rdelaage
/
postgresql
mirror of https://git.postgresql.org/git/postgresql.git
1
0
Fork 0
Code Issues Packages Projects Releases Wiki Activity
postgresql/src/include/access/nbtree.h

569 lines
22 KiB
C
Raw Blame History

/*-------------------------------------------------------------------------
*
* nbtree.h
* header file for postgres btree access method implementation.
*
*
* Portions Copyright (c) 1996-2018, PostgreSQL Global Development Group
* Portions Copyright (c) 1994, Regents of the University of California
*
* src/include/access/nbtree.h
*
*-------------------------------------------------------------------------
*/
#ifndef NBTREE_H
#define NBTREE_H
#include "access/amapi.h"
#include "access/itup.h"
#include "access/sdir.h"
#include "access/xlogreader.h"
#include "catalog/pg_index.h"
#include "lib/stringinfo.h"
#include "storage/bufmgr.h"
#include "storage/shm_toc.h"
/* There's room for a 16-bit vacuum cycle ID in BTPageOpaqueData */
typedef uint16 BTCycleId;
/*
* BTPageOpaqueData -- At the end of every page, we store a pointer
* to both siblings in the tree. This is used to do forward/backward
* index scans. The next-page link is also critical for recovery when
* a search has navigated to the wrong page due to concurrent page splits
* or deletions; see src/backend/access/nbtree/README for more info.
*
* In addition, we store the page's btree level (counting upwards from
* zero at a leaf page) as well as some flag bits indicating the page type
* and status. If the page is deleted, we replace the level with the
* next-transaction-ID value indicating when it is safe to reclaim the page.
*
* We also store a "vacuum cycle ID". When a page is split while VACUUM is
* processing the index, a nonzero value associated with the VACUUM run is
* stored into both halves of the split page. (If VACUUM is not running,
* both pages receive zero cycleids.) This allows VACUUM to detect whether
* a page was split since it started, with a small probability of false match
* if the page was last split some exact multiple of MAX_BT_CYCLE_ID VACUUMs
* ago. Also, during a split, the BTP_SPLIT_END flag is cleared in the left
* (original) page, and set in the right page, but only if the next page
* to its right has a different cycleid.
*
* NOTE: the BTP_LEAF flag bit is redundant since level==0 could be tested
* instead.
*/
typedef struct BTPageOpaqueData
{
BlockNumber btpo_prev; /* left sibling, or P_NONE if leftmost */
BlockNumber btpo_next; /* right sibling, or P_NONE if rightmost */
union
{
uint32 level; /* tree level --- zero for leaf pages */
TransactionId xact; /* next transaction ID, if deleted */
} btpo;
uint16 btpo_flags; /* flag bits, see below */
BTCycleId btpo_cycleid; /* vacuum cycle ID of latest split */
} BTPageOpaqueData;
typedef BTPageOpaqueData *BTPageOpaque;
/* Bits defined in btpo_flags */
#define BTP_LEAF (1 << 0) /* leaf page, i.e. not internal page */
#define BTP_ROOT (1 << 1) /* root page (has no parent) */
#define BTP_DELETED (1 << 2) /* page has been deleted from tree */
#define BTP_META (1 << 3) /* meta-page */
#define BTP_HALF_DEAD (1 << 4) /* empty, but still in tree */
#define BTP_SPLIT_END (1 << 5) /* rightmost page of split group */
#define BTP_HAS_GARBAGE (1 << 6) /* page has LP_DEAD tuples */
#define BTP_INCOMPLETE_SPLIT (1 << 7) /* right sibling's downlink is missing */
/*
* The max allowed value of a cycle ID is a bit less than 64K. This is
* for convenience of pg_filedump and similar utilities: we want to use
* the last 2 bytes of special space as an index type indicator, and
* restricting cycle ID lets btree use that space for vacuum cycle IDs
* while still allowing index type to be identified.
*/
#define MAX_BT_CYCLE_ID 0xFF7F
/*
* The Meta page is always the first page in the btree index.
* Its primary purpose is to point to the location of the btree root page.
* We also point to the "fast" root, which is the current effective root;
* see README for discussion.
*/
typedef struct BTMetaPageData
{
uint32 btm_magic; /* should contain BTREE_MAGIC */
uint32 btm_version; /* should contain BTREE_VERSION */
BlockNumber btm_root; /* current root location */
uint32 btm_level; /* tree level of the root page */
BlockNumber btm_fastroot; /* current "fast" root location */
uint32 btm_fastlevel; /* tree level of the "fast" root page */
/* following fields are available since page version 3 */
TransactionId btm_oldest_btpo_xact; /* oldest btpo_xact among of
* deleted pages */
float4 btm_last_cleanup_num_heap_tuples; /* number of heap tuples
* during last cleanup */
} BTMetaPageData;
#define BTPageGetMeta(p) \
((BTMetaPageData *) PageGetContents(p))
#define BTREE_METAPAGE 0 /* first page is meta */
#define BTREE_MAGIC 0x053162 /* magic number of btree pages */
#define BTREE_VERSION 3 /* current version number */
#define BTREE_MIN_VERSION 2 /* minimal supported version number */
/*
* Maximum size of a btree index entry, including its tuple header.
*
* We actually need to be able to fit three items on every page,
* so restrict any one item to 1/3 the per-page available space.
*/
#define BTMaxItemSize(page) \
MAXALIGN_DOWN((PageGetPageSize(page) - \
MAXALIGN(SizeOfPageHeaderData + 3*sizeof(ItemIdData)) - \
MAXALIGN(sizeof(BTPageOpaqueData))) / 3)
/*
* The leaf-page fillfactor defaults to 90% but is user-adjustable.
* For pages above the leaf level, we use a fixed 70% fillfactor.
* The fillfactor is applied during index build and when splitting
* a rightmost page; when splitting non-rightmost pages we try to
* divide the data equally.
*/
#define BTREE_MIN_FILLFACTOR 10
#define BTREE_DEFAULT_FILLFACTOR 90
#define BTREE_NONLEAF_FILLFACTOR 70
/*
* Test whether two btree entries are "the same".
*
* Old comments:
* In addition, we must guarantee that all tuples in the index are unique,
* in order to satisfy some assumptions in Lehman and Yao. The way that we
* do this is by generating a new OID for every insertion that we do in the
* tree. This adds eight bytes to the size of btree index tuples. Note
* that we do not use the OID as part of a composite key; the OID only
* serves as a unique identifier for a given index tuple (logical position
* within a page).
*
* New comments:
* actually, we must guarantee that all tuples in A LEVEL
* are unique, not in ALL INDEX. So, we can use the t_tid
* as unique identifier for a given index tuple (logical position
* within a level). - vadim 04/09/97
*/
#define BTTidSame(i1, i2) \
((ItemPointerGetBlockNumber(&(i1)) == ItemPointerGetBlockNumber(&(i2))) && \
(ItemPointerGetOffsetNumber(&(i1)) == ItemPointerGetOffsetNumber(&(i2))))
#define BTEntrySame(i1, i2) \
BTTidSame((i1)->t_tid, (i2)->t_tid)
/*
* In general, the btree code tries to localize its knowledge about
* page layout to a couple of routines. However, we need a special
* value to indicate "no page number" in those places where we expect
* page numbers. We can use zero for this because we never need to
* make a pointer to the metadata page.
*/
#define P_NONE 0
/*
* Macros to test whether a page is leftmost or rightmost on its tree level,
* as well as other state info kept in the opaque data.
*/
#define P_LEFTMOST(opaque) ((opaque)->btpo_prev == P_NONE)
#define P_RIGHTMOST(opaque) ((opaque)->btpo_next == P_NONE)
#define P_ISLEAF(opaque) (((opaque)->btpo_flags & BTP_LEAF) != 0)
#define P_ISROOT(opaque) (((opaque)->btpo_flags & BTP_ROOT) != 0)
#define P_ISDELETED(opaque) (((opaque)->btpo_flags & BTP_DELETED) != 0)
#define P_ISMETA(opaque) (((opaque)->btpo_flags & BTP_META) != 0)
#define P_ISHALFDEAD(opaque) (((opaque)->btpo_flags & BTP_HALF_DEAD) != 0)
#define P_IGNORE(opaque) (((opaque)->btpo_flags & (BTP_DELETED|BTP_HALF_DEAD)) != 0)
#define P_HAS_GARBAGE(opaque) (((opaque)->btpo_flags & BTP_HAS_GARBAGE) != 0)
#define P_INCOMPLETE_SPLIT(opaque) (((opaque)->btpo_flags & BTP_INCOMPLETE_SPLIT) != 0)
/*
* Lehman and Yao's algorithm requires a ``high key'' on every non-rightmost
* page. The high key is not a data key, but gives info about what range of
* keys is supposed to be on this page. The high key on a page is required
* to be greater than or equal to any data key that appears on the page.
* If we find ourselves trying to insert a key > high key, we know we need
* to move right (this should only happen if the page was split since we
* examined the parent page).
*
* Our insertion algorithm guarantees that we can use the initial least key
* on our right sibling as the high key. Once a page is created, its high
* key changes only if the page is split.
*
* On a non-rightmost page, the high key lives in item 1 and data items
* start in item 2. Rightmost pages have no high key, so we store data
* items beginning in item 1.
*/
#define P_HIKEY ((OffsetNumber) 1)
#define P_FIRSTKEY ((OffsetNumber) 2)
#define P_FIRSTDATAKEY(opaque) (P_RIGHTMOST(opaque) ? P_HIKEY : P_FIRSTKEY)
/*
* Operator strategy numbers for B-tree have been moved to access/stratnum.h,
* because many places need to use them in ScanKeyInit() calls.
*
* The strategy numbers are chosen so that we can commute them by
* subtraction, thus:
*/
#define BTCommuteStrategyNumber(strat) (BTMaxStrategyNumber + 1 - (strat))
/*
* When a new operator class is declared, we require that the user
* supply us with an amproc procedure (BTORDER_PROC) for determining
* whether, for two keys a and b, a < b, a = b, or a > b. This routine
* must return < 0, 0, > 0, respectively, in these three cases. (It must
* not return INT_MIN, since we may negate the result before using it.)
*
* To facilitate accelerated sorting, an operator class may choose to
* offer a second procedure (BTSORTSUPPORT_PROC). For full details, see
* src/include/utils/sortsupport.h.
*
* To support window frames defined by "RANGE offset PRECEDING/FOLLOWING",
* an operator class may choose to offer a third amproc procedure
* (BTINRANGE_PROC), independently of whether it offers sortsupport.
* For full details, see doc/src/sgml/btree.sgml.
*/
#define BTORDER_PROC 1
#define BTSORTSUPPORT_PROC 2
#define BTINRANGE_PROC 3
#define BTNProcs 3
/*
* We need to be able to tell the difference between read and write
* requests for pages, in order to do locking correctly.
*/
#define BT_READ BUFFER_LOCK_SHARE
#define BT_WRITE BUFFER_LOCK_EXCLUSIVE
/*
* BTStackData -- As we descend a tree, we push the (location, downlink)
* pairs from internal pages onto a private stack. If we split a
* leaf, we use this stack to walk back up the tree and insert data
* into parent pages (and possibly to split them, too). Lehman and
* Yao's update algorithm guarantees that under no circumstances can
* our private stack give us an irredeemably bad picture up the tree.
* Again, see the paper for details.
*/
typedef struct BTStackData
{
BlockNumber bts_blkno;
OffsetNumber bts_offset;
IndexTupleData bts_btentry;
struct BTStackData *bts_parent;
} BTStackData;
typedef BTStackData *BTStack;
/*
* BTScanOpaqueData is the btree-private state needed for an indexscan.
* This consists of preprocessed scan keys (see _bt_preprocess_keys() for
* details of the preprocessing), information about the current location
* of the scan, and information about the marked location, if any. (We use
* BTScanPosData to represent the data needed for each of current and marked
* locations.) In addition we can remember some known-killed index entries
* that must be marked before we can move off the current page.
*
* Index scans work a page at a time: we pin and read-lock the page, identify
* all the matching items on the page and save them in BTScanPosData, then
* release the read-lock while returning the items to the caller for
* processing. This approach minimizes lock/unlock traffic. Note that we
* keep the pin on the index page until the caller is done with all the items
* (this is needed for VACUUM synchronization, see nbtree/README). When we
* are ready to step to the next page, if the caller has told us any of the
* items were killed, we re-lock the page to mark them killed, then unlock.
* Finally we drop the pin and step to the next page in the appropriate
* direction.
*
* If we are doing an index-only scan, we save the entire IndexTuple for each
* matched item, otherwise only its heap TID and offset. The IndexTuples go
* into a separate workspace array; each BTScanPosItem stores its tuple's
* offset within that array.
*/
typedef struct BTScanPosItem /* what we remember about each match */
{
ItemPointerData heapTid; /* TID of referenced heap item */
OffsetNumber indexOffset; /* index item's location within page */
LocationIndex tupleOffset; /* IndexTuple's offset in workspace, if any */
} BTScanPosItem;
typedef struct BTScanPosData
{
Buffer buf; /* if valid, the buffer is pinned */
XLogRecPtr lsn; /* pos in the WAL stream when page was read */
BlockNumber currPage; /* page referenced by items array */
BlockNumber nextPage; /* page's right link when we scanned it */
/*
* moreLeft and moreRight track whether we think there may be matching
* index entries to the left and right of the current page, respectively.
* We can clear the appropriate one of these flags when _bt_checkkeys()
* returns continuescan = false.
*/
bool moreLeft;
bool moreRight;
/*
* If we are doing an index-only scan, nextTupleOffset is the first free
* location in the associated tuple storage workspace.
*/
int nextTupleOffset;
/*
* The items array is always ordered in index order (ie, increasing
* indexoffset). When scanning backwards it is convenient to fill the
* array back-to-front, so we start at the last slot and fill downwards.
* Hence we need both a first-valid-entry and a last-valid-entry counter.
* itemIndex is a cursor showing which entry was last returned to caller.
*/
int firstItem; /* first valid index in items[] */
int lastItem; /* last valid index in items[] */
int itemIndex; /* current index in items[] */
BTScanPosItem items[MaxIndexTuplesPerPage]; /* MUST BE LAST */
} BTScanPosData;
typedef BTScanPosData *BTScanPos;
#define BTScanPosIsPinned(scanpos) \
( \
AssertMacro(BlockNumberIsValid((scanpos).currPage) || \
!BufferIsValid((scanpos).buf)), \
BufferIsValid((scanpos).buf) \
)
#define BTScanPosUnpin(scanpos) \
do { \
ReleaseBuffer((scanpos).buf); \
(scanpos).buf = InvalidBuffer; \
} while (0)
#define BTScanPosUnpinIfPinned(scanpos) \
do { \
if (BTScanPosIsPinned(scanpos)) \
BTScanPosUnpin(scanpos); \
} while (0)
#define BTScanPosIsValid(scanpos) \
( \
AssertMacro(BlockNumberIsValid((scanpos).currPage) || \
!BufferIsValid((scanpos).buf)), \
BlockNumberIsValid((scanpos).currPage) \
)
#define BTScanPosInvalidate(scanpos) \
do { \
(scanpos).currPage = InvalidBlockNumber; \
(scanpos).nextPage = InvalidBlockNumber; \
(scanpos).buf = InvalidBuffer; \
(scanpos).lsn = InvalidXLogRecPtr; \
(scanpos).nextTupleOffset = 0; \
} while (0);
/* We need one of these for each equality-type SK_SEARCHARRAY scan key */
typedef struct BTArrayKeyInfo
{
int scan_key; /* index of associated key in arrayKeyData */
int cur_elem; /* index of current element in elem_values */
int mark_elem; /* index of marked element in elem_values */
int num_elems; /* number of elems in current array value */
Datum *elem_values; /* array of num_elems Datums */
} BTArrayKeyInfo;
typedef struct BTScanOpaqueData
{
/* these fields are set by _bt_preprocess_keys(): */
bool qual_ok; /* false if qual can never be satisfied */
int numberOfKeys; /* number of preprocessed scan keys */
ScanKey keyData; /* array of preprocessed scan keys */
/* workspace for SK_SEARCHARRAY support */
ScanKey arrayKeyData; /* modified copy of scan->keyData */
int numArrayKeys; /* number of equality-type array keys (-1 if
* there are any unsatisfiable array keys) */
int arrayKeyCount; /* count indicating number of array scan keys
* processed */
BTArrayKeyInfo *arrayKeys; /* info about each equality-type array key */
MemoryContext arrayContext; /* scan-lifespan context for array data */
/* info about killed items if any (killedItems is NULL if never used) */
int *killedItems; /* currPos.items indexes of killed items */
int numKilled; /* number of currently stored items */
/*
* If we are doing an index-only scan, these are the tuple storage
* workspaces for the currPos and markPos respectively. Each is of size
* BLCKSZ, so it can hold as much as a full page's worth of tuples.
*/
char *currTuples; /* tuple storage for currPos */
char *markTuples; /* tuple storage for markPos */
/*
* If the marked position is on the same page as current position, we
* don't use markPos, but just keep the marked itemIndex in markItemIndex
* (all the rest of currPos is valid for the mark position). Hence, to
* determine if there is a mark, first look at markItemIndex, then at
* markPos.
*/
int markItemIndex; /* itemIndex, or -1 if not valid */
/* keep these last in struct for efficiency */
BTScanPosData currPos; /* current position data */
BTScanPosData markPos; /* marked position, if any */
} BTScanOpaqueData;
typedef BTScanOpaqueData *BTScanOpaque;
/*
* We use some private sk_flags bits in preprocessed scan keys. We're allowed
* to use bits 16-31 (see skey.h). The uppermost bits are copied from the
* index's indoption[] array entry for the index attribute.
*/
#define SK_BT_REQFWD 0x00010000 /* required to continue forward scan */
#define SK_BT_REQBKWD 0x00020000 /* required to continue backward scan */
#define SK_BT_INDOPTION_SHIFT 24 /* must clear the above bits */
#define SK_BT_DESC (INDOPTION_DESC << SK_BT_INDOPTION_SHIFT)
#define SK_BT_NULLS_FIRST (INDOPTION_NULLS_FIRST << SK_BT_INDOPTION_SHIFT)
/*
* external entry points for btree, in nbtree.c
*/
extern void btbuildempty(Relation index);
extern bool btinsert(Relation rel, Datum *values, bool *isnull,
ItemPointer ht_ctid, Relation heapRel,
IndexUniqueCheck checkUnique,
struct IndexInfo *indexInfo);
extern IndexScanDesc btbeginscan(Relation rel, int nkeys, int norderbys);
extern Size btestimateparallelscan(void);
extern void btinitparallelscan(void *target);
extern bool btgettuple(IndexScanDesc scan, ScanDirection dir);
extern int64 btgetbitmap(IndexScanDesc scan, TIDBitmap *tbm);
extern void btrescan(IndexScanDesc scan, ScanKey scankey, int nscankeys,
ScanKey orderbys, int norderbys);
extern void btparallelrescan(IndexScanDesc scan);
extern void btendscan(IndexScanDesc scan);
extern void btmarkpos(IndexScanDesc scan);
extern void btrestrpos(IndexScanDesc scan);
extern IndexBulkDeleteResult *btbulkdelete(IndexVacuumInfo *info,
IndexBulkDeleteResult *stats,
IndexBulkDeleteCallback callback,
void *callback_state);
extern IndexBulkDeleteResult *btvacuumcleanup(IndexVacuumInfo *info,
IndexBulkDeleteResult *stats);
extern bool btcanreturn(Relation index, int attno);
/*
* prototypes for internal functions in nbtree.c
*/
extern bool _bt_parallel_seize(IndexScanDesc scan, BlockNumber *pageno);
extern void _bt_parallel_release(IndexScanDesc scan, BlockNumber scan_page);
extern void _bt_parallel_done(IndexScanDesc scan);
extern void _bt_parallel_advance_array_keys(IndexScanDesc scan);
/*
* prototypes for functions in nbtinsert.c
*/
extern bool _bt_doinsert(Relation rel, IndexTuple itup,
IndexUniqueCheck checkUnique, Relation heapRel);
extern Buffer _bt_getstackbuf(Relation rel, BTStack stack, int access);
extern void _bt_finish_split(Relation rel, Buffer bbuf, BTStack stack);
/*
* prototypes for functions in nbtpage.c
*/
extern void _bt_initmetapage(Page page, BlockNumber rootbknum, uint32 level);
extern void _bt_update_meta_cleanup_info(Relation rel,
TransactionId oldestBtpoXact, float8 numHeapTuples);
extern void _bt_upgrademetapage(Page page);
extern Buffer _bt_getroot(Relation rel, int access);
extern Buffer _bt_gettrueroot(Relation rel);
extern int _bt_getrootheight(Relation rel);
extern void _bt_checkpage(Relation rel, Buffer buf);
extern Buffer _bt_getbuf(Relation rel, BlockNumber blkno, int access);
extern Buffer _bt_relandgetbuf(Relation rel, Buffer obuf,
BlockNumber blkno, int access);
extern void _bt_relbuf(Relation rel, Buffer buf);
extern void _bt_pageinit(Page page, Size size);
extern bool _bt_page_recyclable(Page page);
extern void _bt_delitems_delete(Relation rel, Buffer buf,
OffsetNumber *itemnos, int nitems, Relation heapRel);
extern void _bt_delitems_vacuum(Relation rel, Buffer buf,
OffsetNumber *itemnos, int nitems,
BlockNumber lastBlockVacuumed);
extern int _bt_pagedel(Relation rel, Buffer buf);
/*
* prototypes for functions in nbtsearch.c
*/
extern BTStack _bt_search(Relation rel,
int keysz, ScanKey scankey, bool nextkey,
Buffer *bufP, int access, Snapshot snapshot);
extern Buffer _bt_moveright(Relation rel, Buffer buf, int keysz,
ScanKey scankey, bool nextkey, bool forupdate, BTStack stack,
int access, Snapshot snapshot);
extern OffsetNumber _bt_binsrch(Relation rel, Buffer buf, int keysz,
ScanKey scankey, bool nextkey);
extern int32 _bt_compare(Relation rel, int keysz, ScanKey scankey,
Page page, OffsetNumber offnum);
extern bool _bt_first(IndexScanDesc scan, ScanDirection dir);
extern bool _bt_next(IndexScanDesc scan, ScanDirection dir);
extern Buffer _bt_get_endpoint(Relation rel, uint32 level, bool rightmost,
Snapshot snapshot);
/*
* prototypes for functions in nbtutils.c
*/
extern ScanKey _bt_mkscankey(Relation rel, IndexTuple itup);
extern ScanKey _bt_mkscankey_nodata(Relation rel);
extern void _bt_freeskey(ScanKey skey);
extern void _bt_freestack(BTStack stack);
extern void _bt_preprocess_array_keys(IndexScanDesc scan);
extern void _bt_start_array_keys(IndexScanDesc scan, ScanDirection dir);
extern bool _bt_advance_array_keys(IndexScanDesc scan, ScanDirection dir);
extern void _bt_mark_array_keys(IndexScanDesc scan);
extern void _bt_restore_array_keys(IndexScanDesc scan);
extern void _bt_preprocess_keys(IndexScanDesc scan);
extern IndexTuple _bt_checkkeys(IndexScanDesc scan,
Page page, OffsetNumber offnum,
ScanDirection dir, bool *continuescan);
extern void _bt_killitems(IndexScanDesc scan);
extern BTCycleId _bt_vacuum_cycleid(Relation rel);
extern BTCycleId _bt_start_vacuum(Relation rel);
extern void _bt_end_vacuum(Relation rel);
extern void _bt_end_vacuum_callback(int code, Datum arg);
extern Size BTreeShmemSize(void);
extern void BTreeShmemInit(void);
extern bytea *btoptions(Datum reloptions, bool validate);
extern bool btproperty(Oid index_oid, int attno,
IndexAMProperty prop, const char *propname,
bool *res, bool *isnull);
/*
* prototypes for functions in nbtvalidate.c
*/
extern bool btvalidate(Oid opclassoid);
/*
* prototypes for functions in nbtsort.c
*/
extern IndexBuildResult *btbuild(Relation heap, Relation index,
struct IndexInfo *indexInfo);
extern void _bt_parallel_build_main(dsm_segment *seg, shm_toc *toc);
#endif /* NBTREE_H */
Reference in New Issue View Git Blame Copy Permalink