Logical tables MSE test #17697
There are no files selected for viewing
This file contains hidden or bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
| Original file line number | Diff line number | Diff line change | ||||||
|---|---|---|---|---|---|---|---|---|
|
|
@@ -32,6 +32,7 @@ | |||||||
| import java.util.Arrays; | ||||||||
| import java.util.Collections; | ||||||||
| import java.util.HashMap; | ||||||||
| import java.util.Iterator; | ||||||||
| import java.util.List; | ||||||||
| import java.util.Map; | ||||||||
| import java.util.Properties; | ||||||||
|
|
@@ -48,6 +49,7 @@ | |||||||
| import org.apache.pinot.common.restlet.resources.ValidDocIdsType; | ||||||||
| import org.apache.pinot.common.utils.TarCompressionUtils; | ||||||||
| import org.apache.pinot.common.utils.config.TagNameUtils; | ||||||||
| import org.apache.pinot.controller.helix.ControllerTest; | ||||||||
| import org.apache.pinot.plugin.inputformat.csv.CSVMessageDecoder; | ||||||||
| import org.apache.pinot.plugin.stream.kafka.KafkaStreamConfigProperties; | ||||||||
| import org.apache.pinot.server.starter.helix.BaseServerStarter; | ||||||||
|
|
@@ -334,9 +336,16 @@ protected TableConfig createTableConfig(File tableConfigFile) | |||||||
| * Creates a new OFFLINE table config. | ||||||||
| */ | ||||||||
| protected TableConfig createOfflineTableConfig() { | ||||||||
| return createOfflineTableConfig(getTableName()); | ||||||||
| } | ||||||||
|
|
||||||||
| /** | ||||||||
| * Creates a new OFFLINE table config. | ||||||||
| */ | ||||||||
| protected TableConfig createOfflineTableConfig(String tableName) { | ||||||||
| // @formatter:off | ||||||||
| return new TableConfigBuilder(TableType.OFFLINE) | ||||||||
| .setTableName(tableName) | ||||||||
| .setTimeColumnName(getTimeColumnName()) | ||||||||
| .setSortedColumn(getSortedColumn()) | ||||||||
| .setInvertedIndexColumns(getInvertedIndexColumns()) | ||||||||
|
|
@@ -406,26 +415,71 @@ protected TableConfig createRealtimeTableConfig(File sampleAvroFile) { | |||||||
| return getTableConfigBuilder(TableType.REALTIME).build(); | ||||||||
| } | ||||||||
|
|
||||||||
| private List<String> getTimeBoundaryTable(List<String> offlineTables) { | ||||||||
| String timeBoundaryTable = null; | ||||||||
| long maxEndTimeMillis = Long.MIN_VALUE; | ||||||||
| try { | ||||||||
| for (String tableName : offlineTables) { | ||||||||
| String url = _controllerRequestURLBuilder.forSegmentMetadata(tableName, TableType.OFFLINE); | ||||||||
| String response = ControllerTest.sendGetRequest(url); | ||||||||
| JsonNode jsonNode = JsonUtils.stringToJsonNode(response); | ||||||||
| Iterator<String> stringIterator = jsonNode.fieldNames(); | ||||||||
| while (stringIterator.hasNext()) { | ||||||||
| String segmentName = stringIterator.next(); | ||||||||
| JsonNode segmentJsonNode = jsonNode.get(segmentName); | ||||||||
| long endTimeMillis = segmentJsonNode.get("endTimeMillis").asLong(); | ||||||||
| if (endTimeMillis > maxEndTimeMillis) { | ||||||||
| maxEndTimeMillis = endTimeMillis; | ||||||||
| timeBoundaryTable = tableName; | ||||||||
| } | ||||||||
| } | ||||||||
| } | ||||||||
| } catch (IOException e) { | ||||||||
| throw new RuntimeException("Failed to get the time boundary table", e); | ||||||||
| } | ||||||||
| return timeBoundaryTable != null ? List.of(TableNameBuilder.OFFLINE.tableNameWithType(timeBoundaryTable)) | ||||||||
| : List.of(); | ||||||||
|
Comment on lines
+440
to
+441
There was a problem hiding this comment.
Suggested change
|
||||||||
| } | ||||||||
|
|
||||||||
| protected LogicalTableConfig createLogicalTableConfig(List<String> offlineTables, List<String> realtimeTables) { | ||||||||
| Map<String, PhysicalTableConfig> physicalTableConfigMap = new HashMap<>(); | ||||||||
| for (String physicalTableName : offlineTables) { | ||||||||
| physicalTableConfigMap.put(physicalTableName, new PhysicalTableConfig()); | ||||||||
| } | ||||||||
| for (String physicalTableName : realtimeTables) { | ||||||||
| physicalTableConfigMap.put(physicalTableName, new PhysicalTableConfig()); | ||||||||
| } | ||||||||
| String offlineTableName = offlineTables.stream().findFirst().orElse(null); | ||||||||
| String realtimeTableName = realtimeTables.stream().findFirst().orElse(null); | ||||||||
| LogicalTableConfigBuilder builder = | ||||||||
| new LogicalTableConfigBuilder().setTableName(getLogicalTableName()) | ||||||||
| .setBrokerTenant(getBrokerTenant()) | ||||||||
| .setRefOfflineTableName(offlineTableName) | ||||||||
| .setRefRealtimeTableName(realtimeTableName) | ||||||||
| .setPhysicalTableConfigMap(physicalTableConfigMap); | ||||||||
| if (!offlineTables.isEmpty() && !realtimeTables.isEmpty()) { | ||||||||
| builder.setTimeBoundaryConfig( | ||||||||
| new TimeBoundaryConfig("min", Map.of("includedTables", getTimeBoundaryTable(offlineTables))) | ||||||||
| ); | ||||||||
| } | ||||||||
| return builder.build(); | ||||||||
| } | ||||||||
|
|
||||||||
| /** | ||||||||
| * Creates a LogicalTableConfig backed by the OFFLINE and REALTIME physical tables. | ||||||||
| */ | ||||||||
| protected LogicalTableConfig createLogicalTableConfig() { | ||||||||
| String offlineTableName = TableNameBuilder.OFFLINE.tableNameWithType(getTableName()); | ||||||||
| String realtimeTableName = TableNameBuilder.REALTIME.tableNameWithType(getTableName()); | ||||||||
| return createLogicalTableConfig(List.of(offlineTableName), List.of(realtimeTableName)); | ||||||||
| } | ||||||||
|
|
||||||||
| protected void createLogicalTableAndSchema() | ||||||||
| throws IOException { | ||||||||
| Schema schema = createSchema(getSchemaFileName()); | ||||||||
| schema.setSchemaName(getTableName()); | ||||||||
|
There was a problem hiding this comment.
Suggested change
|
||||||||
| addSchema(schema); | ||||||||
| createLogicalTable(); | ||||||||
| } | ||||||||
|
|
||||||||
| /** | ||||||||
|
|
@@ -673,6 +727,50 @@ protected List<File> unpackAvroData(File outputDir) | |||||||
| return unpackTarData(getAvroTarFileName(), outputDir); | ||||||||
| } | ||||||||
|
|
||||||||
| protected void uploadDataToOfflineTables(List<String> tableNames, List<File> avroFiles) | ||||||||
| throws Exception { | ||||||||
| Map<String, List<File>> offlineTableDataFiles = distributeFilesToTables(tableNames, avroFiles); | ||||||||
| for (Map.Entry<String, List<File>> entry : offlineTableDataFiles.entrySet()) { | ||||||||
| String tableName = entry.getKey(); | ||||||||
| List<File> avroFilesForTable = entry.getValue(); | ||||||||
|
|
||||||||
| File tarDir = new File(_tarDir, tableName); | ||||||||
|
|
||||||||
| TestUtils.ensureDirectoriesExistAndEmpty(tarDir); | ||||||||
|
|
||||||||
| // Create and upload the schema and table config | ||||||||
| Schema schema = createSchema(getSchemaFileName()); | ||||||||
| schema.setSchemaName(tableName); | ||||||||
| addSchema(schema); | ||||||||
| TableConfig offlineTableConfig = createOfflineTableConfig(tableName); | ||||||||
| addTableConfig(offlineTableConfig); | ||||||||
|
|
||||||||
| // Create and upload segments | ||||||||
| ClusterIntegrationTestUtils.buildSegmentsFromAvro(avroFilesForTable, offlineTableConfig, schema, 0, _segmentDir, | ||||||||
| tarDir); | ||||||||
| uploadSegments(tableName, tarDir); | ||||||||
| } | ||||||||
| } | ||||||||
|
|
||||||||
| // Distributes the given Avro files to the given table names in a round-robin manner and | ||||||||
| // returns the mapping from table name to list of Avro files. | ||||||||
| protected Map<String, List<File>> distributeFilesToTables(List<String> tableNames, List<File> avroFiles) { | ||||||||
| if (tableNames.isEmpty()) { | ||||||||
| return Map.of(); | ||||||||
| } | ||||||||
| Map<String, List<File>> tableNameToFilesMap = new HashMap<>(); | ||||||||
|
|
||||||||
| // Initialize the map with empty lists for each table name | ||||||||
| tableNames.forEach(table -> tableNameToFilesMap.put(table, new ArrayList<>())); | ||||||||
|
|
||||||||
| // Round-robin distribution of files to table names | ||||||||
| for (int i = 0; i < avroFiles.size(); i++) { | ||||||||
| String tableName = tableNames.get(i % tableNames.size()); | ||||||||
| tableNameToFilesMap.get(tableName).add(avroFiles.get(i)); | ||||||||
| } | ||||||||
| return tableNameToFilesMap; | ||||||||
| } | ||||||||
|
|
||||||||
| /** | ||||||||
| * Unpack the tarred data into the given directory. | ||||||||
| * | ||||||||
|
|
||||||||
This file contains hidden or bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
This file contains hidden or bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
Oops, something went wrong.
Oops, something went wrong.
Add this suggestion to a batch that can be applied as a single commit.
This suggestion is invalid because no changes were made to the code.
Suggestions cannot be applied while the pull request is closed.
Suggestions cannot be applied while viewing a subset of changes.
Only one suggestion per line can be applied in a batch.
Add this suggestion to a batch that can be applied as a single commit.
Applying suggestions on deleted lines is not supported.
You must change the existing code in this line in order to create a valid suggestion.
Outdated suggestions cannot be applied.
This suggestion has been applied or marked resolved.
Suggestions cannot be applied from pending reviews.
Suggestions cannot be applied on multi-line comments.
Suggestions cannot be applied while the pull request is queued to merge.
Suggestion cannot be applied right now. Please check back later.
There was a problem hiding this comment.
Choose a reason for hiding this comment
The reason will be displayed to describe this comment to others. Learn more.
These methods are moved from BaseLogicalTableIntegrationTest to this class so that LogicalTableMultiStageEngineIntegrationTest can also leverage them