freelist.c File Reference

#include "postgres.h"
#include "pgstat.h"
#include "port/atomics.h"
#include "storage/buf_internals.h"
#include "storage/bufmgr.h"
#include "storage/proc.h"

Include dependency graph for freelist.c:

Go to the source code of this file.

Data Structures
struct	BufferStrategyControl
struct	BufferAccessStrategyData

Macros
#define	INT_ACCESS_ONCE(var)   ((int)(*((volatile int *)&(var))))

Typedefs
typedef struct BufferAccessStrategyData	BufferAccessStrategyData

Functions
static BufferDesc *	GetBufferFromRing (BufferAccessStrategy strategy, uint32 *buf_state)
static void	AddBufferToRing (BufferAccessStrategy strategy, BufferDesc *buf)
static uint32	ClockSweepTick (void)
bool	have_free_buffer (void)
BufferDesc *	StrategyGetBuffer (BufferAccessStrategy strategy, uint32 *buf_state, bool *from_ring)
void	StrategyFreeBuffer (BufferDesc *buf)
int	StrategySyncStart (uint32 *complete_passes, uint32 *num_buf_alloc)
void	StrategyNotifyBgWriter (int bgwprocno)
Size	StrategyShmemSize (void)
void	StrategyInitialize (bool init)
BufferAccessStrategy	GetAccessStrategy (BufferAccessStrategyType btype)
void	FreeAccessStrategy (BufferAccessStrategy strategy)
IOContext	IOContextForStrategy (BufferAccessStrategy strategy)
bool	StrategyRejectBuffer (BufferAccessStrategy strategy, BufferDesc *buf, bool from_ring)

Variables
static BufferStrategyControl *	StrategyControl = NULL

Macro Definition Documentation

INT_ACCESS_ONCE

#define INT_ACCESS_ONCE

(

var

)

((int)(*((volatile int *)&(var))))

Definition at line 24 of file freelist.c.

Typedef Documentation

BufferAccessStrategyData

typedef struct BufferAccessStrategyData BufferAccessStrategyData

Function Documentation

AddBufferToRing()

static void AddBufferToRing ( BufferAccessStrategy  strategy, BufferDesc *  buf  )

static

Definition at line 663 of file freelist.c.

{
    strategy->buffers[strategy->current] = BufferDescriptorGetBuffer(buf);
}

References buf, BufferDescriptorGetBuffer(), BufferAccessStrategyData::buffers, and BufferAccessStrategyData::current.

Referenced by StrategyGetBuffer().

ClockSweepTick()

static uint32 ClockSweepTick ( void  )

inlinestatic

Definition at line 108 of file freelist.c.

{
    uint32      victim;
 
    /*
     * Atomically move hand ahead one buffer - if there's several processes
     * doing this, this can lead to buffers being returned slightly out of
     * apparent order.
     */
    victim =
        pg_atomic_fetch_add_u32(&StrategyControl->nextVictimBuffer, 1);
 
    if (victim >= NBuffers)
    {
        uint32      originalVictim = victim;
 
        /* always wrap what we look up in BufferDescriptors */
        victim = victim % NBuffers;
 
        /*
         * If we're the one that just caused a wraparound, force
         * completePasses to be incremented while holding the spinlock. We
         * need the spinlock so StrategySyncStart() can return a consistent
         * value consisting of nextVictimBuffer and completePasses.
         */
        if (victim == 0)
        {
            uint32      expected;
            uint32      wrapped;
            bool        success = false;
 
            expected = originalVictim + 1;
 
            while (!success)
            {
                /*
                 * Acquire the spinlock while increasing completePasses. That
                 * allows other readers to read nextVictimBuffer and
                 * completePasses in a consistent manner which is required for
                 * StrategySyncStart().  In theory delaying the increment
                 * could lead to an overflow of nextVictimBuffers, but that's
                 * highly unlikely and wouldn't be particularly harmful.
                 */
                SpinLockAcquire(&StrategyControl->buffer_strategy_lock);
 
                wrapped = expected % NBuffers;
 
                success = pg_atomic_compare_exchange_u32(&StrategyControl->nextVictimBuffer,
                                                         &expected, wrapped);
                if (success)
                    StrategyControl->completePasses++;
                SpinLockRelease(&StrategyControl->buffer_strategy_lock);
            }
        }
    }
    return victim;
}

References BufferStrategyControl::buffer_strategy_lock, BufferStrategyControl::completePasses, NBuffers, BufferStrategyControl::nextVictimBuffer, pg_atomic_compare_exchange_u32(), pg_atomic_fetch_add_u32(), SpinLockAcquire, SpinLockRelease, StrategyControl, and success.

Referenced by StrategyGetBuffer().

FreeAccessStrategy()

void FreeAccessStrategy

(

BufferAccessStrategy

strategy

)

Definition at line 596 of file freelist.c.

{
    /* don't crash if called on a "default" strategy */
    if (strategy != NULL)
        pfree(strategy);
}

References pfree().

Referenced by blgetbitmap(), FreeBulkInsertState(), heap_endscan(), initscan(), parallel_vacuum_main(), and RelationCopyStorageUsingBuffer().

GetAccessStrategy()

BufferAccessStrategy GetAccessStrategy

(

BufferAccessStrategyType

btype

)

Definition at line 541 of file freelist.c.

{
    BufferAccessStrategy strategy;
    int         ring_size;
 
    /*
     * Select ring size to use.  See buffer/README for rationales.
     *
     * Note: if you change the ring size for BAS_BULKREAD, see also
     * SYNC_SCAN_REPORT_INTERVAL in access/heap/syncscan.c.
     */
    switch (btype)
    {
        case BAS_NORMAL:
            /* if someone asks for NORMAL, just give 'em a "default" object */
            return NULL;
 
        case BAS_BULKREAD:
            ring_size = 256 * 1024 / BLCKSZ;
            break;
        case BAS_BULKWRITE:
            ring_size = 16 * 1024 * 1024 / BLCKSZ;
            break;
        case BAS_VACUUM:
            ring_size = 256 * 1024 / BLCKSZ;
            break;
 
        default:
            elog(ERROR, "unrecognized buffer access strategy: %d",
                 (int) btype);
            return NULL;        /* keep compiler quiet */
    }
 
    /* Make sure ring isn't an undue fraction of shared buffers */
    ring_size = Min(NBuffers / 8, ring_size);
 
    /* Allocate the object and initialize all elements to zeroes */
    strategy = (BufferAccessStrategy)
        palloc0(offsetof(BufferAccessStrategyData, buffers) +
                ring_size * sizeof(Buffer));
 
    /* Set fields that don't start out zero */
    strategy->btype = btype;
    strategy->ring_size = ring_size;
 
    return strategy;
}

References BAS_BULKREAD, BAS_BULKWRITE, BAS_NORMAL, BAS_VACUUM, BufferAccessStrategyData::btype, elog(), ERROR, Min, NBuffers, palloc0(), and BufferAccessStrategyData::ring_size.

Referenced by blgetbitmap(), bt_check_every_level(), collect_corrupt_items(), collect_visibility_data(), do_autovacuum(), GetBulkInsertState(), initscan(), parallel_vacuum_main(), pgstat_index(), pgstathashindex(), pgstatindex_impl(), RelationCopyStorageUsingBuffer(), ScanSourceDatabasePgClass(), statapprox_heap(), vacuum(), and verify_heapam().

GetBufferFromRing()

static BufferDesc * GetBufferFromRing ( BufferAccessStrategy  strategy, uint32 *  buf_state  )

static

Definition at line 610 of file freelist.c.

{
    BufferDesc *buf;
    Buffer      bufnum;
    uint32      local_buf_state;    /* to avoid repeated (de-)referencing */
 
 
    /* Advance to next ring slot */
    if (++strategy->current >= strategy->ring_size)
        strategy->current = 0;
 
    /*
     * If the slot hasn't been filled yet, tell the caller to allocate a new
     * buffer with the normal allocation strategy.  He will then fill this
     * slot by calling AddBufferToRing with the new buffer.
     */
    bufnum = strategy->buffers[strategy->current];
    if (bufnum == InvalidBuffer)
        return NULL;
 
    /*
     * If the buffer is pinned we cannot use it under any circumstances.
     *
     * If usage_count is 0 or 1 then the buffer is fair game (we expect 1,
     * since our own previous usage of the ring element would have left it
     * there, but it might've been decremented by clock sweep since then). A
     * higher usage_count indicates someone else has touched the buffer, so we
     * shouldn't re-use it.
     */
    buf = GetBufferDescriptor(bufnum - 1);
    local_buf_state = LockBufHdr(buf);
    if (BUF_STATE_GET_REFCOUNT(local_buf_state) == 0
        && BUF_STATE_GET_USAGECOUNT(local_buf_state) <= 1)
    {
        *buf_state = local_buf_state;
        return buf;
    }
    UnlockBufHdr(buf, local_buf_state);
 
    /*
     * Tell caller to allocate a new buffer with the normal allocation
     * strategy.  He'll then replace this ring element via AddBufferToRing.
     */
    return NULL;
}

References buf, BUF_STATE_GET_REFCOUNT, BUF_STATE_GET_USAGECOUNT, BufferAccessStrategyData::buffers, BufferAccessStrategyData::current, GetBufferDescriptor(), InvalidBuffer, LockBufHdr(), BufferAccessStrategyData::ring_size, and UnlockBufHdr().

Referenced by StrategyGetBuffer().

have_free_buffer()

bool have_free_buffer

(

void

)

Definition at line 175 of file freelist.c.

{
    if (StrategyControl->firstFreeBuffer >= 0)
        return true;
    else
        return false;
}

References BufferStrategyControl::firstFreeBuffer, and StrategyControl.

Referenced by apw_load_buffers(), and autoprewarm_database_main().

IOContextForStrategy()

IOContext IOContextForStrategy

(

BufferAccessStrategy

strategy

)

Definition at line 673 of file freelist.c.

{
    if (!strategy)
        return IOCONTEXT_NORMAL;
 
    switch (strategy->btype)
    {
        case BAS_NORMAL:
 
            /*
             * Currently, GetAccessStrategy() returns NULL for
             * BufferAccessStrategyType BAS_NORMAL, so this case is
             * unreachable.
             */
            pg_unreachable();
            return IOCONTEXT_NORMAL;
        case BAS_BULKREAD:
            return IOCONTEXT_BULKREAD;
        case BAS_BULKWRITE:
            return IOCONTEXT_BULKWRITE;
        case BAS_VACUUM:
            return IOCONTEXT_VACUUM;
    }
 
    elog(ERROR, "unrecognized BufferAccessStrategyType: %d", strategy->btype);
    pg_unreachable();
}

References BAS_BULKREAD, BAS_BULKWRITE, BAS_NORMAL, BAS_VACUUM, BufferAccessStrategyData::btype, elog(), ERROR, IOCONTEXT_BULKREAD, IOCONTEXT_BULKWRITE, IOCONTEXT_NORMAL, IOCONTEXT_VACUUM, and pg_unreachable.

Referenced by BufferAlloc().

StrategyFreeBuffer()

void StrategyFreeBuffer

(

BufferDesc *

buf

)

Definition at line 363 of file freelist.c.

{
    SpinLockAcquire(&StrategyControl->buffer_strategy_lock);
 
    /*
     * It is possible that we are told to put something in the freelist that
     * is already in it; don't screw up the list if so.
     */
    if (buf->freeNext == FREENEXT_NOT_IN_LIST)
    {
        buf->freeNext = StrategyControl->firstFreeBuffer;
        if (buf->freeNext < 0)
            StrategyControl->lastFreeBuffer = buf->buf_id;
        StrategyControl->firstFreeBuffer = buf->buf_id;
    }
 
    SpinLockRelease(&StrategyControl->buffer_strategy_lock);
}

References buf, BufferStrategyControl::buffer_strategy_lock, BufferStrategyControl::firstFreeBuffer, FREENEXT_NOT_IN_LIST, BufferStrategyControl::lastFreeBuffer, SpinLockAcquire, SpinLockRelease, and StrategyControl.

Referenced by InvalidateBuffer().

StrategyGetBuffer()

BufferDesc* StrategyGetBuffer	(	BufferAccessStrategy	strategy,
		uint32 *	buf_state,
		bool *	from_ring
	)

Definition at line 196 of file freelist.c.

{
    BufferDesc *buf;
    int         bgwprocno;
    int         trycounter;
    uint32      local_buf_state;    /* to avoid repeated (de-)referencing */
 
    *from_ring = false;
 
    /*
     * If given a strategy object, see whether it can select a buffer. We
     * assume strategy objects don't need buffer_strategy_lock.
     */
    if (strategy != NULL)
    {
        buf = GetBufferFromRing(strategy, buf_state);
        if (buf != NULL)
        {
            *from_ring = true;
            return buf;
        }
    }
 
    /*
     * If asked, we need to waken the bgwriter. Since we don't want to rely on
     * a spinlock for this we force a read from shared memory once, and then
     * set the latch based on that value. We need to go through that length
     * because otherwise bgwprocno might be reset while/after we check because
     * the compiler might just reread from memory.
     *
     * This can possibly set the latch of the wrong process if the bgwriter
     * dies in the wrong moment. But since PGPROC->procLatch is never
     * deallocated the worst consequence of that is that we set the latch of
     * some arbitrary process.
     */
    bgwprocno = INT_ACCESS_ONCE(StrategyControl->bgwprocno);
    if (bgwprocno != -1)
    {
        /* reset bgwprocno first, before setting the latch */
        StrategyControl->bgwprocno = -1;
 
        /*
         * Not acquiring ProcArrayLock here which is slightly icky. It's
         * actually fine because procLatch isn't ever freed, so we just can
         * potentially set the wrong process' (or no process') latch.
         */
        SetLatch(&ProcGlobal->allProcs[bgwprocno].procLatch);
    }
 
    /*
     * We count buffer allocation requests so that the bgwriter can estimate
     * the rate of buffer consumption.  Note that buffers recycled by a
     * strategy object are intentionally not counted here.
     */
    pg_atomic_fetch_add_u32(&StrategyControl->numBufferAllocs, 1);
 
    /*
     * First check, without acquiring the lock, whether there's buffers in the
     * freelist. Since we otherwise don't require the spinlock in every
     * StrategyGetBuffer() invocation, it'd be sad to acquire it here -
     * uselessly in most cases. That obviously leaves a race where a buffer is
     * put on the freelist but we don't see the store yet - but that's pretty
     * harmless, it'll just get used during the next buffer acquisition.
     *
     * If there's buffers on the freelist, acquire the spinlock to pop one
     * buffer of the freelist. Then check whether that buffer is usable and
     * repeat if not.
     *
     * Note that the freeNext fields are considered to be protected by the
     * buffer_strategy_lock not the individual buffer spinlocks, so it's OK to
     * manipulate them without holding the spinlock.
     */
    if (StrategyControl->firstFreeBuffer >= 0)
    {
        while (true)
        {
            /* Acquire the spinlock to remove element from the freelist */
            SpinLockAcquire(&StrategyControl->buffer_strategy_lock);
 
            if (StrategyControl->firstFreeBuffer < 0)
            {
                SpinLockRelease(&StrategyControl->buffer_strategy_lock);
                break;
            }
 
            buf = GetBufferDescriptor(StrategyControl->firstFreeBuffer);
            Assert(buf->freeNext != FREENEXT_NOT_IN_LIST);
 
            /* Unconditionally remove buffer from freelist */
            StrategyControl->firstFreeBuffer = buf->freeNext;
            buf->freeNext = FREENEXT_NOT_IN_LIST;
 
            /*
             * Release the lock so someone else can access the freelist while
             * we check out this buffer.
             */
            SpinLockRelease(&StrategyControl->buffer_strategy_lock);
 
            /*
             * If the buffer is pinned or has a nonzero usage_count, we cannot
             * use it; discard it and retry.  (This can only happen if VACUUM
             * put a valid buffer in the freelist and then someone else used
             * it before we got to it.  It's probably impossible altogether as
             * of 8.3, but we'd better check anyway.)
             */
            local_buf_state = LockBufHdr(buf);
            if (BUF_STATE_GET_REFCOUNT(local_buf_state) == 0
                && BUF_STATE_GET_USAGECOUNT(local_buf_state) == 0)
            {
                if (strategy != NULL)
                    AddBufferToRing(strategy, buf);
                *buf_state = local_buf_state;
                return buf;
            }
            UnlockBufHdr(buf, local_buf_state);
        }
    }
 
    /* Nothing on the freelist, so run the "clock sweep" algorithm */
    trycounter = NBuffers;
    for (;;)
    {
        buf = GetBufferDescriptor(ClockSweepTick());
 
        /*
         * If the buffer is pinned or has a nonzero usage_count, we cannot use
         * it; decrement the usage_count (unless pinned) and keep scanning.
         */
        local_buf_state = LockBufHdr(buf);
 
        if (BUF_STATE_GET_REFCOUNT(local_buf_state) == 0)
        {
            if (BUF_STATE_GET_USAGECOUNT(local_buf_state) != 0)
            {
                local_buf_state -= BUF_USAGECOUNT_ONE;
 
                trycounter = NBuffers;
            }
            else
            {
                /* Found a usable buffer */
                if (strategy != NULL)
                    AddBufferToRing(strategy, buf);
                *buf_state = local_buf_state;
                return buf;
            }
        }
        else if (--trycounter == 0)
        {
            /*
             * We've scanned all the buffers without making any state changes,
             * so all the buffers are pinned (or were when we looked at them).
             * We could hope that someone will free one eventually, but it's
             * probably better to fail than to risk getting stuck in an
             * infinite loop.
             */
            UnlockBufHdr(buf, local_buf_state);
            elog(ERROR, "no unpinned buffers available");
        }
        UnlockBufHdr(buf, local_buf_state);
    }
}

References AddBufferToRing(), PROC_HDR::allProcs, Assert(), BufferStrategyControl::bgwprocno, buf, BUF_STATE_GET_REFCOUNT, BUF_STATE_GET_USAGECOUNT, BUF_USAGECOUNT_ONE, BufferStrategyControl::buffer_strategy_lock, ClockSweepTick(), elog(), ERROR, BufferStrategyControl::firstFreeBuffer, FREENEXT_NOT_IN_LIST, GetBufferDescriptor(), GetBufferFromRing(), INT_ACCESS_ONCE, LockBufHdr(), NBuffers, BufferStrategyControl::numBufferAllocs, pg_atomic_fetch_add_u32(), ProcGlobal, PGPROC::procLatch, SetLatch(), SpinLockAcquire, SpinLockRelease, StrategyControl, and UnlockBufHdr().

Referenced by BufferAlloc().

StrategyInitialize()

void StrategyInitialize

(

bool

init

)

Definition at line 474 of file freelist.c.

{
    bool        found;
 
    /*
     * Initialize the shared buffer lookup hashtable.
     *
     * Since we can't tolerate running out of lookup table entries, we must be
     * sure to specify an adequate table size here.  The maximum steady-state
     * usage is of course NBuffers entries, but BufferAlloc() tries to insert
     * a new entry before deleting the old.  In principle this could be
     * happening in each partition concurrently, so we could need as many as
     * NBuffers + NUM_BUFFER_PARTITIONS entries.
     */
    InitBufTable(NBuffers + NUM_BUFFER_PARTITIONS);
 
    /*
     * Get or create the shared strategy control block
     */
    StrategyControl = (BufferStrategyControl *)
        ShmemInitStruct("Buffer Strategy Status",
                        sizeof(BufferStrategyControl),
                        &found);
 
    if (!found)
    {
        /*
         * Only done once, usually in postmaster
         */
        Assert(init);
 
        SpinLockInit(&StrategyControl->buffer_strategy_lock);
 
        /*
         * Grab the whole linked list of free buffers for our strategy. We
         * assume it was previously set up by InitBufferPool().
         */
        StrategyControl->firstFreeBuffer = 0;
        StrategyControl->lastFreeBuffer = NBuffers - 1;
 
        /* Initialize the clock sweep pointer */
        pg_atomic_init_u32(&StrategyControl->nextVictimBuffer, 0);
 
        /* Clear statistics */
        StrategyControl->completePasses = 0;
        pg_atomic_init_u32(&StrategyControl->numBufferAllocs, 0);
 
        /* No pending notification */
        StrategyControl->bgwprocno = -1;
    }
    else
        Assert(!init);
}

References Assert(), BufferStrategyControl::bgwprocno, BufferStrategyControl::buffer_strategy_lock, BufferStrategyControl::completePasses, BufferStrategyControl::firstFreeBuffer, init, InitBufTable(), BufferStrategyControl::lastFreeBuffer, NBuffers, BufferStrategyControl::nextVictimBuffer, NUM_BUFFER_PARTITIONS, BufferStrategyControl::numBufferAllocs, pg_atomic_init_u32(), ShmemInitStruct(), SpinLockInit, and StrategyControl.

Referenced by InitBufferPool().

StrategyNotifyBgWriter()

void StrategyNotifyBgWriter

(

int

bgwprocno

)

Definition at line 431 of file freelist.c.

{
    /*
     * We acquire buffer_strategy_lock just to ensure that the store appears
     * atomic to StrategyGetBuffer.  The bgwriter should call this rather
     * infrequently, so there's no performance penalty from being safe.
     */
    SpinLockAcquire(&StrategyControl->buffer_strategy_lock);
    StrategyControl->bgwprocno = bgwprocno;
    SpinLockRelease(&StrategyControl->buffer_strategy_lock);
}

References BufferStrategyControl::bgwprocno, BufferStrategyControl::buffer_strategy_lock, SpinLockAcquire, SpinLockRelease, and StrategyControl.

Referenced by BackgroundWriterMain().

StrategyRejectBuffer()

bool StrategyRejectBuffer	(	BufferAccessStrategy	strategy,
		BufferDesc *	buf,
		bool	from_ring
	)

Definition at line 713 of file freelist.c.

{
    /* We only do this in bulkread mode */
    if (strategy->btype != BAS_BULKREAD)
        return false;
 
    /* Don't muck with behavior of normal buffer-replacement strategy */
    if (!from_ring ||
        strategy->buffers[strategy->current] != BufferDescriptorGetBuffer(buf))
        return false;
 
    /*
     * Remove the dirty buffer from the ring; necessary to prevent infinite
     * loop if all ring members are dirty.
     */
    strategy->buffers[strategy->current] = InvalidBuffer;
 
    return true;
}

References BAS_BULKREAD, BufferAccessStrategyData::btype, buf, BufferDescriptorGetBuffer(), BufferAccessStrategyData::buffers, BufferAccessStrategyData::current, and InvalidBuffer.

Referenced by BufferAlloc().

StrategyShmemSize()

Size StrategyShmemSize

(

void

)

Definition at line 453 of file freelist.c.

{
    Size        size = 0;
 
    /* size of lookup hash table ... see comment in StrategyInitialize */
    size = add_size(size, BufTableShmemSize(NBuffers + NUM_BUFFER_PARTITIONS));
 
    /* size of the shared replacement strategy control block */
    size = add_size(size, MAXALIGN(sizeof(BufferStrategyControl)));
 
    return size;
}

References add_size(), BufTableShmemSize(), MAXALIGN, NBuffers, and NUM_BUFFER_PARTITIONS.

Referenced by BufferShmemSize().

StrategySyncStart()

int StrategySyncStart	(	uint32 *	complete_passes,
		uint32 *	num_buf_alloc
	)

Definition at line 394 of file freelist.c.

{
    uint32      nextVictimBuffer;
    int         result;
 
    SpinLockAcquire(&StrategyControl->buffer_strategy_lock);
    nextVictimBuffer = pg_atomic_read_u32(&StrategyControl->nextVictimBuffer);
    result = nextVictimBuffer % NBuffers;
 
    if (complete_passes)
    {
        *complete_passes = StrategyControl->completePasses;
 
        /*
         * Additionally add the number of wraparounds that happened before
         * completePasses could be incremented. C.f. ClockSweepTick().
         */
        *complete_passes += nextVictimBuffer / NBuffers;
    }
 
    if (num_buf_alloc)
    {
        *num_buf_alloc = pg_atomic_exchange_u32(&StrategyControl->numBufferAllocs, 0);
    }
    SpinLockRelease(&StrategyControl->buffer_strategy_lock);
    return result;
}

References BufferStrategyControl::buffer_strategy_lock, BufferStrategyControl::completePasses, NBuffers, BufferStrategyControl::nextVictimBuffer, BufferStrategyControl::numBufferAllocs, pg_atomic_exchange_u32(), pg_atomic_read_u32(), SpinLockAcquire, SpinLockRelease, and StrategyControl.

Referenced by BgBufferSync().

Variable Documentation

StrategyControl

BufferStrategyControl* StrategyControl = NULL

static

Definition at line 65 of file freelist.c.

Referenced by ClockSweepTick(), have_free_buffer(), StrategyFreeBuffer(), StrategyGetBuffer(), StrategyInitialize(), StrategyNotifyBgWriter(), and StrategySyncStart().