[1/2] phoenix git commit: PHOENIX-2460 Implement scrutiny command to validate whether or not an index is in sync with the data table (Vincent Poon)
Repository: phoenix Updated Branches: refs/heads/4.x-HBase-1.2 4a81d9277 -> 549d22da9 http://git-wip-us.apache.org/repos/asf/phoenix/blob/549d22da/phoenix-core/src/main/java/org/apache/phoenix/mapreduce/index/IndexScrutinyTool.java -- diff --git a/phoenix-core/src/main/java/org/apache/phoenix/mapreduce/index/IndexScrutinyTool.java b/phoenix-core/src/main/java/org/apache/phoenix/mapreduce/index/IndexScrutinyTool.java new file mode 100644 index 000..f3ff39e --- /dev/null +++ b/phoenix-core/src/main/java/org/apache/phoenix/mapreduce/index/IndexScrutinyTool.java @@ -0,0 +1,522 @@ +/* + * Licensed to the Apache Software Foundation (ASF) under one + * or more contributor license agreements. See the NOTICE file + * distributed with this work for additional information + * regarding copyright ownership. The ASF licenses this file + * to you under the Apache License, Version 2.0 (the + * "License"); you may not use this file except in compliance + * with the License. You may obtain a copy of the License at + * + * http://www.apache.org/licenses/LICENSE-2.0 + * + * Unless required by applicable law or agreed to in writing, software + * distributed under the License is distributed on an "AS IS" BASIS, + * WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied. + * See the License for the specific language governing permissions and + * limitations under the License. + */ +package org.apache.phoenix.mapreduce.index; + +import java.io.IOException; +import java.sql.Connection; +import java.sql.DatabaseMetaData; +import java.sql.ResultSet; +import java.sql.SQLException; +import java.util.List; + +import org.apache.commons.cli.CommandLine; +import org.apache.commons.cli.CommandLineParser; +import org.apache.commons.cli.HelpFormatter; +import org.apache.commons.cli.Option; +import org.apache.commons.cli.Options; +import org.apache.commons.cli.ParseException; +import org.apache.commons.cli.PosixParser; +import org.apache.commons.lang.exception.ExceptionUtils; +import org.apache.hadoop.conf.Configuration; +import org.apache.hadoop.conf.Configured; +import org.apache.hadoop.fs.FileSystem; +import org.apache.hadoop.fs.Path; +import org.apache.hadoop.hbase.HBaseConfiguration; +import org.apache.hadoop.hbase.TableName; +import org.apache.hadoop.hbase.client.HBaseAdmin; +import org.apache.hadoop.hbase.mapreduce.TableMapReduceUtil; +import org.apache.hadoop.hbase.util.FSUtils; +import org.apache.hadoop.io.Text; +import org.apache.hadoop.mapreduce.Job; +import org.apache.hadoop.mapreduce.lib.output.FileOutputFormat; +import org.apache.hadoop.mapreduce.lib.output.NullOutputFormat; +import org.apache.hadoop.mapreduce.lib.output.TextOutputFormat; +import org.apache.hadoop.util.Tool; +import org.apache.hadoop.util.ToolRunner; +import org.apache.phoenix.jdbc.PhoenixConnection; +import org.apache.phoenix.mapreduce.CsvBulkImportUtil; +import org.apache.phoenix.mapreduce.util.ConnectionUtil; +import org.apache.phoenix.mapreduce.util.PhoenixConfigurationUtil; +import org.apache.phoenix.mapreduce.util.PhoenixMapReduceUtil; +import org.apache.phoenix.parse.HintNode.Hint; +import org.apache.phoenix.schema.PTable; +import org.apache.phoenix.util.EnvironmentEdgeManager; +import org.apache.phoenix.util.PhoenixRuntime; +import org.apache.phoenix.util.QueryUtil; +import org.apache.phoenix.util.SchemaUtil; +import org.slf4j.Logger; +import org.slf4j.LoggerFactory; + +import com.google.common.annotations.VisibleForTesting; +import com.google.common.base.Preconditions; +import com.google.common.collect.Lists; + +/** + * An MR job to verify that the index table is in sync with the data table. + * + */ +public class IndexScrutinyTool extends Configured implements Tool { + +private static final Logger LOG = LoggerFactory.getLogger(IndexScrutinyTool.class); + +private static final Option SCHEMA_NAME_OPTION = +new Option("s", "schema", true, "Phoenix schema name (optional)"); +private static final Option DATA_TABLE_OPTION = +new Option("dt", "data-table", true, "Data table name (mandatory)"); +private static final Option INDEX_TABLE_OPTION = +new Option("it", "index-table", true, +"Index table name (mandatory)."); +private static final Option TIMESTAMP = +new Option("t", "time", true, +"Timestamp in millis used to compare the index and data tables. Defaults to current time minus 60 seconds"); + +private static final Option RUN_FOREGROUND_OPTION = +new Option("runfg", "run-foreground", false, "Applicable on top of -direct option." ++ "If specified, runs index scrutiny in Foreground. Default - Runs the build in background."); + +private static final Option SNAPSHOT_OPTION = //TODO check if this works +new Option("snap", "snapshot", false, +"If specified, uses Snapshots for
[1/2] phoenix git commit: PHOENIX-2460 Implement scrutiny command to validate whether or not an index is in sync with the data table (Vincent Poon)
Repository: phoenix Updated Branches: refs/heads/4.x-HBase-1.1 cce7ab29a -> 124404ae2 http://git-wip-us.apache.org/repos/asf/phoenix/blob/124404ae/phoenix-core/src/main/java/org/apache/phoenix/mapreduce/index/IndexScrutinyTool.java -- diff --git a/phoenix-core/src/main/java/org/apache/phoenix/mapreduce/index/IndexScrutinyTool.java b/phoenix-core/src/main/java/org/apache/phoenix/mapreduce/index/IndexScrutinyTool.java new file mode 100644 index 000..f3ff39e --- /dev/null +++ b/phoenix-core/src/main/java/org/apache/phoenix/mapreduce/index/IndexScrutinyTool.java @@ -0,0 +1,522 @@ +/* + * Licensed to the Apache Software Foundation (ASF) under one + * or more contributor license agreements. See the NOTICE file + * distributed with this work for additional information + * regarding copyright ownership. The ASF licenses this file + * to you under the Apache License, Version 2.0 (the + * "License"); you may not use this file except in compliance + * with the License. You may obtain a copy of the License at + * + * http://www.apache.org/licenses/LICENSE-2.0 + * + * Unless required by applicable law or agreed to in writing, software + * distributed under the License is distributed on an "AS IS" BASIS, + * WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied. + * See the License for the specific language governing permissions and + * limitations under the License. + */ +package org.apache.phoenix.mapreduce.index; + +import java.io.IOException; +import java.sql.Connection; +import java.sql.DatabaseMetaData; +import java.sql.ResultSet; +import java.sql.SQLException; +import java.util.List; + +import org.apache.commons.cli.CommandLine; +import org.apache.commons.cli.CommandLineParser; +import org.apache.commons.cli.HelpFormatter; +import org.apache.commons.cli.Option; +import org.apache.commons.cli.Options; +import org.apache.commons.cli.ParseException; +import org.apache.commons.cli.PosixParser; +import org.apache.commons.lang.exception.ExceptionUtils; +import org.apache.hadoop.conf.Configuration; +import org.apache.hadoop.conf.Configured; +import org.apache.hadoop.fs.FileSystem; +import org.apache.hadoop.fs.Path; +import org.apache.hadoop.hbase.HBaseConfiguration; +import org.apache.hadoop.hbase.TableName; +import org.apache.hadoop.hbase.client.HBaseAdmin; +import org.apache.hadoop.hbase.mapreduce.TableMapReduceUtil; +import org.apache.hadoop.hbase.util.FSUtils; +import org.apache.hadoop.io.Text; +import org.apache.hadoop.mapreduce.Job; +import org.apache.hadoop.mapreduce.lib.output.FileOutputFormat; +import org.apache.hadoop.mapreduce.lib.output.NullOutputFormat; +import org.apache.hadoop.mapreduce.lib.output.TextOutputFormat; +import org.apache.hadoop.util.Tool; +import org.apache.hadoop.util.ToolRunner; +import org.apache.phoenix.jdbc.PhoenixConnection; +import org.apache.phoenix.mapreduce.CsvBulkImportUtil; +import org.apache.phoenix.mapreduce.util.ConnectionUtil; +import org.apache.phoenix.mapreduce.util.PhoenixConfigurationUtil; +import org.apache.phoenix.mapreduce.util.PhoenixMapReduceUtil; +import org.apache.phoenix.parse.HintNode.Hint; +import org.apache.phoenix.schema.PTable; +import org.apache.phoenix.util.EnvironmentEdgeManager; +import org.apache.phoenix.util.PhoenixRuntime; +import org.apache.phoenix.util.QueryUtil; +import org.apache.phoenix.util.SchemaUtil; +import org.slf4j.Logger; +import org.slf4j.LoggerFactory; + +import com.google.common.annotations.VisibleForTesting; +import com.google.common.base.Preconditions; +import com.google.common.collect.Lists; + +/** + * An MR job to verify that the index table is in sync with the data table. + * + */ +public class IndexScrutinyTool extends Configured implements Tool { + +private static final Logger LOG = LoggerFactory.getLogger(IndexScrutinyTool.class); + +private static final Option SCHEMA_NAME_OPTION = +new Option("s", "schema", true, "Phoenix schema name (optional)"); +private static final Option DATA_TABLE_OPTION = +new Option("dt", "data-table", true, "Data table name (mandatory)"); +private static final Option INDEX_TABLE_OPTION = +new Option("it", "index-table", true, +"Index table name (mandatory)."); +private static final Option TIMESTAMP = +new Option("t", "time", true, +"Timestamp in millis used to compare the index and data tables. Defaults to current time minus 60 seconds"); + +private static final Option RUN_FOREGROUND_OPTION = +new Option("runfg", "run-foreground", false, "Applicable on top of -direct option." ++ "If specified, runs index scrutiny in Foreground. Default - Runs the build in background."); + +private static final Option SNAPSHOT_OPTION = //TODO check if this works +new Option("snap", "snapshot", false, +"If specified, uses Snapshots for
[1/2] phoenix git commit: PHOENIX-2460 Implement scrutiny command to validate whether or not an index is in sync with the data table (Vincent Poon)
Repository: phoenix Updated Branches: refs/heads/4.x-HBase-0.98 ce6810f42 -> 08e2a29f6 http://git-wip-us.apache.org/repos/asf/phoenix/blob/08e2a29f/phoenix-core/src/main/java/org/apache/phoenix/mapreduce/index/IndexScrutinyTool.java -- diff --git a/phoenix-core/src/main/java/org/apache/phoenix/mapreduce/index/IndexScrutinyTool.java b/phoenix-core/src/main/java/org/apache/phoenix/mapreduce/index/IndexScrutinyTool.java new file mode 100644 index 000..f3ff39e --- /dev/null +++ b/phoenix-core/src/main/java/org/apache/phoenix/mapreduce/index/IndexScrutinyTool.java @@ -0,0 +1,522 @@ +/* + * Licensed to the Apache Software Foundation (ASF) under one + * or more contributor license agreements. See the NOTICE file + * distributed with this work for additional information + * regarding copyright ownership. The ASF licenses this file + * to you under the Apache License, Version 2.0 (the + * "License"); you may not use this file except in compliance + * with the License. You may obtain a copy of the License at + * + * http://www.apache.org/licenses/LICENSE-2.0 + * + * Unless required by applicable law or agreed to in writing, software + * distributed under the License is distributed on an "AS IS" BASIS, + * WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied. + * See the License for the specific language governing permissions and + * limitations under the License. + */ +package org.apache.phoenix.mapreduce.index; + +import java.io.IOException; +import java.sql.Connection; +import java.sql.DatabaseMetaData; +import java.sql.ResultSet; +import java.sql.SQLException; +import java.util.List; + +import org.apache.commons.cli.CommandLine; +import org.apache.commons.cli.CommandLineParser; +import org.apache.commons.cli.HelpFormatter; +import org.apache.commons.cli.Option; +import org.apache.commons.cli.Options; +import org.apache.commons.cli.ParseException; +import org.apache.commons.cli.PosixParser; +import org.apache.commons.lang.exception.ExceptionUtils; +import org.apache.hadoop.conf.Configuration; +import org.apache.hadoop.conf.Configured; +import org.apache.hadoop.fs.FileSystem; +import org.apache.hadoop.fs.Path; +import org.apache.hadoop.hbase.HBaseConfiguration; +import org.apache.hadoop.hbase.TableName; +import org.apache.hadoop.hbase.client.HBaseAdmin; +import org.apache.hadoop.hbase.mapreduce.TableMapReduceUtil; +import org.apache.hadoop.hbase.util.FSUtils; +import org.apache.hadoop.io.Text; +import org.apache.hadoop.mapreduce.Job; +import org.apache.hadoop.mapreduce.lib.output.FileOutputFormat; +import org.apache.hadoop.mapreduce.lib.output.NullOutputFormat; +import org.apache.hadoop.mapreduce.lib.output.TextOutputFormat; +import org.apache.hadoop.util.Tool; +import org.apache.hadoop.util.ToolRunner; +import org.apache.phoenix.jdbc.PhoenixConnection; +import org.apache.phoenix.mapreduce.CsvBulkImportUtil; +import org.apache.phoenix.mapreduce.util.ConnectionUtil; +import org.apache.phoenix.mapreduce.util.PhoenixConfigurationUtil; +import org.apache.phoenix.mapreduce.util.PhoenixMapReduceUtil; +import org.apache.phoenix.parse.HintNode.Hint; +import org.apache.phoenix.schema.PTable; +import org.apache.phoenix.util.EnvironmentEdgeManager; +import org.apache.phoenix.util.PhoenixRuntime; +import org.apache.phoenix.util.QueryUtil; +import org.apache.phoenix.util.SchemaUtil; +import org.slf4j.Logger; +import org.slf4j.LoggerFactory; + +import com.google.common.annotations.VisibleForTesting; +import com.google.common.base.Preconditions; +import com.google.common.collect.Lists; + +/** + * An MR job to verify that the index table is in sync with the data table. + * + */ +public class IndexScrutinyTool extends Configured implements Tool { + +private static final Logger LOG = LoggerFactory.getLogger(IndexScrutinyTool.class); + +private static final Option SCHEMA_NAME_OPTION = +new Option("s", "schema", true, "Phoenix schema name (optional)"); +private static final Option DATA_TABLE_OPTION = +new Option("dt", "data-table", true, "Data table name (mandatory)"); +private static final Option INDEX_TABLE_OPTION = +new Option("it", "index-table", true, +"Index table name (mandatory)."); +private static final Option TIMESTAMP = +new Option("t", "time", true, +"Timestamp in millis used to compare the index and data tables. Defaults to current time minus 60 seconds"); + +private static final Option RUN_FOREGROUND_OPTION = +new Option("runfg", "run-foreground", false, "Applicable on top of -direct option." ++ "If specified, runs index scrutiny in Foreground. Default - Runs the build in background."); + +private static final Option SNAPSHOT_OPTION = //TODO check if this works +new Option("snap", "snapshot", false, +"If specified, uses Snapshots for
[1/2] phoenix git commit: PHOENIX-2460 Implement scrutiny command to validate whether or not an index is in sync with the data table (Vincent Poon)
Repository: phoenix Updated Branches: refs/heads/master d6381afc3 -> fc6594883 http://git-wip-us.apache.org/repos/asf/phoenix/blob/fc659488/phoenix-core/src/main/java/org/apache/phoenix/mapreduce/index/IndexScrutinyTool.java -- diff --git a/phoenix-core/src/main/java/org/apache/phoenix/mapreduce/index/IndexScrutinyTool.java b/phoenix-core/src/main/java/org/apache/phoenix/mapreduce/index/IndexScrutinyTool.java new file mode 100644 index 000..f3ff39e --- /dev/null +++ b/phoenix-core/src/main/java/org/apache/phoenix/mapreduce/index/IndexScrutinyTool.java @@ -0,0 +1,522 @@ +/* + * Licensed to the Apache Software Foundation (ASF) under one + * or more contributor license agreements. See the NOTICE file + * distributed with this work for additional information + * regarding copyright ownership. The ASF licenses this file + * to you under the Apache License, Version 2.0 (the + * "License"); you may not use this file except in compliance + * with the License. You may obtain a copy of the License at + * + * http://www.apache.org/licenses/LICENSE-2.0 + * + * Unless required by applicable law or agreed to in writing, software + * distributed under the License is distributed on an "AS IS" BASIS, + * WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied. + * See the License for the specific language governing permissions and + * limitations under the License. + */ +package org.apache.phoenix.mapreduce.index; + +import java.io.IOException; +import java.sql.Connection; +import java.sql.DatabaseMetaData; +import java.sql.ResultSet; +import java.sql.SQLException; +import java.util.List; + +import org.apache.commons.cli.CommandLine; +import org.apache.commons.cli.CommandLineParser; +import org.apache.commons.cli.HelpFormatter; +import org.apache.commons.cli.Option; +import org.apache.commons.cli.Options; +import org.apache.commons.cli.ParseException; +import org.apache.commons.cli.PosixParser; +import org.apache.commons.lang.exception.ExceptionUtils; +import org.apache.hadoop.conf.Configuration; +import org.apache.hadoop.conf.Configured; +import org.apache.hadoop.fs.FileSystem; +import org.apache.hadoop.fs.Path; +import org.apache.hadoop.hbase.HBaseConfiguration; +import org.apache.hadoop.hbase.TableName; +import org.apache.hadoop.hbase.client.HBaseAdmin; +import org.apache.hadoop.hbase.mapreduce.TableMapReduceUtil; +import org.apache.hadoop.hbase.util.FSUtils; +import org.apache.hadoop.io.Text; +import org.apache.hadoop.mapreduce.Job; +import org.apache.hadoop.mapreduce.lib.output.FileOutputFormat; +import org.apache.hadoop.mapreduce.lib.output.NullOutputFormat; +import org.apache.hadoop.mapreduce.lib.output.TextOutputFormat; +import org.apache.hadoop.util.Tool; +import org.apache.hadoop.util.ToolRunner; +import org.apache.phoenix.jdbc.PhoenixConnection; +import org.apache.phoenix.mapreduce.CsvBulkImportUtil; +import org.apache.phoenix.mapreduce.util.ConnectionUtil; +import org.apache.phoenix.mapreduce.util.PhoenixConfigurationUtil; +import org.apache.phoenix.mapreduce.util.PhoenixMapReduceUtil; +import org.apache.phoenix.parse.HintNode.Hint; +import org.apache.phoenix.schema.PTable; +import org.apache.phoenix.util.EnvironmentEdgeManager; +import org.apache.phoenix.util.PhoenixRuntime; +import org.apache.phoenix.util.QueryUtil; +import org.apache.phoenix.util.SchemaUtil; +import org.slf4j.Logger; +import org.slf4j.LoggerFactory; + +import com.google.common.annotations.VisibleForTesting; +import com.google.common.base.Preconditions; +import com.google.common.collect.Lists; + +/** + * An MR job to verify that the index table is in sync with the data table. + * + */ +public class IndexScrutinyTool extends Configured implements Tool { + +private static final Logger LOG = LoggerFactory.getLogger(IndexScrutinyTool.class); + +private static final Option SCHEMA_NAME_OPTION = +new Option("s", "schema", true, "Phoenix schema name (optional)"); +private static final Option DATA_TABLE_OPTION = +new Option("dt", "data-table", true, "Data table name (mandatory)"); +private static final Option INDEX_TABLE_OPTION = +new Option("it", "index-table", true, +"Index table name (mandatory)."); +private static final Option TIMESTAMP = +new Option("t", "time", true, +"Timestamp in millis used to compare the index and data tables. Defaults to current time minus 60 seconds"); + +private static final Option RUN_FOREGROUND_OPTION = +new Option("runfg", "run-foreground", false, "Applicable on top of -direct option." ++ "If specified, runs index scrutiny in Foreground. Default - Runs the build in background."); + +private static final Option SNAPSHOT_OPTION = //TODO check if this works +new Option("snap", "snapshot", false, +"If specified, uses Snapshots for async index