execParallel.c File Reference

#include "postgres.h"
#include "executor/execParallel.h"
#include "executor/executor.h"
#include "executor/nodeAgg.h"
#include "executor/nodeAppend.h"
#include "executor/nodeBitmapHeapscan.h"
#include "executor/nodeBitmapIndexscan.h"
#include "executor/nodeCustom.h"
#include "executor/nodeForeignscan.h"
#include "executor/nodeHash.h"
#include "executor/nodeHashjoin.h"
#include "executor/nodeIncrementalSort.h"
#include "executor/nodeIndexonlyscan.h"
#include "executor/nodeIndexscan.h"
#include "executor/nodeMemoize.h"
#include "executor/nodeSeqscan.h"
#include "executor/nodeSort.h"
#include "executor/nodeSubplan.h"
#include "executor/tqueue.h"
#include "jit/jit.h"
#include "nodes/nodeFuncs.h"
#include "pgstat.h"
#include "tcop/tcopprot.h"
#include "utils/datum.h"
#include "utils/dsa.h"
#include "utils/lsyscache.h"
#include "utils/snapmgr.h"

Include dependency graph for execParallel.c:

Go to the source code of this file.

Data Structures
struct	FixedParallelExecutorState
struct	SharedExecutorInstrumentation
struct	ExecParallelEstimateContext
struct	ExecParallelInitializeDSMContext

Macros
#define	PARALLEL_KEY_EXECUTOR_FIXED   UINT64CONST(0xE000000000000001)
#define	PARALLEL_KEY_PLANNEDSTMT   UINT64CONST(0xE000000000000002)
#define	PARALLEL_KEY_PARAMLISTINFO   UINT64CONST(0xE000000000000003)
#define	PARALLEL_KEY_BUFFER_USAGE   UINT64CONST(0xE000000000000004)
#define	PARALLEL_KEY_TUPLE_QUEUE   UINT64CONST(0xE000000000000005)
#define	PARALLEL_KEY_INSTRUMENTATION   UINT64CONST(0xE000000000000006)
#define	PARALLEL_KEY_DSA   UINT64CONST(0xE000000000000007)
#define	PARALLEL_KEY_QUERY_TEXT   UINT64CONST(0xE000000000000008)
#define	PARALLEL_KEY_JIT_INSTRUMENTATION   UINT64CONST(0xE000000000000009)
#define	PARALLEL_KEY_WAL_USAGE   UINT64CONST(0xE00000000000000A)
#define	PARALLEL_TUPLE_QUEUE_SIZE   65536
#define	GetInstrumentationArray(sei)

Typedefs
typedef struct FixedParallelExecutorState	FixedParallelExecutorState
typedef struct ExecParallelEstimateContext	ExecParallelEstimateContext
typedef struct ExecParallelInitializeDSMContext	ExecParallelInitializeDSMContext

Functions
static char *	ExecSerializePlan (Plan *plan, EState *estate)
static bool	ExecParallelEstimate (PlanState *planstate, ExecParallelEstimateContext *e)
static bool	ExecParallelInitializeDSM (PlanState *planstate, ExecParallelInitializeDSMContext *d)
static shm_mq_handle **	ExecParallelSetupTupleQueues (ParallelContext *pcxt, bool reinitialize)
static bool	ExecParallelReInitializeDSM (PlanState *planstate, ParallelContext *pcxt)
static bool	ExecParallelRetrieveInstrumentation (PlanState *planstate, SharedExecutorInstrumentation *instrumentation)
static DestReceiver *	ExecParallelGetReceiver (dsm_segment *seg, shm_toc *toc)
static Size	EstimateParamExecSpace (EState *estate, Bitmapset *params)
static dsa_pointer	SerializeParamExecParams (EState *estate, Bitmapset *params, dsa_area *area)
static void	RestoreParamExecParams (char *start_address, EState *estate)
ParallelExecutorInfo *	ExecInitParallelPlan (PlanState *planstate, EState *estate, Bitmapset *sendParams, int nworkers, int64 tuples_needed)
void	ExecParallelCreateReaders (ParallelExecutorInfo *pei)
void	ExecParallelReinitialize (PlanState *planstate, ParallelExecutorInfo *pei, Bitmapset *sendParams)
static void	ExecParallelRetrieveJitInstrumentation (PlanState *planstate, SharedJitInstrumentation *shared_jit)
void	ExecParallelFinish (ParallelExecutorInfo *pei)
void	ExecParallelCleanup (ParallelExecutorInfo *pei)
static QueryDesc *	ExecParallelGetQueryDesc (shm_toc *toc, DestReceiver *receiver, int instrument_options)
static bool	ExecParallelReportInstrumentation (PlanState *planstate, SharedExecutorInstrumentation *instrumentation)
static bool	ExecParallelInitializeWorker (PlanState *planstate, ParallelWorkerContext *pwcxt)
void	ParallelQueryMain (dsm_segment *seg, shm_toc *toc)

Macro Definition Documentation

GetInstrumentationArray

#define GetInstrumentationArray

(

sei

)

Value:

    (AssertVariableIsOfTypeMacro(sei, SharedExecutorInstrumentation *), \
     (Instrumentation *) (((char *) sei) + sei->instrument_offset))

Definition at line 107 of file execParallel.c.

PARALLEL_KEY_BUFFER_USAGE

#define PARALLEL_KEY_BUFFER_USAGE   UINT64CONST(0xE000000000000004)

Definition at line 61 of file execParallel.c.

PARALLEL_KEY_DSA

#define PARALLEL_KEY_DSA   UINT64CONST(0xE000000000000007)

Definition at line 64 of file execParallel.c.

PARALLEL_KEY_EXECUTOR_FIXED

#define PARALLEL_KEY_EXECUTOR_FIXED   UINT64CONST(0xE000000000000001)

Definition at line 58 of file execParallel.c.

PARALLEL_KEY_INSTRUMENTATION

#define PARALLEL_KEY_INSTRUMENTATION   UINT64CONST(0xE000000000000006)

Definition at line 63 of file execParallel.c.

PARALLEL_KEY_JIT_INSTRUMENTATION

#define PARALLEL_KEY_JIT_INSTRUMENTATION   UINT64CONST(0xE000000000000009)

Definition at line 66 of file execParallel.c.

PARALLEL_KEY_PARAMLISTINFO

#define PARALLEL_KEY_PARAMLISTINFO   UINT64CONST(0xE000000000000003)

Definition at line 60 of file execParallel.c.

PARALLEL_KEY_PLANNEDSTMT

#define PARALLEL_KEY_PLANNEDSTMT   UINT64CONST(0xE000000000000002)

Definition at line 59 of file execParallel.c.

PARALLEL_KEY_QUERY_TEXT

#define PARALLEL_KEY_QUERY_TEXT   UINT64CONST(0xE000000000000008)

Definition at line 65 of file execParallel.c.

PARALLEL_KEY_TUPLE_QUEUE

#define PARALLEL_KEY_TUPLE_QUEUE   UINT64CONST(0xE000000000000005)

Definition at line 62 of file execParallel.c.

PARALLEL_KEY_WAL_USAGE

#define PARALLEL_KEY_WAL_USAGE   UINT64CONST(0xE00000000000000A)

Definition at line 67 of file execParallel.c.

PARALLEL_TUPLE_QUEUE_SIZE

#define PARALLEL_TUPLE_QUEUE_SIZE   65536

Definition at line 69 of file execParallel.c.

Typedef Documentation

ExecParallelEstimateContext

typedef struct ExecParallelEstimateContext ExecParallelEstimateContext

ExecParallelInitializeDSMContext

typedef struct ExecParallelInitializeDSMContext ExecParallelInitializeDSMContext

FixedParallelExecutorState

typedef struct FixedParallelExecutorState FixedParallelExecutorState

Function Documentation

EstimateParamExecSpace()

static Size EstimateParamExecSpace ( EState *  estate, Bitmapset *  params  )

static

Definition at line 320 of file execParallel.c.

{
    int         paramid;
    Size        sz = sizeof(int);
 
    paramid = -1;
    while ((paramid = bms_next_member(params, paramid)) >= 0)
    {
        Oid         typeOid;
        int16       typLen;
        bool        typByVal;
        ParamExecData *prm;
 
        prm = &(estate->es_param_exec_vals[paramid]);
        typeOid = list_nth_oid(estate->es_plannedstmt->paramExecTypes,
                               paramid);
 
        sz = add_size(sz, sizeof(int)); /* space for paramid */
 
        /* space for datum/isnull */
        if (OidIsValid(typeOid))
            get_typlenbyval(typeOid, &typLen, &typByVal);
        else
        {
            /* If no type OID, assume by-value, like copyParamList does. */
            typLen = sizeof(Datum);
            typByVal = true;
        }
        sz = add_size(sz,
                      datumEstimateSpace(prm->value, prm->isnull,
                                         typByVal, typLen));
    }
    return sz;
}

References add_size(), bms_next_member(), datumEstimateSpace(), EState::es_param_exec_vals, EState::es_plannedstmt, get_typlenbyval(), ParamExecData::isnull, list_nth_oid(), OidIsValid, PlannedStmt::paramExecTypes, and ParamExecData::value.

Referenced by SerializeParamExecParams().

ExecInitParallelPlan()

ParallelExecutorInfo * ExecInitParallelPlan	(	PlanState *	planstate,
		EState *	estate,
		Bitmapset *	sendParams,
		int	nworkers,
		int64	tuples_needed
	)

Definition at line 600 of file execParallel.c.

{
    ParallelExecutorInfo *pei;
    ParallelContext *pcxt;
    ExecParallelEstimateContext e;
    ExecParallelInitializeDSMContext d;
    FixedParallelExecutorState *fpes;
    char       *pstmt_data;
    char       *pstmt_space;
    char       *paramlistinfo_space;
    BufferUsage *bufusage_space;
    WalUsage   *walusage_space;
    SharedExecutorInstrumentation *instrumentation = NULL;
    SharedJitInstrumentation *jit_instrumentation = NULL;
    int         pstmt_len;
    int         paramlistinfo_len;
    int         instrumentation_len = 0;
    int         jit_instrumentation_len = 0;
    int         instrument_offset = 0;
    Size        dsa_minsize = dsa_minimum_size();
    char       *query_string;
    int         query_len;
 
    /*
     * Force any initplan outputs that we're going to pass to workers to be
     * evaluated, if they weren't already.
     *
     * For simplicity, we use the EState's per-output-tuple ExprContext here.
     * That risks intra-query memory leakage, since we might pass through here
     * many times before that ExprContext gets reset; but ExecSetParamPlan
     * doesn't normally leak any memory in the context (see its comments), so
     * it doesn't seem worth complicating this function's API to pass it a
     * shorter-lived ExprContext.  This might need to change someday.
     */
    ExecSetParamPlanMulti(sendParams, GetPerTupleExprContext(estate));
 
    /* Allocate object for return value. */
    pei = palloc0(sizeof(ParallelExecutorInfo));
    pei->finished = false;
    pei->planstate = planstate;
 
    /* Fix up and serialize plan to be sent to workers. */
    pstmt_data = ExecSerializePlan(planstate->plan, estate);
 
    /* Create a parallel context. */
    pcxt = CreateParallelContext("postgres", "ParallelQueryMain", nworkers);
    pei->pcxt = pcxt;
 
    /*
     * Before telling the parallel context to create a dynamic shared memory
     * segment, we need to figure out how big it should be.  Estimate space
     * for the various things we need to store.
     */
 
    /* Estimate space for fixed-size state. */
    shm_toc_estimate_chunk(&pcxt->estimator,
                           sizeof(FixedParallelExecutorState));
    shm_toc_estimate_keys(&pcxt->estimator, 1);
 
    /* Estimate space for query text. */
    query_len = strlen(estate->es_sourceText);
    shm_toc_estimate_chunk(&pcxt->estimator, query_len + 1);
    shm_toc_estimate_keys(&pcxt->estimator, 1);
 
    /* Estimate space for serialized PlannedStmt. */
    pstmt_len = strlen(pstmt_data) + 1;
    shm_toc_estimate_chunk(&pcxt->estimator, pstmt_len);
    shm_toc_estimate_keys(&pcxt->estimator, 1);
 
    /* Estimate space for serialized ParamListInfo. */
    paramlistinfo_len = EstimateParamListSpace(estate->es_param_list_info);
    shm_toc_estimate_chunk(&pcxt->estimator, paramlistinfo_len);
    shm_toc_estimate_keys(&pcxt->estimator, 1);
 
    /*
     * Estimate space for BufferUsage.
     *
     * If EXPLAIN is not in use and there are no extensions loaded that care,
     * we could skip this.  But we have no way of knowing whether anyone's
     * looking at pgBufferUsage, so do it unconditionally.
     */
    shm_toc_estimate_chunk(&pcxt->estimator,
                           mul_size(sizeof(BufferUsage), pcxt->nworkers));
    shm_toc_estimate_keys(&pcxt->estimator, 1);
 
    /*
     * Same thing for WalUsage.
     */
    shm_toc_estimate_chunk(&pcxt->estimator,
                           mul_size(sizeof(WalUsage), pcxt->nworkers));
    shm_toc_estimate_keys(&pcxt->estimator, 1);
 
    /* Estimate space for tuple queues. */
    shm_toc_estimate_chunk(&pcxt->estimator,
                           mul_size(PARALLEL_TUPLE_QUEUE_SIZE, pcxt->nworkers));
    shm_toc_estimate_keys(&pcxt->estimator, 1);
 
    /*
     * Give parallel-aware nodes a chance to add to the estimates, and get a
     * count of how many PlanState nodes there are.
     */
    e.pcxt = pcxt;
    e.nnodes = 0;
    ExecParallelEstimate(planstate, &e);
 
    /* Estimate space for instrumentation, if required. */
    if (estate->es_instrument)
    {
        instrumentation_len =
            offsetof(SharedExecutorInstrumentation, plan_node_id) +
            sizeof(int) * e.nnodes;
        instrumentation_len = MAXALIGN(instrumentation_len);
        instrument_offset = instrumentation_len;
        instrumentation_len +=
            mul_size(sizeof(Instrumentation),
                     mul_size(e.nnodes, nworkers));
        shm_toc_estimate_chunk(&pcxt->estimator, instrumentation_len);
        shm_toc_estimate_keys(&pcxt->estimator, 1);
 
        /* Estimate space for JIT instrumentation, if required. */
        if (estate->es_jit_flags != PGJIT_NONE)
        {
            jit_instrumentation_len =
                offsetof(SharedJitInstrumentation, jit_instr) +
                sizeof(JitInstrumentation) * nworkers;
            shm_toc_estimate_chunk(&pcxt->estimator, jit_instrumentation_len);
            shm_toc_estimate_keys(&pcxt->estimator, 1);
        }
    }
 
    /* Estimate space for DSA area. */
    shm_toc_estimate_chunk(&pcxt->estimator, dsa_minsize);
    shm_toc_estimate_keys(&pcxt->estimator, 1);
 
    /*
     * InitializeParallelDSM() passes the active snapshot to the parallel
     * worker, which uses it to set es_snapshot.  Make sure we don't set
     * es_snapshot differently in the child.
     */
    Assert(GetActiveSnapshot() == estate->es_snapshot);
 
    /* Everyone's had a chance to ask for space, so now create the DSM. */
    InitializeParallelDSM(pcxt);
 
    /*
     * OK, now we have a dynamic shared memory segment, and it should be big
     * enough to store all of the data we estimated we would want to put into
     * it, plus whatever general stuff (not specifically executor-related) the
     * ParallelContext itself needs to store there.  None of the space we
     * asked for has been allocated or initialized yet, though, so do that.
     */
 
    /* Store fixed-size state. */
    fpes = shm_toc_allocate(pcxt->toc, sizeof(FixedParallelExecutorState));
    fpes->tuples_needed = tuples_needed;
    fpes->param_exec = InvalidDsaPointer;
    fpes->eflags = estate->es_top_eflags;
    fpes->jit_flags = estate->es_jit_flags;
    shm_toc_insert(pcxt->toc, PARALLEL_KEY_EXECUTOR_FIXED, fpes);
 
    /* Store query string */
    query_string = shm_toc_allocate(pcxt->toc, query_len + 1);
    memcpy(query_string, estate->es_sourceText, query_len + 1);
    shm_toc_insert(pcxt->toc, PARALLEL_KEY_QUERY_TEXT, query_string);
 
    /* Store serialized PlannedStmt. */
    pstmt_space = shm_toc_allocate(pcxt->toc, pstmt_len);
    memcpy(pstmt_space, pstmt_data, pstmt_len);
    shm_toc_insert(pcxt->toc, PARALLEL_KEY_PLANNEDSTMT, pstmt_space);
 
    /* Store serialized ParamListInfo. */
    paramlistinfo_space = shm_toc_allocate(pcxt->toc, paramlistinfo_len);
    shm_toc_insert(pcxt->toc, PARALLEL_KEY_PARAMLISTINFO, paramlistinfo_space);
    SerializeParamList(estate->es_param_list_info, &paramlistinfo_space);
 
    /* Allocate space for each worker's BufferUsage; no need to initialize. */
    bufusage_space = shm_toc_allocate(pcxt->toc,
                                      mul_size(sizeof(BufferUsage), pcxt->nworkers));
    shm_toc_insert(pcxt->toc, PARALLEL_KEY_BUFFER_USAGE, bufusage_space);
    pei->buffer_usage = bufusage_space;
 
    /* Same for WalUsage. */
    walusage_space = shm_toc_allocate(pcxt->toc,
                                      mul_size(sizeof(WalUsage), pcxt->nworkers));
    shm_toc_insert(pcxt->toc, PARALLEL_KEY_WAL_USAGE, walusage_space);
    pei->wal_usage = walusage_space;
 
    /* Set up the tuple queues that the workers will write into. */
    pei->tqueue = ExecParallelSetupTupleQueues(pcxt, false);
 
    /* We don't need the TupleQueueReaders yet, though. */
    pei->reader = NULL;
 
    /*
     * If instrumentation options were supplied, allocate space for the data.
     * It only gets partially initialized here; the rest happens during
     * ExecParallelInitializeDSM.
     */
    if (estate->es_instrument)
    {
        Instrumentation *instrument;
        int         i;
 
        instrumentation = shm_toc_allocate(pcxt->toc, instrumentation_len);
        instrumentation->instrument_options = estate->es_instrument;
        instrumentation->instrument_offset = instrument_offset;
        instrumentation->num_workers = nworkers;
        instrumentation->num_plan_nodes = e.nnodes;
        instrument = GetInstrumentationArray(instrumentation);
        for (i = 0; i < nworkers * e.nnodes; ++i)
            InstrInit(&instrument[i], estate->es_instrument);
        shm_toc_insert(pcxt->toc, PARALLEL_KEY_INSTRUMENTATION,
                       instrumentation);
        pei->instrumentation = instrumentation;
 
        if (estate->es_jit_flags != PGJIT_NONE)
        {
            jit_instrumentation = shm_toc_allocate(pcxt->toc,
                                                   jit_instrumentation_len);
            jit_instrumentation->num_workers = nworkers;
            memset(jit_instrumentation->jit_instr, 0,
                   sizeof(JitInstrumentation) * nworkers);
            shm_toc_insert(pcxt->toc, PARALLEL_KEY_JIT_INSTRUMENTATION,
                           jit_instrumentation);
            pei->jit_instrumentation = jit_instrumentation;
        }
    }
 
    /*
     * Create a DSA area that can be used by the leader and all workers.
     * (However, if we failed to create a DSM and are using private memory
     * instead, then skip this.)
     */
    if (pcxt->seg != NULL)
    {
        char       *area_space;
 
        area_space = shm_toc_allocate(pcxt->toc, dsa_minsize);
        shm_toc_insert(pcxt->toc, PARALLEL_KEY_DSA, area_space);
        pei->area = dsa_create_in_place(area_space, dsa_minsize,
                                        LWTRANCHE_PARALLEL_QUERY_DSA,
                                        pcxt->seg);
 
        /*
         * Serialize parameters, if any, using DSA storage.  We don't dare use
         * the main parallel query DSM for this because we might relaunch
         * workers after the values have changed (and thus the amount of
         * storage required has changed).
         */
        if (!bms_is_empty(sendParams))
        {
            pei->param_exec = SerializeParamExecParams(estate, sendParams,
                                                       pei->area);
            fpes->param_exec = pei->param_exec;
        }
    }
 
    /*
     * Give parallel-aware nodes a chance to initialize their shared data.
     * This also initializes the elements of instrumentation->ps_instrument,
     * if it exists.
     */
    d.pcxt = pcxt;
    d.instrumentation = instrumentation;
    d.nnodes = 0;
 
    /* Install our DSA area while initializing the plan. */
    estate->es_query_dsa = pei->area;
    ExecParallelInitializeDSM(planstate, &d);
    estate->es_query_dsa = NULL;
 
    /*
     * Make sure that the world hasn't shifted under our feet.  This could
     * probably just be an Assert(), but let's be conservative for now.
     */
    if (e.nnodes != d.nnodes)
        elog(ERROR, "inconsistent count of PlanState nodes");
 
    /* OK, we're ready to rock and roll. */
    return pei;
}

References ParallelExecutorInfo::area, Assert(), bms_is_empty, ParallelExecutorInfo::buffer_usage, CreateParallelContext(), dsa_create_in_place, dsa_minimum_size(), FixedParallelExecutorState::eflags, elog, ERROR, EState::es_instrument, EState::es_jit_flags, EState::es_param_list_info, EState::es_query_dsa, EState::es_snapshot, EState::es_sourceText, EState::es_top_eflags, EstimateParamListSpace(), ParallelContext::estimator, ExecParallelEstimate(), ExecParallelInitializeDSM(), ExecParallelSetupTupleQueues(), ExecSerializePlan(), ExecSetParamPlanMulti(), ParallelExecutorInfo::finished, GetActiveSnapshot(), GetInstrumentationArray, GetPerTupleExprContext, i, InitializeParallelDSM(), InstrInit(), SharedExecutorInstrumentation::instrument_offset, SharedExecutorInstrumentation::instrument_options, ExecParallelInitializeDSMContext::instrumentation, ParallelExecutorInfo::instrumentation, InvalidDsaPointer, FixedParallelExecutorState::jit_flags, SharedJitInstrumentation::jit_instr, ParallelExecutorInfo::jit_instrumentation, MAXALIGN, mul_size(), ExecParallelInitializeDSMContext::nnodes, SharedExecutorInstrumentation::num_plan_nodes, SharedExecutorInstrumentation::num_workers, SharedJitInstrumentation::num_workers, ParallelContext::nworkers, palloc0(), PARALLEL_KEY_BUFFER_USAGE, PARALLEL_KEY_DSA, PARALLEL_KEY_EXECUTOR_FIXED, PARALLEL_KEY_INSTRUMENTATION, PARALLEL_KEY_JIT_INSTRUMENTATION, PARALLEL_KEY_PARAMLISTINFO, PARALLEL_KEY_PLANNEDSTMT, PARALLEL_KEY_QUERY_TEXT, PARALLEL_KEY_WAL_USAGE, PARALLEL_TUPLE_QUEUE_SIZE, FixedParallelExecutorState::param_exec, ParallelExecutorInfo::param_exec, ExecParallelInitializeDSMContext::pcxt, ParallelExecutorInfo::pcxt, PGJIT_NONE, PlanState::plan, ParallelExecutorInfo::planstate, ParallelExecutorInfo::reader, ParallelContext::seg, SerializeParamExecParams(), SerializeParamList(), shm_toc_allocate(), shm_toc_estimate_chunk, shm_toc_estimate_keys, shm_toc_insert(), ParallelContext::toc, ParallelExecutorInfo::tqueue, FixedParallelExecutorState::tuples_needed, and ParallelExecutorInfo::wal_usage.

Referenced by ExecGather(), and ExecGatherMerge().

ExecParallelCleanup()

void ExecParallelCleanup

(

ParallelExecutorInfo *

pei

)

Definition at line 1210 of file execParallel.c.

{
    /* Accumulate instrumentation, if any. */
    if (pei->instrumentation)
        ExecParallelRetrieveInstrumentation(pei->planstate,
                                            pei->instrumentation);
 
    /* Accumulate JIT instrumentation, if any. */
    if (pei->jit_instrumentation)
        ExecParallelRetrieveJitInstrumentation(pei->planstate,
                                               pei->jit_instrumentation);
 
    /* Free any serialized parameters. */
    if (DsaPointerIsValid(pei->param_exec))
    {
        dsa_free(pei->area, pei->param_exec);
        pei->param_exec = InvalidDsaPointer;
    }
    if (pei->area != NULL)
    {
        dsa_detach(pei->area);
        pei->area = NULL;
    }
    if (pei->pcxt != NULL)
    {
        DestroyParallelContext(pei->pcxt);
        pei->pcxt = NULL;
    }
    pfree(pei);
}

References ParallelExecutorInfo::area, DestroyParallelContext(), dsa_detach(), dsa_free(), DsaPointerIsValid, ExecParallelRetrieveInstrumentation(), ExecParallelRetrieveJitInstrumentation(), ParallelExecutorInfo::instrumentation, InvalidDsaPointer, ParallelExecutorInfo::jit_instrumentation, ParallelExecutorInfo::param_exec, ParallelExecutorInfo::pcxt, pfree(), and ParallelExecutorInfo::planstate.

Referenced by ExecShutdownGather(), and ExecShutdownGatherMerge().

ExecParallelCreateReaders()

void ExecParallelCreateReaders

(

ParallelExecutorInfo *

pei

)

Definition at line 891 of file execParallel.c.

{
    int         nworkers = pei->pcxt->nworkers_launched;
    int         i;
 
    Assert(pei->reader == NULL);
 
    if (nworkers > 0)
    {
        pei->reader = (TupleQueueReader **)
            palloc(nworkers * sizeof(TupleQueueReader *));
 
        for (i = 0; i < nworkers; i++)
        {
            shm_mq_set_handle(pei->tqueue[i],
                              pei->pcxt->worker[i].bgwhandle);
            pei->reader[i] = CreateTupleQueueReader(pei->tqueue[i]);
        }
    }
}

References Assert(), ParallelWorkerInfo::bgwhandle, CreateTupleQueueReader(), i, ParallelContext::nworkers_launched, palloc(), ParallelExecutorInfo::pcxt, ParallelExecutorInfo::reader, shm_mq_set_handle(), ParallelExecutorInfo::tqueue, and ParallelContext::worker.

Referenced by ExecGather(), and ExecGatherMerge().

ExecParallelEstimate()

static bool ExecParallelEstimate ( PlanState *  planstate, ExecParallelEstimateContext *  e  )

static

Definition at line 234 of file execParallel.c.

{
    if (planstate == NULL)
        return false;
 
    /* Count this node. */
    e->nnodes++;
 
    switch (nodeTag(planstate))
    {
        case T_SeqScanState:
            if (planstate->plan->parallel_aware)
                ExecSeqScanEstimate((SeqScanState *) planstate,
                                    e->pcxt);
            break;
        case T_IndexScanState:
            /* even when not parallel-aware, for EXPLAIN ANALYZE */
            ExecIndexScanEstimate((IndexScanState *) planstate,
                                  e->pcxt);
            break;
        case T_IndexOnlyScanState:
            /* even when not parallel-aware, for EXPLAIN ANALYZE */
            ExecIndexOnlyScanEstimate((IndexOnlyScanState *) planstate,
                                      e->pcxt);
            break;
        case T_BitmapIndexScanState:
            /* even when not parallel-aware, for EXPLAIN ANALYZE */
            ExecBitmapIndexScanEstimate((BitmapIndexScanState *) planstate,
                                        e->pcxt);
            break;
        case T_ForeignScanState:
            if (planstate->plan->parallel_aware)
                ExecForeignScanEstimate((ForeignScanState *) planstate,
                                        e->pcxt);
            break;
        case T_AppendState:
            if (planstate->plan->parallel_aware)
                ExecAppendEstimate((AppendState *) planstate,
                                   e->pcxt);
            break;
        case T_CustomScanState:
            if (planstate->plan->parallel_aware)
                ExecCustomScanEstimate((CustomScanState *) planstate,
                                       e->pcxt);
            break;
        case T_BitmapHeapScanState:
            if (planstate->plan->parallel_aware)
                ExecBitmapHeapEstimate((BitmapHeapScanState *) planstate,
                                       e->pcxt);
            break;
        case T_HashJoinState:
            if (planstate->plan->parallel_aware)
                ExecHashJoinEstimate((HashJoinState *) planstate,
                                     e->pcxt);
            break;
        case T_HashState:
            /* even when not parallel-aware, for EXPLAIN ANALYZE */
            ExecHashEstimate((HashState *) planstate, e->pcxt);
            break;
        case T_SortState:
            /* even when not parallel-aware, for EXPLAIN ANALYZE */
            ExecSortEstimate((SortState *) planstate, e->pcxt);
            break;
        case T_IncrementalSortState:
            /* even when not parallel-aware, for EXPLAIN ANALYZE */
            ExecIncrementalSortEstimate((IncrementalSortState *) planstate, e->pcxt);
            break;
        case T_AggState:
            /* even when not parallel-aware, for EXPLAIN ANALYZE */
            ExecAggEstimate((AggState *) planstate, e->pcxt);
            break;
        case T_MemoizeState:
            /* even when not parallel-aware, for EXPLAIN ANALYZE */
            ExecMemoizeEstimate((MemoizeState *) planstate, e->pcxt);
            break;
        default:
            break;
    }
 
    return planstate_tree_walker(planstate, ExecParallelEstimate, e);
}

References ExecAggEstimate(), ExecAppendEstimate(), ExecBitmapHeapEstimate(), ExecBitmapIndexScanEstimate(), ExecCustomScanEstimate(), ExecForeignScanEstimate(), ExecHashEstimate(), ExecHashJoinEstimate(), ExecIncrementalSortEstimate(), ExecIndexOnlyScanEstimate(), ExecIndexScanEstimate(), ExecMemoizeEstimate(), ExecParallelEstimate(), ExecSeqScanEstimate(), ExecSortEstimate(), nodeTag, Plan::parallel_aware, PlanState::plan, and planstate_tree_walker.

Referenced by ExecInitParallelPlan(), and ExecParallelEstimate().

ExecParallelFinish()

void ExecParallelFinish

(

ParallelExecutorInfo *

pei

)

Definition at line 1157 of file execParallel.c.

{
    int         nworkers = pei->pcxt->nworkers_launched;
    int         i;
 
    /* Make this be a no-op if called twice in a row. */
    if (pei->finished)
        return;
 
    /*
     * Detach from tuple queues ASAP, so that any still-active workers will
     * notice that no further results are wanted.
     */
    if (pei->tqueue != NULL)
    {
        for (i = 0; i < nworkers; i++)
            shm_mq_detach(pei->tqueue[i]);
        pfree(pei->tqueue);
        pei->tqueue = NULL;
    }
 
    /*
     * While we're waiting for the workers to finish, let's get rid of the
     * tuple queue readers.  (Any other local cleanup could be done here too.)
     */
    if (pei->reader != NULL)
    {
        for (i = 0; i < nworkers; i++)
            DestroyTupleQueueReader(pei->reader[i]);
        pfree(pei->reader);
        pei->reader = NULL;
    }
 
    /* Now wait for the workers to finish. */
    WaitForParallelWorkersToFinish(pei->pcxt);
 
    /*
     * Next, accumulate buffer/WAL usage.  (This must wait for the workers to
     * finish, or we might get incomplete data.)
     */
    for (i = 0; i < nworkers; i++)
        InstrAccumParallelQuery(&pei->buffer_usage[i], &pei->wal_usage[i]);
 
    pei->finished = true;
}

References ParallelExecutorInfo::buffer_usage, DestroyTupleQueueReader(), ParallelExecutorInfo::finished, i, InstrAccumParallelQuery(), ParallelContext::nworkers_launched, ParallelExecutorInfo::pcxt, pfree(), ParallelExecutorInfo::reader, shm_mq_detach(), ParallelExecutorInfo::tqueue, WaitForParallelWorkersToFinish(), and ParallelExecutorInfo::wal_usage.

Referenced by ExecShutdownGatherMergeWorkers(), and ExecShutdownGatherWorkers().

ExecParallelGetQueryDesc()

static QueryDesc * ExecParallelGetQueryDesc ( shm_toc *  toc, DestReceiver *  receiver, int  instrument_options  )

static

Definition at line 1262 of file execParallel.c.

{
    char       *pstmtspace;
    char       *paramspace;
    PlannedStmt *pstmt;
    ParamListInfo paramLI;
    char       *queryString;
 
    /* Get the query string from shared memory */
    queryString = shm_toc_lookup(toc, PARALLEL_KEY_QUERY_TEXT, false);
 
    /* Reconstruct leader-supplied PlannedStmt. */
    pstmtspace = shm_toc_lookup(toc, PARALLEL_KEY_PLANNEDSTMT, false);
    pstmt = (PlannedStmt *) stringToNode(pstmtspace);
 
    /* Reconstruct ParamListInfo. */
    paramspace = shm_toc_lookup(toc, PARALLEL_KEY_PARAMLISTINFO, false);
    paramLI = RestoreParamList(&paramspace);
 
    /* Create a QueryDesc for the query. */
    return CreateQueryDesc(pstmt,
                           queryString,
                           GetActiveSnapshot(), InvalidSnapshot,
                           receiver, paramLI, NULL, instrument_options);
}

References CreateQueryDesc(), GetActiveSnapshot(), InvalidSnapshot, PARALLEL_KEY_PARAMLISTINFO, PARALLEL_KEY_PLANNEDSTMT, PARALLEL_KEY_QUERY_TEXT, RestoreParamList(), shm_toc_lookup(), and stringToNode().

Referenced by ParallelQueryMain().

ExecParallelGetReceiver()

static DestReceiver * ExecParallelGetReceiver ( dsm_segment *  seg, shm_toc *  toc  )

static

Definition at line 1246 of file execParallel.c.

{
    char       *mqspace;
    shm_mq     *mq;
 
    mqspace = shm_toc_lookup(toc, PARALLEL_KEY_TUPLE_QUEUE, false);
    mqspace += ParallelWorkerNumber * PARALLEL_TUPLE_QUEUE_SIZE;
    mq = (shm_mq *) mqspace;
    shm_mq_set_sender(mq, MyProc);
    return CreateTupleQueueDestReceiver(shm_mq_attach(mq, seg, NULL));
}

References CreateTupleQueueDestReceiver(), MyProc, PARALLEL_KEY_TUPLE_QUEUE, PARALLEL_TUPLE_QUEUE_SIZE, ParallelWorkerNumber, shm_mq_attach(), shm_mq_set_sender(), and shm_toc_lookup().

Referenced by ParallelQueryMain().

ExecParallelInitializeDSM()

static bool ExecParallelInitializeDSM ( PlanState *  planstate, ExecParallelInitializeDSMContext *  d  )

static

Definition at line 448 of file execParallel.c.

{
    if (planstate == NULL)
        return false;
 
    /* If instrumentation is enabled, initialize slot for this node. */
    if (d->instrumentation != NULL)
        d->instrumentation->plan_node_id[d->nnodes] =
            planstate->plan->plan_node_id;
 
    /* Count this node. */
    d->nnodes++;
 
    /*
     * Call initializers for DSM-using plan nodes.
     *
     * Most plan nodes won't do anything here, but plan nodes that allocated
     * DSM may need to initialize shared state in the DSM before parallel
     * workers are launched.  They can allocate the space they previously
     * estimated using shm_toc_allocate, and add the keys they previously
     * estimated using shm_toc_insert, in each case targeting pcxt->toc.
     */
    switch (nodeTag(planstate))
    {
        case T_SeqScanState:
            if (planstate->plan->parallel_aware)
                ExecSeqScanInitializeDSM((SeqScanState *) planstate,
                                         d->pcxt);
            break;
        case T_IndexScanState:
            /* even when not parallel-aware, for EXPLAIN ANALYZE */
            ExecIndexScanInitializeDSM((IndexScanState *) planstate, d->pcxt);
            break;
        case T_IndexOnlyScanState:
            /* even when not parallel-aware, for EXPLAIN ANALYZE */
            ExecIndexOnlyScanInitializeDSM((IndexOnlyScanState *) planstate,
                                           d->pcxt);
            break;
        case T_BitmapIndexScanState:
            /* even when not parallel-aware, for EXPLAIN ANALYZE */
            ExecBitmapIndexScanInitializeDSM((BitmapIndexScanState *) planstate, d->pcxt);
            break;
        case T_ForeignScanState:
            if (planstate->plan->parallel_aware)
                ExecForeignScanInitializeDSM((ForeignScanState *) planstate,
                                             d->pcxt);
            break;
        case T_AppendState:
            if (planstate->plan->parallel_aware)
                ExecAppendInitializeDSM((AppendState *) planstate,
                                        d->pcxt);
            break;
        case T_CustomScanState:
            if (planstate->plan->parallel_aware)
                ExecCustomScanInitializeDSM((CustomScanState *) planstate,
                                            d->pcxt);
            break;
        case T_BitmapHeapScanState:
            if (planstate->plan->parallel_aware)
                ExecBitmapHeapInitializeDSM((BitmapHeapScanState *) planstate,
                                            d->pcxt);
            break;
        case T_HashJoinState:
            if (planstate->plan->parallel_aware)
                ExecHashJoinInitializeDSM((HashJoinState *) planstate,
                                          d->pcxt);
            break;
        case T_HashState:
            /* even when not parallel-aware, for EXPLAIN ANALYZE */
            ExecHashInitializeDSM((HashState *) planstate, d->pcxt);
            break;
        case T_SortState:
            /* even when not parallel-aware, for EXPLAIN ANALYZE */
            ExecSortInitializeDSM((SortState *) planstate, d->pcxt);
            break;
        case T_IncrementalSortState:
            /* even when not parallel-aware, for EXPLAIN ANALYZE */
            ExecIncrementalSortInitializeDSM((IncrementalSortState *) planstate, d->pcxt);
            break;
        case T_AggState:
            /* even when not parallel-aware, for EXPLAIN ANALYZE */
            ExecAggInitializeDSM((AggState *) planstate, d->pcxt);
            break;
        case T_MemoizeState:
            /* even when not parallel-aware, for EXPLAIN ANALYZE */
            ExecMemoizeInitializeDSM((MemoizeState *) planstate, d->pcxt);
            break;
        default:
            break;
    }
 
    return planstate_tree_walker(planstate, ExecParallelInitializeDSM, d);
}

References ExecAggInitializeDSM(), ExecAppendInitializeDSM(), ExecBitmapHeapInitializeDSM(), ExecBitmapIndexScanInitializeDSM(), ExecCustomScanInitializeDSM(), ExecForeignScanInitializeDSM(), ExecHashInitializeDSM(), ExecHashJoinInitializeDSM(), ExecIncrementalSortInitializeDSM(), ExecIndexOnlyScanInitializeDSM(), ExecIndexScanInitializeDSM(), ExecMemoizeInitializeDSM(), ExecParallelInitializeDSM(), ExecSeqScanInitializeDSM(), ExecSortInitializeDSM(), ExecParallelInitializeDSMContext::instrumentation, ExecParallelInitializeDSMContext::nnodes, nodeTag, Plan::parallel_aware, ExecParallelInitializeDSMContext::pcxt, PlanState::plan, SharedExecutorInstrumentation::plan_node_id, Plan::plan_node_id, and planstate_tree_walker.

Referenced by ExecInitParallelPlan(), and ExecParallelInitializeDSM().

ExecParallelInitializeWorker()

static bool ExecParallelInitializeWorker ( PlanState *  planstate, ParallelWorkerContext *  pwcxt  )

static

Definition at line 1335 of file execParallel.c.

{
    if (planstate == NULL)
        return false;
 
    switch (nodeTag(planstate))
    {
        case T_SeqScanState:
            if (planstate->plan->parallel_aware)
                ExecSeqScanInitializeWorker((SeqScanState *) planstate, pwcxt);
            break;
        case T_IndexScanState:
            /* even when not parallel-aware, for EXPLAIN ANALYZE */
            ExecIndexScanInitializeWorker((IndexScanState *) planstate, pwcxt);
            break;
        case T_IndexOnlyScanState:
            /* even when not parallel-aware, for EXPLAIN ANALYZE */
            ExecIndexOnlyScanInitializeWorker((IndexOnlyScanState *) planstate,
                                              pwcxt);
            break;
        case T_BitmapIndexScanState:
            /* even when not parallel-aware, for EXPLAIN ANALYZE */
            ExecBitmapIndexScanInitializeWorker((BitmapIndexScanState *) planstate,
                                                pwcxt);
            break;
        case T_ForeignScanState:
            if (planstate->plan->parallel_aware)
                ExecForeignScanInitializeWorker((ForeignScanState *) planstate,
                                                pwcxt);
            break;
        case T_AppendState:
            if (planstate->plan->parallel_aware)
                ExecAppendInitializeWorker((AppendState *) planstate, pwcxt);
            break;
        case T_CustomScanState:
            if (planstate->plan->parallel_aware)
                ExecCustomScanInitializeWorker((CustomScanState *) planstate,
                                               pwcxt);
            break;
        case T_BitmapHeapScanState:
            if (planstate->plan->parallel_aware)
                ExecBitmapHeapInitializeWorker((BitmapHeapScanState *) planstate,
                                               pwcxt);
            break;
        case T_HashJoinState:
            if (planstate->plan->parallel_aware)
                ExecHashJoinInitializeWorker((HashJoinState *) planstate,
                                             pwcxt);
            break;
        case T_HashState:
            /* even when not parallel-aware, for EXPLAIN ANALYZE */
            ExecHashInitializeWorker((HashState *) planstate, pwcxt);
            break;
        case T_SortState:
            /* even when not parallel-aware, for EXPLAIN ANALYZE */
            ExecSortInitializeWorker((SortState *) planstate, pwcxt);
            break;
        case T_IncrementalSortState:
            /* even when not parallel-aware, for EXPLAIN ANALYZE */
            ExecIncrementalSortInitializeWorker((IncrementalSortState *) planstate,
                                                pwcxt);
            break;
        case T_AggState:
            /* even when not parallel-aware, for EXPLAIN ANALYZE */
            ExecAggInitializeWorker((AggState *) planstate, pwcxt);
            break;
        case T_MemoizeState:
            /* even when not parallel-aware, for EXPLAIN ANALYZE */
            ExecMemoizeInitializeWorker((MemoizeState *) planstate, pwcxt);
            break;
        default:
            break;
    }
 
    return planstate_tree_walker(planstate, ExecParallelInitializeWorker,
                                 pwcxt);
}

References ExecAggInitializeWorker(), ExecAppendInitializeWorker(), ExecBitmapHeapInitializeWorker(), ExecBitmapIndexScanInitializeWorker(), ExecCustomScanInitializeWorker(), ExecForeignScanInitializeWorker(), ExecHashInitializeWorker(), ExecHashJoinInitializeWorker(), ExecIncrementalSortInitializeWorker(), ExecIndexOnlyScanInitializeWorker(), ExecIndexScanInitializeWorker(), ExecMemoizeInitializeWorker(), ExecParallelInitializeWorker(), ExecSeqScanInitializeWorker(), ExecSortInitializeWorker(), nodeTag, Plan::parallel_aware, PlanState::plan, and planstate_tree_walker.

Referenced by ExecParallelInitializeWorker(), and ParallelQueryMain().

ExecParallelReinitialize()

void ExecParallelReinitialize	(	PlanState *	planstate,
		ParallelExecutorInfo *	pei,
		Bitmapset *	sendParams
	)

Definition at line 917 of file execParallel.c.

{
    EState     *estate = planstate->state;
    FixedParallelExecutorState *fpes;
 
    /* Old workers must already be shut down */
    Assert(pei->finished);
 
    /*
     * Force any initplan outputs that we're going to pass to workers to be
     * evaluated, if they weren't already (see comments in
     * ExecInitParallelPlan).
     */
    ExecSetParamPlanMulti(sendParams, GetPerTupleExprContext(estate));
 
    ReinitializeParallelDSM(pei->pcxt);
    pei->tqueue = ExecParallelSetupTupleQueues(pei->pcxt, true);
    pei->reader = NULL;
    pei->finished = false;
 
    fpes = shm_toc_lookup(pei->pcxt->toc, PARALLEL_KEY_EXECUTOR_FIXED, false);
 
    /* Free any serialized parameters from the last round. */
    if (DsaPointerIsValid(fpes->param_exec))
    {
        dsa_free(pei->area, fpes->param_exec);
        fpes->param_exec = InvalidDsaPointer;
    }
 
    /* Serialize current parameter values if required. */
    if (!bms_is_empty(sendParams))
    {
        pei->param_exec = SerializeParamExecParams(estate, sendParams,
                                                   pei->area);
        fpes->param_exec = pei->param_exec;
    }
 
    /* Traverse plan tree and let each child node reset associated state. */
    estate->es_query_dsa = pei->area;
    ExecParallelReInitializeDSM(planstate, pei->pcxt);
    estate->es_query_dsa = NULL;
}

References ParallelExecutorInfo::area, Assert(), bms_is_empty, dsa_free(), DsaPointerIsValid, EState::es_query_dsa, ExecParallelReInitializeDSM(), ExecParallelSetupTupleQueues(), ExecSetParamPlanMulti(), ParallelExecutorInfo::finished, GetPerTupleExprContext, InvalidDsaPointer, PARALLEL_KEY_EXECUTOR_FIXED, FixedParallelExecutorState::param_exec, ParallelExecutorInfo::param_exec, ParallelExecutorInfo::pcxt, ParallelExecutorInfo::reader, ReinitializeParallelDSM(), SerializeParamExecParams(), shm_toc_lookup(), PlanState::state, ParallelContext::toc, and ParallelExecutorInfo::tqueue.

Referenced by ExecGather(), and ExecGatherMerge().

ExecParallelReInitializeDSM()

static bool ExecParallelReInitializeDSM ( PlanState *  planstate, ParallelContext *  pcxt  )

static

Definition at line 966 of file execParallel.c.

{
    if (planstate == NULL)
        return false;
 
    /*
     * Call reinitializers for DSM-using plan nodes.
     */
    switch (nodeTag(planstate))
    {
        case T_SeqScanState:
            if (planstate->plan->parallel_aware)
                ExecSeqScanReInitializeDSM((SeqScanState *) planstate,
                                           pcxt);
            break;
        case T_IndexScanState:
            if (planstate->plan->parallel_aware)
                ExecIndexScanReInitializeDSM((IndexScanState *) planstate,
                                             pcxt);
            break;
        case T_IndexOnlyScanState:
            if (planstate->plan->parallel_aware)
                ExecIndexOnlyScanReInitializeDSM((IndexOnlyScanState *) planstate,
                                                 pcxt);
            break;
        case T_ForeignScanState:
            if (planstate->plan->parallel_aware)
                ExecForeignScanReInitializeDSM((ForeignScanState *) planstate,
                                               pcxt);
            break;
        case T_AppendState:
            if (planstate->plan->parallel_aware)
                ExecAppendReInitializeDSM((AppendState *) planstate, pcxt);
            break;
        case T_CustomScanState:
            if (planstate->plan->parallel_aware)
                ExecCustomScanReInitializeDSM((CustomScanState *) planstate,
                                              pcxt);
            break;
        case T_BitmapHeapScanState:
            if (planstate->plan->parallel_aware)
                ExecBitmapHeapReInitializeDSM((BitmapHeapScanState *) planstate,
                                              pcxt);
            break;
        case T_HashJoinState:
            if (planstate->plan->parallel_aware)
                ExecHashJoinReInitializeDSM((HashJoinState *) planstate,
                                            pcxt);
            break;
        case T_BitmapIndexScanState:
        case T_HashState:
        case T_SortState:
        case T_IncrementalSortState:
        case T_MemoizeState:
            /* these nodes have DSM state, but no reinitialization is required */
            break;
 
        default:
            break;
    }
 
    return planstate_tree_walker(planstate, ExecParallelReInitializeDSM, pcxt);
}

References ExecAppendReInitializeDSM(), ExecBitmapHeapReInitializeDSM(), ExecCustomScanReInitializeDSM(), ExecForeignScanReInitializeDSM(), ExecHashJoinReInitializeDSM(), ExecIndexOnlyScanReInitializeDSM(), ExecIndexScanReInitializeDSM(), ExecParallelReInitializeDSM(), ExecSeqScanReInitializeDSM(), nodeTag, Plan::parallel_aware, PlanState::plan, and planstate_tree_walker.

Referenced by ExecParallelReinitialize(), and ExecParallelReInitializeDSM().

ExecParallelReportInstrumentation()

static bool ExecParallelReportInstrumentation ( PlanState *  planstate, SharedExecutorInstrumentation *  instrumentation  )

static

Definition at line 1294 of file execParallel.c.

{
    int         i;
    int         plan_node_id = planstate->plan->plan_node_id;
    Instrumentation *instrument;
 
    InstrEndLoop(planstate->instrument);
 
    /*
     * If we shuffled the plan_node_id values in ps_instrument into sorted
     * order, we could use binary search here.  This might matter someday if
     * we're pushing down sufficiently large plan trees.  For now, do it the
     * slow, dumb way.
     */
    for (i = 0; i < instrumentation->num_plan_nodes; ++i)
        if (instrumentation->plan_node_id[i] == plan_node_id)
            break;
    if (i >= instrumentation->num_plan_nodes)
        elog(ERROR, "plan node %d not found", plan_node_id);
 
    /*
     * Add our statistics to the per-node, per-worker totals.  It's possible
     * that this could happen more than once if we relaunched workers.
     */
    instrument = GetInstrumentationArray(instrumentation);
    instrument += i * instrumentation->num_workers;
    Assert(IsParallelWorker());
    Assert(ParallelWorkerNumber < instrumentation->num_workers);
    InstrAggNode(&instrument[ParallelWorkerNumber], planstate->instrument);
 
    return planstate_tree_walker(planstate, ExecParallelReportInstrumentation,
                                 instrumentation);
}

References Assert(), elog, ERROR, ExecParallelReportInstrumentation(), GetInstrumentationArray, i, InstrAggNode(), InstrEndLoop(), PlanState::instrument, IsParallelWorker, SharedExecutorInstrumentation::num_plan_nodes, SharedExecutorInstrumentation::num_workers, ParallelWorkerNumber, PlanState::plan, SharedExecutorInstrumentation::plan_node_id, Plan::plan_node_id, and planstate_tree_walker.

Referenced by ExecParallelReportInstrumentation(), and ParallelQueryMain().

ExecParallelRetrieveInstrumentation()

static bool ExecParallelRetrieveInstrumentation ( PlanState *  planstate, SharedExecutorInstrumentation *  instrumentation  )

static

Definition at line 1036 of file execParallel.c.

{
    Instrumentation *instrument;
    int         i;
    int         n;
    int         ibytes;
    int         plan_node_id = planstate->plan->plan_node_id;
    MemoryContext oldcontext;
 
    /* Find the instrumentation for this node. */
    for (i = 0; i < instrumentation->num_plan_nodes; ++i)
        if (instrumentation->plan_node_id[i] == plan_node_id)
            break;
    if (i >= instrumentation->num_plan_nodes)
        elog(ERROR, "plan node %d not found", plan_node_id);
 
    /* Accumulate the statistics from all workers. */
    instrument = GetInstrumentationArray(instrumentation);
    instrument += i * instrumentation->num_workers;
    for (n = 0; n < instrumentation->num_workers; ++n)
        InstrAggNode(planstate->instrument, &instrument[n]);
 
    /*
     * Also store the per-worker detail.
     *
     * Worker instrumentation should be allocated in the same context as the
     * regular instrumentation information, which is the per-query context.
     * Switch into per-query memory context.
     */
    oldcontext = MemoryContextSwitchTo(planstate->state->es_query_cxt);
    ibytes = mul_size(instrumentation->num_workers, sizeof(Instrumentation));
    planstate->worker_instrument =
        palloc(ibytes + offsetof(WorkerInstrumentation, instrument));
    MemoryContextSwitchTo(oldcontext);
 
    planstate->worker_instrument->num_workers = instrumentation->num_workers;
    memcpy(&planstate->worker_instrument->instrument, instrument, ibytes);
 
    /* Perform any node-type-specific work that needs to be done. */
    switch (nodeTag(planstate))
    {
        case T_IndexScanState:
            ExecIndexScanRetrieveInstrumentation((IndexScanState *) planstate);
            break;
        case T_IndexOnlyScanState:
            ExecIndexOnlyScanRetrieveInstrumentation((IndexOnlyScanState *) planstate);
            break;
        case T_BitmapIndexScanState:
            ExecBitmapIndexScanRetrieveInstrumentation((BitmapIndexScanState *) planstate);
            break;
        case T_SortState:
            ExecSortRetrieveInstrumentation((SortState *) planstate);
            break;
        case T_IncrementalSortState:
            ExecIncrementalSortRetrieveInstrumentation((IncrementalSortState *) planstate);
            break;
        case T_HashState:
            ExecHashRetrieveInstrumentation((HashState *) planstate);
            break;
        case T_AggState:
            ExecAggRetrieveInstrumentation((AggState *) planstate);
            break;
        case T_MemoizeState:
            ExecMemoizeRetrieveInstrumentation((MemoizeState *) planstate);
            break;
        case T_BitmapHeapScanState:
            ExecBitmapHeapRetrieveInstrumentation((BitmapHeapScanState *) planstate);
            break;
        default:
            break;
    }
 
    return planstate_tree_walker(planstate, ExecParallelRetrieveInstrumentation,
                                 instrumentation);
}

References elog, ERROR, EState::es_query_cxt, ExecAggRetrieveInstrumentation(), ExecBitmapHeapRetrieveInstrumentation(), ExecBitmapIndexScanRetrieveInstrumentation(), ExecHashRetrieveInstrumentation(), ExecIncrementalSortRetrieveInstrumentation(), ExecIndexOnlyScanRetrieveInstrumentation(), ExecIndexScanRetrieveInstrumentation(), ExecMemoizeRetrieveInstrumentation(), ExecParallelRetrieveInstrumentation(), ExecSortRetrieveInstrumentation(), GetInstrumentationArray, i, InstrAggNode(), WorkerInstrumentation::instrument, PlanState::instrument, MemoryContextSwitchTo(), mul_size(), nodeTag, SharedExecutorInstrumentation::num_plan_nodes, SharedExecutorInstrumentation::num_workers, WorkerInstrumentation::num_workers, palloc(), PlanState::plan, SharedExecutorInstrumentation::plan_node_id, Plan::plan_node_id, planstate_tree_walker, PlanState::state, and PlanState::worker_instrument.

Referenced by ExecParallelCleanup(), and ExecParallelRetrieveInstrumentation().

ExecParallelRetrieveJitInstrumentation()

static void ExecParallelRetrieveJitInstrumentation ( PlanState *  planstate, SharedJitInstrumentation *  shared_jit  )

static

Definition at line 1117 of file execParallel.c.

{
    JitInstrumentation *combined;
    int         ibytes;
 
    int         n;
 
    /*
     * Accumulate worker JIT instrumentation into the combined JIT
     * instrumentation, allocating it if required.
     */
    if (!planstate->state->es_jit_worker_instr)
        planstate->state->es_jit_worker_instr =
            MemoryContextAllocZero(planstate->state->es_query_cxt, sizeof(JitInstrumentation));
    combined = planstate->state->es_jit_worker_instr;
 
    /* Accumulate all the workers' instrumentations. */
    for (n = 0; n < shared_jit->num_workers; ++n)
        InstrJitAgg(combined, &shared_jit->jit_instr[n]);
 
    /*
     * Store the per-worker detail.
     *
     * Similar to ExecParallelRetrieveInstrumentation(), allocate the
     * instrumentation in per-query context.
     */
    ibytes = offsetof(SharedJitInstrumentation, jit_instr)
        + mul_size(shared_jit->num_workers, sizeof(JitInstrumentation));
    planstate->worker_jit_instrument =
        MemoryContextAlloc(planstate->state->es_query_cxt, ibytes);
 
    memcpy(planstate->worker_jit_instrument, shared_jit, ibytes);
}

References EState::es_jit_worker_instr, EState::es_query_cxt, InstrJitAgg(), SharedJitInstrumentation::jit_instr, MemoryContextAlloc(), MemoryContextAllocZero(), mul_size(), SharedJitInstrumentation::num_workers, PlanState::state, and PlanState::worker_jit_instrument.

Referenced by ExecParallelCleanup().

ExecParallelSetupTupleQueues()

static shm_mq_handle ** ExecParallelSetupTupleQueues ( ParallelContext *  pcxt, bool  reinitialize  )

static

Definition at line 548 of file execParallel.c.

{
    shm_mq_handle **responseq;
    char       *tqueuespace;
    int         i;
 
    /* Skip this if no workers. */
    if (pcxt->nworkers == 0)
        return NULL;
 
    /* Allocate memory for shared memory queue handles. */
    responseq = (shm_mq_handle **)
        palloc(pcxt->nworkers * sizeof(shm_mq_handle *));
 
    /*
     * If not reinitializing, allocate space from the DSM for the queues;
     * otherwise, find the already allocated space.
     */
    if (!reinitialize)
        tqueuespace =
            shm_toc_allocate(pcxt->toc,
                             mul_size(PARALLEL_TUPLE_QUEUE_SIZE,
                                      pcxt->nworkers));
    else
        tqueuespace = shm_toc_lookup(pcxt->toc, PARALLEL_KEY_TUPLE_QUEUE, false);
 
    /* Create the queues, and become the receiver for each. */
    for (i = 0; i < pcxt->nworkers; ++i)
    {
        shm_mq     *mq;
 
        mq = shm_mq_create(tqueuespace +
                           ((Size) i) * PARALLEL_TUPLE_QUEUE_SIZE,
                           (Size) PARALLEL_TUPLE_QUEUE_SIZE);
 
        shm_mq_set_receiver(mq, MyProc);
        responseq[i] = shm_mq_attach(mq, pcxt->seg, NULL);
    }
 
    /* Add array of queues to shm_toc, so others can find it. */
    if (!reinitialize)
        shm_toc_insert(pcxt->toc, PARALLEL_KEY_TUPLE_QUEUE, tqueuespace);
 
    /* Return array of handles. */
    return responseq;
}

References i, mul_size(), MyProc, ParallelContext::nworkers, palloc(), PARALLEL_KEY_TUPLE_QUEUE, PARALLEL_TUPLE_QUEUE_SIZE, ParallelContext::seg, shm_mq_attach(), shm_mq_create(), shm_mq_set_receiver(), shm_toc_allocate(), shm_toc_insert(), shm_toc_lookup(), and ParallelContext::toc.

Referenced by ExecInitParallelPlan(), and ExecParallelReinitialize().

ExecSerializePlan()

static char * ExecSerializePlan ( Plan *  plan, EState *  estate  )

static

Definition at line 146 of file execParallel.c.

{
    PlannedStmt *pstmt;
    ListCell   *lc;
 
    /* We can't scribble on the original plan, so make a copy. */
    plan = copyObject(plan);
 
    /*
     * The worker will start its own copy of the executor, and that copy will
     * insert a junk filter if the toplevel node has any resjunk entries. We
     * don't want that to happen, because while resjunk columns shouldn't be
     * sent back to the user, here the tuples are coming back to another
     * backend which may very well need them.  So mutate the target list
     * accordingly.  This is sort of a hack; there might be better ways to do
     * this...
     */
    foreach(lc, plan->targetlist)
    {
        TargetEntry *tle = lfirst_node(TargetEntry, lc);
 
        tle->resjunk = false;
    }
 
    /*
     * Create a dummy PlannedStmt.  Most of the fields don't need to be valid
     * for our purposes, but the worker will need at least a minimal
     * PlannedStmt to start the executor.
     */
    pstmt = makeNode(PlannedStmt);
    pstmt->commandType = CMD_SELECT;
    pstmt->queryId = pgstat_get_my_query_id();
    pstmt->planId = pgstat_get_my_plan_id();
    pstmt->hasReturning = false;
    pstmt->hasModifyingCTE = false;
    pstmt->canSetTag = true;
    pstmt->transientPlan = false;
    pstmt->dependsOnRole = false;
    pstmt->parallelModeNeeded = false;
    pstmt->planTree = plan;
    pstmt->partPruneInfos = estate->es_part_prune_infos;
    pstmt->rtable = estate->es_range_table;
    pstmt->unprunableRelids = estate->es_unpruned_relids;
    pstmt->permInfos = estate->es_rteperminfos;
    pstmt->resultRelations = NIL;
    pstmt->appendRelations = NIL;
    pstmt->planOrigin = PLAN_STMT_INTERNAL;
 
    /*
     * Transfer only parallel-safe subplans, leaving a NULL "hole" in the list
     * for unsafe ones (so that the list indexes of the safe ones are
     * preserved).  This positively ensures that the worker won't try to run,
     * or even do ExecInitNode on, an unsafe subplan.  That's important to
     * protect, eg, non-parallel-aware FDWs from getting into trouble.
     */
    pstmt->subplans = NIL;
    foreach(lc, estate->es_plannedstmt->subplans)
    {
        Plan       *subplan = (Plan *) lfirst(lc);
 
        if (subplan && !subplan->parallel_safe)
            subplan = NULL;
        pstmt->subplans = lappend(pstmt->subplans, subplan);
    }
 
    pstmt->rewindPlanIDs = NULL;
    pstmt->rowMarks = NIL;
    pstmt->relationOids = NIL;
    pstmt->invalItems = NIL;    /* workers can't replan anyway... */
    pstmt->paramExecTypes = estate->es_plannedstmt->paramExecTypes;
    pstmt->utilityStmt = NULL;
    pstmt->stmt_location = -1;
    pstmt->stmt_len = -1;
 
    /* Return serialized copy of our dummy PlannedStmt. */
    return nodeToString(pstmt);
}

References PlannedStmt::appendRelations, PlannedStmt::canSetTag, CMD_SELECT, PlannedStmt::commandType, copyObject, PlannedStmt::dependsOnRole, EState::es_part_prune_infos, EState::es_plannedstmt, EState::es_range_table, EState::es_rteperminfos, EState::es_unpruned_relids, PlannedStmt::hasModifyingCTE, PlannedStmt::hasReturning, PlannedStmt::invalItems, lappend(), lfirst, lfirst_node, makeNode, NIL, nodeToString(), Plan::parallel_safe, PlannedStmt::parallelModeNeeded, PlannedStmt::paramExecTypes, PlannedStmt::partPruneInfos, PlannedStmt::permInfos, pgstat_get_my_plan_id(), pgstat_get_my_query_id(), plan, PLAN_STMT_INTERNAL, PlannedStmt::planId, PlannedStmt::planOrigin, PlannedStmt::planTree, PlannedStmt::queryId, PlannedStmt::relationOids, PlannedStmt::resultRelations, PlannedStmt::rewindPlanIDs, PlannedStmt::rowMarks, PlannedStmt::rtable, PlannedStmt::stmt_len, PlannedStmt::stmt_location, PlannedStmt::subplans, PlannedStmt::transientPlan, PlannedStmt::unprunableRelids, and PlannedStmt::utilityStmt.

Referenced by ExecInitParallelPlan().

ParallelQueryMain()

void ParallelQueryMain	(	dsm_segment *	seg,
		shm_toc *	toc
	)

Definition at line 1430 of file execParallel.c.

{
    FixedParallelExecutorState *fpes;
    BufferUsage *buffer_usage;
    WalUsage   *wal_usage;
    DestReceiver *receiver;
    QueryDesc  *queryDesc;
    SharedExecutorInstrumentation *instrumentation;
    SharedJitInstrumentation *jit_instrumentation;
    int         instrument_options = 0;
    void       *area_space;
    dsa_area   *area;
    ParallelWorkerContext pwcxt;
 
    /* Get fixed-size state. */
    fpes = shm_toc_lookup(toc, PARALLEL_KEY_EXECUTOR_FIXED, false);
 
    /* Set up DestReceiver, SharedExecutorInstrumentation, and QueryDesc. */
    receiver = ExecParallelGetReceiver(seg, toc);
    instrumentation = shm_toc_lookup(toc, PARALLEL_KEY_INSTRUMENTATION, true);
    if (instrumentation != NULL)
        instrument_options = instrumentation->instrument_options;
    jit_instrumentation = shm_toc_lookup(toc, PARALLEL_KEY_JIT_INSTRUMENTATION,
                                         true);
    queryDesc = ExecParallelGetQueryDesc(toc, receiver, instrument_options);
 
    /* Setting debug_query_string for individual workers */
    debug_query_string = queryDesc->sourceText;
 
    /* Report workers' query for monitoring purposes */
    pgstat_report_activity(STATE_RUNNING, debug_query_string);
 
    /* Attach to the dynamic shared memory area. */
    area_space = shm_toc_lookup(toc, PARALLEL_KEY_DSA, false);
    area = dsa_attach_in_place(area_space, seg);
 
    /* Start up the executor */
    queryDesc->plannedstmt->jitFlags = fpes->jit_flags;
    ExecutorStart(queryDesc, fpes->eflags);
 
    /* Special executor initialization steps for parallel workers */
    queryDesc->planstate->state->es_query_dsa = area;
    if (DsaPointerIsValid(fpes->param_exec))
    {
        char       *paramexec_space;
 
        paramexec_space = dsa_get_address(area, fpes->param_exec);
        RestoreParamExecParams(paramexec_space, queryDesc->estate);
    }
    pwcxt.toc = toc;
    pwcxt.seg = seg;
    ExecParallelInitializeWorker(queryDesc->planstate, &pwcxt);
 
    /* Pass down any tuple bound */
    ExecSetTupleBound(fpes->tuples_needed, queryDesc->planstate);
 
    /*
     * Prepare to track buffer/WAL usage during query execution.
     *
     * We do this after starting up the executor to match what happens in the
     * leader, which also doesn't count buffer accesses and WAL activity that
     * occur during executor startup.
     */
    InstrStartParallelQuery();
 
    /*
     * Run the plan.  If we specified a tuple bound, be careful not to demand
     * more tuples than that.
     */
    ExecutorRun(queryDesc,
                ForwardScanDirection,
                fpes->tuples_needed < 0 ? (int64) 0 : fpes->tuples_needed);
 
    /* Shut down the executor */
    ExecutorFinish(queryDesc);
 
    /* Report buffer/WAL usage during parallel execution. */
    buffer_usage = shm_toc_lookup(toc, PARALLEL_KEY_BUFFER_USAGE, false);
    wal_usage = shm_toc_lookup(toc, PARALLEL_KEY_WAL_USAGE, false);
    InstrEndParallelQuery(&buffer_usage[ParallelWorkerNumber],
                          &wal_usage[ParallelWorkerNumber]);
 
    /* Report instrumentation data if any instrumentation options are set. */
    if (instrumentation != NULL)
        ExecParallelReportInstrumentation(queryDesc->planstate,
                                          instrumentation);
 
    /* Report JIT instrumentation data if any */
    if (queryDesc->estate->es_jit && jit_instrumentation != NULL)
    {
        Assert(ParallelWorkerNumber < jit_instrumentation->num_workers);
        jit_instrumentation->jit_instr[ParallelWorkerNumber] =
            queryDesc->estate->es_jit->instr;
    }
 
    /* Must do this after capturing instrumentation. */
    ExecutorEnd(queryDesc);
 
    /* Cleanup. */
    dsa_detach(area);
    FreeQueryDesc(queryDesc);
    receiver->rDestroy(receiver);
}

References Assert(), debug_query_string, dsa_attach_in_place(), dsa_detach(), dsa_get_address(), DsaPointerIsValid, FixedParallelExecutorState::eflags, EState::es_jit, EState::es_query_dsa, QueryDesc::estate, ExecParallelGetQueryDesc(), ExecParallelGetReceiver(), ExecParallelInitializeWorker(), ExecParallelReportInstrumentation(), ExecSetTupleBound(), ExecutorEnd(), ExecutorFinish(), ExecutorRun(), ExecutorStart(), ForwardScanDirection, FreeQueryDesc(), JitContext::instr, InstrEndParallelQuery(), InstrStartParallelQuery(), SharedExecutorInstrumentation::instrument_options, FixedParallelExecutorState::jit_flags, SharedJitInstrumentation::jit_instr, PlannedStmt::jitFlags, PARALLEL_KEY_BUFFER_USAGE, PARALLEL_KEY_DSA, PARALLEL_KEY_EXECUTOR_FIXED, PARALLEL_KEY_INSTRUMENTATION, PARALLEL_KEY_JIT_INSTRUMENTATION, PARALLEL_KEY_WAL_USAGE, ParallelWorkerNumber, FixedParallelExecutorState::param_exec, pgstat_report_activity(), QueryDesc::plannedstmt, QueryDesc::planstate, _DestReceiver::rDestroy, RestoreParamExecParams(), ParallelWorkerContext::seg, shm_toc_lookup(), QueryDesc::sourceText, PlanState::state, STATE_RUNNING, ParallelWorkerContext::toc, and FixedParallelExecutorState::tuples_needed.

RestoreParamExecParams()

static void RestoreParamExecParams ( char *  start_address, EState *  estate  )

static

Definition at line 419 of file execParallel.c.

{
    int         nparams;
    int         i;
    int         paramid;
 
    memcpy(&nparams, start_address, sizeof(int));
    start_address += sizeof(int);
 
    for (i = 0; i < nparams; i++)
    {
        ParamExecData *prm;
 
        /* Read paramid */
        memcpy(&paramid, start_address, sizeof(int));
        start_address += sizeof(int);
        prm = &(estate->es_param_exec_vals[paramid]);
 
        /* Read datum/isnull. */
        prm->value = datumRestore(&start_address, &prm->isnull);
        prm->execPlan = NULL;
    }
}

References datumRestore(), EState::es_param_exec_vals, ParamExecData::execPlan, i, ParamExecData::isnull, and ParamExecData::value.

Referenced by ParallelQueryMain().

SerializeParamExecParams()

static dsa_pointer SerializeParamExecParams ( EState *  estate, Bitmapset *  params, dsa_area *  area  )

static

Definition at line 364 of file execParallel.c.

{
    Size        size;
    int         nparams;
    int         paramid;
    ParamExecData *prm;
    dsa_pointer handle;
    char       *start_address;
 
    /* Allocate enough space for the current parameter values. */
    size = EstimateParamExecSpace(estate, params);
    handle = dsa_allocate(area, size);
    start_address = dsa_get_address(area, handle);
 
    /* First write the number of parameters as a 4-byte integer. */
    nparams = bms_num_members(params);
    memcpy(start_address, &nparams, sizeof(int));
    start_address += sizeof(int);
 
    /* Write details for each parameter in turn. */
    paramid = -1;
    while ((paramid = bms_next_member(params, paramid)) >= 0)
    {
        Oid         typeOid;
        int16       typLen;
        bool        typByVal;
 
        prm = &(estate->es_param_exec_vals[paramid]);
        typeOid = list_nth_oid(estate->es_plannedstmt->paramExecTypes,
                               paramid);
 
        /* Write paramid. */
        memcpy(start_address, &paramid, sizeof(int));
        start_address += sizeof(int);
 
        /* Write datum/isnull */
        if (OidIsValid(typeOid))
            get_typlenbyval(typeOid, &typLen, &typByVal);
        else
        {
            /* If no type OID, assume by-value, like copyParamList does. */
            typLen = sizeof(Datum);
            typByVal = true;
        }
        datumSerialize(prm->value, prm->isnull, typByVal, typLen,
                       &start_address);
    }
 
    return handle;
}

References bms_next_member(), bms_num_members(), datumSerialize(), dsa_allocate, dsa_get_address(), EState::es_param_exec_vals, EState::es_plannedstmt, EstimateParamExecSpace(), get_typlenbyval(), ParamExecData::isnull, list_nth_oid(), OidIsValid, PlannedStmt::paramExecTypes, and ParamExecData::value.

Referenced by ExecInitParallelPlan(), and ExecParallelReinitialize().