bulk_write.c File Reference

#include "postgres.h"
#include "access/xloginsert.h"
#include "access/xlogrecord.h"
#include "storage/bufmgr.h"
#include "storage/bufpage.h"
#include "storage/bulk_write.h"
#include "storage/proc.h"
#include "storage/smgr.h"
#include "utils/rel.h"

Include dependency graph for bulk_write.c:

Go to the source code of this file.

Data Structures
struct	PendingWrite
struct	BulkWriteState

Macros
#define	MAX_PENDING_WRITES   XLR_MAX_BLOCK_ID

Typedefs
typedef struct PendingWrite	PendingWrite

Functions
static void	smgr_bulk_flush (BulkWriteState *bulkstate)
BulkWriteState *	smgr_bulk_start_rel (Relation rel, ForkNumber forknum)
BulkWriteState *	smgr_bulk_start_smgr (SMgrRelation smgr, ForkNumber forknum, bool use_wal)
void	smgr_bulk_finish (BulkWriteState *bulkstate)
static int	buffer_cmp (const void *a, const void *b)
void	smgr_bulk_write (BulkWriteState *bulkstate, BlockNumber blocknum, BulkWriteBuffer buf, bool page_std)
BulkWriteBuffer	smgr_bulk_get_buf (BulkWriteState *bulkstate)

Variables
static const PGIOAlignedBlock	zero_buffer = {{0}}

Macro Definition Documentation

MAX_PENDING_WRITES

#define MAX_PENDING_WRITES   XLR_MAX_BLOCK_ID

Definition at line 46 of file bulk_write.c.

Typedef Documentation

PendingWrite

typedef struct PendingWrite PendingWrite

Function Documentation

buffer_cmp()

static int buffer_cmp ( const void *  a, const void *  b  )

static

Definition at line 224 of file bulk_write.c.

{
    const PendingWrite *bufa = (const PendingWrite *) a;
    const PendingWrite *bufb = (const PendingWrite *) b;
 
    /* We should not see duplicated writes for the same block */
    Assert(bufa->blkno != bufb->blkno);
    if (bufa->blkno > bufb->blkno)
        return 1;
    else
        return -1;
}

References a, Assert, b, and PendingWrite::blkno.

Referenced by smgr_bulk_flush().

smgr_bulk_finish()

void smgr_bulk_finish

(

BulkWriteState *

bulkstate

)

Definition at line 129 of file bulk_write.c.

{
    /* WAL-log and flush any remaining pages */
    smgr_bulk_flush(bulkstate);
 
    /*
     * Fsync the relation, or register it for the next checkpoint, if
     * necessary.
     */
    if (SmgrIsTemp(bulkstate->smgr))
    {
        /* Temporary relations don't need to be fsync'd, ever */
    }
    else if (!bulkstate->use_wal)
    {
        /*----------
         * This is either an unlogged relation, or a permanent relation but we
         * skipped WAL-logging because wal_level=minimal:
         *
         * A) Unlogged relation
         *
         *    Unlogged relations will go away on crash, but they need to be
         *    fsync'd on a clean shutdown. It's sufficient to call
         *    smgrregistersync(), that ensures that the checkpointer will
         *    flush it at the shutdown checkpoint. (It will flush it on the
         *    next online checkpoint too, which is not strictly necessary.)
         *
         *    Note that the init-fork of an unlogged relation is not
         *    considered unlogged for our purposes. It's treated like a
         *    regular permanent relation. The callers will pass use_wal=true
         *    for the init fork.
         *
         * B) Permanent relation, WAL-logging skipped because wal_level=minimal
         *
         *    This is a new relation, and we didn't WAL-log the pages as we
         *    wrote, but they need to be fsync'd before commit.
         *
         *    We don't need to do that here, however. The fsync() is done at
         *    commit, by smgrDoPendingSyncs() (*).
         *
         *    (*) smgrDoPendingSyncs() might decide to WAL-log the whole
         *    relation at commit instead of fsyncing it, if the relation was
         *    very small, but it's smgrDoPendingSyncs() responsibility in any
         *    case.
         *
         * We cannot distinguish the two here, so conservatively assume it's
         * an unlogged relation. A permanent relation with wal_level=minimal
         * would require no actions, see above.
         */
        smgrregistersync(bulkstate->smgr, bulkstate->forknum);
    }
    else
    {
        /*
         * Permanent relation, WAL-logged normally.
         *
         * We already WAL-logged all the pages, so they will be replayed from
         * WAL on crash. However, when we wrote out the pages, we passed
         * skipFsync=true to avoid the overhead of registering all the writes
         * with the checkpointer.  Register the whole relation now.
         *
         * There is one hole in that idea: If a checkpoint occurred while we
         * were writing the pages, it already missed fsyncing the pages we had
         * written before the checkpoint started.  A crash later on would
         * replay the WAL starting from the checkpoint, therefore it wouldn't
         * replay our earlier WAL records.  So if a checkpoint started after
         * the bulk write, fsync the files now.
         */
 
        /*
         * Prevent a checkpoint from starting between the GetRedoRecPtr() and
         * smgrregistersync() calls.
         */
        Assert((MyProc->delayChkptFlags & DELAY_CHKPT_START) == 0);
        MyProc->delayChkptFlags |= DELAY_CHKPT_START;
 
        if (bulkstate->start_RedoRecPtr != GetRedoRecPtr())
        {
            /*
             * A checkpoint occurred and it didn't know about our writes, so
             * fsync() the relation ourselves.
             */
            MyProc->delayChkptFlags &= ~DELAY_CHKPT_START;
            smgrimmedsync(bulkstate->smgr, bulkstate->forknum);
            elog(DEBUG1, "flushed relation because a checkpoint occurred concurrently");
        }
        else
        {
            smgrregistersync(bulkstate->smgr, bulkstate->forknum);
            MyProc->delayChkptFlags &= ~DELAY_CHKPT_START;
        }
    }
}

References Assert, DEBUG1, DELAY_CHKPT_START, PGPROC::delayChkptFlags, elog, BulkWriteState::forknum, GetRedoRecPtr(), MyProc, BulkWriteState::smgr, smgr_bulk_flush(), smgrimmedsync(), SmgrIsTemp, smgrregistersync(), BulkWriteState::start_RedoRecPtr, and BulkWriteState::use_wal.

Referenced by _bt_load(), btbuildempty(), end_heap_rewrite(), gist_indexsortbuild(), RelationCopyStorage(), and spgbuildempty().

smgr_bulk_flush()

static void smgr_bulk_flush ( BulkWriteState *  bulkstate )

static

Definition at line 241 of file bulk_write.c.

{
    int         npending = bulkstate->npending;
    PendingWrite *pending_writes = bulkstate->pending_writes;
 
    if (npending == 0)
        return;
 
    if (npending > 1)
        qsort(pending_writes, npending, sizeof(PendingWrite), buffer_cmp);
 
    if (bulkstate->use_wal)
    {
        BlockNumber blknos[MAX_PENDING_WRITES];
        Page        pages[MAX_PENDING_WRITES];
        bool        page_std = true;
 
        for (int i = 0; i < npending; i++)
        {
            blknos[i] = pending_writes[i].blkno;
            pages[i] = pending_writes[i].buf->data;
 
            /*
             * If any of the pages use !page_std, we log them all as such.
             * That's a bit wasteful, but in practice, a mix of standard and
             * non-standard page layout is rare.  None of the built-in AMs do
             * that.
             */
            if (!pending_writes[i].page_std)
                page_std = false;
        }
        log_newpages(&bulkstate->smgr->smgr_rlocator.locator, bulkstate->forknum,
                     npending, blknos, pages, page_std);
    }
 
    for (int i = 0; i < npending; i++)
    {
        BlockNumber blkno = pending_writes[i].blkno;
        Page        page = pending_writes[i].buf->data;
 
        PageSetChecksumInplace(page, blkno);
 
        if (blkno >= bulkstate->pages_written)
        {
            /*
             * If we have to write pages nonsequentially, fill in the space
             * with zeroes until we come back and overwrite.  This is not
             * logically necessary on standard Unix filesystems (unwritten
             * space will read as zeroes anyway), but it should help to avoid
             * fragmentation.  The dummy pages aren't WAL-logged though.
             */
            while (blkno > bulkstate->pages_written)
            {
                /* don't set checksum for all-zero page */
                smgrextend(bulkstate->smgr, bulkstate->forknum,
                           bulkstate->pages_written++,
                           &zero_buffer,
                           true);
            }
 
            smgrextend(bulkstate->smgr, bulkstate->forknum, blkno, page, true);
            bulkstate->pages_written = pending_writes[i].blkno + 1;
        }
        else
            smgrwrite(bulkstate->smgr, bulkstate->forknum, blkno, page, true);
        pfree(page);
    }
 
    bulkstate->npending = 0;
}

References PendingWrite::blkno, PendingWrite::buf, buffer_cmp(), PGIOAlignedBlock::data, BulkWriteState::forknum, i, RelFileLocatorBackend::locator, log_newpages(), MAX_PENDING_WRITES, BulkWriteState::npending, BulkWriteState::pages_written, PageSetChecksumInplace(), BulkWriteState::pending_writes, pfree(), qsort, BulkWriteState::smgr, SMgrRelationData::smgr_rlocator, smgrextend(), smgrwrite(), BulkWriteState::use_wal, and zero_buffer.

Referenced by smgr_bulk_finish(), and smgr_bulk_write().

smgr_bulk_get_buf()

BulkWriteBuffer smgr_bulk_get_buf

(

BulkWriteState *

bulkstate

)

Definition at line 345 of file bulk_write.c.

{
    return MemoryContextAllocAligned(bulkstate->memcxt, BLCKSZ, PG_IO_ALIGN_SIZE, 0);
}

References BulkWriteState::memcxt, MemoryContextAllocAligned(), and PG_IO_ALIGN_SIZE.

Referenced by _bt_blnewpage(), _bt_uppershutdown(), btbuildempty(), gist_indexsortbuild(), gist_indexsortbuild_levelstate_flush(), raw_heap_insert(), RelationCopyStorage(), and spgbuildempty().

smgr_bulk_start_rel()

BulkWriteState* smgr_bulk_start_rel	(	Relation	rel,
		ForkNumber	forknum
	)

Definition at line 86 of file bulk_write.c.

{
    return smgr_bulk_start_smgr(RelationGetSmgr(rel),
                                forknum,
                                RelationNeedsWAL(rel) || forknum == INIT_FORKNUM);
}

References INIT_FORKNUM, RelationGetSmgr(), RelationNeedsWAL, and smgr_bulk_start_smgr().

Referenced by _bt_load(), begin_heap_rewrite(), btbuildempty(), gist_indexsortbuild(), and spgbuildempty().

smgr_bulk_start_smgr()

BulkWriteState* smgr_bulk_start_smgr	(	SMgrRelation	smgr,
		ForkNumber	forknum,
		bool	use_wal
	)

Definition at line 99 of file bulk_write.c.

{
    BulkWriteState *state;
 
    state = palloc(sizeof(BulkWriteState));
    state->smgr = smgr;
    state->forknum = forknum;
    state->use_wal = use_wal;
 
    state->npending = 0;
    state->pages_written = 0;
 
    state->start_RedoRecPtr = GetRedoRecPtr();
 
    /*
     * Remember the memory context.  We will use it to allocate all the
     * buffers later.
     */
    state->memcxt = CurrentMemoryContext;
 
    return state;
}

References CurrentMemoryContext, GetRedoRecPtr(), and palloc().

Referenced by RelationCopyStorage(), and smgr_bulk_start_rel().

smgr_bulk_write()

void smgr_bulk_write	(	BulkWriteState *	bulkstate,
		BlockNumber	blocknum,
		BulkWriteBuffer	buf,
		bool	page_std
	)

Definition at line 321 of file bulk_write.c.

{
    PendingWrite *w;
 
    w = &bulkstate->pending_writes[bulkstate->npending++];
    w->buf = buf;
    w->blkno = blocknum;
    w->page_std = page_std;
 
    if (bulkstate->npending == MAX_PENDING_WRITES)
        smgr_bulk_flush(bulkstate);
}

References PendingWrite::blkno, PendingWrite::buf, buf, MAX_PENDING_WRITES, BulkWriteState::npending, PendingWrite::page_std, BulkWriteState::pending_writes, and smgr_bulk_flush().

Referenced by _bt_blwritepage(), btbuildempty(), end_heap_rewrite(), gist_indexsortbuild(), gist_indexsortbuild_levelstate_flush(), raw_heap_insert(), RelationCopyStorage(), and spgbuildempty().

Variable Documentation

zero_buffer

const PGIOAlignedBlock zero_buffer = {{0}}

static

Definition at line 48 of file bulk_write.c.

Referenced by smgr_bulk_flush().