PostgreSQL/src/include/storage/bufmgr.h

/*-------------------------------------------------------------------------
 *
 * bufmgr.h
 *	  POSTGRES buffer manager definitions.
 *
 *
 * Portions Copyright (c) 1996-2016, PostgreSQL Global Development Group
 * Portions Copyright (c) 1994, Regents of the University of California
 *
 * src/include/storage/bufmgr.h
 *
 *-------------------------------------------------------------------------
 */
#ifndef BUFMGR_H
#define BUFMGR_H

#include "catalog/catalog.h"
#include "storage/block.h"
#include "storage/buf.h"
#include "storage/bufpage.h"
#include "storage/relfilenode.h"
#include "utils/relcache.h"
#include "utils/snapmgr.h"
#include "utils/tqual.h"

typedef void *Block;

/* Possible arguments for GetAccessStrategy() */
typedef enum BufferAccessStrategyType
{
	BAS_NORMAL,					/* Normal random access */
	BAS_BULKREAD,				/* Large read-only scan (hint bit updates are
								 * ok) */
	BAS_BULKWRITE,				/* Large multi-block write (e.g. COPY IN) */
	BAS_VACUUM					/* VACUUM */
} BufferAccessStrategyType;

/* Possible modes for ReadBufferExtended() */
typedef enum
{
	RBM_NORMAL,					/* Normal read */
	RBM_ZERO_AND_LOCK,			/* Don't read from disk, caller will
								 * initialize. Also locks the page. */
	RBM_ZERO_AND_CLEANUP_LOCK,	/* Like RBM_ZERO_AND_LOCK, but locks the page
								 * in "cleanup" mode */
	RBM_ZERO_ON_ERROR,			/* Read, but return an all-zeros page on error */
	RBM_NORMAL_NO_LOG			/* Don't log page as invalid during WAL
								 * replay; otherwise same as RBM_NORMAL */
} ReadBufferMode;

/*
 * Forced choice for whether BufferGetPage() must check snapshot age
 *
 * A scan must test for old snapshot, unless the test would be redundant (for
 * example, to tests already made at a lower level on all code paths).
 * Positioning for DML or vacuuming does not need this sort of test.
 */
typedef enum
{
	BGP_NO_SNAPSHOT_TEST,		/* Not used for scan, or is redundant */
	BGP_TEST_FOR_OLD_SNAPSHOT	/* Test for old snapshot is needed */
} BufferGetPageAgeTest;

/* forward declared, to avoid having to expose buf_internals.h here */
struct WritebackContext;

/* in globals.c ... this duplicates miscadmin.h */
extern PGDLLIMPORT int NBuffers;

/* in bufmgr.c */
#define WRITEBACK_MAX_PENDING_FLUSHES 256

/* FIXME: Also default to on for mmap && msync(MS_ASYNC)? */
#ifdef HAVE_SYNC_FILE_RANGE
#define DEFAULT_CHECKPOINT_FLUSH_AFTER 32
#define DEFAULT_BACKEND_FLUSH_AFTER 16
#define DEFAULT_BGWRITER_FLUSH_AFTER 64
#else
#define DEFAULT_CHECKPOINT_FLUSH_AFTER 0
#define DEFAULT_BACKEND_FLUSH_AFTER 0
#define DEFAULT_BGWRITER_FLUSH_AFTER 0
#endif   /* HAVE_SYNC_FILE_RANGE */

extern bool zero_damaged_pages;
extern int	bgwriter_lru_maxpages;
extern double bgwriter_lru_multiplier;
extern bool track_io_timing;
extern int	target_prefetch_pages;

extern int	checkpoint_flush_after;
extern int	backend_flush_after;
extern int	bgwriter_flush_after;

/* in buf_init.c */
extern PGDLLIMPORT char *BufferBlocks;

/* in guc.c */
extern int	effective_io_concurrency;

/* in localbuf.c */
extern PGDLLIMPORT int NLocBuffer;
extern PGDLLIMPORT Block *LocalBufferBlockPointers;
extern PGDLLIMPORT int32 *LocalRefCount;

/* upper limit for effective_io_concurrency */
#define MAX_IO_CONCURRENCY 1000

/* special block number for ReadBuffer() */
#define P_NEW	InvalidBlockNumber		/* grow the file to get a new page */

/*
 * Buffer content lock modes (mode argument for LockBuffer())
 */
#define BUFFER_LOCK_UNLOCK		0
#define BUFFER_LOCK_SHARE		1
#define BUFFER_LOCK_EXCLUSIVE	2

/*
 * These routines are beaten on quite heavily, hence the macroization.
 */

/*
 * BufferIsValid
 *		True iff the given buffer number is valid (either as a shared
 *		or local buffer).
 *
 * Note: For a long time this was defined the same as BufferIsPinned,
 * that is it would say False if you didn't hold a pin on the buffer.
 * I believe this was bogus and served only to mask logic errors.
 * Code should always know whether it has a buffer reference,
 * independently of the pin state.
 *
 * Note: For a further long time this was not quite the inverse of the
 * BufferIsInvalid() macro, in that it also did sanity checks to verify
 * that the buffer number was in range.  Most likely, this macro was
 * originally intended only to be used in assertions, but its use has
 * since expanded quite a bit, and the overhead of making those checks
 * even in non-assert-enabled builds can be significant.  Thus, we've
 * now demoted the range checks to assertions within the macro itself.
 */
#define BufferIsValid(bufnum) \
( \
	AssertMacro((bufnum) <= NBuffers && (bufnum) >= -NLocBuffer), \
	(bufnum) != InvalidBuffer  \
)

/*
 * BufferGetBlock
 *		Returns a reference to a disk page image associated with a buffer.
 *
 * Note:
 *		Assumes buffer is valid.
 */
#define BufferGetBlock(buffer) \
( \
	AssertMacro(BufferIsValid(buffer)), \
	BufferIsLocal(buffer) ? \
		LocalBufferBlockPointers[-(buffer) - 1] \
	: \
		(Block) (BufferBlocks + ((Size) ((buffer) - 1)) * BLCKSZ) \
)

/*
 * BufferGetPageSize
 *		Returns the page size within a buffer.
 *
 * Notes:
 *		Assumes buffer is valid.
 *
 *		The buffer can be a raw disk block and need not contain a valid
 *		(formatted) disk page.
 */
/* XXX should dig out of buffer descriptor */
#define BufferGetPageSize(buffer) \
( \
	AssertMacro(BufferIsValid(buffer)), \
	(Size)BLCKSZ \
)

/*
 * prototypes for functions in bufmgr.c
 */
extern bool ComputeIoConcurrency(int io_concurrency, double *target);
extern void PrefetchBuffer(Relation reln, ForkNumber forkNum,
			   BlockNumber blockNum);
extern Buffer ReadBuffer(Relation reln, BlockNumber blockNum);
extern Buffer ReadBufferExtended(Relation reln, ForkNumber forkNum,
				   BlockNumber blockNum, ReadBufferMode mode,
				   BufferAccessStrategy strategy);
extern Buffer ReadBufferWithoutRelcache(RelFileNode rnode,
						  ForkNumber forkNum, BlockNumber blockNum,
						  ReadBufferMode mode, BufferAccessStrategy strategy);
extern void ReleaseBuffer(Buffer buffer);
extern void UnlockReleaseBuffer(Buffer buffer);
extern void MarkBufferDirty(Buffer buffer);
extern void IncrBufferRefCount(Buffer buffer);
extern Buffer ReleaseAndReadBuffer(Buffer buffer, Relation relation,
					 BlockNumber blockNum);

extern void InitBufferPool(void);
extern void InitBufferPoolAccess(void);
extern void InitBufferPoolBackend(void);
extern void AtEOXact_Buffers(bool isCommit);
extern void PrintBufferLeakWarning(Buffer buffer);
extern void CheckPointBuffers(int flags);
extern BlockNumber BufferGetBlockNumber(Buffer buffer);
extern BlockNumber RelationGetNumberOfBlocksInFork(Relation relation,
								ForkNumber forkNum);
extern void FlushOneBuffer(Buffer buffer);
extern void FlushRelationBuffers(Relation rel);
extern void FlushDatabaseBuffers(Oid dbid);
extern void DropRelFileNodeBuffers(RelFileNodeBackend rnode,
					   ForkNumber forkNum, BlockNumber firstDelBlock);
extern void DropRelFileNodesAllBuffers(RelFileNodeBackend *rnodes, int nnodes);
extern void DropDatabaseBuffers(Oid dbid);

#define RelationGetNumberOfBlocks(reln) \
	RelationGetNumberOfBlocksInFork(reln, MAIN_FORKNUM)

extern bool BufferIsPermanent(Buffer buffer);
extern XLogRecPtr BufferGetLSNAtomic(Buffer buffer);

#ifdef NOT_USED
extern void PrintPinnedBufs(void);
#endif
extern Size BufferShmemSize(void);
extern void BufferGetTag(Buffer buffer, RelFileNode *rnode,
			 ForkNumber *forknum, BlockNumber *blknum);

extern void MarkBufferDirtyHint(Buffer buffer, bool buffer_std);

extern void UnlockBuffers(void);
extern void LockBuffer(Buffer buffer, int mode);
extern bool ConditionalLockBuffer(Buffer buffer);
extern void LockBufferForCleanup(Buffer buffer);
extern bool ConditionalLockBufferForCleanup(Buffer buffer);
extern bool HoldingBufferPinThatDelaysRecovery(void);

extern void AbortBufferIO(void);

extern void BufmgrCommit(void);
extern bool BgBufferSync(struct WritebackContext *wb_context);

extern void AtProcExit_LocalBuffers(void);

extern void TestForOldSnapshot(Snapshot snapshot, Relation relation, Page page);

/* in freelist.c */
extern BufferAccessStrategy GetAccessStrategy(BufferAccessStrategyType btype);
extern void FreeAccessStrategy(BufferAccessStrategy strategy);


/* inline functions */

/*
 * BufferGetPage
 *		Returns the page associated with a buffer.
 *
 * For call sites where the check is not needed (which is the vast majority of
 * them), the snapshot and relation parameters can, and generally should, be
 * NULL.
 */
static inline Page
BufferGetPage(Buffer buffer, Snapshot snapshot, Relation relation,
			  BufferGetPageAgeTest agetest)
{
	Page		page = (Page) BufferGetBlock(buffer);

	if (agetest == BGP_TEST_FOR_OLD_SNAPSHOT)
		TestForOldSnapshot(snapshot, relation, page);

	return page;
}

#endif