bufmgr.c File Reference

#include "postgres.h"
#include <sys/file.h>
#include <unistd.h>
#include "access/tableam.h"
#include "access/xlog.h"
#include "catalog/catalog.h"
#include "catalog/storage.h"
#include "executor/instrument.h"
#include "lib/binaryheap.h"
#include "miscadmin.h"
#include "pg_trace.h"
#include "pgstat.h"
#include "postmaster/bgwriter.h"
#include "storage/buf_internals.h"
#include "storage/bufmgr.h"
#include "storage/ipc.h"
#include "storage/proc.h"
#include "storage/smgr.h"
#include "storage/standby.h"
#include "utils/memdebug.h"
#include "utils/ps_status.h"
#include "utils/rel.h"
#include "utils/resowner_private.h"
#include "utils/timestamp.h"

Include dependency graph for bufmgr.c:

Go to the source code of this file.

Data Structures
struct	PrivateRefCountEntry
struct	CkptTsStatus
struct	SMgrSortArray

Macros
#define	BufHdrGetBlock(bufHdr)   ((Block) (BufferBlocks + ((Size) (bufHdr)->buf_id) * BLCKSZ))
#define	BufferGetLSN(bufHdr)   (PageGetLSN(BufHdrGetBlock(bufHdr)))
#define	LocalBufHdrGetBlock(bufHdr)   LocalBufferBlockPointers[-((bufHdr)->buf_id + 2)]
#define	BUF_WRITTEN   0x01
#define	BUF_REUSABLE   0x02
#define	RELS_BSEARCH_THRESHOLD   20
#define	BUF_DROP_FULL_SCAN_THRESHOLD   (uint32) (NBuffers / 32)
#define	REFCOUNT_ARRAY_ENTRIES   8
#define	BufferIsPinned(bufnum)

Typedefs
typedef struct PrivateRefCountEntry	PrivateRefCountEntry
typedef struct CkptTsStatus	CkptTsStatus
typedef struct SMgrSortArray	SMgrSortArray

Functions
static void	ReservePrivateRefCountEntry (void)
static PrivateRefCountEntry *	NewPrivateRefCountEntry (Buffer buffer)
static PrivateRefCountEntry *	GetPrivateRefCountEntry (Buffer buffer, bool do_move)
static int32	GetPrivateRefCount (Buffer buffer)
static void	ForgetPrivateRefCountEntry (PrivateRefCountEntry *ref)
static Buffer	ReadBuffer_common (SMgrRelation reln, char relpersistence, ForkNumber forkNum, BlockNumber blockNum, ReadBufferMode mode, BufferAccessStrategy strategy, bool *hit)
static bool	PinBuffer (BufferDesc *buf, BufferAccessStrategy strategy)
static void	PinBuffer_Locked (BufferDesc *buf)
static void	UnpinBuffer (BufferDesc *buf, bool fixOwner)
static void	BufferSync (int flags)
static uint32	WaitBufHdrUnlocked (BufferDesc *buf)
static int	SyncOneBuffer (int buf_id, bool skip_recently_used, WritebackContext *wb_context)
static void	WaitIO (BufferDesc *buf)
static bool	StartBufferIO (BufferDesc *buf, bool forInput)
static void	TerminateBufferIO (BufferDesc *buf, bool clear_dirty, uint32 set_flag_bits)
static void	shared_buffer_write_error_callback (void *arg)
static void	local_buffer_write_error_callback (void *arg)
static BufferDesc *	BufferAlloc (SMgrRelation smgr, char relpersistence, ForkNumber forkNum, BlockNumber blockNum, BufferAccessStrategy strategy, bool *foundPtr)
static void	FlushBuffer (BufferDesc *buf, SMgrRelation reln)
static void	FindAndDropRelFileNodeBuffers (RelFileNode rnode, ForkNumber forkNum, BlockNumber nForkBlock, BlockNumber firstDelBlock)
static void	AtProcExit_Buffers (int code, Datum arg)
static void	CheckForBufferLeaks (void)
static int	rnode_comparator (const void *p1, const void *p2)
static int	buffertag_comparator (const void *p1, const void *p2)
static int	ckpt_buforder_comparator (const void *pa, const void *pb)
static int	ts_ckpt_progress_comparator (Datum a, Datum b, void *arg)
PrefetchBufferResult	PrefetchSharedBuffer (SMgrRelation smgr_reln, ForkNumber forkNum, BlockNumber blockNum)
PrefetchBufferResult	PrefetchBuffer (Relation reln, ForkNumber forkNum, BlockNumber blockNum)
Buffer	ReadBuffer (Relation reln, BlockNumber blockNum)
Buffer	ReadBufferExtended (Relation reln, ForkNumber forkNum, BlockNumber blockNum, ReadBufferMode mode, BufferAccessStrategy strategy)
Buffer	ReadBufferWithoutRelcache (RelFileNode rnode, ForkNumber forkNum, BlockNumber blockNum, ReadBufferMode mode, BufferAccessStrategy strategy)
static void	InvalidateBuffer (BufferDesc *buf)
void	MarkBufferDirty (Buffer buffer)
Buffer	ReleaseAndReadBuffer (Buffer buffer, Relation relation, BlockNumber blockNum)
bool	BgBufferSync (WritebackContext *wb_context)
void	AtEOXact_Buffers (bool isCommit)
void	InitBufferPoolAccess (void)
void	InitBufferPoolBackend (void)
void	PrintBufferLeakWarning (Buffer buffer)
void	CheckPointBuffers (int flags)
void	BufmgrCommit (void)
BlockNumber	BufferGetBlockNumber (Buffer buffer)
void	BufferGetTag (Buffer buffer, RelFileNode *rnode, ForkNumber *forknum, BlockNumber *blknum)
BlockNumber	RelationGetNumberOfBlocksInFork (Relation relation, ForkNumber forkNum)
bool	BufferIsPermanent (Buffer buffer)
XLogRecPtr	BufferGetLSNAtomic (Buffer buffer)
void	DropRelFileNodeBuffers (SMgrRelation smgr_reln, ForkNumber *forkNum, int nforks, BlockNumber *firstDelBlock)
void	DropRelFileNodesAllBuffers (SMgrRelation *smgr_reln, int nnodes)
void	DropDatabaseBuffers (Oid dbid)
void	FlushRelationBuffers (Relation rel)
void	FlushRelationsAllBuffers (SMgrRelation *smgrs, int nrels)
void	FlushDatabaseBuffers (Oid dbid)
void	FlushOneBuffer (Buffer buffer)
void	ReleaseBuffer (Buffer buffer)
void	UnlockReleaseBuffer (Buffer buffer)
void	IncrBufferRefCount (Buffer buffer)
void	MarkBufferDirtyHint (Buffer buffer, bool buffer_std)
void	UnlockBuffers (void)
void	LockBuffer (Buffer buffer, int mode)
bool	ConditionalLockBuffer (Buffer buffer)
void	LockBufferForCleanup (Buffer buffer)
bool	HoldingBufferPinThatDelaysRecovery (void)
bool	ConditionalLockBufferForCleanup (Buffer buffer)
bool	IsBufferCleanupOK (Buffer buffer)
void	AbortBufferIO (void)
uint32	LockBufHdr (BufferDesc *desc)
void	WritebackContextInit (WritebackContext *context, int *max_pending)
void	ScheduleBufferTagForWriteback (WritebackContext *context, BufferTag *tag)
void	IssuePendingWritebacks (WritebackContext *context)
void	TestForOldSnapshot_impl (Snapshot snapshot, Relation relation)

Variables
bool	zero_damaged_pages = false
int	bgwriter_lru_maxpages = 100
double	bgwriter_lru_multiplier = 2.0
bool	track_io_timing = false
int	effective_io_concurrency = 0
int	maintenance_io_concurrency = 0
int	checkpoint_flush_after = 0
int	bgwriter_flush_after = 0
int	backend_flush_after = 0
static BufferDesc *	InProgressBuf = NULL
static bool	IsForInput
static BufferDesc *	PinCountWaitBuf = NULL
static struct PrivateRefCountEntry	PrivateRefCountArray [REFCOUNT_ARRAY_ENTRIES]
static HTAB *	PrivateRefCountHash = NULL
static int32	PrivateRefCountOverflowed = 0
static uint32	PrivateRefCountClock = 0
static PrivateRefCountEntry *	ReservedRefCountEntry = NULL

Macro Definition Documentation

BUF_DROP_FULL_SCAN_THRESHOLD

#define BUF_DROP_FULL_SCAN_THRESHOLD   (uint32) (NBuffers / 32)

Definition at line 79 of file bufmgr.c.

Referenced by DropRelFileNodeBuffers(), and DropRelFileNodesAllBuffers().

BUF_REUSABLE

#define BUF_REUSABLE   0x02

Definition at line 69 of file bufmgr.c.

Referenced by BgBufferSync(), and SyncOneBuffer().

BUF_WRITTEN

#define BUF_WRITTEN   0x01

Definition at line 68 of file bufmgr.c.

Referenced by BgBufferSync(), BufferSync(), and SyncOneBuffer().

BufferGetLSN

#define BufferGetLSN

(

bufHdr

)

(PageGetLSN(BufHdrGetBlock(bufHdr)))

Definition at line 61 of file bufmgr.c.

Referenced by BufferAlloc(), and FlushBuffer().

BufferIsPinned

#define BufferIsPinned

(

bufnum

)

Value:

( \
    !BufferIsValid(bufnum) ? \
        false \
    : \
        BufferIsLocal(bufnum) ? \
            (LocalRefCount[-(bufnum) - 1] > 0) \
        : \
    (GetPrivateRefCount(bufnum) > 0) \
)

Definition at line 448 of file bufmgr.c.

Referenced by BufferGetBlockNumber(), BufferGetLSNAtomic(), BufferGetTag(), BufferIsPermanent(), ConditionalLockBuffer(), FlushOneBuffer(), IncrBufferRefCount(), LockBuffer(), LockBufferForCleanup(), MarkBufferDirty(), and ReleaseAndReadBuffer().

BufHdrGetBlock

#define BufHdrGetBlock

(

bufHdr

)

((Block) (BufferBlocks + ((Size) (bufHdr)->buf_id) * BLCKSZ))

Definition at line 60 of file bufmgr.c.

Referenced by FlushBuffer(), PinBuffer(), PinBuffer_Locked(), ReadBuffer_common(), and UnpinBuffer().

LocalBufHdrGetBlock

#define LocalBufHdrGetBlock

(

bufHdr

)

LocalBufferBlockPointers[-((bufHdr)->buf_id + 2)]

Definition at line 64 of file bufmgr.c.

Referenced by FlushRelationBuffers(), and ReadBuffer_common().

REFCOUNT_ARRAY_ENTRIES

#define REFCOUNT_ARRAY_ENTRIES   8

Definition at line 88 of file bufmgr.c.

Referenced by CheckForBufferLeaks(), ForgetPrivateRefCountEntry(), GetPrivateRefCountEntry(), and ReservePrivateRefCountEntry().

RELS_BSEARCH_THRESHOLD

#define RELS_BSEARCH_THRESHOLD   20

Definition at line 71 of file bufmgr.c.

Referenced by DropRelFileNodesAllBuffers(), and FlushRelationsAllBuffers().

Typedef Documentation

CkptTsStatus

typedef struct CkptTsStatus CkptTsStatus

PrivateRefCountEntry

typedef struct PrivateRefCountEntry PrivateRefCountEntry

SMgrSortArray

typedef struct SMgrSortArray SMgrSortArray

Function Documentation

AbortBufferIO()

void AbortBufferIO

(

void

)

Definition at line 4429 of file bufmgr.c.

References Assert, buftag::blockNum, BM_DIRTY, BM_IO_ERROR, BM_IO_IN_PROGRESS, BM_VALID, buf, BufferDescriptorGetIOLock, ereport, errcode(), errdetail(), errmsg(), buftag::forkNum, InProgressBuf, IsForInput, LockBufHdr(), LW_EXCLUSIVE, LWLockAcquire(), pfree(), relpathperm, buftag::rnode, BufferDesc::tag, TerminateBufferIO(), UnlockBufHdr, and WARNING.

Referenced by AbortSubTransaction(), AbortTransaction(), AtProcExit_Buffers(), AutoVacLauncherMain(), BackgroundWriterMain(), CheckpointerMain(), and WalWriterMain().

{
    BufferDesc *buf = InProgressBuf;

    if (buf)
    {
        uint32      buf_state;

        /*
         * Since LWLockReleaseAll has already been called, we're not holding
         * the buffer's io_in_progress_lock. We have to re-acquire it so that
         * we can use TerminateBufferIO. Anyone who's executing WaitIO on the
         * buffer will be in a busy spin until we succeed in doing this.
         */
        LWLockAcquire(BufferDescriptorGetIOLock(buf), LW_EXCLUSIVE);

        buf_state = LockBufHdr(buf);
        Assert(buf_state & BM_IO_IN_PROGRESS);
        if (IsForInput)
        {
            Assert(!(buf_state & BM_DIRTY));

            /* We'd better not think buffer is valid yet */
            Assert(!(buf_state & BM_VALID));
            UnlockBufHdr(buf, buf_state);
        }
        else
        {
            Assert(buf_state & BM_DIRTY);
            UnlockBufHdr(buf, buf_state);
            /* Issue notice if this is not the first failure... */
            if (buf_state & BM_IO_ERROR)
            {
                /* Buffer is pinned, so we can read tag without spinlock */
                char       *path;

                path = relpathperm(buf->tag.rnode, buf->tag.forkNum);
                ereport(WARNING,
                        (errcode(ERRCODE_IO_ERROR),
                         errmsg("could not write block %u of %s",
                                buf->tag.blockNum, path),
                         errdetail("Multiple failures --- write error might be permanent.")));
                pfree(path);
            }
        }
        TerminateBufferIO(buf, false, BM_IO_ERROR);
    }
}

AtEOXact_Buffers()

void AtEOXact_Buffers

(

bool

isCommit

)

Definition at line 2492 of file bufmgr.c.

References Assert, AtEOXact_LocalBuffers(), CheckForBufferLeaks(), and PrivateRefCountOverflowed.

Referenced by AbortTransaction(), AutoVacLauncherMain(), BackgroundWriterMain(), CheckpointerMain(), CommitTransaction(), PrepareTransaction(), and WalWriterMain().

{
    CheckForBufferLeaks();

    AtEOXact_LocalBuffers(isCommit);

    Assert(PrivateRefCountOverflowed == 0);
}

AtProcExit_Buffers()

static void AtProcExit_Buffers ( int  code, Datum  arg  )

static

Definition at line 2547 of file bufmgr.c.

References AbortBufferIO(), AtProcExit_LocalBuffers(), CheckForBufferLeaks(), and UnlockBuffers().

Referenced by InitBufferPoolBackend().

{
    AbortBufferIO();
    UnlockBuffers();

    CheckForBufferLeaks();

    /* localbuf.c needs a chance too */
    AtProcExit_LocalBuffers();
}

BgBufferSync()

bool BgBufferSync

(

WritebackContext *

wb_context

)

Definition at line 2122 of file bufmgr.c.

References Assert, bgwriter_lru_maxpages, bgwriter_lru_multiplier, BgWriterDelay, BgWriterStats, BUF_REUSABLE, BUF_WRITTEN, CurrentResourceOwner, DEBUG1, DEBUG2, elog, PgStat_MsgBgWriter::m_buf_alloc, PgStat_MsgBgWriter::m_buf_written_clean, PgStat_MsgBgWriter::m_maxwritten_clean, NBuffers, ResourceOwnerEnlargeBuffers(), StrategySyncStart(), and SyncOneBuffer().

Referenced by BackgroundWriterMain().

{
    /* info obtained from freelist.c */
    int         strategy_buf_id;
    uint32      strategy_passes;
    uint32      recent_alloc;

    /*
     * Information saved between calls so we can determine the strategy
     * point's advance rate and avoid scanning already-cleaned buffers.
     */
    static bool saved_info_valid = false;
    static int  prev_strategy_buf_id;
    static uint32 prev_strategy_passes;
    static int  next_to_clean;
    static uint32 next_passes;

    /* Moving averages of allocation rate and clean-buffer density */
    static float smoothed_alloc = 0;
    static float smoothed_density = 10.0;

    /* Potentially these could be tunables, but for now, not */
    float       smoothing_samples = 16;
    float       scan_whole_pool_milliseconds = 120000.0;

    /* Used to compute how far we scan ahead */
    long        strategy_delta;
    int         bufs_to_lap;
    int         bufs_ahead;
    float       scans_per_alloc;
    int         reusable_buffers_est;
    int         upcoming_alloc_est;
    int         min_scan_buffers;

    /* Variables for the scanning loop proper */
    int         num_to_scan;
    int         num_written;
    int         reusable_buffers;

    /* Variables for final smoothed_density update */
    long        new_strategy_delta;
    uint32      new_recent_alloc;

    /*
     * Find out where the freelist clock sweep currently is, and how many
     * buffer allocations have happened since our last call.
     */
    strategy_buf_id = StrategySyncStart(&strategy_passes, &recent_alloc);

    /* Report buffer alloc counts to pgstat */
    BgWriterStats.m_buf_alloc += recent_alloc;

    /*
     * If we're not running the LRU scan, just stop after doing the stats
     * stuff.  We mark the saved state invalid so that we can recover sanely
     * if LRU scan is turned back on later.
     */
    if (bgwriter_lru_maxpages <= 0)
    {
        saved_info_valid = false;
        return true;
    }

    /*
     * Compute strategy_delta = how many buffers have been scanned by the
     * clock sweep since last time.  If first time through, assume none. Then
     * see if we are still ahead of the clock sweep, and if so, how many
     * buffers we could scan before we'd catch up with it and "lap" it. Note:
     * weird-looking coding of xxx_passes comparisons are to avoid bogus
     * behavior when the passes counts wrap around.
     */
    if (saved_info_valid)
    {
        int32       passes_delta = strategy_passes - prev_strategy_passes;

        strategy_delta = strategy_buf_id - prev_strategy_buf_id;
        strategy_delta += (long) passes_delta * NBuffers;

        Assert(strategy_delta >= 0);

        if ((int32) (next_passes - strategy_passes) > 0)
        {
            /* we're one pass ahead of the strategy point */
            bufs_to_lap = strategy_buf_id - next_to_clean;
#ifdef BGW_DEBUG
            elog(DEBUG2, "bgwriter ahead: bgw %u-%u strategy %u-%u delta=%ld lap=%d",
                 next_passes, next_to_clean,
                 strategy_passes, strategy_buf_id,
                 strategy_delta, bufs_to_lap);
#endif
        }
        else if (next_passes == strategy_passes &&
                 next_to_clean >= strategy_buf_id)
        {
            /* on same pass, but ahead or at least not behind */
            bufs_to_lap = NBuffers - (next_to_clean - strategy_buf_id);
#ifdef BGW_DEBUG
            elog(DEBUG2, "bgwriter ahead: bgw %u-%u strategy %u-%u delta=%ld lap=%d",
                 next_passes, next_to_clean,
                 strategy_passes, strategy_buf_id,
                 strategy_delta, bufs_to_lap);
#endif
        }
        else
        {
            /*
             * We're behind, so skip forward to the strategy point and start
             * cleaning from there.
             */
#ifdef BGW_DEBUG
            elog(DEBUG2, "bgwriter behind: bgw %u-%u strategy %u-%u delta=%ld",
                 next_passes, next_to_clean,
                 strategy_passes, strategy_buf_id,
                 strategy_delta);
#endif
            next_to_clean = strategy_buf_id;
            next_passes = strategy_passes;
            bufs_to_lap = NBuffers;
        }
    }
    else
    {
        /*
         * Initializing at startup or after LRU scanning had been off. Always
         * start at the strategy point.
         */
#ifdef BGW_DEBUG
        elog(DEBUG2, "bgwriter initializing: strategy %u-%u",
             strategy_passes, strategy_buf_id);
#endif
        strategy_delta = 0;
        next_to_clean = strategy_buf_id;
        next_passes = strategy_passes;
        bufs_to_lap = NBuffers;
    }

    /* Update saved info for next time */
    prev_strategy_buf_id = strategy_buf_id;
    prev_strategy_passes = strategy_passes;
    saved_info_valid = true;

    /*
     * Compute how many buffers had to be scanned for each new allocation, ie,
     * 1/density of reusable buffers, and track a moving average of that.
     *
     * If the strategy point didn't move, we don't update the density estimate
     */
    if (strategy_delta > 0 && recent_alloc > 0)
    {
        scans_per_alloc = (float) strategy_delta / (float) recent_alloc;
        smoothed_density += (scans_per_alloc - smoothed_density) /
            smoothing_samples;
    }

    /*
     * Estimate how many reusable buffers there are between the current
     * strategy point and where we've scanned ahead to, based on the smoothed
     * density estimate.
     */
    bufs_ahead = NBuffers - bufs_to_lap;
    reusable_buffers_est = (float) bufs_ahead / smoothed_density;

    /*
     * Track a moving average of recent buffer allocations.  Here, rather than
     * a true average we want a fast-attack, slow-decline behavior: we
     * immediately follow any increase.
     */
    if (smoothed_alloc <= (float) recent_alloc)
        smoothed_alloc = recent_alloc;
    else
        smoothed_alloc += ((float) recent_alloc - smoothed_alloc) /
            smoothing_samples;

    /* Scale the estimate by a GUC to allow more aggressive tuning. */
    upcoming_alloc_est = (int) (smoothed_alloc * bgwriter_lru_multiplier);

    /*
     * If recent_alloc remains at zero for many cycles, smoothed_alloc will
     * eventually underflow to zero, and the underflows produce annoying
     * kernel warnings on some platforms.  Once upcoming_alloc_est has gone to
     * zero, there's no point in tracking smaller and smaller values of
     * smoothed_alloc, so just reset it to exactly zero to avoid this
     * syndrome.  It will pop back up as soon as recent_alloc increases.
     */
    if (upcoming_alloc_est == 0)
        smoothed_alloc = 0;

    /*
     * Even in cases where there's been little or no buffer allocation
     * activity, we want to make a small amount of progress through the buffer
     * cache so that as many reusable buffers as possible are clean after an
     * idle period.
     *
     * (scan_whole_pool_milliseconds / BgWriterDelay) computes how many times
     * the BGW will be called during the scan_whole_pool time; slice the
     * buffer pool into that many sections.
     */
    min_scan_buffers = (int) (NBuffers / (scan_whole_pool_milliseconds / BgWriterDelay));

    if (upcoming_alloc_est < (min_scan_buffers + reusable_buffers_est))
    {
#ifdef BGW_DEBUG
        elog(DEBUG2, "bgwriter: alloc_est=%d too small, using min=%d + reusable_est=%d",
             upcoming_alloc_est, min_scan_buffers, reusable_buffers_est);
#endif
        upcoming_alloc_est = min_scan_buffers + reusable_buffers_est;
    }

    /*
     * Now write out dirty reusable buffers, working forward from the
     * next_to_clean point, until we have lapped the strategy scan, or cleaned
     * enough buffers to match our estimate of the next cycle's allocation
     * requirements, or hit the bgwriter_lru_maxpages limit.
     */

    /* Make sure we can handle the pin inside SyncOneBuffer */
    ResourceOwnerEnlargeBuffers(CurrentResourceOwner);

    num_to_scan = bufs_to_lap;
    num_written = 0;
    reusable_buffers = reusable_buffers_est;

    /* Execute the LRU scan */
    while (num_to_scan > 0 && reusable_buffers < upcoming_alloc_est)
    {
        int         sync_state = SyncOneBuffer(next_to_clean, true,
                                               wb_context);

        if (++next_to_clean >= NBuffers)
        {
            next_to_clean = 0;
            next_passes++;
        }
        num_to_scan--;

        if (sync_state & BUF_WRITTEN)
        {
            reusable_buffers++;
            if (++num_written >= bgwriter_lru_maxpages)
            {
                BgWriterStats.m_maxwritten_clean++;
                break;
            }
        }
        else if (sync_state & BUF_REUSABLE)
            reusable_buffers++;
    }

    BgWriterStats.m_buf_written_clean += num_written;

#ifdef BGW_DEBUG
    elog(DEBUG1, "bgwriter: recent_alloc=%u smoothed=%.2f delta=%ld ahead=%d density=%.2f reusable_est=%d upcoming_est=%d scanned=%d wrote=%d reusable=%d",
         recent_alloc, smoothed_alloc, strategy_delta, bufs_ahead,
         smoothed_density, reusable_buffers_est, upcoming_alloc_est,
         bufs_to_lap - num_to_scan,
         num_written,
         reusable_buffers - reusable_buffers_est);
#endif

    /*
     * Consider the above scan as being like a new allocation scan.
     * Characterize its density and update the smoothed one based on it. This
     * effectively halves the moving average period in cases where both the
     * strategy and the background writer are doing some useful scanning,
     * which is helpful because a long memory isn't as desirable on the
     * density estimates.
     */
    new_strategy_delta = bufs_to_lap - num_to_scan;
    new_recent_alloc = reusable_buffers - reusable_buffers_est;
    if (new_strategy_delta > 0 && new_recent_alloc > 0)
    {
        scans_per_alloc = (float) new_strategy_delta / (float) new_recent_alloc;
        smoothed_density += (scans_per_alloc - smoothed_density) /
            smoothing_samples;

#ifdef BGW_DEBUG
        elog(DEBUG2, "bgwriter: cleaner density alloc=%u scan=%ld density=%.2f new smoothed=%.2f",
             new_recent_alloc, new_strategy_delta,
             scans_per_alloc, smoothed_density);
#endif
    }

    /* Return true if OK to hibernate */
    return (bufs_to_lap == 0 && recent_alloc == 0);
}

BufferAlloc()

static BufferDesc * BufferAlloc ( SMgrRelation  smgr, char  relpersistence, ForkNumber  forkNum, BlockNumber  blockNum, BufferAccessStrategy  strategy, bool *  foundPtr  )

static

Definition at line 1020 of file bufmgr.c.

References Assert, BackendWritebackContext, BM_CHECKPOINT_NEEDED, BM_DIRTY, BM_IO_ERROR, BM_JUST_DIRTIED, BM_PERMANENT, BM_TAG_VALID, BM_VALID, buf, BUF_FLAG_MASK, BufferDesc::buf_id, BUF_STATE_GET_REFCOUNT, BUF_USAGECOUNT_MASK, BUF_USAGECOUNT_ONE, BufferDescriptorGetContentLock, BufferGetLSN, BufMappingPartitionLock, BufTableDelete(), BufTableHashCode(), BufTableInsert(), BufTableLookup(), RelFileNode::dbNode, FlushBuffer(), GetBufferDescriptor, INIT_BUFFERTAG, INIT_FORKNUM, LockBufHdr(), LW_EXCLUSIVE, LW_SHARED, LWLockAcquire(), LWLockConditionalAcquire(), LWLockRelease(), RelFileNodeBackend::node, PinBuffer(), PinBuffer_Locked(), RelFileNode::relNode, ReservePrivateRefCountEntry(), ScheduleBufferTagForWriteback(), SMgrRelationData::smgr_rnode, RelFileNode::spcNode, StartBufferIO(), StrategyGetBuffer(), StrategyRejectBuffer(), BufferDesc::tag, UnlockBufHdr, UnpinBuffer(), and XLogNeedsFlush().

Referenced by ReadBuffer_common().

{
    BufferTag   newTag;         /* identity of requested block */
    uint32      newHash;        /* hash value for newTag */
    LWLock     *newPartitionLock;   /* buffer partition lock for it */
    BufferTag   oldTag;         /* previous identity of selected buffer */
    uint32      oldHash;        /* hash value for oldTag */
    LWLock     *oldPartitionLock;   /* buffer partition lock for it */
    uint32      oldFlags;
    int         buf_id;
    BufferDesc *buf;
    bool        valid;
    uint32      buf_state;

    /* create a tag so we can lookup the buffer */
    INIT_BUFFERTAG(newTag, smgr->smgr_rnode.node, forkNum, blockNum);

    /* determine its hash code and partition lock ID */
    newHash = BufTableHashCode(&newTag);
    newPartitionLock = BufMappingPartitionLock(newHash);

    /* see if the block is in the buffer pool already */
    LWLockAcquire(newPartitionLock, LW_SHARED);
    buf_id = BufTableLookup(&newTag, newHash);
    if (buf_id >= 0)
    {
        /*
         * Found it.  Now, pin the buffer so no one can steal it from the
         * buffer pool, and check to see if the correct data has been loaded
         * into the buffer.
         */
        buf = GetBufferDescriptor(buf_id);

        valid = PinBuffer(buf, strategy);

        /* Can release the mapping lock as soon as we've pinned it */
        LWLockRelease(newPartitionLock);

        *foundPtr = true;

        if (!valid)
        {
            /*
             * We can only get here if (a) someone else is still reading in
             * the page, or (b) a previous read attempt failed.  We have to
             * wait for any active read attempt to finish, and then set up our
             * own read attempt if the page is still not BM_VALID.
             * StartBufferIO does it all.
             */
            if (StartBufferIO(buf, true))
            {
                /*
                 * If we get here, previous attempts to read the buffer must
                 * have failed ... but we shall bravely try again.
                 */
                *foundPtr = false;
            }
        }

        return buf;
    }

    /*
     * Didn't find it in the buffer pool.  We'll have to initialize a new
     * buffer.  Remember to unlock the mapping lock while doing the work.
     */
    LWLockRelease(newPartitionLock);

    /* Loop here in case we have to try another victim buffer */
    for (;;)
    {
        /*
         * Ensure, while the spinlock's not yet held, that there's a free
         * refcount entry.
         */
        ReservePrivateRefCountEntry();

        /*
         * Select a victim buffer.  The buffer is returned with its header
         * spinlock still held!
         */
        buf = StrategyGetBuffer(strategy, &buf_state);

        Assert(BUF_STATE_GET_REFCOUNT(buf_state) == 0);

        /* Must copy buffer flags while we still hold the spinlock */
        oldFlags = buf_state & BUF_FLAG_MASK;

        /* Pin the buffer and then release the buffer spinlock */
        PinBuffer_Locked(buf);

        /*
         * If the buffer was dirty, try to write it out.  There is a race
         * condition here, in that someone might dirty it after we released it
         * above, or even while we are writing it out (since our share-lock
         * won't prevent hint-bit updates).  We will recheck the dirty bit
         * after re-locking the buffer header.
         */
        if (oldFlags & BM_DIRTY)
        {
            /*
             * We need a share-lock on the buffer contents to write it out
             * (else we might write invalid data, eg because someone else is
             * compacting the page contents while we write).  We must use a
             * conditional lock acquisition here to avoid deadlock.  Even
             * though the buffer was not pinned (and therefore surely not
             * locked) when StrategyGetBuffer returned it, someone else could
             * have pinned and exclusive-locked it by the time we get here. If
             * we try to get the lock unconditionally, we'd block waiting for
             * them; if they later block waiting for us, deadlock ensues.
             * (This has been observed to happen when two backends are both
             * trying to split btree index pages, and the second one just
             * happens to be trying to split the page the first one got from
             * StrategyGetBuffer.)
             */
            if (LWLockConditionalAcquire(BufferDescriptorGetContentLock(buf),
                                         LW_SHARED))
            {
                /*
                 * If using a nondefault strategy, and writing the buffer
                 * would require a WAL flush, let the strategy decide whether
                 * to go ahead and write/reuse the buffer or to choose another
                 * victim.  We need lock to inspect the page LSN, so this
                 * can't be done inside StrategyGetBuffer.
                 */
                if (strategy != NULL)
                {
                    XLogRecPtr  lsn;

                    /* Read the LSN while holding buffer header lock */
                    buf_state = LockBufHdr(buf);
                    lsn = BufferGetLSN(buf);
                    UnlockBufHdr(buf, buf_state);

                    if (XLogNeedsFlush(lsn) &&
                        StrategyRejectBuffer(strategy, buf))
                    {
                        /* Drop lock/pin and loop around for another buffer */
                        LWLockRelease(BufferDescriptorGetContentLock(buf));
                        UnpinBuffer(buf, true);
                        continue;
                    }
                }

                /* OK, do the I/O */
                TRACE_POSTGRESQL_BUFFER_WRITE_DIRTY_START(forkNum, blockNum,
                                                          smgr->smgr_rnode.node.spcNode,
                                                          smgr->smgr_rnode.node.dbNode,
                                                          smgr->smgr_rnode.node.relNode);

                FlushBuffer(buf, NULL);
                LWLockRelease(BufferDescriptorGetContentLock(buf));

                ScheduleBufferTagForWriteback(&BackendWritebackContext,
                                              &buf->tag);

                TRACE_POSTGRESQL_BUFFER_WRITE_DIRTY_DONE(forkNum, blockNum,
                                                         smgr->smgr_rnode.node.spcNode,
                                                         smgr->smgr_rnode.node.dbNode,
                                                         smgr->smgr_rnode.node.relNode);
            }
            else
            {
                /*
                 * Someone else has locked the buffer, so give it up and loop
                 * back to get another one.
                 */
                UnpinBuffer(buf, true);
                continue;
            }
        }

        /*
         * To change the association of a valid buffer, we'll need to have
         * exclusive lock on both the old and new mapping partitions.
         */
        if (oldFlags & BM_TAG_VALID)
        {
            /*
             * Need to compute the old tag's hashcode and partition lock ID.
             * XXX is it worth storing the hashcode in BufferDesc so we need
             * not recompute it here?  Probably not.
             */
            oldTag = buf->tag;
            oldHash = BufTableHashCode(&oldTag);
            oldPartitionLock = BufMappingPartitionLock(oldHash);

            /*
             * Must lock the lower-numbered partition first to avoid
             * deadlocks.
             */
            if (oldPartitionLock < newPartitionLock)
            {
                LWLockAcquire(oldPartitionLock, LW_EXCLUSIVE);
                LWLockAcquire(newPartitionLock, LW_EXCLUSIVE);
            }
            else if (oldPartitionLock > newPartitionLock)
            {
                LWLockAcquire(newPartitionLock, LW_EXCLUSIVE);
                LWLockAcquire(oldPartitionLock, LW_EXCLUSIVE);
            }
            else
            {
                /* only one partition, only one lock */
                LWLockAcquire(newPartitionLock, LW_EXCLUSIVE);
            }
        }
        else
        {
            /* if it wasn't valid, we need only the new partition */
            LWLockAcquire(newPartitionLock, LW_EXCLUSIVE);
            /* remember we have no old-partition lock or tag */
            oldPartitionLock = NULL;
            /* keep the compiler quiet about uninitialized variables */
            oldHash = 0;
        }

        /*
         * Try to make a hashtable entry for the buffer under its new tag.
         * This could fail because while we were writing someone else
         * allocated another buffer for the same block we want to read in.
         * Note that we have not yet removed the hashtable entry for the old
         * tag.
         */
        buf_id = BufTableInsert(&newTag, newHash, buf->buf_id);

        if (buf_id >= 0)
        {
            /*
             * Got a collision. Someone has already done what we were about to
             * do. We'll just handle this as if it were found in the buffer
             * pool in the first place.  First, give up the buffer we were
             * planning to use.
             */
            UnpinBuffer(buf, true);

            /* Can give up that buffer's mapping partition lock now */
            if (oldPartitionLock != NULL &&
                oldPartitionLock != newPartitionLock)
                LWLockRelease(oldPartitionLock);

            /* remaining code should match code at top of routine */

            buf = GetBufferDescriptor(buf_id);

            valid = PinBuffer(buf, strategy);

            /* Can release the mapping lock as soon as we've pinned it */
            LWLockRelease(newPartitionLock);

            *foundPtr = true;

            if (!valid)
            {
                /*
                 * We can only get here if (a) someone else is still reading
                 * in the page, or (b) a previous read attempt failed.  We
                 * have to wait for any active read attempt to finish, and
                 * then set up our own read attempt if the page is still not
                 * BM_VALID.  StartBufferIO does it all.
                 */
                if (StartBufferIO(buf, true))
                {
                    /*
                     * If we get here, previous attempts to read the buffer
                     * must have failed ... but we shall bravely try again.
                     */
                    *foundPtr = false;
                }
            }

            return buf;
        }

        /*
         * Need to lock the buffer header too in order to change its tag.
         */
        buf_state = LockBufHdr(buf);

        /*
         * Somebody could have pinned or re-dirtied the buffer while we were
         * doing the I/O and making the new hashtable entry.  If so, we can't
         * recycle this buffer; we must undo everything we've done and start
         * over with a new victim buffer.
         */
        oldFlags = buf_state & BUF_FLAG_MASK;
        if (BUF_STATE_GET_REFCOUNT(buf_state) == 1 && !(oldFlags & BM_DIRTY))
            break;

        UnlockBufHdr(buf, buf_state);
        BufTableDelete(&newTag, newHash);
        if (oldPartitionLock != NULL &&
            oldPartitionLock != newPartitionLock)
            LWLockRelease(oldPartitionLock);
        LWLockRelease(newPartitionLock);
        UnpinBuffer(buf, true);
    }

    /*
     * Okay, it's finally safe to rename the buffer.
     *
     * Clearing BM_VALID here is necessary, clearing the dirtybits is just
     * paranoia.  We also reset the usage_count since any recency of use of
     * the old content is no longer relevant.  (The usage_count starts out at
     * 1 so that the buffer can survive one clock-sweep pass.)
     *
     * Make sure BM_PERMANENT is set for buffers that must be written at every
     * checkpoint.  Unlogged buffers only need to be written at shutdown
     * checkpoints, except for their "init" forks, which need to be treated
     * just like permanent relations.
     */
    buf->tag = newTag;
    buf_state &= ~(BM_VALID | BM_DIRTY | BM_JUST_DIRTIED |
                   BM_CHECKPOINT_NEEDED | BM_IO_ERROR | BM_PERMANENT |
                   BUF_USAGECOUNT_MASK);
    if (relpersistence == RELPERSISTENCE_PERMANENT || forkNum == INIT_FORKNUM)
        buf_state |= BM_TAG_VALID | BM_PERMANENT | BUF_USAGECOUNT_ONE;
    else
        buf_state |= BM_TAG_VALID | BUF_USAGECOUNT_ONE;

    UnlockBufHdr(buf, buf_state);

    if (oldPartitionLock != NULL)
    {
        BufTableDelete(&oldTag, oldHash);
        if (oldPartitionLock != newPartitionLock)
            LWLockRelease(oldPartitionLock);
    }

    LWLockRelease(newPartitionLock);

    /*
     * Buffer contents are currently invalid.  Try to get the io_in_progress
     * lock.  If StartBufferIO returns false, then someone else managed to
     * read it before we did, so there's nothing left for BufferAlloc() to do.
     */
    if (StartBufferIO(buf, true))
        *foundPtr = false;
    else
        *foundPtr = true;

    return buf;
}

BufferGetBlockNumber()

BlockNumber BufferGetBlockNumber

(

Buffer

buffer

)

Definition at line 2674 of file bufmgr.c.

References Assert, buftag::blockNum, BufferIsLocal, BufferIsPinned, GetBufferDescriptor, GetLocalBufferDescriptor, and BufferDesc::tag.

Referenced by _bt_check_unique(), _bt_checkpage(), _bt_delitems_delete(), _bt_delitems_vacuum(), _bt_doinsert(), _bt_endpoint(), _bt_finish_split(), _bt_first(), _bt_getroot(), _bt_insert_parent(), _bt_insertonpg(), _bt_mark_page_halfdead(), _bt_moveright(), _bt_newroot(), _bt_pagedel(), _bt_readnextpage(), _bt_readpage(), _bt_restore_meta(), _bt_search(), _bt_split(), _bt_unlink_halfdead_page(), _bt_walk_left(), _hash_addovflpage(), _hash_checkpage(), _hash_doinsert(), _hash_first(), _hash_freeovflpage(), _hash_getnewbuf(), _hash_readnext(), _hash_readpage(), _hash_splitbucket(), allocNewBuffer(), blinsert(), BloomInitMetapage(), brin_doinsert(), brin_doupdate(), brin_getinsertbuffer(), brin_initialize_empty_new_buffer(), brin_page_cleanup(), brin_xlog_insert_update(), brinbuild(), brinGetTupleForHeapBlock(), createPostingTree(), dataBeginPlaceToPageLeaf(), dataPrepareDownlink(), doPickSplit(), entryPrepareDownlink(), fill_seq_with_data(), ginEntryInsert(), ginFindParents(), ginFinishSplit(), ginPlaceToPage(), ginRedoDeleteListPages(), ginRedoUpdateMetapage(), ginScanToDelete(), gistbufferinginserttuples(), gistbuild(), gistcheckpage(), gistdeletepage(), gistformdownlink(), gistinserttuples(), gistMemorizeAllDownlinks(), gistplacetopage(), gistRelocateBuildBuffersOnSplit(), gistScanPage(), hash_xlog_add_ovfl_page(), heap_delete(), heap_hot_search_buffer(), heap_insert(), heap_multi_insert(), heap_page_is_all_visible(), heap_prune_chain(), heap_update(), heap_xlog_confirm(), heap_xlog_lock(), makeSublist(), moveLeafs(), moveRightIfItNeeded(), pgstathashindex(), ReadBufferBI(), RelationAddExtraBlocks(), RelationGetBufferForTuple(), RelationPutHeapTuple(), revmap_get_buffer(), revmap_physical_extend(), spgAddNodeAction(), spgbuild(), spgdoinsert(), SpGistSetLastUsedPage(), spgSplitNodeAction(), spgWalk(), startScanEntry(), terminate_brin_buildstate(), vacuumLeafPage(), visibilitymap_clear(), visibilitymap_get_status(), visibilitymap_pin(), visibilitymap_pin_ok(), visibilitymap_set(), and XLogReadBufferExtended().

{
    BufferDesc *bufHdr;

    Assert(BufferIsPinned(buffer));

    if (BufferIsLocal(buffer))
        bufHdr = GetLocalBufferDescriptor(-buffer - 1);
    else
        bufHdr = GetBufferDescriptor(buffer - 1);

    /* pinned, so OK to read tag without spinlock */
    return bufHdr->tag.blockNum;
}

BufferGetLSNAtomic()

XLogRecPtr BufferGetLSNAtomic

(

Buffer

buffer

)

Definition at line 2937 of file bufmgr.c.

References Assert, BufferGetPage, BufferIsLocal, BufferIsPinned, BufferIsValid, GetBufferDescriptor, LockBufHdr(), PageGetLSN, UnlockBufHdr, and XLogHintBitIsNeeded.

Referenced by _bt_killitems(), _bt_readpage(), gistdoinsert(), gistFindPath(), gistkillitems(), gistScanPage(), SetHintBits(), and XLogSaveBufferForHint().

{
    BufferDesc *bufHdr = GetBufferDescriptor(buffer - 1);
    char       *page = BufferGetPage(buffer);
    XLogRecPtr  lsn;
    uint32      buf_state;

    /*
     * If we don't need locking for correctness, fastpath out.
     */
    if (!XLogHintBitIsNeeded() || BufferIsLocal(buffer))
        return PageGetLSN(page);

    /* Make sure we've got a real buffer, and that we hold a pin on it. */
    Assert(BufferIsValid(buffer));
    Assert(BufferIsPinned(buffer));

    buf_state = LockBufHdr(bufHdr);
    lsn = PageGetLSN(page);
    UnlockBufHdr(bufHdr, buf_state);

    return lsn;
}

BufferGetTag()

void BufferGetTag	(	Buffer	buffer,
		RelFileNode *	rnode,
		ForkNumber *	forknum,
		BlockNumber *	blknum
	)

Definition at line 2695 of file bufmgr.c.

References Assert, buftag::blockNum, BufferIsLocal, BufferIsPinned, buftag::forkNum, GetBufferDescriptor, GetLocalBufferDescriptor, buftag::rnode, and BufferDesc::tag.

Referenced by fsm_search_avail(), ginRedoInsertEntry(), log_newpage_buffer(), ResolveCminCmaxDuringDecoding(), XLogRegisterBuffer(), and XLogSaveBufferForHint().

{
    BufferDesc *bufHdr;

    /* Do the same checks as BufferGetBlockNumber. */
    Assert(BufferIsPinned(buffer));

    if (BufferIsLocal(buffer))
        bufHdr = GetLocalBufferDescriptor(-buffer - 1);
    else
        bufHdr = GetBufferDescriptor(buffer - 1);

    /* pinned, so OK to read tag without spinlock */
    *rnode = bufHdr->tag.rnode;
    *forknum = bufHdr->tag.forkNum;
    *blknum = bufHdr->tag.blockNum;
}

BufferIsPermanent()

bool BufferIsPermanent

(

Buffer

buffer

)

Definition at line 2907 of file bufmgr.c.

References Assert, BM_PERMANENT, BufferIsLocal, BufferIsPinned, BufferIsValid, GetBufferDescriptor, pg_atomic_read_u32(), and BufferDesc::state.

Referenced by SetHintBits().

{
    BufferDesc *bufHdr;

    /* Local buffers are used only for temp relations. */
    if (BufferIsLocal(buffer))
        return false;

    /* Make sure we've got a real buffer, and that we hold a pin on it. */
    Assert(BufferIsValid(buffer));
    Assert(BufferIsPinned(buffer));

    /*
     * BM_PERMANENT can't be changed while we hold a pin on the buffer, so we
     * need not bother with the buffer header spinlock.  Even if someone else
     * changes the buffer header state while we're doing this, the state is
     * changed atomically, so we'll read the old value or the new value, but
     * not random garbage.
     */
    bufHdr = GetBufferDescriptor(buffer - 1);
    return (pg_atomic_read_u32(&bufHdr->state) & BM_PERMANENT) != 0;
}

BufferSync()

static void BufferSync ( int  flags )

static

Definition at line 1845 of file bufmgr.c.

References Assert, BgWriterStats, binaryheap_add_unordered(), binaryheap_allocate(), binaryheap_build(), binaryheap_empty, binaryheap_first(), binaryheap_free(), binaryheap_remove_first(), binaryheap_replace_first(), buftag::blockNum, CkptSortItem::blockNum, BM_CHECKPOINT_NEEDED, BM_DIRTY, BM_PERMANENT, CkptSortItem::buf_id, BUF_WRITTEN, CHECKPOINT_END_OF_RECOVERY, checkpoint_flush_after, CHECKPOINT_FLUSH_ALL, CHECKPOINT_IS_SHUTDOWN, CheckpointStats, CheckpointWriteDelay(), ckpt_buforder_comparator(), CheckpointStatsData::ckpt_bufs_written, CkptBufferIds, CurrentResourceOwner, DatumGetPointer, buftag::forkNum, CkptSortItem::forkNum, GetBufferDescriptor, i, CkptTsStatus::index, InvalidOid, IssuePendingWritebacks(), LockBufHdr(), PgStat_MsgBgWriter::m_buf_written_checkpoints, NBuffers, CkptTsStatus::num_scanned, CkptTsStatus::num_to_scan, palloc(), pfree(), pg_atomic_read_u32(), PointerGetDatum, ProcessProcSignalBarrier(), ProcSignalBarrierPending, CkptTsStatus::progress, CkptTsStatus::progress_slice, qsort, RelFileNode::relNode, CkptSortItem::relNode, repalloc(), ResourceOwnerEnlargeBuffers(), buftag::rnode, RelFileNode::spcNode, BufferDesc::state, SyncOneBuffer(), BufferDesc::tag, ts_ckpt_progress_comparator(), CkptTsStatus::tsId, CkptSortItem::tsId, UnlockBufHdr, and WritebackContextInit().

Referenced by CheckPointBuffers().

{
    uint32      buf_state;
    int         buf_id;
    int         num_to_scan;
    int         num_spaces;
    int         num_processed;
    int         num_written;
    CkptTsStatus *per_ts_stat = NULL;
    Oid         last_tsid;
    binaryheap *ts_heap;
    int         i;
    int         mask = BM_DIRTY;
    WritebackContext wb_context;

    /* Make sure we can handle the pin inside SyncOneBuffer */
    ResourceOwnerEnlargeBuffers(CurrentResourceOwner);

    /*
     * Unless this is a shutdown checkpoint or we have been explicitly told,
     * we write only permanent, dirty buffers.  But at shutdown or end of
     * recovery, we write all dirty buffers.
     */
    if (!((flags & (CHECKPOINT_IS_SHUTDOWN | CHECKPOINT_END_OF_RECOVERY |
                    CHECKPOINT_FLUSH_ALL))))
        mask |= BM_PERMANENT;

    /*
     * Loop over all buffers, and mark the ones that need to be written with
     * BM_CHECKPOINT_NEEDED.  Count them as we go (num_to_scan), so that we
     * can estimate how much work needs to be done.
     *
     * This allows us to write only those pages that were dirty when the
     * checkpoint began, and not those that get dirtied while it proceeds.
     * Whenever a page with BM_CHECKPOINT_NEEDED is written out, either by us
     * later in this function, or by normal backends or the bgwriter cleaning
     * scan, the flag is cleared.  Any buffer dirtied after this point won't
     * have the flag set.
     *
     * Note that if we fail to write some buffer, we may leave buffers with
     * BM_CHECKPOINT_NEEDED still set.  This is OK since any such buffer would
     * certainly need to be written for the next checkpoint attempt, too.
     */
    num_to_scan = 0;
    for (buf_id = 0; buf_id < NBuffers; buf_id++)
    {
        BufferDesc *bufHdr = GetBufferDescriptor(buf_id);

        /*
         * Header spinlock is enough to examine BM_DIRTY, see comment in
         * SyncOneBuffer.
         */
        buf_state = LockBufHdr(bufHdr);

        if ((buf_state & mask) == mask)
        {
            CkptSortItem *item;

            buf_state |= BM_CHECKPOINT_NEEDED;

            item = &CkptBufferIds[num_to_scan++];
            item->buf_id = buf_id;
            item->tsId = bufHdr->tag.rnode.spcNode;
            item->relNode = bufHdr->tag.rnode.relNode;
            item->forkNum = bufHdr->tag.forkNum;
            item->blockNum = bufHdr->tag.blockNum;
        }

        UnlockBufHdr(bufHdr, buf_state);

        /* Check for barrier events in case NBuffers is large. */
        if (ProcSignalBarrierPending)
            ProcessProcSignalBarrier();
    }

    if (num_to_scan == 0)
        return;                 /* nothing to do */

    WritebackContextInit(&wb_context, &checkpoint_flush_after);

    TRACE_POSTGRESQL_BUFFER_SYNC_START(NBuffers, num_to_scan);

    /*
     * Sort buffers that need to be written to reduce the likelihood of random
     * IO. The sorting is also important for the implementation of balancing
     * writes between tablespaces. Without balancing writes we'd potentially
     * end up writing to the tablespaces one-by-one; possibly overloading the
     * underlying system.
     */
    qsort(CkptBufferIds, num_to_scan, sizeof(CkptSortItem),
          ckpt_buforder_comparator);

    num_spaces = 0;

    /*
     * Allocate progress status for each tablespace with buffers that need to
     * be flushed. This requires the to-be-flushed array to be sorted.
     */
    last_tsid = InvalidOid;
    for (i = 0; i < num_to_scan; i++)
    {
        CkptTsStatus *s;
        Oid         cur_tsid;

        cur_tsid = CkptBufferIds[i].tsId;

        /*
         * Grow array of per-tablespace status structs, every time a new
         * tablespace is found.
         */
        if (last_tsid == InvalidOid || last_tsid != cur_tsid)
        {
            Size        sz;

            num_spaces++;

            /*
             * Not worth adding grow-by-power-of-2 logic here - even with a
             * few hundred tablespaces this should be fine.
             */
            sz = sizeof(CkptTsStatus) * num_spaces;

            if (per_ts_stat == NULL)
                per_ts_stat = (CkptTsStatus *) palloc(sz);
            else
                per_ts_stat = (CkptTsStatus *) repalloc(per_ts_stat, sz);

            s = &per_ts_stat[num_spaces - 1];
            memset(s, 0, sizeof(*s));
            s->tsId = cur_tsid;

            /*
             * The first buffer in this tablespace. As CkptBufferIds is sorted
             * by tablespace all (s->num_to_scan) buffers in this tablespace
             * will follow afterwards.
             */
            s->index = i;

            /*
             * progress_slice will be determined once we know how many buffers
             * are in each tablespace, i.e. after this loop.
             */

            last_tsid = cur_tsid;
        }
        else
        {
            s = &per_ts_stat[num_spaces - 1];
        }

        s->num_to_scan++;

        /* Check for barrier events. */
        if (ProcSignalBarrierPending)
            ProcessProcSignalBarrier();
    }

    Assert(num_spaces > 0);

    /*
     * Build a min-heap over the write-progress in the individual tablespaces,
     * and compute how large a portion of the total progress a single
     * processed buffer is.
     */
    ts_heap = binaryheap_allocate(num_spaces,
                                  ts_ckpt_progress_comparator,
                                  NULL);

    for (i = 0; i < num_spaces; i++)
    {
        CkptTsStatus *ts_stat = &per_ts_stat[i];

        ts_stat->progress_slice = (float8) num_to_scan / ts_stat->num_to_scan;

        binaryheap_add_unordered(ts_heap, PointerGetDatum(ts_stat));
    }

    binaryheap_build(ts_heap);

    /*
     * Iterate through to-be-checkpointed buffers and write the ones (still)
     * marked with BM_CHECKPOINT_NEEDED. The writes are balanced between
     * tablespaces; otherwise the sorting would lead to only one tablespace
     * receiving writes at a time, making inefficient use of the hardware.
     */
    num_processed = 0;
    num_written = 0;
    while (!binaryheap_empty(ts_heap))
    {
        BufferDesc *bufHdr = NULL;
        CkptTsStatus *ts_stat = (CkptTsStatus *)
        DatumGetPointer(binaryheap_first(ts_heap));

        buf_id = CkptBufferIds[ts_stat->index].buf_id;
        Assert(buf_id != -1);

        bufHdr = GetBufferDescriptor(buf_id);

        num_processed++;

        /*
         * We don't need to acquire the lock here, because we're only looking
         * at a single bit. It's possible that someone else writes the buffer
         * and clears the flag right after we check, but that doesn't matter
         * since SyncOneBuffer will then do nothing.  However, there is a
         * further race condition: it's conceivable that between the time we
         * examine the bit here and the time SyncOneBuffer acquires the lock,
         * someone else not only wrote the buffer but replaced it with another
         * page and dirtied it.  In that improbable case, SyncOneBuffer will
         * write the buffer though we didn't need to.  It doesn't seem worth
         * guarding against this, though.
         */
        if (pg_atomic_read_u32(&bufHdr->state) & BM_CHECKPOINT_NEEDED)
        {
            if (SyncOneBuffer(buf_id, false, &wb_context) & BUF_WRITTEN)
            {
                TRACE_POSTGRESQL_BUFFER_SYNC_WRITTEN(buf_id);
                BgWriterStats.m_buf_written_checkpoints++;
                num_written++;
            }
        }

        /*
         * Measure progress independent of actually having to flush the buffer
         * - otherwise writing become unbalanced.
         */
        ts_stat->progress += ts_stat->progress_slice;
        ts_stat->num_scanned++;
        ts_stat->index++;

        /* Have all the buffers from the tablespace been processed? */
        if (ts_stat->num_scanned == ts_stat->num_to_scan)
        {
            binaryheap_remove_first(ts_heap);
        }
        else
        {
            /* update heap with the new progress */
            binaryheap_replace_first(ts_heap, PointerGetDatum(ts_stat));
        }

        /*
         * Sleep to throttle our I/O rate.
         *
         * (This will check for barrier events even if it doesn't sleep.)
         */
        CheckpointWriteDelay(flags, (double) num_processed / num_to_scan);
    }

    /* issue all pending flushes */
    IssuePendingWritebacks(&wb_context);

    pfree(per_ts_stat);
    per_ts_stat = NULL;
    binaryheap_free(ts_heap);

    /*
     * Update checkpoint statistics. As noted above, this doesn't include
     * buffers written by other backends or bgwriter scan.
     */
    CheckpointStats.ckpt_bufs_written += num_written;

    TRACE_POSTGRESQL_BUFFER_SYNC_DONE(NBuffers, num_written, num_to_scan);
}

buffertag_comparator()

static int buffertag_comparator ( const void *  p1, const void *  p2  )

static

Definition at line 4599 of file bufmgr.c.

References buftag::blockNum, buftag::forkNum, buftag::rnode, and rnode_comparator().

Referenced by IssuePendingWritebacks().

{
    const BufferTag *ba = (const BufferTag *) a;
    const BufferTag *bb = (const BufferTag *) b;
    int         ret;

    ret = rnode_comparator(&ba->rnode, &bb->rnode);

    if (ret != 0)
        return ret;

    if (ba->forkNum < bb->forkNum)
        return -1;
    if (ba->forkNum > bb->forkNum)
        return 1;

    if (ba->blockNum < bb->blockNum)
        return -1;
    if (ba->blockNum > bb->blockNum)
        return 1;

    return 0;
}

BufmgrCommit()

void BufmgrCommit

(

void

)

Definition at line 2660 of file bufmgr.c.

Referenced by PrepareTransaction(), and RecordTransactionCommit().

{
    /* Nothing to do in bufmgr anymore... */
}

CheckForBufferLeaks()

static void CheckForBufferLeaks ( void  )

static

Definition at line 2566 of file bufmgr.c.

References Assert, PrivateRefCountEntry::buffer, hash_seq_init(), hash_seq_search(), i, InvalidBuffer, PrintBufferLeakWarning(), PrivateRefCountArray, PrivateRefCountOverflowed, and REFCOUNT_ARRAY_ENTRIES.

Referenced by AtEOXact_Buffers(), and AtProcExit_Buffers().

{
#ifdef USE_ASSERT_CHECKING
    int         RefCountErrors = 0;
    PrivateRefCountEntry *res;
    int         i;

    /* check the array */
    for (i = 0; i < REFCOUNT_ARRAY_ENTRIES; i++)
    {
        res = &PrivateRefCountArray[i];

        if (res->buffer != InvalidBuffer)
        {
            PrintBufferLeakWarning(res->buffer);
            RefCountErrors++;
        }
    }

    /* if necessary search the hash */
    if (PrivateRefCountOverflowed)
    {
        HASH_SEQ_STATUS hstat;

        hash_seq_init(&hstat, PrivateRefCountHash);
        while ((res = (PrivateRefCountEntry *) hash_seq_search(&hstat)) != NULL)
        {
            PrintBufferLeakWarning(res->buffer);
            RefCountErrors++;
        }

    }

    Assert(RefCountErrors == 0);
#endif
}

CheckPointBuffers()

void CheckPointBuffers

(

int

flags

)

Definition at line 2650 of file bufmgr.c.

References BufferSync().

Referenced by CheckPointGuts().

{
    BufferSync(flags);
}

ckpt_buforder_comparator()

static int ckpt_buforder_comparator ( const void *  pa, const void *  pb  )

static

Definition at line 4630 of file bufmgr.c.

References CkptSortItem::blockNum, CkptSortItem::forkNum, CkptSortItem::relNode, and CkptSortItem::tsId.

Referenced by BufferSync().

{
    const CkptSortItem *a = (const CkptSortItem *) pa;
    const CkptSortItem *b = (const CkptSortItem *) pb;

    /* compare tablespace */
    if (a->tsId < b->tsId)
        return -1;
    else if (a->tsId > b->tsId)
        return 1;
    /* compare relation */
    if (a->relNode < b->relNode)
        return -1;
    else if (a->relNode > b->relNode)
        return 1;
    /* compare fork */
    else if (a->forkNum < b->forkNum)
        return -1;
    else if (a->forkNum > b->forkNum)
        return 1;
    /* compare block number */
    else if (a->blockNum < b->blockNum)
        return -1;
    else if (a->blockNum > b->blockNum)
        return 1;
    /* equal page IDs are unlikely, but not impossible */
    return 0;
}

ConditionalLockBuffer()

bool ConditionalLockBuffer

(

Buffer

buffer

)

Definition at line 3965 of file bufmgr.c.

References Assert, buf, BufferDescriptorGetContentLock, BufferIsLocal, BufferIsPinned, GetBufferDescriptor, LW_EXCLUSIVE, and LWLockConditionalAcquire().

Referenced by _bt_conditionallockbuf(), BloomNewBuffer(), ConditionalLockBufferForCleanup(), GinNewBuffer(), gistNewBuffer(), RelationGetBufferForTuple(), spgdoinsert(), SpGistGetBuffer(), SpGistNewBuffer(), and SpGistUpdateMetaPage().

{
    BufferDesc *buf;

    Assert(BufferIsPinned(buffer));
    if (BufferIsLocal(buffer))
        return true;            /* act as though we got it */

    buf = GetBufferDescriptor(buffer - 1);

    return LWLockConditionalAcquire(BufferDescriptorGetContentLock(buf),
                                    LW_EXCLUSIVE);
}

ConditionalLockBufferForCleanup()

bool ConditionalLockBufferForCleanup

(

Buffer

buffer

)

Definition at line 4173 of file bufmgr.c.

References Assert, BUF_STATE_GET_REFCOUNT, BUFFER_LOCK_UNLOCK, BufferIsLocal, BufferIsValid, ConditionalLockBuffer(), GetBufferDescriptor, GetPrivateRefCount(), LocalRefCount, LockBuffer(), LockBufHdr(), PrivateRefCountEntry::refcount, and UnlockBufHdr.

Referenced by _hash_finish_split(), _hash_getbuf_with_condlock_cleanup(), heap_page_prune_opt(), lazy_scan_heap(), and lazy_vacuum_heap().

{
    BufferDesc *bufHdr;
    uint32      buf_state,
                refcount;

    Assert(BufferIsValid(buffer));

    if (BufferIsLocal(buffer))
    {
        refcount = LocalRefCount[-buffer - 1];
        /* There should be exactly one pin */
        Assert(refcount > 0);
        if (refcount != 1)
            return false;
        /* Nobody else to wait for */
        return true;
    }

    /* There should be exactly one local pin */
    refcount = GetPrivateRefCount(buffer);
    Assert(refcount);
    if (refcount != 1)
        return false;

    /* Try to acquire lock */
    if (!ConditionalLockBuffer(buffer))
        return false;

    bufHdr = GetBufferDescriptor(buffer - 1);
    buf_state = LockBufHdr(bufHdr);
    refcount = BUF_STATE_GET_REFCOUNT(buf_state);

    Assert(refcount > 0);
    if (refcount == 1)
    {
        /* Successfully acquired exclusive lock with pincount 1 */
        UnlockBufHdr(bufHdr, buf_state);
        return true;
    }

    /* Failed, so release the lock */
    UnlockBufHdr(bufHdr, buf_state);
    LockBuffer(buffer, BUFFER_LOCK_UNLOCK);
    return false;
}

DropDatabaseBuffers()

void DropDatabaseBuffers

(

Oid

dbid

)

Definition at line 3337 of file bufmgr.c.

References buftag::blockNum, buf, BufferDescriptorGetBuffer, RelFileNode::dbNode, elog, buftag::forkNum, BufferDesc::freeNext, GetBufferDescriptor, GetPrivateRefCount(), i, InvalidateBuffer(), InvalidBackendId, LockBufHdr(), LOG, NBuffers, relpathbackend, relpathperm, buftag::rnode, BufferDesc::tag, and UnlockBufHdr.

Referenced by dbase_redo(), dropdb(), and movedb().

{
    int         i;

    /*
     * We needn't consider local buffers, since by assumption the target
     * database isn't our own.
     */

    for (i = 0; i < NBuffers; i++)
    {
        BufferDesc *bufHdr = GetBufferDescriptor(i);
        uint32      buf_state;

        /*
         * As in DropRelFileNodeBuffers, an unlocked precheck should be safe
         * and saves some cycles.
         */
        if (bufHdr->tag.rnode.dbNode != dbid)
            continue;

        buf_state = LockBufHdr(bufHdr);
        if (bufHdr->tag.rnode.dbNode == dbid)
            InvalidateBuffer(bufHdr);   /* releases spinlock */
        else
            UnlockBufHdr(bufHdr, buf_state);
    }
}

DropRelFileNodeBuffers()

void DropRelFileNodeBuffers	(	SMgrRelation	smgr_reln,
		ForkNumber *	forkNum,
		int	nforks,
		BlockNumber *	firstDelBlock
	)

Definition at line 2983 of file bufmgr.c.

References RelFileNodeBackend::backend, buftag::blockNum, BlockNumberIsValid, BUF_DROP_FULL_SCAN_THRESHOLD, DropRelFileNodeLocalBuffers(), FindAndDropRelFileNodeBuffers(), buftag::forkNum, GetBufferDescriptor, i, InvalidateBuffer(), InvalidBlockNumber, LockBufHdr(), MAX_FORKNUM, MyBackendId, NBuffers, RelFileNodeBackend::node, RelFileNodeBackendIsTemp, RelFileNodeEquals, buftag::rnode, SMgrRelationData::smgr_rnode, smgrnblocks_cached(), BufferDesc::tag, and UnlockBufHdr.

Referenced by smgrtruncate().

{
    int         i;
    int         j;
    RelFileNodeBackend rnode;
    BlockNumber nForkBlock[MAX_FORKNUM];
    BlockNumber nBlocksToInvalidate = 0;

    rnode = smgr_reln->smgr_rnode;

    /* If it's a local relation, it's localbuf.c's problem. */
    if (RelFileNodeBackendIsTemp(rnode))
    {
        if (rnode.backend == MyBackendId)
        {
            for (j = 0; j < nforks; j++)
                DropRelFileNodeLocalBuffers(rnode.node, forkNum[j],
                                            firstDelBlock[j]);
        }
        return;
    }

    /*
     * To remove all the pages of the specified relation forks from the buffer
     * pool, we need to scan the entire buffer pool but we can optimize it by
     * finding the buffers from BufMapping table provided we know the exact
     * size of each fork of the relation. The exact size is required to ensure
     * that we don't leave any buffer for the relation being dropped as
     * otherwise the background writer or checkpointer can lead to a PANIC
     * error while flushing buffers corresponding to files that don't exist.
     *
     * To know the exact size, we rely on the size cached for each fork by us
     * during recovery which limits the optimization to recovery and on
     * standbys but we can easily extend it once we have shared cache for
     * relation size.
     *
     * In recovery, we cache the value returned by the first lseek(SEEK_END)
     * and the future writes keeps the cached value up-to-date. See
     * smgrextend. It is possible that the value of the first lseek is smaller
     * than the actual number of existing blocks in the file due to buggy
     * Linux kernels that might not have accounted for the recent write. But
     * that should be fine because there must not be any buffers after that
     * file size.
     */
    for (i = 0; i < nforks; i++)
    {
        /* Get the number of blocks for a relation's fork */
        nForkBlock[i] = smgrnblocks_cached(smgr_reln, forkNum[i]);

        if (nForkBlock[i] == InvalidBlockNumber)
        {
            nBlocksToInvalidate = InvalidBlockNumber;
            break;
        }

        /* calculate the number of blocks to be invalidated */
        nBlocksToInvalidate += (nForkBlock[i] - firstDelBlock[i]);
    }

    /*
     * We apply the optimization iff the total number of blocks to invalidate
     * is below the BUF_DROP_FULL_SCAN_THRESHOLD.
     */
    if (BlockNumberIsValid(nBlocksToInvalidate) &&
        nBlocksToInvalidate < BUF_DROP_FULL_SCAN_THRESHOLD)
    {
        for (j = 0; j < nforks; j++)
            FindAndDropRelFileNodeBuffers(rnode.node, forkNum[j],
                                          nForkBlock[j], firstDelBlock[j]);
        return;
    }

    for (i = 0; i < NBuffers; i++)
    {
        BufferDesc *bufHdr = GetBufferDescriptor(i);
        uint32      buf_state;

        /*
         * We can make this a tad faster by prechecking the buffer tag before
         * we attempt to lock the buffer; this saves a lot of lock
         * acquisitions in typical cases.  It should be safe because the
         * caller must have AccessExclusiveLock on the relation, or some other
         * reason to be certain that no one is loading new pages of the rel
         * into the buffer pool.  (Otherwise we might well miss such pages
         * entirely.)  Therefore, while the tag might be changing while we
         * look at it, it can't be changing *to* a value we care about, only
         * *away* from such a value.  So false negatives are impossible, and
         * false positives are safe because we'll recheck after getting the
         * buffer lock.
         *
         * We could check forkNum and blockNum as well as the rnode, but the
         * incremental win from doing so seems small.
         */
        if (!RelFileNodeEquals(bufHdr->tag.rnode, rnode.node))
            continue;

        buf_state = LockBufHdr(bufHdr);

        for (j = 0; j < nforks; j++)
        {
            if (RelFileNodeEquals(bufHdr->tag.rnode, rnode.node) &&
                bufHdr->tag.forkNum == forkNum[j] &&
                bufHdr->tag.blockNum >= firstDelBlock[j])
            {
                InvalidateBuffer(bufHdr);   /* releases spinlock */
                break;
            }
        }
        if (j >= nforks)
            UnlockBufHdr(bufHdr, buf_state);
    }
}

DropRelFileNodesAllBuffers()

void DropRelFileNodesAllBuffers	(	SMgrRelation *	smgr_reln,
		int	nnodes
	)

Definition at line 3107 of file bufmgr.c.

References BlockNumberIsValid, BUF_DROP_FULL_SCAN_THRESHOLD, DropRelFileNodeAllLocalBuffers(), FindAndDropRelFileNodeBuffers(), GetBufferDescriptor, i, InvalidateBuffer(), InvalidBlockNumber, LockBufHdr(), MAX_FORKNUM, MyBackendId, NBuffers, SMgrRelationData::node, palloc(), pfree(), pg_qsort(), RelFileNodeBackendIsTemp, RelFileNodeEquals, RELS_BSEARCH_THRESHOLD, buftag::rnode, rnode_comparator(), smgrexists(), smgrnblocks_cached(), BufferDesc::tag, and UnlockBufHdr.

Referenced by smgrdounlinkall().

{
    int         i;
    int         j;
    int         n = 0;
    SMgrRelation *rels;
    BlockNumber (*block)[MAX_FORKNUM + 1];
    BlockNumber nBlocksToInvalidate = 0;
    RelFileNode *nodes;
    bool        cached = true;
    bool        use_bsearch;

    if (nnodes == 0)
        return;

    rels = palloc(sizeof(SMgrRelation) * nnodes);   /* non-local relations */

    /* If it's a local relation, it's localbuf.c's problem. */
    for (i = 0; i < nnodes; i++)
    {
        if (RelFileNodeBackendIsTemp(smgr_reln[i]->smgr_rnode))
        {
            if (smgr_reln[i]->smgr_rnode.backend == MyBackendId)
                DropRelFileNodeAllLocalBuffers(smgr_reln[i]->smgr_rnode.node);
        }
        else
            rels[n++] = smgr_reln[i];
    }

    /*
     * If there are no non-local relations, then we're done. Release the
     * memory and return.
     */
    if (n == 0)
    {
        pfree(rels);
        return;
    }

    /*
     * This is used to remember the number of blocks for all the relations
     * forks.
     */
    block = (BlockNumber (*)[MAX_FORKNUM + 1])
        palloc(sizeof(BlockNumber) * n * (MAX_FORKNUM + 1));

    /*
     * We can avoid scanning the entire buffer pool if we know the exact size
     * of each of the given relation forks. See DropRelFileNodeBuffers.
     */
    for (i = 0; i < n && cached; i++)
    {
        for (j = 0; j <= MAX_FORKNUM; j++)
        {
            /* Get the number of blocks for a relation's fork. */
            block[i][j] = smgrnblocks_cached(rels[i], j);

            /* We need to only consider the relation forks that exists. */
            if (block[i][j] == InvalidBlockNumber)
            {
                if (!smgrexists(rels[i], j))
                    continue;
                cached = false;
                break;
            }

            /* calculate the total number of blocks to be invalidated */
            nBlocksToInvalidate += block[i][j];
        }
    }

    /*
     * We apply the optimization iff the total number of blocks to invalidate
     * is below the BUF_DROP_FULL_SCAN_THRESHOLD.
     */
    if (cached && nBlocksToInvalidate < BUF_DROP_FULL_SCAN_THRESHOLD)
    {
        for (i = 0; i < n; i++)
        {
            for (j = 0; j <= MAX_FORKNUM; j++)
            {
                /* ignore relation forks that doesn't exist */
                if (!BlockNumberIsValid(block[i][j]))
                    continue;

                /* drop all the buffers for a particular relation fork */
                FindAndDropRelFileNodeBuffers(rels[i]->smgr_rnode.node,
                                              j, block[i][j], 0);
            }
        }

        pfree(block);
        pfree(rels);
        return;
    }

    pfree(block);
    nodes = palloc(sizeof(RelFileNode) * n);    /* non-local relations */
    for (i = 0; i < n; i++)
        nodes[i] = rels[i]->smgr_rnode.node;

    /*
     * For low number of relations to drop just use a simple walk through, to
     * save the bsearch overhead. The threshold to use is rather a guess than
     * an exactly determined value, as it depends on many factors (CPU and RAM
     * speeds, amount of shared buffers etc.).
     */
    use_bsearch = n > RELS_BSEARCH_THRESHOLD;

    /* sort the list of rnodes if necessary */
    if (use_bsearch)
        pg_qsort(nodes, n, sizeof(RelFileNode), rnode_comparator);

    for (i = 0; i < NBuffers; i++)
    {
        RelFileNode *rnode = NULL;
        BufferDesc *bufHdr = GetBufferDescriptor(i);
        uint32      buf_state;

        /*
         * As in DropRelFileNodeBuffers, an unlocked precheck should be safe
         * and saves some cycles.
         */

        if (!use_bsearch)
        {
            int         j;

            for (j = 0; j < n; j++)
            {
                if (RelFileNodeEquals(bufHdr->tag.rnode, nodes[j]))
                {
                    rnode = &nodes[j];
                    break;
                }
            }
        }
        else
        {
            rnode = bsearch((const void *) &(bufHdr->tag.rnode),
                            nodes, n, sizeof(RelFileNode),
                            rnode_comparator);
        }

        /* buffer doesn't belong to any of the given relfilenodes; skip it */
        if (rnode == NULL)
            continue;

        buf_state = LockBufHdr(bufHdr);
        if (RelFileNodeEquals(bufHdr->tag.rnode, (*rnode)))
            InvalidateBuffer(bufHdr);   /* releases spinlock */
        else
            UnlockBufHdr(bufHdr, buf_state);
    }

    pfree(nodes);
    pfree(rels);
}

FindAndDropRelFileNodeBuffers()

static void FindAndDropRelFileNodeBuffers ( RelFileNode  rnode, ForkNumber  forkNum, BlockNumber  nForkBlock, BlockNumber  firstDelBlock  )

static

Definition at line 3276 of file bufmgr.c.

References buftag::blockNum, BufMappingPartitionLock, BufTableHashCode(), BufTableLookup(), buftag::forkNum, GetBufferDescriptor, INIT_BUFFERTAG, InvalidateBuffer(), LockBufHdr(), LW_SHARED, LWLockAcquire(), LWLockRelease(), RelFileNodeEquals, buftag::rnode, BufferDesc::tag, and UnlockBufHdr.

Referenced by DropRelFileNodeBuffers(), and DropRelFileNodesAllBuffers().

{
    BlockNumber curBlock;

    for (curBlock = firstDelBlock; curBlock < nForkBlock; curBlock++)
    {
        uint32      bufHash;    /* hash value for tag */
        BufferTag   bufTag;     /* identity of requested block */
        LWLock     *bufPartitionLock;   /* buffer partition lock for it */
        int         buf_id;
        BufferDesc *bufHdr;
        uint32      buf_state;

        /* create a tag so we can lookup the buffer */
        INIT_BUFFERTAG(bufTag, rnode, forkNum, curBlock);

        /* determine its hash code and partition lock ID */
        bufHash = BufTableHashCode(&bufTag);
        bufPartitionLock = BufMappingPartitionLock(bufHash);

        /* Check that it is in the buffer pool. If not, do nothing. */
        LWLockAcquire(bufPartitionLock, LW_SHARED);
        buf_id = BufTableLookup(&bufTag, bufHash);
        LWLockRelease(bufPartitionLock);

        if (buf_id < 0)
            continue;

        bufHdr = GetBufferDescriptor(buf_id);

        /*
         * We need to lock the buffer header and recheck if the buffer is
         * still associated with the same block because the buffer could be
         * evicted by some other backend loading blocks for a different
         * relation after we release lock on the BufMapping table.
         */
        buf_state = LockBufHdr(bufHdr);

        if (RelFileNodeEquals(bufHdr->tag.rnode, rnode) &&
            bufHdr->tag.forkNum == forkNum &&
            bufHdr->tag.blockNum >= firstDelBlock)
            InvalidateBuffer(bufHdr);   /* releases spinlock */
        else
            UnlockBufHdr(bufHdr, buf_state);
    }
}

FlushBuffer()

static void FlushBuffer ( BufferDesc *  buf, SMgrRelation  reln  )

static

Definition at line 2734 of file bufmgr.c.

References ErrorContextCallback::arg, BufferUsage::blk_write_time, buftag::blockNum, BM_JUST_DIRTIED, BM_PERMANENT, BufferGetLSN, BufHdrGetBlock, ErrorContextCallback::callback, RelFileNode::dbNode, error_context_stack, buftag::forkNum, INSTR_TIME_ADD, INSTR_TIME_GET_MICROSEC, INSTR_TIME_SET_CURRENT, INSTR_TIME_SUBTRACT, InvalidBackendId, LockBufHdr(), RelFileNodeBackend::node, PageSetChecksumCopy(), pgBufferUsage, pgstat_count_buffer_write_time, ErrorContextCallback::previous, RelFileNode::relNode, buftag::rnode, BufferUsage::shared_blks_written, shared_buffer_write_error_callback(), SMgrRelationData::smgr_rnode, smgropen(), smgrwrite(), RelFileNode::spcNode, StartBufferIO(), BufferDesc::tag, TerminateBufferIO(), track_io_timing, UnlockBufHdr, and XLogFlush().

Referenced by BufferAlloc(), FlushDatabaseBuffers(), FlushOneBuffer(), FlushRelationBuffers(), FlushRelationsAllBuffers(), and SyncOneBuffer().

{
    XLogRecPtr  recptr;
    ErrorContextCallback errcallback;
    instr_time  io_start,
                io_time;
    Block       bufBlock;
    char       *bufToWrite;
    uint32      buf_state;

    /*
     * Acquire the buffer's io_in_progress lock.  If StartBufferIO returns
     * false, then someone else flushed the buffer before we could, so we need
     * not do anything.
     */
    if (!StartBufferIO(buf, false))
        return;

    /* Setup error traceback support for ereport() */
    errcallback.callback = shared_buffer_write_error_callback;
    errcallback.arg = (void *) buf;
    errcallback.previous = error_context_stack;
    error_context_stack = &errcallback;

    /* Find smgr relation for buffer */
    if (reln == NULL)
        reln = smgropen(buf->tag.rnode, InvalidBackendId);

    TRACE_POSTGRESQL_BUFFER_FLUSH_START(buf->tag.forkNum,
                                        buf->tag.blockNum,
                                        reln->smgr_rnode.node.spcNode,
                                        reln->smgr_rnode.node.dbNode,
                                        reln->smgr_rnode.node.relNode);

    buf_state = LockBufHdr(buf);

    /*
     * Run PageGetLSN while holding header lock, since we don't have the
     * buffer locked exclusively in all cases.
     */
    recptr = BufferGetLSN(buf);

    /* To check if block content changes while flushing. - vadim 01/17/97 */
    buf_state &= ~BM_JUST_DIRTIED;
    UnlockBufHdr(buf, buf_state);

    /*
     * Force XLOG flush up to buffer's LSN.  This implements the basic WAL
     * rule that log updates must hit disk before any of the data-file changes
     * they describe do.
     *
     * However, this rule does not apply to unlogged relations, which will be
     * lost after a crash anyway.  Most unlogged relation pages do not bear
     * LSNs since we never emit WAL records for them, and therefore flushing
     * up through the buffer LSN would be useless, but harmless.  However,
     * GiST indexes use LSNs internally to track page-splits, and therefore
     * unlogged GiST pages bear "fake" LSNs generated by
     * GetFakeLSNForUnloggedRel.  It is unlikely but possible that the fake
     * LSN counter could advance past the WAL insertion point; and if it did
     * happen, attempting to flush WAL through that location would fail, with
     * disastrous system-wide consequences.  To make sure that can't happen,
     * skip the flush if the buffer isn't permanent.
     */
    if (buf_state & BM_PERMANENT)
        XLogFlush(recptr);

    /*
     * Now it's safe to write buffer to disk. Note that no one else should
     * have been able to write it while we were busy with log flushing because
     * we have the io_in_progress lock.
     */
    bufBlock = BufHdrGetBlock(buf);

    /*
     * Update page checksum if desired.  Since we have only shared lock on the
     * buffer, other processes might be updating hint bits in it, so we must
     * copy the page to private storage if we do checksumming.
     */
    bufToWrite = PageSetChecksumCopy((Page) bufBlock, buf->tag.blockNum);

    if (track_io_timing)
        INSTR_TIME_SET_CURRENT(io_start);

    /*
     * bufToWrite is either the shared buffer or a copy, as appropriate.
     */
    smgrwrite(reln,
              buf->tag.forkNum,
              buf->tag.blockNum,
              bufToWrite,
              false);

    if (track_io_timing)
    {
        INSTR_TIME_SET_CURRENT(io_time);
        INSTR_TIME_SUBTRACT(io_time, io_start);
        pgstat_count_buffer_write_time(INSTR_TIME_GET_MICROSEC(io_time));
        INSTR_TIME_ADD(pgBufferUsage.blk_write_time, io_time);
    }

    pgBufferUsage.shared_blks_written++;

    /*
     * Mark the buffer as clean (unless BM_JUST_DIRTIED has become set) and
     * end the io_in_progress state.
     */
    TerminateBufferIO(buf, true, 0);

    TRACE_POSTGRESQL_BUFFER_FLUSH_DONE(buf->tag.forkNum,
                                       buf->tag.blockNum,
                                       reln->smgr_rnode.node.spcNode,
                                       reln->smgr_rnode.node.dbNode,
                                       reln->smgr_rnode.node.relNode);

    /* Pop the error context stack */
    error_context_stack = errcallback.previous;
}

FlushDatabaseBuffers()

void FlushDatabaseBuffers

(

Oid

dbid

)

Definition at line 3637 of file bufmgr.c.

References BM_DIRTY, BM_VALID, BufferDescriptorGetContentLock, CurrentResourceOwner, RelFileNode::dbNode, FlushBuffer(), GetBufferDescriptor, i, LockBufHdr(), LW_SHARED, LWLockAcquire(), LWLockRelease(), NBuffers, PinBuffer_Locked(), ReservePrivateRefCountEntry(), ResourceOwnerEnlargeBuffers(), buftag::rnode, BufferDesc::tag, UnlockBufHdr, and UnpinBuffer().

Referenced by dbase_redo().

{
    int         i;
    BufferDesc *bufHdr;

    /* Make sure we can handle the pin inside the loop */
    ResourceOwnerEnlargeBuffers(CurrentResourceOwner);

    for (i = 0; i < NBuffers; i++)
    {
        uint32      buf_state;

        bufHdr = GetBufferDescriptor(i);

        /*
         * As in DropRelFileNodeBuffers, an unlocked precheck should be safe
         * and saves some cycles.
         */
        if (bufHdr->tag.rnode.dbNode != dbid)
            continue;

        ReservePrivateRefCountEntry();

        buf_state = LockBufHdr(bufHdr);
        if (bufHdr->tag.rnode.dbNode == dbid &&
            (buf_state & (BM_VALID | BM_DIRTY)) == (BM_VALID | BM_DIRTY))
        {
            PinBuffer_Locked(bufHdr);
            LWLockAcquire(BufferDescriptorGetContentLock(bufHdr), LW_SHARED);
            FlushBuffer(bufHdr, NULL);
            LWLockRelease(BufferDescriptorGetContentLock(bufHdr));
            UnpinBuffer(bufHdr, true);
        }
        else
            UnlockBufHdr(bufHdr, buf_state);
    }
}

FlushOneBuffer()

void FlushOneBuffer

(

Buffer

buffer

)

Definition at line 3680 of file bufmgr.c.

References Assert, BufferDescriptorGetContentLock, BufferIsLocal, BufferIsPinned, FlushBuffer(), GetBufferDescriptor, and LWLockHeldByMe().

Referenced by hash_xlog_init_bitmap_page(), hash_xlog_init_meta_page(), and XLogReadBufferForRedoExtended().

{
    BufferDesc *bufHdr;

    /* currently not needed, but no fundamental reason not to support */
    Assert(!BufferIsLocal(buffer));

    Assert(BufferIsPinned(buffer));

    bufHdr = GetBufferDescriptor(buffer - 1);

    Assert(LWLockHeldByMe(BufferDescriptorGetContentLock(bufHdr)));

    FlushBuffer(bufHdr, NULL);
}

FlushRelationBuffers()

void FlushRelationBuffers

(

Relation

rel

)

Definition at line 3441 of file bufmgr.c.

References ErrorContextCallback::arg, buftag::blockNum, BM_DIRTY, BM_JUST_DIRTIED, BM_VALID, BufferDescriptorGetContentLock, ErrorContextCallback::callback, CurrentResourceOwner, error_context_stack, FlushBuffer(), buftag::forkNum, GetBufferDescriptor, GetLocalBufferDescriptor, i, local_buffer_write_error_callback(), LocalBufHdrGetBlock, LockBufHdr(), LW_SHARED, LWLockAcquire(), LWLockRelease(), NBuffers, NLocBuffer, PageSetChecksumInplace(), pg_atomic_read_u32(), pg_atomic_unlocked_write_u32(), PinBuffer_Locked(), ErrorContextCallback::previous, RelationData::rd_node, RelationData::rd_smgr, RelationOpenSmgr, RelationUsesLocalBuffers, RelFileNodeEquals, ReservePrivateRefCountEntry(), ResourceOwnerEnlargeBuffers(), buftag::rnode, smgrwrite(), BufferDesc::state, BufferDesc::tag, UnlockBufHdr, and UnpinBuffer().

Referenced by heapam_relation_copy_data(), and index_copy_data().

{
    int         i;
    BufferDesc *bufHdr;

    /* Open rel at the smgr level if not already done */
    RelationOpenSmgr(rel);

    if (RelationUsesLocalBuffers(rel))
    {
        for (i = 0; i < NLocBuffer; i++)
        {
            uint32      buf_state;

            bufHdr = GetLocalBufferDescriptor(i);
            if (RelFileNodeEquals(bufHdr->tag.rnode, rel->rd_node) &&
                ((buf_state = pg_atomic_read_u32(&bufHdr->state)) &
                 (BM_VALID | BM_DIRTY)) == (BM_VALID | BM_DIRTY))
            {
                ErrorContextCallback errcallback;
                Page        localpage;

                localpage = (char *) LocalBufHdrGetBlock(bufHdr);

                /* Setup error traceback support for ereport() */
                errcallback.callback = local_buffer_write_error_callback;
                errcallback.arg = (void *) bufHdr;
                errcallback.previous = error_context_stack;
                error_context_stack = &errcallback;

                PageSetChecksumInplace(localpage, bufHdr->tag.blockNum);

                smgrwrite(rel->rd_smgr,
                          bufHdr->tag.forkNum,
                          bufHdr->tag.blockNum,
                          localpage,
                          false);

                buf_state &= ~(BM_DIRTY | BM_JUST_DIRTIED);
                pg_atomic_unlocked_write_u32(&bufHdr->state, buf_state);

                /* Pop the error context stack */
                error_context_stack = errcallback.previous;
            }
        }

        return;
    }

    /* Make sure we can handle the pin inside the loop */
    ResourceOwnerEnlargeBuffers(CurrentResourceOwner);

    for (i = 0; i < NBuffers; i++)
    {
        uint32      buf_state;

        bufHdr = GetBufferDescriptor(i);

        /*
         * As in DropRelFileNodeBuffers, an unlocked precheck should be safe
         * and saves some cycles.
         */
        if (!RelFileNodeEquals(bufHdr->tag.rnode, rel->rd_node))
            continue;

        ReservePrivateRefCountEntry();

        buf_state = LockBufHdr(bufHdr);
        if (RelFileNodeEquals(bufHdr->tag.rnode, rel->rd_node) &&
            (buf_state & (BM_VALID | BM_DIRTY)) == (BM_VALID | BM_DIRTY))
        {
            PinBuffer_Locked(bufHdr);
            LWLockAcquire(BufferDescriptorGetContentLock(bufHdr), LW_SHARED);
            FlushBuffer(bufHdr, rel->rd_smgr);
            LWLockRelease(BufferDescriptorGetContentLock(bufHdr));
            UnpinBuffer(bufHdr, true);
        }
        else
            UnlockBufHdr(bufHdr, buf_state);
    }
}

FlushRelationsAllBuffers()

void FlushRelationsAllBuffers	(	SMgrRelation *	smgrs,
		int	nrels
	)

Definition at line 3533 of file bufmgr.c.

References Assert, BM_DIRTY, BM_VALID, BufferDescriptorGetContentLock, CurrentResourceOwner, FlushBuffer(), GetBufferDescriptor, i, LockBufHdr(), LW_SHARED, LWLockAcquire(), LWLockRelease(), NBuffers, RelFileNodeBackend::node, palloc(), pfree(), pg_qsort(), PinBuffer_Locked(), RelFileNodeBackendIsTemp, RelFileNodeEquals, RELS_BSEARCH_THRESHOLD, ReservePrivateRefCountEntry(), ResourceOwnerEnlargeBuffers(), buftag::rnode, SMgrSortArray::rnode, rnode_comparator(), SMgrRelationData::smgr_rnode, SMgrSortArray::srel, BufferDesc::tag, UnlockBufHdr, and UnpinBuffer().

Referenced by smgrdosyncall().

{
    int         i;
    SMgrSortArray *srels;
    bool        use_bsearch;

    if (nrels == 0)
        return;

    /* fill-in array for qsort */
    srels = palloc(sizeof(SMgrSortArray) * nrels);

    for (i = 0; i < nrels; i++)
    {
        Assert(!RelFileNodeBackendIsTemp(smgrs[i]->smgr_rnode));

        srels[i].rnode = smgrs[i]->smgr_rnode.node;
        srels[i].srel = smgrs[i];
    }

    /*
     * Save the bsearch overhead for low number of relations to sync. See
     * DropRelFileNodesAllBuffers for details.
     */
    use_bsearch = nrels > RELS_BSEARCH_THRESHOLD;

    /* sort the list of SMgrRelations if necessary */
    if (use_bsearch)
        pg_qsort(srels, nrels, sizeof(SMgrSortArray), rnode_comparator);

    /* Make sure we can handle the pin inside the loop */
    ResourceOwnerEnlargeBuffers(CurrentResourceOwner);

    for (i = 0; i < NBuffers; i++)
    {
        SMgrSortArray *srelent = NULL;
        BufferDesc *bufHdr = GetBufferDescriptor(i);
        uint32      buf_state;

        /*
         * As in DropRelFileNodeBuffers, an unlocked precheck should be safe
         * and saves some cycles.
         */

        if (!use_bsearch)
        {
            int         j;

            for (j = 0; j < nrels; j++)
            {
                if (RelFileNodeEquals(bufHdr->tag.rnode, srels[j].rnode))
                {
                    srelent = &srels[j];
                    break;
                }
            }

        }
        else
        {
            srelent = bsearch((const void *) &(bufHdr->tag.rnode),
                              srels, nrels, sizeof(SMgrSortArray),
                              rnode_comparator);
        }

        /* buffer doesn't belong to any of the given relfilenodes; skip it */
        if (srelent == NULL)
            continue;

        ReservePrivateRefCountEntry();

        buf_state = LockBufHdr(bufHdr);
        if (RelFileNodeEquals(bufHdr->tag.rnode, srelent->rnode) &&
            (buf_state & (BM_VALID | BM_DIRTY)) == (BM_VALID | BM_DIRTY))
        {
            PinBuffer_Locked(bufHdr);
            LWLockAcquire(BufferDescriptorGetContentLock(bufHdr), LW_SHARED);
            FlushBuffer(bufHdr, srelent->srel);
            LWLockRelease(BufferDescriptorGetContentLock(bufHdr));
            UnpinBuffer(bufHdr, true);
        }
        else
            UnlockBufHdr(bufHdr, buf_state);
    }

    pfree(srels);
}

ForgetPrivateRefCountEntry()

static void ForgetPrivateRefCountEntry ( PrivateRefCountEntry *  ref )

static

Definition at line 410 of file bufmgr.c.

References Assert, PrivateRefCountEntry::buffer, HASH_REMOVE, hash_search(), InvalidBuffer, PrivateRefCountArray, PrivateRefCountOverflowed, PrivateRefCountEntry::refcount, and REFCOUNT_ARRAY_ENTRIES.

Referenced by UnpinBuffer().

{
    Assert(ref->refcount == 0);

    if (ref >= &PrivateRefCountArray[0] &&
        ref < &PrivateRefCountArray[REFCOUNT_ARRAY_ENTRIES])
    {
        ref->buffer = InvalidBuffer;

        /*
         * Mark the just used entry as reserved - in many scenarios that
         * allows us to avoid ever having to search the array/hash for free
         * entries.
         */
        ReservedRefCountEntry = ref;
    }
    else
    {
        bool        found;
        Buffer      buffer = ref->buffer;

        hash_search(PrivateRefCountHash,
                    (void *) &buffer,
                    HASH_REMOVE,
                    &found);
        Assert(found);
        Assert(PrivateRefCountOverflowed > 0);
        PrivateRefCountOverflowed--;
    }
}

GetPrivateRefCount()

static int32 GetPrivateRefCount ( Buffer  buffer )

inlinestatic

Definition at line 387 of file bufmgr.c.

References Assert, BufferIsLocal, BufferIsValid, GetPrivateRefCountEntry(), and PrivateRefCountEntry::refcount.

Referenced by ConditionalLockBufferForCleanup(), DropDatabaseBuffers(), HoldingBufferPinThatDelaysRecovery(), InvalidateBuffer(), IsBufferCleanupOK(), LockBufferForCleanup(), MarkBufferDirtyHint(), and PrintBufferLeakWarning().

{
    PrivateRefCountEntry *ref;

    Assert(BufferIsValid(buffer));
    Assert(!BufferIsLocal(buffer));

    /*
     * Not moving the entry - that's ok for the current users, but we might
     * want to change this one day.
     */
    ref = GetPrivateRefCountEntry(buffer, false);

    if (ref == NULL)
        return 0;
    return ref->refcount;
}

GetPrivateRefCountEntry()

static PrivateRefCountEntry * GetPrivateRefCountEntry ( Buffer  buffer, bool  do_move  )

static

Definition at line 307 of file bufmgr.c.

References Assert, PrivateRefCountEntry::buffer, BufferIsLocal, BufferIsValid, free, HASH_FIND, HASH_REMOVE, hash_search(), i, InvalidBuffer, PrivateRefCountArray, PrivateRefCountOverflowed, PrivateRefCountEntry::refcount, REFCOUNT_ARRAY_ENTRIES, ReservedRefCountEntry, and ReservePrivateRefCountEntry().

Referenced by GetPrivateRefCount(), IncrBufferRefCount(), PinBuffer(), PinBuffer_Locked(), and UnpinBuffer().

{
    PrivateRefCountEntry *res;
    int         i;

    Assert(BufferIsValid(buffer));
    Assert(!BufferIsLocal(buffer));

    /*
     * First search for references in the array, that'll be sufficient in the
     * majority of cases.
     */
    for (i = 0; i < REFCOUNT_ARRAY_ENTRIES; i++)
    {
        res = &PrivateRefCountArray[i];

        if (res->buffer == buffer)
            return res;
    }

    /*
     * By here we know that the buffer, if already pinned, isn't residing in
     * the array.
     *
     * Only look up the buffer in the hashtable if we've previously overflowed
     * into it.
     */
    if (PrivateRefCountOverflowed == 0)
        return NULL;

    res = hash_search(PrivateRefCountHash,
                      (void *) &buffer,
                      HASH_FIND,
                      NULL);

    if (res == NULL)
        return NULL;
    else if (!do_move)
    {
        /* caller doesn't want us to move the hash entry into the array */
        return res;
    }
    else
    {
        /* move buffer from hashtable into the free array slot */
        bool        found;
        PrivateRefCountEntry *free;

        /* Ensure there's a free array slot */
        ReservePrivateRefCountEntry();

        /* Use up the reserved slot */
        Assert(ReservedRefCountEntry != NULL);
        free = ReservedRefCountEntry;
        ReservedRefCountEntry = NULL;
        Assert(free->buffer == InvalidBuffer);

        /* and fill it */
        free->buffer = buffer;
        free->refcount = res->refcount;

        /* delete from hashtable */
        hash_search(PrivateRefCountHash,
                    (void *) &buffer,
                    HASH_REMOVE,
                    &found);
        Assert(found);
        Assert(PrivateRefCountOverflowed > 0);
        PrivateRefCountOverflowed--;

        return free;
    }
}

HoldingBufferPinThatDelaysRecovery()

bool HoldingBufferPinThatDelaysRecovery

(

void

)

Definition at line 4147 of file bufmgr.c.

References GetPrivateRefCount(), and GetStartupBufferPinWaitBufId().

Referenced by CheckRecoveryConflictDeadlock(), and RecoveryConflictInterrupt().

{
    int         bufid = GetStartupBufferPinWaitBufId();

    /*
     * If we get woken slowly then it's possible that the Startup process was
     * already woken by other backends before we got here. Also possible that
     * we get here by multiple interrupts or interrupts at inappropriate
     * times, so make sure we do nothing if the bufid is not set.
     */
    if (bufid < 0)
        return false;

    if (GetPrivateRefCount(bufid + 1) > 0)
        return true;

    return false;
}

IncrBufferRefCount()

void IncrBufferRefCount

(

Buffer

buffer

)

Definition at line 3738 of file bufmgr.c.

References Assert, BufferIsLocal, BufferIsPinned, CurrentResourceOwner, GetPrivateRefCountEntry(), LocalRefCount, PrivateRefCountEntry::refcount, ResourceOwnerEnlargeBuffers(), and ResourceOwnerRememberBuffer().

Referenced by _bt_steppage(), btrestrpos(), entryLoadMoreItems(), ReadBufferBI(), scanPostingTree(), startScanEntry(), and tts_buffer_heap_store_tuple().

{
    Assert(BufferIsPinned(buffer));
    ResourceOwnerEnlargeBuffers(CurrentResourceOwner);
    if (BufferIsLocal(buffer))
        LocalRefCount[-buffer - 1]++;
    else
    {
        PrivateRefCountEntry *ref;

        ref = GetPrivateRefCountEntry(buffer, true);
        Assert(ref != NULL);
        ref->refcount++;
    }
    ResourceOwnerRememberBuffer(CurrentResourceOwner, buffer);
}

InitBufferPoolAccess()

void InitBufferPoolAccess

(

void

)

Definition at line 2514 of file bufmgr.c.

References HASHCTL::entrysize, HASH_BLOBS, hash_create(), HASH_ELEM, HASHCTL::keysize, and PrivateRefCountArray.

Referenced by BaseInit().

{
    HASHCTL     hash_ctl;

    memset(&PrivateRefCountArray, 0, sizeof(PrivateRefCountArray));

    hash_ctl.keysize = sizeof(int32);
    hash_ctl.entrysize = sizeof(PrivateRefCountEntry);

    PrivateRefCountHash = hash_create("PrivateRefCount", 100, &hash_ctl,
                                      HASH_ELEM | HASH_BLOBS);
}

InitBufferPoolBackend()

void InitBufferPoolBackend

(

void

)

Definition at line 2537 of file bufmgr.c.

References AtProcExit_Buffers(), and on_shmem_exit().

Referenced by AuxiliaryProcessMain(), and InitPostgres().

{
    on_shmem_exit(AtProcExit_Buffers, 0);
}

InvalidateBuffer()

static void InvalidateBuffer ( BufferDesc *  buf )

static

Definition at line 1385 of file bufmgr.c.

References Assert, BM_LOCKED, BM_TAG_VALID, BUF_FLAG_MASK, BUF_STATE_GET_REFCOUNT, BUF_USAGECOUNT_MASK, BufferDescriptorGetBuffer, BUFFERTAGS_EQUAL, BufMappingPartitionLock, BufTableDelete(), BufTableHashCode(), CLEAR_BUFFERTAG, elog, ERROR, GetPrivateRefCount(), LockBufHdr(), LW_EXCLUSIVE, LWLockAcquire(), LWLockRelease(), pg_atomic_read_u32(), BufferDesc::state, StrategyFreeBuffer(), BufferDesc::tag, UnlockBufHdr, and WaitIO().

Referenced by DropDatabaseBuffers(), DropRelFileNodeBuffers(), DropRelFileNodesAllBuffers(), and FindAndDropRelFileNodeBuffers().

{
    BufferTag   oldTag;
    uint32      oldHash;        /* hash value for oldTag */
    LWLock     *oldPartitionLock;   /* buffer partition lock for it */
    uint32      oldFlags;
    uint32      buf_state;

    /* Save the original buffer tag before dropping the spinlock */
    oldTag = buf->tag;

    buf_state = pg_atomic_read_u32(&buf->state);
    Assert(buf_state & BM_LOCKED);
    UnlockBufHdr(buf, buf_state);

    /*
     * Need to compute the old tag's hashcode and partition lock ID. XXX is it
     * worth storing the hashcode in BufferDesc so we need not recompute it
     * here?  Probably not.
     */
    oldHash = BufTableHashCode(&oldTag);
    oldPartitionLock = BufMappingPartitionLock(oldHash);

retry:

    /*
     * Acquire exclusive mapping lock in preparation for changing the buffer's
     * association.
     */
    LWLockAcquire(oldPartitionLock, LW_EXCLUSIVE);

    /* Re-lock the buffer header */
    buf_state = LockBufHdr(buf);

    /* If it's changed while we were waiting for lock, do nothing */
    if (!BUFFERTAGS_EQUAL(buf->tag, oldTag))
    {
        UnlockBufHdr(buf, buf_state);
        LWLockRelease(oldPartitionLock);
        return;
    }

    /*
     * We assume the only reason for it to be pinned is that someone else is
     * flushing the page out.  Wait for them to finish.  (This could be an
     * infinite loop if the refcount is messed up... it would be nice to time
     * out after awhile, but there seems no way to be sure how many loops may
     * be needed.  Note that if the other guy has pinned the buffer but not
     * yet done StartBufferIO, WaitIO will fall through and we'll effectively
     * be busy-looping here.)
     */
    if (BUF_STATE_GET_REFCOUNT(buf_state) != 0)
    {
        UnlockBufHdr(buf, buf_state);
        LWLockRelease(oldPartitionLock);
        /* safety check: should definitely not be our *own* pin */
        if (GetPrivateRefCount(BufferDescriptorGetBuffer(buf)) > 0)
            elog(ERROR, "buffer is pinned in InvalidateBuffer");
        WaitIO(buf);
        goto retry;
    }

    /*
     * Clear out the buffer's tag and flags.  We must do this to ensure that
     * linear scans of the buffer array don't think the buffer is valid.
     */
    oldFlags = buf_state & BUF_FLAG_MASK;
    CLEAR_BUFFERTAG(buf->tag);
    buf_state &= ~(BUF_FLAG_MASK | BUF_USAGECOUNT_MASK);
    UnlockBufHdr(buf, buf_state);

    /*
     * Remove the buffer from the lookup hashtable, if it was in there.
     */
    if (oldFlags & BM_TAG_VALID)
        BufTableDelete(&oldTag, oldHash);

    /*
     * Done with mapping lock.
     */
    LWLockRelease(oldPartitionLock);

    /*
     * Insert the buffer at the head of the list of free buffers.
     */
    StrategyFreeBuffer(buf);
}

IsBufferCleanupOK()

bool IsBufferCleanupOK

(

Buffer

buffer

)

Definition at line 4229 of file bufmgr.c.

References Assert, BUF_STATE_GET_REFCOUNT, BufferDescriptorGetContentLock, BufferIsLocal, BufferIsValid, GetBufferDescriptor, GetPrivateRefCount(), LocalRefCount, LockBufHdr(), LW_EXCLUSIVE, LWLockHeldByMeInMode(), and UnlockBufHdr.

Referenced by _hash_doinsert(), _hash_expandtable(), _hash_splitbucket(), hash_xlog_split_allocate_page(), and hashbucketcleanup().

{
    BufferDesc *bufHdr;
    uint32      buf_state;

    Assert(BufferIsValid(buffer));

    if (BufferIsLocal(buffer))
    {
        /* There should be exactly one pin */
        if (LocalRefCount[-buffer - 1] != 1)
            return false;
        /* Nobody else to wait for */
        return true;
    }

    /* There should be exactly one local pin */
    if (GetPrivateRefCount(buffer) != 1)
        return false;

    bufHdr = GetBufferDescriptor(buffer - 1);

    /* caller must hold exclusive lock on buffer */
    Assert(LWLockHeldByMeInMode(BufferDescriptorGetContentLock(bufHdr),
                                LW_EXCLUSIVE));

    buf_state = LockBufHdr(bufHdr);

    Assert(BUF_STATE_GET_REFCOUNT(buf_state) > 0);
    if (BUF_STATE_GET_REFCOUNT(buf_state) == 1)
    {
        /* pincount is OK. */
        UnlockBufHdr(bufHdr, buf_state);
        return true;
    }

    UnlockBufHdr(bufHdr, buf_state);
    return false;
}

IssuePendingWritebacks()

void IssuePendingWritebacks

(

WritebackContext *

context

)

Definition at line 4733 of file bufmgr.c.

References buftag::blockNum, buffertag_comparator(), cur, buftag::forkNum, i, InvalidBackendId, next, WritebackContext::nr_pending, WritebackContext::pending_writebacks, qsort, RelFileNodeEquals, buftag::rnode, smgropen(), smgrwriteback(), and PendingWriteback::tag.

Referenced by BufferSync(), and ScheduleBufferTagForWriteback().

{
    int         i;

    if (context->nr_pending == 0)
        return;

    /*
     * Executing the writes in-order can make them a lot faster, and allows to
     * merge writeback requests to consecutive blocks into larger writebacks.
     */
    qsort(&context->pending_writebacks, context->nr_pending,
          sizeof(PendingWriteback), buffertag_comparator);

    /*
     * Coalesce neighbouring writes, but nothing else. For that we iterate
     * through the, now sorted, array of pending flushes, and look forward to
     * find all neighbouring (or identical) writes.
     */
    for (i = 0; i < context->nr_pending; i++)
    {
        PendingWriteback *cur;
        PendingWriteback *next;
        SMgrRelation reln;
        int         ahead;
        BufferTag   tag;
        Size        nblocks = 1;

        cur = &context->pending_writebacks[i];
        tag = cur->tag;

        /*
         * Peek ahead, into following writeback requests, to see if they can
         * be combined with the current one.
         */
        for (ahead = 0; i + ahead + 1 < context->nr_pending; ahead++)
        {
            next = &context->pending_writebacks[i + ahead + 1];

            /* different file, stop */
            if (!RelFileNodeEquals(cur->tag.rnode, next->tag.rnode) ||
                cur->tag.forkNum != next->tag.forkNum)
                break;

            /* ok, block queued twice, skip */
            if (cur->tag.blockNum == next->tag.blockNum)
                continue;

            /* only merge consecutive writes */
            if (cur->tag.blockNum + 1 != next->tag.blockNum)
                break;

            nblocks++;
            cur = next;
        }

        i += ahead;

        /* and finally tell the kernel to write the data to storage */
        reln = smgropen(tag.rnode, InvalidBackendId);
        smgrwriteback(reln, tag.forkNum, tag.blockNum, nblocks);
    }

    context->nr_pending = 0;
}

local_buffer_write_error_callback()

static void local_buffer_write_error_callback ( void *  arg )

static

Definition at line 4501 of file bufmgr.c.

References buftag::blockNum, errcontext, buftag::forkNum, MyBackendId, pfree(), relpathbackend, buftag::rnode, and BufferDesc::tag.

Referenced by FlushRelationBuffers().

{
    BufferDesc *bufHdr = (BufferDesc *) arg;

    if (bufHdr != NULL)
    {
        char       *path = relpathbackend(bufHdr->tag.rnode, MyBackendId,
                                          bufHdr->tag.forkNum);

        errcontext("writing block %u of relation %s",
                   bufHdr->tag.blockNum, path);
        pfree(path);
    }
}

LockBuffer()

void LockBuffer	(	Buffer	buffer,
		int	mode
	)

Definition at line 3939 of file bufmgr.c.

References Assert, buf, BUFFER_LOCK_EXCLUSIVE, BUFFER_LOCK_SHARE, BUFFER_LOCK_UNLOCK, BufferDescriptorGetContentLock, BufferIsLocal, BufferIsPinned, elog, ERROR, GetBufferDescriptor, LW_EXCLUSIVE, LW_SHARED, LWLockAcquire(), and LWLockRelease().

Referenced by _bt_lockbuf(), _bt_unlockbuf(), _bt_upgradelockbufcleanup(), _hash_addovflpage(), _hash_doinsert(), _hash_expandtable(), _hash_finish_split(), _hash_first(), _hash_freeovflpage(), _hash_getbuf(), _hash_getbuf_with_strategy(), _hash_getcachedmetap(), _hash_getnewbuf(), _hash_init(), _hash_kill_items(), _hash_readnext(), _hash_readpage(), _hash_readprev(), _hash_splitbucket(), _hash_squeezebucket(), _hash_vacuum_one_page(), blbulkdelete(), blgetbitmap(), blinsert(), BloomNewBuffer(), blvacuumcleanup(), brin_doinsert(), brin_doupdate(), brin_evacuate_page(), brin_getinsertbuffer(), brin_page_cleanup(), brinbuild(), brinbuildempty(), bringetbitmap(), brinGetStats(), brinGetTupleForHeapBlock(), brininsert(), brinLockRevmapPageForUpdate(), brinRevmapDesummarizeRange(), brinRevmapInitialize(), brinsummarize(), bt_metap(), bt_page_items_internal(), bt_page_stats_internal(), bt_recheck_sibling_links(), checkXLogConsistency(), collect_corrupt_items(), collect_visibility_data(), collectMatchBitmap(), ConditionalLockBufferForCleanup(), count_nondeletable_pages(), entryLoadMoreItems(), fill_seq_with_data(), FreeSpaceMapPrepareTruncateRel(), fsm_readbuf(), fsm_search(), fsm_search_avail(), fsm_set_and_search(), fsm_vacuum_page(), get_raw_page_internal(), GetVisibilityMapPins(), ginbuildempty(), ginbulkdelete(), ginEntryInsert(), ginFindLeafPage(), ginFindParents(), ginFinishSplit(), ginGetStats(), ginHeapTupleFastInsert(), ginInsertCleanup(), ginInsertValue(), GinNewBuffer(), ginScanToDelete(), ginStepRight(), ginTraverseLock(), ginUpdateStats(), ginvacuumcleanup(), ginVacuumPostingTreeLeaves(), gistBufferingFindCorrectParent(), gistbufferinginserttuples(), gistbuildempty(), gistdoinsert(), gistFindCorrectParent(), gistFindPath(), gistfinishsplit(), gistfixsplit(), gistformdownlink(), gistGetMaxLevel(), gistinserttuples(), gistkillitems(), gistNewBuffer(), gistProcessItup(), gistScanPage(), gistvacuum_delete_empty_pages(), gistvacuumpage(), hashbucketcleanup(), hashbulkdelete(), heap_abort_speculative(), heap_delete(), heap_fetch(), heap_finish_speculative(), heap_get_latest_tid(), heap_index_delete_tuples(), heap_inplace_update(), heap_lock_tuple(), heap_lock_updated_tuple_rec(), heap_page_prune_opt(), heap_update(), heap_xlog_visible(), heapam_index_build_range_scan(), heapam_index_fetch_tuple(), heapam_index_validate_scan(), heapam_relation_copy_for_cluster(), heapam_scan_analyze_next_block(), heapam_scan_bitmap_next_block(), heapam_scan_sample_next_tuple(), heapam_tuple_satisfies_snapshot(), heapgetpage(), heapgettup(), initBloomState(), lazy_scan_heap(), LockBufferForCleanup(), log_newpage_range(), palloc_btree_page(), pg_visibility(), pgrowlocks(), pgstat_btree_page(), pgstat_gist_page(), pgstat_heap(), pgstatginindex_internal(), pgstathashindex(), pgstatindex_impl(), read_seq_tuple(), RelationGetBufferForTuple(), revmap_physical_extend(), scanGetCandidate(), scanPendingInsert(), shiftList(), spgdoinsert(), spgGetCache(), SpGistNewBuffer(), spgprocesspending(), spgvacuumpage(), spgWalk(), startScanEntry(), statapprox_heap(), summarize_range(), UnlockReleaseBuffer(), verify_heapam(), visibilitymap_clear(), visibilitymap_prepare_truncate(), visibilitymap_set(), vm_readbuf(), XLogReadBufferExtended(), XLogReadBufferForRedoExtended(), and XLogRecordPageWithFreeSpace().

{
    BufferDesc *buf;

    Assert(BufferIsPinned(buffer));
    if (BufferIsLocal(buffer))
        return;                 /* local buffers need no lock */

    buf = GetBufferDescriptor(buffer - 1);

    if (mode == BUFFER_LOCK_UNLOCK)
        LWLockRelease(BufferDescriptorGetContentLock(buf));
    else if (mode == BUFFER_LOCK_SHARE)
        LWLockAcquire(BufferDescriptorGetContentLock(buf), LW_SHARED);
    else if (mode == BUFFER_LOCK_EXCLUSIVE)
        LWLockAcquire(BufferDescriptorGetContentLock(buf), LW_EXCLUSIVE);
    else
        elog(ERROR, "unrecognized buffer lock mode: %d", mode);
}

LockBufferForCleanup()

void LockBufferForCleanup

(

Buffer

buffer

)

Definition at line 3996 of file bufmgr.c.

References Assert, BM_PIN_COUNT_WAITER, BUF_STATE_GET_REFCOUNT, BUFFER_LOCK_EXCLUSIVE, BUFFER_LOCK_UNLOCK, BufferIsLocal, BufferIsPinned, DeadlockTimeout, elog, ERROR, get_ps_display(), GetBufferDescriptor, GetCurrentTimestamp(), GetPrivateRefCount(), InHotStandby, LocalRefCount, LockBuffer(), LockBufHdr(), log_recovery_conflict_waits, LogRecoveryConflict(), MyProcPid, now(), palloc(), pfree(), PG_WAIT_BUFFER_PIN, PROCSIG_RECOVERY_CONFLICT_BUFFERPIN, ProcWaitForSignal(), ResolveRecoveryConflictWithBufferPin(), set_ps_display(), SetStartupBufferPinWaitBufId(), TimestampDifferenceExceeds(), UnlockBufHdr, update_process_title, and BufferDesc::wait_backend_pid.

Referenced by _bt_upgradelockbufcleanup(), ginVacuumPostingTree(), hashbulkdelete(), heap_force_common(), lazy_scan_heap(), ReadBuffer_common(), and XLogReadBufferForRedoExtended().

{
    BufferDesc *bufHdr;
    char       *new_status = NULL;
    TimestampTz waitStart = 0;
    bool        logged_recovery_conflict = false;

    Assert(BufferIsPinned(buffer));
    Assert(PinCountWaitBuf == NULL);

    if (BufferIsLocal(buffer))
    {
        /* There should be exactly one pin */
        if (LocalRefCount[-buffer - 1] != 1)
            elog(ERROR, "incorrect local pin count: %d",
                 LocalRefCount[-buffer - 1]);
        /* Nobody else to wait for */
        return;
    }

    /* There should be exactly one local pin */
    if (GetPrivateRefCount(buffer) != 1)
        elog(ERROR, "incorrect local pin count: %d",
             GetPrivateRefCount(buffer));

    bufHdr = GetBufferDescriptor(buffer - 1);

    for (;;)
    {
        uint32      buf_state;

        /* Try to acquire lock */
        LockBuffer(buffer, BUFFER_LOCK_EXCLUSIVE);
        buf_state = LockBufHdr(bufHdr);

        Assert(BUF_STATE_GET_REFCOUNT(buf_state) > 0);
        if (BUF_STATE_GET_REFCOUNT(buf_state) == 1)
        {
            /* Successfully acquired exclusive lock with pincount 1 */
            UnlockBufHdr(bufHdr, buf_state);

            /*
             * Emit the log message if recovery conflict on buffer pin was
             * resolved but the startup process waited longer than
             * deadlock_timeout for it.
             */
            if (logged_recovery_conflict)
                LogRecoveryConflict(PROCSIG_RECOVERY_CONFLICT_BUFFERPIN,
                                    waitStart, GetCurrentTimestamp(),
                                    NULL, false);

            /* Report change to non-waiting status */
            if (new_status)
            {
                set_ps_display(new_status);
                pfree(new_status);
            }
            return;
        }
        /* Failed, so mark myself as waiting for pincount 1 */
        if (buf_state & BM_PIN_COUNT_WAITER)
        {
            UnlockBufHdr(bufHdr, buf_state);
            LockBuffer(buffer, BUFFER_LOCK_UNLOCK);
            elog(ERROR, "multiple backends attempting to wait for pincount 1");
        }
        bufHdr->wait_backend_pid = MyProcPid;
        PinCountWaitBuf = bufHdr;
        buf_state |= BM_PIN_COUNT_WAITER;
        UnlockBufHdr(bufHdr, buf_state);
        LockBuffer(buffer, BUFFER_LOCK_UNLOCK);

        /* Wait to be signaled by UnpinBuffer() */
        if (InHotStandby)
        {
            /* Report change to waiting status */
            if (update_process_title && new_status == NULL)
            {
                const char *old_status;
                int         len;

                old_status = get_ps_display(&len);
                new_status = (char *) palloc(len + 8 + 1);
                memcpy(new_status, old_status, len);
                strcpy(new_status + len, " waiting");
                set_ps_display(new_status);
                new_status[len] = '\0'; /* truncate off " waiting" */
            }

            /*
             * Emit the log message if the startup process is waiting longer
             * than deadlock_timeout for recovery conflict on buffer pin.
             *
             * Skip this if first time through because the startup process has
             * not started waiting yet in this case. So, the wait start
             * timestamp is set after this logic.
             */
            if (waitStart != 0 && !logged_recovery_conflict)
            {
                TimestampTz now = GetCurrentTimestamp();

                if (TimestampDifferenceExceeds(waitStart, now,
                                               DeadlockTimeout))
                {
                    LogRecoveryConflict(PROCSIG_RECOVERY_CONFLICT_BUFFERPIN,
                                        waitStart, now, NULL, true);
                    logged_recovery_conflict = true;
                }
            }

            /*
             * Set the wait start timestamp if logging is enabled and first
             * time through.
             */
            if (log_recovery_conflict_waits && waitStart == 0)
                waitStart = GetCurrentTimestamp();

            /* Publish the bufid that Startup process waits on */
            SetStartupBufferPinWaitBufId(buffer - 1);
            /* Set alarm and then wait to be signaled by UnpinBuffer() */
            ResolveRecoveryConflictWithBufferPin();
            /* Reset the published bufid */
            SetStartupBufferPinWaitBufId(-1);
        }
        else
            ProcWaitForSignal(PG_WAIT_BUFFER_PIN);

        /*
         * Remove flag marking us as waiter. Normally this will not be set
         * anymore, but ProcWaitForSignal() can return for other signals as
         * well.  We take care to only reset the flag if we're the waiter, as
         * theoretically another backend could have started waiting. That's
         * impossible with the current usages due to table level locking, but
         * better be safe.
         */
        buf_state = LockBufHdr(bufHdr);
        if ((buf_state & BM_PIN_COUNT_WAITER) != 0 &&
            bufHdr->wait_backend_pid == MyProcPid)
            buf_state &= ~BM_PIN_COUNT_WAITER;
        UnlockBufHdr(bufHdr, buf_state);

        PinCountWaitBuf = NULL;
        /* Loop back and try again */
    }
}

LockBufHdr()

uint32 LockBufHdr

(

BufferDesc *

desc

)

Definition at line 4547 of file bufmgr.c.

References BM_LOCKED, finish_spin_delay(), init_local_spin_delay, perform_spin_delay(), pg_atomic_fetch_or_u32(), and BufferDesc::state.

Referenced by AbortBufferIO(), apw_dump_now(), BufferAlloc(), BufferGetLSNAtomic(), BufferSync(), ConditionalLockBufferForCleanup(), DropDatabaseBuffers(), DropRelFileNodeBuffers(), DropRelFileNodesAllBuffers(), FindAndDropRelFileNodeBuffers(), FlushBuffer(), FlushDatabaseBuffers(), FlushRelationBuffers(), FlushRelationsAllBuffers(), GetBufferFromRing(), InvalidateBuffer(), IsBufferCleanupOK(), LockBufferForCleanup(), MarkBufferDirtyHint(), pg_buffercache_pages(), ReadBuffer_common(), StartBufferIO(), StrategyGetBuffer(), SyncOneBuffer(), TerminateBufferIO(), UnlockBuffers(), UnpinBuffer(), and WaitIO().

{
    SpinDelayStatus delayStatus;
    uint32      old_buf_state;

    init_local_spin_delay(&delayStatus);

    while (true)
    {
        /* set BM_LOCKED flag */
        old_buf_state = pg_atomic_fetch_or_u32(&desc->state, BM_LOCKED);
        /* if it wasn't set before we're OK */
        if (!(old_buf_state & BM_LOCKED))
            break;
        perform_spin_delay(&delayStatus);
    }
    finish_spin_delay(&delayStatus);
    return old_buf_state | BM_LOCKED;
}

MarkBufferDirty()

void MarkBufferDirty

(

Buffer

buffer

)

Definition at line 1483 of file bufmgr.c.

References Assert, BM_DIRTY, BM_JUST_DIRTIED, BM_LOCKED, BUF_STATE_GET_REFCOUNT, BufferDescriptorGetContentLock, BufferIsLocal, BufferIsPinned, BufferIsValid, elog, ERROR, GetBufferDescriptor, LW_EXCLUSIVE, LWLockHeldByMeInMode(), MarkLocalBufferDirty(), pg_atomic_compare_exchange_u32(), pg_atomic_read_u32(), pgBufferUsage, BufferUsage::shared_blks_dirtied, BufferDesc::state, VacuumCostActive, VacuumCostBalance, VacuumCostPageDirty, VacuumPageDirty, and WaitBufHdrUnlocked().

Referenced by _bt_clear_incomplete_split(), _bt_dedup_pass(), _bt_delitems_delete(), _bt_delitems_vacuum(), _bt_getroot(), _bt_insertonpg(), _bt_mark_page_halfdead(), _bt_newroot(), _bt_restore_meta(), _bt_split(), _bt_unlink_halfdead_page(), _bt_update_meta_cleanup_info(), _hash_addovflpage(), _hash_doinsert(), _hash_expandtable(), _hash_freeovflpage(), _hash_init(), _hash_splitbucket(), _hash_squeezebucket(), _hash_vacuum_one_page(), addLeafTuple(), brin_doinsert(), brin_doupdate(), brin_initialize_empty_new_buffer(), brin_xlog_createidx(), brin_xlog_desummarize_page(), brin_xlog_insert_update(), brin_xlog_revmap_extend(), brin_xlog_samepage_update(), brin_xlog_update(), brinbuild(), brinbuildempty(), brinRevmapDesummarizeRange(), btree_xlog_dedup(), btree_xlog_delete(), btree_xlog_insert(), btree_xlog_mark_page_halfdead(), btree_xlog_newroot(), btree_xlog_split(), btree_xlog_unlink_page(), btree_xlog_vacuum(), createPostingTree(), do_setval(), doPickSplit(), fill_seq_with_data(), FreeSpaceMapPrepareTruncateRel(), generic_redo(), GenericXLogFinish(), ginbuild(), ginbuildempty(), ginbulkdelete(), ginDeletePage(), ginHeapTupleFastInsert(), ginPlaceToPage(), ginRedoClearIncompleteSplit(), ginRedoCreatePTree(), ginRedoDeleteListPages(), ginRedoDeletePage(), ginRedoInsert(), ginRedoInsertListPage(), ginRedoUpdateMetapage(), ginRedoVacuumDataLeafPage(), ginUpdateStats(), ginVacuumPostingTreeLeaf(), gistbuild(), gistbuildempty(), gistdeletepage(), gistplacetopage(), gistprunepage(), gistRedoClearFollowRight(), gistRedoDeleteRecord(), gistRedoPageDelete(), gistRedoPageSplitRecord(), gistRedoPageUpdateRecord(), gistvacuumpage(), hash_xlog_add_ovfl_page(), hash_xlog_delete(), hash_xlog_init_bitmap_page(), hash_xlog_init_meta_page(), hash_xlog_insert(), hash_xlog_move_page_contents(), hash_xlog_split_allocate_page(), hash_xlog_split_cleanup(), hash_xlog_split_complete(), hash_xlog_squeeze_page(), hash_xlog_update_meta_page(), hash_xlog_vacuum_one_page(), hashbucketcleanup(), hashbulkdelete(), heap_abort_speculative(), heap_delete(), heap_finish_speculative(), heap_force_common(), heap_inplace_update(), heap_insert(), heap_lock_tuple(), heap_lock_updated_tuple_rec(), heap_multi_insert(), heap_page_prune(), heap_update(), heap_xlog_clean(), heap_xlog_confirm(), heap_xlog_delete(), heap_xlog_freeze_page(), heap_xlog_inplace(), heap_xlog_insert(), heap_xlog_lock(), heap_xlog_lock_updated(), heap_xlog_multi_insert(), heap_xlog_update(), heap_xlog_visible(), lazy_scan_heap(), lazy_vacuum_page(), log_newpage_range(), moveLeafs(), nextval_internal(), RelationGetBufferForTuple(), revmap_physical_extend(), saveNodeLink(), seq_redo(), shiftList(), spgAddNodeAction(), spgbuild(), SpGistUpdateMetaPage(), spgRedoAddLeaf(), spgRedoAddNode(), spgRedoMoveLeafs(), spgRedoPickSplit(), spgRedoSplitTuple(), spgRedoVacuumLeaf(), spgRedoVacuumRedirect(), spgRedoVacuumRoot(), spgSplitNodeAction(), vacuumLeafPage(), vacuumLeafRoot(), vacuumRedirectAndPlaceholder(), visibilitymap_clear(), visibilitymap_prepare_truncate(), visibilitymap_set(), writeListPage(), and XLogReadBufferForRedoExtended().

{
    BufferDesc *bufHdr;
    uint32      buf_state;
    uint32      old_buf_state;

    if (!BufferIsValid(buffer))
        elog(ERROR, "bad buffer ID: %d", buffer);

    if (BufferIsLocal(buffer))
    {
        MarkLocalBufferDirty(buffer);
        return;
    }

    bufHdr = GetBufferDescriptor(buffer - 1);

    Assert(BufferIsPinned(buffer));
    Assert(LWLockHeldByMeInMode(BufferDescriptorGetContentLock(bufHdr),
                                LW_EXCLUSIVE));

    old_buf_state = pg_atomic_read_u32(&bufHdr->state);
    for (;;)
    {
        if (old_buf_state & BM_LOCKED)
            old_buf_state = WaitBufHdrUnlocked(bufHdr);

        buf_state = old_buf_state;

        Assert(BUF_STATE_GET_REFCOUNT(buf_state) > 0);
        buf_state |= BM_DIRTY | BM_JUST_DIRTIED;

        if (pg_atomic_compare_exchange_u32(&bufHdr->state, &old_buf_state,
                                           buf_state))
            break;
    }

    /*
     * If the buffer was not dirty already, do vacuum accounting.
     */
    if (!(old_buf_state & BM_DIRTY))
    {
        VacuumPageDirty++;
        pgBufferUsage.shared_blks_dirtied++;
        if (VacuumCostActive)
            VacuumCostBalance += VacuumCostPageDirty;
    }
}

MarkBufferDirtyHint()

void MarkBufferDirtyHint	(	Buffer	buffer,
		bool	buffer_std
	)

Definition at line 3770 of file bufmgr.c.

References Assert, BM_DIRTY, BM_JUST_DIRTIED, BM_PERMANENT, BUF_STATE_GET_REFCOUNT, BufferDescriptorGetContentLock, BufferGetPage, BufferIsLocal, BufferIsValid, PGPROC::delayChkpt, elog, ERROR, GetBufferDescriptor, GetPrivateRefCount(), InvalidXLogRecPtr, LockBufHdr(), LWLockHeldByMe(), MarkLocalBufferDirty(), MyProc, PageSetLSN, pg_atomic_read_u32(), pgBufferUsage, RecoveryInProgress(), RelFileNodeSkippingWAL(), buftag::rnode, BufferUsage::shared_blks_dirtied, BufferDesc::state, BufferDesc::tag, UnlockBufHdr, VacuumCostActive, VacuumCostBalance, VacuumCostPageDirty, VacuumPageDirty, XLogHintBitIsNeeded, XLogRecPtrIsInvalid, and XLogSaveBufferForHint().

Referenced by _bt_check_unique(), _bt_killitems(), _hash_kill_items(), brin_start_evacuating_page(), btvacuumpage(), fsm_search_avail(), fsm_set_and_search(), fsm_vacuum_page(), gistkillitems(), heap_page_prune(), read_seq_tuple(), SetHintBits(), and XLogRecordPageWithFreeSpace().

{
    BufferDesc *bufHdr;
    Page        page = BufferGetPage(buffer);

    if (!BufferIsValid(buffer))
        elog(ERROR, "bad buffer ID: %d", buffer);

    if (BufferIsLocal(buffer))
    {
        MarkLocalBufferDirty(buffer);
        return;
    }

    bufHdr = GetBufferDescriptor(buffer - 1);

    Assert(GetPrivateRefCount(buffer) > 0);
    /* here, either share or exclusive lock is OK */
    Assert(LWLockHeldByMe(BufferDescriptorGetContentLock(bufHdr)));

    /*
     * This routine might get called many times on the same page, if we are
     * making the first scan after commit of an xact that added/deleted many
     * tuples. So, be as quick as we can if the buffer is already dirty.  We
     * do this by not acquiring spinlock if it looks like the status bits are
     * already set.  Since we make this test unlocked, there's a chance we
     * might fail to notice that the flags have just been cleared, and failed
     * to reset them, due to memory-ordering issues.  But since this function
     * is only intended to be used in cases where failing to write out the
     * data would be harmless anyway, it doesn't really matter.
     */
    if ((pg_atomic_read_u32(&bufHdr->state) & (BM_DIRTY | BM_JUST_DIRTIED)) !=
        (BM_DIRTY | BM_JUST_DIRTIED))
    {
        XLogRecPtr  lsn = InvalidXLogRecPtr;
        bool        dirtied = false;
        bool        delayChkpt = false;
        uint32      buf_state;

        /*
         * If we need to protect hint bit updates from torn writes, WAL-log a
         * full page image of the page. This full page image is only necessary
         * if the hint bit update is the first change to the page since the
         * last checkpoint.
         *
         * We don't check full_page_writes here because that logic is included
         * when we call XLogInsert() since the value changes dynamically.
         */
        if (XLogHintBitIsNeeded() &&
            (pg_atomic_read_u32(&bufHdr->state) & BM_PERMANENT))
        {
            /*
             * If we must not write WAL, due to a relfilenode-specific
             * condition or being in recovery, don't dirty the page.  We can
             * set the hint, just not dirty the page as a result so the hint
             * is lost when we evict the page or shutdown.
             *
             * See src/backend/storage/page/README for longer discussion.
             */
            if (RecoveryInProgress() ||
                RelFileNodeSkippingWAL(bufHdr->tag.rnode))
                return;

            /*
             * If the block is already dirty because we either made a change
             * or set a hint already, then we don't need to write a full page
             * image.  Note that aggressive cleaning of blocks dirtied by hint
             * bit setting would increase the call rate. Bulk setting of hint
             * bits would reduce the call rate...
             *
             * We must issue the WAL record before we mark the buffer dirty.
             * Otherwise we might write the page before we write the WAL. That
             * causes a race condition, since a checkpoint might occur between
             * writing the WAL record and marking the buffer dirty. We solve
             * that with a kluge, but one that is already in use during
             * transaction commit to prevent race conditions. Basically, we
             * simply prevent the checkpoint WAL record from being written
             * until we have marked the buffer dirty. We don't start the
             * checkpoint flush until we have marked dirty, so our checkpoint
             * must flush the change to disk successfully or the checkpoint
             * never gets written, so crash recovery will fix.
             *
             * It's possible we may enter here without an xid, so it is
             * essential that CreateCheckpoint waits for virtual transactions
             * rather than full transactionids.
             */
            MyProc->delayChkpt = delayChkpt = true;
            lsn = XLogSaveBufferForHint(buffer, buffer_std);
        }

        buf_state = LockBufHdr(bufHdr);

        Assert(BUF_STATE_GET_REFCOUNT(buf_state) > 0);

        if (!(buf_state & BM_DIRTY))
        {
            dirtied = true;     /* Means "will be dirtied by this action" */

            /*
             * Set the page LSN if we wrote a backup block. We aren't supposed
             * to set this when only holding a share lock but as long as we
             * serialise it somehow we're OK. We choose to set LSN while
             * holding the buffer header lock, which causes any reader of an
             * LSN who holds only a share lock to also obtain a buffer header
             * lock before using PageGetLSN(), which is enforced in
             * BufferGetLSNAtomic().
             *
             * If checksums are enabled, you might think we should reset the
             * checksum here. That will happen when the page is written
             * sometime later in this checkpoint cycle.
             */
            if (!XLogRecPtrIsInvalid(lsn))
                PageSetLSN(page, lsn);
        }

        buf_state |= BM_DIRTY | BM_JUST_DIRTIED;
        UnlockBufHdr(bufHdr, buf_state);

        if (delayChkpt)
            MyProc->delayChkpt = false;

        if (dirtied)
        {
            VacuumPageDirty++;
            pgBufferUsage.shared_blks_dirtied++;
            if (VacuumCostActive)
                VacuumCostBalance += VacuumCostPageDirty;
        }
    }
}

NewPrivateRefCountEntry()

static PrivateRefCountEntry * NewPrivateRefCountEntry ( Buffer  buffer )

static

Definition at line 281 of file bufmgr.c.

References Assert, PrivateRefCountEntry::buffer, PrivateRefCountEntry::refcount, and ReservedRefCountEntry.

Referenced by PinBuffer(), and PinBuffer_Locked().

{
    PrivateRefCountEntry *res;

    /* only allowed to be called when a reservation has been made */
    Assert(ReservedRefCountEntry != NULL);

    /* use up the reserved entry */
    res = ReservedRefCountEntry;
    ReservedRefCountEntry = NULL;

    /* and fill it */
    res->buffer = buffer;
    res->refcount = 0;

    return res;
}

PinBuffer()

static bool PinBuffer ( BufferDesc *  buf, BufferAccessStrategy  strategy  )

static

Definition at line 1604 of file bufmgr.c.

References Assert, BM_LOCKED, BM_MAX_USAGE_COUNT, BM_VALID, BUF_REFCOUNT_ONE, BUF_STATE_GET_USAGECOUNT, BUF_USAGECOUNT_ONE, BufferDescriptorGetBuffer, BufHdrGetBlock, CurrentResourceOwner, GetPrivateRefCountEntry(), NewPrivateRefCountEntry(), pg_atomic_compare_exchange_u32(), pg_atomic_read_u32(), PrivateRefCountEntry::refcount, ReservePrivateRefCountEntry(), ResourceOwnerRememberBuffer(), BufferDesc::state, VALGRIND_MAKE_MEM_DEFINED, and WaitBufHdrUnlocked().

Referenced by BufferAlloc().

{
    Buffer      b = BufferDescriptorGetBuffer(buf);
    bool        result;
    PrivateRefCountEntry *ref;

    ref = GetPrivateRefCountEntry(b, true);

    if (ref == NULL)
    {
        uint32      buf_state;
        uint32      old_buf_state;

        ReservePrivateRefCountEntry();
        ref = NewPrivateRefCountEntry(b);

        old_buf_state = pg_atomic_read_u32(&buf->state);
        for (;;)
        {
            if (old_buf_state & BM_LOCKED)
                old_buf_state = WaitBufHdrUnlocked(buf);

            buf_state = old_buf_state;

            /* increase refcount */
            buf_state += BUF_REFCOUNT_ONE;

            if (strategy == NULL)
            {
                /* Default case: increase usagecount unless already max. */
                if (BUF_STATE_GET_USAGECOUNT(buf_state) < BM_MAX_USAGE_COUNT)
                    buf_state += BUF_USAGECOUNT_ONE;
            }
            else
            {
                /*
                 * Ring buffers shouldn't evict others from pool.  Thus we
                 * don't make usagecount more than 1.
                 */
                if (BUF_STATE_GET_USAGECOUNT(buf_state) == 0)
                    buf_state += BUF_USAGECOUNT_ONE;
            }

            if (pg_atomic_compare_exchange_u32(&buf->state, &old_buf_state,
                                               buf_state))
            {
                result = (buf_state & BM_VALID) != 0;

                /*
                 * Assume that we acquired a buffer pin for the purposes of
                 * Valgrind buffer client checks (even in !result case) to
                 * keep things simple.  Buffers that are unsafe to access are
                 * not generally guaranteed to be marked undefined or
                 * non-accessible in any case.
                 */
                VALGRIND_MAKE_MEM_DEFINED(BufHdrGetBlock(buf), BLCKSZ);
                break;
            }
        }
    }
    else
    {
        /*
         * If we previously pinned the buffer, it must surely be valid.
         *
         * Note: We deliberately avoid a Valgrind client request here.
         * Individual access methods can optionally superimpose buffer page
         * client requests on top of our client requests to enforce that
         * buffers are only accessed while locked (and pinned).  It's possible
         * that the buffer page is legitimately non-accessible here.  We
         * cannot meddle with that.
         */
        result = true;
    }

    ref->refcount++;
    Assert(ref->refcount > 0);
    ResourceOwnerRememberBuffer(CurrentResourceOwner, b);
    return result;
}

PinBuffer_Locked()

static void PinBuffer_Locked ( BufferDesc *  buf )

static

Definition at line 1707 of file bufmgr.c.

References Assert, BM_LOCKED, BUF_REFCOUNT_ONE, BufferDescriptorGetBuffer, BufHdrGetBlock, CurrentResourceOwner, GetPrivateRefCountEntry(), NewPrivateRefCountEntry(), pg_atomic_read_u32(), PrivateRefCountEntry::refcount, ResourceOwnerRememberBuffer(), BufferDesc::state, UnlockBufHdr, and VALGRIND_MAKE_MEM_DEFINED.

Referenced by BufferAlloc(), FlushDatabaseBuffers(), FlushRelationBuffers(), FlushRelationsAllBuffers(), and SyncOneBuffer().

{
    Buffer      b;
    PrivateRefCountEntry *ref;
    uint32      buf_state;

    /*
     * As explained, We don't expect any preexisting pins. That allows us to
     * manipulate the PrivateRefCount after releasing the spinlock
     */
    Assert(GetPrivateRefCountEntry(BufferDescriptorGetBuffer(buf), false) == NULL);

    /*
     * Buffer can't have a preexisting pin, so mark its page as defined to
     * Valgrind (this is similar to the PinBuffer() case where the backend
     * doesn't already have a buffer pin)
     */
    VALGRIND_MAKE_MEM_DEFINED(BufHdrGetBlock(buf), BLCKSZ);

    /*
     * Since we hold the buffer spinlock, we can update the buffer state and
     * release the lock in one operation.
     */
    buf_state = pg_atomic_read_u32(&buf->state);
    Assert(buf_state & BM_LOCKED);
    buf_state += BUF_REFCOUNT_ONE;
    UnlockBufHdr(buf, buf_state);

    b = BufferDescriptorGetBuffer(buf);

    ref = NewPrivateRefCountEntry(b);
    ref->refcount++;

    ResourceOwnerRememberBuffer(CurrentResourceOwner, b);
}

PrefetchBuffer()

PrefetchBufferResult PrefetchBuffer	(	Relation	reln,
		ForkNumber	forkNum,
		BlockNumber	blockNum
	)

Definition at line 587 of file bufmgr.c.

References Assert, BlockNumberIsValid, ereport, errcode(), errmsg(), ERROR, PrefetchLocalBuffer(), PrefetchSharedBuffer(), RelationData::rd_smgr, RELATION_IS_OTHER_TEMP, RelationIsValid, RelationOpenSmgr, and RelationUsesLocalBuffers.

Referenced by BitmapPrefetch(), count_nondeletable_pages(), HeapTupleHeaderAdvanceLatestRemovedXid(), and pg_prewarm().

{
    Assert(RelationIsValid(reln));
    Assert(BlockNumberIsValid(blockNum));

    /* Open it at the smgr level if not already done */
    RelationOpenSmgr(reln);

    if (RelationUsesLocalBuffers(reln))
    {
        /* see comments in ReadBufferExtended */
        if (RELATION_IS_OTHER_TEMP(reln))
            ereport(ERROR,
                    (errcode(ERRCODE_FEATURE_NOT_SUPPORTED),
                     errmsg("cannot access temporary tables of other sessions")));

        /* pass it off to localbuf.c */
        return PrefetchLocalBuffer(reln->rd_smgr, forkNum, blockNum);
    }
    else
    {
        /* pass it to the shared buffer version */
        return PrefetchSharedBuffer(reln->rd_smgr, forkNum, blockNum);
    }
}

PrefetchSharedBuffer()

PrefetchBufferResult PrefetchSharedBuffer	(	SMgrRelation	smgr_reln,
		ForkNumber	forkNum,
		BlockNumber	blockNum
	)

Definition at line 500 of file bufmgr.c.

References Assert, BlockNumberIsValid, BufMappingPartitionLock, BufTableHashCode(), BufTableLookup(), INIT_BUFFERTAG, PrefetchBufferResult::initiated_io, InvalidBuffer, LW_SHARED, LWLockAcquire(), LWLockRelease(), RelFileNodeBackend::node, PrefetchBufferResult::recent_buffer, SMgrRelationData::smgr_rnode, and smgrprefetch().

Referenced by PrefetchBuffer().

{
    PrefetchBufferResult result = {InvalidBuffer, false};
    BufferTag   newTag;         /* identity of requested block */
    uint32      newHash;        /* hash value for newTag */
    LWLock     *newPartitionLock;   /* buffer partition lock for it */
    int         buf_id;

    Assert(BlockNumberIsValid(blockNum));

    /* create a tag so we can lookup the buffer */
    INIT_BUFFERTAG(newTag, smgr_reln->smgr_rnode.node,
                   forkNum, blockNum);

    /* determine its hash code and partition lock ID */
    newHash = BufTableHashCode(&newTag);
    newPartitionLock = BufMappingPartitionLock(newHash);

    /* see if the block is in the buffer pool already */
    LWLockAcquire(newPartitionLock, LW_SHARED);
    buf_id = BufTableLookup(&newTag, newHash);
    LWLockRelease(newPartitionLock);

    /* If not in buffers, initiate prefetch */
    if (buf_id < 0)
    {
#ifdef USE_PREFETCH
        /*
         * Try to initiate an asynchronous read.  This returns false in
         * recovery if the relation file doesn't exist.
         */
        if (smgrprefetch(smgr_reln, forkNum, blockNum))
            result.initiated_io = true;
#endif                          /* USE_PREFETCH */
    }
    else
    {
        /*
         * Report the buffer it was in at that time.  The caller may be able
         * to avoid a buffer table lookup, but it's not pinned and it must be
         * rechecked!
         */
        result.recent_buffer = buf_id + 1;
    }

    /*
     * If the block *is* in buffers, we do nothing.  This is not really ideal:
     * the block might be just about to be evicted, which would be stupid
     * since we know we are going to need it soon.  But the only easy answer
     * is to bump the usage_count, which does not seem like a great solution:
     * when the caller does ultimately touch the block, usage_count would get
     * bumped again, resulting in too much favoritism for blocks that are
     * involved in a prefetch sequence. A real fix would involve some
     * additional per-buffer state, and it's not clear that there's enough of
     * a problem to justify that.
     */

    return result;
}

PrintBufferLeakWarning()

void PrintBufferLeakWarning

(

Buffer

buffer

)

Definition at line 2607 of file bufmgr.c.

References Assert, buftag::blockNum, buf, BUF_FLAG_MASK, BUF_STATE_GET_REFCOUNT, BufferIsLocal, BufferIsValid, elog, buftag::forkNum, GetBufferDescriptor, GetLocalBufferDescriptor, GetPrivateRefCount(), InvalidBackendId, LocalRefCount, MyBackendId, pfree(), pg_atomic_read_u32(), relpathbackend, buftag::rnode, BufferDesc::state, BufferDesc::tag, and WARNING.

Referenced by CheckForBufferLeaks(), CheckForLocalBufferLeaks(), and ResourceOwnerReleaseInternal().

{
    BufferDesc *buf;
    int32       loccount;
    char       *path;
    BackendId   backend;
    uint32      buf_state;

    Assert(BufferIsValid(buffer));
    if (BufferIsLocal(buffer))
    {
        buf = GetLocalBufferDescriptor(-buffer - 1);
        loccount = LocalRefCount[-buffer - 1];
        backend = MyBackendId;
    }
    else
    {
        buf = GetBufferDescriptor(buffer - 1);
        loccount = GetPrivateRefCount(buffer);
        backend = InvalidBackendId;
    }

    /* theoretically we should lock the bufhdr here */
    path = relpathbackend(buf->tag.rnode, backend, buf->tag.forkNum);
    buf_state = pg_atomic_read_u32(&buf->state);
    elog(WARNING,
         "buffer refcount leak: [%03d] "
         "(rel=%s, blockNum=%u, flags=0x%x, refcount=%u %d)",
         buffer, path,
         buf->tag.blockNum, buf_state & BUF_FLAG_MASK,
         BUF_STATE_GET_REFCOUNT(buf_state), loccount);
    pfree(path);
}

ReadBuffer()

Buffer ReadBuffer	(	Relation	reln,
		BlockNumber	blockNum
	)

Definition at line 619 of file bufmgr.c.

References MAIN_FORKNUM, RBM_NORMAL, and ReadBufferExtended().

Referenced by _bt_getbuf(), _bt_search_insert(), _hash_getbuf(), _hash_getbuf_with_condlock_cleanup(), blbulkdelete(), blinsert(), BloomNewBuffer(), brin_getinsertbuffer(), brinbuild(), brinGetStats(), brinGetTupleForHeapBlock(), brinRevmapDesummarizeRange(), brinRevmapInitialize(), bt_metap(), bt_page_items_internal(), bt_page_stats_internal(), fill_seq_with_data(), ginFindLeafPage(), ginFindParents(), ginGetStats(), ginHeapTupleFastInsert(), ginInsertCleanup(), GinNewBuffer(), ginStepRight(), ginUpdateStats(), gistBufferingFindCorrectParent(), gistbufferinginserttuples(), gistdoinsert(), gistFindCorrectParent(), gistFindPath(), gistfixsplit(), gistGetMaxLevel(), gistkillitems(), gistNewBuffer(), gistProcessItup(), gistScanPage(), heap_abort_speculative(), heap_delete(), heap_fetch(), heap_finish_speculative(), heap_force_common(), heap_get_latest_tid(), heap_index_delete_tuples(), heap_inplace_update(), heap_lock_tuple(), heap_update(), initBloomState(), pg_visibility(), pgstatginindex_internal(), read_seq_tuple(), RelationGetBufferForTuple(), ReleaseAndReadBuffer(), revmap_get_buffer(), revmap_physical_extend(), scanGetCandidate(), scanPendingInsert(), shiftList(), spgdoinsert(), spgGetCache(), SpGistGetBuffer(), SpGistNewBuffer(), SpGistUpdateMetaPage(), and spgWalk().

{
    return ReadBufferExtended(reln, MAIN_FORKNUM, blockNum, RBM_NORMAL, NULL);
}

ReadBuffer_common()

static Buffer ReadBuffer_common ( SMgrRelation  reln, char  relpersistence, ForkNumber  forkNum, BlockNumber  blockNum, ReadBufferMode  mode, BufferAccessStrategy  strategy, bool *  hit  )

static

Definition at line 729 of file bufmgr.c.

References Assert, RelFileNodeBackend::backend, BufferUsage::blk_read_time, BM_VALID, BufferAlloc(), BufferDescriptorGetBuffer, BufferDescriptorGetContentLock, BufHdrGetBlock, CurrentResourceOwner, RelFileNode::dbNode, ereport, errcode(), ERRCODE_DATA_CORRUPTED, errhint(), errmsg(), ERROR, INSTR_TIME_ADD, INSTR_TIME_GET_MICROSEC, INSTR_TIME_SET_CURRENT, INSTR_TIME_SUBTRACT, BufferUsage::local_blks_hit, BufferUsage::local_blks_read, BufferUsage::local_blks_written, LocalBufferAlloc(), LocalBufHdrGetBlock, LockBufferForCleanup(), LockBufHdr(), LW_EXCLUSIVE, LWLockAcquire(), MemSet, RelFileNodeBackend::node, P_NEW, PageIsNew, PageIsVerifiedExtended(), pg_atomic_read_u32(), pg_atomic_unlocked_write_u32(), pgBufferUsage, pgstat_count_buffer_read_time, PIV_LOG_WARNING, PIV_REPORT_STAT, RBM_NORMAL, RBM_NORMAL_NO_LOG, RBM_ZERO_AND_CLEANUP_LOCK, RBM_ZERO_AND_LOCK, RBM_ZERO_ON_ERROR, RelFileNode::relNode, relpath, ResourceOwnerEnlargeBuffers(), BufferUsage::shared_blks_hit, BufferUsage::shared_blks_read, BufferUsage::shared_blks_written, SMgrRelationData::smgr_rnode, smgrextend(), SmgrIsTemp, smgrnblocks(), smgrread(), RelFileNode::spcNode, StartBufferIO(), BufferDesc::state, TerminateBufferIO(), track_io_timing, UnlockBufHdr, VacuumCostActive, VacuumCostBalance, VacuumCostPageHit, VacuumCostPageMiss, VacuumPageHit, VacuumPageMiss, WARNING, and zero_damaged_pages.

Referenced by ReadBufferExtended(), and ReadBufferWithoutRelcache().

{
    BufferDesc *bufHdr;
    Block       bufBlock;
    bool        found;
    bool        isExtend;
    bool        isLocalBuf = SmgrIsTemp(smgr);

    *hit = false;

    /* Make sure we will have room to remember the buffer pin */
    ResourceOwnerEnlargeBuffers(CurrentResourceOwner);

    isExtend = (blockNum == P_NEW);

    TRACE_POSTGRESQL_BUFFER_READ_START(forkNum, blockNum,
                                       smgr->smgr_rnode.node.spcNode,
                                       smgr->smgr_rnode.node.dbNode,
                                       smgr->smgr_rnode.node.relNode,
                                       smgr->smgr_rnode.backend,
                                       isExtend);

    /* Substitute proper block number if caller asked for P_NEW */
    if (isExtend)
        blockNum = smgrnblocks(smgr, forkNum);

    if (isLocalBuf)
    {
        bufHdr = LocalBufferAlloc(smgr, forkNum, blockNum, &found);
        if (found)
            pgBufferUsage.local_blks_hit++;
        else if (isExtend)
            pgBufferUsage.local_blks_written++;
        else if (mode == RBM_NORMAL || mode == RBM_NORMAL_NO_LOG ||
                 mode == RBM_ZERO_ON_ERROR)
            pgBufferUsage.local_blks_read++;
    }
    else
    {
        /*
         * lookup the buffer.  IO_IN_PROGRESS is set if the requested block is
         * not currently in memory.
         */
        bufHdr = BufferAlloc(smgr, relpersistence, forkNum, blockNum,
                             strategy, &found);
        if (found)
            pgBufferUsage.shared_blks_hit++;
        else if (isExtend)
            pgBufferUsage.shared_blks_written++;
        else if (mode == RBM_NORMAL || mode == RBM_NORMAL_NO_LOG ||
                 mode == RBM_ZERO_ON_ERROR)
            pgBufferUsage.shared_blks_read++;
    }

    /* At this point we do NOT hold any locks. */

    /* if it was already in the buffer pool, we're done */
    if (found)
    {
        if (!isExtend)
        {
            /* Just need to update stats before we exit */
            *hit = true;
            VacuumPageHit++;

            if (VacuumCostActive)
                VacuumCostBalance += VacuumCostPageHit;

            TRACE_POSTGRESQL_BUFFER_READ_DONE(forkNum, blockNum,
                                              smgr->smgr_rnode.node.spcNode,
                                              smgr->smgr_rnode.node.dbNode,
                                              smgr->smgr_rnode.node.relNode,
                                              smgr->smgr_rnode.backend,
                                              isExtend,
                                              found);

            /*
             * In RBM_ZERO_AND_LOCK mode the caller expects the page to be
             * locked on return.
             */
            if (!isLocalBuf)
            {
                if (mode == RBM_ZERO_AND_LOCK)
                    LWLockAcquire(BufferDescriptorGetContentLock(bufHdr),
                                  LW_EXCLUSIVE);
                else if (mode == RBM_ZERO_AND_CLEANUP_LOCK)
                    LockBufferForCleanup(BufferDescriptorGetBuffer(bufHdr));
            }

            return BufferDescriptorGetBuffer(bufHdr);
        }

        /*
         * We get here only in the corner case where we are trying to extend
         * the relation but we found a pre-existing buffer marked BM_VALID.
         * This can happen because mdread doesn't complain about reads beyond
         * EOF (when zero_damaged_pages is ON) and so a previous attempt to
         * read a block beyond EOF could have left a "valid" zero-filled
         * buffer.  Unfortunately, we have also seen this case occurring
         * because of buggy Linux kernels that sometimes return an