smgr.h File Reference

#include "fmgr.h"
#include "storage/block.h"
#include "storage/relfilenode.h"

Include dependency graph for smgr.h:

This graph shows which files directly or indirectly include this file:

Go to the source code of this file.

Data Structures
struct	SMgrRelationData

Macros
#define	SmgrIsTemp(smgr)   RelFileNodeBackendIsTemp((smgr)->smgr_rnode)

Typedefs
typedef struct SMgrRelationData	SMgrRelationData
typedef SMgrRelationData *	SMgrRelation

Functions
void	smgrinit (void)
SMgrRelation	smgropen (RelFileNode rnode, BackendId backend)
bool	smgrexists (SMgrRelation reln, ForkNumber forknum)
void	smgrsetowner (SMgrRelation *owner, SMgrRelation reln)
void	smgrclearowner (SMgrRelation *owner, SMgrRelation reln)
void	smgrclose (SMgrRelation reln)
void	smgrcloseall (void)
void	smgrclosenode (RelFileNodeBackend rnode)
void	smgrcreate (SMgrRelation reln, ForkNumber forknum, bool isRedo)
void	smgrdounlink (SMgrRelation reln, bool isRedo)
void	smgrdounlinkall (SMgrRelation *rels, int nrels, bool isRedo)
void	smgrdounlinkfork (SMgrRelation reln, ForkNumber forknum, bool isRedo)
void	smgrextend (SMgrRelation reln, ForkNumber forknum, BlockNumber blocknum, char *buffer, bool skipFsync)
void	smgrprefetch (SMgrRelation reln, ForkNumber forknum, BlockNumber blocknum)
void	smgrread (SMgrRelation reln, ForkNumber forknum, BlockNumber blocknum, char *buffer)
void	smgrwrite (SMgrRelation reln, ForkNumber forknum, BlockNumber blocknum, char *buffer, bool skipFsync)
void	smgrwriteback (SMgrRelation reln, ForkNumber forknum, BlockNumber blocknum, BlockNumber nblocks)
BlockNumber	smgrnblocks (SMgrRelation reln, ForkNumber forknum)
void	smgrtruncate (SMgrRelation reln, ForkNumber forknum, BlockNumber nblocks)
void	smgrimmedsync (SMgrRelation reln, ForkNumber forknum)
void	smgrpreckpt (void)
void	smgrsync (void)
void	smgrpostckpt (void)
void	AtEOXact_SMgr (void)
void	mdinit (void)
void	mdclose (SMgrRelation reln, ForkNumber forknum)
void	mdcreate (SMgrRelation reln, ForkNumber forknum, bool isRedo)
bool	mdexists (SMgrRelation reln, ForkNumber forknum)
void	mdunlink (RelFileNodeBackend rnode, ForkNumber forknum, bool isRedo)
void	mdextend (SMgrRelation reln, ForkNumber forknum, BlockNumber blocknum, char *buffer, bool skipFsync)
void	mdprefetch (SMgrRelation reln, ForkNumber forknum, BlockNumber blocknum)
void	mdread (SMgrRelation reln, ForkNumber forknum, BlockNumber blocknum, char *buffer)
void	mdwrite (SMgrRelation reln, ForkNumber forknum, BlockNumber blocknum, char *buffer, bool skipFsync)
void	mdwriteback (SMgrRelation reln, ForkNumber forknum, BlockNumber blocknum, BlockNumber nblocks)
BlockNumber	mdnblocks (SMgrRelation reln, ForkNumber forknum)
void	mdtruncate (SMgrRelation reln, ForkNumber forknum, BlockNumber nblocks)
void	mdimmedsync (SMgrRelation reln, ForkNumber forknum)
void	mdpreckpt (void)
void	mdsync (void)
void	mdpostckpt (void)
void	SetForwardFsyncRequests (void)
void	RememberFsyncRequest (RelFileNode rnode, ForkNumber forknum, BlockNumber segno)
void	ForgetRelationFsyncRequests (RelFileNode rnode, ForkNumber forknum)
void	ForgetDatabaseFsyncRequests (Oid dbid)

Macro Definition Documentation

#define SmgrIsTemp

(

smgr

)

RelFileNodeBackendIsTemp((smgr)->smgr_rnode)

Definition at line 80 of file smgr.h.

Referenced by mdextend(), mdtruncate(), mdwrite(), ReadBuffer_common(), and register_dirty_segment().

Typedef Documentation

typedef SMgrRelationData* SMgrRelation

Definition at line 78 of file smgr.h.

typedef struct SMgrRelationData SMgrRelationData

Function Documentation

void AtEOXact_SMgr

(

void

)

Definition at line 798 of file smgr.c.

References Assert, SMgrRelationData::smgr_owner, and smgrclose().

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

{
    /*
     * Zap all unowned SMgrRelations.  We rely on smgrclose() to remove each
     * one from the list.
     */
    while (first_unowned_reln != NULL)
    {
        Assert(first_unowned_reln->smgr_owner == NULL);
        smgrclose(first_unowned_reln);
    }
}

void ForgetDatabaseFsyncRequests

(

Oid

dbid

)

Definition at line 1685 of file md.c.

References RelFileNode::dbNode, FORGET_DATABASE_FSYNC, ForwardFsyncRequest(), InvalidForkNumber, IsUnderPostmaster, pg_usleep(), RelFileNode::relNode, RememberFsyncRequest(), and RelFileNode::spcNode.

Referenced by dbase_redo(), and dropdb().

{
    RelFileNode rnode;

    rnode.dbNode = dbid;
    rnode.spcNode = 0;
    rnode.relNode = 0;

    if (pendingOpsTable)
    {
        /* standalone backend or startup process: fsync state is local */
        RememberFsyncRequest(rnode, InvalidForkNumber, FORGET_DATABASE_FSYNC);
    }
    else if (IsUnderPostmaster)
    {
        /* see notes in ForgetRelationFsyncRequests */
        while (!ForwardFsyncRequest(rnode, InvalidForkNumber,
                                    FORGET_DATABASE_FSYNC))
            pg_usleep(10000L);  /* 10 msec seems a good number */
    }
}

void ForgetRelationFsyncRequests	(	RelFileNode	rnode,
		ForkNumber	forknum
	)

Definition at line 1652 of file md.c.

References FORGET_RELATION_FSYNC, ForwardFsyncRequest(), IsUnderPostmaster, pg_usleep(), and RememberFsyncRequest().

Referenced by mdunlink().

{
    if (pendingOpsTable)
    {
        /* standalone backend or startup process: fsync state is local */
        RememberFsyncRequest(rnode, forknum, FORGET_RELATION_FSYNC);
    }
    else if (IsUnderPostmaster)
    {
        /*
         * Notify the checkpointer about it.  If we fail to queue the cancel
         * message, we have to sleep and try again ... ugly, but hopefully
         * won't happen often.
         *
         * XXX should we CHECK_FOR_INTERRUPTS in this loop?  Escaping with an
         * error would leave the no-longer-used file still present on disk,
         * which would be bad, so I'm inclined to assume that the checkpointer
         * will always empty the queue soon.
         */
        while (!ForwardFsyncRequest(rnode, forknum, FORGET_RELATION_FSYNC))
            pg_usleep(10000L);  /* 10 msec seems a good number */

        /*
         * Note we don't wait for the checkpointer to actually absorb the
         * cancel message; see mdsync() for the implications.
         */
    }
}

void mdclose	(	SMgrRelation	reln,
		ForkNumber	forknum
	)

Definition at line 628 of file md.c.

References _fdvec_resize(), FileClose(), SMgrRelationData::md_num_open_segs, SMgrRelationData::md_seg_fds, and _MdfdVec::mdfd_vfd.

Referenced by mdexists().

{
    int         nopensegs = reln->md_num_open_segs[forknum];

    /* No work if already closed */
    if (nopensegs == 0)
        return;

    /* close segments starting from the end */
    while (nopensegs > 0)
    {
        MdfdVec    *v = &reln->md_seg_fds[forknum][nopensegs - 1];

        /* if not closed already */
        if (v->mdfd_vfd >= 0)
        {
            FileClose(v->mdfd_vfd);
            v->mdfd_vfd = -1;
        }

        nopensegs--;
    }

    /* resize just once, avoids pointless reallocations */
    _fdvec_resize(reln, forknum, 0);
}

void mdcreate	(	SMgrRelation	reln,
		ForkNumber	forknum,
		bool	isRedo
	)

Definition at line 294 of file md.c.

References _fdvec_resize(), Assert, ereport, errcode_for_file_access(), errmsg(), ERROR, fd(), IsBootstrapProcessingMode, SMgrRelationData::md_num_open_segs, SMgrRelationData::md_seg_fds, _MdfdVec::mdfd_segno, _MdfdVec::mdfd_vfd, PathNameOpenFile(), pfree(), PG_BINARY, relpath, and SMgrRelationData::smgr_rnode.

{
    MdfdVec    *mdfd;
    char       *path;
    File        fd;

    if (isRedo && reln->md_num_open_segs[forkNum] > 0)
        return;                 /* created and opened already... */

    Assert(reln->md_num_open_segs[forkNum] == 0);

    path = relpath(reln->smgr_rnode, forkNum);

    fd = PathNameOpenFile(path, O_RDWR | O_CREAT | O_EXCL | PG_BINARY, 0600);

    if (fd < 0)
    {
        int         save_errno = errno;

        /*
         * During bootstrap, there are cases where a system relation will be
         * accessed (by internal backend processes) before the bootstrap
         * script nominally creates it.  Therefore, allow the file to exist
         * already, even if isRedo is not set.  (See also mdopen)
         */
        if (isRedo || IsBootstrapProcessingMode())
            fd = PathNameOpenFile(path, O_RDWR | PG_BINARY, 0600);
        if (fd < 0)
        {
            /* be sure to report the error reported by create, not open */
            errno = save_errno;
            ereport(ERROR,
                    (errcode_for_file_access(),
                     errmsg("could not create file \"%s\": %m", path)));
        }
    }

    pfree(path);

    _fdvec_resize(reln, forkNum, 1);
    mdfd = &reln->md_seg_fds[forkNum][0];
    mdfd->mdfd_vfd = fd;
    mdfd->mdfd_segno = 0;
}

bool mdexists	(	SMgrRelation	reln,
		ForkNumber	forknum
	)

Definition at line 277 of file md.c.

References EXTENSION_RETURN_NULL, mdclose(), and mdopen().

{
    /*
     * Close it first, to ensure that we notice if the fork has been unlinked
     * since we opened it.
     */
    mdclose(reln, forkNum);

    return (mdopen(reln, forkNum, EXTENSION_RETURN_NULL) != NULL);
}

void mdextend	(	SMgrRelation	reln,
		ForkNumber	forknum,
		BlockNumber	blocknum,
		char *	buffer,
		bool	skipFsync
	)

Definition at line 495 of file md.c.

References _mdfd_getseg(), _mdnblocks(), Assert, ereport, errcode(), errcode_for_file_access(), errhint(), errmsg(), ERROR, EXTENSION_CREATE, FilePathName(), FileSeek(), FileWrite(), InvalidBlockNumber, _MdfdVec::mdfd_vfd, mdnblocks(), register_dirty_segment(), relpath, SMgrRelationData::smgr_rnode, SmgrIsTemp, and WAIT_EVENT_DATA_FILE_EXTEND.

Referenced by _mdfd_getseg().

{
    off_t       seekpos;
    int         nbytes;
    MdfdVec    *v;

    /* This assert is too expensive to have on normally ... */
#ifdef CHECK_WRITE_VS_EXTEND
    Assert(blocknum >= mdnblocks(reln, forknum));
#endif

    /*
     * If a relation manages to grow to 2^32-1 blocks, refuse to extend it any
     * more --- we mustn't create a block whose number actually is
     * InvalidBlockNumber.
     */
    if (blocknum == InvalidBlockNumber)
        ereport(ERROR,
                (errcode(ERRCODE_PROGRAM_LIMIT_EXCEEDED),
                 errmsg("cannot extend file \"%s\" beyond %u blocks",
                        relpath(reln->smgr_rnode, forknum),
                        InvalidBlockNumber)));

    v = _mdfd_getseg(reln, forknum, blocknum, skipFsync, EXTENSION_CREATE);

    seekpos = (off_t) BLCKSZ * (blocknum % ((BlockNumber) RELSEG_SIZE));

    Assert(seekpos < (off_t) BLCKSZ * RELSEG_SIZE);

    /*
     * Note: because caller usually obtained blocknum by calling mdnblocks,
     * which did a seek(SEEK_END), this seek is often redundant and will be
     * optimized away by fd.c.  It's not redundant, however, if there is a
     * partial page at the end of the file. In that case we want to try to
     * overwrite the partial page with a full page.  It's also not redundant
     * if bufmgr.c had to dump another buffer of the same file to make room
     * for the new page's buffer.
     */
    if (FileSeek(v->mdfd_vfd, seekpos, SEEK_SET) != seekpos)
        ereport(ERROR,
                (errcode_for_file_access(),
                 errmsg("could not seek to block %u in file \"%s\": %m",
                        blocknum, FilePathName(v->mdfd_vfd))));

    if ((nbytes = FileWrite(v->mdfd_vfd, buffer, BLCKSZ, WAIT_EVENT_DATA_FILE_EXTEND)) != BLCKSZ)
    {
        if (nbytes < 0)
            ereport(ERROR,
                    (errcode_for_file_access(),
                     errmsg("could not extend file \"%s\": %m",
                            FilePathName(v->mdfd_vfd)),
                     errhint("Check free disk space.")));
        /* short write: complain appropriately */
        ereport(ERROR,
                (errcode(ERRCODE_DISK_FULL),
                 errmsg("could not extend file \"%s\": wrote only %d of %d bytes at block %u",
                        FilePathName(v->mdfd_vfd),
                        nbytes, BLCKSZ, blocknum),
                 errhint("Check free disk space.")));
    }

    if (!skipFsync && !SmgrIsTemp(reln))
        register_dirty_segment(reln, forknum, v);

    Assert(_mdnblocks(reln, forknum, v) <= ((BlockNumber) RELSEG_SIZE));
}

void mdimmedsync	(	SMgrRelation	reln,
		ForkNumber	forknum
	)

Definition at line 1025 of file md.c.

References ereport, errcode_for_file_access(), errmsg(), ERROR, FilePathName(), FileSync(), SMgrRelationData::md_num_open_segs, SMgrRelationData::md_seg_fds, _MdfdVec::mdfd_vfd, mdnblocks(), and WAIT_EVENT_DATA_FILE_IMMEDIATE_SYNC.

{
    int         segno;

    /*
     * NOTE: mdnblocks makes sure we have opened all active segments, so that
     * fsync loop will get them all!
     */
    mdnblocks(reln, forknum);

    segno = reln->md_num_open_segs[forknum];

    while (segno > 0)
    {
        MdfdVec    *v = &reln->md_seg_fds[forknum][segno - 1];

        if (FileSync(v->mdfd_vfd, WAIT_EVENT_DATA_FILE_IMMEDIATE_SYNC) < 0)
            ereport(ERROR,
                    (errcode_for_file_access(),
                     errmsg("could not fsync file \"%s\": %m",
                            FilePathName(v->mdfd_vfd))));
        segno--;
    }
}

void mdinit

(

void

)

Definition at line 206 of file md.c.

References ALLOCSET_DEFAULT_SIZES, AllocSetContextCreate(), AmCheckpointerProcess, AmStartupProcess, HASHCTL::entrysize, HASH_BLOBS, HASH_CONTEXT, hash_create(), HASH_ELEM, HASHCTL::hcxt, IsUnderPostmaster, HASHCTL::keysize, MemoryContextAllowInCriticalSection(), MemSet, NIL, pendingOpsCxt, and TopMemoryContext.

{
    MdCxt = AllocSetContextCreate(TopMemoryContext,
                                  "MdSmgr",
                                  ALLOCSET_DEFAULT_SIZES);

    /*
     * Create pending-operations hashtable if we need it.  Currently, we need
     * it if we are standalone (not under a postmaster) or if we are a startup
     * or checkpointer auxiliary process.
     */
    if (!IsUnderPostmaster || AmStartupProcess() || AmCheckpointerProcess())
    {
        HASHCTL     hash_ctl;

        /*
         * XXX: The checkpointer needs to add entries to the pending ops table
         * when absorbing fsync requests.  That is done within a critical
         * section, which isn't usually allowed, but we make an exception. It
         * means that there's a theoretical possibility that you run out of
         * memory while absorbing fsync requests, which leads to a PANIC.
         * Fortunately the hash table is small so that's unlikely to happen in
         * practice.
         */
        pendingOpsCxt = AllocSetContextCreate(MdCxt,
                                              "Pending ops context",
                                              ALLOCSET_DEFAULT_SIZES);
        MemoryContextAllowInCriticalSection(pendingOpsCxt, true);

        MemSet(&hash_ctl, 0, sizeof(hash_ctl));
        hash_ctl.keysize = sizeof(RelFileNode);
        hash_ctl.entrysize = sizeof(PendingOperationEntry);
        hash_ctl.hcxt = pendingOpsCxt;
        pendingOpsTable = hash_create("Pending Ops Table",
                                      100L,
                                      &hash_ctl,
                                      HASH_ELEM | HASH_BLOBS | HASH_CONTEXT);
        pendingUnlinks = NIL;
    }
}

BlockNumber mdnblocks	(	SMgrRelation	reln,
		ForkNumber	forknum
	)

Definition at line 873 of file md.c.

References _mdfd_openseg(), _mdnblocks(), Assert, elog, EXTENSION_FAIL, FATAL, SMgrRelationData::md_num_open_segs, SMgrRelationData::md_seg_fds, and mdopen().

Referenced by mdextend(), mdimmedsync(), mdtruncate(), and mdwrite().

{
    MdfdVec    *v = mdopen(reln, forknum, EXTENSION_FAIL);
    BlockNumber nblocks;
    BlockNumber segno = 0;

    /* mdopen has opened the first segment */
    Assert(reln->md_num_open_segs[forknum] > 0);

    /*
     * Start from the last open segments, to avoid redundant seeks.  We have
     * previously verified that these segments are exactly RELSEG_SIZE long,
     * and it's useless to recheck that each time.
     *
     * NOTE: this assumption could only be wrong if another backend has
     * truncated the relation.  We rely on higher code levels to handle that
     * scenario by closing and re-opening the md fd, which is handled via
     * relcache flush.  (Since the checkpointer doesn't participate in
     * relcache flush, it could have segment entries for inactive segments;
     * that's OK because the checkpointer never needs to compute relation
     * size.)
     */
    segno = reln->md_num_open_segs[forknum] - 1;
    v = &reln->md_seg_fds[forknum][segno];

    for (;;)
    {
        nblocks = _mdnblocks(reln, forknum, v);
        if (nblocks > ((BlockNumber) RELSEG_SIZE))
            elog(FATAL, "segment too big");
        if (nblocks < ((BlockNumber) RELSEG_SIZE))
            return (segno * ((BlockNumber) RELSEG_SIZE)) + nblocks;

        /*
         * If segment is exactly RELSEG_SIZE, advance to next one.
         */
        segno++;

        /*
         * We used to pass O_CREAT here, but that's has the disadvantage that
         * it might create a segment which has vanished through some operating
         * system misadventure.  In such a case, creating the segment here
         * undermines _mdfd_getseg's attempts to notice and report an error
         * upon access to a missing segment.
         */
        v = _mdfd_openseg(reln, forknum, segno, 0);
        if (v == NULL)
            return segno * ((BlockNumber) RELSEG_SIZE);
    }
}

void mdpostckpt

(

void

)

Definition at line 1361 of file md.c.

References AbsorbFsyncRequests(), PendingUnlinkEntry::cycle_ctr, ereport, errcode_for_file_access(), errmsg(), linitial, list_delete_first(), MAIN_FORKNUM, mdckpt_cycle_ctr, NIL, pfree(), relpathperm, PendingUnlinkEntry::rnode, unlink(), UNLINKS_PER_ABSORB, and WARNING.

{
    int         absorb_counter;

    absorb_counter = UNLINKS_PER_ABSORB;
    while (pendingUnlinks != NIL)
    {
        PendingUnlinkEntry *entry = (PendingUnlinkEntry *) linitial(pendingUnlinks);
        char       *path;

        /*
         * New entries are appended to the end, so if the entry is new we've
         * reached the end of old entries.
         *
         * Note: if just the right number of consecutive checkpoints fail, we
         * could be fooled here by cycle_ctr wraparound.  However, the only
         * consequence is that we'd delay unlinking for one more checkpoint,
         * which is perfectly tolerable.
         */
        if (entry->cycle_ctr == mdckpt_cycle_ctr)
            break;

        /* Unlink the file */
        path = relpathperm(entry->rnode, MAIN_FORKNUM);
        if (unlink(path) < 0)
        {
            /*
             * There's a race condition, when the database is dropped at the
             * same time that we process the pending unlink requests. If the
             * DROP DATABASE deletes the file before we do, we will get ENOENT
             * here. rmtree() also has to ignore ENOENT errors, to deal with
             * the possibility that we delete the file first.
             */
            if (errno != ENOENT)
                ereport(WARNING,
                        (errcode_for_file_access(),
                         errmsg("could not remove file \"%s\": %m", path)));
        }
        pfree(path);

        /* And remove the list entry */
        pendingUnlinks = list_delete_first(pendingUnlinks);
        pfree(entry);

        /*
         * As in mdsync, we don't want to stop absorbing fsync requests for a
         * long time when there are many deletions to be done.  We can safely
         * call AbsorbFsyncRequests() at this point in the loop (note it might
         * try to delete list entries).
         */
        if (--absorb_counter <= 0)
        {
            AbsorbFsyncRequests();
            absorb_counter = UNLINKS_PER_ABSORB;
        }
    }
}

void mdpreckpt

(

void

)

Definition at line 1346 of file md.c.

References mdckpt_cycle_ctr.

{
    /*
     * Any unlink requests arriving after this point will be assigned the next
     * cycle counter, and won't be unlinked until next checkpoint.
     */
    mdckpt_cycle_ctr++;
}

void mdprefetch	(	SMgrRelation	reln,
		ForkNumber	forknum,
		BlockNumber	blocknum
	)

Definition at line 659 of file md.c.

References _mdfd_getseg(), Assert, EXTENSION_FAIL, FilePrefetch(), _MdfdVec::mdfd_vfd, and WAIT_EVENT_DATA_FILE_PREFETCH.

{
#ifdef USE_PREFETCH
    off_t       seekpos;
    MdfdVec    *v;

    v = _mdfd_getseg(reln, forknum, blocknum, false, EXTENSION_FAIL);

    seekpos = (off_t) BLCKSZ * (blocknum % ((BlockNumber) RELSEG_SIZE));

    Assert(seekpos < (off_t) BLCKSZ * RELSEG_SIZE);

    (void) FilePrefetch(v->mdfd_vfd, seekpos, BLCKSZ, WAIT_EVENT_DATA_FILE_PREFETCH);
#endif                          /* USE_PREFETCH */
}

void mdread	(	SMgrRelation	reln,
		ForkNumber	forknum,
		BlockNumber	blocknum,
		char *	buffer
	)

Definition at line 731 of file md.c.

References _mdfd_getseg(), Assert, RelFileNodeBackend::backend, RelFileNode::dbNode, ereport, errcode(), errcode_for_file_access(), errmsg(), ERROR, EXTENSION_CREATE_RECOVERY, EXTENSION_FAIL, FilePathName(), FileRead(), FileSeek(), InRecovery, _MdfdVec::mdfd_vfd, MemSet, RelFileNodeBackend::node, RelFileNode::relNode, SMgrRelationData::smgr_rnode, RelFileNode::spcNode, WAIT_EVENT_DATA_FILE_READ, and zero_damaged_pages.

{
    off_t       seekpos;
    int         nbytes;
    MdfdVec    *v;

    TRACE_POSTGRESQL_SMGR_MD_READ_START(forknum, blocknum,
                                        reln->smgr_rnode.node.spcNode,
                                        reln->smgr_rnode.node.dbNode,
                                        reln->smgr_rnode.node.relNode,
                                        reln->smgr_rnode.backend);

    v = _mdfd_getseg(reln, forknum, blocknum, false,
                     EXTENSION_FAIL | EXTENSION_CREATE_RECOVERY);

    seekpos = (off_t) BLCKSZ * (blocknum % ((BlockNumber) RELSEG_SIZE));

    Assert(seekpos < (off_t) BLCKSZ * RELSEG_SIZE);

    if (FileSeek(v->mdfd_vfd, seekpos, SEEK_SET) != seekpos)
        ereport(ERROR,
                (errcode_for_file_access(),
                 errmsg("could not seek to block %u in file \"%s\": %m",
                        blocknum, FilePathName(v->mdfd_vfd))));

    nbytes = FileRead(v->mdfd_vfd, buffer, BLCKSZ, WAIT_EVENT_DATA_FILE_READ);

    TRACE_POSTGRESQL_SMGR_MD_READ_DONE(forknum, blocknum,
                                       reln->smgr_rnode.node.spcNode,
                                       reln->smgr_rnode.node.dbNode,
                                       reln->smgr_rnode.node.relNode,
                                       reln->smgr_rnode.backend,
                                       nbytes,
                                       BLCKSZ);

    if (nbytes != BLCKSZ)
    {
        if (nbytes < 0)
            ereport(ERROR,
                    (errcode_for_file_access(),
                     errmsg("could not read block %u in file \"%s\": %m",
                            blocknum, FilePathName(v->mdfd_vfd))));

        /*
         * Short read: we are at or past EOF, or we read a partial block at
         * EOF.  Normally this is an error; upper levels should never try to
         * read a nonexistent block.  However, if zero_damaged_pages is ON or
         * we are InRecovery, we should instead return zeroes without
         * complaining.  This allows, for example, the case of trying to
         * update a block that was later truncated away.
         */
        if (zero_damaged_pages || InRecovery)
            MemSet(buffer, 0, BLCKSZ);
        else
            ereport(ERROR,
                    (errcode(ERRCODE_DATA_CORRUPTED),
                     errmsg("could not read block %u in file \"%s\": read only %d of %d bytes",
                            blocknum, FilePathName(v->mdfd_vfd),
                            nbytes, BLCKSZ)));
    }
}

void mdsync

(

void

)

Definition at line 1054 of file md.c.

References _mdfd_getseg(), _mdfd_segpath(), AbsorbFsyncRequests(), Assert, bms_first_member(), bms_free(), PendingOperationEntry::canceled, CheckpointStats, CheckpointStatsData::ckpt_agg_sync_time, CheckpointStatsData::ckpt_longest_sync, CheckpointStatsData::ckpt_sync_rels, PendingOperationEntry::cycle_ctr, DEBUG1, elog, enableFsync, ereport, errcode_for_file_access(), errmsg(), ERROR, EXTENSION_DONT_CHECK_SIZE, EXTENSION_RETURN_NULL, FILE_POSSIBLY_DELETED, FilePathName(), FileSync(), FSYNCS_PER_ABSORB, HASH_REMOVE, hash_search(), hash_seq_init(), hash_seq_search(), INSTR_TIME_GET_MICROSEC, INSTR_TIME_SET_CURRENT, INSTR_TIME_SUBTRACT, InvalidBackendId, log_checkpoints, longest(), MAX_FORKNUM, _MdfdVec::mdfd_vfd, mdsync_cycle_ctr, pfree(), PendingOperationEntry::requests, PendingOperationEntry::rnode, smgropen(), and WAIT_EVENT_DATA_FILE_SYNC.

Referenced by SetForwardFsyncRequests().

{
    static bool mdsync_in_progress = false;

    HASH_SEQ_STATUS hstat;
    PendingOperationEntry *entry;
    int         absorb_counter;

    /* Statistics on sync times */
    int         processed = 0;
    instr_time  sync_start,
                sync_end,
                sync_diff;
    uint64      elapsed;
    uint64      longest = 0;
    uint64      total_elapsed = 0;

    /*
     * This is only called during checkpoints, and checkpoints should only
     * occur in processes that have created a pendingOpsTable.
     */
    if (!pendingOpsTable)
        elog(ERROR, "cannot sync without a pendingOpsTable");

    /*
     * If we are in the checkpointer, the sync had better include all fsync
     * requests that were queued by backends up to this point.  The tightest
     * race condition that could occur is that a buffer that must be written
     * and fsync'd for the checkpoint could have been dumped by a backend just
     * before it was visited by BufferSync().  We know the backend will have
     * queued an fsync request before clearing the buffer's dirtybit, so we
     * are safe as long as we do an Absorb after completing BufferSync().
     */
    AbsorbFsyncRequests();

    /*
     * To avoid excess fsync'ing (in the worst case, maybe a never-terminating
     * checkpoint), we want to ignore fsync requests that are entered into the
     * hashtable after this point --- they should be processed next time,
     * instead.  We use mdsync_cycle_ctr to tell old entries apart from new
     * ones: new ones will have cycle_ctr equal to the incremented value of
     * mdsync_cycle_ctr.
     *
     * In normal circumstances, all entries present in the table at this point
     * will have cycle_ctr exactly equal to the current (about to be old)
     * value of mdsync_cycle_ctr.  However, if we fail partway through the
     * fsync'ing loop, then older values of cycle_ctr might remain when we
     * come back here to try again.  Repeated checkpoint failures would
     * eventually wrap the counter around to the point where an old entry
     * might appear new, causing us to skip it, possibly allowing a checkpoint
     * to succeed that should not have.  To forestall wraparound, any time the
     * previous mdsync() failed to complete, run through the table and
     * forcibly set cycle_ctr = mdsync_cycle_ctr.
     *
     * Think not to merge this loop with the main loop, as the problem is
     * exactly that that loop may fail before having visited all the entries.
     * From a performance point of view it doesn't matter anyway, as this path
     * will never be taken in a system that's functioning normally.
     */
    if (mdsync_in_progress)
    {
        /* prior try failed, so update any stale cycle_ctr values */
        hash_seq_init(&hstat, pendingOpsTable);
        while ((entry = (PendingOperationEntry *) hash_seq_search(&hstat)) != NULL)
        {
            entry->cycle_ctr = mdsync_cycle_ctr;
        }
    }

    /* Advance counter so that new hashtable entries are distinguishable */
    mdsync_cycle_ctr++;

    /* Set flag to detect failure if we don't reach the end of the loop */
    mdsync_in_progress = true;

    /* Now scan the hashtable for fsync requests to process */
    absorb_counter = FSYNCS_PER_ABSORB;
    hash_seq_init(&hstat, pendingOpsTable);
    while ((entry = (PendingOperationEntry *) hash_seq_search(&hstat)) != NULL)
    {
        ForkNumber  forknum;

        /*
         * If the entry is new then don't process it this time; it might
         * contain multiple fsync-request bits, but they are all new.  Note
         * "continue" bypasses the hash-remove call at the bottom of the loop.
         */
        if (entry->cycle_ctr == mdsync_cycle_ctr)
            continue;

        /* Else assert we haven't missed it */
        Assert((CycleCtr) (entry->cycle_ctr + 1) == mdsync_cycle_ctr);

        /*
         * Scan over the forks and segments represented by the entry.
         *
         * The bitmap manipulations are slightly tricky, because we can call
         * AbsorbFsyncRequests() inside the loop and that could result in
         * bms_add_member() modifying and even re-palloc'ing the bitmapsets.
         * This is okay because we unlink each bitmapset from the hashtable
         * entry before scanning it.  That means that any incoming fsync
         * requests will be processed now if they reach the table before we
         * begin to scan their fork.
         */
        for (forknum = 0; forknum <= MAX_FORKNUM; forknum++)
        {
            Bitmapset  *requests = entry->requests[forknum];
            int         segno;

            entry->requests[forknum] = NULL;
            entry->canceled[forknum] = false;

            while ((segno = bms_first_member(requests)) >= 0)
            {
                int         failures;

                /*
                 * If fsync is off then we don't have to bother opening the
                 * file at all.  (We delay checking until this point so that
                 * changing fsync on the fly behaves sensibly.)
                 */
                if (!enableFsync)
                    continue;

                /*
                 * If in checkpointer, we want to absorb pending requests
                 * every so often to prevent overflow of the fsync request
                 * queue.  It is unspecified whether newly-added entries will
                 * be visited by hash_seq_search, but we don't care since we
                 * don't need to process them anyway.
                 */
                if (--absorb_counter <= 0)
                {
                    AbsorbFsyncRequests();
                    absorb_counter = FSYNCS_PER_ABSORB;
                }

                /*
                 * The fsync table could contain requests to fsync segments
                 * that have been deleted (unlinked) by the time we get to
                 * them. Rather than just hoping an ENOENT (or EACCES on
                 * Windows) error can be ignored, what we do on error is
                 * absorb pending requests and then retry.  Since mdunlink()
                 * queues a "cancel" message before actually unlinking, the
                 * fsync request is guaranteed to be marked canceled after the
                 * absorb if it really was this case. DROP DATABASE likewise
                 * has to tell us to forget fsync requests before it starts
                 * deletions.
                 */
                for (failures = 0;; failures++) /* loop exits at "break" */
                {
                    SMgrRelation reln;
                    MdfdVec    *seg;
                    char       *path;
                    int         save_errno;

                    /*
                     * Find or create an smgr hash entry for this relation.
                     * This may seem a bit unclean -- md calling smgr?  But
                     * it's really the best solution.  It ensures that the
                     * open file reference isn't permanently leaked if we get
                     * an error here. (You may say "but an unreferenced
                     * SMgrRelation is still a leak!" Not really, because the
                     * only case in which a checkpoint is done by a process
                     * that isn't about to shut down is in the checkpointer,
                     * and it will periodically do smgrcloseall(). This fact
                     * justifies our not closing the reln in the success path
                     * either, which is a good thing since in non-checkpointer
                     * cases we couldn't safely do that.)
                     */
                    reln = smgropen(entry->rnode, InvalidBackendId);

                    /* Attempt to open and fsync the target segment */
                    seg = _mdfd_getseg(reln, forknum,
                                       (BlockNumber) segno * (BlockNumber) RELSEG_SIZE,
                                       false,
                                       EXTENSION_RETURN_NULL
                                       | EXTENSION_DONT_CHECK_SIZE);

                    INSTR_TIME_SET_CURRENT(sync_start);

                    if (seg != NULL &&
                        FileSync(seg->mdfd_vfd, WAIT_EVENT_DATA_FILE_SYNC) >= 0)
                    {
                        /* Success; update statistics about sync timing */
                        INSTR_TIME_SET_CURRENT(sync_end);
                        sync_diff = sync_end;
                        INSTR_TIME_SUBTRACT(sync_diff, sync_start);
                        elapsed = INSTR_TIME_GET_MICROSEC(sync_diff);
                        if (elapsed > longest)
                            longest = elapsed;
                        total_elapsed += elapsed;
                        processed++;
                        if (log_checkpoints)
                            elog(DEBUG1, "checkpoint sync: number=%d file=%s time=%.3f msec",
                                 processed,
                                 FilePathName(seg->mdfd_vfd),
                                 (double) elapsed / 1000);

                        break;  /* out of retry loop */
                    }

                    /* Compute file name for use in message */
                    save_errno = errno;
                    path = _mdfd_segpath(reln, forknum, (BlockNumber) segno);
                    errno = save_errno;

                    /*
                     * It is possible that the relation has been dropped or
                     * truncated since the fsync request was entered.
                     * Therefore, allow ENOENT, but only if we didn't fail
                     * already on this file.  This applies both for
                     * _mdfd_getseg() and for FileSync, since fd.c might have
                     * closed the file behind our back.
                     *
                     * XXX is there any point in allowing more than one retry?
                     * Don't see one at the moment, but easy to change the
                     * test here if so.
                     */
                    if (!FILE_POSSIBLY_DELETED(errno) ||
                        failures > 0)
                        ereport(ERROR,
                                (errcode_for_file_access(),
                                 errmsg("could not fsync file \"%s\": %m",
                                        path)));
                    else
                        ereport(DEBUG1,
                                (errcode_for_file_access(),
                                 errmsg("could not fsync file \"%s\" but retrying: %m",
                                        path)));
                    pfree(path);

                    /*
                     * Absorb incoming requests and check to see if a cancel
                     * arrived for this relation fork.
                     */
                    AbsorbFsyncRequests();
                    absorb_counter = FSYNCS_PER_ABSORB; /* might as well... */

                    if (entry->canceled[forknum])
                        break;
                }               /* end retry loop */
            }
            bms_free(requests);
        }

        /*
         * We've finished everything that was requested before we started to
         * scan the entry.  If no new requests have been inserted meanwhile,
         * remove the entry.  Otherwise, update its cycle counter, as all the
         * requests now in it must have arrived during this cycle.
         */
        for (forknum = 0; forknum <= MAX_FORKNUM; forknum++)
        {
            if (entry->requests[forknum] != NULL)
                break;
        }
        if (forknum <= MAX_FORKNUM)
            entry->cycle_ctr = mdsync_cycle_ctr;
        else
        {
            /* Okay to remove it */
            if (hash_search(pendingOpsTable, &entry->rnode,
                            HASH_REMOVE, NULL) == NULL)
                elog(ERROR, "pendingOpsTable corrupted");
        }
    }                           /* end loop over hashtable entries */

    /* Return sync performance metrics for report at checkpoint end */
    CheckpointStats.ckpt_sync_rels = processed;
    CheckpointStats.ckpt_longest_sync = longest;
    CheckpointStats.ckpt_agg_sync_time = total_elapsed;

    /* Flag successful completion of mdsync */
    mdsync_in_progress = false;
}

void mdtruncate	(	SMgrRelation	reln,
		ForkNumber	forknum,
		BlockNumber	nblocks
	)

Definition at line 928 of file md.c.

References _fdvec_resize(), Assert, ereport, errcode_for_file_access(), errmsg(), ERROR, FileClose(), FilePathName(), FileTruncate(), InRecovery, SMgrRelationData::md_num_open_segs, SMgrRelationData::md_seg_fds, _MdfdVec::mdfd_vfd, mdnblocks(), register_dirty_segment(), relpath, SMgrRelationData::smgr_rnode, SmgrIsTemp, and WAIT_EVENT_DATA_FILE_TRUNCATE.

{
    BlockNumber curnblk;
    BlockNumber priorblocks;
    int         curopensegs;

    /*
     * NOTE: mdnblocks makes sure we have opened all active segments, so that
     * truncation loop will get them all!
     */
    curnblk = mdnblocks(reln, forknum);
    if (nblocks > curnblk)
    {
        /* Bogus request ... but no complaint if InRecovery */
        if (InRecovery)
            return;
        ereport(ERROR,
                (errmsg("could not truncate file \"%s\" to %u blocks: it's only %u blocks now",
                        relpath(reln->smgr_rnode, forknum),
                        nblocks, curnblk)));
    }
    if (nblocks == curnblk)
        return;                 /* no work */

    /*
     * Truncate segments, starting at the last one. Starting at the end makes
     * managing the memory for the fd array easier, should there be errors.
     */
    curopensegs = reln->md_num_open_segs[forknum];
    while (curopensegs > 0)
    {
        MdfdVec    *v;

        priorblocks = (curopensegs - 1) * RELSEG_SIZE;

        v = &reln->md_seg_fds[forknum][curopensegs - 1];

        if (priorblocks > nblocks)
        {
            /*
             * This segment is no longer active. We truncate the file, but do
             * not delete it, for reasons explained in the header comments.
             */
            if (FileTruncate(v->mdfd_vfd, 0, WAIT_EVENT_DATA_FILE_TRUNCATE) < 0)
                ereport(ERROR,
                        (errcode_for_file_access(),
                         errmsg("could not truncate file \"%s\": %m",
                                FilePathName(v->mdfd_vfd))));

            if (!SmgrIsTemp(reln))
                register_dirty_segment(reln, forknum, v);

            /* we never drop the 1st segment */
            Assert(v != &reln->md_seg_fds[forknum][0]);

            FileClose(v->mdfd_vfd);
            _fdvec_resize(reln, forknum, curopensegs - 1);
        }
        else if (priorblocks + ((BlockNumber) RELSEG_SIZE) > nblocks)
        {
            /*
             * This is the last segment we want to keep. Truncate the file to
             * the right length. NOTE: if nblocks is exactly a multiple K of
             * RELSEG_SIZE, we will truncate the K+1st segment to 0 length but
             * keep it. This adheres to the invariant given in the header
             * comments.
             */
            BlockNumber lastsegblocks = nblocks - priorblocks;

            if (FileTruncate(v->mdfd_vfd, (off_t) lastsegblocks * BLCKSZ, WAIT_EVENT_DATA_FILE_TRUNCATE) < 0)
                ereport(ERROR,
                        (errcode_for_file_access(),
                         errmsg("could not truncate file \"%s\" to %u blocks: %m",
                                FilePathName(v->mdfd_vfd),
                                nblocks)));
            if (!SmgrIsTemp(reln))
                register_dirty_segment(reln, forknum, v);
        }
        else
        {
            /*
             * We still need this segment, so nothing to do for this and any
             * earlier segment.
             */
            break;
        }
        curopensegs--;
    }
}

void mdunlink	(	RelFileNodeBackend	rnode,
		ForkNumber	forknum,
		bool	isRedo
	)

Definition at line 387 of file md.c.

References ForgetRelationFsyncRequests(), InvalidForkNumber, MAX_FORKNUM, mdunlinkfork(), RelFileNodeBackend::node, and RelFileNodeBackendIsTemp.

{
    /*
     * We have to clean out any pending fsync requests for the doomed
     * relation, else the next mdsync() will fail.  There can't be any such
     * requests for a temp relation, though.  We can send just one request
     * even when deleting multiple forks, since the fsync queuing code accepts
     * the "InvalidForkNumber = all forks" convention.
     */
    if (!RelFileNodeBackendIsTemp(rnode))
        ForgetRelationFsyncRequests(rnode.node, forkNum);

    /* Now do the per-fork work */
    if (forkNum == InvalidForkNumber)
    {
        for (forkNum = 0; forkNum <= MAX_FORKNUM; forkNum++)
            mdunlinkfork(rnode, forkNum, isRedo);
    }
    else
        mdunlinkfork(rnode, forkNum, isRedo);
}

void mdwrite	(	SMgrRelation	reln,
		ForkNumber	forknum,
		BlockNumber	blocknum,
		char *	buffer,
		bool	skipFsync
	)

Definition at line 802 of file md.c.

References _mdfd_getseg(), Assert, RelFileNodeBackend::backend, RelFileNode::dbNode, ereport, errcode(), errcode_for_file_access(), errhint(), errmsg(), ERROR, EXTENSION_CREATE_RECOVERY, EXTENSION_FAIL, FilePathName(), FileSeek(), FileWrite(), _MdfdVec::mdfd_vfd, mdnblocks(), RelFileNodeBackend::node, register_dirty_segment(), RelFileNode::relNode, SMgrRelationData::smgr_rnode, SmgrIsTemp, RelFileNode::spcNode, and WAIT_EVENT_DATA_FILE_WRITE.

{
    off_t       seekpos;
    int         nbytes;
    MdfdVec    *v;

    /* This assert is too expensive to have on normally ... */
#ifdef CHECK_WRITE_VS_EXTEND
    Assert(blocknum < mdnblocks(reln, forknum));
#endif

    TRACE_POSTGRESQL_SMGR_MD_WRITE_START(forknum, blocknum,
                                         reln->smgr_rnode.node.spcNode,
                                         reln->smgr_rnode.node.dbNode,
                                         reln->smgr_rnode.node.relNode,
                                         reln->smgr_rnode.backend);

    v = _mdfd_getseg(reln, forknum, blocknum, skipFsync,
                     EXTENSION_FAIL | EXTENSION_CREATE_RECOVERY);

    seekpos = (off_t) BLCKSZ * (blocknum % ((BlockNumber) RELSEG_SIZE));

    Assert(seekpos < (off_t) BLCKSZ * RELSEG_SIZE);

    if (FileSeek(v->mdfd_vfd, seekpos, SEEK_SET) != seekpos)
        ereport(ERROR,
                (errcode_for_file_access(),
                 errmsg("could not seek to block %u in file \"%s\": %m",
                        blocknum, FilePathName(v->mdfd_vfd))));

    nbytes = FileWrite(v->mdfd_vfd, buffer, BLCKSZ, WAIT_EVENT_DATA_FILE_WRITE);

    TRACE_POSTGRESQL_SMGR_MD_WRITE_DONE(forknum, blocknum,
                                        reln->smgr_rnode.node.spcNode,
                                        reln->smgr_rnode.node.dbNode,
                                        reln->smgr_rnode.node.relNode,
                                        reln->smgr_rnode.backend,
                                        nbytes,
                                        BLCKSZ);

    if (nbytes != BLCKSZ)
    {
        if (nbytes < 0)
            ereport(ERROR,
                    (errcode_for_file_access(),
                     errmsg("could not write block %u in file \"%s\": %m",
                            blocknum, FilePathName(v->mdfd_vfd))));
        /* short write: complain appropriately */
        ereport(ERROR,
                (errcode(ERRCODE_DISK_FULL),
                 errmsg("could not write block %u in file \"%s\": wrote only %d of %d bytes",
                        blocknum,
                        FilePathName(v->mdfd_vfd),
                        nbytes, BLCKSZ),
                 errhint("Check free disk space.")));
    }

    if (!skipFsync && !SmgrIsTemp(reln))
        register_dirty_segment(reln, forknum, v);
}

void mdwriteback	(	SMgrRelation	reln,
		ForkNumber	forknum,
		BlockNumber	blocknum,
		BlockNumber	nblocks
	)

Definition at line 682 of file md.c.

References _mdfd_getseg(), Assert, EXTENSION_RETURN_NULL, FileWriteback(), _MdfdVec::mdfd_vfd, and WAIT_EVENT_DATA_FILE_FLUSH.

{
    /*
     * Issue flush requests in as few requests as possible; have to split at
     * segment boundaries though, since those are actually separate files.
     */
    while (nblocks > 0)
    {
        BlockNumber nflush = nblocks;
        off_t       seekpos;
        MdfdVec    *v;
        int         segnum_start,
                    segnum_end;

        v = _mdfd_getseg(reln, forknum, blocknum, true /* not used */ ,
                         EXTENSION_RETURN_NULL);

        /*
         * We might be flushing buffers of already removed relations, that's
         * ok, just ignore that case.
         */
        if (!v)
            return;

        /* compute offset inside the current segment */
        segnum_start = blocknum / RELSEG_SIZE;

        /* compute number of desired writes within the current segment */
        segnum_end = (blocknum + nblocks - 1) / RELSEG_SIZE;
        if (segnum_start != segnum_end)
            nflush = RELSEG_SIZE - (blocknum % ((BlockNumber) RELSEG_SIZE));

        Assert(nflush >= 1);
        Assert(nflush <= nblocks);

        seekpos = (off_t) BLCKSZ * (blocknum % ((BlockNumber) RELSEG_SIZE));

        FileWriteback(v->mdfd_vfd, seekpos, (off_t) BLCKSZ * nflush, WAIT_EVENT_DATA_FILE_FLUSH);

        nblocks -= nflush;
        blocknum += nflush;
    }
}

void RememberFsyncRequest	(	RelFileNode	rnode,
		ForkNumber	forknum,
		BlockNumber	segno
	)

Definition at line 1514 of file md.c.

References Assert, bms_add_member(), bms_free(), PendingOperationEntry::canceled, PendingOperationEntry::cycle_ctr, PendingUnlinkEntry::cycle_ctr, RelFileNode::dbNode, FORGET_DATABASE_FSYNC, FORGET_RELATION_FSYNC, HASH_ENTER, HASH_FIND, hash_search(), hash_seq_init(), hash_seq_search(), InvalidForkNumber, lappend(), lfirst, list_delete_cell(), list_head(), lnext, MAIN_FORKNUM, MAX_FORKNUM, mdckpt_cycle_ctr, mdsync_cycle_ctr, MemoryContextSwitchTo(), MemSet, next, palloc(), pfree(), PendingOperationEntry::requests, PendingOperationEntry::rnode, PendingUnlinkEntry::rnode, and UNLINK_RELATION_REQUEST.

Referenced by AbsorbFsyncRequests(), ForgetDatabaseFsyncRequests(), ForgetRelationFsyncRequests(), register_dirty_segment(), and register_unlink().

{
    Assert(pendingOpsTable);

    if (segno == FORGET_RELATION_FSYNC)
    {
        /* Remove any pending requests for the relation (one or all forks) */
        PendingOperationEntry *entry;

        entry = (PendingOperationEntry *) hash_search(pendingOpsTable,
                                                      &rnode,
                                                      HASH_FIND,
                                                      NULL);
        if (entry)
        {
            /*
             * We can't just delete the entry since mdsync could have an
             * active hashtable scan.  Instead we delete the bitmapsets; this
             * is safe because of the way mdsync is coded.  We also set the
             * "canceled" flags so that mdsync can tell that a cancel arrived
             * for the fork(s).
             */
            if (forknum == InvalidForkNumber)
            {
                /* remove requests for all forks */
                for (forknum = 0; forknum <= MAX_FORKNUM; forknum++)
                {
                    bms_free(entry->requests[forknum]);
                    entry->requests[forknum] = NULL;
                    entry->canceled[forknum] = true;
                }
            }
            else
            {
                /* remove requests for single fork */
                bms_free(entry->requests[forknum]);
                entry->requests[forknum] = NULL;
                entry->canceled[forknum] = true;
            }
        }
    }
    else if (segno == FORGET_DATABASE_FSYNC)
    {
        /* Remove any pending requests for the entire database */
        HASH_SEQ_STATUS hstat;
        PendingOperationEntry *entry;
        ListCell   *cell,
                   *prev,
                   *next;

        /* Remove fsync requests */
        hash_seq_init(&hstat, pendingOpsTable);
        while ((entry = (PendingOperationEntry *) hash_seq_search(&hstat)) != NULL)
        {
            if (entry->rnode.dbNode == rnode.dbNode)
            {
                /* remove requests for all forks */
                for (forknum = 0; forknum <= MAX_FORKNUM; forknum++)
                {
                    bms_free(entry->requests[forknum]);
                    entry->requests[forknum] = NULL;
                    entry->canceled[forknum] = true;
                }
            }
        }

        /* Remove unlink requests */
        prev = NULL;
        for (cell = list_head(pendingUnlinks); cell; cell = next)
        {
            PendingUnlinkEntry *entry = (PendingUnlinkEntry *) lfirst(cell);

            next = lnext(cell);
            if (entry->rnode.dbNode == rnode.dbNode)
            {
                pendingUnlinks = list_delete_cell(pendingUnlinks, cell, prev);
                pfree(entry);
            }
            else
                prev = cell;
        }
    }
    else if (segno == UNLINK_RELATION_REQUEST)
    {
        /* Unlink request: put it in the linked list */
        MemoryContext oldcxt = MemoryContextSwitchTo(pendingOpsCxt);
        PendingUnlinkEntry *entry;

        /* PendingUnlinkEntry doesn't store forknum, since it's always MAIN */
        Assert(forknum == MAIN_FORKNUM);

        entry = palloc(sizeof(PendingUnlinkEntry));
        entry->rnode = rnode;
        entry->cycle_ctr = mdckpt_cycle_ctr;

        pendingUnlinks = lappend(pendingUnlinks, entry);

        MemoryContextSwitchTo(oldcxt);
    }
    else
    {
        /* Normal case: enter a request to fsync this segment */
        MemoryContext oldcxt = MemoryContextSwitchTo(pendingOpsCxt);
        PendingOperationEntry *entry;
        bool        found;

        entry = (PendingOperationEntry *) hash_search(pendingOpsTable,
                                                      &rnode,
                                                      HASH_ENTER,
                                                      &found);
        /* if new entry, initialize it */
        if (!found)
        {
            entry->cycle_ctr = mdsync_cycle_ctr;
            MemSet(entry->requests, 0, sizeof(entry->requests));
            MemSet(entry->canceled, 0, sizeof(entry->canceled));
        }

        /*
         * NB: it's intentional that we don't change cycle_ctr if the entry
         * already exists.  The cycle_ctr must represent the oldest fsync
         * request that could be in the entry.
         */

        entry->requests[forknum] = bms_add_member(entry->requests[forknum],
                                                  (int) segno);

        MemoryContextSwitchTo(oldcxt);
    }
}

void SetForwardFsyncRequests

(

void

)

Definition at line 254 of file md.c.

References Assert, hash_destroy(), mdsync(), and NIL.

Referenced by StartupXLOG().

{
    /* Perform any pending fsyncs we may have queued up, then drop table */
    if (pendingOpsTable)
    {
        mdsync();
        hash_destroy(pendingOpsTable);
    }
    pendingOpsTable = NULL;

    /*
     * We should not have any pending unlink requests, since mdunlink doesn't
     * queue unlink requests when isRedo.
     */
    Assert(pendingUnlinks == NIL);
}

void smgrclearowner	(	SMgrRelation *	owner,
		SMgrRelation	reln
	)

Definition at line 222 of file smgr.c.

References add_to_unowned_list(), and SMgrRelationData::smgr_owner.

Referenced by FreeFakeRelcacheEntry().

{
    /* Do nothing if the SMgrRelation object is not owned by the owner */
    if (reln->smgr_owner != owner)
        return;

    /* unset the owner's reference */
    *owner = NULL;

    /* unset our reference to the owner */
    reln->smgr_owner = NULL;

    add_to_unowned_list(reln);
}

void smgrclose

(

SMgrRelation

reln

)

Definition at line 296 of file smgr.c.

References elog, ERROR, HASH_REMOVE, hash_search(), MAX_FORKNUM, remove_from_unowned_list(), f_smgr::smgr_close, SMgrRelationData::smgr_owner, SMgrRelationData::smgr_rnode, and SMgrRelationData::smgr_which.

Referenced by AtEOXact_SMgr(), ATExecSetTableSpace(), FinishPreparedTransaction(), smgrcloseall(), smgrclosenode(), smgrDoPendingDeletes(), xact_redo_abort(), and xact_redo_commit().

{
    SMgrRelation *owner;
    ForkNumber  forknum;

    for (forknum = 0; forknum <= MAX_FORKNUM; forknum++)
        smgrsw[reln->smgr_which].smgr_close(reln, forknum);

    owner = reln->smgr_owner;

    if (!owner)
        remove_from_unowned_list(reln);

    if (hash_search(SMgrRelationHash,
                    (void *) &(reln->smgr_rnode),
                    HASH_REMOVE, NULL) == NULL)
        elog(ERROR, "SMgrRelation hashtable corrupted");

    /*
     * Unhook the owner pointer, if any.  We do this last since in the remote
     * possibility of failure above, the SMgrRelation object will still exist.
     */
    if (owner)
        *owner = NULL;
}

void smgrcloseall

(

void

)

Definition at line 326 of file smgr.c.

References hash_seq_init(), hash_seq_search(), smgrclose(), and status().

Referenced by BackgroundWriterMain(), CheckpointerMain(), RelationCacheInvalidate(), RequestCheckpoint(), WalWriterMain(), and XLogDropDatabase().

{
    HASH_SEQ_STATUS status;
    SMgrRelation reln;

    /* Nothing to do if hashtable not set up */
    if (SMgrRelationHash == NULL)
        return;

    hash_seq_init(&status, SMgrRelationHash);

    while ((reln = (SMgrRelation) hash_seq_search(&status)) != NULL)
        smgrclose(reln);
}

void smgrclosenode

(

RelFileNodeBackend

rnode

)

Definition at line 350 of file smgr.c.

References HASH_FIND, hash_search(), and smgrclose().

Referenced by LocalExecuteInvalidationMessage(), and RelationSetNewRelfilenode().

{
    SMgrRelation reln;

    /* Nothing to do if hashtable not set up */
    if (SMgrRelationHash == NULL)
        return;

    reln = (SMgrRelation) hash_search(SMgrRelationHash,
                                      (void *) &rnode,
                                      HASH_FIND, NULL);
    if (reln != NULL)
        smgrclose(reln);
}

void smgrcreate	(	SMgrRelation	reln,
		ForkNumber	forknum,
		bool	isRedo
	)

Definition at line 376 of file smgr.c.

References RelFileNode::dbNode, SMgrRelationData::md_num_open_segs, RelFileNodeBackend::node, f_smgr::smgr_create, SMgrRelationData::smgr_rnode, SMgrRelationData::smgr_which, RelFileNode::spcNode, and TablespaceCreateDbspace().

Referenced by ATExecSetTableSpace(), fsm_extend(), heap_create_init_fork(), index_build(), RelationCreateStorage(), smgr_redo(), vm_extend(), and XLogReadBufferExtended().

{
    /*
     * Exit quickly in WAL replay mode if we've already opened the file. If
     * it's open, it surely must exist.
     */
    if (isRedo && reln->md_num_open_segs[forknum] > 0)
        return;

    /*
     * We may be using the target table space for the first time in this
     * database, so create a per-database subdirectory if needed.
     *
     * XXX this is a fairly ugly violation of module layering, but this seems
     * to be the best place to put the check.  Maybe TablespaceCreateDbspace
     * should be here and not in commands/tablespace.c?  But that would imply
     * importing a lot of stuff that smgr.c oughtn't know, either.
     */
    TablespaceCreateDbspace(reln->smgr_rnode.node.spcNode,
                            reln->smgr_rnode.node.dbNode,
                            isRedo);

    smgrsw[reln->smgr_which].smgr_create(reln, forknum, isRedo);
}

void smgrdounlink	(	SMgrRelation	reln,
		bool	isRedo
	)

Definition at line 414 of file smgr.c.

References CacheInvalidateSmgr(), DropRelFileNodesAllBuffers(), InvalidForkNumber, MAX_FORKNUM, SMgrRelationData::smgr_rnode, f_smgr::smgr_unlink, and SMgrRelationData::smgr_which.

Referenced by FinishPreparedTransaction(), xact_redo_abort(), and xact_redo_commit().

{
    RelFileNodeBackend rnode = reln->smgr_rnode;
    int         which = reln->smgr_which;
    ForkNumber  forknum;

    /* Close the forks at smgr level */
    for (forknum = 0; forknum <= MAX_FORKNUM; forknum++)
        smgrsw[which].smgr_close(reln, forknum);

    /*
     * Get rid of any remaining buffers for the relation.  bufmgr will just
     * drop them without bothering to write the contents.
     */
    DropRelFileNodesAllBuffers(&rnode, 1);

    /*
     * It'd be nice to tell the stats collector to forget it immediately, too.
     * But we can't because we don't know the OID (and in cases involving
     * relfilenode swaps, it's not always clear which table OID to forget,
     * anyway).
     */

    /*
     * Send a shared-inval message to force other backends to close any
     * dangling smgr references they may have for this rel.  We should do this
     * before starting the actual unlinking, in case we fail partway through
     * that step.  Note that the sinval message will eventually come back to
     * this backend, too, and thereby provide a backstop that we closed our
     * own smgr rel.
     */
    CacheInvalidateSmgr(rnode);

    /*
     * Delete the physical file(s).
     *
     * Note: smgr_unlink must treat deletion failure as a WARNING, not an
     * ERROR, because we've already decided to commit or abort the current
     * xact.
     */
    smgrsw[which].smgr_unlink(rnode, InvalidForkNumber, isRedo);
}

void smgrdounlinkall	(	SMgrRelation *	rels,
		int	nrels,
		bool	isRedo
	)

Definition at line 471 of file smgr.c.

References CacheInvalidateSmgr(), DropRelFileNodesAllBuffers(), i, MAX_FORKNUM, palloc(), pfree(), SMgrRelationData::smgr_rnode, and SMgrRelationData::smgr_which.

Referenced by smgrDoPendingDeletes().

{
    int         i = 0;
    RelFileNodeBackend *rnodes;
    ForkNumber  forknum;

    if (nrels == 0)
        return;

    /*
     * create an array which contains all relations to be dropped, and close
     * each relation's forks at the smgr level while at it
     */
    rnodes = palloc(sizeof(RelFileNodeBackend) * nrels);
    for (i = 0; i < nrels; i++)
    {
        RelFileNodeBackend rnode = rels[i]->smgr_rnode;
        int         which = rels[i]->smgr_which;

        rnodes[i] = rnode;

        /* Close the forks at smgr level */
        for (forknum = 0; forknum <= MAX_FORKNUM; forknum++)
            smgrsw[which].smgr_close(rels[i], forknum);
    }

    /*
     * Get rid of any remaining buffers for the relations.  bufmgr will just
     * drop them without bothering to write the contents.
     */
    DropRelFileNodesAllBuffers(rnodes, nrels);

    /*
     * It'd be nice to tell the stats collector to forget them immediately,
     * too. But we can't because we don't know the OIDs.
     */

    /*
     * Send a shared-inval message to force other backends to close any
     * dangling smgr references they may have for these rels.  We should do
     * this before starting the actual unlinking, in case we fail partway
     * through that step.  Note that the sinval messages will eventually come
     * back to this backend, too, and thereby provide a backstop that we
     * closed our own smgr rel.
     */
    for (i = 0; i < nrels; i++)
        CacheInvalidateSmgr(rnodes[i]);

    /*
     * Delete the physical file(s).
     *
     * Note: smgr_unlink must treat deletion failure as a WARNING, not an
     * ERROR, because we've already decided to commit or abort the current
     * xact.
     */

    for (i = 0; i < nrels; i++)
    {
        int         which = rels[i]->smgr_which;

        for (forknum = 0; forknum <= MAX_FORKNUM; forknum++)
            smgrsw[which].smgr_unlink(rnodes[i], forknum, isRedo);
    }

    pfree(rnodes);
}

void smgrdounlinkfork	(	SMgrRelation	reln,
		ForkNumber	forknum,
		bool	isRedo
	)

Definition at line 549 of file smgr.c.

References CacheInvalidateSmgr(), DropRelFileNodeBuffers(), f_smgr::smgr_close, SMgrRelationData::smgr_rnode, f_smgr::smgr_unlink, and SMgrRelationData::smgr_which.

{
    RelFileNodeBackend rnode = reln->smgr_rnode;
    int         which = reln->smgr_which;

    /* Close the fork at smgr level */
    smgrsw[which].smgr_close(reln, forknum);

    /*
     * Get rid of any remaining buffers for the fork.  bufmgr will just drop
     * them without bothering to write the contents.
     */
    DropRelFileNodeBuffers(rnode, forknum, 0);

    /*
     * It'd be nice to tell the stats collector to forget it immediately, too.
     * But we can't because we don't know the OID (and in cases involving
     * relfilenode swaps, it's not always clear which table OID to forget,
     * anyway).
     */

    /*
     * Send a shared-inval message to force other backends to close any
     * dangling smgr references they may have for this rel.  We should do this
     * before starting the actual unlinking, in case we fail partway through
     * that step.  Note that the sinval message will eventually come back to
     * this backend, too, and thereby provide a backstop that we closed our
     * own smgr rel.
     */
    CacheInvalidateSmgr(rnode);

    /*
     * Delete the physical file(s).
     *
     * Note: smgr_unlink must treat deletion failure as a WARNING, not an
     * ERROR, because we've already decided to commit or abort the current
     * xact.
     */
    smgrsw[which].smgr_unlink(rnode, forknum, isRedo);
}

bool smgrexists	(	SMgrRelation	reln,
		ForkNumber	forknum
	)

Definition at line 287 of file smgr.c.

References f_smgr::smgr_exists, and SMgrRelationData::smgr_which.

Referenced by ATExecSetTableSpace(), autoprewarm_database_main(), FreeSpaceMapTruncateRel(), fsm_extend(), fsm_readbuf(), index_build(), pg_prewarm(), RelationTruncate(), smgr_redo(), visibilitymap_truncate(), vm_extend(), and vm_readbuf().

{
    return smgrsw[reln->smgr_which].smgr_exists(reln, forknum);
}

void smgrextend	(	SMgrRelation	reln,
		ForkNumber	forknum,
		BlockNumber	blocknum,
		char *	buffer,
		bool	skipFsync
	)

Definition at line 600 of file smgr.c.

References f_smgr::smgr_extend, and SMgrRelationData::smgr_which.

Referenced by _bt_blwritepage(), _hash_alloc_buckets(), copy_relation_data(), end_heap_rewrite(), fsm_extend(), raw_heap_insert(), ReadBuffer_common(), and vm_extend().

{
    smgrsw[reln->smgr_which].smgr_extend(reln, forknum, blocknum,
                                               buffer, skipFsync);
}

void smgrimmedsync	(	SMgrRelation	reln,
		ForkNumber	forknum
	)

Definition at line 734 of file smgr.c.

References f_smgr::smgr_immedsync, and SMgrRelationData::smgr_which.

Referenced by _bt_load(), blbuildempty(), btbuildempty(), copy_relation_data(), heap_create_init_fork(), heap_sync(), and spgbuildempty().

{
    smgrsw[reln->smgr_which].smgr_immedsync(reln, forknum);
}

void smgrinit

(

void

)

Definition at line 102 of file smgr.c.

References i, NSmgr, on_proc_exit(), f_smgr::smgr_init, and smgrshutdown().

Referenced by BaseInit().

{
    int         i;

    for (i = 0; i < NSmgr; i++)
    {
        if (smgrsw[i].smgr_init)
            smgrsw[i].smgr_init();
    }

    /* register the shutdown proc */
    on_proc_exit(smgrshutdown, 0);
}

BlockNumber smgrnblocks	(	SMgrRelation	reln,
		ForkNumber	forknum
	)

Definition at line 672 of file smgr.c.

References f_smgr::smgr_nblocks, and SMgrRelationData::smgr_which.

Referenced by copy_relation_data(), FreeSpaceMapTruncateRel(), fsm_extend(), fsm_readbuf(), gistBuildCallback(), ReadBuffer_common(), RelationGetNumberOfBlocksInFork(), visibilitymap_truncate(), vm_extend(), vm_readbuf(), and XLogReadBufferExtended().

{
    return smgrsw[reln->smgr_which].smgr_nblocks(reln, forknum);
}

SMgrRelation smgropen	(	RelFileNode	rnode,
		BackendId	backend
	)

Definition at line 137 of file smgr.c.

References add_to_unowned_list(), RelFileNodeBackend::backend, HASHCTL::entrysize, HASH_BLOBS, hash_create(), HASH_ELEM, HASH_ENTER, hash_search(), InvalidBlockNumber, HASHCTL::keysize, MAX_FORKNUM, SMgrRelationData::md_num_open_segs, MemSet, RelFileNodeBackend::node, SMgrRelationData::smgr_fsm_nblocks, SMgrRelationData::smgr_owner, SMgrRelationData::smgr_targblock, SMgrRelationData::smgr_vm_nblocks, and SMgrRelationData::smgr_which.

Referenced by ATExecSetTableSpace(), FinishPreparedTransaction(), FlushBuffer(), IssuePendingWritebacks(), LocalBufferAlloc(), mdsync(), ReadBufferWithoutRelcache(), RelationCreateStorage(), smgr_redo(), smgrDoPendingDeletes(), xact_redo_abort(), xact_redo_commit(), and XLogReadBufferExtended().

{
    RelFileNodeBackend brnode;
    SMgrRelation reln;
    bool        found;

    if (SMgrRelationHash == NULL)
    {
        /* First time through: initialize the hash table */
        HASHCTL     ctl;

        MemSet(&ctl, 0, sizeof(ctl));
        ctl.keysize = sizeof(RelFileNodeBackend);
        ctl.entrysize = sizeof(SMgrRelationData);
        SMgrRelationHash = hash_create("smgr relation table", 400,
                                       &ctl, HASH_ELEM | HASH_BLOBS);
        first_unowned_reln = NULL;
    }

    /* Look up or create an entry */
    brnode.node = rnode;
    brnode.backend = backend;
    reln = (SMgrRelation) hash_search(SMgrRelationHash,
                                      (void *) &brnode,
                                      HASH_ENTER, &found);

    /* Initialize it if not present before */
    if (!found)
    {
        int         forknum;

        /* hash_search already filled in the lookup key */
        reln->smgr_owner = NULL;
        reln->smgr_targblock = InvalidBlockNumber;
        reln->smgr_fsm_nblocks = InvalidBlockNumber;
        reln->smgr_vm_nblocks = InvalidBlockNumber;
        reln->smgr_which = 0;   /* we only have md.c at present */

        /* mark it not open */
        for (forknum = 0; forknum <= MAX_FORKNUM; forknum++)
            reln->md_num_open_segs[forknum] = 0;

        /* it has no owner yet */
        add_to_unowned_list(reln);
    }

    return reln;
}

void smgrpostckpt

(

void

)

Definition at line 774 of file smgr.c.

References i, NSmgr, and f_smgr::smgr_post_ckpt.

Referenced by CreateCheckPoint().

{
    int         i;

    for (i = 0; i < NSmgr; i++)
    {
        if (smgrsw[i].smgr_post_ckpt)
            smgrsw[i].smgr_post_ckpt();
    }
}

void smgrpreckpt

(

void

)

Definition at line 744 of file smgr.c.

References i, NSmgr, and f_smgr::smgr_pre_ckpt.

Referenced by CreateCheckPoint().

{
    int         i;

    for (i = 0; i < NSmgr; i++)
    {
        if (smgrsw[i].smgr_pre_ckpt)
            smgrsw[i].smgr_pre_ckpt();
    }
}

void smgrprefetch	(	SMgrRelation	reln,
		ForkNumber	forknum,
		BlockNumber	blocknum
	)

Definition at line 611 of file smgr.c.

References f_smgr::smgr_prefetch, and SMgrRelationData::smgr_which.

Referenced by LocalPrefetchBuffer(), and PrefetchBuffer().

{
    smgrsw[reln->smgr_which].smgr_prefetch(reln, forknum, blocknum);
}

void smgrread	(	SMgrRelation	reln,
		ForkNumber	forknum,
		BlockNumber	blocknum,
		char *	buffer
	)

Definition at line 625 of file smgr.c.

References f_smgr::smgr_read, and SMgrRelationData::smgr_which.

Referenced by copy_relation_data(), pg_prewarm(), and ReadBuffer_common().

{
    smgrsw[reln->smgr_which].smgr_read(reln, forknum, blocknum, buffer);
}

void smgrsetowner	(	SMgrRelation *	owner,
		SMgrRelation	reln
	)

Definition at line 193 of file smgr.c.

References Assert, remove_from_unowned_list(), and SMgrRelationData::smgr_owner.

{
    /* We don't support "disowning" an SMgrRelation here, use smgrclearowner */
    Assert(owner != NULL);

    /*
     * First, unhook any old owner.  (Normally there shouldn't be any, but it
     * seems possible that this can happen during swap_relation_files()
     * depending on the order of processing.  It's ok to close the old
     * relcache entry early in that case.)
     *
     * If there isn't an old owner, then the reln should be in the unowned
     * list, and we need to remove it.
     */
    if (reln->smgr_owner)
        *(reln->smgr_owner) = NULL;
    else
        remove_from_unowned_list(reln);

    /* Now establish the ownership relationship. */
    reln->smgr_owner = owner;
    *owner = reln;
}

void smgrsync

(

void

)

Definition at line 759 of file smgr.c.

References i, NSmgr, and f_smgr::smgr_sync.

Referenced by CheckPointBuffers().

{
    int         i;

    for (i = 0; i < NSmgr; i++)
    {
        if (smgrsw[i].smgr_sync)
            smgrsw[i].smgr_sync();
    }
}

void smgrtruncate	(	SMgrRelation	reln,
		ForkNumber	forknum,
		BlockNumber	nblocks
	)

Definition at line 684 of file smgr.c.

References CacheInvalidateSmgr(), DropRelFileNodeBuffers(), SMgrRelationData::smgr_rnode, f_smgr::smgr_truncate, and SMgrRelationData::smgr_which.

Referenced by FreeSpaceMapTruncateRel(), RelationTruncate(), smgr_redo(), and visibilitymap_truncate().

{
    /*
     * Get rid of any buffers for the about-to-be-deleted blocks. bufmgr will
     * just drop them without bothering to write the contents.
     */
    DropRelFileNodeBuffers(reln->smgr_rnode, forknum, nblocks);

    /*
     * Send a shared-inval message to force other backends to close any smgr
     * references they may have for this rel.  This is useful because they
     * might have open file pointers to segments that got removed, and/or
     * smgr_targblock variables pointing past the new rel end.  (The inval
     * message will come back to our backend, too, causing a
     * probably-unnecessary local smgr flush.  But we don't expect that this
     * is a performance-critical path.)  As in the unlink code, we want to be
     * sure the message is sent before we start changing things on-disk.
     */
    CacheInvalidateSmgr(reln->smgr_rnode);

    /*
     * Do the truncation.
     */
    smgrsw[reln->smgr_which].smgr_truncate(reln, forknum, nblocks);
}

void smgrwrite	(	SMgrRelation	reln,
		ForkNumber	forknum,
		BlockNumber	blocknum,
		char *	buffer,
		bool	skipFsync
	)

Definition at line 647 of file smgr.c.

References SMgrRelationData::smgr_which, and f_smgr::smgr_write.

Referenced by _bt_blwritepage(), blbuildempty(), btbuildempty(), FlushBuffer(), FlushRelationBuffers(), LocalBufferAlloc(), and spgbuildempty().

{
    smgrsw[reln->smgr_which].smgr_write(reln, forknum, blocknum,
                                              buffer, skipFsync);
}

void smgrwriteback	(	SMgrRelation	reln,
		ForkNumber	forknum,
		BlockNumber	blocknum,
		BlockNumber	nblocks
	)

Definition at line 660 of file smgr.c.

References SMgrRelationData::smgr_which, and f_smgr::smgr_writeback.

Referenced by IssuePendingWritebacks().

{
    smgrsw[reln->smgr_which].smgr_writeback(reln, forknum, blocknum,
                                                  nblocks);
}