Impala
Impalaistheopensource,nativeanalyticdatabaseforApacheHadoop.
 All Classes Namespaces Files Functions Variables Typedefs Enumerations Enumerator Friends Macros
impala::UnionNode Class Reference

#include <union-node.h>

Inheritance diagram for impala::UnionNode:
Collaboration diagram for impala::UnionNode:

Public Member Functions

 UnionNode (ObjectPool *pool, const TPlanNode &tnode, const DescriptorTbl &descs)
 
virtual Status Init (const TPlanNode &tnode)
 
virtual Status Prepare (RuntimeState *state)
 
virtual Status Open (RuntimeState *state)
 
virtual Status GetNext (RuntimeState *state, RowBatch *row_batch, bool *eos)
 
virtual Status Reset (RuntimeState *state)
 
virtual void Close (RuntimeState *state)
 
void CollectNodes (TPlanNodeType::type node_type, std::vector< ExecNode * > *nodes)
 
void CollectScanNodes (std::vector< ExecNode * > *nodes)
 Collect all scan node types. More...
 
std::string DebugString () const
 Returns a string representation in DFS order of the plan rooted at this. More...
 
virtual void DebugString (int indentation_level, std::stringstream *out) const
 
const std::vector< ExprContext * > & conjunct_ctxs () const
 
int id () const
 
TPlanNodeType::type type () const
 
const RowDescriptorrow_desc () const
 
int64_t rows_returned () const
 
int64_t limit () const
 
bool ReachedLimit ()
 
RuntimeProfileruntime_profile ()
 
MemTrackermem_tracker ()
 
MemTrackerexpr_mem_tracker ()
 

Static Public Member Functions

static Status CreateTree (ObjectPool *pool, const TPlan &plan, const DescriptorTbl &descs, ExecNode **root)
 
static void SetDebugOptions (int node_id, TExecNodePhase::type phase, TDebugAction::type action, ExecNode *tree)
 Set debug action for node with given id in 'tree'. More...
 
static bool EvalConjuncts (ExprContext *const *ctxs, int num_ctxs, TupleRow *row)
 
static llvm::Function * CodegenEvalConjuncts (RuntimeState *state, const std::vector< ExprContext * > &conjunct_ctxs, const char *name="EvalConjuncts")
 
static int GetNodeIdFromProfile (RuntimeProfile *p)
 Extract node id from p->name(). More...
 

Static Public Attributes

static const std::string ROW_THROUGHPUT_COUNTER = "RowsReturnedRate"
 Names of counters shared by all exec nodes. More...
 

Protected Member Functions

ExecNodechild (int i)
 
bool is_closed ()
 
virtual bool IsScanNode () const
 
void InitRuntimeProfile (const std::string &name)
 
Status ExecDebugAction (TExecNodePhase::type phase, RuntimeState *state)
 
void AddRuntimeExecOption (const std::string &option)
 Appends option to 'runtime_exec_options_'. More...
 
virtual Status QueryMaintenance (RuntimeState *state)
 
void AddExprCtxToFree (ExprContext *ctx)
 
void AddExprCtxsToFree (const std::vector< ExprContext * > &ctxs)
 
void AddExprCtxsToFree (const SortExecExprs &sort_exec_exprs)
 

Static Protected Member Functions

static Status CreateNode (ObjectPool *pool, const TPlanNode &tnode, const DescriptorTbl &descs, ExecNode **node)
 Create a single exec node derived from thrift node; place exec node in 'pool'. More...
 
static Status CreateTreeHelper (ObjectPool *pool, const std::vector< TPlanNode > &tnodes, const DescriptorTbl &descs, ExecNode *parent, int *node_idx, ExecNode **root)
 

Protected Attributes

int id_
 
TPlanNodeType::type type_
 
ObjectPoolpool_
 
std::vector< ExprContext * > conjunct_ctxs_
 
std::vector< ExecNode * > children_
 
RowDescriptor row_descriptor_
 
TExecNodePhase::type debug_phase_
 
TDebugAction::type debug_action_
 
int64_t limit_
 
int64_t num_rows_returned_
 
boost::scoped_ptr< RuntimeProfileruntime_profile_
 
RuntimeProfile::Counterrows_returned_counter_
 
RuntimeProfile::Counterrows_returned_rate_
 
boost::scoped_ptr< MemTrackermem_tracker_
 Account for peak memory used by this node. More...
 
boost::scoped_ptr< MemTrackerexpr_mem_tracker_
 MemTracker that should be used for ExprContexts. More...
 
boost::mutex exec_options_lock_
 
std::string runtime_exec_options_
 

Private Member Functions

Status OpenCurrentChild (RuntimeState *state)
 
bool EvalAndMaterializeExprs (const std::vector< ExprContext * > &ctxs, bool const_exprs, Tuple **tuple, RowBatch *row_batch)
 

Private Attributes

int tuple_id_
 Tuple id resolved in Prepare() to set tuple_desc_;. More...
 
const TupleDescriptortuple_desc_
 Descriptor for tuples this union node constructs. More...
 
std::vector< SlotDescriptor * > materialized_slots_
 those tuple_desc_->slots() which are materialized, in the same order More...
 
std::vector< std::vector
< ExprContext * > > 
const_result_expr_ctx_lists_
 Const exprs materialized by this node. These exprs don't refer to any children. More...
 
int const_result_expr_idx_
 Index of current const result expr list. More...
 
std::vector< std::vector
< ExprContext * > > 
result_expr_ctx_lists_
 Exprs materialized by this node. The i-th result expr list refers to the i-th child. More...
 
int child_idx_
 Index of current child. More...
 
boost::scoped_ptr< RowBatchchild_row_batch_
 
bool child_eos_
 Saved from the last to GetNext() on the current child. More...
 
int child_row_idx_
 Index of current row in child_row_batch_. More...
 

Detailed Description

Node that merges the results of its children by materializing their evaluated expressions into row batches. The UnionNode pulls row batches from its children sequentially, i.e., it exhausts one child completely before moving on to the next one.

Definition at line 35 of file union-node.h.

Constructor & Destructor Documentation

impala::UnionNode::UnionNode ( ObjectPool pool,
const TPlanNode &  tnode,
const DescriptorTbl descs 
)

Definition at line 27 of file union-node.cc.

Member Function Documentation

void impala::ExecNode::AddExprCtxsToFree ( const SortExecExprs sort_exec_exprs)
protectedinherited
void impala::ExecNode::AddExprCtxToFree ( ExprContext ctx)
inlineprotectedinherited

Add an ExprContext to have its local allocations freed by QueryMaintenance(). Exprs that are evaluated in the main execution thread should be added. Exprs evaluated in a separate thread are generally not safe to add, since a local allocation may be freed while it's being used. Rather than using this mechanism, threads should call FreeLocalAllocations() on local ExprContexts periodically.

Definition at line 276 of file exec-node.h.

References impala::ExecNode::expr_ctxs_to_free_.

Referenced by impala::AnalyticEvalNode::Prepare().

ExecNode* impala::ExecNode::child ( int  i)
inlineprotectedinherited

Definition at line 241 of file exec-node.h.

References impala::ExecNode::children_.

Referenced by impala::CrossJoinNode::BuildListDebugString(), impala::BlockingJoinNode::BuildSideThread(), impala::HashJoinNode::CodegenCreateOutputRow(), impala::PartitionedHashJoinNode::CodegenCreateOutputRow(), impala::CrossJoinNode::ConstructBuildSide(), impala::HashJoinNode::ConstructBuildSide(), impala::PartitionedHashJoinNode::ConstructBuildSide(), impala::BlockingJoinNode::GetLeftChildRowString(), impala::SelectNode::GetNext(), GetNext(), impala::CrossJoinNode::GetNext(), impala::HashJoinNode::GetNext(), impala::AnalyticEvalNode::GetNextOutputBatch(), impala::PartitionedAggregationNode::Partition::InitStreams(), impala::HashJoinNode::LeftJoinGetNext(), impala::PartitionedHashJoinNode::NextProbeRowBatch(), impala::SelectNode::Open(), impala::SortNode::Open(), impala::TopNNode::Open(), impala::BlockingJoinNode::Open(), impala::AggregationNode::Open(), impala::AnalyticEvalNode::Open(), impala::PartitionedAggregationNode::Open(), OpenCurrentChild(), impala::SelectNode::Prepare(), impala::SortNode::Prepare(), Prepare(), impala::TopNNode::Prepare(), impala::BlockingJoinNode::Prepare(), impala::HashJoinNode::Prepare(), impala::AggregationNode::Prepare(), impala::AnalyticEvalNode::Prepare(), impala::PartitionedHashJoinNode::Prepare(), impala::PartitionedAggregationNode::Prepare(), impala::PartitionedHashJoinNode::ProcessBuildInput(), impala::AnalyticEvalNode::ProcessChildBatches(), and impala::SortNode::SortInput().

void impala::UnionNode::Close ( RuntimeState state)
virtual

Close() will get called for every exec node, regardless of what else is called and the status of these calls (i.e. Prepare() may never have been called, or Prepare()/Open()/GetNext() returned with an error). Close() releases all resources that were allocated in Open()/GetNext(), even if the latter ended with an error. Close() can be called if the node has been prepared or the node is closed. The default implementation updates runtime profile counters and calls Close() on the children. Subclasses should check if the node has already been closed (is_closed()), then close themselves, then call the base Close(). Nodes that are using tuples returned by a child may call Close() on their children before their own Close() if the child node has returned eos. It is only safe to call Close() on the child node while the parent node is still returning rows if the parent node fully materializes the child's input.

Reimplemented from impala::ExecNode.

Definition at line 186 of file union-node.cc.

References child_row_batch_, impala::ExecNode::Close(), impala::Expr::Close(), const_result_expr_ctx_lists_, impala::ExecNode::is_closed(), and result_expr_ctx_lists_.

void impala::ExecNode::CollectNodes ( TPlanNodeType::type  node_type,
std::vector< ExecNode * > *  nodes 
)
inherited

Collect all nodes of given 'node_type' that are part of this subtree, and return in 'nodes'.

Definition at line 359 of file exec-node.cc.

References impala::ExecNode::children_, and impala::ExecNode::type_.

Referenced by impala::ExecNode::CollectScanNodes(), and impala::PlanFragmentExecutor::Prepare().

void impala::ExecNode::CollectScanNodes ( std::vector< ExecNode * > *  nodes)
inherited

Collect all scan node types.

Definition at line 366 of file exec-node.cc.

References impala::ExecNode::CollectNodes().

Referenced by impala::PlanFragmentExecutor::Prepare().

Status impala::ExecNode::CreateNode ( ObjectPool pool,
const TPlanNode &  tnode,
const DescriptorTbl descs,
ExecNode **  node 
)
staticprotectedinherited

Create a single exec node derived from thrift node; place exec node in 'pool'.

Definition at line 260 of file exec-node.cc.

References impala::ObjectPool::Add(), impala::Status::OK, and RETURN_IF_ERROR.

Referenced by impala::ExecNode::CreateTreeHelper().

Status impala::ExecNode::CreateTree ( ObjectPool pool,
const TPlan &  plan,
const DescriptorTbl descs,
ExecNode **  root 
)
staticinherited

Creates exec node tree from list of nodes contained in plan via depth-first traversal. All nodes are placed in pool. Returns error if 'plan' is corrupted, otherwise success.

Definition at line 199 of file exec-node.cc.

References impala::ExecNode::CreateTreeHelper(), impala::Status::OK, and impala::Status::ok().

Referenced by impala::PlanFragmentExecutor::Prepare().

Status impala::ExecNode::CreateTreeHelper ( ObjectPool pool,
const std::vector< TPlanNode > &  tnodes,
const DescriptorTbl descs,
ExecNode parent,
int *  node_idx,
ExecNode **  root 
)
staticprotectedinherited
virtual void impala::ExecNode::DebugString ( int  indentation_level,
std::stringstream *  out 
) const
virtualinherited

Recursive helper method for generating a string for DebugString(). Implementations should call DebugString(int, std::stringstream) on their children. Input parameters: indentation_level: Current level in plan tree. Output parameters: out: Stream to accumulate debug string.

Reimplemented in impala::BlockingJoinNode, impala::PartitionedAggregationNode, impala::AnalyticEvalNode, impala::AggregationNode, impala::DataSourceScanNode, impala::ExchangeNode, impala::HBaseScanNode, impala::TopNNode, and impala::SortNode.

bool impala::UnionNode::EvalAndMaterializeExprs ( const std::vector< ExprContext * > &  ctxs,
bool  const_exprs,
Tuple **  tuple,
RowBatch row_batch 
)
private

Evaluates exprs on all rows in child_row_batch_ starting from child_row_idx_, and materializes their results into *tuple. Adds *tuple into row_batch, and increments *tuple. If const_exprs is true, then the exprs are evaluated exactly once without fetching rows from child_row_batch_. Only commits tuples to row_batch if they are not filtered by conjuncts. Returns true if row_batch should be returned to caller or limit has been reached, false otherwise.

Definition at line 198 of file union-node.cc.

References impala::RowBatch::AddRow(), impala::RowBatch::AtCapacity(), impala::TupleDescriptor::byte_size(), child_row_batch_, child_row_idx_, impala::RowBatch::CommitLastRow(), impala::ExecNode::conjunct_ctxs(), impala::ExecNode::conjunct_ctxs_, COUNTER_SET, impala::ExecNode::EvalConjuncts(), impala::RowBatch::GetRow(), impala::Tuple::Init(), impala::RowBatch::INVALID_ROW_INDEX, materialized_slots_, impala::ExecNode::num_rows_returned_, impala::ExecNode::ReachedLimit(), impala::ExecNode::rows_returned_counter_, impala::TupleRow::SetTuple(), impala::RowBatch::tuple_data_pool(), tuple_desc_, and impala::RawValue::Write().

Referenced by GetNext().

Status impala::UnionNode::GetNext ( RuntimeState state,
RowBatch row_batch,
bool eos 
)
virtual

Retrieves rows and returns them via row_batch. Sets eos to true if subsequent calls will not retrieve any more rows. Data referenced by any tuples returned in row_batch must not be overwritten by the callee until Close() is called. The memory holding that data can be returned via row_batch's tuple_data_pool (in which case it may be deleted by the caller) or held on to by the callee. The row_batch, including its tuple_data_pool, will be destroyed by the caller at some point prior to the final Close() call. In other words, if the memory holding the tuple data will be referenced by the callee in subsequent GetNext() calls, it must not be attached to the row_batch's tuple_data_pool. Caller must not be holding any io buffers. This will cause deadlock. TODO: AggregationNode and HashJoinNode cannot be "re-opened" yet.

Implements impala::ExecNode.

Definition at line 119 of file union-node.cc.

References impala::RowBatch::AtCapacity(), impala::ExecNode::child(), child_eos_, child_idx_, child_row_batch_, child_row_idx_, impala::ExecNode::children_, impala::ExecNode::Close(), const_result_expr_ctx_lists_, const_result_expr_idx_, impala::Tuple::Create(), EvalAndMaterializeExprs(), impala::ExecNode::ExecDebugAction(), impala::RuntimeState::fragment_ctx(), impala::RowBatch::MaxTupleBufferSize(), impala::Status::OK, OpenCurrentChild(), impala::ExecNode::QueryMaintenance(), impala::ExecNode::ReachedLimit(), result_expr_ctx_lists_, RETURN_IF_CANCELLED, RETURN_IF_ERROR, impala::ExecNode::runtime_profile_, SCOPED_TIMER, and impala::RowBatch::tuple_data_pool().

Referenced by OpenCurrentChild().

int impala::ExecNode::GetNodeIdFromProfile ( RuntimeProfile p)
staticinherited

Extract node id from p->name().

Definition at line 62 of file exec-node.cc.

References impala::RuntimeProfile::metadata().

Status impala::UnionNode::Init ( const TPlanNode &  tnode)
virtual

Initializes this object from the thrift tnode desc. The subclass should do any initialization that can fail in Init() rather than the ctor. If overridden in subclass, must first call superclass's Init().

Reimplemented from impala::ExecNode.

Definition at line 38 of file union-node.cc.

References const_result_expr_ctx_lists_, impala::Expr::CreateExprTrees(), impala::ExecNode::Init(), impala::Status::OK, impala::ExecNode::pool_, result_expr_ctx_lists_, and RETURN_IF_ERROR.

void impala::ExecNode::InitRuntimeProfile ( const std::string &  name)
protectedinherited
virtual bool impala::ExecNode::IsScanNode ( ) const
inlineprotectedvirtualinherited

Reimplemented in impala::ScanNode.

Definition at line 251 of file exec-node.h.

int64_t impala::ExecNode::limit ( ) const
inlineinherited
Status impala::UnionNode::Open ( RuntimeState state)
virtual

Performs any preparatory work prior to calling GetNext(). Caller must not be holding any io buffers. This will cause deadlock. If overridden in subclass, must first call superclass's Open(). If a parent exec node adds slot filters (see RuntimeState::AddBitmapFilter()), they need to be added before calling Open() on the child that will consume them.

Reimplemented from impala::ExecNode.

Definition at line 88 of file union-node.cc.

References impala::ExecNode::children_, const_result_expr_ctx_lists_, impala::Status::OK, impala::ExecNode::Open(), impala::Expr::Open(), OpenCurrentChild(), result_expr_ctx_lists_, RETURN_IF_ERROR, impala::ExecNode::runtime_profile_, and SCOPED_TIMER.

Referenced by OpenCurrentChild().

Status impala::UnionNode::OpenCurrentChild ( RuntimeState state)
private

Opens the child at child_idx_, fetches the first batch into child_row_batch_, and sets child_row_idx_ to 0. May set child_eos_.

Definition at line 107 of file union-node.cc.

References impala::RuntimeState::batch_size(), impala::ExecNode::child(), child_eos_, child_idx_, child_row_batch_, child_row_idx_, impala::ExecNode::children_, GetNext(), impala::ExecNode::mem_tracker(), impala::Status::OK, Open(), RETURN_IF_ERROR, and impala::ExecNode::row_desc().

Referenced by GetNext(), and Open().

Status impala::UnionNode::Prepare ( RuntimeState state)
virtual

Sets up internal structures, etc., without doing any actual work. Must be called prior to Open(). Will only be called once in this node's lifetime. All code generation (adding functions to the LlvmCodeGen object) must happen in Prepare(). Retrieving the jit compiled function pointer must happen in Open(). If overridden in subclass, must first call superclass's Prepare().

Reimplemented from impala::ExecNode.

Definition at line 58 of file union-node.cc.

References impala::ExecNode::AddExprCtxsToFree(), impala::ExecNode::child(), const_result_expr_ctx_lists_, impala::RuntimeState::desc_tbl(), impala::ExecNode::expr_mem_tracker(), impala::DescriptorTbl::GetTupleDescriptor(), impala::SlotDescriptor::is_materialized(), materialized_slots_, impala::Status::OK, impala::ExecNode::Prepare(), impala::Expr::Prepare(), result_expr_ctx_lists_, RETURN_IF_ERROR, impala::ExecNode::row_desc(), impala::ExecNode::runtime_profile_, SCOPED_TIMER, impala::TupleDescriptor::slots(), tuple_desc_, and tuple_id_.

Status impala::ExecNode::QueryMaintenance ( RuntimeState state)
protectedvirtualinherited
Status impala::UnionNode::Reset ( RuntimeState state)
virtual

Resets all data-specific state, returning this node to the state it was in after calling Prepare() and before calling Open(). Prepare() must have already been called before calling Reset(). Open() and GetNext() may have optionally been called. Close() must not have been called. If overridden in a subclass, must call superclass's Reset() at the end. The default implementation calls Reset() on children. Note that this function may be called many times, so should be fast. For example, accumulated memory does not need to be freed on every call if it's expensive.

Reimplemented from impala::ExecNode.

Definition at line 181 of file union-node.cc.

void impala::ExecNode::SetDebugOptions ( int  node_id,
TExecNodePhase::type  phase,
TDebugAction::type  action,
ExecNode tree 
)
staticinherited

Set debug action for node with given id in 'tree'.

Definition at line 332 of file exec-node.cc.

References impala::ExecNode::children_, impala::ExecNode::debug_action_, impala::ExecNode::debug_phase_, and impala::ExecNode::id_.

Referenced by impala::PlanFragmentExecutor::Prepare().

TPlanNodeType::type impala::ExecNode::type ( ) const
inlineinherited

Member Data Documentation

bool impala::UnionNode::child_eos_
private

Saved from the last to GetNext() on the current child.

Definition at line 73 of file union-node.h.

Referenced by GetNext(), and OpenCurrentChild().

int impala::UnionNode::child_idx_
private

Index of current child.

Definition at line 66 of file union-node.h.

Referenced by GetNext(), and OpenCurrentChild().

boost::scoped_ptr<RowBatch> impala::UnionNode::child_row_batch_
private

Current row batch of current child. We reset the pointer to a new RowBatch when switching to a different child.

Definition at line 70 of file union-node.h.

Referenced by Close(), EvalAndMaterializeExprs(), GetNext(), and OpenCurrentChild().

int impala::UnionNode::child_row_idx_
private

Index of current row in child_row_batch_.

Definition at line 76 of file union-node.h.

Referenced by EvalAndMaterializeExprs(), GetNext(), and OpenCurrentChild().

std::vector<std::vector<ExprContext*> > impala::UnionNode::const_result_expr_ctx_lists_
private

Const exprs materialized by this node. These exprs don't refer to any children.

Definition at line 57 of file union-node.h.

Referenced by Close(), GetNext(), Init(), Open(), and Prepare().

int impala::UnionNode::const_result_expr_idx_
private

Index of current const result expr list.

Definition at line 60 of file union-node.h.

Referenced by GetNext().

TDebugAction::type impala::ExecNode::debug_action_
protectedinherited
TExecNodePhase::type impala::ExecNode::debug_phase_
protectedinherited

debug-only: if debug_action_ is not INVALID, node will perform action in debug_phase_

Definition at line 219 of file exec-node.h.

Referenced by impala::ExecNode::ExecDebugAction(), and impala::ExecNode::SetDebugOptions().

boost::mutex impala::ExecNode::exec_options_lock_
protectedinherited

Execution options that are determined at runtime. This is added to the runtime profile at Close(). Examples for options logged here would be "Codegen Enabled"

Definition at line 238 of file exec-node.h.

Referenced by impala::ExecNode::AddRuntimeExecOption().

boost::scoped_ptr<MemTracker> impala::ExecNode::expr_mem_tracker_
protectedinherited

MemTracker that should be used for ExprContexts.

Definition at line 233 of file exec-node.h.

Referenced by impala::ExecNode::expr_mem_tracker(), and impala::ExecNode::Prepare().

std::vector<SlotDescriptor*> impala::UnionNode::materialized_slots_
private

those tuple_desc_->slots() which are materialized, in the same order

Definition at line 54 of file union-node.h.

Referenced by EvalAndMaterializeExprs(), and Prepare().

boost::scoped_ptr<MemTracker> impala::ExecNode::mem_tracker_
protectedinherited

Account for peak memory used by this node.

Definition at line 230 of file exec-node.h.

Referenced by impala::ExecNode::mem_tracker(), and impala::ExecNode::Prepare().

std::vector<std::vector<ExprContext*> > impala::UnionNode::result_expr_ctx_lists_
private

Exprs materialized by this node. The i-th result expr list refers to the i-th child.

Definition at line 63 of file union-node.h.

Referenced by Close(), GetNext(), Init(), Open(), and Prepare().

RowDescriptor impala::ExecNode::row_descriptor_
protectedinherited
const string impala::ExecNode::ROW_THROUGHPUT_COUNTER = "RowsReturnedRate"
staticinherited

Names of counters shared by all exec nodes.

Definition at line 169 of file exec-node.h.

Referenced by impala::ExecNode::Prepare().

RuntimeProfile::Counter* impala::ExecNode::rows_returned_rate_
protectedinherited

Definition at line 227 of file exec-node.h.

Referenced by impala::ExecNode::Prepare().

std::string impala::ExecNode::runtime_exec_options_
protectedinherited

Definition at line 239 of file exec-node.h.

Referenced by impala::ExecNode::AddRuntimeExecOption().

const TupleDescriptor* impala::UnionNode::tuple_desc_
private

Descriptor for tuples this union node constructs.

Definition at line 51 of file union-node.h.

Referenced by EvalAndMaterializeExprs(), and Prepare().

int impala::UnionNode::tuple_id_
private

Tuple id resolved in Prepare() to set tuple_desc_;.

Definition at line 48 of file union-node.h.

Referenced by Prepare().

TPlanNodeType::type impala::ExecNode::type_
protectedinherited

Definition at line 210 of file exec-node.h.

Referenced by impala::ExecNode::CollectNodes(), and impala::ExecNode::type().


The documentation for this class was generated from the following files: