bernoulli.c File Reference

#include "postgres.h"
#include <math.h>
#include "access/tsmapi.h"
#include "catalog/pg_type.h"
#include "common/hashfn.h"
#include "optimizer/optimizer.h"
#include "utils/fmgrprotos.h"

Include dependency graph for bernoulli.c:

Go to the source code of this file.

Data Structures
struct	BernoulliSamplerData

Functions
static void	bernoulli_samplescangetsamplesize (PlannerInfo *root, RelOptInfo *baserel, List *paramexprs, BlockNumber *pages, double *tuples)
static void	bernoulli_initsamplescan (SampleScanState *node, int eflags)
static void	bernoulli_beginsamplescan (SampleScanState *node, Datum *params, int nparams, uint32 seed)
static OffsetNumber	bernoulli_nextsampletuple (SampleScanState *node, BlockNumber blockno, OffsetNumber maxoffset)
Datum	tsm_bernoulli_handler (PG_FUNCTION_ARGS)

Function Documentation

bernoulli_beginsamplescan()

static void bernoulli_beginsamplescan ( SampleScanState *  node, Datum *  params, int  nparams, uint32  seed  )

static

Definition at line 136 of file bernoulli.c.

{
    BernoulliSamplerData *sampler = (BernoulliSamplerData *) node->tsm_state;
    double      percent = DatumGetFloat4(params[0]);
    double      dcutoff;
 
    if (percent < 0 || percent > 100 || isnan(percent))
        ereport(ERROR,
                (errcode(ERRCODE_INVALID_TABLESAMPLE_ARGUMENT),
                 errmsg("sample percentage must be between 0 and 100")));
 
    /*
     * The cutoff is sample probability times (PG_UINT32_MAX + 1); we have to
     * store that as a uint64, of course.  Note that this gives strictly
     * correct behavior at the limits of zero or one probability.
     */
    dcutoff = rint(((double) PG_UINT32_MAX + 1) * percent / 100);
    sampler->cutoff = (uint64) dcutoff;
    sampler->seed = seed;
    sampler->lt = InvalidOffsetNumber;
 
    /*
     * Use bulkread, since we're scanning all pages.  But pagemode visibility
     * checking is a win only at larger sampling fractions.  The 25% cutoff
     * here is based on very limited experimentation.
     */
    node->use_bulkread = true;
    node->use_pagemode = (percent >= 25);
}

References BernoulliSamplerData::cutoff, DatumGetFloat4(), ereport, errcode(), errmsg(), ERROR, InvalidOffsetNumber, BernoulliSamplerData::lt, PG_UINT32_MAX, BernoulliSamplerData::seed, SampleScanState::tsm_state, SampleScanState::use_bulkread, and SampleScanState::use_pagemode.

Referenced by tsm_bernoulli_handler().

bernoulli_initsamplescan()

static void bernoulli_initsamplescan ( SampleScanState *  node, int  eflags  )

static

Definition at line 127 of file bernoulli.c.

{
    node->tsm_state = palloc0(sizeof(BernoulliSamplerData));
}

References palloc0(), and SampleScanState::tsm_state.

Referenced by tsm_bernoulli_handler().

bernoulli_nextsampletuple()

static OffsetNumber bernoulli_nextsampletuple ( SampleScanState *  node, BlockNumber  blockno, OffsetNumber  maxoffset  )

static

Definition at line 181 of file bernoulli.c.

{
    BernoulliSamplerData *sampler = (BernoulliSamplerData *) node->tsm_state;
    OffsetNumber tupoffset = sampler->lt;
    uint32      hashinput[3];
 
    /* Advance to first/next tuple in block */
    if (tupoffset == InvalidOffsetNumber)
        tupoffset = FirstOffsetNumber;
    else
        tupoffset++;
 
    /*
     * We compute the hash by applying hash_any to an array of 3 uint32's
     * containing the block, offset, and seed.  This is efficient to set up,
     * and with the current implementation of hash_any, it gives
     * machine-independent results, which is a nice property for regression
     * testing.
     *
     * These words in the hash input are the same throughout the block:
     */
    hashinput[0] = blockno;
    hashinput[2] = sampler->seed;
 
    /*
     * Loop over tuple offsets until finding suitable TID or reaching end of
     * block.
     */
    for (; tupoffset <= maxoffset; tupoffset++)
    {
        uint32      hash;
 
        hashinput[1] = tupoffset;
 
        hash = DatumGetUInt32(hash_any((const unsigned char *) hashinput,
                                       (int) sizeof(hashinput)));
        if (hash < sampler->cutoff)
            break;
    }
 
    if (tupoffset > maxoffset)
        tupoffset = InvalidOffsetNumber;
 
    sampler->lt = tupoffset;
 
    return tupoffset;
}

References DatumGetUInt32(), FirstOffsetNumber, hash(), hash_any(), if(), InvalidOffsetNumber, BernoulliSamplerData::lt, BernoulliSamplerData::seed, and SampleScanState::tsm_state.

Referenced by tsm_bernoulli_handler().

bernoulli_samplescangetsamplesize()

static void bernoulli_samplescangetsamplesize ( PlannerInfo *  root, RelOptInfo *  baserel, List *  paramexprs, BlockNumber *  pages, double *  tuples  )

static

Definition at line 86 of file bernoulli.c.

{
    Node       *pctnode;
    float4      samplefract;
 
    /* Try to extract an estimate for the sample percentage */
    pctnode = (Node *) linitial(paramexprs);
    pctnode = estimate_expression_value(root, pctnode);
 
    if (IsA(pctnode, Const) &&
        !((Const *) pctnode)->constisnull)
    {
        samplefract = DatumGetFloat4(((Const *) pctnode)->constvalue);
        if (samplefract >= 0 && samplefract <= 100 && !isnan(samplefract))
            samplefract /= 100.0f;
        else
        {
            /* Default samplefract if the value is bogus */
            samplefract = 0.1f;
        }
    }
    else
    {
        /* Default samplefract if we didn't obtain a non-null Const */
        samplefract = 0.1f;
    }
 
    /* We'll visit all pages of the baserel */
    *pages = baserel->pages;
 
    *tuples = clamp_row_est(baserel->tuples * samplefract);
}

References clamp_row_est(), DatumGetFloat4(), estimate_expression_value(), IsA, linitial, RelOptInfo::pages, root, and RelOptInfo::tuples.

Referenced by tsm_bernoulli_handler().

tsm_bernoulli_handler()

Datum tsm_bernoulli_handler

(

PG_FUNCTION_ARGS

)

Definition at line 65 of file bernoulli.c.

{
    TsmRoutine *tsm = makeNode(TsmRoutine);
 
    tsm->parameterTypes = list_make1_oid(FLOAT4OID);
    tsm->repeatable_across_queries = true;
    tsm->repeatable_across_scans = true;
    tsm->SampleScanGetSampleSize = bernoulli_samplescangetsamplesize;
    tsm->InitSampleScan = bernoulli_initsamplescan;
    tsm->BeginSampleScan = bernoulli_beginsamplescan;
    tsm->NextSampleBlock = NULL;
    tsm->NextSampleTuple = bernoulli_nextsampletuple;
    tsm->EndSampleScan = NULL;
 
    PG_RETURN_POINTER(tsm);
}

References TsmRoutine::BeginSampleScan, bernoulli_beginsamplescan(), bernoulli_initsamplescan(), bernoulli_nextsampletuple(), bernoulli_samplescangetsamplesize(), TsmRoutine::EndSampleScan, TsmRoutine::InitSampleScan, list_make1_oid, makeNode, TsmRoutine::NextSampleBlock, TsmRoutine::NextSampleTuple, TsmRoutine::parameterTypes, PG_RETURN_POINTER, TsmRoutine::repeatable_across_queries, TsmRoutine::repeatable_across_scans, and TsmRoutine::SampleScanGetSampleSize.