Tom Lane afb9249d06 Add support for doing late row locking in FDWs.
Previously, FDWs could only do "early row locking", that is lock a row as
soon as it's fetched, even though local restriction/join conditions might
discard the row later.  This patch adds callbacks that allow FDWs to do
late locking in the same way that it's done for regular tables.

To make use of this feature, an FDW must support the "ctid" column as a
unique row identifier.  Currently, since ctid has to be of type TID,
the feature is of limited use, though in principle it could be used by
postgres_fdw.  We may eventually allow FDWs to specify another data type
for ctid, which would make it possible for more FDWs to use this feature.

This commit does not modify postgres_fdw to use late locking.  We've
tested some prototype code for that, but it's not in committable shape,
and besides it's quite unclear whether it actually makes sense to do late
locking against a remote server.  The extra round trips required are likely
to outweigh any benefit from improved concurrency.

Etsuro Fujita, reviewed by Ashutosh Bapat, and hacked up a lot by me
2015-05-12 14:10:17 -04:00

381 lines
15 KiB
C

/*-------------------------------------------------------------------------
*
* executor.h
* support for the POSTGRES executor module
*
*
* Portions Copyright (c) 1996-2015, PostgreSQL Global Development Group
* Portions Copyright (c) 1994, Regents of the University of California
*
* src/include/executor/executor.h
*
*-------------------------------------------------------------------------
*/
#ifndef EXECUTOR_H
#define EXECUTOR_H
#include "executor/execdesc.h"
#include "nodes/parsenodes.h"
/*
* The "eflags" argument to ExecutorStart and the various ExecInitNode
* routines is a bitwise OR of the following flag bits, which tell the
* called plan node what to expect. Note that the flags will get modified
* as they are passed down the plan tree, since an upper node may require
* functionality in its subnode not demanded of the plan as a whole
* (example: MergeJoin requires mark/restore capability in its inner input),
* or an upper node may shield its input from some functionality requirement
* (example: Materialize shields its input from needing to do backward scan).
*
* EXPLAIN_ONLY indicates that the plan tree is being initialized just so
* EXPLAIN can print it out; it will not be run. Hence, no side-effects
* of startup should occur. However, error checks (such as permission checks)
* should be performed.
*
* REWIND indicates that the plan node should try to efficiently support
* rescans without parameter changes. (Nodes must support ExecReScan calls
* in any case, but if this flag was not given, they are at liberty to do it
* through complete recalculation. Note that a parameter change forces a
* full recalculation in any case.)
*
* BACKWARD indicates that the plan node must respect the es_direction flag.
* When this is not passed, the plan node will only be run forwards.
*
* MARK indicates that the plan node must support Mark/Restore calls.
* When this is not passed, no Mark/Restore will occur.
*
* SKIP_TRIGGERS tells ExecutorStart/ExecutorFinish to skip calling
* AfterTriggerBeginQuery/AfterTriggerEndQuery. This does not necessarily
* mean that the plan can't queue any AFTER triggers; just that the caller
* is responsible for there being a trigger context for them to be queued in.
*
* WITH/WITHOUT_OIDS tell the executor to emit tuples with or without space
* for OIDs, respectively. These are currently used only for CREATE TABLE AS.
* If neither is set, the plan may or may not produce tuples including OIDs.
*/
#define EXEC_FLAG_EXPLAIN_ONLY 0x0001 /* EXPLAIN, no ANALYZE */
#define EXEC_FLAG_REWIND 0x0002 /* need efficient rescan */
#define EXEC_FLAG_BACKWARD 0x0004 /* need backward scan */
#define EXEC_FLAG_MARK 0x0008 /* need mark/restore */
#define EXEC_FLAG_SKIP_TRIGGERS 0x0010 /* skip AfterTrigger calls */
#define EXEC_FLAG_WITH_OIDS 0x0020 /* force OIDs in returned tuples */
#define EXEC_FLAG_WITHOUT_OIDS 0x0040 /* force no OIDs in returned tuples */
#define EXEC_FLAG_WITH_NO_DATA 0x0080 /* rel scannability doesn't matter */
/*
* ExecEvalExpr was formerly a function containing a switch statement;
* now it's just a macro invoking the function pointed to by an ExprState
* node. Beware of double evaluation of the ExprState argument!
*/
#define ExecEvalExpr(expr, econtext, isNull, isDone) \
((*(expr)->evalfunc) (expr, econtext, isNull, isDone))
/* Hook for plugins to get control in ExecutorStart() */
typedef void (*ExecutorStart_hook_type) (QueryDesc *queryDesc, int eflags);
extern PGDLLIMPORT ExecutorStart_hook_type ExecutorStart_hook;
/* Hook for plugins to get control in ExecutorRun() */
typedef void (*ExecutorRun_hook_type) (QueryDesc *queryDesc,
ScanDirection direction,
long count);
extern PGDLLIMPORT ExecutorRun_hook_type ExecutorRun_hook;
/* Hook for plugins to get control in ExecutorFinish() */
typedef void (*ExecutorFinish_hook_type) (QueryDesc *queryDesc);
extern PGDLLIMPORT ExecutorFinish_hook_type ExecutorFinish_hook;
/* Hook for plugins to get control in ExecutorEnd() */
typedef void (*ExecutorEnd_hook_type) (QueryDesc *queryDesc);
extern PGDLLIMPORT ExecutorEnd_hook_type ExecutorEnd_hook;
/* Hook for plugins to get control in ExecCheckRTPerms() */
typedef bool (*ExecutorCheckPerms_hook_type) (List *, bool);
extern PGDLLIMPORT ExecutorCheckPerms_hook_type ExecutorCheckPerms_hook;
/*
* prototypes from functions in execAmi.c
*/
struct Path; /* avoid including relation.h here */
extern void ExecReScan(PlanState *node);
extern void ExecMarkPos(PlanState *node);
extern void ExecRestrPos(PlanState *node);
extern bool ExecSupportsMarkRestore(struct Path *pathnode);
extern bool ExecSupportsBackwardScan(Plan *node);
extern bool ExecMaterializesOutput(NodeTag plantype);
/*
* prototypes from functions in execCurrent.c
*/
extern bool execCurrentOf(CurrentOfExpr *cexpr,
ExprContext *econtext,
Oid table_oid,
ItemPointer current_tid);
/*
* prototypes from functions in execGrouping.c
*/
extern bool execTuplesMatch(TupleTableSlot *slot1,
TupleTableSlot *slot2,
int numCols,
AttrNumber *matchColIdx,
FmgrInfo *eqfunctions,
MemoryContext evalContext);
extern bool execTuplesUnequal(TupleTableSlot *slot1,
TupleTableSlot *slot2,
int numCols,
AttrNumber *matchColIdx,
FmgrInfo *eqfunctions,
MemoryContext evalContext);
extern FmgrInfo *execTuplesMatchPrepare(int numCols,
Oid *eqOperators);
extern void execTuplesHashPrepare(int numCols,
Oid *eqOperators,
FmgrInfo **eqFunctions,
FmgrInfo **hashFunctions);
extern TupleHashTable BuildTupleHashTable(int numCols, AttrNumber *keyColIdx,
FmgrInfo *eqfunctions,
FmgrInfo *hashfunctions,
long nbuckets, Size entrysize,
MemoryContext tablecxt,
MemoryContext tempcxt);
extern TupleHashEntry LookupTupleHashEntry(TupleHashTable hashtable,
TupleTableSlot *slot,
bool *isnew);
extern TupleHashEntry FindTupleHashEntry(TupleHashTable hashtable,
TupleTableSlot *slot,
FmgrInfo *eqfunctions,
FmgrInfo *hashfunctions);
/*
* prototypes from functions in execJunk.c
*/
extern JunkFilter *ExecInitJunkFilter(List *targetList, bool hasoid,
TupleTableSlot *slot);
extern JunkFilter *ExecInitJunkFilterConversion(List *targetList,
TupleDesc cleanTupType,
TupleTableSlot *slot);
extern AttrNumber ExecFindJunkAttribute(JunkFilter *junkfilter,
const char *attrName);
extern AttrNumber ExecFindJunkAttributeInTlist(List *targetlist,
const char *attrName);
extern Datum ExecGetJunkAttribute(TupleTableSlot *slot, AttrNumber attno,
bool *isNull);
extern TupleTableSlot *ExecFilterJunk(JunkFilter *junkfilter,
TupleTableSlot *slot);
/*
* prototypes from functions in execMain.c
*/
extern void ExecutorStart(QueryDesc *queryDesc, int eflags);
extern void standard_ExecutorStart(QueryDesc *queryDesc, int eflags);
extern void ExecutorRun(QueryDesc *queryDesc,
ScanDirection direction, long count);
extern void standard_ExecutorRun(QueryDesc *queryDesc,
ScanDirection direction, long count);
extern void ExecutorFinish(QueryDesc *queryDesc);
extern void standard_ExecutorFinish(QueryDesc *queryDesc);
extern void ExecutorEnd(QueryDesc *queryDesc);
extern void standard_ExecutorEnd(QueryDesc *queryDesc);
extern void ExecutorRewind(QueryDesc *queryDesc);
extern bool ExecCheckRTPerms(List *rangeTable, bool ereport_on_violation);
extern void CheckValidResultRel(Relation resultRel, CmdType operation);
extern void InitResultRelInfo(ResultRelInfo *resultRelInfo,
Relation resultRelationDesc,
Index resultRelationIndex,
int instrument_options);
extern ResultRelInfo *ExecGetTriggerResultRel(EState *estate, Oid relid);
extern bool ExecContextForcesOids(PlanState *planstate, bool *hasoids);
extern void ExecConstraints(ResultRelInfo *resultRelInfo,
TupleTableSlot *slot, EState *estate);
extern void ExecWithCheckOptions(WCOKind kind, ResultRelInfo *resultRelInfo,
TupleTableSlot *slot, EState *estate);
extern LockTupleMode ExecUpdateLockMode(EState *estate, ResultRelInfo *relinfo);
extern ExecRowMark *ExecFindRowMark(EState *estate, Index rti, bool missing_ok);
extern ExecAuxRowMark *ExecBuildAuxRowMark(ExecRowMark *erm, List *targetlist);
extern TupleTableSlot *EvalPlanQual(EState *estate, EPQState *epqstate,
Relation relation, Index rti, int lockmode,
ItemPointer tid, TransactionId priorXmax);
extern HeapTuple EvalPlanQualFetch(EState *estate, Relation relation,
int lockmode, LockWaitPolicy wait_policy, ItemPointer tid,
TransactionId priorXmax);
extern void EvalPlanQualInit(EPQState *epqstate, EState *estate,
Plan *subplan, List *auxrowmarks, int epqParam);
extern void EvalPlanQualSetPlan(EPQState *epqstate,
Plan *subplan, List *auxrowmarks);
extern void EvalPlanQualSetTuple(EPQState *epqstate, Index rti,
HeapTuple tuple);
extern HeapTuple EvalPlanQualGetTuple(EPQState *epqstate, Index rti);
#define EvalPlanQualSetSlot(epqstate, slot) ((epqstate)->origslot = (slot))
extern void EvalPlanQualFetchRowMarks(EPQState *epqstate);
extern TupleTableSlot *EvalPlanQualNext(EPQState *epqstate);
extern void EvalPlanQualBegin(EPQState *epqstate, EState *parentestate);
extern void EvalPlanQualEnd(EPQState *epqstate);
/*
* prototypes from functions in execProcnode.c
*/
extern PlanState *ExecInitNode(Plan *node, EState *estate, int eflags);
extern TupleTableSlot *ExecProcNode(PlanState *node);
extern Node *MultiExecProcNode(PlanState *node);
extern void ExecEndNode(PlanState *node);
/*
* prototypes from functions in execQual.c
*/
extern Datum GetAttributeByNum(HeapTupleHeader tuple, AttrNumber attrno,
bool *isNull);
extern Datum GetAttributeByName(HeapTupleHeader tuple, const char *attname,
bool *isNull);
extern Tuplestorestate *ExecMakeTableFunctionResult(ExprState *funcexpr,
ExprContext *econtext,
MemoryContext argContext,
TupleDesc expectedDesc,
bool randomAccess);
extern Datum ExecEvalExprSwitchContext(ExprState *expression, ExprContext *econtext,
bool *isNull, ExprDoneCond *isDone);
extern ExprState *ExecInitExpr(Expr *node, PlanState *parent);
extern ExprState *ExecPrepareExpr(Expr *node, EState *estate);
extern bool ExecQual(List *qual, ExprContext *econtext, bool resultForNull);
extern int ExecTargetListLength(List *targetlist);
extern int ExecCleanTargetListLength(List *targetlist);
extern TupleTableSlot *ExecProject(ProjectionInfo *projInfo,
ExprDoneCond *isDone);
/*
* prototypes from functions in execScan.c
*/
typedef TupleTableSlot *(*ExecScanAccessMtd) (ScanState *node);
typedef bool (*ExecScanRecheckMtd) (ScanState *node, TupleTableSlot *slot);
extern TupleTableSlot *ExecScan(ScanState *node, ExecScanAccessMtd accessMtd,
ExecScanRecheckMtd recheckMtd);
extern void ExecAssignScanProjectionInfo(ScanState *node);
extern void ExecAssignScanProjectionInfoWithVarno(ScanState *node, Index varno);
extern void ExecScanReScan(ScanState *node);
/*
* prototypes from functions in execTuples.c
*/
extern void ExecInitResultTupleSlot(EState *estate, PlanState *planstate);
extern void ExecInitScanTupleSlot(EState *estate, ScanState *scanstate);
extern TupleTableSlot *ExecInitExtraTupleSlot(EState *estate);
extern TupleTableSlot *ExecInitNullTupleSlot(EState *estate,
TupleDesc tupType);
extern TupleDesc ExecTypeFromTL(List *targetList, bool hasoid);
extern TupleDesc ExecCleanTypeFromTL(List *targetList, bool hasoid);
extern TupleDesc ExecTypeFromExprList(List *exprList);
extern void ExecTypeSetColNames(TupleDesc typeInfo, List *namesList);
extern void UpdateChangedParamSet(PlanState *node, Bitmapset *newchg);
typedef struct TupOutputState
{
TupleTableSlot *slot;
DestReceiver *dest;
} TupOutputState;
extern TupOutputState *begin_tup_output_tupdesc(DestReceiver *dest,
TupleDesc tupdesc);
extern void do_tup_output(TupOutputState *tstate, Datum *values, bool *isnull);
extern void do_text_output_multiline(TupOutputState *tstate, char *text);
extern void end_tup_output(TupOutputState *tstate);
/*
* Write a single line of text given as a C string.
*
* Should only be used with a single-TEXT-attribute tupdesc.
*/
#define do_text_output_oneline(tstate, str_to_emit) \
do { \
Datum values_[1]; \
bool isnull_[1]; \
values_[0] = PointerGetDatum(cstring_to_text(str_to_emit)); \
isnull_[0] = false; \
do_tup_output(tstate, values_, isnull_); \
pfree(DatumGetPointer(values_[0])); \
} while (0)
/*
* prototypes from functions in execUtils.c
*/
extern EState *CreateExecutorState(void);
extern void FreeExecutorState(EState *estate);
extern ExprContext *CreateExprContext(EState *estate);
extern ExprContext *CreateStandaloneExprContext(void);
extern void FreeExprContext(ExprContext *econtext, bool isCommit);
extern void ReScanExprContext(ExprContext *econtext);
#define ResetExprContext(econtext) \
MemoryContextReset((econtext)->ecxt_per_tuple_memory)
extern ExprContext *MakePerTupleExprContext(EState *estate);
/* Get an EState's per-output-tuple exprcontext, making it if first use */
#define GetPerTupleExprContext(estate) \
((estate)->es_per_tuple_exprcontext ? \
(estate)->es_per_tuple_exprcontext : \
MakePerTupleExprContext(estate))
#define GetPerTupleMemoryContext(estate) \
(GetPerTupleExprContext(estate)->ecxt_per_tuple_memory)
/* Reset an EState's per-output-tuple exprcontext, if one's been created */
#define ResetPerTupleExprContext(estate) \
do { \
if ((estate)->es_per_tuple_exprcontext) \
ResetExprContext((estate)->es_per_tuple_exprcontext); \
} while (0)
extern void ExecAssignExprContext(EState *estate, PlanState *planstate);
extern void ExecAssignResultType(PlanState *planstate, TupleDesc tupDesc);
extern void ExecAssignResultTypeFromTL(PlanState *planstate);
extern TupleDesc ExecGetResultType(PlanState *planstate);
extern ProjectionInfo *ExecBuildProjectionInfo(List *targetList,
ExprContext *econtext,
TupleTableSlot *slot,
TupleDesc inputDesc);
extern void ExecAssignProjectionInfo(PlanState *planstate,
TupleDesc inputDesc);
extern void ExecFreeExprContext(PlanState *planstate);
extern TupleDesc ExecGetScanType(ScanState *scanstate);
extern void ExecAssignScanType(ScanState *scanstate, TupleDesc tupDesc);
extern void ExecAssignScanTypeFromOuterPlan(ScanState *scanstate);
extern bool ExecRelationIsTargetRelation(EState *estate, Index scanrelid);
extern Relation ExecOpenScanRelation(EState *estate, Index scanrelid, int eflags);
extern void ExecCloseScanRelation(Relation scanrel);
extern void RegisterExprContextCallback(ExprContext *econtext,
ExprContextCallbackFunction function,
Datum arg);
extern void UnregisterExprContextCallback(ExprContext *econtext,
ExprContextCallbackFunction function,
Datum arg);
/*
* prototypes from functions in execIndexing.c
*/
extern void ExecOpenIndices(ResultRelInfo *resultRelInfo, bool speculative);
extern void ExecCloseIndices(ResultRelInfo *resultRelInfo);
extern List *ExecInsertIndexTuples(TupleTableSlot *slot, ItemPointer tupleid,
EState *estate, bool noDupErr, bool *specConflict,
List *arbiterIndexes);
extern bool ExecCheckIndexConstraints(TupleTableSlot *slot, EState *estate,
ItemPointer conflictTid, List *arbiterIndexes);
extern void check_exclusion_constraint(Relation heap, Relation index,
IndexInfo *indexInfo,
ItemPointer tupleid,
Datum *values, bool *isnull,
EState *estate, bool newIndex);
#endif /* EXECUTOR_H */