postgresql/src/backend/executor/nodeCustom.c
David Rowley c456e39113 Optimize tuple deformation
This commit includes various optimizations to improve the performance of
tuple deformation.

We now precalculate CompactAttribute's attcacheoff, which allows us to
remove the code from the deform routines which was setting the
attcacheoff.  Setting the attcacheoff is now handled by
TupleDescFinalize(), which must be called before the TupleDesc is used for
anything.  Having TupleDescFinalize() means we can store the first
attribute in the TupleDesc which does not have an offset cached.  That
allows us to add a dedicated deforming loop to deform all attributes up
to the final one with an attcacheoff set, or up to the first NULL
attribute, whichever comes first.

Here we also improve tuple deformation performance of tuples with NULLs.
Previously, if the HEAP_HASNULL bit was set in the tuple's t_infomask,
deforming would, one-by-one, check each and every bit in the NULL bitmap
to see if it was zero.  Now, we process the NULL bitmap 1 byte at a time
rather than 1 bit at a time to find the attnum with the first NULL.  We
can now deform the tuple without checking for NULLs up to just before that
attribute.

We also record the maximum attribute number which is guaranteed to exist
in the tuple, that is, has a NOT NULL constraint and isn't an
atthasmissing attribute.  When deforming only attributes prior to the
guaranteed attnum, we've no need to access the tuple's natt count.  As an
additional optimization, we only count fixed-width columns when
calculating the maximum guaranteed column, as this eliminates the need to
emit code to fetch byref types in the deformation loop for guaranteed
attributes.

Some locations in the code deform tuples that have yet to go through NOT
NULL constraint validation.  We're unable to perform the guaranteed
attribute optimization when that's the case.  This optimization is opt-in
via the TupleTableSlot using the TTS_FLAG_OBEYS_NOT_NULL_CONSTRAINTS
flag.

This commit also adds a more efficient way of populating the isnull
array by using a bit-wise SWAR trick which performs multiplication on the
inverse of the tuple's bitmap byte and masking out all but the lower bit
of each of the boolean's byte.  This results in much more optimal code
when compared to determining the NULLness via att_isnull().  8 isnull
elements are processed at once using this method, which means we need to
round the tts_isnull array size up to the next 8 bytes.  The palloc code
does this anyway, but the round-up needed to be formalized so as not to
overwrite the sentinel byte in MEMORY_CONTEXT_CHECKING builds.  Doing
this also allows the NULL-checking deforming loop to more efficiently
check the isnull array, rather than doing the bit-wise processing for each
attribute that att_isnull() does.

The level of performance improvement from these changes seems to vary
depending on the CPU architecture.  Apple's M chips seem particularly
fond of the changes, with some of the tested deform-heavy queries going
over twice as fast as before.  With x86-64, the speedups aren't quite as
large.  With tables containing only a small number of columns, the
speedups will be less.

Author: David Rowley <dgrowleyml@gmail.com>
Reviewed-by: Chao Li <li.evan.chao@gmail.com>
Reviewed-by: Andres Freund <andres@anarazel.de>
Reviewed-by: John Naylor <johncnaylorls@gmail.com>
Reviewed-by: Amit Langote <amitlangote09@gmail.com>
Reviewed-by: Zsolt Parragi <zsolt.parragi@percona.com>
Reviewed-by: Álvaro Herrera <alvherre@kurilemu.de>
Reviewed-by: Junwang Zhao <zhjwpku@gmail.com>
Discussion: https://postgr.es/m/CAApHDvpoFjaj3%2Bw_jD5uPnGazaw41A71tVJokLDJg2zfcigpMQ%40mail.gmail.com
2026-03-16 11:46:00 +13:00

227 lines
5.9 KiB
C

/* ------------------------------------------------------------------------
*
* nodeCustom.c
* Routines to handle execution of custom scan node
*
* Portions Copyright (c) 1996-2026, PostgreSQL Global Development Group
* Portions Copyright (c) 1994, Regents of the University of California
*
* ------------------------------------------------------------------------
*/
#include "postgres.h"
#include "access/parallel.h"
#include "executor/executor.h"
#include "executor/nodeCustom.h"
#include "miscadmin.h"
#include "nodes/execnodes.h"
#include "nodes/extensible.h"
#include "nodes/plannodes.h"
#include "utils/rel.h"
static TupleTableSlot *ExecCustomScan(PlanState *pstate);
CustomScanState *
ExecInitCustomScan(CustomScan *cscan, EState *estate, int eflags)
{
CustomScanState *css;
const TupleTableSlotOps *slotOps;
Relation scan_rel = NULL;
Index scanrelid = cscan->scan.scanrelid;
int tlistvarno;
/*
* Allocate the CustomScanState object. We let the custom scan provider
* do the palloc, in case it wants to make a larger object that embeds
* CustomScanState as the first field. It must set the node tag and the
* methods field correctly at this time. Other standard fields should be
* set to zero.
*/
css = castNode(CustomScanState,
cscan->methods->CreateCustomScanState(cscan));
/* ensure flags is filled correctly */
css->flags = cscan->flags;
/* fill up fields of ScanState */
css->ss.ps.plan = &cscan->scan.plan;
css->ss.ps.state = estate;
css->ss.ps.ExecProcNode = ExecCustomScan;
/* create expression context for node */
ExecAssignExprContext(estate, &css->ss.ps);
/*
* open the scan relation, if any
*/
if (scanrelid > 0)
{
scan_rel = ExecOpenScanRelation(estate, scanrelid, eflags);
css->ss.ss_currentRelation = scan_rel;
}
/*
* Use a custom slot if specified in CustomScanState or use virtual slot
* otherwise.
*/
slotOps = css->slotOps;
if (!slotOps)
slotOps = &TTSOpsVirtual;
/*
* Determine the scan tuple type. If the custom scan provider provided a
* targetlist describing the scan tuples, use that; else use base
* relation's rowtype.
*/
if (cscan->custom_scan_tlist != NIL || scan_rel == NULL)
{
TupleDesc scan_tupdesc;
scan_tupdesc = ExecTypeFromTL(cscan->custom_scan_tlist);
ExecInitScanTupleSlot(estate, &css->ss, scan_tupdesc, slotOps, 0);
/* Node's targetlist will contain Vars with varno = INDEX_VAR */
tlistvarno = INDEX_VAR;
}
else
{
ExecInitScanTupleSlot(estate, &css->ss, RelationGetDescr(scan_rel),
slotOps, 0);
/* Node's targetlist will contain Vars with varno = scanrelid */
tlistvarno = scanrelid;
}
/*
* Initialize result slot, type and projection.
*/
ExecInitResultTupleSlotTL(&css->ss.ps, &TTSOpsVirtual);
ExecAssignScanProjectionInfoWithVarno(&css->ss, tlistvarno);
/* initialize child expressions */
css->ss.ps.qual =
ExecInitQual(cscan->scan.plan.qual, (PlanState *) css);
/*
* The callback of custom-scan provider applies the final initialization
* of the custom-scan-state node according to its logic.
*/
css->methods->BeginCustomScan(css, estate, eflags);
return css;
}
static TupleTableSlot *
ExecCustomScan(PlanState *pstate)
{
CustomScanState *node = castNode(CustomScanState, pstate);
CHECK_FOR_INTERRUPTS();
Assert(node->methods->ExecCustomScan != NULL);
return node->methods->ExecCustomScan(node);
}
void
ExecEndCustomScan(CustomScanState *node)
{
Assert(node->methods->EndCustomScan != NULL);
node->methods->EndCustomScan(node);
}
void
ExecReScanCustomScan(CustomScanState *node)
{
Assert(node->methods->ReScanCustomScan != NULL);
node->methods->ReScanCustomScan(node);
}
void
ExecCustomMarkPos(CustomScanState *node)
{
if (!node->methods->MarkPosCustomScan)
ereport(ERROR,
(errcode(ERRCODE_FEATURE_NOT_SUPPORTED),
errmsg("custom scan \"%s\" does not support MarkPos",
node->methods->CustomName)));
node->methods->MarkPosCustomScan(node);
}
void
ExecCustomRestrPos(CustomScanState *node)
{
if (!node->methods->RestrPosCustomScan)
ereport(ERROR,
(errcode(ERRCODE_FEATURE_NOT_SUPPORTED),
errmsg("custom scan \"%s\" does not support MarkPos",
node->methods->CustomName)));
node->methods->RestrPosCustomScan(node);
}
void
ExecCustomScanEstimate(CustomScanState *node, ParallelContext *pcxt)
{
const CustomExecMethods *methods = node->methods;
if (methods->EstimateDSMCustomScan)
{
node->pscan_len = methods->EstimateDSMCustomScan(node, pcxt);
shm_toc_estimate_chunk(&pcxt->estimator, node->pscan_len);
shm_toc_estimate_keys(&pcxt->estimator, 1);
}
}
void
ExecCustomScanInitializeDSM(CustomScanState *node, ParallelContext *pcxt)
{
const CustomExecMethods *methods = node->methods;
if (methods->InitializeDSMCustomScan)
{
int plan_node_id = node->ss.ps.plan->plan_node_id;
void *coordinate;
coordinate = shm_toc_allocate(pcxt->toc, node->pscan_len);
methods->InitializeDSMCustomScan(node, pcxt, coordinate);
shm_toc_insert(pcxt->toc, plan_node_id, coordinate);
}
}
void
ExecCustomScanReInitializeDSM(CustomScanState *node, ParallelContext *pcxt)
{
const CustomExecMethods *methods = node->methods;
if (methods->ReInitializeDSMCustomScan)
{
int plan_node_id = node->ss.ps.plan->plan_node_id;
void *coordinate;
coordinate = shm_toc_lookup(pcxt->toc, plan_node_id, false);
methods->ReInitializeDSMCustomScan(node, pcxt, coordinate);
}
}
void
ExecCustomScanInitializeWorker(CustomScanState *node,
ParallelWorkerContext *pwcxt)
{
const CustomExecMethods *methods = node->methods;
if (methods->InitializeWorkerCustomScan)
{
int plan_node_id = node->ss.ps.plan->plan_node_id;
void *coordinate;
coordinate = shm_toc_lookup(pwcxt->toc, plan_node_id, false);
methods->InitializeWorkerCustomScan(node, pwcxt->toc, coordinate);
}
}
void
ExecShutdownCustomScan(CustomScanState *node)
{
const CustomExecMethods *methods = node->methods;
if (methods->ShutdownCustomScan)
methods->ShutdownCustomScan(node);
}