize related properties */
   @Deprecated public static final String ENABLE_OPTIMIZE = "optimize.enable";
 
@@ -145,49 +146,49 @@ private TableProperties() {}
   public static final String ENABLE_TABLE_EXPIRE = "table-expire.enabled";
 
   public static final boolean ENABLE_TABLE_EXPIRE_DEFAULT = true;
-  @Deprecated public static final String ENABLE_TABLE_EXPIRE_LEGACY = "table-expire.enable";
 
   public static final String CHANGE_DATA_TTL = "change.data.ttl.minutes";
   public static final long CHANGE_DATA_TTL_DEFAULT = 10080; // 7 Days
 
   public static final String BASE_SNAPSHOT_KEEP_MINUTES = "snapshot.base.keep.minutes";
   public static final long BASE_SNAPSHOT_KEEP_MINUTES_DEFAULT = 720; // 12 Hours
 
+  public static final String ENABLE_ORPHAN_CLEAN = "clean-orphan-file.enabled";
+  public static final boolean ENABLE_ORPHAN_CLEAN_DEFAULT = false;
+
+  public static final String MIN_ORPHAN_FILE_EXISTING_TIME =
+      "clean-orphan-file.min-existing-time-minutes";
+  public static final long MIN_ORPHAN_FILE_EXISTING_TIME_DEFAULT = 2880; // 2 Days
+  public static final String ENABLE_DANGLING_DELETE_FILES_CLEAN =
+      "clean-dangling-delete-files.enabled";
+  public static final boolean ENABLE_DANGLING_DELETE_FILES_CLEAN_DEFAULT = true;
+
   public static final String ENABLE_DATA_EXPIRATION = "data-expire.enabled";
   public static final boolean ENABLE_DATA_EXPIRATION_DEFAULT = false;
+
   public static final String DATA_EXPIRATION_LEVEL = "data-expire.level";
   public static final String DATA_EXPIRATION_LEVEL_DEFAULT = "partition";
+
   public static final String DATA_EXPIRATION_FIELD = "data-expire.field";
+
   public static final String DATA_EXPIRATION_DATE_STRING_PATTERN =
       "data-expire.datetime-string-pattern";
   public static final String DATA_EXPIRATION_DATE_STRING_PATTERN_DEFAULT = "yyyy-MM-dd";
+
   public static final String DATA_EXPIRATION_DATE_NUMBER_FORMAT =
       "data-expire.datetime-number-format";
   public static final String DATA_EXPIRATION_DATE_NUMBER_FORMAT_DEFAULT = "TIMESTAMP_MS";
+
   public static final String DATA_EXPIRATION_RETENTION_TIME = "data-expire.retention-time";
+
   public static final String DATA_EXPIRATION_BASE_ON_RULE = "data-expire.base-on-rule";
   public static final String DATA_EXPIRATION_BASE_ON_RULE_DEFAULT = "LAST_COMMIT_TIME";
 
-  public static final String ENABLE_DANGLING_DELETE_FILES_CLEAN =
-      "clean-dangling-delete-files.enabled";
-  public static final boolean ENABLE_DANGLING_DELETE_FILES_CLEAN_DEFAULT = true;
-
-  public static final String ENABLE_ORPHAN_CLEAN = "clean-orphan-file.enabled";
-  public static final boolean ENABLE_ORPHAN_CLEAN_DEFAULT = false;
-  @Deprecated public static final String ENABLE_ORPHAN_CLEAN_LEGACY = "clean-orphan-file.enable";
-
-  public static final String MIN_ORPHAN_FILE_EXISTING_TIME =
-      "clean-orphan-file.min-existing-time-minutes";
-  public static final long MIN_ORPHAN_FILE_EXISTING_TIME_DEFAULT = 2880; // 2 Days
-
   public static final String ENABLE_TABLE_TRASH = "table-trash.enabled";
   public static final boolean ENABLE_TABLE_TRASH_DEFAULT = false;
 
   public static final String TABLE_TRASH_CUSTOM_ROOT_LOCATION = "table-trash.custom-root-location";
 
-  public static final String TABLE_TRASH_KEEP_DAYS = "table-trash.keep.days";
-  public static final int TABLE_TRASH_KEEP_DAYS_DEFAULT = 7; // 7 Days
-
   public static final String TABLE_TRASH_FILE_PATTERN = "table-trash.file-pattern";
   public static final String TABLE_TRASH_FILE_PATTERN_DEFAULT =
       ".+\\.parquet"
@@ -199,6 +200,9 @@ private TableProperties() {}
           + // v123.metadata.json
           "|.*[0-9a-fA-F]{8}(-[0-9a-fA-F]{4}){3}-[0-9a-fA-F]{12}-m[0-9]+\\.avro"; // UUID-m0.avro
 
+  @Deprecated public static final String ENABLE_TABLE_EXPIRE_LEGACY = "table-expire.enable";
+  @Deprecated public static final String ENABLE_ORPHAN_CLEAN_LEGACY = "clean-orphan-file.enable";
+
   /** table tag management related properties */
   public static final String ENABLE_AUTO_CREATE_TAG = "tag.auto-create.enabled";
 
@@ -226,15 +230,18 @@ private TableProperties() {}
   public static final String FILE_FORMAT_PARQUET = "parquet";
 
   public static final String FILE_FORMAT_ORC = "orc";
+
   public static final String BASE_FILE_FORMAT = "base.write.format";
-  public static final String DELTA_FILE_FORMAT = "delta.write.format";
   public static final String BASE_FILE_FORMAT_DEFAULT = FILE_FORMAT_PARQUET;
 
+  public static final String DELTA_FILE_FORMAT = "delta.write.format";
+
   public static final String CHANGE_FILE_FORMAT = "change.write.format";
   public static final String CHANGE_FILE_FORMAT_DEFAULT = FILE_FORMAT_PARQUET;
 
   public static final String DEFAULT_FILE_FORMAT =
       org.apache.iceberg.TableProperties.DEFAULT_FILE_FORMAT;
+
   public static final String DEFAULT_FILE_FORMAT_DEFAULT =
       org.apache.iceberg.TableProperties.DEFAULT_FILE_FORMAT_DEFAULT;
 
@@ -280,11 +287,11 @@ private TableProperties() {}
   public static final String SPLIT_OPEN_FILE_COST =
       org.apache.iceberg.TableProperties.SPLIT_OPEN_FILE_COST;
   public static final long SPLIT_OPEN_FILE_COST_DEFAULT = 4 * 1024 * 1024; // 4MB
+
   /** log store related properties */
   public static final String ENABLE_LOG_STORE = "log-store.enabled";
 
   public static final boolean ENABLE_LOG_STORE_DEFAULT = false;
-  @Deprecated public static final String ENABLE_LOG_STORE_LEGACY = "log-store.enable";
 
   public static final String LOG_STORE_TYPE = "log-store.type";
   public static final String LOG_STORE_STORAGE_TYPE_KAFKA = "kafka";
@@ -305,13 +312,19 @@ private TableProperties() {}
 
   public static final String OWNER = "owner";
 
+  @Deprecated public static final String ENABLE_LOG_STORE_LEGACY = "log-store.enable";
+
   /** table format related properties */
   public static final String TABLE_FORMAT = "table-format";
 
   public static final String MIXED_FORMAT_PRIMARY_KEY_FIELDS = "mixed-format.primary-key-fields";
+
   public static final String MIXED_FORMAT_TABLE_STORE = "mixed-format.table-store";
+
   public static final String MIXED_FORMAT_TABLE_STORE_BASE = "base";
+
   public static final String MIXED_FORMAT_TABLE_STORE_CHANGE = "change";
+
   public static final String MIXED_FORMAT_CHANGE_STORE_IDENTIFIER =
       "mixed-format.change.identifier";
 

docs/admin-guides/deployment.md

@@ -14,12 +14,10 @@ You can choose to download the stable release package from [download page](../..
 
 ## System requirements
 
-- Java 8 is required. Java 17 is required for Trino.
+- Java 8 is required.
 - Optional: MySQL 5.5 or higher
 - Optional: PostgreSQL 14.x or higher
 - Optional: ZooKeeper 3.4.x or higher
-- Optional: Hive (2.x or 3.x)
-- Optional: Hadoop (2.9.x or 3.x)
 
 ## Download the distribution
 
@@ -32,54 +30,24 @@ Unzip it to create the amoro-x.y.z directory in the same directory, and then go
 You can build based on the master branch without compiling Trino. The compilation method and the directory of results are described below:
 
 ```shell
-git clone https://github.com/apache/amoro.git
-cd amoro
-base_dir=$(pwd) 
-mvn clean package -DskipTests
-cd amoro-ams/dist/target/
-ls
-apache-amoro-x.y.z-bin.tar.gz # AMS release package
-dist-x.y.z-tests.jar
-dist-x.y.z.jar
-archive-tmp/
-maven-archiver/
-
-cd ${base_dir}/amoro-mixed-format/amoro-mixed-format-flink/v1.15/amoro-mixed-format-flink-runtime-1.15/target
-ls 
-amoro-mixed-format-flink-runtime-1.15-x.y.z-tests.jar
+$ git clone https://github.com/apache/amoro.git
+$ cd amoro
+$ base_dir=$(pwd) 
+$ mvn clean package -DskipTests
+$ cd amoro-ams/dist/target/
+$ ls
+amoro-x.y.z-bin.zip # AMS release package
+
+$ cd ${base_dir}/amoro-mixed-format/amoro-mixed-format-flink/v1.15/amoro-mixed-format-flink-runtime-1.15/target
+$ ls 
 amoro-mixed-format-flink-runtime-1.15-x.y.z.jar # Flink 1.15 runtime package
-original-amoro-mixed-format-flink-runtime-1.15-x.y.z.jar
-maven-archiver/
 
-cd ${base_dir}/amoro-mixed-format/amoro-mixed-format-spark/v3.2/amoro-mixed-format-spark-runtime-3.2/target
-ls
+$ cd ${base_dir}/amoro-mixed-format/amoro-mixed-format-spark/v3.2/amoro-mixed-format-spark-runtime-3.2/target
+$ ls
 amoro-mixed-format-spark-runtime-3.2-x.y.z.jar # Spark v3.2 runtime package)
-amoro-mixed-format-spark-runtime-3.2-x.y.z-tests.jar
-amoro-mixed-format-spark-runtime-3.2-x.y.z-sources.jar
-original-amoro-mixed-format-spark-runtime-3.2-x.y.z.jar
 ```
 
-If the Flink version in the amoro-ams/amoro-ams-optimizer/amoro-optimizer-flink module you compiled is lower than 1.15, you must add the `-Pflink-pre-1.15` parameter before mvn.
-for example `mvn clean package -Pflink-pre-1.15 -Dflink-optimizer.flink-version=1.14.6 -DskipTests` to compile.
-
-If you need to compile the Trino module at the same time, you need to install jdk17 locally and configure `toolchains.xml` in the user's `${user.home}/.m2/` directory,
-then run `mvn package -Ptoolchain,build-mixed-format-trino` to compile the entire project.
-
-```xml
-<?xml version="1.0" encoding="UTF-8"?>
-<toolchains>
-    <toolchain>
-        <type>jdk</type>
-        <provides>
-            <version>17</version>
-            <vendor>sun</vendor>
-        </provides>
-        <configuration>
-            <jdkHome>${YourJDK17Home}</jdkHome>
-        </configuration>
-    </toolchain>
-</toolchains>
-```
+More build guide can be found in the project's [README](https://github.com/apache/amoro?tab=readme-ov-file#building).
 
 ## Configuration
 
@@ -120,13 +88,13 @@ You can use MySQL/PostgreSQL as the system database instead of the default Derby
 If you would like to use MySQL as the system database, you need to manually download the [MySQL JDBC Connector](https://repo1.maven.org/maven2/com/mysql/mysql-connector-j/8.1.0/mysql-connector-j-8.1.0.jar)
 and move it into the `{AMORO_HOME}/lib/` directory. You can use the following command to complete these operations:
 ```shell
-cd ${AMORO_HOME}
-MYSQL_JDBC_DRIVER_VERSION=8.0.30
-wget https://repo1.maven.org/maven2/mysql/mysql-connector-java/${MYSQL_JDBC_DRIVER_VERSION}/mysql-connector-java-${MYSQL_JDBC_DRIVER_VERSION}.jar
-mv mysql-connector-java-${MYSQL_JDBC_DRIVER_VERSION}.jar lib
+$ cd ${AMORO_HOME}
+$ MYSQL_JDBC_DRIVER_VERSION=8.0.30
+$ wget https://repo1.maven.org/maven2/mysql/mysql-connector-java/${MYSQL_JDBC_DRIVER_VERSION}/mysql-connector-java-${MYSQL_JDBC_DRIVER_VERSION}.jar
+$ mv mysql-connector-java-${MYSQL_JDBC_DRIVER_VERSION}.jar lib
 ```
 
-Create an empty database in MySQL/PostgreSQL, then AMS will automatically create table structures in this MySQL/PostgreSQL database when it first started.
+Create an empty database in MySQL/PostgreSQL, then AMS will automatically create tables in this MySQL/PostgreSQL database when it first started.
 
 One thing you need to do is Adding MySQL/PostgreSQL configuration under `config.yaml` of Ams:
 
@@ -172,20 +140,33 @@ AMS provides implementations of `LocalContainer` and `FlinkContainer` by default
 ```yaml
 containers:
   - name: localContainer
-    container-impl: org.apache.amoro.optimizer.LocalOptimizerContainer
+    container-impl: org.apache.amoro.server.manager.LocalOptimizerContainer
     properties:
       export.JAVA_HOME: "/opt/java"   # JDK environment
 
   - name: flinkContainer
-    container-impl: org.apache.amoro.optimizer.FlinkOptimizerContainer
+    container-impl: org.apache.amoro.server.manager.FlinkOptimizerContainer
     properties:
       flink-home: "/opt/flink/"                                     # The installation directory of Flink
       export.JVM_ARGS: "-Djava.security.krb5.conf=/opt/krb5.conf"   # Submitting Flink jobs with Java parameters, such as Kerberos parameters.
       export.HADOOP_CONF_DIR: "/etc/hadoop/conf/"                   # Hadoop configuration file directory
       export.HADOOP_USER_NAME: "hadoop"                             # Hadoop user
       export.FLINK_CONF_DIR: "/etc/hadoop/conf/"                    # Flink configuration file directory
+
+  - name: sparkContainer
+    container-impl: org.apache.amoro.server.manager.SparkOptimizerContainer
+    properties:
+      spark-home: /opt/spark/                                     # Spark install home
+      master: yarn                                                # The cluster manager to connect to. See the list of https://spark.apache.org/docs/latest/submitting-applications.html#master-urls.
+      deploy-mode: cluster                                        # Spark deploy mode, client or cluster
+      export.JVM_ARGS: -Djava.security.krb5.conf=/opt/krb5.conf   # Spark launch jvm args, like kerberos config when ues kerberos
+      export.HADOOP_CONF_DIR: /etc/hadoop/conf/                   # Hadoop config dir
+      export.HADOOP_USER_NAME: hadoop                             # Hadoop user submit on yarn
+      export.SPARK_CONF_DIR: /opt/spark/conf/                     # Spark config dir
 ```
 
+More optimizer container configurations can be found in [managing optimizers](../managing-optimizers/).
+
 ### Configure terminal
 
 The Terminal module in the AMS Dashboard allows users to execute SQL directly on the platform. Currently, the Terminal backend supports two implementations: `local` and `kyuubi`.
@@ -201,6 +182,16 @@ ams:
     local.using-session-catalog-for-hive: true
 ```
 
+More properties the terminal supports including:
+
+| Key                      | Default | Description                                                                                       |
+|--------------------------|---------|---------------------------------------------------------------------------------------------------|
+| terminal.backend         | local   | Terminal backend implementation. local, kyuubi and custom are valid values.                       |
+| terminal.factory         | -       | Session factory implement of terminal, `terminal.backend` must be `custom` if this is set.        |
+| terminal.result.limit    | 1000    | Row limit of result-set                                                                           |
+| terminal.stop-on-error   | false   | When a statement fails to execute, stop execution or continue executing the remaining statements. |
+| terminal.session.timeout | 30      | Session timeout in minutes.                                                                       |
+
 ### Configure metric reporter
 
 Amoro provides metric reporters by plugin mechanism to connect to  external metric systems.
@@ -266,26 +257,13 @@ The following JVM options could be set in `${AMORO_CONF_DIR}/jvm.properties`.
 | jmx.remote.port | "-Dcom.sun.management.jmxremote.port=${value}  | Enable remote debug      |
 | extra.options   | "JAVA_OPTS="${JAVA_OPTS} ${JVM_EXTRA_CONFIG}"  | The addition jvm options |
 
-### Terminal configurations
-
-Terminal support local and kyuubi, the default is local. If the user uses local to run in the spark local context, you can set the **spark.*** configuration, and if you use kyuubi, you can set the **kyuubi.*** configuration
-
-| Key                      | Default | Description                                                                                       |
-|--------------------------|---------|---------------------------------------------------------------------------------------------------|
-| terminal.backend         | local   | Terminal backend implementation. local, kyuubi and custom are valid values.                       |
-| terminal.factory         | -       | Session factory implement of terminal, `terminal.backend` must be `custom` if this is set.        |
-| terminal.result.limit    | 1000    | Row limit of result-set                                                                           |
-| terminal.stop-on-error   | false   | When a statement fails to execute, stop execution or continue executing the remaining statements. |
-| terminal.session.timeout | 30      | Session timeout in minutes.                                                                       |
-
-
 ## Start AMS
 
 Enter the directory amoro-x.y.z and execute bin/ams.sh start to start AMS.
 
 ```shell
-cd amoro-x.y.z
-bin/ams.sh start
+$ cd amoro-x.y.z
+$ bin/ams.sh start
 ```
 
 Then, access http://localhost:1630 through a browser to see the login page. If it appears, it means that the startup is
@@ -294,7 +272,8 @@ successful. The default username and password for login are both "admin".
 You can also restart/stop AMS with the following command:
 
 ```shell
-bin/ams.sh restart/stop
+$ bin/ams.sh restart
+$ bin/ams.sh stop
 ```
 
 ## Upgrade AMS
@@ -313,7 +292,7 @@ Replace all contents in the original `{AMORO_HOME}/plugin` directory with the co
 Backup the old content before replacing it, so that you can roll back the upgrade operation if necessary.
 {{< /hint >}}
 
-### Configure new parameters
+### Configure new properties
 
 The old configuration file `{AMORO_HOME}/conf/config.yaml` is usually compatible with the new version, but the new version may introduce new parameters. Try to compare the configuration files of the old and new versions, and reconfigure the parameters if necessary.