storage.c File Reference

#include "postgres.h"
#include "miscadmin.h"
#include "access/visibilitymap.h"
#include "access/xact.h"
#include "access/xlog.h"
#include "access/xloginsert.h"
#include "access/xlogutils.h"
#include "catalog/storage.h"
#include "catalog/storage_xlog.h"
#include "storage/freespace.h"
#include "storage/smgr.h"
#include "utils/memutils.h"
#include "utils/rel.h"

Include dependency graph for storage.c:

Go to the source code of this file.

Data Structures
struct	PendingRelDelete

Typedefs
typedef struct PendingRelDelete	PendingRelDelete

Functions
SMgrRelation	RelationCreateStorage (RelFileNode rnode, char relpersistence)
void	log_smgrcreate (const RelFileNode *rnode, ForkNumber forkNum)
void	RelationDropStorage (Relation rel)
void	RelationPreserveStorage (RelFileNode rnode, bool atCommit)
void	RelationTruncate (Relation rel, BlockNumber nblocks)
void	RelationCopyStorage (SMgrRelation src, SMgrRelation dst, ForkNumber forkNum, char relpersistence)
void	smgrDoPendingDeletes (bool isCommit)
int	smgrGetPendingDeletes (bool forCommit, RelFileNode **ptr)
void	PostPrepare_smgr (void)
void	AtSubCommit_smgr (void)
void	AtSubAbort_smgr (void)
void	smgr_redo (XLogReaderState *record)

Variables
static PendingRelDelete *	pendingDeletes = NULL

Typedef Documentation

PendingRelDelete

typedef struct PendingRelDelete PendingRelDelete

Function Documentation

AtSubAbort_smgr()

void AtSubAbort_smgr

(

void

)

Definition at line 564 of file storage.c.

References smgrDoPendingDeletes().

Referenced by AbortSubTransaction().

{
    smgrDoPendingDeletes(false);
}

AtSubCommit_smgr()

void AtSubCommit_smgr

(

void

)

Definition at line 544 of file storage.c.

References GetCurrentTransactionNestLevel(), PendingRelDelete::nestLevel, and PendingRelDelete::next.

Referenced by CommitSubTransaction().

{
    int         nestLevel = GetCurrentTransactionNestLevel();
    PendingRelDelete *pending;

    for (pending = pendingDeletes; pending != NULL; pending = pending->next)
    {
        if (pending->nestLevel >= nestLevel)
            pending->nestLevel = nestLevel - 1;
    }
}

log_smgrcreate()

void log_smgrcreate	(	const RelFileNode *	rnode,
		ForkNumber	forkNum
	)

Definition at line 128 of file storage.c.

References xl_smgr_create::forkNum, xl_smgr_create::rnode, XLOG_SMGR_CREATE, XLogBeginInsert(), XLogInsert(), XLogRegisterData(), and XLR_SPECIAL_REL_UPDATE.

Referenced by heapam_relation_copy_data(), heapam_relation_set_new_filenode(), index_copy_data(), and RelationCreateStorage().

{
    xl_smgr_create xlrec;

    /*
     * Make an XLOG entry reporting the file creation.
     */
    xlrec.rnode = *rnode;
    xlrec.forkNum = forkNum;

    XLogBeginInsert();
    XLogRegisterData((char *) &xlrec, sizeof(xlrec));
    XLogInsert(RM_SMGR_ID, XLOG_SMGR_CREATE | XLR_SPECIAL_REL_UPDATE);
}

PostPrepare_smgr()

void PostPrepare_smgr

(

void

)

Definition at line 523 of file storage.c.

References PendingRelDelete::next, and pfree().

Referenced by PrepareTransaction().

{
    PendingRelDelete *pending;
    PendingRelDelete *next;

    for (pending = pendingDeletes; pending != NULL; pending = next)
    {
        next = pending->next;
        pendingDeletes = next;
        /* must explicitly free the list entry */
        pfree(pending);
    }
}

RelationCopyStorage()

void RelationCopyStorage	(	SMgrRelation	src,
		SMgrRelation	dst,
		ForkNumber	forkNum,
		char	relpersistence
	)

Definition at line 305 of file storage.c.

References RelFileNodeBackend::backend, buf, CHECK_FOR_INTERRUPTS, PGAlignedBlock::data, ereport, errcode(), ERRCODE_DATA_CORRUPTED, errmsg(), ERROR, INIT_FORKNUM, log_newpage(), RelFileNodeBackend::node, PageIsVerified(), PageSetChecksumInplace(), relpathbackend, SMgrRelationData::smgr_rnode, smgrextend(), smgrimmedsync(), smgrnblocks(), smgrread(), and XLogIsNeeded.

Referenced by heapam_relation_copy_data(), and index_copy_data().

{
    PGAlignedBlock buf;
    Page        page;
    bool        use_wal;
    bool        copying_initfork;
    BlockNumber nblocks;
    BlockNumber blkno;

    page = (Page) buf.data;

    /*
     * The init fork for an unlogged relation in many respects has to be
     * treated the same as normal relation, changes need to be WAL logged and
     * it needs to be synced to disk.
     */
    copying_initfork = relpersistence == RELPERSISTENCE_UNLOGGED &&
        forkNum == INIT_FORKNUM;

    /*
     * We need to log the copied data in WAL iff WAL archiving/streaming is
     * enabled AND it's a permanent relation.
     */
    use_wal = XLogIsNeeded() &&
        (relpersistence == RELPERSISTENCE_PERMANENT || copying_initfork);

    nblocks = smgrnblocks(src, forkNum);

    for (blkno = 0; blkno < nblocks; blkno++)
    {
        /* If we got a cancel signal during the copy of the data, quit */
        CHECK_FOR_INTERRUPTS();

        smgrread(src, forkNum, blkno, buf.data);

        if (!PageIsVerified(page, blkno))
            ereport(ERROR,
                    (errcode(ERRCODE_DATA_CORRUPTED),
                     errmsg("invalid page in block %u of relation %s",
                            blkno,
                            relpathbackend(src->smgr_rnode.node,
                                           src->smgr_rnode.backend,
                                           forkNum))));

        /*
         * WAL-log the copied page. Unfortunately we don't know what kind of a
         * page this is, so we have to log the full page including any unused
         * space.
         */
        if (use_wal)
            log_newpage(&dst->smgr_rnode.node, forkNum, blkno, page, false);

        PageSetChecksumInplace(page, blkno);

        /*
         * Now write the page.  We say isTemp = true even if it's not a temp
         * rel, because there's no need for smgr to schedule an fsync for this
         * write; we'll do it ourselves below.
         */
        smgrextend(dst, forkNum, blkno, buf.data, true);
    }

    /*
     * If the rel is WAL-logged, must fsync before commit.  We use heap_sync
     * to ensure that the toast table gets fsync'd too.  (For a temp or
     * unlogged rel we don't care since the data will be gone after a crash
     * anyway.)
     *
     * It's obvious that we must do this when not WAL-logging the copy. It's
     * less obvious that we have to do it even if we did WAL-log the copied
     * pages. The reason is that since we're copying outside shared buffers, a
     * CHECKPOINT occurring during the copy has no way to flush the previously
     * written data to disk (indeed it won't know the new rel even exists).  A
     * crash later on would replay WAL from the checkpoint, therefore it
     * wouldn't replay our earlier WAL entries. If we do not fsync those pages
     * here, they might still not be on disk when the crash occurs.
     */
    if (relpersistence == RELPERSISTENCE_PERMANENT || copying_initfork)
        smgrimmedsync(dst, forkNum);
}

RelationCreateStorage()

SMgrRelation RelationCreateStorage	(	RelFileNode	rnode,
		char	relpersistence
	)

Definition at line 79 of file storage.c.

References PendingRelDelete::atCommit, PendingRelDelete::backend, BackendIdForTempRelations, elog, ERROR, GetCurrentTransactionNestLevel(), InvalidBackendId, log_smgrcreate(), MAIN_FORKNUM, MemoryContextAlloc(), PendingRelDelete::nestLevel, PendingRelDelete::next, RelFileNodeBackend::node, pendingDeletes, PendingRelDelete::relnode, SMgrRelationData::smgr_rnode, smgrcreate(), smgropen(), and TopMemoryContext.

Referenced by heap_create(), heapam_relation_copy_data(), heapam_relation_set_new_filenode(), index_copy_data(), and RelationSetNewRelfilenode().

{
    PendingRelDelete *pending;
    SMgrRelation srel;
    BackendId   backend;
    bool        needs_wal;

    switch (relpersistence)
    {
        case RELPERSISTENCE_TEMP:
            backend = BackendIdForTempRelations();
            needs_wal = false;
            break;
        case RELPERSISTENCE_UNLOGGED:
            backend = InvalidBackendId;
            needs_wal = false;
            break;
        case RELPERSISTENCE_PERMANENT:
            backend = InvalidBackendId;
            needs_wal = true;
            break;
        default:
            elog(ERROR, "invalid relpersistence: %c", relpersistence);
            return NULL;        /* placate compiler */
    }

    srel = smgropen(rnode, backend);
    smgrcreate(srel, MAIN_FORKNUM, false);

    if (needs_wal)
        log_smgrcreate(&srel->smgr_rnode.node, MAIN_FORKNUM);

    /* Add the relation to the list of stuff to delete at abort */
    pending = (PendingRelDelete *)
        MemoryContextAlloc(TopMemoryContext, sizeof(PendingRelDelete));
    pending->relnode = rnode;
    pending->backend = backend;
    pending->atCommit = false;  /* delete if abort */
    pending->nestLevel = GetCurrentTransactionNestLevel();
    pending->next = pendingDeletes;
    pendingDeletes = pending;

    return srel;
}

RelationDropStorage()

void RelationDropStorage

(

Relation

rel

)

Definition at line 148 of file storage.c.

References PendingRelDelete::atCommit, PendingRelDelete::backend, GetCurrentTransactionNestLevel(), MemoryContextAlloc(), PendingRelDelete::nestLevel, PendingRelDelete::next, pendingDeletes, RelationData::rd_backend, RelationData::rd_node, RelationCloseSmgr, PendingRelDelete::relnode, and TopMemoryContext.

Referenced by DefineQueryRewrite(), heap_drop_with_catalog(), heapam_relation_copy_data(), index_copy_data(), index_drop(), and RelationSetNewRelfilenode().

{
    PendingRelDelete *pending;

    /* Add the relation to the list of stuff to delete at commit */
    pending = (PendingRelDelete *)
        MemoryContextAlloc(TopMemoryContext, sizeof(PendingRelDelete));
    pending->relnode = rel->rd_node;
    pending->backend = rel->rd_backend;
    pending->atCommit = true;   /* delete if commit */
    pending->nestLevel = GetCurrentTransactionNestLevel();
    pending->next = pendingDeletes;
    pendingDeletes = pending;

    /*
     * NOTE: if the relation was created in this transaction, it will now be
     * present in the pending-delete list twice, once with atCommit true and
     * once with atCommit false.  Hence, it will be physically deleted at end
     * of xact in either case (and the other entry will be ignored by
     * smgrDoPendingDeletes, so no error will occur).  We could instead remove
     * the existing list entry and delete the physical file immediately, but
     * for now I'll keep the logic simple.
     */

    RelationCloseSmgr(rel);
}

RelationPreserveStorage()

void RelationPreserveStorage	(	RelFileNode	rnode,
		bool	atCommit
	)

Definition at line 193 of file storage.c.

References PendingRelDelete::atCommit, PendingRelDelete::next, pfree(), RelFileNodeEquals, and PendingRelDelete::relnode.

Referenced by ATExecAddIndex(), and write_relmap_file().

{
    PendingRelDelete *pending;
    PendingRelDelete *prev;
    PendingRelDelete *next;

    prev = NULL;
    for (pending = pendingDeletes; pending != NULL; pending = next)
    {
        next = pending->next;
        if (RelFileNodeEquals(rnode, pending->relnode)
            && pending->atCommit == atCommit)
        {
            /* unlink and delete list entry */
            if (prev)
                prev->next = next;
            else
                pendingDeletes = next;
            pfree(pending);
            /* prev does not change */
        }
        else
        {
            /* unrelated entry, don't touch it */
            prev = pending;
        }
    }
}

RelationTruncate()

void RelationTruncate	(	Relation	rel,
		BlockNumber	nblocks
	)

Definition at line 230 of file storage.c.

References xl_smgr_truncate::blkno, xl_smgr_truncate::flags, FreeSpaceMapTruncateRel(), FSM_FORKNUM, InvalidBlockNumber, MAIN_FORKNUM, RelationData::rd_node, RelationData::rd_smgr, RelationNeedsWAL, RelationOpenSmgr, xl_smgr_truncate::rnode, SMgrRelationData::smgr_fsm_nblocks, SMgrRelationData::smgr_targblock, SMGR_TRUNCATE_ALL, SMgrRelationData::smgr_vm_nblocks, smgrexists(), smgrtruncate(), VISIBILITYMAP_FORKNUM, visibilitymap_truncate(), XLOG_SMGR_TRUNCATE, XLogBeginInsert(), XLogFlush(), XLogInsert(), XLogRegisterData(), and XLR_SPECIAL_REL_UPDATE.

Referenced by heapam_relation_nontransactional_truncate(), lazy_truncate_heap(), RelationTruncateIndexes(), and spgvacuumscan().

{
    bool        fsm;
    bool        vm;

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

    /*
     * Make sure smgr_targblock etc aren't pointing somewhere past new end
     */
    rel->rd_smgr->smgr_targblock = InvalidBlockNumber;
    rel->rd_smgr->smgr_fsm_nblocks = InvalidBlockNumber;
    rel->rd_smgr->smgr_vm_nblocks = InvalidBlockNumber;

    /* Truncate the FSM first if it exists */
    fsm = smgrexists(rel->rd_smgr, FSM_FORKNUM);
    if (fsm)
        FreeSpaceMapTruncateRel(rel, nblocks);

    /* Truncate the visibility map too if it exists. */
    vm = smgrexists(rel->rd_smgr, VISIBILITYMAP_FORKNUM);
    if (vm)
        visibilitymap_truncate(rel, nblocks);

    /*
     * We WAL-log the truncation before actually truncating, which means
     * trouble if the truncation fails. If we then crash, the WAL replay
     * likely isn't going to succeed in the truncation either, and cause a
     * PANIC. It's tempting to put a critical section here, but that cure
     * would be worse than the disease. It would turn a usually harmless
     * failure to truncate, that might spell trouble at WAL replay, into a
     * certain PANIC.
     */
    if (RelationNeedsWAL(rel))
    {
        /*
         * Make an XLOG entry reporting the file truncation.
         */
        XLogRecPtr  lsn;
        xl_smgr_truncate xlrec;

        xlrec.blkno = nblocks;
        xlrec.rnode = rel->rd_node;
        xlrec.flags = SMGR_TRUNCATE_ALL;

        XLogBeginInsert();
        XLogRegisterData((char *) &xlrec, sizeof(xlrec));

        lsn = XLogInsert(RM_SMGR_ID,
                         XLOG_SMGR_TRUNCATE | XLR_SPECIAL_REL_UPDATE);

        /*
         * Flush, because otherwise the truncation of the main relation might
         * hit the disk before the WAL record, and the truncation of the FSM
         * or visibility map. If we crashed during that window, we'd be left
         * with a truncated heap, but the FSM or visibility map would still
         * contain entries for the non-existent heap pages.
         */
        if (fsm || vm)
            XLogFlush(lsn);
    }

    /* Do the real work */
    smgrtruncate(rel->rd_smgr, MAIN_FORKNUM, nblocks);
}

smgr_redo()

void smgr_redo

(

XLogReaderState *

record

)

Definition at line 570 of file storage.c.

References Assert, xl_smgr_truncate::blkno, CreateFakeRelcacheEntry(), elog, XLogReaderState::EndRecPtr, xl_smgr_truncate::flags, xl_smgr_create::forkNum, FreeFakeRelcacheEntry(), FreeSpaceMapTruncateRel(), FSM_FORKNUM, InvalidBackendId, MAIN_FORKNUM, PANIC, xl_smgr_create::rnode, xl_smgr_truncate::rnode, SMGR_TRUNCATE_FSM, SMGR_TRUNCATE_HEAP, SMGR_TRUNCATE_VM, smgrcreate(), smgrexists(), smgropen(), smgrtruncate(), VISIBILITYMAP_FORKNUM, visibilitymap_truncate(), XLOG_SMGR_CREATE, XLOG_SMGR_TRUNCATE, XLogFlush(), XLogRecGetData, XLogRecGetInfo, XLogRecHasAnyBlockRefs, XLogTruncateRelation(), and XLR_INFO_MASK.

{
    XLogRecPtr  lsn = record->EndRecPtr;
    uint8       info = XLogRecGetInfo(record) & ~XLR_INFO_MASK;

    /* Backup blocks are not used in smgr records */
    Assert(!XLogRecHasAnyBlockRefs(record));

    if (info == XLOG_SMGR_CREATE)
    {
        xl_smgr_create *xlrec = (xl_smgr_create *) XLogRecGetData(record);
        SMgrRelation reln;

        reln = smgropen(xlrec->rnode, InvalidBackendId);
        smgrcreate(reln, xlrec->forkNum, true);
    }
    else if (info == XLOG_SMGR_TRUNCATE)
    {
        xl_smgr_truncate *xlrec = (xl_smgr_truncate *) XLogRecGetData(record);
        SMgrRelation reln;
        Relation    rel;

        reln = smgropen(xlrec->rnode, InvalidBackendId);

        /*
         * Forcibly create relation if it doesn't exist (which suggests that
         * it was dropped somewhere later in the WAL sequence).  As in
         * XLogReadBufferForRedo, we prefer to recreate the rel and replay the
         * log as best we can until the drop is seen.
         */
        smgrcreate(reln, MAIN_FORKNUM, true);

        /*
         * Before we perform the truncation, update minimum recovery point to
         * cover this WAL record. Once the relation is truncated, there's no
         * going back. The buffer manager enforces the WAL-first rule for
         * normal updates to relation files, so that the minimum recovery
         * point is always updated before the corresponding change in the data
         * file is flushed to disk. We have to do the same manually here.
         *
         * Doing this before the truncation means that if the truncation fails
         * for some reason, you cannot start up the system even after restart,
         * until you fix the underlying situation so that the truncation will
         * succeed. Alternatively, we could update the minimum recovery point
         * after truncation, but that would leave a small window where the
         * WAL-first rule could be violated.
         */
        XLogFlush(lsn);

        if ((xlrec->flags & SMGR_TRUNCATE_HEAP) != 0)
        {
            smgrtruncate(reln, MAIN_FORKNUM, xlrec->blkno);

            /* Also tell xlogutils.c about it */
            XLogTruncateRelation(xlrec->rnode, MAIN_FORKNUM, xlrec->blkno);
        }

        /* Truncate FSM and VM too */
        rel = CreateFakeRelcacheEntry(xlrec->rnode);

        if ((xlrec->flags & SMGR_TRUNCATE_FSM) != 0 &&
            smgrexists(reln, FSM_FORKNUM))
            FreeSpaceMapTruncateRel(rel, xlrec->blkno);
        if ((xlrec->flags & SMGR_TRUNCATE_VM) != 0 &&
            smgrexists(reln, VISIBILITYMAP_FORKNUM))
            visibilitymap_truncate(rel, xlrec->blkno);

        FreeFakeRelcacheEntry(rel);
    }
    else
        elog(PANIC, "smgr_redo: unknown op code %u", info);
}

smgrDoPendingDeletes()

void smgrDoPendingDeletes

(

bool

isCommit

)

Definition at line 399 of file storage.c.

References PendingRelDelete::atCommit, PendingRelDelete::backend, GetCurrentTransactionNestLevel(), i, PendingRelDelete::nestLevel, PendingRelDelete::next, palloc(), pfree(), PendingRelDelete::relnode, repalloc(), smgrclose(), smgrdounlinkall(), and smgropen().

Referenced by AbortTransaction(), AtSubAbort_smgr(), and CommitTransaction().

{
    int         nestLevel = GetCurrentTransactionNestLevel();
    PendingRelDelete *pending;
    PendingRelDelete *prev;
    PendingRelDelete *next;
    int         nrels = 0,
                i = 0,
                maxrels = 0;
    SMgrRelation *srels = NULL;

    prev = NULL;
    for (pending = pendingDeletes; pending != NULL; pending = next)
    {
        next = pending->next;
        if (pending->nestLevel < nestLevel)
        {
            /* outer-level entries should not be processed yet */
            prev = pending;
        }
        else
        {
            /* unlink list entry first, so we don't retry on failure */
            if (prev)
                prev->next = next;
            else
                pendingDeletes = next;
            /* do deletion if called for */
            if (pending->atCommit == isCommit)
            {
                SMgrRelation srel;

                srel = smgropen(pending->relnode, pending->backend);

                /* allocate the initial array, or extend it, if needed */
                if (maxrels == 0)
                {
                    maxrels = 8;
                    srels = palloc(sizeof(SMgrRelation) * maxrels);
                }
                else if (maxrels <= nrels)
                {
                    maxrels *= 2;
                    srels = repalloc(srels, sizeof(SMgrRelation) * maxrels);
                }

                srels[nrels++] = srel;
            }
            /* must explicitly free the list entry */
            pfree(pending);
            /* prev does not change */
        }
    }

    if (nrels > 0)
    {
        smgrdounlinkall(srels, nrels, false);

        for (i = 0; i < nrels; i++)
            smgrclose(srels[i]);

        pfree(srels);
    }
}

smgrGetPendingDeletes()

int smgrGetPendingDeletes	(	bool	forCommit,
		RelFileNode **	ptr
	)

Definition at line 482 of file storage.c.

References PendingRelDelete::atCommit, PendingRelDelete::backend, GetCurrentTransactionNestLevel(), InvalidBackendId, PendingRelDelete::nestLevel, PendingRelDelete::next, palloc(), and PendingRelDelete::relnode.

Referenced by RecordTransactionAbort(), RecordTransactionCommit(), and StartPrepare().

{
    int         nestLevel = GetCurrentTransactionNestLevel();
    int         nrels;
    RelFileNode *rptr;
    PendingRelDelete *pending;

    nrels = 0;
    for (pending = pendingDeletes; pending != NULL; pending = pending->next)
    {
        if (pending->nestLevel >= nestLevel && pending->atCommit == forCommit
            && pending->backend == InvalidBackendId)
            nrels++;
    }
    if (nrels == 0)
    {
        *ptr = NULL;
        return 0;
    }
    rptr = (RelFileNode *) palloc(nrels * sizeof(RelFileNode));
    *ptr = rptr;
    for (pending = pendingDeletes; pending != NULL; pending = pending->next)
    {
        if (pending->nestLevel >= nestLevel && pending->atCommit == forCommit
            && pending->backend == InvalidBackendId)
        {
            *rptr = pending->relnode;
            rptr++;
        }
    }
    return nrels;
}

Variable Documentation

pendingDeletes

PendingRelDelete* pendingDeletes = NULL

static

Definition at line 65 of file storage.c.

Referenced by RelationCreateStorage(), and RelationDropStorage().