vacuumlazy.c File Reference

#include "postgres.h"
#include <math.h>
#include "access/amapi.h"
#include "access/genam.h"
#include "access/heapam.h"
#include "access/heapam_xlog.h"
#include "access/htup_details.h"
#include "access/multixact.h"
#include "access/transam.h"
#include "access/visibilitymap.h"
#include "access/xact.h"
#include "access/xlog.h"
#include "access/xloginsert.h"
#include "catalog/index.h"
#include "catalog/storage.h"
#include "commands/dbcommands.h"
#include "commands/progress.h"
#include "commands/vacuum.h"
#include "executor/instrument.h"
#include "miscadmin.h"
#include "optimizer/paths.h"
#include "pgstat.h"
#include "portability/instr_time.h"
#include "postmaster/autovacuum.h"
#include "storage/bufmgr.h"
#include "storage/freespace.h"
#include "storage/lmgr.h"
#include "tcop/tcopprot.h"
#include "utils/lsyscache.h"
#include "utils/memutils.h"
#include "utils/pg_rusage.h"
#include "utils/timestamp.h"

Include dependency graph for vacuumlazy.c:

Go to the source code of this file.

Data Structures
struct	LVRelState
struct	LVPagePruneState
struct	LVSavedErrInfo

Macros
#define	REL_TRUNCATE_MINIMUM   1000
#define	REL_TRUNCATE_FRACTION   16
#define	VACUUM_TRUNCATE_LOCK_CHECK_INTERVAL   20 /* ms */
#define	VACUUM_TRUNCATE_LOCK_WAIT_INTERVAL   50 /* ms */
#define	VACUUM_TRUNCATE_LOCK_TIMEOUT   5000 /* ms */
#define	BYPASS_THRESHOLD_PAGES   0.02 /* i.e. 2% of rel_pages */
#define	FAILSAFE_EVERY_PAGES    ((BlockNumber) (((uint64) 4 * 1024 * 1024 * 1024) / BLCKSZ))
#define	VACUUM_FSM_EVERY_PAGES    ((BlockNumber) (((uint64) 8 * 1024 * 1024 * 1024) / BLCKSZ))
#define	SKIP_PAGES_THRESHOLD   ((BlockNumber) 32)
#define	PREFETCH_SIZE   ((BlockNumber) 32)
#define	ParallelVacuumIsActive(vacrel)   ((vacrel)->pvs != NULL)

Typedefs
typedef struct LVRelState	LVRelState
typedef struct LVPagePruneState	LVPagePruneState
typedef struct LVSavedErrInfo	LVSavedErrInfo

Enumerations
enum	VacErrPhase {   VACUUM_ERRCB_PHASE_UNKNOWN , VACUUM_ERRCB_PHASE_SCAN_HEAP , VACUUM_ERRCB_PHASE_VACUUM_INDEX , VACUUM_ERRCB_PHASE_VACUUM_HEAP ,   VACUUM_ERRCB_PHASE_INDEX_CLEANUP , VACUUM_ERRCB_PHASE_TRUNCATE }

Functions
static void	lazy_scan_heap (LVRelState *vacrel)
static BlockNumber	lazy_scan_skip (LVRelState *vacrel, Buffer *vmbuffer, BlockNumber next_block, bool *next_unskippable_allvis, bool *skipping_current_range)
static bool	lazy_scan_new_or_empty (LVRelState *vacrel, Buffer buf, BlockNumber blkno, Page page, bool sharelock, Buffer vmbuffer)
static void	lazy_scan_prune (LVRelState *vacrel, Buffer buf, BlockNumber blkno, Page page, LVPagePruneState *prunestate)
static bool	lazy_scan_noprune (LVRelState *vacrel, Buffer buf, BlockNumber blkno, Page page, bool *hastup, bool *recordfreespace)
static void	lazy_vacuum (LVRelState *vacrel)
static bool	lazy_vacuum_all_indexes (LVRelState *vacrel)
static void	lazy_vacuum_heap_rel (LVRelState *vacrel)
static int	lazy_vacuum_heap_page (LVRelState *vacrel, BlockNumber blkno, Buffer buffer, int index, Buffer vmbuffer)
static bool	lazy_check_wraparound_failsafe (LVRelState *vacrel)
static void	lazy_cleanup_all_indexes (LVRelState *vacrel)
static IndexBulkDeleteResult *	lazy_vacuum_one_index (Relation indrel, IndexBulkDeleteResult *istat, double reltuples, LVRelState *vacrel)
static IndexBulkDeleteResult *	lazy_cleanup_one_index (Relation indrel, IndexBulkDeleteResult *istat, double reltuples, bool estimated_count, LVRelState *vacrel)
static bool	should_attempt_truncation (LVRelState *vacrel)
static void	lazy_truncate_heap (LVRelState *vacrel)
static BlockNumber	count_nondeletable_pages (LVRelState *vacrel, bool *lock_waiter_detected)
static void	dead_items_alloc (LVRelState *vacrel, int nworkers)
static void	dead_items_cleanup (LVRelState *vacrel)
static bool	heap_page_is_all_visible (LVRelState *vacrel, Buffer buf, TransactionId *visibility_cutoff_xid, bool *all_frozen)
static void	update_relstats_all_indexes (LVRelState *vacrel)
static void	vacuum_error_callback (void *arg)
static void	update_vacuum_error_info (LVRelState *vacrel, LVSavedErrInfo *saved_vacrel, int phase, BlockNumber blkno, OffsetNumber offnum)
static void	restore_vacuum_error_info (LVRelState *vacrel, const LVSavedErrInfo *saved_vacrel)
void	heap_vacuum_rel (Relation rel, VacuumParams *params, BufferAccessStrategy bstrategy)
static int	dead_items_max_items (LVRelState *vacrel)

Macro Definition Documentation

BYPASS_THRESHOLD_PAGES

#define BYPASS_THRESHOLD_PAGES   0.02 /* i.e. 2% of rel_pages */

Definition at line 94 of file vacuumlazy.c.

FAILSAFE_EVERY_PAGES

#define FAILSAFE_EVERY_PAGES    ((BlockNumber) (((uint64) 4 * 1024 * 1024 * 1024) / BLCKSZ))

Definition at line 100 of file vacuumlazy.c.

ParallelVacuumIsActive

#define ParallelVacuumIsActive

(

vacrel

)

((vacrel)->pvs != NULL)

Definition at line 128 of file vacuumlazy.c.

PREFETCH_SIZE

#define PREFETCH_SIZE   ((BlockNumber) 32)

Definition at line 122 of file vacuumlazy.c.

REL_TRUNCATE_FRACTION

#define REL_TRUNCATE_FRACTION   16

Definition at line 77 of file vacuumlazy.c.

REL_TRUNCATE_MINIMUM

#define REL_TRUNCATE_MINIMUM   1000

Definition at line 76 of file vacuumlazy.c.

SKIP_PAGES_THRESHOLD

#define SKIP_PAGES_THRESHOLD   ((BlockNumber) 32)

Definition at line 116 of file vacuumlazy.c.

VACUUM_FSM_EVERY_PAGES

#define VACUUM_FSM_EVERY_PAGES    ((BlockNumber) (((uint64) 8 * 1024 * 1024 * 1024) / BLCKSZ))

Definition at line 109 of file vacuumlazy.c.

VACUUM_TRUNCATE_LOCK_CHECK_INTERVAL

#define VACUUM_TRUNCATE_LOCK_CHECK_INTERVAL   20 /* ms */

Definition at line 86 of file vacuumlazy.c.

VACUUM_TRUNCATE_LOCK_TIMEOUT

#define VACUUM_TRUNCATE_LOCK_TIMEOUT   5000 /* ms */

Definition at line 88 of file vacuumlazy.c.

VACUUM_TRUNCATE_LOCK_WAIT_INTERVAL

#define VACUUM_TRUNCATE_LOCK_WAIT_INTERVAL   50 /* ms */

Definition at line 87 of file vacuumlazy.c.

Typedef Documentation

LVPagePruneState

typedef struct LVPagePruneState LVPagePruneState

LVRelState

typedef struct LVRelState LVRelState

LVSavedErrInfo

typedef struct LVSavedErrInfo LVSavedErrInfo

Enumeration Type Documentation

VacErrPhase

enum VacErrPhase

Enumerator
VACUUM_ERRCB_PHASE_UNKNOWN
VACUUM_ERRCB_PHASE_SCAN_HEAP
VACUUM_ERRCB_PHASE_VACUUM_INDEX
VACUUM_ERRCB_PHASE_VACUUM_HEAP
VACUUM_ERRCB_PHASE_INDEX_CLEANUP
VACUUM_ERRCB_PHASE_TRUNCATE

Definition at line 131 of file vacuumlazy.c.

{
    VACUUM_ERRCB_PHASE_UNKNOWN,
    VACUUM_ERRCB_PHASE_SCAN_HEAP,
    VACUUM_ERRCB_PHASE_VACUUM_INDEX,
    VACUUM_ERRCB_PHASE_VACUUM_HEAP,
    VACUUM_ERRCB_PHASE_INDEX_CLEANUP,
    VACUUM_ERRCB_PHASE_TRUNCATE
} VacErrPhase;

Function Documentation

count_nondeletable_pages()

static BlockNumber count_nondeletable_pages ( LVRelState *  vacrel, bool *  lock_waiter_detected  )

static

Definition at line 3016 of file vacuumlazy.c.

{
    BlockNumber blkno;
    BlockNumber prefetchedUntil;
    instr_time  starttime;
 
    /* Initialize the starttime if we check for conflicting lock requests */
    INSTR_TIME_SET_CURRENT(starttime);
 
    /*
     * Start checking blocks at what we believe relation end to be and move
     * backwards.  (Strange coding of loop control is needed because blkno is
     * unsigned.)  To make the scan faster, we prefetch a few blocks at a time
     * in forward direction, so that OS-level readahead can kick in.
     */
    blkno = vacrel->rel_pages;
    StaticAssertStmt((PREFETCH_SIZE & (PREFETCH_SIZE - 1)) == 0,
                     "prefetch size must be power of 2");
    prefetchedUntil = InvalidBlockNumber;
    while (blkno > vacrel->nonempty_pages)
    {
        Buffer      buf;
        Page        page;
        OffsetNumber offnum,
                    maxoff;
        bool        hastup;
 
        /*
         * Check if another process requests a lock on our relation. We are
         * holding an AccessExclusiveLock here, so they will be waiting. We
         * only do this once per VACUUM_TRUNCATE_LOCK_CHECK_INTERVAL, and we
         * only check if that interval has elapsed once every 32 blocks to
         * keep the number of system calls and actual shared lock table
         * lookups to a minimum.
         */
        if ((blkno % 32) == 0)
        {
            instr_time  currenttime;
            instr_time  elapsed;
 
            INSTR_TIME_SET_CURRENT(currenttime);
            elapsed = currenttime;
            INSTR_TIME_SUBTRACT(elapsed, starttime);
            if ((INSTR_TIME_GET_MICROSEC(elapsed) / 1000)
                >= VACUUM_TRUNCATE_LOCK_CHECK_INTERVAL)
            {
                if (LockHasWaitersRelation(vacrel->rel, AccessExclusiveLock))
                {
                    ereport(vacrel->verbose ? INFO : DEBUG2,
                            (errmsg("table \"%s\": suspending truncate due to conflicting lock request",
                                    vacrel->relname)));
 
                    *lock_waiter_detected = true;
                    return blkno;
                }
                starttime = currenttime;
            }
        }
 
        /*
         * We don't insert a vacuum delay point here, because we have an
         * exclusive lock on the table which we want to hold for as short a
         * time as possible.  We still need to check for interrupts however.
         */
        CHECK_FOR_INTERRUPTS();
 
        blkno--;
 
        /* If we haven't prefetched this lot yet, do so now. */
        if (prefetchedUntil > blkno)
        {
            BlockNumber prefetchStart;
            BlockNumber pblkno;
 
            prefetchStart = blkno & ~(PREFETCH_SIZE - 1);
            for (pblkno = prefetchStart; pblkno <= blkno; pblkno++)
            {
                PrefetchBuffer(vacrel->rel, MAIN_FORKNUM, pblkno);
                CHECK_FOR_INTERRUPTS();
            }
            prefetchedUntil = prefetchStart;
        }
 
        buf = ReadBufferExtended(vacrel->rel, MAIN_FORKNUM, blkno, RBM_NORMAL,
                                 vacrel->bstrategy);
 
        /* In this phase we only need shared access to the buffer */
        LockBuffer(buf, BUFFER_LOCK_SHARE);
 
        page = BufferGetPage(buf);
 
        if (PageIsNew(page) || PageIsEmpty(page))
        {
            UnlockReleaseBuffer(buf);
            continue;
        }
 
        hastup = false;
        maxoff = PageGetMaxOffsetNumber(page);
        for (offnum = FirstOffsetNumber;
             offnum <= maxoff;
             offnum = OffsetNumberNext(offnum))
        {
            ItemId      itemid;
 
            itemid = PageGetItemId(page, offnum);
 
            /*
             * Note: any non-unused item should be taken as a reason to keep
             * this page.  Even an LP_DEAD item makes truncation unsafe, since
             * we must not have cleaned out its index entries.
             */
            if (ItemIdIsUsed(itemid))
            {
                hastup = true;
                break;          /* can stop scanning */
            }
        }                       /* scan along page */
 
        UnlockReleaseBuffer(buf);
 
        /* Done scanning if we found a tuple here */
        if (hastup)
            return blkno + 1;
    }
 
    /*
     * If we fall out of the loop, all the previously-thought-to-be-empty
     * pages still are; we need not bother to look at the last known-nonempty
     * page.
     */
    return vacrel->nonempty_pages;
}

References AccessExclusiveLock, LVRelState::bstrategy, buf, BUFFER_LOCK_SHARE, BufferGetPage(), CHECK_FOR_INTERRUPTS, DEBUG2, ereport, errmsg(), FirstOffsetNumber, INFO, INSTR_TIME_GET_MICROSEC, INSTR_TIME_SET_CURRENT, INSTR_TIME_SUBTRACT, InvalidBlockNumber, ItemIdIsUsed, LockBuffer(), LockHasWaitersRelation(), MAIN_FORKNUM, LVRelState::nonempty_pages, OffsetNumberNext, PageGetItemId(), PageGetMaxOffsetNumber(), PageIsEmpty(), PageIsNew(), PREFETCH_SIZE, PrefetchBuffer(), RBM_NORMAL, ReadBufferExtended(), LVRelState::rel, LVRelState::rel_pages, LVRelState::relname, StaticAssertStmt, UnlockReleaseBuffer(), VACUUM_TRUNCATE_LOCK_CHECK_INTERVAL, and LVRelState::verbose.

Referenced by lazy_truncate_heap().

dead_items_alloc()

static void dead_items_alloc ( LVRelState *  vacrel, int  nworkers  )

static

Definition at line 3198 of file vacuumlazy.c.

{
    VacDeadItems *dead_items;
    int         max_items;
 
    max_items = dead_items_max_items(vacrel);
    Assert(max_items >= MaxHeapTuplesPerPage);
 
    /*
     * Initialize state for a parallel vacuum.  As of now, only one worker can
     * be used for an index, so we invoke parallelism only if there are at
     * least two indexes on a table.
     */
    if (nworkers >= 0 && vacrel->nindexes > 1 && vacrel->do_index_vacuuming)
    {
        /*
         * Since parallel workers cannot access data in temporary tables, we
         * can't perform parallel vacuum on them.
         */
        if (RelationUsesLocalBuffers(vacrel->rel))
        {
            /*
             * Give warning only if the user explicitly tries to perform a
             * parallel vacuum on the temporary table.
             */
            if (nworkers > 0)
                ereport(WARNING,
                        (errmsg("disabling parallel option of vacuum on \"%s\" --- cannot vacuum temporary tables in parallel",
                                vacrel->relname)));
        }
        else
            vacrel->pvs = parallel_vacuum_init(vacrel->rel, vacrel->indrels,
                                               vacrel->nindexes, nworkers,
                                               max_items,
                                               vacrel->verbose ? INFO : DEBUG2,
                                               vacrel->bstrategy);
 
        /* If parallel mode started, dead_items space is allocated in DSM */
        if (ParallelVacuumIsActive(vacrel))
        {
            vacrel->dead_items = parallel_vacuum_get_dead_items(vacrel->pvs);
            return;
        }
    }
 
    /* Serial VACUUM case */
    dead_items = (VacDeadItems *) palloc(vac_max_items_to_alloc_size(max_items));
    dead_items->max_items = max_items;
    dead_items->num_items = 0;
 
    vacrel->dead_items = dead_items;
}

References Assert(), LVRelState::bstrategy, LVRelState::dead_items, dead_items_max_items(), DEBUG2, LVRelState::do_index_vacuuming, ereport, errmsg(), LVRelState::indrels, INFO, VacDeadItems::max_items, MaxHeapTuplesPerPage, LVRelState::nindexes, VacDeadItems::num_items, palloc(), parallel_vacuum_get_dead_items(), parallel_vacuum_init(), ParallelVacuumIsActive, LVRelState::pvs, LVRelState::rel, RelationUsesLocalBuffers, LVRelState::relname, vac_max_items_to_alloc_size(), LVRelState::verbose, and WARNING.

Referenced by heap_vacuum_rel().

dead_items_cleanup()

static void dead_items_cleanup ( LVRelState *  vacrel )

static

Definition at line 3255 of file vacuumlazy.c.

{
    if (!ParallelVacuumIsActive(vacrel))
    {
        /* Don't bother with pfree here */
        return;
    }
 
    /* End parallel mode */
    parallel_vacuum_end(vacrel->pvs, vacrel->indstats);
    vacrel->pvs = NULL;
}

References LVRelState::indstats, parallel_vacuum_end(), ParallelVacuumIsActive, and LVRelState::pvs.

Referenced by heap_vacuum_rel().

dead_items_max_items()

static int dead_items_max_items ( LVRelState *  vacrel )

static

Definition at line 3159 of file vacuumlazy.c.

{
    int64       max_items;
    int         vac_work_mem = IsAutoVacuumWorkerProcess() &&
        autovacuum_work_mem != -1 ?
        autovacuum_work_mem : maintenance_work_mem;
 
    if (vacrel->nindexes > 0)
    {
        BlockNumber rel_pages = vacrel->rel_pages;
 
        max_items = MAXDEADITEMS(vac_work_mem * 1024L);
        max_items = Min(max_items, INT_MAX);
        max_items = Min(max_items, MAXDEADITEMS(MaxAllocSize));
 
        /* curious coding here to ensure the multiplication can't overflow */
        if ((BlockNumber) (max_items / MaxHeapTuplesPerPage) > rel_pages)
            max_items = rel_pages * MaxHeapTuplesPerPage;
 
        /* stay sane if small maintenance_work_mem */
        max_items = Max(max_items, MaxHeapTuplesPerPage);
    }
    else
    {
        /* One-pass case only stores a single heap page's TIDs at a time */
        max_items = MaxHeapTuplesPerPage;
    }
 
    return (int) max_items;
}

References autovacuum_work_mem, IsAutoVacuumWorkerProcess(), maintenance_work_mem, Max, MaxAllocSize, MAXDEADITEMS, MaxHeapTuplesPerPage, Min, LVRelState::nindexes, and LVRelState::rel_pages.

Referenced by dead_items_alloc().

heap_page_is_all_visible()

static bool heap_page_is_all_visible ( LVRelState *  vacrel, Buffer  buf, TransactionId *  visibility_cutoff_xid, bool *  all_frozen  )

static

Definition at line 3280 of file vacuumlazy.c.

{
    Page        page = BufferGetPage(buf);
    BlockNumber blockno = BufferGetBlockNumber(buf);
    OffsetNumber offnum,
                maxoff;
    bool        all_visible = true;
 
    *visibility_cutoff_xid = InvalidTransactionId;
    *all_frozen = true;
 
    maxoff = PageGetMaxOffsetNumber(page);
    for (offnum = FirstOffsetNumber;
         offnum <= maxoff && all_visible;
         offnum = OffsetNumberNext(offnum))
    {
        ItemId      itemid;
        HeapTupleData tuple;
 
        /*
         * Set the offset number so that we can display it along with any
         * error that occurred while processing this tuple.
         */
        vacrel->offnum = offnum;
        itemid = PageGetItemId(page, offnum);
 
        /* Unused or redirect line pointers are of no interest */
        if (!ItemIdIsUsed(itemid) || ItemIdIsRedirected(itemid))
            continue;
 
        ItemPointerSet(&(tuple.t_self), blockno, offnum);
 
        /*
         * Dead line pointers can have index pointers pointing to them. So
         * they can't be treated as visible
         */
        if (ItemIdIsDead(itemid))
        {
            all_visible = false;
            *all_frozen = false;
            break;
        }
 
        Assert(ItemIdIsNormal(itemid));
 
        tuple.t_data = (HeapTupleHeader) PageGetItem(page, itemid);
        tuple.t_len = ItemIdGetLength(itemid);
        tuple.t_tableOid = RelationGetRelid(vacrel->rel);
 
        switch (HeapTupleSatisfiesVacuum(&tuple, vacrel->cutoffs.OldestXmin,
                                         buf))
        {
            case HEAPTUPLE_LIVE:
                {
                    TransactionId xmin;
 
                    /* Check comments in lazy_scan_prune. */
                    if (!HeapTupleHeaderXminCommitted(tuple.t_data))
                    {
                        all_visible = false;
                        *all_frozen = false;
                        break;
                    }
 
                    /*
                     * The inserter definitely committed. But is it old enough
                     * that everyone sees it as committed?
                     */
                    xmin = HeapTupleHeaderGetXmin(tuple.t_data);
                    if (!TransactionIdPrecedes(xmin,
                                               vacrel->cutoffs.OldestXmin))
                    {
                        all_visible = false;
                        *all_frozen = false;
                        break;
                    }
 
                    /* Track newest xmin on page. */
                    if (TransactionIdFollows(xmin, *visibility_cutoff_xid) &&
                        TransactionIdIsNormal(xmin))
                        *visibility_cutoff_xid = xmin;
 
                    /* Check whether this tuple is already frozen or not */
                    if (all_visible && *all_frozen &&
                        heap_tuple_needs_eventual_freeze(tuple.t_data))
                        *all_frozen = false;
                }
                break;
 
            case HEAPTUPLE_DEAD:
            case HEAPTUPLE_RECENTLY_DEAD:
            case HEAPTUPLE_INSERT_IN_PROGRESS:
            case HEAPTUPLE_DELETE_IN_PROGRESS:
                {
                    all_visible = false;
                    *all_frozen = false;
                    break;
                }
            default:
                elog(ERROR, "unexpected HeapTupleSatisfiesVacuum result");
                break;
        }
    }                           /* scan along page */
 
    /* Clear the offset information once we have processed the given page. */
    vacrel->offnum = InvalidOffsetNumber;
 
    return all_visible;
}

References Assert(), buf, BufferGetBlockNumber(), BufferGetPage(), LVRelState::cutoffs, elog(), ERROR, FirstOffsetNumber, heap_tuple_needs_eventual_freeze(), HEAPTUPLE_DEAD, HEAPTUPLE_DELETE_IN_PROGRESS, HEAPTUPLE_INSERT_IN_PROGRESS, HEAPTUPLE_LIVE, HEAPTUPLE_RECENTLY_DEAD, HeapTupleHeaderGetXmin, HeapTupleHeaderXminCommitted, HeapTupleSatisfiesVacuum(), InvalidOffsetNumber, InvalidTransactionId, ItemIdGetLength, ItemIdIsDead, ItemIdIsNormal, ItemIdIsRedirected, ItemIdIsUsed, ItemPointerSet(), LVRelState::offnum, OffsetNumberNext, VacuumCutoffs::OldestXmin, PageGetItem(), PageGetItemId(), PageGetMaxOffsetNumber(), LVRelState::rel, RelationGetRelid, HeapTupleData::t_data, HeapTupleData::t_len, HeapTupleData::t_self, HeapTupleData::t_tableOid, TransactionIdFollows(), TransactionIdIsNormal, and TransactionIdPrecedes().

Referenced by lazy_scan_prune(), and lazy_vacuum_heap_page().

heap_vacuum_rel()

void heap_vacuum_rel	(	Relation	rel,
		VacuumParams *	params,
		BufferAccessStrategy	bstrategy
	)

Definition at line 303 of file vacuumlazy.c.

{
    LVRelState *vacrel;
    bool        verbose,
                instrument,
                skipwithvm,
                frozenxid_updated,
                minmulti_updated;
    BlockNumber orig_rel_pages,
                new_rel_pages,
                new_rel_allvisible;
    PGRUsage    ru0;
    TimestampTz starttime = 0;
    PgStat_Counter startreadtime = 0,
                startwritetime = 0;
    WalUsage    startwalusage = pgWalUsage;
    int64       StartPageHit = VacuumPageHit,
                StartPageMiss = VacuumPageMiss,
                StartPageDirty = VacuumPageDirty;
    ErrorContextCallback errcallback;
    char      **indnames = NULL;
 
    verbose = (params->options & VACOPT_VERBOSE) != 0;
    instrument = (verbose || (IsAutoVacuumWorkerProcess() &&
                              params->log_min_duration >= 0));
    if (instrument)
    {
        pg_rusage_init(&ru0);
        starttime = GetCurrentTimestamp();
        if (track_io_timing)
        {
            startreadtime = pgStatBlockReadTime;
            startwritetime = pgStatBlockWriteTime;
        }
    }
 
    pgstat_progress_start_command(PROGRESS_COMMAND_VACUUM,
                                  RelationGetRelid(rel));
 
    /*
     * Setup error traceback support for ereport() first.  The idea is to set
     * up an error context callback to display additional information on any
     * error during a vacuum.  During different phases of vacuum, we update
     * the state so that the error context callback always display current
     * information.
     *
     * Copy the names of heap rel into local memory for error reporting
     * purposes, too.  It isn't always safe to assume that we can get the name
     * of each rel.  It's convenient for code in lazy_scan_heap to always use
     * these temp copies.
     */
    vacrel = (LVRelState *) palloc0(sizeof(LVRelState));
    vacrel->dbname = get_database_name(MyDatabaseId);
    vacrel->relnamespace = get_namespace_name(RelationGetNamespace(rel));
    vacrel->relname = pstrdup(RelationGetRelationName(rel));
    vacrel->indname = NULL;
    vacrel->phase = VACUUM_ERRCB_PHASE_UNKNOWN;
    vacrel->verbose = verbose;
    errcallback.callback = vacuum_error_callback;
    errcallback.arg = vacrel;
    errcallback.previous = error_context_stack;
    error_context_stack = &errcallback;
 
    /* Set up high level stuff about rel and its indexes */
    vacrel->rel = rel;
    vac_open_indexes(vacrel->rel, RowExclusiveLock, &vacrel->nindexes,
                     &vacrel->indrels);
    vacrel->bstrategy = bstrategy;
    if (instrument && vacrel->nindexes > 0)
    {
        /* Copy index names used by instrumentation (not error reporting) */
        indnames = palloc(sizeof(char *) * vacrel->nindexes);
        for (int i = 0; i < vacrel->nindexes; i++)
            indnames[i] = pstrdup(RelationGetRelationName(vacrel->indrels[i]));
    }
 
    /*
     * The index_cleanup param either disables index vacuuming and cleanup or
     * forces it to go ahead when we would otherwise apply the index bypass
     * optimization.  The default is 'auto', which leaves the final decision
     * up to lazy_vacuum().
     *
     * The truncate param allows user to avoid attempting relation truncation,
     * though it can't force truncation to happen.
     */
    Assert(params->index_cleanup != VACOPTVALUE_UNSPECIFIED);
    Assert(params->truncate != VACOPTVALUE_UNSPECIFIED &&
           params->truncate != VACOPTVALUE_AUTO);
 
    /*
     * While VacuumFailSafeActive is reset to false before calling this, we
     * still need to reset it here due to recursive calls.
     */
    VacuumFailsafeActive = false;
    vacrel->consider_bypass_optimization = true;
    vacrel->do_index_vacuuming = true;
    vacrel->do_index_cleanup = true;
    vacrel->do_rel_truncate = (params->truncate != VACOPTVALUE_DISABLED);
    if (params->index_cleanup == VACOPTVALUE_DISABLED)
    {
        /* Force disable index vacuuming up-front */
        vacrel->do_index_vacuuming = false;
        vacrel->do_index_cleanup = false;
    }
    else if (params->index_cleanup == VACOPTVALUE_ENABLED)
    {
        /* Force index vacuuming.  Note that failsafe can still bypass. */
        vacrel->consider_bypass_optimization = false;
    }
    else
    {
        /* Default/auto, make all decisions dynamically */
        Assert(params->index_cleanup == VACOPTVALUE_AUTO);
    }
 
    /* Initialize page counters explicitly (be tidy) */
    vacrel->scanned_pages = 0;
    vacrel->removed_pages = 0;
    vacrel->frozen_pages = 0;
    vacrel->lpdead_item_pages = 0;
    vacrel->missed_dead_pages = 0;
    vacrel->nonempty_pages = 0;
    /* dead_items_alloc allocates vacrel->dead_items later on */
 
    /* Allocate/initialize output statistics state */
    vacrel->new_rel_tuples = 0;
    vacrel->new_live_tuples = 0;
    vacrel->indstats = (IndexBulkDeleteResult **)
        palloc0(vacrel->nindexes * sizeof(IndexBulkDeleteResult *));
 
    /* Initialize remaining counters (be tidy) */
    vacrel->num_index_scans = 0;
    vacrel->tuples_deleted = 0;
    vacrel->tuples_frozen = 0;
    vacrel->lpdead_items = 0;
    vacrel->live_tuples = 0;
    vacrel->recently_dead_tuples = 0;
    vacrel->missed_dead_tuples = 0;
 
    /*
     * Get cutoffs that determine which deleted tuples are considered DEAD,
     * not just RECENTLY_DEAD, and which XIDs/MXIDs to freeze.  Then determine
     * the extent of the blocks that we'll scan in lazy_scan_heap.  It has to
     * happen in this order to ensure that the OldestXmin cutoff field works
     * as an upper bound on the XIDs stored in the pages we'll actually scan
     * (NewRelfrozenXid tracking must never be allowed to miss unfrozen XIDs).
     *
     * Next acquire vistest, a related cutoff that's used in heap_page_prune.
     * We expect vistest will always make heap_page_prune remove any deleted
     * tuple whose xmax is < OldestXmin.  lazy_scan_prune must never become
     * confused about whether a tuple should be frozen or removed.  (In the
     * future we might want to teach lazy_scan_prune to recompute vistest from
     * time to time, to increase the number of dead tuples it can prune away.)
     */
    vacrel->aggressive = vacuum_get_cutoffs(rel, params, &vacrel->cutoffs);
    vacrel->rel_pages = orig_rel_pages = RelationGetNumberOfBlocks(rel);
    vacrel->vistest = GlobalVisTestFor(rel);
    /* Initialize state used to track oldest extant XID/MXID */
    vacrel->NewRelfrozenXid = vacrel->cutoffs.OldestXmin;
    vacrel->NewRelminMxid = vacrel->cutoffs.OldestMxact;
    vacrel->skippedallvis = false;
    skipwithvm = true;
    if (params->options & VACOPT_DISABLE_PAGE_SKIPPING)
    {
        /*
         * Force aggressive mode, and disable skipping blocks using the
         * visibility map (even those set all-frozen)
         */
        vacrel->aggressive = true;
        skipwithvm = false;
    }
 
    vacrel->skipwithvm = skipwithvm;
 
    if (verbose)
    {
        if (vacrel->aggressive)
            ereport(INFO,
                    (errmsg("aggressively vacuuming \"%s.%s.%s\"",
                            vacrel->dbname, vacrel->relnamespace,
                            vacrel->relname)));
        else
            ereport(INFO,
                    (errmsg("vacuuming \"%s.%s.%s\"",
                            vacrel->dbname, vacrel->relnamespace,
                            vacrel->relname)));
    }
 
    /*
     * Allocate dead_items array memory using dead_items_alloc.  This handles
     * parallel VACUUM initialization as part of allocating shared memory
     * space used for dead_items.  (But do a failsafe precheck first, to
     * ensure that parallel VACUUM won't be attempted at all when relfrozenxid
     * is already dangerously old.)
     */
    lazy_check_wraparound_failsafe(vacrel);
    dead_items_alloc(vacrel, params->nworkers);
 
    /*
     * Call lazy_scan_heap to perform all required heap pruning, index
     * vacuuming, and heap vacuuming (plus related processing)
     */
    lazy_scan_heap(vacrel);
 
    /*
     * Free resources managed by dead_items_alloc.  This ends parallel mode in
     * passing when necessary.
     */
    dead_items_cleanup(vacrel);
    Assert(!IsInParallelMode());
 
    /*
     * Update pg_class entries for each of rel's indexes where appropriate.
     *
     * Unlike the later update to rel's pg_class entry, this is not critical.
     * Maintains relpages/reltuples statistics used by the planner only.
     */
    if (vacrel->do_index_cleanup)
        update_relstats_all_indexes(vacrel);
 
    /* Done with rel's indexes */
    vac_close_indexes(vacrel->nindexes, vacrel->indrels, NoLock);
 
    /* Optionally truncate rel */
    if (should_attempt_truncation(vacrel))
        lazy_truncate_heap(vacrel);
 
    /* Pop the error context stack */
    error_context_stack = errcallback.previous;
 
    /* Report that we are now doing final cleanup */
    pgstat_progress_update_param(PROGRESS_VACUUM_PHASE,
                                 PROGRESS_VACUUM_PHASE_FINAL_CLEANUP);
 
    /*
     * Prepare to update rel's pg_class entry.
     *
     * Aggressive VACUUMs must always be able to advance relfrozenxid to a
     * value >= FreezeLimit, and relminmxid to a value >= MultiXactCutoff.
     * Non-aggressive VACUUMs may advance them by any amount, or not at all.
     */
    Assert(vacrel->NewRelfrozenXid == vacrel->cutoffs.OldestXmin ||
           TransactionIdPrecedesOrEquals(vacrel->aggressive ? vacrel->cutoffs.FreezeLimit :
                                         vacrel->cutoffs.relfrozenxid,
                                         vacrel->NewRelfrozenXid));
    Assert(vacrel->NewRelminMxid == vacrel->cutoffs.OldestMxact ||
           MultiXactIdPrecedesOrEquals(vacrel->aggressive ? vacrel->cutoffs.MultiXactCutoff :
                                       vacrel->cutoffs.relminmxid,
                                       vacrel->NewRelminMxid));
    if (vacrel->skippedallvis)
    {
        /*
         * Must keep original relfrozenxid in a non-aggressive VACUUM that
         * chose to skip an all-visible page range.  The state that tracks new
         * values will have missed unfrozen XIDs from the pages we skipped.
         */
        Assert(!vacrel->aggressive);
        vacrel->NewRelfrozenXid = InvalidTransactionId;
        vacrel->NewRelminMxid = InvalidMultiXactId;
    }
 
    /*
     * For safety, clamp relallvisible to be not more than what we're setting
     * pg_class.relpages to
     */
    new_rel_pages = vacrel->rel_pages;  /* After possible rel truncation */
    visibilitymap_count(rel, &new_rel_allvisible, NULL);
    if (new_rel_allvisible > new_rel_pages)
        new_rel_allvisible = new_rel_pages;
 
    /*
     * Now actually update rel's pg_class entry.
     *
     * In principle new_live_tuples could be -1 indicating that we (still)
     * don't know the tuple count.  In practice that can't happen, since we
     * scan every page that isn't skipped using the visibility map.
     */
    vac_update_relstats(rel, new_rel_pages, vacrel->new_live_tuples,
                        new_rel_allvisible, vacrel->nindexes > 0,
                        vacrel->NewRelfrozenXid, vacrel->NewRelminMxid,
                        &frozenxid_updated, &minmulti_updated, false);
 
    /*
     * Report results to the cumulative stats system, too.
     *
     * Deliberately avoid telling the stats system about LP_DEAD items that
     * remain in the table due to VACUUM bypassing index and heap vacuuming.
     * ANALYZE will consider the remaining LP_DEAD items to be dead "tuples".
     * It seems like a good idea to err on the side of not vacuuming again too
     * soon in cases where the failsafe prevented significant amounts of heap
     * vacuuming.
     */
    pgstat_report_vacuum(RelationGetRelid(rel),
                         rel->rd_rel->relisshared,
                         Max(vacrel->new_live_tuples, 0),
                         vacrel->recently_dead_tuples +
                         vacrel->missed_dead_tuples);
    pgstat_progress_end_command();
 
    if (instrument)
    {
        TimestampTz endtime = GetCurrentTimestamp();
 
        if (verbose || params->log_min_duration == 0 ||
            TimestampDifferenceExceeds(starttime, endtime,
                                       params->log_min_duration))
        {
            long        secs_dur;
            int         usecs_dur;
            WalUsage    walusage;
            StringInfoData buf;
            char       *msgfmt;
            int32       diff;
            int64       PageHitOp = VacuumPageHit - StartPageHit,
                        PageMissOp = VacuumPageMiss - StartPageMiss,
                        PageDirtyOp = VacuumPageDirty - StartPageDirty;
            double      read_rate = 0,
                        write_rate = 0;
 
            TimestampDifference(starttime, endtime, &secs_dur, &usecs_dur);
            memset(&walusage, 0, sizeof(WalUsage));
            WalUsageAccumDiff(&walusage, &pgWalUsage, &startwalusage);
 
            initStringInfo(&buf);
            if (verbose)
            {
                /*
                 * Aggressiveness already reported earlier, in dedicated
                 * VACUUM VERBOSE ereport
                 */
                Assert(!params->is_wraparound);
                msgfmt = _("finished vacuuming \"%s.%s.%s\": index scans: %d\n");
            }
            else if (params->is_wraparound)
            {
                /*
                 * While it's possible for a VACUUM to be both is_wraparound
                 * and !aggressive, that's just a corner-case -- is_wraparound
                 * implies aggressive.  Produce distinct output for the corner
                 * case all the same, just in case.
                 */
                if (vacrel->aggressive)
                    msgfmt = _("automatic aggressive vacuum to prevent wraparound of table \"%s.%s.%s\": index scans: %d\n");
                else
                    msgfmt = _("automatic vacuum to prevent wraparound of table \"%s.%s.%s\": index scans: %d\n");
            }
            else
            {
                if (vacrel->aggressive)
                    msgfmt = _("automatic aggressive vacuum of table \"%s.%s.%s\": index scans: %d\n");
                else
                    msgfmt = _("automatic vacuum of table \"%s.%s.%s\": index scans: %d\n");
            }
            appendStringInfo(&buf, msgfmt,
                             vacrel->dbname,
                             vacrel->relnamespace,
                             vacrel->relname,
                             vacrel->num_index_scans);
            appendStringInfo(&buf, _("pages: %u removed, %u remain, %u scanned (%.2f%% of total)\n"),
                             vacrel->removed_pages,
                             new_rel_pages,
                             vacrel->scanned_pages,
                             orig_rel_pages == 0 ? 100.0 :
                             100.0 * vacrel->scanned_pages / orig_rel_pages);
            appendStringInfo(&buf,
                             _("tuples: %lld removed, %lld remain, %lld are dead but not yet removable\n"),
                             (long long) vacrel->tuples_deleted,
                             (long long) vacrel->new_rel_tuples,
                             (long long) vacrel->recently_dead_tuples);
            if (vacrel->missed_dead_tuples > 0)
                appendStringInfo(&buf,
                                 _("tuples missed: %lld dead from %u pages not removed due to cleanup lock contention\n"),
                                 (long long) vacrel->missed_dead_tuples,
                                 vacrel->missed_dead_pages);
            diff = (int32) (ReadNextTransactionId() -
                            vacrel->cutoffs.OldestXmin);
            appendStringInfo(&buf,
                             _("removable cutoff: %u, which was %d XIDs old when operation ended\n"),
                             vacrel->cutoffs.OldestXmin, diff);
            if (frozenxid_updated)
            {
                diff = (int32) (vacrel->NewRelfrozenXid -
                                vacrel->cutoffs.relfrozenxid);
                appendStringInfo(&buf,
                                 _("new relfrozenxid: %u, which is %d XIDs ahead of previous value\n"),
                                 vacrel->NewRelfrozenXid, diff);
            }
            if (minmulti_updated)
            {
                diff = (int32) (vacrel->NewRelminMxid -
                                vacrel->cutoffs.relminmxid);
                appendStringInfo(&buf,
                                 _("new relminmxid: %u, which is %d MXIDs ahead of previous value\n"),
                                 vacrel->NewRelminMxid, diff);
            }
            appendStringInfo(&buf, _("frozen: %u pages from table (%.2f%% of total) had %lld tuples frozen\n"),
                             vacrel->frozen_pages,
                             orig_rel_pages == 0 ? 100.0 :
                             100.0 * vacrel->frozen_pages / orig_rel_pages,
                             (long long) vacrel->tuples_frozen);
            if (vacrel->do_index_vacuuming)
            {
                if (vacrel->nindexes == 0 || vacrel->num_index_scans == 0)
                    appendStringInfoString(&buf, _("index scan not needed: "));
                else
                    appendStringInfoString(&buf, _("index scan needed: "));
 
                msgfmt = _("%u pages from table (%.2f%% of total) had %lld dead item identifiers removed\n");
            }
            else
            {
                if (!VacuumFailsafeActive)
                    appendStringInfoString(&buf, _("index scan bypassed: "));
                else
                    appendStringInfoString(&buf, _("index scan bypassed by failsafe: "));
 
                msgfmt = _("%u pages from table (%.2f%% of total) have %lld dead item identifiers\n");
            }
            appendStringInfo(&buf, msgfmt,
                             vacrel->lpdead_item_pages,
                             orig_rel_pages == 0 ? 100.0 :
                             100.0 * vacrel->lpdead_item_pages / orig_rel_pages,
                             (long long) vacrel->lpdead_items);
            for (int i = 0; i < vacrel->nindexes; i++)
            {
                IndexBulkDeleteResult *istat = vacrel->indstats[i];
 
                if (!istat)
                    continue;
 
                appendStringInfo(&buf,
                                 _("index \"%s\": pages: %u in total, %u newly deleted, %u currently deleted, %u reusable\n"),
                                 indnames[i],
                                 istat->num_pages,
                                 istat->pages_newly_deleted,
                                 istat->pages_deleted,
                                 istat->pages_free);
            }
            if (track_io_timing)
            {
                double      read_ms = (double) (pgStatBlockReadTime - startreadtime) / 1000;
                double      write_ms = (double) (pgStatBlockWriteTime - startwritetime) / 1000;
 
                appendStringInfo(&buf, _("I/O timings: read: %.3f ms, write: %.3f ms\n"),
                                 read_ms, write_ms);
            }
            if (secs_dur > 0 || usecs_dur > 0)
            {
                read_rate = (double) BLCKSZ * PageMissOp / (1024 * 1024) /
                    (secs_dur + usecs_dur / 1000000.0);
                write_rate = (double) BLCKSZ * PageDirtyOp / (1024 * 1024) /
                    (secs_dur + usecs_dur / 1000000.0);
            }
            appendStringInfo(&buf, _("avg read rate: %.3f MB/s, avg write rate: %.3f MB/s\n"),
                             read_rate, write_rate);
            appendStringInfo(&buf,
                             _("buffer usage: %lld hits, %lld misses, %lld dirtied\n"),
                             (long long) PageHitOp,
                             (long long) PageMissOp,
                             (long long) PageDirtyOp);
            appendStringInfo(&buf,
                             _("WAL usage: %lld records, %lld full page images, %llu bytes\n"),
                             (long long) walusage.wal_records,
                             (long long) walusage.wal_fpi,
                             (unsigned long long) walusage.wal_bytes);
            appendStringInfo(&buf, _("system usage: %s"), pg_rusage_show(&ru0));
 
            ereport(verbose ? INFO : LOG,
                    (errmsg_internal("%s", buf.data)));
            pfree(buf.data);
        }
    }
 
    /* Cleanup index statistics and index names */
    for (int i = 0; i < vacrel->nindexes; i++)
    {
        if (vacrel->indstats[i])
            pfree(vacrel->indstats[i]);
 
        if (instrument)
            pfree(indnames[i]);
    }
}

References _, LVRelState::aggressive, appendStringInfo(), appendStringInfoString(), ErrorContextCallback::arg, Assert(), LVRelState::bstrategy, buf, ErrorContextCallback::callback, LVRelState::consider_bypass_optimization, LVRelState::cutoffs, LVRelState::dbname, dead_items_alloc(), dead_items_cleanup(), LVRelState::do_index_cleanup, LVRelState::do_index_vacuuming, LVRelState::do_rel_truncate, ereport, errmsg(), errmsg_internal(), error_context_stack, VacuumCutoffs::FreezeLimit, LVRelState::frozen_pages, get_database_name(), get_namespace_name(), GetCurrentTimestamp(), GlobalVisTestFor(), i, VacuumParams::index_cleanup, LVRelState::indname, LVRelState::indrels, LVRelState::indstats, INFO, initStringInfo(), InvalidMultiXactId, InvalidTransactionId, VacuumParams::is_wraparound, IsAutoVacuumWorkerProcess(), IsInParallelMode(), lazy_check_wraparound_failsafe(), lazy_scan_heap(), lazy_truncate_heap(), LVRelState::live_tuples, LOG, VacuumParams::log_min_duration, LVRelState::lpdead_item_pages, LVRelState::lpdead_items, Max, LVRelState::missed_dead_pages, LVRelState::missed_dead_tuples, VacuumCutoffs::MultiXactCutoff, MultiXactIdPrecedesOrEquals(), MyDatabaseId, LVRelState::new_live_tuples, LVRelState::new_rel_tuples, LVRelState::NewRelfrozenXid, LVRelState::NewRelminMxid, LVRelState::nindexes, NoLock, LVRelState::nonempty_pages, LVRelState::num_index_scans, IndexBulkDeleteResult::num_pages, VacuumParams::nworkers, VacuumCutoffs::OldestMxact, VacuumCutoffs::OldestXmin, VacuumParams::options, IndexBulkDeleteResult::pages_deleted, IndexBulkDeleteResult::pages_free, IndexBulkDeleteResult::pages_newly_deleted, palloc(), palloc0(), pfree(), pg_rusage_init(), pg_rusage_show(), pgstat_progress_end_command(), pgstat_progress_start_command(), pgstat_progress_update_param(), pgstat_report_vacuum(), pgStatBlockReadTime, pgStatBlockWriteTime, pgWalUsage, LVRelState::phase, ErrorContextCallback::previous, PROGRESS_COMMAND_VACUUM, PROGRESS_VACUUM_PHASE, PROGRESS_VACUUM_PHASE_FINAL_CLEANUP, pstrdup(), RelationData::rd_rel, ReadNextTransactionId(), LVRelState::recently_dead_tuples, LVRelState::rel, LVRelState::rel_pages, RelationGetNamespace, RelationGetNumberOfBlocks, RelationGetRelationName, RelationGetRelid, VacuumCutoffs::relfrozenxid, VacuumCutoffs::relminmxid, LVRelState::relname, LVRelState::relnamespace, LVRelState::removed_pages, RowExclusiveLock, LVRelState::scanned_pages, should_attempt_truncation(), LVRelState::skippedallvis, LVRelState::skipwithvm, TimestampDifference(), TimestampDifferenceExceeds(), track_io_timing, TransactionIdPrecedesOrEquals(), VacuumParams::truncate, LVRelState::tuples_deleted, LVRelState::tuples_frozen, update_relstats_all_indexes(), vac_close_indexes(), vac_open_indexes(), vac_update_relstats(), VACOPT_DISABLE_PAGE_SKIPPING, VACOPT_VERBOSE, VACOPTVALUE_AUTO, VACOPTVALUE_DISABLED, VACOPTVALUE_ENABLED, VACOPTVALUE_UNSPECIFIED, VACUUM_ERRCB_PHASE_UNKNOWN, vacuum_error_callback(), vacuum_get_cutoffs(), VacuumFailsafeActive, VacuumPageDirty, VacuumPageHit, VacuumPageMiss, LVRelState::verbose, verbose, visibilitymap_count(), LVRelState::vistest, WalUsage::wal_bytes, WalUsage::wal_fpi, WalUsage::wal_records, and WalUsageAccumDiff().

lazy_check_wraparound_failsafe()

static bool lazy_check_wraparound_failsafe ( LVRelState *  vacrel )

static

Definition at line 2636 of file vacuumlazy.c.

{
    /* Don't warn more than once per VACUUM */
    if (VacuumFailsafeActive)
        return true;
 
    if (unlikely(vacuum_xid_failsafe_check(&vacrel->cutoffs)))
    {
        const int   progress_index[] = {
            PROGRESS_VACUUM_INDEXES_TOTAL,
            PROGRESS_VACUUM_INDEXES_PROCESSED
        };
        int64       progress_val[2] = {0, 0};
 
        VacuumFailsafeActive = true;
 
        /*
         * Abandon use of a buffer access strategy to allow use of all of
         * shared buffers.  We assume the caller who allocated the memory for
         * the BufferAccessStrategy will free it.
         */
        vacrel->bstrategy = NULL;
 
        /* Disable index vacuuming, index cleanup, and heap rel truncation */
        vacrel->do_index_vacuuming = false;
        vacrel->do_index_cleanup = false;
        vacrel->do_rel_truncate = false;
 
        /* Reset the progress counters */
        pgstat_progress_update_multi_param(2, progress_index, progress_val);
 
        ereport(WARNING,
                (errmsg("bypassing nonessential maintenance of table \"%s.%s.%s\" as a failsafe after %d index scans",
                        vacrel->dbname, vacrel->relnamespace, vacrel->relname,
                        vacrel->num_index_scans),
                 errdetail("The table's relfrozenxid or relminmxid is too far in the past."),
                 errhint("Consider increasing configuration parameter \"maintenance_work_mem\" or \"autovacuum_work_mem\".\n"
                         "You might also need to consider other ways for VACUUM to keep up with the allocation of transaction IDs.")));
 
        /* Stop applying cost limits from this point on */
        VacuumCostActive = false;
        VacuumCostBalance = 0;
 
        return true;
    }
 
    return false;
}

References LVRelState::bstrategy, LVRelState::cutoffs, LVRelState::dbname, LVRelState::do_index_cleanup, LVRelState::do_index_vacuuming, LVRelState::do_rel_truncate, ereport, errdetail(), errhint(), errmsg(), LVRelState::num_index_scans, pgstat_progress_update_multi_param(), PROGRESS_VACUUM_INDEXES_PROCESSED, PROGRESS_VACUUM_INDEXES_TOTAL, LVRelState::relname, LVRelState::relnamespace, unlikely, vacuum_xid_failsafe_check(), VacuumCostActive, VacuumCostBalance, VacuumFailsafeActive, and WARNING.

Referenced by heap_vacuum_rel(), lazy_scan_heap(), and lazy_vacuum_all_indexes().

lazy_cleanup_all_indexes()

static void lazy_cleanup_all_indexes ( LVRelState *  vacrel )

static

Definition at line 2689 of file vacuumlazy.c.

{
    double      reltuples = vacrel->new_rel_tuples;
    bool        estimated_count = vacrel->scanned_pages < vacrel->rel_pages;
    const int   progress_start_index[] = {
        PROGRESS_VACUUM_PHASE,
        PROGRESS_VACUUM_INDEXES_TOTAL
    };
    const int   progress_end_index[] = {
        PROGRESS_VACUUM_INDEXES_TOTAL,
        PROGRESS_VACUUM_INDEXES_PROCESSED
    };
    int64       progress_start_val[2];
    int64       progress_end_val[2] = {0, 0};
 
    Assert(vacrel->do_index_cleanup);
    Assert(vacrel->nindexes > 0);
 
    /*
     * Report that we are now cleaning up indexes and the number of indexes to
     * cleanup.
     */
    progress_start_val[0] = PROGRESS_VACUUM_PHASE_INDEX_CLEANUP;
    progress_start_val[1] = vacrel->nindexes;
    pgstat_progress_update_multi_param(2, progress_start_index, progress_start_val);
 
    if (!ParallelVacuumIsActive(vacrel))
    {
        for (int idx = 0; idx < vacrel->nindexes; idx++)
        {
            Relation    indrel = vacrel->indrels[idx];
            IndexBulkDeleteResult *istat = vacrel->indstats[idx];
 
            vacrel->indstats[idx] =
                lazy_cleanup_one_index(indrel, istat, reltuples,
                                       estimated_count, vacrel);
 
            /* Report the number of indexes cleaned up */
            pgstat_progress_update_param(PROGRESS_VACUUM_INDEXES_PROCESSED,
                                         idx + 1);
        }
    }
    else
    {
        /* Outsource everything to parallel variant */
        parallel_vacuum_cleanup_all_indexes(vacrel->pvs, reltuples,
                                            vacrel->num_index_scans,
                                            estimated_count);
    }
 
    /* Reset the progress counters */
    pgstat_progress_update_multi_param(2, progress_end_index, progress_end_val);
}

References Assert(), LVRelState::do_index_cleanup, idx(), LVRelState::indrels, LVRelState::indstats, lazy_cleanup_one_index(), LVRelState::new_rel_tuples, LVRelState::nindexes, LVRelState::num_index_scans, parallel_vacuum_cleanup_all_indexes(), ParallelVacuumIsActive, pgstat_progress_update_multi_param(), pgstat_progress_update_param(), PROGRESS_VACUUM_INDEXES_PROCESSED, PROGRESS_VACUUM_INDEXES_TOTAL, PROGRESS_VACUUM_PHASE, PROGRESS_VACUUM_PHASE_INDEX_CLEANUP, LVRelState::pvs, LVRelState::rel_pages, and LVRelState::scanned_pages.

Referenced by lazy_scan_heap().

lazy_cleanup_one_index()

static IndexBulkDeleteResult * lazy_cleanup_one_index ( Relation  indrel, IndexBulkDeleteResult *  istat, double  reltuples, bool  estimated_count, LVRelState *  vacrel  )

static

Definition at line 2805 of file vacuumlazy.c.

{
    IndexVacuumInfo ivinfo;
    LVSavedErrInfo saved_err_info;
 
    ivinfo.index = indrel;
    ivinfo.heaprel = vacrel->rel;
    ivinfo.analyze_only = false;
    ivinfo.report_progress = false;
    ivinfo.estimated_count = estimated_count;
    ivinfo.message_level = DEBUG2;
 
    ivinfo.num_heap_tuples = reltuples;
    ivinfo.strategy = vacrel->bstrategy;
 
    /*
     * Update error traceback information.
     *
     * The index name is saved during this phase and restored immediately
     * after this phase.  See vacuum_error_callback.
     */
    Assert(vacrel->indname == NULL);
    vacrel->indname = pstrdup(RelationGetRelationName(indrel));
    update_vacuum_error_info(vacrel, &saved_err_info,
                             VACUUM_ERRCB_PHASE_INDEX_CLEANUP,
                             InvalidBlockNumber, InvalidOffsetNumber);
 
    istat = vac_cleanup_one_index(&ivinfo, istat);
 
    /* Revert to the previous phase information for error traceback */
    restore_vacuum_error_info(vacrel, &saved_err_info);
    pfree(vacrel->indname);
    vacrel->indname = NULL;
 
    return istat;
}

References IndexVacuumInfo::analyze_only, Assert(), LVRelState::bstrategy, DEBUG2, IndexVacuumInfo::estimated_count, IndexVacuumInfo::heaprel, IndexVacuumInfo::index, LVRelState::indname, InvalidBlockNumber, InvalidOffsetNumber, IndexVacuumInfo::message_level, IndexVacuumInfo::num_heap_tuples, pfree(), pstrdup(), LVRelState::rel, RelationGetRelationName, IndexVacuumInfo::report_progress, restore_vacuum_error_info(), IndexVacuumInfo::strategy, update_vacuum_error_info(), vac_cleanup_one_index(), and VACUUM_ERRCB_PHASE_INDEX_CLEANUP.

Referenced by lazy_cleanup_all_indexes().

lazy_scan_heap()

static void lazy_scan_heap ( LVRelState *  vacrel )

static

Definition at line 825 of file vacuumlazy.c.

{
    BlockNumber rel_pages = vacrel->rel_pages,
                blkno,
                next_unskippable_block,
                next_fsm_block_to_vacuum = 0;
    VacDeadItems *dead_items = vacrel->dead_items;
    Buffer      vmbuffer = InvalidBuffer;
    bool        next_unskippable_allvis,
                skipping_current_range;
    const int   initprog_index[] = {
        PROGRESS_VACUUM_PHASE,
        PROGRESS_VACUUM_TOTAL_HEAP_BLKS,
        PROGRESS_VACUUM_MAX_DEAD_TUPLES
    };
    int64       initprog_val[3];
 
    /* Report that we're scanning the heap, advertising total # of blocks */
    initprog_val[0] = PROGRESS_VACUUM_PHASE_SCAN_HEAP;
    initprog_val[1] = rel_pages;
    initprog_val[2] = dead_items->max_items;
    pgstat_progress_update_multi_param(3, initprog_index, initprog_val);
 
    /* Set up an initial range of skippable blocks using the visibility map */
    next_unskippable_block = lazy_scan_skip(vacrel, &vmbuffer, 0,
                                            &next_unskippable_allvis,
                                            &skipping_current_range);
    for (blkno = 0; blkno < rel_pages; blkno++)
    {
        Buffer      buf;
        Page        page;
        bool        all_visible_according_to_vm;
        LVPagePruneState prunestate;
 
        if (blkno == next_unskippable_block)
        {
            /*
             * Can't skip this page safely.  Must scan the page.  But
             * determine the next skippable range after the page first.
             */
            all_visible_according_to_vm = next_unskippable_allvis;
            next_unskippable_block = lazy_scan_skip(vacrel, &vmbuffer,
                                                    blkno + 1,
                                                    &next_unskippable_allvis,
                                                    &skipping_current_range);
 
            Assert(next_unskippable_block >= blkno + 1);
        }
        else
        {
            /* Last page always scanned (may need to set nonempty_pages) */
            Assert(blkno < rel_pages - 1);
 
            if (skipping_current_range)
                continue;
 
            /* Current range is too small to skip -- just scan the page */
            all_visible_according_to_vm = true;
        }
 
        vacrel->scanned_pages++;
 
        /* Report as block scanned, update error traceback information */
        pgstat_progress_update_param(PROGRESS_VACUUM_HEAP_BLKS_SCANNED, blkno);
        update_vacuum_error_info(vacrel, NULL, VACUUM_ERRCB_PHASE_SCAN_HEAP,
                                 blkno, InvalidOffsetNumber);
 
        vacuum_delay_point();
 
        /*
         * Regularly check if wraparound failsafe should trigger.
         *
         * There is a similar check inside lazy_vacuum_all_indexes(), but
         * relfrozenxid might start to look dangerously old before we reach
         * that point.  This check also provides failsafe coverage for the
         * one-pass strategy, and the two-pass strategy with the index_cleanup
         * param set to 'off'.
         */
        if (vacrel->scanned_pages % FAILSAFE_EVERY_PAGES == 0)
            lazy_check_wraparound_failsafe(vacrel);
 
        /*
         * Consider if we definitely have enough space to process TIDs on page
         * already.  If we are close to overrunning the available space for
         * dead_items TIDs, pause and do a cycle of vacuuming before we tackle
         * this page.
         */
        Assert(dead_items->max_items >= MaxHeapTuplesPerPage);
        if (dead_items->max_items - dead_items->num_items < MaxHeapTuplesPerPage)
        {
            /*
             * Before beginning index vacuuming, we release any pin we may
             * hold on the visibility map page.  This isn't necessary for
             * correctness, but we do it anyway to avoid holding the pin
             * across a lengthy, unrelated operation.
             */
            if (BufferIsValid(vmbuffer))
            {
                ReleaseBuffer(vmbuffer);
                vmbuffer = InvalidBuffer;
            }
 
            /* Perform a round of index and heap vacuuming */
            vacrel->consider_bypass_optimization = false;
            lazy_vacuum(vacrel);
 
            /*
             * Vacuum the Free Space Map to make newly-freed space visible on
             * upper-level FSM pages.  Note we have not yet processed blkno.
             */
            FreeSpaceMapVacuumRange(vacrel->rel, next_fsm_block_to_vacuum,
                                    blkno);
            next_fsm_block_to_vacuum = blkno;
 
            /* Report that we are once again scanning the heap */
            pgstat_progress_update_param(PROGRESS_VACUUM_PHASE,
                                         PROGRESS_VACUUM_PHASE_SCAN_HEAP);
        }
 
        /*
         * Pin the visibility map page in case we need to mark the page
         * all-visible.  In most cases this will be very cheap, because we'll
         * already have the correct page pinned anyway.
         */
        visibilitymap_pin(vacrel->rel, blkno, &vmbuffer);
 
        /*
         * We need a buffer cleanup lock to prune HOT chains and defragment
         * the page in lazy_scan_prune.  But when it's not possible to acquire
         * a cleanup lock right away, we may be able to settle for reduced
         * processing using lazy_scan_noprune.
         */
        buf = ReadBufferExtended(vacrel->rel, MAIN_FORKNUM, blkno, RBM_NORMAL,
                                 vacrel->bstrategy);
        page = BufferGetPage(buf);
        if (!ConditionalLockBufferForCleanup(buf))
        {
            bool        hastup,
                        recordfreespace;
 
            LockBuffer(buf, BUFFER_LOCK_SHARE);
 
            /* Check for new or empty pages before lazy_scan_noprune call */
            if (lazy_scan_new_or_empty(vacrel, buf, blkno, page, true,
                                       vmbuffer))
            {
                /* Processed as new/empty page (lock and pin released) */
                continue;
            }
 
            /* Collect LP_DEAD items in dead_items array, count tuples */
            if (lazy_scan_noprune(vacrel, buf, blkno, page, &hastup,
                                  &recordfreespace))
            {
                Size        freespace = 0;
 
                /*
                 * Processed page successfully (without cleanup lock) -- just
                 * need to perform rel truncation and FSM steps, much like the
                 * lazy_scan_prune case.  Don't bother trying to match its
                 * visibility map setting steps, though.
                 */
                if (hastup)
                    vacrel->nonempty_pages = blkno + 1;
                if (recordfreespace)
                    freespace = PageGetHeapFreeSpace(page);
                UnlockReleaseBuffer(buf);
                if (recordfreespace)
                    RecordPageWithFreeSpace(vacrel->rel, blkno, freespace);
                continue;
            }
 
            /*
             * lazy_scan_noprune could not do all required processing.  Wait
             * for a cleanup lock, and call lazy_scan_prune in the usual way.
             */
            Assert(vacrel->aggressive);
            LockBuffer(buf, BUFFER_LOCK_UNLOCK);
            LockBufferForCleanup(buf);
        }
 
        /* Check for new or empty pages before lazy_scan_prune call */
        if (lazy_scan_new_or_empty(vacrel, buf, blkno, page, false, vmbuffer))
        {
            /* Processed as new/empty page (lock and pin released) */
            continue;
        }
 
        /*
         * Prune, freeze, and count tuples.
         *
         * Accumulates details of remaining LP_DEAD line pointers on page in
         * dead_items array.  This includes LP_DEAD line pointers that we
         * pruned ourselves, as well as existing LP_DEAD line pointers that
         * were pruned some time earlier.  Also considers freezing XIDs in the
         * tuple headers of remaining items with storage.
         */
        lazy_scan_prune(vacrel, buf, blkno, page, &prunestate);
 
        Assert(!prunestate.all_visible || !prunestate.has_lpdead_items);
 
        /* Remember the location of the last page with nonremovable tuples */
        if (prunestate.hastup)
            vacrel->nonempty_pages = blkno + 1;
 
        if (vacrel->nindexes == 0)
        {
            /*
             * Consider the need to do page-at-a-time heap vacuuming when
             * using the one-pass strategy now.
             *
             * The one-pass strategy will never call lazy_vacuum().  The steps
             * performed here can be thought of as the one-pass equivalent of
             * a call to lazy_vacuum().
             */
            if (prunestate.has_lpdead_items)
            {
                Size        freespace;
 
                lazy_vacuum_heap_page(vacrel, blkno, buf, 0, vmbuffer);
 
                /* Forget the LP_DEAD items that we just vacuumed */
                dead_items->num_items = 0;
 
                /*
                 * Periodically perform FSM vacuuming to make newly-freed
                 * space visible on upper FSM pages.  Note we have not yet
                 * performed FSM processing for blkno.
                 */
                if (blkno - next_fsm_block_to_vacuum >= VACUUM_FSM_EVERY_PAGES)
                {
                    FreeSpaceMapVacuumRange(vacrel->rel, next_fsm_block_to_vacuum,
                                            blkno);
                    next_fsm_block_to_vacuum = blkno;
                }
 
                /*
                 * Now perform FSM processing for blkno, and move on to next
                 * page.
                 *
                 * Our call to lazy_vacuum_heap_page() will have considered if
                 * it's possible to set all_visible/all_frozen independently
                 * of lazy_scan_prune().  Note that prunestate was invalidated
                 * by lazy_vacuum_heap_page() call.
                 */
                freespace = PageGetHeapFreeSpace(page);
 
                UnlockReleaseBuffer(buf);
                RecordPageWithFreeSpace(vacrel->rel, blkno, freespace);
                continue;
            }
 
            /*
             * There was no call to lazy_vacuum_heap_page() because pruning
             * didn't encounter/create any LP_DEAD items that needed to be
             * vacuumed.  Prune state has not been invalidated, so proceed
             * with prunestate-driven visibility map and FSM steps (just like
             * the two-pass strategy).
             */
            Assert(dead_items->num_items == 0);
        }
 
        /*
         * Handle setting visibility map bit based on information from the VM
         * (as of last lazy_scan_skip() call), and from prunestate
         */
        if (!all_visible_according_to_vm && prunestate.all_visible)
        {
            uint8       flags = VISIBILITYMAP_ALL_VISIBLE;
 
            if (prunestate.all_frozen)
            {
                Assert(!TransactionIdIsValid(prunestate.visibility_cutoff_xid));
                flags |= VISIBILITYMAP_ALL_FROZEN;
            }
 
            /*
             * It should never be the case that the visibility map page is set
             * while the page-level bit is clear, but the reverse is allowed
             * (if checksums are not enabled).  Regardless, set both bits so
             * that we get back in sync.
             *
             * NB: If the heap page is all-visible but the VM bit is not set,
             * we don't need to dirty the heap page.  However, if checksums
             * are enabled, we do need to make sure that the heap page is
             * dirtied before passing it to visibilitymap_set(), because it
             * may be logged.  Given that this situation should only happen in
             * rare cases after a crash, it is not worth optimizing.
             */
            PageSetAllVisible(page);
            MarkBufferDirty(buf);
            visibilitymap_set(vacrel->rel, blkno, buf, InvalidXLogRecPtr,
                              vmbuffer, prunestate.visibility_cutoff_xid,
                              flags);
        }
 
        /*
         * As of PostgreSQL 9.2, the visibility map bit should never be set if
         * the page-level bit is clear.  However, it's possible that the bit
         * got cleared after lazy_scan_skip() was called, so we must recheck
         * with buffer lock before concluding that the VM is corrupt.
         */
        else if (all_visible_according_to_vm && !PageIsAllVisible(page) &&
                 visibilitymap_get_status(vacrel->rel, blkno, &vmbuffer) != 0)
        {
            elog(WARNING, "page is not marked all-visible but visibility map bit is set in relation \"%s\" page %u",
                 vacrel->relname, blkno);
            visibilitymap_clear(vacrel->rel, blkno, vmbuffer,
                                VISIBILITYMAP_VALID_BITS);
        }
 
        /*
         * It's possible for the value returned by
         * GetOldestNonRemovableTransactionId() to move backwards, so it's not
         * wrong for us to see tuples that appear to not be visible to
         * everyone yet, while PD_ALL_VISIBLE is already set. The real safe
         * xmin value never moves backwards, but
         * GetOldestNonRemovableTransactionId() is conservative and sometimes
         * returns a value that's unnecessarily small, so if we see that
         * contradiction it just means that the tuples that we think are not
         * visible to everyone yet actually are, and the PD_ALL_VISIBLE flag
         * is correct.
         *
         * There should never be LP_DEAD items on a page with PD_ALL_VISIBLE
         * set, however.
         */
        else if (prunestate.has_lpdead_items && PageIsAllVisible(page))
        {
            elog(WARNING, "page containing LP_DEAD items is marked as all-visible in relation \"%s\" page %u",
                 vacrel->relname, blkno);
            PageClearAllVisible(page);
            MarkBufferDirty(buf);
            visibilitymap_clear(vacrel->rel, blkno, vmbuffer,
                                VISIBILITYMAP_VALID_BITS);
        }
 
        /*
         * If the all-visible page is all-frozen but not marked as such yet,
         * mark it as all-frozen.  Note that all_frozen is only valid if
         * all_visible is true, so we must check both prunestate fields.
         */
        else if (all_visible_according_to_vm && prunestate.all_visible &&
                 prunestate.all_frozen &&
                 !VM_ALL_FROZEN(vacrel->rel, blkno, &vmbuffer))
        {
            /*
             * Avoid relying on all_visible_according_to_vm as a proxy for the
             * page-level PD_ALL_VISIBLE bit being set, since it might have
             * become stale -- even when all_visible is set in prunestate
             */
            if (!PageIsAllVisible(page))
            {
                PageSetAllVisible(page);
                MarkBufferDirty(buf);
            }
 
            /*
             * Set the page all-frozen (and all-visible) in the VM.
             *
             * We can pass InvalidTransactionId as our visibility_cutoff_xid,
             * since a snapshotConflictHorizon sufficient to make everything
             * safe for REDO was logged when the page's tuples were frozen.
             */
            Assert(!TransactionIdIsValid(prunestate.visibility_cutoff_xid));
            visibilitymap_set(vacrel->rel, blkno, buf, InvalidXLogRecPtr,
                              vmbuffer, InvalidTransactionId,
                              VISIBILITYMAP_ALL_VISIBLE |
                              VISIBILITYMAP_ALL_FROZEN);
        }
 
        /*
         * Final steps for block: drop cleanup lock, record free space in the
         * FSM
         */
        if (prunestate.has_lpdead_items && vacrel->do_index_vacuuming)
        {
            /*
             * Wait until lazy_vacuum_heap_rel() to save free space.  This
             * doesn't just save us some cycles; it also allows us to record
             * any additional free space that lazy_vacuum_heap_page() will
             * make available in cases where it's possible to truncate the
             * page's line pointer array.
             *
             * Note: It's not in fact 100% certain that we really will call
             * lazy_vacuum_heap_rel() -- lazy_vacuum() might yet opt to skip
             * index vacuuming (and so must skip heap vacuuming).  This is
             * deemed okay because it only happens in emergencies, or when
             * there is very little free space anyway. (Besides, we start
             * recording free space in the FSM once index vacuuming has been
             * abandoned.)
             *
             * Note: The one-pass (no indexes) case is only supposed to make
             * it this far when there were no LP_DEAD items during pruning.
             */
            Assert(vacrel->nindexes > 0);
            UnlockReleaseBuffer(buf);
        }
        else
        {
            Size        freespace = PageGetHeapFreeSpace(page);
 
            UnlockReleaseBuffer(buf);
            RecordPageWithFreeSpace(vacrel->rel, blkno, freespace);
        }
    }
 
    vacrel->blkno = InvalidBlockNumber;
    if (BufferIsValid(vmbuffer))
        ReleaseBuffer(vmbuffer);
 
    /* report that everything is now scanned */
    pgstat_progress_update_param(PROGRESS_VACUUM_HEAP_BLKS_SCANNED, blkno);
 
    /* now we can compute the new value for pg_class.reltuples */
    vacrel->new_live_tuples = vac_estimate_reltuples(vacrel->rel, rel_pages,
                                                     vacrel->scanned_pages,
                                                     vacrel->live_tuples);
 
    /*
     * Also compute the total number of surviving heap entries.  In the
     * (unlikely) scenario that new_live_tuples is -1, take it as zero.
     */
    vacrel->new_rel_tuples =
        Max(vacrel->new_live_tuples, 0) + vacrel->recently_dead_tuples +
        vacrel->missed_dead_tuples;
 
    /*
     * Do index vacuuming (call each index's ambulkdelete routine), then do
     * related heap vacuuming
     */
    if (dead_items->num_items > 0)
        lazy_vacuum(vacrel);
 
    /*
     * Vacuum the remainder of the Free Space Map.  We must do this whether or
     * not there were indexes, and whether or not we bypassed index vacuuming.
     */
    if (blkno > next_fsm_block_to_vacuum)
        FreeSpaceMapVacuumRange(vacrel->rel, next_fsm_block_to_vacuum, blkno);
 
    /* report all blocks vacuumed */
    pgstat_progress_update_param(PROGRESS_VACUUM_HEAP_BLKS_VACUUMED, blkno);
 
    /* Do final index cleanup (call each index's amvacuumcleanup routine) */
    if (vacrel->nindexes > 0 && vacrel->do_index_cleanup)
        lazy_cleanup_all_indexes(vacrel);
}

References LVRelState::aggressive, LVPagePruneState::all_frozen, LVPagePruneState::all_visible, Assert(), LVRelState::blkno, LVRelState::bstrategy, buf, BUFFER_LOCK_SHARE, BUFFER_LOCK_UNLOCK, BufferGetPage(), BufferIsValid(), ConditionalLockBufferForCleanup(), LVRelState::consider_bypass_optimization, LVRelState::dead_items, LVRelState::do_index_cleanup, LVRelState::do_index_vacuuming, elog(), FAILSAFE_EVERY_PAGES, FreeSpaceMapVacuumRange(), LVPagePruneState::has_lpdead_items, LVPagePruneState::hastup, InvalidBlockNumber, InvalidBuffer, InvalidOffsetNumber, InvalidTransactionId, InvalidXLogRecPtr, lazy_check_wraparound_failsafe(), lazy_cleanup_all_indexes(), lazy_scan_new_or_empty(), lazy_scan_noprune(), lazy_scan_prune(), lazy_scan_skip(), lazy_vacuum(), lazy_vacuum_heap_page(), LVRelState::live_tuples, LockBuffer(), LockBufferForCleanup(), MAIN_FORKNUM, MarkBufferDirty(), Max, VacDeadItems::max_items, MaxHeapTuplesPerPage, LVRelState::missed_dead_tuples, LVRelState::new_live_tuples, LVRelState::new_rel_tuples, LVRelState::nindexes, LVRelState::nonempty_pages, VacDeadItems::num_items, PageClearAllVisible(), PageGetHeapFreeSpace(), PageIsAllVisible(), PageSetAllVisible(), pgstat_progress_update_multi_param(), pgstat_progress_update_param(), PROGRESS_VACUUM_HEAP_BLKS_SCANNED, PROGRESS_VACUUM_HEAP_BLKS_VACUUMED, PROGRESS_VACUUM_MAX_DEAD_TUPLES, PROGRESS_VACUUM_PHASE, PROGRESS_VACUUM_PHASE_SCAN_HEAP, PROGRESS_VACUUM_TOTAL_HEAP_BLKS, RBM_NORMAL, ReadBufferExtended(), LVRelState::recently_dead_tuples, RecordPageWithFreeSpace(), LVRelState::rel, LVRelState::rel_pages, ReleaseBuffer(), LVRelState::relname, LVRelState::scanned_pages, TransactionIdIsValid, UnlockReleaseBuffer(), update_vacuum_error_info(), vac_estimate_reltuples(), vacuum_delay_point(), VACUUM_ERRCB_PHASE_SCAN_HEAP, VACUUM_FSM_EVERY_PAGES, LVPagePruneState::visibility_cutoff_xid, VISIBILITYMAP_ALL_FROZEN, VISIBILITYMAP_ALL_VISIBLE, visibilitymap_clear(), visibilitymap_get_status(), visibilitymap_pin(), visibilitymap_set(), VISIBILITYMAP_VALID_BITS, VM_ALL_FROZEN, and WARNING.

Referenced by heap_vacuum_rel().

lazy_scan_new_or_empty()

static bool lazy_scan_new_or_empty ( LVRelState *  vacrel, Buffer  buf, BlockNumber  blkno, Page  page, bool  sharelock, Buffer  vmbuffer  )

static

Definition at line 1412 of file vacuumlazy.c.

{
    Size        freespace;
 
    if (PageIsNew(page))
    {
        /*
         * All-zeroes pages can be left over if either a backend extends the
         * relation by a single page, but crashes before the newly initialized
         * page has been written out, or when bulk-extending the relation
         * (which creates a number of empty pages at the tail end of the
         * relation), and then enters them into the FSM.
         *
         * Note we do not enter the page into the visibilitymap. That has the
         * downside that we repeatedly visit this page in subsequent vacuums,
         * but otherwise we'll never discover the space on a promoted standby.
         * The harm of repeated checking ought to normally not be too bad. The
         * space usually should be used at some point, otherwise there
         * wouldn't be any regular vacuums.
         *
         * Make sure these pages are in the FSM, to ensure they can be reused.
         * Do that by testing if there's any space recorded for the page. If
         * not, enter it. We do so after releasing the lock on the heap page,
         * the FSM is approximate, after all.
         */
        UnlockReleaseBuffer(buf);
 
        if (GetRecordedFreeSpace(vacrel->rel, blkno) == 0)
        {
            freespace = BLCKSZ - SizeOfPageHeaderData;
 
            RecordPageWithFreeSpace(vacrel->rel, blkno, freespace);
        }
 
        return true;
    }
 
    if (PageIsEmpty(page))
    {
        /*
         * It seems likely that caller will always be able to get a cleanup
         * lock on an empty page.  But don't take any chances -- escalate to
         * an exclusive lock (still don't need a cleanup lock, though).
         */
        if (sharelock)
        {
            LockBuffer(buf, BUFFER_LOCK_UNLOCK);
            LockBuffer(buf, BUFFER_LOCK_EXCLUSIVE);
 
            if (!PageIsEmpty(page))
            {
                /* page isn't new or empty -- keep lock and pin for now */
                return false;
            }
        }
        else
        {
            /* Already have a full cleanup lock (which is more than enough) */
        }
 
        /*
         * Unlike new pages, empty pages are always set all-visible and
         * all-frozen.
         */
        if (!PageIsAllVisible(page))
        {
            START_CRIT_SECTION();
 
            /* mark buffer dirty before writing a WAL record */
            MarkBufferDirty(buf);
 
            /*
             * It's possible that another backend has extended the heap,
             * initialized the page, and then failed to WAL-log the page due
             * to an ERROR.  Since heap extension is not WAL-logged, recovery
             * might try to replay our record setting the page all-visible and
             * find that the page isn't initialized, which will cause a PANIC.
             * To prevent that, check whether the page has been previously
             * WAL-logged, and if not, do that now.
             */
            if (RelationNeedsWAL(vacrel->rel) &&
                PageGetLSN(page) == InvalidXLogRecPtr)
                log_newpage_buffer(buf, true);
 
            PageSetAllVisible(page);
            visibilitymap_set(vacrel->rel, blkno, buf, InvalidXLogRecPtr,
                              vmbuffer, InvalidTransactionId,
                              VISIBILITYMAP_ALL_VISIBLE | VISIBILITYMAP_ALL_FROZEN);
            END_CRIT_SECTION();
        }
 
        freespace = PageGetHeapFreeSpace(page);
        UnlockReleaseBuffer(buf);
        RecordPageWithFreeSpace(vacrel->rel, blkno, freespace);
        return true;
    }
 
    /* page isn't new or empty -- keep lock and pin */
    return false;
}

References buf, BUFFER_LOCK_EXCLUSIVE, BUFFER_LOCK_UNLOCK, END_CRIT_SECTION, GetRecordedFreeSpace(), InvalidTransactionId, InvalidXLogRecPtr, LockBuffer(), log_newpage_buffer(), MarkBufferDirty(), PageGetHeapFreeSpace(), PageGetLSN(), PageIsAllVisible(), PageIsEmpty(), PageIsNew(), PageSetAllVisible(), RecordPageWithFreeSpace(), LVRelState::rel, RelationNeedsWAL, SizeOfPageHeaderData, START_CRIT_SECTION, UnlockReleaseBuffer(), VISIBILITYMAP_ALL_FROZEN, VISIBILITYMAP_ALL_VISIBLE, and visibilitymap_set().

Referenced by lazy_scan_heap().

lazy_scan_noprune()

static bool lazy_scan_noprune ( LVRelState *  vacrel, Buffer  buf, BlockNumber  blkno, Page  page, bool *  hastup, bool *  recordfreespace  )

static

Definition at line 1954 of file vacuumlazy.c.

{
    OffsetNumber offnum,
                maxoff;
    int         lpdead_items,
                live_tuples,
                recently_dead_tuples,
                missed_dead_tuples;
    HeapTupleHeader tupleheader;
    TransactionId NoFreezePageRelfrozenXid = vacrel->NewRelfrozenXid;
    MultiXactId NoFreezePageRelminMxid = vacrel->NewRelminMxid;
    OffsetNumber deadoffsets[MaxHeapTuplesPerPage];
 
    Assert(BufferGetBlockNumber(buf) == blkno);
 
    *hastup = false;            /* for now */
    *recordfreespace = false;   /* for now */
 
    lpdead_items = 0;
    live_tuples = 0;
    recently_dead_tuples = 0;
    missed_dead_tuples = 0;
 
    maxoff = PageGetMaxOffsetNumber(page);
    for (offnum = FirstOffsetNumber;
         offnum <= maxoff;
         offnum = OffsetNumberNext(offnum))
    {
        ItemId      itemid;
        HeapTupleData tuple;
 
        vacrel->offnum = offnum;
        itemid = PageGetItemId(page, offnum);
 
        if (!ItemIdIsUsed(itemid))
            continue;
 
        if (ItemIdIsRedirected(itemid))
        {
            *hastup = true;
            continue;
        }
 
        if (ItemIdIsDead(itemid))
        {
            /*
             * Deliberately don't set hastup=true here.  See same point in
             * lazy_scan_prune for an explanation.
             */
            deadoffsets[lpdead_items++] = offnum;
            continue;
        }
 
        *hastup = true;         /* page prevents rel truncation */
        tupleheader = (HeapTupleHeader) PageGetItem(page, itemid);
        if (heap_tuple_should_freeze(tupleheader, &vacrel->cutoffs,
                                     &NoFreezePageRelfrozenXid,
                                     &NoFreezePageRelminMxid))
        {
            /* Tuple with XID < FreezeLimit (or MXID < MultiXactCutoff) */
            if (vacrel->aggressive)
            {
                /*
                 * Aggressive VACUUMs must always be able to advance rel's
                 * relfrozenxid to a value >= FreezeLimit (and be able to
                 * advance rel's relminmxid to a value >= MultiXactCutoff).
                 * The ongoing aggressive VACUUM won't be able to do that
                 * unless it can freeze an XID (or MXID) from this tuple now.
                 *
                 * The only safe option is to have caller perform processing
                 * of this page using lazy_scan_prune.  Caller might have to
                 * wait a while for a cleanup lock, but it can't be helped.
                 */
                vacrel->offnum = InvalidOffsetNumber;
                return false;
            }
 
            /*
             * Non-aggressive VACUUMs are under no obligation to advance
             * relfrozenxid (even by one XID).  We can be much laxer here.
             *
             * Currently we always just accept an older final relfrozenxid
             * and/or relminmxid value.  We never make caller wait or work a
             * little harder, even when it likely makes sense to do so.
             */
        }
 
        ItemPointerSet(&(tuple.t_self), blkno, offnum);
        tuple.t_data = (HeapTupleHeader) PageGetItem(page, itemid);
        tuple.t_len = ItemIdGetLength(itemid);
        tuple.t_tableOid = RelationGetRelid(vacrel->rel);
 
        switch (HeapTupleSatisfiesVacuum(&tuple, vacrel->cutoffs.OldestXmin,
                                         buf))
        {
            case HEAPTUPLE_DELETE_IN_PROGRESS:
            case HEAPTUPLE_LIVE:
 
                /*
                 * Count both cases as live, just like lazy_scan_prune
                 */
                live_tuples++;
 
                break;
            case HEAPTUPLE_DEAD:
 
                /*
                 * There is some useful work for pruning to do, that won't be
                 * done due to failure to get a cleanup lock.
                 */
                missed_dead_tuples++;
                break;
            case HEAPTUPLE_RECENTLY_DEAD:
 
                /*
                 * Count in recently_dead_tuples, just like lazy_scan_prune
                 */
                recently_dead_tuples++;
                break;
            case HEAPTUPLE_INSERT_IN_PROGRESS:
 
                /*
                 * Do not count these rows as live, just like lazy_scan_prune
                 */
                break;
            default:
                elog(ERROR, "unexpected HeapTupleSatisfiesVacuum result");
                break;
        }
    }
 
    vacrel->offnum = InvalidOffsetNumber;
 
    /*
     * By here we know for sure that caller can put off freezing and pruning
     * this particular page until the next VACUUM.  Remember its details now.
     * (lazy_scan_prune expects a clean slate, so we have to do this last.)
     */
    vacrel->NewRelfrozenXid = NoFreezePageRelfrozenXid;
    vacrel->NewRelminMxid = NoFreezePageRelminMxid;
 
    /* Save any LP_DEAD items found on the page in dead_items array */
    if (vacrel->nindexes == 0)
    {
        /* Using one-pass strategy (since table has no indexes) */
        if (lpdead_items > 0)
        {
            /*
             * Perfunctory handling for the corner case where a single pass
             * strategy VACUUM cannot get a cleanup lock, and it turns out
             * that there is one or more LP_DEAD items: just count the LP_DEAD
             * items as missed_dead_tuples instead. (This is a bit dishonest,
             * but it beats having to maintain specialized heap vacuuming code
             * forever, for vanishingly little benefit.)
             */
            *hastup = true;
            missed_dead_tuples += lpdead_items;
        }
 
        *recordfreespace = true;
    }
    else if (lpdead_items == 0)
    {
        /*
         * Won't be vacuuming this page later, so record page's freespace in
         * the FSM now
         */
        *recordfreespace = true;
    }
    else
    {
        VacDeadItems *dead_items = vacrel->dead_items;
        ItemPointerData tmp;
 
        /*
         * Page has LP_DEAD items, and so any references/TIDs that remain in
         * indexes will be deleted during index vacuuming (and then marked
         * LP_UNUSED in the heap)
         */
        vacrel->lpdead_item_pages++;
 
        ItemPointerSetBlockNumber(&tmp, blkno);
 
        for (int i = 0; i < lpdead_items; i++)
        {
            ItemPointerSetOffsetNumber(&tmp, deadoffsets[i]);
            dead_items->items[dead_items->num_items++] = tmp;
        }
 
        Assert(dead_items->num_items <= dead_items->max_items);
        pgstat_progress_update_param(PROGRESS_VACUUM_NUM_DEAD_TUPLES,
                                     dead_items->num_items);
 
        vacrel->lpdead_items += lpdead_items;
 
        /*
         * Assume that we'll go on to vacuum this heap page during final pass
         * over the heap.  Don't record free space until then.
         */
        *recordfreespace = false;
    }
 
    /*
     * Finally, add relevant page-local counts to whole-VACUUM counts
     */
    vacrel->live_tuples += live_tuples;
    vacrel->recently_dead_tuples += recently_dead_tuples;
    vacrel->missed_dead_tuples += missed_dead_tuples;
    if (missed_dead_tuples > 0)
        vacrel->missed_dead_pages++;
 
    /* Caller won't need to call lazy_scan_prune with same page */
    return true;
}

References LVRelState::aggressive, Assert(), buf, BufferGetBlockNumber(), LVRelState::cutoffs, LVRelState::dead_items, elog(), ERROR, FirstOffsetNumber, heap_tuple_should_freeze(), HEAPTUPLE_DEAD, HEAPTUPLE_DELETE_IN_PROGRESS, HEAPTUPLE_INSERT_IN_PROGRESS, HEAPTUPLE_LIVE, HEAPTUPLE_RECENTLY_DEAD, HeapTupleSatisfiesVacuum(), i, InvalidOffsetNumber, ItemIdGetLength, ItemIdIsDead, ItemIdIsRedirected, ItemIdIsUsed, ItemPointerSet(), ItemPointerSetBlockNumber(), ItemPointerSetOffsetNumber(), VacDeadItems::items, LVRelState::live_tuples, LVRelState::lpdead_item_pages, LVRelState::lpdead_items, VacDeadItems::max_items, MaxHeapTuplesPerPage, LVRelState::missed_dead_pages, LVRelState::missed_dead_tuples, LVRelState::NewRelfrozenXid, LVRelState::NewRelminMxid, LVRelState::nindexes, VacDeadItems::num_items, LVRelState::offnum, OffsetNumberNext, VacuumCutoffs::OldestXmin, PageGetItem(), PageGetItemId(), PageGetMaxOffsetNumber(), pgstat_progress_update_param(), PROGRESS_VACUUM_NUM_DEAD_TUPLES, LVRelState::recently_dead_tuples, LVRelState::rel, RelationGetRelid, HeapTupleData::t_data, HeapTupleData::t_len, HeapTupleData::t_self, and HeapTupleData::t_tableOid.

Referenced by lazy_scan_heap().

lazy_scan_prune()

static void lazy_scan_prune ( LVRelState *  vacrel, Buffer  buf, BlockNumber  blkno, Page  page, LVPagePruneState *  prunestate  )

static

Definition at line 1535 of file vacuumlazy.c.

{
    Relation    rel = vacrel->rel;
    OffsetNumber offnum,
                maxoff;
    ItemId      itemid;
    HeapTupleData tuple;
    HTSV_Result res;
    PruneResult presult;
    int         tuples_frozen,
                lpdead_items,
                live_tuples,
                recently_dead_tuples;
    HeapPageFreeze pagefrz;
    int64       fpi_before = pgWalUsage.wal_fpi;
    OffsetNumber deadoffsets[MaxHeapTuplesPerPage];
    HeapTupleFreeze frozen[MaxHeapTuplesPerPage];
 
    Assert(BufferGetBlockNumber(buf) == blkno);
 
    /*
     * maxoff might be reduced following line pointer array truncation in
     * heap_page_prune.  That's safe for us to ignore, since the reclaimed
     * space will continue to look like LP_UNUSED items below.
     */
    maxoff = PageGetMaxOffsetNumber(page);
 
retry:
 
    /* Initialize (or reset) page-level state */
    pagefrz.freeze_required = false;
    pagefrz.FreezePageRelfrozenXid = vacrel->NewRelfrozenXid;
    pagefrz.FreezePageRelminMxid = vacrel->NewRelminMxid;
    pagefrz.NoFreezePageRelfrozenXid = vacrel->NewRelfrozenXid;
    pagefrz.NoFreezePageRelminMxid = vacrel->NewRelminMxid;
    tuples_frozen = 0;
    lpdead_items = 0;
    live_tuples = 0;
    recently_dead_tuples = 0;
 
    /*
     * Prune all HOT-update chains in this page.
     *
     * We count the number of tuples removed from the page by the pruning step
     * in presult.ndeleted. It should not be confused with lpdead_items;
     * lpdead_items's final value can be thought of as the number of tuples
     * that were deleted from indexes.
     */
    heap_page_prune(rel, buf, vacrel->vistest, &presult, &vacrel->offnum);
 
    /*
     * Now scan the page to collect LP_DEAD items and check for tuples
     * requiring freezing among remaining tuples with storage
     */
    prunestate->hastup = false;
    prunestate->has_lpdead_items = false;
    prunestate->all_visible = true;
    prunestate->all_frozen = true;
    prunestate->visibility_cutoff_xid = InvalidTransactionId;
 
    for (offnum = FirstOffsetNumber;
         offnum <= maxoff;
         offnum = OffsetNumberNext(offnum))
    {
        bool        totally_frozen;
 
        /*
         * Set the offset number so that we can display it along with any
         * error that occurred while processing this tuple.
         */
        vacrel->offnum = offnum;
        itemid = PageGetItemId(page, offnum);
 
        if (!ItemIdIsUsed(itemid))
            continue;
 
        /* Redirect items mustn't be touched */
        if (ItemIdIsRedirected(itemid))
        {
            /* page makes rel truncation unsafe */
            prunestate->hastup = true;
            continue;
        }
 
        if (ItemIdIsDead(itemid))
        {
            /*
             * Deliberately don't set hastup for LP_DEAD items.  We make the
             * soft assumption that any LP_DEAD items encountered here will
             * become LP_UNUSED later on, before count_nondeletable_pages is
             * reached.  If we don't make this assumption then rel truncation
             * will only happen every other VACUUM, at most.  Besides, VACUUM
             * must treat hastup/nonempty_pages as provisional no matter how
             * LP_DEAD items are handled (handled here, or handled later on).
             *
             * Also deliberately delay unsetting all_visible until just before
             * we return to lazy_scan_heap caller, as explained in full below.
             * (This is another case where it's useful to anticipate that any
             * LP_DEAD items will become LP_UNUSED during the ongoing VACUUM.)
             */
            deadoffsets[lpdead_items++] = offnum;
            continue;
        }
 
        Assert(ItemIdIsNormal(itemid));
 
        ItemPointerSet(&(tuple.t_self), blkno, offnum);
        tuple.t_data = (HeapTupleHeader) PageGetItem(page, itemid);
        tuple.t_len = ItemIdGetLength(itemid);
        tuple.t_tableOid = RelationGetRelid(rel);
 
        /*
         * DEAD tuples are almost always pruned into LP_DEAD line pointers by
         * heap_page_prune(), but it's possible that the tuple state changed
         * since heap_page_prune() looked.  Handle that here by restarting.
         * (See comments at the top of function for a full explanation.)
         */
        res = HeapTupleSatisfiesVacuum(&tuple, vacrel->cutoffs.OldestXmin,
                                       buf);
 
        if (unlikely(res == HEAPTUPLE_DEAD))
            goto retry;
 
        /*
         * The criteria for counting a tuple as live in this block need to
         * match what analyze.c's acquire_sample_rows() does, otherwise VACUUM
         * and ANALYZE may produce wildly different reltuples values, e.g.
         * when there are many recently-dead tuples.
         *
         * The logic here is a bit simpler than acquire_sample_rows(), as
         * VACUUM can't run inside a transaction block, which makes some cases
         * impossible (e.g. in-progress insert from the same transaction).
         *
         * We treat LP_DEAD items (which are the closest thing to DEAD tuples
         * that might be seen here) differently, too: we assume that they'll
         * become LP_UNUSED before VACUUM finishes.  This difference is only
         * superficial.  VACUUM effectively agrees with ANALYZE about DEAD
         * items, in the end.  VACUUM won't remember LP_DEAD items, but only
         * because they're not supposed to be left behind when it is done.
         * (Cases where we bypass index vacuuming will violate this optimistic
         * assumption, but the overall impact of that should be negligible.)
         */
        switch (res)
        {
            case HEAPTUPLE_LIVE:
 
                /*
                 * Count it as live.  Not only is this natural, but it's also
                 * what acquire_sample_rows() does.
                 */
                live_tuples++;
 
                /*
                 * Is the tuple definitely visible to all transactions?
                 *
                 * NB: Like with per-tuple hint bits, we can't set the
                 * PD_ALL_VISIBLE flag if the inserter committed
                 * asynchronously. See SetHintBits for more info. Check that
                 * the tuple is hinted xmin-committed because of that.
                 */
                if (prunestate->all_visible)
                {
                    TransactionId xmin;
 
                    if (!HeapTupleHeaderXminCommitted(tuple.t_data))
                    {
                        prunestate->all_visible = false;
                        break;
                    }
 
                    /*
                     * The inserter definitely committed. But is it old enough
                     * that everyone sees it as committed?
                     */
                    xmin = HeapTupleHeaderGetXmin(tuple.t_data);
                    if (!TransactionIdPrecedes(xmin,
                                               vacrel->cutoffs.OldestXmin))
                    {
                        prunestate->all_visible = false;
                        break;
                    }
 
                    /* Track newest xmin on page. */
                    if (TransactionIdFollows(xmin, prunestate->visibility_cutoff_xid) &&
                        TransactionIdIsNormal(xmin))
                        prunestate->visibility_cutoff_xid = xmin;
                }
                break;
            case HEAPTUPLE_RECENTLY_DEAD:
 
                /*
                 * If tuple is recently dead then we must not remove it from
                 * the relation.  (We only remove items that are LP_DEAD from
                 * pruning.)
                 */
                recently_dead_tuples++;
                prunestate->all_visible = false;
                break;
            case HEAPTUPLE_INSERT_IN_PROGRESS:
 
                /*
                 * We do not count these rows as live, because we expect the
                 * inserting transaction to update the counters at commit, and
                 * we assume that will happen only after we report our
                 * results.  This assumption is a bit shaky, but it is what
                 * acquire_sample_rows() does, so be consistent.
                 */
                prunestate->all_visible = false;
                break;
            case HEAPTUPLE_DELETE_IN_PROGRESS:
                /* This is an expected case during concurrent vacuum */
                prunestate->all_visible = false;
 
                /*
                 * Count such rows as live.  As above, we assume the deleting
                 * transaction will commit and update the counters after we
                 * report.
                 */
                live_tuples++;
                break;
            default:
                elog(ERROR, "unexpected HeapTupleSatisfiesVacuum result");
                break;
        }
 
        prunestate->hastup = true;  /* page makes rel truncation unsafe */
 
        /* Tuple with storage -- consider need to freeze */
        if (heap_prepare_freeze_tuple(tuple.t_data, &vacrel->cutoffs, &pagefrz,
                                      &frozen[tuples_frozen], &totally_frozen))
        {
            /* Save prepared freeze plan for later */
            frozen[tuples_frozen++].offset = offnum;
        }
 
        /*
         * If any tuple isn't either totally frozen already or eligible to
         * become totally frozen (according to its freeze plan), then the page
         * definitely cannot be set all-frozen in the visibility map later on
         */
        if (!totally_frozen)
            prunestate->all_frozen = false;
    }
 
    /*
     * We have now divided every item on the page into either an LP_DEAD item
     * that will need to be vacuumed in indexes later, or a LP_NORMAL tuple
     * that remains and needs to be considered for freezing now (LP_UNUSED and
     * LP_REDIRECT items also remain, but are of no further interest to us).
     */
    vacrel->offnum = InvalidOffsetNumber;
 
    /*
     * Freeze the page when heap_prepare_freeze_tuple indicates that at least
     * one XID/MXID from before FreezeLimit/MultiXactCutoff is present.  Also
     * freeze when pruning generated an FPI, if doing so means that we set the
     * page all-frozen afterwards (might not happen until final heap pass).
     */
    if (pagefrz.freeze_required || tuples_frozen == 0 ||
        (prunestate->all_visible && prunestate->all_frozen &&
         fpi_before != pgWalUsage.wal_fpi))
    {
        /*
         * We're freezing the page.  Our final NewRelfrozenXid doesn't need to
         * be affected by the XIDs that are just about to be frozen anyway.
         */
        vacrel->NewRelfrozenXid = pagefrz.FreezePageRelfrozenXid;
        vacrel->NewRelminMxid = pagefrz.FreezePageRelminMxid;
 
        if (tuples_frozen == 0)
        {
            /*
             * We have no freeze plans to execute, so there's no added cost
             * from following the freeze path.  That's why it was chosen. This
             * is important in the case where the page only contains totally
             * frozen tuples at this point (perhaps only following pruning).
             * Such pages can be marked all-frozen in the VM by our caller,
             * even though none of its tuples were newly frozen here (note
             * that the "no freeze" path never sets pages all-frozen).
             *
             * We never increment the frozen_pages instrumentation counter
             * here, since it only counts pages with newly frozen tuples
             * (don't confuse that with pages newly set all-frozen in VM).
             */
        }
        else
        {
            TransactionId snapshotConflictHorizon;
 
            vacrel->frozen_pages++;
 
            /*
             * We can use visibility_cutoff_xid as our cutoff for conflicts
             * when the whole page is eligible to become all-frozen in the VM
             * once we're done with it.  Otherwise we generate a conservative
             * cutoff by stepping back from OldestXmin.
             */
            if (prunestate->all_visible && prunestate->all_frozen)
            {
                /* Using same cutoff when setting VM is now unnecessary */
                snapshotConflictHorizon = prunestate->visibility_cutoff_xid;
                prunestate->visibility_cutoff_xid = InvalidTransactionId;
            }
            else
            {
                /* Avoids false conflicts when hot_standby_feedback in use */
                snapshotConflictHorizon = vacrel->cutoffs.OldestXmin;
                TransactionIdRetreat(snapshotConflictHorizon);
            }
 
            /* Execute all freeze plans for page as a single atomic action */
            heap_freeze_execute_prepared(vacrel->rel, buf,
                                         snapshotConflictHorizon,
                                         frozen, tuples_frozen);
        }
    }
    else
    {
        /*
         * Page requires "no freeze" processing.  It might be set all-visible
         * in the visibility map, but it can never be set all-frozen.
         */
        vacrel->NewRelfrozenXid = pagefrz.NoFreezePageRelfrozenXid;
        vacrel->NewRelminMxid = pagefrz.NoFreezePageRelminMxid;
        prunestate->all_frozen = false;
        tuples_frozen = 0;      /* avoid miscounts in instrumentation */
    }
 
    /*
     * VACUUM will call heap_page_is_all_visible() during the second pass over
     * the heap to determine all_visible and all_frozen for the page -- this
     * is a specialized version of the logic from this function.  Now that
     * we've finished pruning and freezing, make sure that we're in total
     * agreement with heap_page_is_all_visible() using an assertion.
     */
#ifdef USE_ASSERT_CHECKING
    /* Note that all_frozen value does not matter when !all_visible */
    if (prunestate->all_visible && lpdead_items == 0)
    {
        TransactionId cutoff;
        bool        all_frozen;
 
        if (!heap_page_is_all_visible(vacrel, buf, &cutoff, &all_frozen))
            Assert(false);
 
        Assert(!TransactionIdIsValid(cutoff) ||
               cutoff == prunestate->visibility_cutoff_xid);
    }
#endif
 
    /*
     * Now save details of the LP_DEAD items from the page in vacrel
     */
    if (lpdead_items > 0)
    {
        VacDeadItems *dead_items = vacrel->dead_items;
        ItemPointerData tmp;
 
        vacrel->lpdead_item_pages++;
        prunestate->has_lpdead_items = true;
 
        ItemPointerSetBlockNumber(&tmp, blkno);
 
        for (int i = 0; i < lpdead_items; i++)
        {
            ItemPointerSetOffsetNumber(&tmp, deadoffsets[i]);
            dead_items->items[dead_items->num_items++] = tmp;
        }
 
        Assert(dead_items->num_items <= dead_items->max_items);
        pgstat_progress_update_param(PROGRESS_VACUUM_NUM_DEAD_TUPLES,
                                     dead_items->num_items);
 
        /*
         * It was convenient to ignore LP_DEAD items in all_visible earlier on
         * to make the choice of whether or not to freeze the page unaffected
         * by the short-term presence of LP_DEAD items.  These LP_DEAD items
         * were effectively assumed to be LP_UNUSED items in the making.  It
         * doesn't matter which heap pass (initial pass or final pass) ends up
         * setting the page all-frozen, as long as the ongoing VACUUM does it.
         *
         * Now that freezing has been finalized, unset all_visible.  It needs
         * to reflect the present state of things, as expected by our caller.
         */
        prunestate->all_visible = false;
    }
 
    /* Finally, add page-local counts to whole-VACUUM counts */
    vacrel->tuples_deleted += presult.ndeleted;
    vacrel->tuples_frozen += tuples_frozen;
    vacrel->lpdead_items += lpdead_items;
    vacrel->live_tuples += live_tuples;
    vacrel->recently_dead_tuples += recently_dead_tuples;
}

References LVPagePruneState::all_frozen, LVPagePruneState::all_visible, Assert(), buf, BufferGetBlockNumber(), LVRelState::cutoffs, LVRelState::dead_items, elog(), ERROR, FirstOffsetNumber, HeapPageFreeze::freeze_required, HeapPageFreeze::FreezePageRelfrozenXid, HeapPageFreeze::FreezePageRelminMxid, LVRelState::frozen_pages, LVPagePruneState::has_lpdead_items, LVPagePruneState::hastup, heap_freeze_execute_prepared(), heap_page_is_all_visible(), heap_page_prune(), heap_prepare_freeze_tuple(), HEAPTUPLE_DEAD, HEAPTUPLE_DELETE_IN_PROGRESS, HEAPTUPLE_INSERT_IN_PROGRESS, HEAPTUPLE_LIVE, HEAPTUPLE_RECENTLY_DEAD, HeapTupleHeaderGetXmin, HeapTupleHeaderXminCommitted, HeapTupleSatisfiesVacuum(), i, InvalidOffsetNumber, InvalidTransactionId, ItemIdGetLength, ItemIdIsDead, ItemIdIsNormal, ItemIdIsRedirected, ItemIdIsUsed, ItemPointerSet(), ItemPointerSetBlockNumber(), ItemPointerSetOffsetNumber(), VacDeadItems::items, LVRelState::live_tuples, LVRelState::lpdead_item_pages, LVRelState::lpdead_items, VacDeadItems::max_items, MaxHeapTuplesPerPage, PruneResult::ndeleted, LVRelState::NewRelfrozenXid, LVRelState::NewRelminMxid, HeapPageFreeze::NoFreezePageRelfrozenXid, HeapPageFreeze::NoFreezePageRelminMxid, VacDeadItems::num_items, LVRelState::offnum, HeapTupleFreeze::offset, OffsetNumberNext, VacuumCutoffs::OldestXmin, PageGetItem(), PageGetItemId(), PageGetMaxOffsetNumber(), pgstat_progress_update_param(), pgWalUsage, PROGRESS_VACUUM_NUM_DEAD_TUPLES, LVRelState::recently_dead_tuples, LVRelState::rel, RelationGetRelid, res, HeapTupleData::t_data, HeapTupleData::t_len, HeapTupleData::t_self, HeapTupleData::t_tableOid, TransactionIdFollows(), TransactionIdIsNormal, TransactionIdIsValid, TransactionIdPrecedes(), TransactionIdRetreat, LVRelState::tuples_deleted, LVRelState::tuples_frozen, unlikely, LVPagePruneState::visibility_cutoff_xid, LVRelState::vistest, and WalUsage::wal_fpi.

Referenced by lazy_scan_heap().

lazy_scan_skip()

static BlockNumber lazy_scan_skip ( LVRelState *  vacrel, Buffer *  vmbuffer, BlockNumber  next_block, bool *  next_unskippable_allvis, bool *  skipping_current_range  )

static

Definition at line 1296 of file vacuumlazy.c.

{
    BlockNumber rel_pages = vacrel->rel_pages,
                next_unskippable_block = next_block,
                nskippable_blocks = 0;
    bool        skipsallvis = false;
 
    *next_unskippable_allvis = true;
    while (next_unskippable_block < rel_pages)
    {
        uint8       mapbits = visibilitymap_get_status(vacrel->rel,
                                                       next_unskippable_block,
                                                       vmbuffer);
 
        if ((mapbits & VISIBILITYMAP_ALL_VISIBLE) == 0)
        {
            Assert((mapbits & VISIBILITYMAP_ALL_FROZEN) == 0);
            *next_unskippable_allvis = false;
            break;
        }
 
        /*
         * Caller must scan the last page to determine whether it has tuples
         * (caller must have the opportunity to set vacrel->nonempty_pages).
         * This rule avoids having lazy_truncate_heap() take access-exclusive
         * lock on rel to attempt a truncation that fails anyway, just because
         * there are tuples on the last page (it is likely that there will be
         * tuples on other nearby pages as well, but those can be skipped).
         *
         * Implement this by always treating the last block as unsafe to skip.
         */
        if (next_unskippable_block == rel_pages - 1)
            break;
 
        /* DISABLE_PAGE_SKIPPING makes all skipping unsafe */
        if (!vacrel->skipwithvm)
        {
            /* Caller shouldn't rely on all_visible_according_to_vm */
            *next_unskippable_allvis = false;
            break;
        }
 
        /*
         * Aggressive VACUUM caller can't skip pages just because they are
         * all-visible.  They may still skip all-frozen pages, which can't
         * contain XIDs < OldestXmin (XIDs that aren't already frozen by now).
         */
        if ((mapbits & VISIBILITYMAP_ALL_FROZEN) == 0)
        {
            if (vacrel->aggressive)
                break;
 
            /*
             * All-visible block is safe to skip in non-aggressive case.  But
             * remember that the final range contains such a block for later.
             */
            skipsallvis = true;
        }
 
        vacuum_delay_point();
        next_unskippable_block++;
        nskippable_blocks++;
    }
 
    /*
     * We only skip a range with at least SKIP_PAGES_THRESHOLD consecutive
     * pages.  Since we're reading sequentially, the OS should be doing
     * readahead for us, so there's no gain in skipping a page now and then.
     * Skipping such a range might even discourage sequential detection.
     *
     * This test also enables more frequent relfrozenxid advancement during
     * non-aggressive VACUUMs.  If the range has any all-visible pages then
     * skipping makes updating relfrozenxid unsafe, which is a real downside.
     */
    if (nskippable_blocks < SKIP_PAGES_THRESHOLD)
        *skipping_current_range = false;
    else
    {
        *skipping_current_range = true;
        if (skipsallvis)
            vacrel->skippedallvis = true;
    }
 
    return next_unskippable_block;
}

References LVRelState::aggressive, Assert(), LVRelState::rel, LVRelState::rel_pages, SKIP_PAGES_THRESHOLD, LVRelState::skippedallvis, LVRelState::skipwithvm, vacuum_delay_point(), VISIBILITYMAP_ALL_FROZEN, VISIBILITYMAP_ALL_VISIBLE, and visibilitymap_get_status().

Referenced by lazy_scan_heap().

lazy_truncate_heap()

static void lazy_truncate_heap ( LVRelState *  vacrel )

static

Definition at line 2885 of file vacuumlazy.c.

{
    BlockNumber orig_rel_pages = vacrel->rel_pages;
    BlockNumber new_rel_pages;
    bool        lock_waiter_detected;
    int         lock_retry;
 
    /* Report that we are now truncating */
    pgstat_progress_update_param(PROGRESS_VACUUM_PHASE,
                                 PROGRESS_VACUUM_PHASE_TRUNCATE);
 
    /* Update error traceback information one last time */
    update_vacuum_error_info(vacrel, NULL, VACUUM_ERRCB_PHASE_TRUNCATE,
                             vacrel->nonempty_pages, InvalidOffsetNumber);
 
    /*
     * Loop until no more truncating can be done.
     */
    do
    {
        /*
         * We need full exclusive lock on the relation in order to do
         * truncation. If we can't get it, give up rather than waiting --- we
         * don't want to block other backends, and we don't want to deadlock
         * (which is quite possible considering we already hold a lower-grade
         * lock).
         */
        lock_waiter_detected = false;
        lock_retry = 0;
        while (true)
        {
            if (ConditionalLockRelation(vacrel->rel, AccessExclusiveLock))
                break;
 
            /*
             * Check for interrupts while trying to (re-)acquire the exclusive
             * lock.
             */
            CHECK_FOR_INTERRUPTS();
 
            if (++lock_retry > (VACUUM_TRUNCATE_LOCK_TIMEOUT /
                                VACUUM_TRUNCATE_LOCK_WAIT_INTERVAL))
            {
                /*
                 * We failed to establish the lock in the specified number of
                 * retries. This means we give up truncating.
                 */
                ereport(vacrel->verbose ? INFO : DEBUG2,
                        (errmsg("\"%s\": stopping truncate due to conflicting lock request",
                                vacrel->relname)));
                return;
            }
 
            (void) WaitLatch(MyLatch,
                             WL_LATCH_SET | WL_TIMEOUT | WL_EXIT_ON_PM_DEATH,
                             VACUUM_TRUNCATE_LOCK_WAIT_INTERVAL,
                             WAIT_EVENT_VACUUM_TRUNCATE);
            ResetLatch(MyLatch);
        }
 
        /*
         * Now that we have exclusive lock, look to see if the rel has grown
         * whilst we were vacuuming with non-exclusive lock.  If so, give up;
         * the newly added pages presumably contain non-deletable tuples.
         */
        new_rel_pages = RelationGetNumberOfBlocks(vacrel->rel);
        if (new_rel_pages != orig_rel_pages)
        {
            /*
             * Note: we intentionally don't update vacrel->rel_pages with the
             * new rel size here.  If we did, it would amount to assuming that
             * the new pages are empty, which is unlikely. Leaving the numbers
             * alone amounts to assuming that the new pages have the same
             * tuple density as existing ones, which is less unlikely.
             */
            UnlockRelation(vacrel->rel, AccessExclusiveLock);
            return;
        }
 
        /*
         * Scan backwards from the end to verify that the end pages actually
         * contain no tuples.  This is *necessary*, not optional, because
         * other backends could have added tuples to these pages whilst we
         * were vacuuming.
         */
        new_rel_pages = count_nondeletable_pages(vacrel, &lock_waiter_detected);
        vacrel->blkno = new_rel_pages;
 
        if (new_rel_pages >= orig_rel_pages)
        {
            /* can't do anything after all */
            UnlockRelation(vacrel->rel, AccessExclusiveLock);
            return;
        }
 
        /*
         * Okay to truncate.
         */
        RelationTruncate(vacrel->rel, new_rel_pages);
 
        /*
         * We can release the exclusive lock as soon as we have truncated.
         * Other backends can't safely access the relation until they have
         * processed the smgr invalidation that smgrtruncate sent out ... but
         * that should happen as part of standard invalidation processing once
         * they acquire lock on the relation.
         */
        UnlockRelation(vacrel->rel, AccessExclusiveLock);
 
        /*
         * Update statistics.  Here, it *is* correct to adjust rel_pages
         * without also touching reltuples, since the tuple count wasn't
         * changed by the truncation.
         */
        vacrel->removed_pages += orig_rel_pages - new_rel_pages;
        vacrel->rel_pages = new_rel_pages;
 
        ereport(vacrel->verbose ? INFO : DEBUG2,
                (errmsg("table \"%s\": truncated %u to %u pages",
                        vacrel->relname,
                        orig_rel_pages, new_rel_pages)));
        orig_rel_pages = new_rel_pages;
    } while (new_rel_pages > vacrel->nonempty_pages && lock_waiter_detected);
}

References AccessExclusiveLock, LVRelState::blkno, CHECK_FOR_INTERRUPTS, ConditionalLockRelation(), count_nondeletable_pages(), DEBUG2, ereport, errmsg(), INFO, InvalidOffsetNumber, MyLatch, LVRelState::nonempty_pages, pgstat_progress_update_param(), PROGRESS_VACUUM_PHASE, PROGRESS_VACUUM_PHASE_TRUNCATE, LVRelState::rel, LVRelState::rel_pages, RelationGetNumberOfBlocks, RelationTruncate(), LVRelState::relname, LVRelState::removed_pages, ResetLatch(), UnlockRelation(), update_vacuum_error_info(), VACUUM_ERRCB_PHASE_TRUNCATE, VACUUM_TRUNCATE_LOCK_TIMEOUT, VACUUM_TRUNCATE_LOCK_WAIT_INTERVAL, LVRelState::verbose, WaitLatch(), WL_EXIT_ON_PM_DEATH, WL_LATCH_SET, and WL_TIMEOUT.

Referenced by heap_vacuum_rel().

lazy_vacuum()

static void lazy_vacuum ( LVRelState *  vacrel )

static

Definition at line 2188 of file vacuumlazy.c.

{
    bool        bypass;
 
    /* Should not end up here with no indexes */
    Assert(vacrel->nindexes > 0);
    Assert(vacrel->lpdead_item_pages > 0);
 
    if (!vacrel->do_index_vacuuming)
    {
        Assert(!vacrel->do_index_cleanup);
        vacrel->dead_items->num_items = 0;
        return;
    }
 
    /*
     * Consider bypassing index vacuuming (and heap vacuuming) entirely.
     *
     * We currently only do this in cases where the number of LP_DEAD items
     * for the entire VACUUM operation is close to zero.  This avoids sharp
     * discontinuities in the duration and overhead of successive VACUUM
     * operations that run against the same table with a fixed workload.
     * Ideally, successive VACUUM operations will behave as if there are
     * exactly zero LP_DEAD items in cases where there are close to zero.
     *
     * This is likely to be helpful with a table that is continually affected
     * by UPDATEs that can mostly apply the HOT optimization, but occasionally
     * have small aberrations that lead to just a few heap pages retaining
     * only one or two LP_DEAD items.  This is pretty common; even when the
     * DBA goes out of their way to make UPDATEs use HOT, it is practically
     * impossible to predict whether HOT will be applied in 100% of cases.
     * It's far easier to ensure that 99%+ of all UPDATEs against a table use
     * HOT through careful tuning.
     */
    bypass = false;
    if (vacrel->consider_bypass_optimization && vacrel->rel_pages > 0)
    {
        BlockNumber threshold;
 
        Assert(vacrel->num_index_scans == 0);
        Assert(vacrel->lpdead_items == vacrel->dead_items->num_items);
        Assert(vacrel->do_index_vacuuming);
        Assert(vacrel->do_index_cleanup);
 
        /*
         * This crossover point at which we'll start to do index vacuuming is
         * expressed as a percentage of the total number of heap pages in the
         * table that are known to have at least one LP_DEAD item.  This is
         * much more important than the total number of LP_DEAD items, since
         * it's a proxy for the number of heap pages whose visibility map bits
         * cannot be set on account of bypassing index and heap vacuuming.
         *
         * We apply one further precautionary test: the space currently used
         * to store the TIDs (TIDs that now all point to LP_DEAD items) must
         * not exceed 32MB.  This limits the risk that we will bypass index
         * vacuuming again and again until eventually there is a VACUUM whose
         * dead_items space is not CPU cache resident.
         *
         * We don't take any special steps to remember the LP_DEAD items (such
         * as counting them in our final update to the stats system) when the
         * optimization is applied.  Though the accounting used in analyze.c's
         * acquire_sample_rows() will recognize the same LP_DEAD items as dead
         * rows in its own stats report, that's okay. The discrepancy should
         * be negligible.  If this optimization is ever expanded to cover more
         * cases then this may need to be reconsidered.
         */
        threshold = (double) vacrel->rel_pages * BYPASS_THRESHOLD_PAGES;
        bypass = (vacrel->lpdead_item_pages < threshold &&
                  vacrel->lpdead_items < MAXDEADITEMS(32L * 1024L * 1024L));
    }
 
    if (bypass)
    {
        /*
         * There are almost zero TIDs.  Behave as if there were precisely
         * zero: bypass index vacuuming, but do index cleanup.
         *
         * We expect that the ongoing VACUUM operation will finish very
         * quickly, so there is no point in considering speeding up as a
         * failsafe against wraparound failure. (Index cleanup is expected to
         * finish very quickly in cases where there were no ambulkdelete()
         * calls.)
         */
        vacrel->do_index_vacuuming = false;
    }
    else if (lazy_vacuum_all_indexes(vacrel))
    {
        /*
         * We successfully completed a round of index vacuuming.  Do related
         * heap vacuuming now.
         */
        lazy_vacuum_heap_rel(vacrel);
    }
    else
    {
        /*
         * Failsafe case.
         *
         * We attempted index vacuuming, but didn't finish a full round/full
         * index scan.  This happens when relfrozenxid or relminmxid is too
         * far in the past.
         *
         * From this point on the VACUUM operation will do no further index
         * vacuuming or heap vacuuming.  This VACUUM operation won't end up
         * back here again.
         */
        Assert(VacuumFailsafeActive);
    }
 
    /*
     * Forget the LP_DEAD items that we just vacuumed (or just decided to not
     * vacuum)
     */
    vacrel->dead_items->num_items = 0;
}

References Assert(), BYPASS_THRESHOLD_PAGES, LVRelState::consider_bypass_optimization, LVRelState::dead_items, LVRelState::do_index_cleanup, LVRelState::do_index_vacuuming, lazy_vacuum_all_indexes(), lazy_vacuum_heap_rel(), LVRelState::lpdead_item_pages, LVRelState::lpdead_items, MAXDEADITEMS, LVRelState::nindexes, LVRelState::num_index_scans, VacDeadItems::num_items, LVRelState::rel_pages, and VacuumFailsafeActive.

Referenced by lazy_scan_heap().

lazy_vacuum_all_indexes()

static bool lazy_vacuum_all_indexes ( LVRelState *  vacrel )

static

Definition at line 2313 of file vacuumlazy.c.

{
    bool        allindexes = true;
    double      old_live_tuples = vacrel->rel->rd_rel->reltuples;
    const int   progress_start_index[] = {
        PROGRESS_VACUUM_PHASE,
        PROGRESS_VACUUM_INDEXES_TOTAL
    };
    const int   progress_end_index[] = {
        PROGRESS_VACUUM_INDEXES_TOTAL,
        PROGRESS_VACUUM_INDEXES_PROCESSED,
        PROGRESS_VACUUM_NUM_INDEX_VACUUMS
    };
    int64       progress_start_val[2];
    int64       progress_end_val[3];
 
    Assert(vacrel->nindexes > 0);
    Assert(vacrel->do_index_vacuuming);
    Assert(vacrel->do_index_cleanup);
 
    /* Precheck for XID wraparound emergencies */
    if (lazy_check_wraparound_failsafe(vacrel))
    {
        /* Wraparound emergency -- don't even start an index scan */
        return false;
    }
 
    /*
     * Report that we are now vacuuming indexes and the number of indexes to
     * vacuum.
     */
    progress_start_val[0] = PROGRESS_VACUUM_PHASE_VACUUM_INDEX;
    progress_start_val[1] = vacrel->nindexes;
    pgstat_progress_update_multi_param(2, progress_start_index, progress_start_val);
 
    if (!ParallelVacuumIsActive(vacrel))
    {
        for (int idx = 0; idx < vacrel->nindexes; idx++)
        {
            Relation    indrel = vacrel->indrels[idx];
            IndexBulkDeleteResult *istat = vacrel->indstats[idx];
 
            vacrel->indstats[idx] = lazy_vacuum_one_index(indrel, istat,
                                                          old_live_tuples,
                                                          vacrel);
 
            /* Report the number of indexes vacuumed */
            pgstat_progress_update_param(PROGRESS_VACUUM_INDEXES_PROCESSED,
                                         idx + 1);
 
            if (lazy_check_wraparound_failsafe(vacrel))
            {
                /* Wraparound emergency -- end current index scan */
                allindexes = false;
                break;
            }
        }
    }
    else
    {
        /* Outsource everything to parallel variant */
        parallel_vacuum_bulkdel_all_indexes(vacrel->pvs, old_live_tuples,
                                            vacrel->num_index_scans);
 
        /*
         * Do a postcheck to consider applying wraparound failsafe now.  Note
         * that parallel VACUUM only gets the precheck and this postcheck.
         */
        if (lazy_check_wraparound_failsafe(vacrel))
            allindexes = false;
    }
 
    /*
     * We delete all LP_DEAD items from the first heap pass in all indexes on
     * each call here (except calls where we choose to do the failsafe). This
     * makes the next call to lazy_vacuum_heap_rel() safe (except in the event
     * of the failsafe triggering, which prevents the next call from taking
     * place).
     */
    Assert(vacrel->num_index_scans > 0 ||
           vacrel->dead_items->num_items == vacrel->lpdead_items);
    Assert(allindexes || VacuumFailsafeActive);
 
    /*
     * Increase and report the number of index scans.  Also, we reset
     * PROGRESS_VACUUM_INDEXES_TOTAL and PROGRESS_VACUUM_INDEXES_PROCESSED.
     *
     * We deliberately include the case where we started a round of bulk
     * deletes that we weren't able to finish due to the failsafe triggering.
     */
    vacrel->num_index_scans++;
    progress_end_val[0] = 0;
    progress_end_val[1] = 0;
    progress_end_val[2] = vacrel->num_index_scans;
    pgstat_progress_update_multi_param(3, progress_end_index, progress_end_val);
 
    return allindexes;
}

References Assert(), LVRelState::dead_items, LVRelState::do_index_cleanup, LVRelState::do_index_vacuuming, idx(), LVRelState::indrels, LVRelState::indstats, lazy_check_wraparound_failsafe(), lazy_vacuum_one_index(), LVRelState::lpdead_items, LVRelState::nindexes, LVRelState::num_index_scans, VacDeadItems::num_items, parallel_vacuum_bulkdel_all_indexes(), ParallelVacuumIsActive, pgstat_progress_update_multi_param(), pgstat_progress_update_param(), PROGRESS_VACUUM_INDEXES_PROCESSED, PROGRESS_VACUUM_INDEXES_TOTAL, PROGRESS_VACUUM_NUM_INDEX_VACUUMS, PROGRESS_VACUUM_PHASE, PROGRESS_VACUUM_PHASE_VACUUM_INDEX, LVRelState::pvs, RelationData::rd_rel, LVRelState::rel, and VacuumFailsafeActive.

Referenced by lazy_vacuum().

lazy_vacuum_heap_page()

static int lazy_vacuum_heap_page ( LVRelState *  vacrel, BlockNumber  blkno, Buffer  buffer, int  index, Buffer  vmbuffer  )

static

Definition at line 2519 of file vacuumlazy.c.

{
    VacDeadItems *dead_items = vacrel->dead_items;
    Page        page = BufferGetPage(buffer);
    OffsetNumber unused[MaxHeapTuplesPerPage];
    int         nunused = 0;
    TransactionId visibility_cutoff_xid;
    bool        all_frozen;
    LVSavedErrInfo saved_err_info;
 
    Assert(vacrel->nindexes == 0 || vacrel->do_index_vacuuming);
 
    pgstat_progress_update_param(PROGRESS_VACUUM_HEAP_BLKS_VACUUMED, blkno);
 
    /* Update error traceback information */
    update_vacuum_error_info(vacrel, &saved_err_info,
                             VACUUM_ERRCB_PHASE_VACUUM_HEAP, blkno,
                             InvalidOffsetNumber);
 
    START_CRIT_SECTION();
 
    for (; index < dead_items->num_items; index++)
    {
        BlockNumber tblk;
        OffsetNumber toff;
        ItemId      itemid;
 
        tblk = ItemPointerGetBlockNumber(&dead_items->items[index]);
        if (tblk != blkno)
            break;              /* past end of tuples for this block */
        toff = ItemPointerGetOffsetNumber(&dead_items->items[index]);
        itemid = PageGetItemId(page, toff);
 
        Assert(ItemIdIsDead(itemid) && !ItemIdHasStorage(itemid));
        ItemIdSetUnused(itemid);
        unused[nunused++] = toff;
    }
 
    Assert(nunused > 0);
 
    /* Attempt to truncate line pointer array now */
    PageTruncateLinePointerArray(page);
 
    /*
     * Mark buffer dirty before we write WAL.
     */
    MarkBufferDirty(buffer);
 
    /* XLOG stuff */
    if (RelationNeedsWAL(vacrel->rel))
    {
        xl_heap_vacuum xlrec;
        XLogRecPtr  recptr;
 
        xlrec.nunused = nunused;
 
        XLogBeginInsert();
        XLogRegisterData((char *) &xlrec, SizeOfHeapVacuum);
 
        XLogRegisterBuffer(0, buffer, REGBUF_STANDARD);
        XLogRegisterBufData(0, (char *) unused, nunused * sizeof(OffsetNumber));
 
        recptr = XLogInsert(RM_HEAP2_ID, XLOG_HEAP2_VACUUM);
 
        PageSetLSN(page, recptr);
    }
 
    /*
     * End critical section, so we safely can do visibility tests (which
     * possibly need to perform IO and allocate memory!). If we crash now the
     * page (including the corresponding vm bit) might not be marked all
     * visible, but that's fine. A later vacuum will fix that.
     */
    END_CRIT_SECTION();
 
    /*
     * Now that we have removed the LP_DEAD items from the page, once again
     * check if the page has become all-visible.  The page is already marked
     * dirty, exclusively locked, and, if needed, a full page image has been
     * emitted.
     */
    Assert(!PageIsAllVisible(page));
    if (heap_page_is_all_visible(vacrel, buffer, &visibility_cutoff_xid,
                                 &all_frozen))
    {
        uint8       flags = VISIBILITYMAP_ALL_VISIBLE;
 
        if (all_frozen)
        {
            Assert(!TransactionIdIsValid(visibility_cutoff_xid));
            flags |= VISIBILITYMAP_ALL_FROZEN;
        }
 
        PageSetAllVisible(page);
        visibilitymap_set(vacrel->rel, blkno, buffer, InvalidXLogRecPtr,
                          vmbuffer, visibility_cutoff_xid, flags);
    }
 
    /* Revert to the previous phase information for error traceback */
    restore_vacuum_error_info(vacrel, &saved_err_info);
    return index;
}

References Assert(), BufferGetPage(), LVRelState::dead_items, LVRelState::do_index_vacuuming, END_CRIT_SECTION, heap_page_is_all_visible(), InvalidOffsetNumber, InvalidXLogRecPtr, ItemIdHasStorage, ItemIdIsDead, ItemIdSetUnused, ItemPointerGetBlockNumber(), ItemPointerGetOffsetNumber(), VacDeadItems::items, MarkBufferDirty(), MaxHeapTuplesPerPage, LVRelState::nindexes, VacDeadItems::num_items, xl_heap_vacuum::nunused, PageGetItemId(), PageIsAllVisible(), PageSetAllVisible(), PageSetLSN(), PageTruncateLinePointerArray(), pgstat_progress_update_param(), PROGRESS_VACUUM_HEAP_BLKS_VACUUMED, REGBUF_STANDARD, LVRelState::rel, RelationNeedsWAL, restore_vacuum_error_info(), SizeOfHeapVacuum, START_CRIT_SECTION, TransactionIdIsValid, update_vacuum_error_info(), VACUUM_ERRCB_PHASE_VACUUM_HEAP, VISIBILITYMAP_ALL_FROZEN, VISIBILITYMAP_ALL_VISIBLE, visibilitymap_set(), XLOG_HEAP2_VACUUM, XLogBeginInsert(), XLogInsert(), XLogRegisterBufData(), XLogRegisterBuffer(), and XLogRegisterData().

Referenced by lazy_scan_heap(), and lazy_vacuum_heap_rel().

lazy_vacuum_heap_rel()

static void lazy_vacuum_heap_rel ( LVRelState *  vacrel )

static

Definition at line 2431 of file vacuumlazy.c.

{
    int         index = 0;
    BlockNumber vacuumed_pages = 0;
    Buffer      vmbuffer = InvalidBuffer;
    LVSavedErrInfo saved_err_info;
 
    Assert(vacrel->do_index_vacuuming);
    Assert(vacrel->do_index_cleanup);
    Assert(vacrel->num_index_scans > 0);
 
    /* Report that we are now vacuuming the heap */
    pgstat_progress_update_param(PROGRESS_VACUUM_PHASE,
                                 PROGRESS_VACUUM_PHASE_VACUUM_HEAP);
 
    /* Update error traceback information */
    update_vacuum_error_info(vacrel, &saved_err_info,
                             VACUUM_ERRCB_PHASE_VACUUM_HEAP,
                             InvalidBlockNumber, InvalidOffsetNumber);
 
    while (index < vacrel->dead_items->num_items)
    {
        BlockNumber blkno;
        Buffer      buf;
        Page        page;
        Size        freespace;
 
        vacuum_delay_point();
 
        blkno = ItemPointerGetBlockNumber(&vacrel->dead_items->items[index]);
        vacrel->blkno = blkno;
 
        /*
         * Pin the visibility map page in case we need to mark the page
         * all-visible.  In most cases this will be very cheap, because we'll
         * already have the correct page pinned anyway.
         */
        visibilitymap_pin(vacrel->rel, blkno, &vmbuffer);
 
        /* We need a non-cleanup exclusive lock to mark dead_items unused */
        buf = ReadBufferExtended(vacrel->rel, MAIN_FORKNUM, blkno, RBM_NORMAL,
                                 vacrel->bstrategy);
        LockBuffer(buf, BUFFER_LOCK_EXCLUSIVE);
        index = lazy_vacuum_heap_page(vacrel, blkno, buf, index, vmbuffer);
 
        /* Now that we've vacuumed the page, record its available space */
        page = BufferGetPage(buf);
        freespace = PageGetHeapFreeSpace(page);
 
        UnlockReleaseBuffer(buf);
        RecordPageWithFreeSpace(vacrel->rel, blkno, freespace);
        vacuumed_pages++;
    }
 
    vacrel->blkno = InvalidBlockNumber;
    if (BufferIsValid(vmbuffer))
        ReleaseBuffer(vmbuffer);
 
    /*
     * We set all LP_DEAD items from the first heap pass to LP_UNUSED during
     * the second heap pass.  No more, no less.
     */
    Assert(index > 0);
    Assert(vacrel->num_index_scans > 1 ||
           (index == vacrel->lpdead_items &&
            vacuumed_pages == vacrel->lpdead_item_pages));
 
    ereport(DEBUG2,
            (errmsg("table \"%s\": removed %lld dead item identifiers in %u pages",
                    vacrel->relname, (long long) index, vacuumed_pages)));
 
    /* Revert to the previous phase information for error traceback */
    restore_vacuum_error_info(vacrel, &saved_err_info);
}

References Assert(), LVRelState::blkno, LVRelState::bstrategy, buf, BUFFER_LOCK_EXCLUSIVE, BufferGetPage(), BufferIsValid(), LVRelState::dead_items, DEBUG2, LVRelState::do_index_cleanup, LVRelState::do_index_vacuuming, ereport, errmsg(), InvalidBlockNumber, InvalidBuffer, InvalidOffsetNumber, ItemPointerGetBlockNumber(), VacDeadItems::items, lazy_vacuum_heap_page(), LockBuffer(), LVRelState::lpdead_item_pages, LVRelState::lpdead_items, MAIN_FORKNUM, LVRelState::num_index_scans, PageGetHeapFreeSpace(), pgstat_progress_update_param(), PROGRESS_VACUUM_PHASE, PROGRESS_VACUUM_PHASE_VACUUM_HEAP, RBM_NORMAL, ReadBufferExtended(), RecordPageWithFreeSpace(), LVRelState::rel, ReleaseBuffer(), LVRelState::relname, restore_vacuum_error_info(), UnlockReleaseBuffer(), update_vacuum_error_info(), vacuum_delay_point(), VACUUM_ERRCB_PHASE_VACUUM_HEAP, and visibilitymap_pin().

Referenced by lazy_vacuum().

lazy_vacuum_one_index()

static IndexBulkDeleteResult * lazy_vacuum_one_index ( Relation  indrel, IndexBulkDeleteResult *  istat, double  reltuples, LVRelState *  vacrel  )

static

Definition at line 2757 of file vacuumlazy.c.

{
    IndexVacuumInfo ivinfo;
    LVSavedErrInfo saved_err_info;
 
    ivinfo.index = indrel;
    ivinfo.heaprel = vacrel->rel;
    ivinfo.analyze_only = false;
    ivinfo.report_progress = false;
    ivinfo.estimated_count = true;
    ivinfo.message_level = DEBUG2;
    ivinfo.num_heap_tuples = reltuples;
    ivinfo.strategy = vacrel->bstrategy;
 
    /*
     * Update error traceback information.
     *
     * The index name is saved during this phase and restored immediately
     * after this phase.  See vacuum_error_callback.
     */
    Assert(vacrel->indname == NULL);
    vacrel->indname = pstrdup(RelationGetRelationName(indrel));
    update_vacuum_error_info(vacrel, &saved_err_info,
                             VACUUM_ERRCB_PHASE_VACUUM_INDEX,
                             InvalidBlockNumber, InvalidOffsetNumber);
 
    /* Do bulk deletion */
    istat = vac_bulkdel_one_index(&ivinfo, istat, (void *) vacrel->dead_items);
 
    /* Revert to the previous phase information for error traceback */
    restore_vacuum_error_info(vacrel, &saved_err_info);
    pfree(vacrel->indname);
    vacrel->indname = NULL;
 
    return istat;
}

References IndexVacuumInfo::analyze_only, Assert(), LVRelState::bstrategy, LVRelState::dead_items, DEBUG2, IndexVacuumInfo::estimated_count, IndexVacuumInfo::heaprel, IndexVacuumInfo::index, LVRelState::indname, InvalidBlockNumber, InvalidOffsetNumber, IndexVacuumInfo::message_level, IndexVacuumInfo::num_heap_tuples, pfree(), pstrdup(), LVRelState::rel, RelationGetRelationName, IndexVacuumInfo::report_progress, restore_vacuum_error_info(), IndexVacuumInfo::strategy, update_vacuum_error_info(), vac_bulkdel_one_index(), and VACUUM_ERRCB_PHASE_VACUUM_INDEX.

Referenced by lazy_vacuum_all_indexes().

restore_vacuum_error_info()

static void restore_vacuum_error_info ( LVRelState *  vacrel, const LVSavedErrInfo *  saved_vacrel  )

static

Definition at line 3514 of file vacuumlazy.c.

{
    vacrel->blkno = saved_vacrel->blkno;
    vacrel->offnum = saved_vacrel->offnum;
    vacrel->phase = saved_vacrel->phase;
}

References LVRelState::blkno, LVSavedErrInfo::blkno, LVRelState::offnum, LVSavedErrInfo::offnum, LVRelState::phase, and LVSavedErrInfo::phase.

Referenced by lazy_cleanup_one_index(), lazy_vacuum_heap_page(), lazy_vacuum_heap_rel(), and lazy_vacuum_one_index().

should_attempt_truncation()

static bool should_attempt_truncation ( LVRelState *  vacrel )

static

Definition at line 2865 of file vacuumlazy.c.

{
    BlockNumber possibly_freeable;
 
    if (!vacrel->do_rel_truncate || VacuumFailsafeActive)
        return false;
 
    possibly_freeable = vacrel->rel_pages - vacrel->nonempty_pages;
    if (possibly_freeable > 0 &&
        (possibly_freeable >= REL_TRUNCATE_MINIMUM ||
         possibly_freeable >= vacrel->rel_pages / REL_TRUNCATE_FRACTION))
        return true;
 
    return false;
}

References LVRelState::do_rel_truncate, LVRelState::nonempty_pages, LVRelState::rel_pages, REL_TRUNCATE_FRACTION, REL_TRUNCATE_MINIMUM, and VacuumFailsafeActive.

Referenced by heap_vacuum_rel().

update_relstats_all_indexes()

static void update_relstats_all_indexes ( LVRelState *  vacrel )

static

Definition at line 3396 of file vacuumlazy.c.

{
    Relation   *indrels = vacrel->indrels;
    int         nindexes = vacrel->nindexes;
    IndexBulkDeleteResult **indstats = vacrel->indstats;
 
    Assert(vacrel->do_index_cleanup);
 
    for (int idx = 0; idx < nindexes; idx++)
    {
        Relation    indrel = indrels[idx];
        IndexBulkDeleteResult *istat = indstats[idx];
 
        if (istat == NULL || istat->estimated_count)
            continue;
 
        /* Update index statistics */
        vac_update_relstats(indrel,
                            istat->num_pages,
                            istat->num_index_tuples,
                            0,
                            false,
                            InvalidTransactionId,
                            InvalidMultiXactId,
                            NULL, NULL, false);
    }
}

References Assert(), LVRelState::do_index_cleanup, IndexBulkDeleteResult::estimated_count, idx(), LVRelState::indrels, LVRelState::indstats, InvalidMultiXactId, InvalidTransactionId, LVRelState::nindexes, IndexBulkDeleteResult::num_index_tuples, IndexBulkDeleteResult::num_pages, and vac_update_relstats().

Referenced by heap_vacuum_rel().

update_vacuum_error_info()

static void update_vacuum_error_info ( LVRelState *  vacrel, LVSavedErrInfo *  saved_vacrel, int  phase, BlockNumber  blkno, OffsetNumber  offnum  )

static

Definition at line 3495 of file vacuumlazy.c.

{
    if (saved_vacrel)
    {
        saved_vacrel->offnum = vacrel->offnum;
        saved_vacrel->blkno = vacrel->blkno;
        saved_vacrel->phase = vacrel->phase;
    }
 
    vacrel->blkno = blkno;
    vacrel->offnum = offnum;
    vacrel->phase = phase;
}

References LVRelState::blkno, LVSavedErrInfo::blkno, LVRelState::offnum, LVSavedErrInfo::offnum, LVRelState::phase, and LVSavedErrInfo::phase.

Referenced by lazy_cleanup_one_index(), lazy_scan_heap(), lazy_truncate_heap(), lazy_vacuum_heap_page(), lazy_vacuum_heap_rel(), and lazy_vacuum_one_index().

vacuum_error_callback()

static void vacuum_error_callback ( void *  arg )

static

Definition at line 3431 of file vacuumlazy.c.

{
    LVRelState *errinfo = arg;
 
    switch (errinfo->phase)
    {
        case VACUUM_ERRCB_PHASE_SCAN_HEAP:
            if (BlockNumberIsValid(errinfo->blkno))
            {
                if (OffsetNumberIsValid(errinfo->offnum))
                    errcontext("while scanning block %u offset %u of relation \"%s.%s\"",
                               errinfo->blkno, errinfo->offnum, errinfo->relnamespace, errinfo->relname);
                else
                    errcontext("while scanning block %u of relation \"%s.%s\"",
                               errinfo->blkno, errinfo->relnamespace, errinfo->relname);
            }
            else
                errcontext("while scanning relation \"%s.%s\"",
                           errinfo->relnamespace, errinfo->relname);
            break;
 
        case VACUUM_ERRCB_PHASE_VACUUM_HEAP:
            if (BlockNumberIsValid(errinfo->blkno))
            {
                if (OffsetNumberIsValid(errinfo->offnum))
                    errcontext("while vacuuming block %u offset %u of relation \"%s.%s\"",
                               errinfo->blkno, errinfo->offnum, errinfo->relnamespace, errinfo->relname);
                else
                    errcontext("while vacuuming block %u of relation \"%s.%s\"",
                               errinfo->blkno, errinfo->relnamespace, errinfo->relname);
            }
            else
                errcontext("while vacuuming relation \"%s.%s\"",
                           errinfo->relnamespace, errinfo->relname);
            break;
 
        case VACUUM_ERRCB_PHASE_VACUUM_INDEX:
            errcontext("while vacuuming index \"%s\" of relation \"%s.%s\"",
                       errinfo->indname, errinfo->relnamespace, errinfo->relname);
            break;
 
        case VACUUM_ERRCB_PHASE_INDEX_CLEANUP:
            errcontext("while cleaning up index \"%s\" of relation \"%s.%s\"",
                       errinfo->indname, errinfo->relnamespace, errinfo->relname);
            break;
 
        case VACUUM_ERRCB_PHASE_TRUNCATE:
            if (BlockNumberIsValid(errinfo->blkno))
                errcontext("while truncating relation \"%s.%s\" to %u blocks",
                           errinfo->relnamespace, errinfo->relname, errinfo->blkno);
            break;
 
        case VACUUM_ERRCB_PHASE_UNKNOWN:
        default:
            return;             /* do nothing; the errinfo may not be
                                 * initialized */
    }
}

References arg, LVRelState::blkno, BlockNumberIsValid(), errcontext, LVRelState::indname, LVRelState::offnum, OffsetNumberIsValid, LVRelState::phase, LVRelState::relname, LVRelState::relnamespace, VACUUM_ERRCB_PHASE_INDEX_CLEANUP, VACUUM_ERRCB_PHASE_SCAN_HEAP, VACUUM_ERRCB_PHASE_TRUNCATE, VACUUM_ERRCB_PHASE_UNKNOWN, VACUUM_ERRCB_PHASE_VACUUM_HEAP, and VACUUM_ERRCB_PHASE_VACUUM_INDEX.

Referenced by heap_vacuum_rel().