use of org.apache.hadoop.hive.ql.exec.ConditionalTask in project hive by apache.
the class GenMapRedUtils method createMRWorkForMergingFiles.
/**
* @param fsInput The FileSink operator.
* @param ctx The MR processing context.
* @param finalName the final destination path the merge job should output.
* @param dependencyTask
* @param mvTasks
* @param conf
* @param currTask
* @throws SemanticException
* create a Map-only merge job using CombineHiveInputFormat for all partitions with
* following operators:
* MR job J0:
* ...
* |
* v
* FileSinkOperator_1 (fsInput)
* |
* v
* Merge job J1:
* |
* v
* TableScan (using CombineHiveInputFormat) (tsMerge)
* |
* v
* FileSinkOperator (fsMerge)
*
* Here the pathToPartitionInfo & pathToAlias will remain the same, which means the paths
* do
* not contain the dynamic partitions (their parent). So after the dynamic partitions are
* created (after the first job finished before the moveTask or ConditionalTask start),
* we need to change the pathToPartitionInfo & pathToAlias to include the dynamic
* partition
* directories.
*
*/
public static void createMRWorkForMergingFiles(FileSinkOperator fsInput, Path finalName, DependencyCollectionTask dependencyTask, List<Task<MoveWork>> mvTasks, HiveConf conf, Task<? extends Serializable> currTask) throws SemanticException {
//
// 1. create the operator tree
//
FileSinkDesc fsInputDesc = fsInput.getConf();
// Create a TableScan operator
RowSchema inputRS = fsInput.getSchema();
TableScanOperator tsMerge = GenMapRedUtils.createTemporaryTableScanOperator(fsInput.getCompilationOpContext(), inputRS);
// Create a FileSink operator
TableDesc ts = (TableDesc) fsInputDesc.getTableInfo().clone();
FileSinkDesc fsOutputDesc = new FileSinkDesc(finalName, ts, conf.getBoolVar(ConfVars.COMPRESSRESULT));
FileSinkOperator fsOutput = (FileSinkOperator) OperatorFactory.getAndMakeChild(fsOutputDesc, inputRS, tsMerge);
// If the input FileSinkOperator is a dynamic partition enabled, the tsMerge input schema
// needs to include the partition column, and the fsOutput should have
// a DynamicPartitionCtx to indicate that it needs to dynamically partitioned.
DynamicPartitionCtx dpCtx = fsInputDesc.getDynPartCtx();
if (dpCtx != null && dpCtx.getNumDPCols() > 0) {
// adding DP ColumnInfo to the RowSchema signature
ArrayList<ColumnInfo> signature = inputRS.getSignature();
String tblAlias = fsInputDesc.getTableInfo().getTableName();
for (String dpCol : dpCtx.getDPColNames()) {
ColumnInfo colInfo = new ColumnInfo(dpCol, // all partition column type should be string
TypeInfoFactory.stringTypeInfo, tblAlias, // partition column is virtual column
true);
signature.add(colInfo);
}
inputRS.setSignature(signature);
// create another DynamicPartitionCtx, which has a different input-to-DP column mapping
DynamicPartitionCtx dpCtx2 = new DynamicPartitionCtx(dpCtx);
fsOutputDesc.setDynPartCtx(dpCtx2);
// update the FileSinkOperator to include partition columns
usePartitionColumns(fsInputDesc.getTableInfo().getProperties(), dpCtx.getDPColNames());
} else {
// non-partitioned table
fsInputDesc.getTableInfo().getProperties().remove(org.apache.hadoop.hive.metastore.api.hive_metastoreConstants.META_TABLE_PARTITION_COLUMNS);
}
//
// 2. Constructing a conditional task consisting of a move task and a map reduce task
//
MoveWork dummyMv = new MoveWork(null, null, null, new LoadFileDesc(fsInputDesc.getFinalDirName(), finalName, true, null, null), false);
MapWork cplan;
Serializable work;
if ((conf.getBoolVar(ConfVars.HIVEMERGERCFILEBLOCKLEVEL) && fsInputDesc.getTableInfo().getInputFileFormatClass().equals(RCFileInputFormat.class)) || (conf.getBoolVar(ConfVars.HIVEMERGEORCFILESTRIPELEVEL) && fsInputDesc.getTableInfo().getInputFileFormatClass().equals(OrcInputFormat.class))) {
cplan = GenMapRedUtils.createMergeTask(fsInputDesc, finalName, dpCtx != null && dpCtx.getNumDPCols() > 0, fsInput.getCompilationOpContext());
if (conf.getVar(ConfVars.HIVE_EXECUTION_ENGINE).equals("tez")) {
work = new TezWork(conf.getVar(HiveConf.ConfVars.HIVEQUERYID), conf);
cplan.setName("File Merge");
((TezWork) work).add(cplan);
} else if (conf.getVar(ConfVars.HIVE_EXECUTION_ENGINE).equals("spark")) {
work = new SparkWork(conf.getVar(HiveConf.ConfVars.HIVEQUERYID));
cplan.setName("Spark Merge File Work");
((SparkWork) work).add(cplan);
} else {
work = cplan;
}
} else {
cplan = createMRWorkForMergingFiles(conf, tsMerge, fsInputDesc);
if (conf.getVar(ConfVars.HIVE_EXECUTION_ENGINE).equals("tez")) {
work = new TezWork(conf.getVar(HiveConf.ConfVars.HIVEQUERYID), conf);
cplan.setName("File Merge");
((TezWork) work).add(cplan);
} else if (conf.getVar(ConfVars.HIVE_EXECUTION_ENGINE).equals("spark")) {
work = new SparkWork(conf.getVar(HiveConf.ConfVars.HIVEQUERYID));
cplan.setName("Spark Merge File Work");
((SparkWork) work).add(cplan);
} else {
work = new MapredWork();
((MapredWork) work).setMapWork(cplan);
}
}
// use CombineHiveInputFormat for map-only merging
cplan.setInputformat("org.apache.hadoop.hive.ql.io.CombineHiveInputFormat");
// NOTE: we should gather stats in MR1 rather than MR2 at merge job since we don't
// know if merge MR2 will be triggered at execution time
Task<MoveWork> mvTask = GenMapRedUtils.findMoveTask(mvTasks, fsOutput);
ConditionalTask cndTsk = GenMapRedUtils.createCondTask(conf, currTask, dummyMv, work, fsInputDesc.getFinalDirName(), finalName, mvTask, dependencyTask);
// keep the dynamic partition context in conditional task resolver context
ConditionalResolverMergeFilesCtx mrCtx = (ConditionalResolverMergeFilesCtx) cndTsk.getResolverCtx();
mrCtx.setDPCtx(fsInputDesc.getDynPartCtx());
mrCtx.setLbCtx(fsInputDesc.getLbCtx());
}
use of org.apache.hadoop.hive.ql.exec.ConditionalTask in project hive by apache.
the class CrossProductCheck method dispatch.
@Override
public Object dispatch(Node nd, Stack<Node> stack, Object... nodeOutputs) throws SemanticException {
@SuppressWarnings("unchecked") Task<? extends Serializable> currTask = (Task<? extends Serializable>) nd;
if (currTask instanceof MapRedTask) {
MapRedTask mrTsk = (MapRedTask) currTask;
MapredWork mrWrk = mrTsk.getWork();
checkMapJoins(mrTsk);
checkMRReducer(currTask.toString(), mrWrk);
} else if (currTask instanceof ConditionalTask) {
List<Task<? extends Serializable>> taskListInConditionalTask = ((ConditionalTask) currTask).getListTasks();
for (Task<? extends Serializable> tsk : taskListInConditionalTask) {
dispatch(tsk, stack, nodeOutputs);
}
} else if (currTask instanceof TezTask) {
TezTask tzTask = (TezTask) currTask;
TezWork tzWrk = tzTask.getWork();
checkMapJoins(tzWrk);
checkTezReducer(tzWrk);
}
return null;
}
use of org.apache.hadoop.hive.ql.exec.ConditionalTask in project hive by apache.
the class MapReduceCompiler method setInputFormat.
// loop over all the tasks recursively
@Override
protected void setInputFormat(Task<? extends Serializable> task) {
if (task instanceof ExecDriver) {
MapWork work = ((MapredWork) task.getWork()).getMapWork();
HashMap<String, Operator<? extends OperatorDesc>> opMap = work.getAliasToWork();
if (!opMap.isEmpty()) {
for (Operator<? extends OperatorDesc> op : opMap.values()) {
setInputFormat(work, op);
}
}
} else if (task instanceof ConditionalTask) {
List<Task<? extends Serializable>> listTasks = ((ConditionalTask) task).getListTasks();
for (Task<? extends Serializable> tsk : listTasks) {
setInputFormat(tsk);
}
}
if (task.getChildTasks() != null) {
for (Task<? extends Serializable> childTask : task.getChildTasks()) {
setInputFormat(childTask);
}
}
}
use of org.apache.hadoop.hive.ql.exec.ConditionalTask in project hive by apache.
the class TezCompiler method setInputFormat.
@Override
protected void setInputFormat(Task<? extends Serializable> task) {
if (task instanceof TezTask) {
TezWork work = ((TezTask) task).getWork();
List<BaseWork> all = work.getAllWork();
for (BaseWork w : all) {
if (w instanceof MapWork) {
MapWork mapWork = (MapWork) w;
HashMap<String, Operator<? extends OperatorDesc>> opMap = mapWork.getAliasToWork();
if (!opMap.isEmpty()) {
for (Operator<? extends OperatorDesc> op : opMap.values()) {
setInputFormat(mapWork, op);
}
}
}
}
} else if (task instanceof ConditionalTask) {
List<Task<? extends Serializable>> listTasks = ((ConditionalTask) task).getListTasks();
for (Task<? extends Serializable> tsk : listTasks) {
setInputFormat(tsk);
}
}
if (task.getChildTasks() != null) {
for (Task<? extends Serializable> childTask : task.getChildTasks()) {
setInputFormat(childTask);
}
}
}
use of org.apache.hadoop.hive.ql.exec.ConditionalTask in project hive by apache.
the class GenMRSkewJoinProcessor method processSkewJoin.
/**
* Create tasks for processing skew joins. The idea is (HIVE-964) to use
* separated jobs and map-joins to handle skew joins.
* <p>
* <ul>
* <li>
* Number of mr jobs to handle skew keys is the number of table minus 1 (we
* can stream the last table, so big keys in the last table will not be a
* problem).
* <li>
* At runtime in Join, we output big keys in one table into one corresponding
* directories, and all same keys in other tables into different dirs(one for
* each table). The directories will look like:
* <ul>
* <li>
* dir-T1-bigkeys(containing big keys in T1), dir-T2-keys(containing keys
* which is big in T1),dir-T3-keys(containing keys which is big in T1), ...
* <li>
* dir-T1-keys(containing keys which is big in T2), dir-T2-bigkeys(containing
* big keys in T2),dir-T3-keys(containing keys which is big in T2), ...
* <li>
* dir-T1-keys(containing keys which is big in T3), dir-T2-keys(containing big
* keys in T3),dir-T3-bigkeys(containing keys which is big in T3), ... .....
* </ul>
* </ul>
* For each table, we launch one mapjoin job, taking the directory containing
* big keys in this table and corresponding dirs in other tables as input.
* (Actally one job for one row in the above.)
*
* <p>
* For more discussions, please check
* https://issues.apache.org/jira/browse/HIVE-964.
*/
@SuppressWarnings("unchecked")
public static void processSkewJoin(JoinOperator joinOp, Task<? extends Serializable> currTask, ParseContext parseCtx) throws SemanticException {
// now does not work with outer joins
if (!GenMRSkewJoinProcessor.skewJoinEnabled(parseCtx.getConf(), joinOp)) {
return;
}
List<Task<? extends Serializable>> children = currTask.getChildTasks();
Path baseTmpDir = parseCtx.getContext().getMRTmpPath();
JoinDesc joinDescriptor = joinOp.getConf();
Map<Byte, List<ExprNodeDesc>> joinValues = joinDescriptor.getExprs();
int numAliases = joinValues.size();
Map<Byte, Path> bigKeysDirMap = new HashMap<Byte, Path>();
Map<Byte, Map<Byte, Path>> smallKeysDirMap = new HashMap<Byte, Map<Byte, Path>>();
Map<Byte, Path> skewJoinJobResultsDir = new HashMap<Byte, Path>();
Byte[] tags = joinDescriptor.getTagOrder();
for (int i = 0; i < numAliases; i++) {
Byte alias = tags[i];
bigKeysDirMap.put(alias, getBigKeysDir(baseTmpDir, alias));
Map<Byte, Path> smallKeysMap = new HashMap<Byte, Path>();
smallKeysDirMap.put(alias, smallKeysMap);
for (Byte src2 : tags) {
if (!src2.equals(alias)) {
smallKeysMap.put(src2, getSmallKeysDir(baseTmpDir, alias, src2));
}
}
skewJoinJobResultsDir.put(alias, getBigKeysSkewJoinResultDir(baseTmpDir, alias));
}
joinDescriptor.setHandleSkewJoin(true);
joinDescriptor.setBigKeysDirMap(bigKeysDirMap);
joinDescriptor.setSmallKeysDirMap(smallKeysDirMap);
joinDescriptor.setSkewKeyDefinition(HiveConf.getIntVar(parseCtx.getConf(), HiveConf.ConfVars.HIVESKEWJOINKEY));
HashMap<Path, Task<? extends Serializable>> bigKeysDirToTaskMap = new HashMap<Path, Task<? extends Serializable>>();
List<Serializable> listWorks = new ArrayList<Serializable>();
List<Task<? extends Serializable>> listTasks = new ArrayList<Task<? extends Serializable>>();
MapredWork currPlan = (MapredWork) currTask.getWork();
TableDesc keyTblDesc = (TableDesc) currPlan.getReduceWork().getKeyDesc().clone();
List<String> joinKeys = Utilities.getColumnNames(keyTblDesc.getProperties());
List<String> joinKeyTypes = Utilities.getColumnTypes(keyTblDesc.getProperties());
Map<Byte, TableDesc> tableDescList = new HashMap<Byte, TableDesc>();
Map<Byte, RowSchema> rowSchemaList = new HashMap<Byte, RowSchema>();
Map<Byte, List<ExprNodeDesc>> newJoinValues = new HashMap<Byte, List<ExprNodeDesc>>();
Map<Byte, List<ExprNodeDesc>> newJoinKeys = new HashMap<Byte, List<ExprNodeDesc>>();
// used for create mapJoinDesc, should be in order
List<TableDesc> newJoinValueTblDesc = new ArrayList<TableDesc>();
for (Byte tag : tags) {
newJoinValueTblDesc.add(null);
}
for (int i = 0; i < numAliases; i++) {
Byte alias = tags[i];
List<ExprNodeDesc> valueCols = joinValues.get(alias);
String colNames = "";
String colTypes = "";
int columnSize = valueCols.size();
List<ExprNodeDesc> newValueExpr = new ArrayList<ExprNodeDesc>();
List<ExprNodeDesc> newKeyExpr = new ArrayList<ExprNodeDesc>();
ArrayList<ColumnInfo> columnInfos = new ArrayList<ColumnInfo>();
boolean first = true;
for (int k = 0; k < columnSize; k++) {
TypeInfo type = valueCols.get(k).getTypeInfo();
// any name, it does not matter.
String newColName = i + "_VALUE_" + k;
ColumnInfo columnInfo = new ColumnInfo(newColName, type, alias.toString(), false);
columnInfos.add(columnInfo);
newValueExpr.add(new ExprNodeColumnDesc(columnInfo));
if (!first) {
colNames = colNames + ",";
colTypes = colTypes + ",";
}
first = false;
colNames = colNames + newColName;
colTypes = colTypes + valueCols.get(k).getTypeString();
}
// we are putting join keys at last part of the spilled table
for (int k = 0; k < joinKeys.size(); k++) {
if (!first) {
colNames = colNames + ",";
colTypes = colTypes + ",";
}
first = false;
colNames = colNames + joinKeys.get(k);
colTypes = colTypes + joinKeyTypes.get(k);
ColumnInfo columnInfo = new ColumnInfo(joinKeys.get(k), TypeInfoFactory.getPrimitiveTypeInfo(joinKeyTypes.get(k)), alias.toString(), false);
columnInfos.add(columnInfo);
newKeyExpr.add(new ExprNodeColumnDesc(columnInfo));
}
newJoinValues.put(alias, newValueExpr);
newJoinKeys.put(alias, newKeyExpr);
tableDescList.put(alias, Utilities.getTableDesc(colNames, colTypes));
rowSchemaList.put(alias, new RowSchema(columnInfos));
// construct value table Desc
String valueColNames = "";
String valueColTypes = "";
first = true;
for (int k = 0; k < columnSize; k++) {
// any name, it does not matter.
String newColName = i + "_VALUE_" + k;
if (!first) {
valueColNames = valueColNames + ",";
valueColTypes = valueColTypes + ",";
}
valueColNames = valueColNames + newColName;
valueColTypes = valueColTypes + valueCols.get(k).getTypeString();
first = false;
}
newJoinValueTblDesc.set(Byte.valueOf((byte) i), Utilities.getTableDesc(valueColNames, valueColTypes));
}
joinDescriptor.setSkewKeysValuesTables(tableDescList);
joinDescriptor.setKeyTableDesc(keyTblDesc);
for (int i = 0; i < numAliases - 1; i++) {
Byte src = tags[i];
MapWork newPlan = PlanUtils.getMapRedWork().getMapWork();
// This code has been only added for testing
boolean mapperCannotSpanPartns = parseCtx.getConf().getBoolVar(HiveConf.ConfVars.HIVE_MAPPER_CANNOT_SPAN_MULTIPLE_PARTITIONS);
newPlan.setMapperCannotSpanPartns(mapperCannotSpanPartns);
MapredWork clonePlan = SerializationUtilities.clonePlan(currPlan);
Operator<? extends OperatorDesc>[] parentOps = new TableScanOperator[tags.length];
for (int k = 0; k < tags.length; k++) {
Operator<? extends OperatorDesc> ts = GenMapRedUtils.createTemporaryTableScanOperator(joinOp.getCompilationOpContext(), rowSchemaList.get((byte) k));
((TableScanOperator) ts).setTableDescSkewJoin(tableDescList.get((byte) k));
parentOps[k] = ts;
}
Operator<? extends OperatorDesc> tblScan_op = parentOps[i];
ArrayList<String> aliases = new ArrayList<String>();
String alias = src.toString().intern();
aliases.add(alias);
Path bigKeyDirPath = bigKeysDirMap.get(src);
newPlan.addPathToAlias(bigKeyDirPath, aliases);
newPlan.getAliasToWork().put(alias, tblScan_op);
PartitionDesc part = new PartitionDesc(tableDescList.get(src), null);
newPlan.addPathToPartitionInfo(bigKeyDirPath, part);
newPlan.getAliasToPartnInfo().put(alias, part);
Operator<? extends OperatorDesc> reducer = clonePlan.getReduceWork().getReducer();
assert reducer instanceof JoinOperator;
JoinOperator cloneJoinOp = (JoinOperator) reducer;
String dumpFilePrefix = "mapfile" + PlanUtils.getCountForMapJoinDumpFilePrefix();
MapJoinDesc mapJoinDescriptor = new MapJoinDesc(newJoinKeys, keyTblDesc, newJoinValues, newJoinValueTblDesc, newJoinValueTblDesc, joinDescriptor.getOutputColumnNames(), i, joinDescriptor.getConds(), joinDescriptor.getFilters(), joinDescriptor.getNoOuterJoin(), dumpFilePrefix, joinDescriptor.getMemoryMonitorInfo(), joinDescriptor.getInMemoryDataSize());
mapJoinDescriptor.setTagOrder(tags);
mapJoinDescriptor.setHandleSkewJoin(false);
mapJoinDescriptor.setNullSafes(joinDescriptor.getNullSafes());
mapJoinDescriptor.setColumnExprMap(joinDescriptor.getColumnExprMap());
MapredLocalWork localPlan = new MapredLocalWork(new LinkedHashMap<String, Operator<? extends OperatorDesc>>(), new LinkedHashMap<String, FetchWork>());
Map<Byte, Path> smallTblDirs = smallKeysDirMap.get(src);
for (int j = 0; j < numAliases; j++) {
if (j == i) {
continue;
}
Byte small_alias = tags[j];
Operator<? extends OperatorDesc> tblScan_op2 = parentOps[j];
localPlan.getAliasToWork().put(small_alias.toString(), tblScan_op2);
Path tblDir = smallTblDirs.get(small_alias);
localPlan.getAliasToFetchWork().put(small_alias.toString(), new FetchWork(tblDir, tableDescList.get(small_alias)));
}
newPlan.setMapRedLocalWork(localPlan);
// construct a map join and set it as the child operator of tblScan_op
MapJoinOperator mapJoinOp = (MapJoinOperator) OperatorFactory.getAndMakeChild(joinOp.getCompilationOpContext(), mapJoinDescriptor, (RowSchema) null, parentOps);
// change the children of the original join operator to point to the map
// join operator
List<Operator<? extends OperatorDesc>> childOps = cloneJoinOp.getChildOperators();
for (Operator<? extends OperatorDesc> childOp : childOps) {
childOp.replaceParent(cloneJoinOp, mapJoinOp);
}
mapJoinOp.setChildOperators(childOps);
HiveConf jc = new HiveConf(parseCtx.getConf(), GenMRSkewJoinProcessor.class);
newPlan.setNumMapTasks(HiveConf.getIntVar(jc, HiveConf.ConfVars.HIVESKEWJOINMAPJOINNUMMAPTASK));
newPlan.setMinSplitSize(HiveConf.getLongVar(jc, HiveConf.ConfVars.HIVESKEWJOINMAPJOINMINSPLIT));
newPlan.setInputformat(HiveInputFormat.class.getName());
MapredWork w = new MapredWork();
w.setMapWork(newPlan);
Task<? extends Serializable> skewJoinMapJoinTask = TaskFactory.get(w);
skewJoinMapJoinTask.setFetchSource(currTask.isFetchSource());
bigKeysDirToTaskMap.put(bigKeyDirPath, skewJoinMapJoinTask);
listWorks.add(skewJoinMapJoinTask.getWork());
listTasks.add(skewJoinMapJoinTask);
}
if (children != null) {
for (Task<? extends Serializable> tsk : listTasks) {
for (Task<? extends Serializable> oldChild : children) {
tsk.addDependentTask(oldChild);
}
}
currTask.setChildTasks(new ArrayList<Task<? extends Serializable>>());
for (Task<? extends Serializable> oldChild : children) {
oldChild.getParentTasks().remove(currTask);
}
listTasks.addAll(children);
}
ConditionalResolverSkewJoinCtx context = new ConditionalResolverSkewJoinCtx(bigKeysDirToTaskMap, children);
ConditionalWork cndWork = new ConditionalWork(listWorks);
ConditionalTask cndTsk = (ConditionalTask) TaskFactory.get(cndWork);
cndTsk.setListTasks(listTasks);
cndTsk.setResolver(new ConditionalResolverSkewJoin());
cndTsk.setResolverCtx(context);
currTask.setChildTasks(new ArrayList<Task<? extends Serializable>>());
currTask.addDependentTask(cndTsk);
return;
}
Aggregations