postgresql/src/include/access/relscan.h
Tomas Vondra 681daed931 Add EXPLAIN (IO) infrastructure with BitmapHeapScan support
Allows collecting details about AIO / prefetch for scan nodes backed by
a ReadStream. This may be enabled by a new "IO" option in EXPLAIN, and
it shows information about the prefetch distance and I/O requests.

As of this commit this applies only to BitmapHeapScan, because that's
the only scan node using a ReadStream and collecting instrumentation
from workers in a parallel query. Support for SeqScan and TidRangeScan,
the other scan nodes using ReadStream, will be added in subsequent
commits.

The stats are collected only when required by EXPLAIN ANALYZE, with the
IO option (disabled by default). The amount of collected statistics is
very limited, but we don't want to clutter EXPLAIN with too much data.

The IOStats struct is stored in the scan descriptor as a field, next to
other fields used by table AMs. A pointer to the field is passed to the
ReadStream, and updated directly.

It's the responsibility of the table AM to allocate the struct (e.g. in
ambeginscan) whenever the flag SO_SCAN_INSTRUMENT flag is passed to the
scan, so that the executor and ReadStream has access to it.

The collected stats are designed for ReadStream, but are meant to be
reasonably generic in case a TAM manages I/Os in different ways.

Author: Tomas Vondra <tomas@vondra.me>
Reviewed-by: Melanie Plageman <melanieplageman@gmail.com>
Reviewed-by: Lukas Fittl <lukas@fittl.com>
Reviewed-by: Andres Freund <andres@anarazel.de>
Discussion: https://postgr.es/m/flat/a177a6dd-240b-455a-8f25-aca0b1c08c6e%40vondra.me
2026-04-07 22:33:34 +02:00

229 lines
7.6 KiB
C

/*-------------------------------------------------------------------------
*
* relscan.h
* POSTGRES relation scan descriptor definitions.
*
*
* Portions Copyright (c) 1996-2026, PostgreSQL Global Development Group
* Portions Copyright (c) 1994, Regents of the University of California
*
* src/include/access/relscan.h
*
*-------------------------------------------------------------------------
*/
#ifndef RELSCAN_H
#define RELSCAN_H
#include "access/htup_details.h"
#include "access/itup.h"
#include "nodes/tidbitmap.h"
#include "port/atomics.h"
#include "storage/relfilelocator.h"
#include "storage/spin.h"
#include "utils/relcache.h"
struct ParallelTableScanDescData;
struct TableScanInstrumentation;
/*
* Generic descriptor for table scans. This is the base-class for table scans,
* which needs to be embedded in the scans of individual AMs.
*/
typedef struct TableScanDescData
{
/* scan parameters */
Relation rs_rd; /* heap relation descriptor */
struct SnapshotData *rs_snapshot; /* snapshot to see */
int rs_nkeys; /* number of scan keys */
struct ScanKeyData *rs_key; /* array of scan key descriptors */
/*
* Scan type-specific members
*/
union
{
/* Iterator for Bitmap Table Scans */
TBMIterator rs_tbmiterator;
/*
* Range of ItemPointers for table_scan_getnextslot_tidrange() to
* scan.
*/
struct
{
ItemPointerData rs_mintid;
ItemPointerData rs_maxtid;
} tidrange;
} st;
/*
* Information about type and behaviour of the scan, a bitmask of members
* of the ScanOptions enum (see tableam.h).
*/
uint32 rs_flags;
struct ParallelTableScanDescData *rs_parallel; /* parallel scan
* information */
/*
* Instrumentation counters maintained by all table AMs.
*/
struct TableScanInstrumentation *rs_instrument;
} TableScanDescData;
typedef struct TableScanDescData *TableScanDesc;
/*
* Shared state for parallel table scan.
*
* Each backend participating in a parallel table scan has its own
* TableScanDesc in backend-private memory, and those objects all contain a
* pointer to this structure. The information here must be sufficient to
* properly initialize each new TableScanDesc as workers join the scan, and it
* must act as a information what to scan for those workers.
*/
typedef struct ParallelTableScanDescData
{
RelFileLocator phs_locator; /* physical relation to scan */
bool phs_syncscan; /* report location to syncscan logic? */
bool phs_snapshot_any; /* SnapshotAny, not phs_snapshot_data? */
Size phs_snapshot_off; /* data for snapshot */
} ParallelTableScanDescData;
typedef struct ParallelTableScanDescData *ParallelTableScanDesc;
/*
* Shared state for parallel table scans, for block oriented storage.
*/
typedef struct ParallelBlockTableScanDescData
{
ParallelTableScanDescData base;
BlockNumber phs_nblocks; /* # blocks in relation at start of scan */
slock_t phs_mutex; /* mutual exclusion for setting startblock */
BlockNumber phs_startblock; /* starting block number */
BlockNumber phs_numblock; /* # blocks to scan, or InvalidBlockNumber if
* no limit */
pg_atomic_uint64 phs_nallocated; /* number of blocks allocated to
* workers so far. */
} ParallelBlockTableScanDescData;
typedef struct ParallelBlockTableScanDescData *ParallelBlockTableScanDesc;
/*
* Per backend state for parallel table scan, for block-oriented storage.
*/
typedef struct ParallelBlockTableScanWorkerData
{
uint64 phsw_nallocated; /* Current # of blocks into the scan */
uint32 phsw_chunk_remaining; /* # blocks left in this chunk */
uint32 phsw_chunk_size; /* The number of blocks to allocate in
* each I/O chunk for the scan */
} ParallelBlockTableScanWorkerData;
typedef struct ParallelBlockTableScanWorkerData *ParallelBlockTableScanWorker;
/*
* Base class for fetches from a table via an index. This is the base-class
* for such scans, which needs to be embedded in the respective struct for
* individual AMs.
*/
typedef struct IndexFetchTableData
{
Relation rel;
/*
* Bitmask of ScanOptions affecting the relation. No SO_INTERNAL_FLAGS are
* permitted.
*/
uint32 flags;
} IndexFetchTableData;
struct IndexScanInstrumentation;
/*
* We use the same IndexScanDescData structure for both amgettuple-based
* and amgetbitmap-based index scans. Some fields are only relevant in
* amgettuple-based scans.
*/
typedef struct IndexScanDescData
{
/* scan parameters */
Relation heapRelation; /* heap relation descriptor, or NULL */
Relation indexRelation; /* index relation descriptor */
struct SnapshotData *xs_snapshot; /* snapshot to see */
int numberOfKeys; /* number of index qualifier conditions */
int numberOfOrderBys; /* number of ordering operators */
struct ScanKeyData *keyData; /* array of index qualifier descriptors */
struct ScanKeyData *orderByData; /* array of ordering op descriptors */
bool xs_want_itup; /* caller requests index tuples */
bool xs_temp_snap; /* unregister snapshot at scan end? */
/* signaling to index AM about killing index tuples */
bool kill_prior_tuple; /* last-returned tuple is dead */
bool ignore_killed_tuples; /* do not return killed entries */
bool xactStartedInRecovery; /* prevents killing/seeing killed
* tuples */
/* index access method's private state */
void *opaque; /* access-method-specific info */
/*
* Instrumentation counters maintained by all index AMs during both
* amgettuple calls and amgetbitmap calls (unless field remains NULL)
*/
struct IndexScanInstrumentation *instrument;
/*
* In an index-only scan, a successful amgettuple call must fill either
* xs_itup (and xs_itupdesc) or xs_hitup (and xs_hitupdesc) to provide the
* data returned by the scan. It can fill both, in which case the heap
* format will be used.
*/
IndexTuple xs_itup; /* index tuple returned by AM */
struct TupleDescData *xs_itupdesc; /* rowtype descriptor of xs_itup */
HeapTuple xs_hitup; /* index data returned by AM, as HeapTuple */
struct TupleDescData *xs_hitupdesc; /* rowtype descriptor of xs_hitup */
ItemPointerData xs_heaptid; /* result */
bool xs_heap_continue; /* T if must keep walking, potential
* further results */
IndexFetchTableData *xs_heapfetch;
bool xs_recheck; /* T means scan keys must be rechecked */
/*
* When fetching with an ordering operator, the values of the ORDER BY
* expressions of the last returned tuple, according to the index. If
* xs_recheckorderby is true, these need to be rechecked just like the
* scan keys, and the values returned here are a lower-bound on the actual
* values.
*/
Datum *xs_orderbyvals;
bool *xs_orderbynulls;
bool xs_recheckorderby;
/* parallel index scan information, in shared memory */
struct ParallelIndexScanDescData *parallel_scan;
} IndexScanDescData;
/* Generic structure for parallel scans */
typedef struct ParallelIndexScanDescData
{
RelFileLocator ps_locator; /* physical table relation to scan */
RelFileLocator ps_indexlocator; /* physical index relation to scan */
Size ps_offset_am; /* Offset to am-specific structure */
char ps_snapshot_data[FLEXIBLE_ARRAY_MEMBER];
} ParallelIndexScanDescData;
struct TupleTableSlot;
/* Struct for storage-or-index scans of system tables */
typedef struct SysScanDescData
{
Relation heap_rel; /* catalog being scanned */
Relation irel; /* NULL if doing heap scan */
struct TableScanDescData *scan; /* only valid in storage-scan case */
struct IndexScanDescData *iscan; /* only valid in index-scan case */
struct SnapshotData *snapshot; /* snapshot to unregister at end of scan */
struct TupleTableSlot *slot;
} SysScanDescData;
#endif /* RELSCAN_H */