use of org.apache.hadoop.hive.ql.plan.PartitionDesc in project hive by apache.
the class CombineHiveInputFormat method getCombineSplits.
/**
* Create Hive splits based on CombineFileSplit.
*/
private InputSplit[] getCombineSplits(JobConf job, int numSplits, Map<Path, PartitionDesc> pathToPartitionInfo) throws IOException {
init(job);
Map<Path, ArrayList<String>> pathToAliases = mrwork.getPathToAliases();
Map<String, Operator<? extends OperatorDesc>> aliasToWork = mrwork.getAliasToWork();
CombineFileInputFormatShim combine = ShimLoader.getHadoopShims().getCombineFileInputFormat();
InputSplit[] splits = null;
if (combine == null) {
splits = super.getSplits(job, numSplits);
return splits;
}
if (combine.getInputPathsShim(job).length == 0) {
throw new IOException("No input paths specified in job");
}
ArrayList<InputSplit> result = new ArrayList<InputSplit>();
// combine splits only from same tables and same partitions. Do not combine splits from multiple
// tables or multiple partitions.
Path[] paths = StringInternUtils.internUriStringsInPathArray(combine.getInputPathsShim(job));
List<Path> inpDirs = new ArrayList<Path>();
List<Path> inpFiles = new ArrayList<Path>();
Map<CombinePathInputFormat, CombineFilter> poolMap = new HashMap<CombinePathInputFormat, CombineFilter>();
Set<Path> poolSet = new HashSet<Path>();
for (Path path : paths) {
PartitionDesc part = HiveFileFormatUtils.getPartitionDescFromPathRecursively(pathToPartitionInfo, path, IOPrepareCache.get().allocatePartitionDescMap());
TableDesc tableDesc = part.getTableDesc();
if ((tableDesc != null) && tableDesc.isNonNative()) {
return super.getSplits(job, numSplits);
}
// Use HiveInputFormat if any of the paths is not splittable
Class inputFormatClass = part.getInputFileFormatClass();
String inputFormatClassName = inputFormatClass.getName();
InputFormat inputFormat = getInputFormatFromCache(inputFormatClass, job);
String deserializerClassName = null;
try {
deserializerClassName = part.getDeserializer(job).getClass().getName();
} catch (Exception e) {
// ignore
}
FileSystem inpFs = path.getFileSystem(job);
//don't combine if inputformat is a SymlinkTextInputFormat
if (inputFormat instanceof SymlinkTextInputFormat) {
splits = super.getSplits(job, numSplits);
return splits;
}
Path filterPath = path;
// Does a pool exist for this path already
CombineFilter f = null;
List<Operator<? extends OperatorDesc>> opList = null;
if (!mrwork.isMapperCannotSpanPartns()) {
//if mapper can span partitions, make sure a splits does not contain multiple
// opList + inputFormatClassName + deserializerClassName combination
// This is done using the Map of CombinePathInputFormat to PathFilter
opList = HiveFileFormatUtils.doGetWorksFromPath(pathToAliases, aliasToWork, filterPath);
CombinePathInputFormat combinePathInputFormat = new CombinePathInputFormat(opList, inputFormatClassName, deserializerClassName);
f = poolMap.get(combinePathInputFormat);
if (f == null) {
f = new CombineFilter(filterPath);
LOG.info("CombineHiveInputSplit creating pool for " + path + "; using filter path " + filterPath);
combine.createPool(job, f);
poolMap.put(combinePathInputFormat, f);
} else {
LOG.info("CombineHiveInputSplit: pool is already created for " + path + "; using filter path " + filterPath);
f.addPath(filterPath);
}
} else {
// but won't cross multiple partitions if the user has asked so.
if (!path.getFileSystem(job).getFileStatus(path).isDir()) {
// path is not directory
filterPath = path.getParent();
inpFiles.add(path);
poolSet.add(filterPath);
} else {
inpDirs.add(path);
}
}
}
// Processing directories
List<CombineFileSplit> iss = new ArrayList<CombineFileSplit>();
if (!mrwork.isMapperCannotSpanPartns()) {
//mapper can span partitions
//combine into as few as one split, subject to the PathFilters set
// using combine.createPool.
iss = Arrays.asList(combine.getSplits(job, 1));
} else {
for (Path path : inpDirs) {
processPaths(job, combine, iss, path);
}
if (inpFiles.size() > 0) {
// Processing files
for (Path filterPath : poolSet) {
combine.createPool(job, new CombineFilter(filterPath));
}
processPaths(job, combine, iss, inpFiles.toArray(new Path[0]));
}
}
if (mrwork.getNameToSplitSample() != null && !mrwork.getNameToSplitSample().isEmpty()) {
iss = sampleSplits(iss);
}
for (CombineFileSplit is : iss) {
CombineHiveInputSplit csplit = new CombineHiveInputSplit(job, is, pathToPartitionInfo);
result.add(csplit);
}
LOG.info("number of splits " + result.size());
return result.toArray(new CombineHiveInputSplit[result.size()]);
}
use of org.apache.hadoop.hive.ql.plan.PartitionDesc in project hive by apache.
the class GenMapRedUtils method getMapRedWorkFromConf.
/**
* create a new plan and return. The pan won't contain the name to split
* sample information in parse context.
*
* @return the new plan
*/
public static MapredWork getMapRedWorkFromConf(HiveConf conf) {
MapredWork mrWork = new MapredWork();
MapWork work = mrWork.getMapWork();
boolean mapperCannotSpanPartns = conf.getBoolVar(HiveConf.ConfVars.HIVE_MAPPER_CANNOT_SPAN_MULTIPLE_PARTITIONS);
work.setMapperCannotSpanPartns(mapperCannotSpanPartns);
work.setPathToAliases(new LinkedHashMap<Path, ArrayList<String>>());
work.setPathToPartitionInfo(new LinkedHashMap<Path, PartitionDesc>());
work.setAliasToWork(new LinkedHashMap<String, Operator<? extends OperatorDesc>>());
return mrWork;
}
use of org.apache.hadoop.hive.ql.plan.PartitionDesc 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).setTableDesc(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);
mapJoinDescriptor.setTagOrder(tags);
mapJoinDescriptor.setHandleSkewJoin(false);
mapJoinDescriptor.setNullSafes(joinDescriptor.getNullSafes());
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, jc);
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, parseCtx.getConf());
cndTsk.setListTasks(listTasks);
cndTsk.setResolver(new ConditionalResolverSkewJoin());
cndTsk.setResolverCtx(context);
currTask.setChildTasks(new ArrayList<Task<? extends Serializable>>());
currTask.addDependentTask(cndTsk);
return;
}
use of org.apache.hadoop.hive.ql.plan.PartitionDesc in project hive by apache.
the class SortMergeJoinTaskDispatcher method genSMBJoinWork.
// Convert the work in the SMB plan to a regular join
// Note that the operator tree is not fixed, only the path/alias mappings in the
// plan are fixed. The operator tree will still contain the SMBJoinOperator
private void genSMBJoinWork(MapWork currWork, SMBMapJoinOperator smbJoinOp) {
// Remove the paths which are not part of aliasToPartitionInfo
Map<String, PartitionDesc> aliasToPartitionInfo = currWork.getAliasToPartnInfo();
List<Path> removePaths = new ArrayList<>();
for (Map.Entry<Path, ArrayList<String>> entry : currWork.getPathToAliases().entrySet()) {
boolean keepPath = false;
for (String alias : entry.getValue()) {
if (aliasToPartitionInfo.containsKey(alias)) {
keepPath = true;
break;
}
}
// Remove if the path is not present
if (!keepPath) {
removePaths.add(entry.getKey());
}
}
List<String> removeAliases = new ArrayList<String>();
for (Path removePath : removePaths) {
removeAliases.addAll(currWork.getPathToAliases().get(removePath));
currWork.removePathToAlias(removePath);
currWork.removePathToPartitionInfo(removePath);
}
for (String alias : removeAliases) {
currWork.getAliasToPartnInfo().remove(alias);
currWork.getAliasToWork().remove(alias);
}
// Get the MapredLocalWork
MapredLocalWork localWork = smbJoinOp.getConf().getLocalWork();
for (Map.Entry<String, Operator<? extends OperatorDesc>> entry : localWork.getAliasToWork().entrySet()) {
String alias = entry.getKey();
Operator<? extends OperatorDesc> op = entry.getValue();
FetchWork fetchWork = localWork.getAliasToFetchWork().get(alias);
// Add the entry in mapredwork
currWork.getAliasToWork().put(alias, op);
PartitionDesc partitionInfo = currWork.getAliasToPartnInfo().get(alias);
if (fetchWork.getTblDir() != null) {
currWork.mergeAliasedInput(alias, fetchWork.getTblDir(), partitionInfo);
} else {
for (Path pathDir : fetchWork.getPartDir()) {
currWork.mergeAliasedInput(alias, pathDir, partitionInfo);
}
}
}
// Remove the dummy store operator from the tree
for (Operator<? extends OperatorDesc> parentOp : smbJoinOp.getParentOperators()) {
if (parentOp instanceof DummyStoreOperator) {
Operator<? extends OperatorDesc> grandParentOp = parentOp.getParentOperators().get(0);
smbJoinOp.replaceParent(parentOp, grandParentOp);
grandParentOp.setChildOperators(parentOp.getChildOperators());
parentOp.setParentOperators(null);
parentOp.setParentOperators(null);
}
}
}
use of org.apache.hadoop.hive.ql.plan.PartitionDesc in project hive by apache.
the class VectorDeserializeOrcWriter method create.
// TODO: if more writers are added, separate out an EncodingWriterFactory
public static EncodingWriter create(InputFormat<?, ?> sourceIf, Deserializer serDe, Map<Path, PartitionDesc> parts, Configuration daemonConf, Configuration jobConf, Path splitPath, StructObjectInspector sourceOi, List<Integer> sourceIncludes, boolean[] cacheIncludes, int allocSize) throws IOException {
// Vector SerDe can be disabled both on client and server side.
if (!HiveConf.getBoolVar(daemonConf, ConfVars.LLAP_IO_ENCODE_VECTOR_SERDE_ENABLED) || !HiveConf.getBoolVar(jobConf, ConfVars.LLAP_IO_ENCODE_VECTOR_SERDE_ENABLED) || !(sourceIf instanceof TextInputFormat) || !(serDe instanceof LazySimpleSerDe)) {
return new DeserializerOrcWriter(serDe, sourceOi, allocSize);
}
Path path = splitPath.getFileSystem(daemonConf).makeQualified(splitPath);
PartitionDesc partDesc = HiveFileFormatUtils.getPartitionDescFromPathRecursively(parts, path, null);
if (partDesc == null) {
LlapIoImpl.LOG.info("Not using VertorDeserializeOrcWriter: no partition desc for " + path);
return new DeserializerOrcWriter(serDe, sourceOi, allocSize);
}
Properties tblProps = partDesc.getTableDesc().getProperties();
if ("true".equalsIgnoreCase(tblProps.getProperty(serdeConstants.SERIALIZATION_LAST_COLUMN_TAKES_REST))) {
LlapIoImpl.LOG.info("Not using VertorDeserializeOrcWriter due to " + serdeConstants.SERIALIZATION_LAST_COLUMN_TAKES_REST);
return new DeserializerOrcWriter(serDe, sourceOi, allocSize);
}
for (StructField sf : sourceOi.getAllStructFieldRefs()) {
Category c = sf.getFieldObjectInspector().getCategory();
if (c != Category.PRIMITIVE) {
LlapIoImpl.LOG.info("Not using VertorDeserializeOrcWriter: " + c + " is not supported");
return new DeserializerOrcWriter(serDe, sourceOi, allocSize);
}
}
LlapIoImpl.LOG.info("Creating VertorDeserializeOrcWriter for " + path);
return new VectorDeserializeOrcWriter(daemonConf, tblProps, sourceOi, sourceIncludes, cacheIncludes, allocSize);
}
Aggregations