/*
* do a TransactionId -> txid conversion for an XID near the given epoch
*/
static txid
convert_xid(TransactionId xid, const TxidEpoch *state)
{
uint64 epoch;
/* return special xid's as-is */
if (!TransactionIdIsNormal(xid))
return (txid) xid;
/* xid can be on either side when near wrap-around */
epoch = (uint64) state->epoch;
if (xid > state->last_xid &&
TransactionIdPrecedes(xid, state->last_xid))
epoch--;
else if (xid < state->last_xid &&
TransactionIdFollows(xid, state->last_xid))
epoch++;
return (epoch << 32) | xid;
}
Datum
spoof_next_xid(PG_FUNCTION_ARGS)
{
TransactionId desiredXid = PG_GETARG_UINT32(0);
TransactionId oldXid = ShmemVariableCache->nextXid;
ShmemVariableCache->nextXid = desiredXid;
/*
* If we're raising the xid, the intent is presumably to cross some
* threshold and make assertions about expected behavior.
* On the other hand, lowering the xid is meant to be a tear down of
* a completed test case. Because of this distinction, only when
* we're raising the xid, do we take extra precaution to zero out
* the new pg_clog/pg_subtrans/pg_distributedlog files. (We don't
* want to zero out existing files...)
*/
if (TransactionIdFollows(desiredXid, oldXid))
{
/*
* The nature of xid arithmetic is such that we only bother zeroing out
* new pages of transaction files when we've crossed page boundaries.
* So, here we fool the following routines into zeroing out the desired
* pages of transaction metadata by lowering the input xid to the first
* of its corresponding page.
*/
#define CLOG_XACTS_PER_BYTE 4
#define CLOG_XACTS_PER_PAGE (BLCKSZ * CLOG_XACTS_PER_BYTE)
#define TransactionIdToPgIndex(xid) ((xid) % (TransactionId) CLOG_XACTS_PER_PAGE)
ExtendCLOG(desiredXid - TransactionIdToPgIndex(desiredXid));
#define SUBTRANS_XACTS_PER_PAGE (BLCKSZ / sizeof(SubTransData))
#define TransactionIdToEntry(xid) ((xid) % (uint32) SUBTRANS_XACTS_PER_PAGE)
ExtendSUBTRANS(desiredXid - TransactionIdToEntry(desiredXid));
#undef TransactionIdToEntry
#define ENTRIES_PER_PAGE (BLCKSZ / sizeof(DistributedLogEntry))
#define TransactionIdToEntry(localXid) ((localXid) % (TransactionId) ENTRIES_PER_PAGE)
DistributedLog_Extend(desiredXid - TransactionIdToEntry(desiredXid));
}
PG_RETURN_XID(oldXid);
}
/*
* PrescanPreparedTransactions
*
* Scan the pg_twophase directory and determine the range of valid XIDs
* present. This is run during database startup, after we have completed
* reading WAL. ShmemVariableCache->nextXid has been set to one more than
* the highest XID for which evidence exists in WAL.
*
* We throw away any prepared xacts with main XID beyond nextXid --- if any
* are present, it suggests that the DBA has done a PITR recovery to an
* earlier point in time without cleaning out pg_twophase. We dare not
* try to recover such prepared xacts since they likely depend on database
* state that doesn't exist now.
*
* However, we will advance nextXid beyond any subxact XIDs belonging to
* valid prepared xacts. We need to do this since subxact commit doesn't
* write a WAL entry, and so there might be no evidence in WAL of those
* subxact XIDs.
*
* Our other responsibility is to determine and return the oldest valid XID
* among the prepared xacts (if none, return ShmemVariableCache->nextXid).
* This is needed to synchronize pg_subtrans startup properly.
*/
TransactionId
PrescanPreparedTransactions(void)
{
TransactionId origNextXid = ShmemVariableCache->nextXid;
TransactionId result = origNextXid;
DIR *cldir;
struct dirent *clde;
cldir = AllocateDir(TWOPHASE_DIR);
while ((clde = ReadDir(cldir, TWOPHASE_DIR)) != NULL)
{
if (strlen(clde->d_name) == 8 &&
strspn(clde->d_name, "0123456789ABCDEF") == 8)
{
TransactionId xid;
char *buf;
TwoPhaseFileHeader *hdr;
TransactionId *subxids;
int i;
xid = (TransactionId) strtoul(clde->d_name, NULL, 16);
/* Reject XID if too new */
if (TransactionIdFollowsOrEquals(xid, origNextXid))
{
ereport(WARNING,
(errmsg("removing future two-phase state file \"%s\"",
clde->d_name)));
RemoveTwoPhaseFile(xid, true);
continue;
}
/*
* Note: we can't check if already processed because clog
* subsystem isn't up yet.
*/
/* Read and validate file */
buf = ReadTwoPhaseFile(xid);
if (buf == NULL)
{
ereport(WARNING,
(errmsg("removing corrupt two-phase state file \"%s\"",
clde->d_name)));
RemoveTwoPhaseFile(xid, true);
continue;
}
/* Deconstruct header */
hdr = (TwoPhaseFileHeader *) buf;
if (!TransactionIdEquals(hdr->xid, xid))
{
ereport(WARNING,
(errmsg("removing corrupt two-phase state file \"%s\"",
clde->d_name)));
RemoveTwoPhaseFile(xid, true);
pfree(buf);
continue;
}
/*
* OK, we think this file is valid. Incorporate xid into the
* running-minimum result.
*/
if (TransactionIdPrecedes(xid, result))
result = xid;
/*
* Examine subtransaction XIDs ... they should all follow main
* XID, and they may force us to advance nextXid.
*/
subxids = (TransactionId *)
(buf + MAXALIGN(sizeof(TwoPhaseFileHeader)));
for (i = 0; i < hdr->nsubxacts; i++)
{
TransactionId subxid = subxids[i];
Assert(TransactionIdFollows(subxid, xid));
if (TransactionIdFollowsOrEquals(subxid,
ShmemVariableCache->nextXid))
{
ShmemVariableCache->nextXid = subxid;
TransactionIdAdvance(ShmemVariableCache->nextXid);
}
}
pfree(buf);
}
}
FreeDir(cldir);
return result;
}
/*
* This is a copy of swap_relation_files in cluster.c, but it also swaps
* relfrozenxid.
*/
static void
swap_heap_or_index_files(Oid r1, Oid r2)
{
Relation relRelation;
HeapTuple reltup1,
reltup2;
Form_pg_class relform1,
relform2;
Oid swaptemp;
CatalogIndexState indstate;
/* We need writable copies of both pg_class tuples. */
relRelation = heap_open(RelationRelationId, RowExclusiveLock);
reltup1 = SearchSysCacheCopy(RELOID,
ObjectIdGetDatum(r1),
0, 0, 0);
if (!HeapTupleIsValid(reltup1))
elog(ERROR, "cache lookup failed for relation %u", r1);
relform1 = (Form_pg_class) GETSTRUCT(reltup1);
reltup2 = SearchSysCacheCopy(RELOID,
ObjectIdGetDatum(r2),
0, 0, 0);
if (!HeapTupleIsValid(reltup2))
elog(ERROR, "cache lookup failed for relation %u", r2);
relform2 = (Form_pg_class) GETSTRUCT(reltup2);
Assert(relform1->relkind == relform2->relkind);
/*
* Actually swap the fields in the two tuples
*/
swaptemp = relform1->relfilenode;
relform1->relfilenode = relform2->relfilenode;
relform2->relfilenode = swaptemp;
swaptemp = relform1->reltablespace;
relform1->reltablespace = relform2->reltablespace;
relform2->reltablespace = swaptemp;
swaptemp = relform1->reltoastrelid;
relform1->reltoastrelid = relform2->reltoastrelid;
relform2->reltoastrelid = swaptemp;
/* set rel1's frozen Xid to larger one */
if (TransactionIdIsNormal(relform1->relfrozenxid))
{
if (TransactionIdFollows(relform1->relfrozenxid,
relform2->relfrozenxid))
relform1->relfrozenxid = relform2->relfrozenxid;
else
relform2->relfrozenxid = relform1->relfrozenxid;
}
/* swap size statistics too, since new rel has freshly-updated stats */
{
#if PG_VERSION_NUM >= 90300
int32 swap_pages;
#else
int4 swap_pages;
#endif
float4 swap_tuples;
swap_pages = relform1->relpages;
relform1->relpages = relform2->relpages;
relform2->relpages = swap_pages;
swap_tuples = relform1->reltuples;
relform1->reltuples = relform2->reltuples;
relform2->reltuples = swap_tuples;
}
/* Update the tuples in pg_class */
simple_heap_update(relRelation, &reltup1->t_self, reltup1);
simple_heap_update(relRelation, &reltup2->t_self, reltup2);
/* Keep system catalogs current */
indstate = CatalogOpenIndexes(relRelation);
CatalogIndexInsert(indstate, reltup1);
CatalogIndexInsert(indstate, reltup2);
CatalogCloseIndexes(indstate);
/*
* If we have toast tables associated with the relations being swapped,
* change their dependency links to re-associate them with their new
* owning relations. Otherwise the wrong one will get dropped ...
*
* NOTE: it is possible that only one table has a toast table; this can
* happen in CLUSTER if there were dropped columns in the old table, and
* in ALTER TABLE when adding or changing type of columns.
*
* NOTE: at present, a TOAST table's only dependency is the one on its
* owning table. If more are ever created, we'd need to use something
* more selective than deleteDependencyRecordsFor() to get rid of only the
* link we want.
*/
if (relform1->reltoastrelid || relform2->reltoastrelid)
{
ObjectAddress baseobject,
toastobject;
long count;
/* Delete old dependencies */
if (relform1->reltoastrelid)
{
count = deleteDependencyRecordsFor(RelationRelationId,
relform1->reltoastrelid,
false);
if (count != 1)
elog(ERROR, "expected one dependency record for TOAST table, found %ld",
count);
}
if (relform2->reltoastrelid)
{
count = deleteDependencyRecordsFor(RelationRelationId,
relform2->reltoastrelid,
false);
if (count != 1)
elog(ERROR, "expected one dependency record for TOAST table, found %ld",
count);
}
/* Register new dependencies */
baseobject.classId = RelationRelationId;
baseobject.objectSubId = 0;
toastobject.classId = RelationRelationId;
toastobject.objectSubId = 0;
if (relform1->reltoastrelid)
{
baseobject.objectId = r1;
toastobject.objectId = relform1->reltoastrelid;
recordDependencyOn(&toastobject, &baseobject, DEPENDENCY_INTERNAL);
}
if (relform2->reltoastrelid)
{
baseobject.objectId = r2;
toastobject.objectId = relform2->reltoastrelid;
recordDependencyOn(&toastobject, &baseobject, DEPENDENCY_INTERNAL);
}
}
/*
* Blow away the old relcache entries now. We need this kluge because
* relcache.c keeps a link to the smgr relation for the physical file, and
* that will be out of date as soon as we do CommandCounterIncrement.
* Whichever of the rels is the second to be cleared during cache
* invalidation will have a dangling reference to an already-deleted smgr
* relation. Rather than trying to avoid this by ordering operations just
* so, it's easiest to not have the relcache entries there at all.
* (Fortunately, since one of the entries is local in our transaction,
* it's sufficient to clear out our own relcache this way; the problem
* cannot arise for other backends when they see our update on the
* non-local relation.)
*/
RelationForgetRelation(r1);
RelationForgetRelation(r2);
/* Clean up. */
heap_freetuple(reltup1);
heap_freetuple(reltup2);
heap_close(relRelation, RowExclusiveLock);
}
/*
* lazy_scan_heap() -- scan an open heap relation
*
* This routine prunes each page in the heap, which will among other
* things truncate dead tuples to dead line pointers, defragment the
* page, and set commit status bits (see heap_page_prune). It also builds
* lists of dead tuples and pages with free space, calculates statistics
* on the number of live tuples in the heap, and marks pages as
* all-visible if appropriate. When done, or when we run low on space for
* dead-tuple TIDs, invoke vacuuming of indexes and call lazy_vacuum_heap
* to reclaim dead line pointers.
*
* If there are no indexes then we can reclaim line pointers on the fly;
* dead line pointers need only be retained until all index pointers that
* reference them have been killed.
*/
static void
lazy_scan_heap(Relation onerel, LVRelStats *vacrelstats,
Relation *Irel, int nindexes, bool scan_all)
{
BlockNumber nblocks,
blkno;
HeapTupleData tuple;
char *relname;
BlockNumber empty_pages,
vacuumed_pages;
double num_tuples,
tups_vacuumed,
nkeep,
nunused;
IndexBulkDeleteResult **indstats;
int i;
PGRUsage ru0;
Buffer vmbuffer = InvalidBuffer;
BlockNumber next_not_all_visible_block;
bool skipping_all_visible_blocks;
pg_rusage_init(&ru0);
relname = RelationGetRelationName(onerel);
ereport(elevel,
(errmsg("vacuuming \"%s.%s\"",
get_namespace_name(RelationGetNamespace(onerel)),
relname)));
empty_pages = vacuumed_pages = 0;
num_tuples = tups_vacuumed = nkeep = nunused = 0;
indstats = (IndexBulkDeleteResult **)
palloc0(nindexes * sizeof(IndexBulkDeleteResult *));
nblocks = RelationGetNumberOfBlocks(onerel);
vacrelstats->rel_pages = nblocks;
vacrelstats->scanned_pages = 0;
vacrelstats->nonempty_pages = 0;
vacrelstats->latestRemovedXid = InvalidTransactionId;
lazy_space_alloc(vacrelstats, nblocks);
/*
* We want to skip pages that don't require vacuuming according to the
* visibility map, but only when we can skip 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; that's likely to disable readahead and so be counterproductive.
* Also, skipping even a single page means that we can't update
* relfrozenxid, so we only want to do it if we can skip a goodly number
* of pages.
*
* Before entering the main loop, establish the invariant that
* next_not_all_visible_block is the next block number >= blkno that's not
* all-visible according to the visibility map, or nblocks if there's no
* such block. Also, we set up the skipping_all_visible_blocks flag,
* which is needed because we need hysteresis in the decision: once we've
* started skipping blocks, we may as well skip everything up to the next
* not-all-visible block.
*
* Note: if scan_all is true, we won't actually skip any pages; but we
* maintain next_not_all_visible_block anyway, so as to set up the
* all_visible_according_to_vm flag correctly for each page.
*
* Note: The value returned by visibilitymap_test could be slightly
* out-of-date, since we make this test before reading the corresponding
* heap page or locking the buffer. This is OK. If we mistakenly think
* that the page is all-visible when in fact the flag's just been cleared,
* we might fail to vacuum the page. But it's OK to skip pages when
* scan_all is not set, so no great harm done; the next vacuum will find
* them. If we make the reverse mistake and vacuum a page unnecessarily,
* it'll just be a no-op.
*/
for (next_not_all_visible_block = 0;
next_not_all_visible_block < nblocks;
next_not_all_visible_block++)
{
if (!visibilitymap_test(onerel, next_not_all_visible_block, &vmbuffer))
break;
vacuum_delay_point();
}
if (next_not_all_visible_block >= SKIP_PAGES_THRESHOLD)
skipping_all_visible_blocks = true;
else
skipping_all_visible_blocks = false;
for (blkno = 0; blkno < nblocks; blkno++)
{
Buffer buf;
Page page;
OffsetNumber offnum,
maxoff;
bool tupgone,
hastup;
int prev_dead_count;
OffsetNumber frozen[MaxOffsetNumber];
int nfrozen;
Size freespace;
bool all_visible_according_to_vm;
bool all_visible;
bool has_dead_tuples;
TransactionId visibility_cutoff_xid = InvalidTransactionId;
if (blkno == next_not_all_visible_block)
{
/* Time to advance next_not_all_visible_block */
for (next_not_all_visible_block++;
next_not_all_visible_block < nblocks;
next_not_all_visible_block++)
{
if (!visibilitymap_test(onerel, next_not_all_visible_block,
&vmbuffer))
break;
vacuum_delay_point();
}
/*
* We know we can't skip the current block. But set up
* skipping_all_visible_blocks to do the right thing at the
* following blocks.
*/
if (next_not_all_visible_block - blkno > SKIP_PAGES_THRESHOLD)
skipping_all_visible_blocks = true;
else
skipping_all_visible_blocks = false;
all_visible_according_to_vm = false;
}
else
{
/* Current block is all-visible */
if (skipping_all_visible_blocks && !scan_all)
continue;
all_visible_according_to_vm = true;
}
vacuum_delay_point();
/*
* If we are close to overrunning the available space for dead-tuple
* TIDs, pause and do a cycle of vacuuming before we tackle this page.
*/
if ((vacrelstats->max_dead_tuples - vacrelstats->num_dead_tuples) < MaxHeapTuplesPerPage &&
vacrelstats->num_dead_tuples > 0)
{
/*
* 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;
}
/* Log cleanup info before we touch indexes */
vacuum_log_cleanup_info(onerel, vacrelstats);
/* Remove index entries */
for (i = 0; i < nindexes; i++)
lazy_vacuum_index(Irel[i],
&indstats[i],
vacrelstats);
/* Remove tuples from heap */
lazy_vacuum_heap(onerel, vacrelstats);
/*
* Forget the now-vacuumed tuples, and press on, but be careful
* not to reset latestRemovedXid since we want that value to be
* valid.
*/
vacrelstats->num_dead_tuples = 0;
vacrelstats->num_index_scans++;
}
/*
* 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. However, it's
* possible that (a) next_not_all_visible_block is covered by a
* different VM page than the current block or (b) we released our pin
* and did a cycle of index vacuuming.
*/
visibilitymap_pin(onerel, blkno, &vmbuffer);
buf = ReadBufferExtended(onerel, MAIN_FORKNUM, blkno,
RBM_NORMAL, vac_strategy);
/* We need buffer cleanup lock so that we can prune HOT chains. */
if (!ConditionalLockBufferForCleanup(buf))
{
/*
* If we're not scanning the whole relation to guard against XID
* wraparound, it's OK to skip vacuuming a page. The next vacuum
* will clean it up.
*/
if (!scan_all)
{
ReleaseBuffer(buf);
continue;
}
/*
* If this is a wraparound checking vacuum, then we read the page
* with share lock to see if any xids need to be frozen. If the
* page doesn't need attention we just skip and continue. If it
* does, we wait for cleanup lock.
*
* We could defer the lock request further by remembering the page
* and coming back to it later, or we could even register
* ourselves for multiple buffers and then service whichever one
* is received first. For now, this seems good enough.
*/
LockBuffer(buf, BUFFER_LOCK_SHARE);
if (!lazy_check_needs_freeze(buf))
{
UnlockReleaseBuffer(buf);
continue;
}
LockBuffer(buf, BUFFER_LOCK_UNLOCK);
LockBufferForCleanup(buf);
/* drop through to normal processing */
}
vacrelstats->scanned_pages++;
page = BufferGetPage(buf);
if (PageIsNew(page))
{
/*
* An all-zeroes page could be left over if a backend extends the
* relation but crashes before initializing the page. Reclaim such
* pages for use.
*
* We have to be careful here because we could be looking at a
* page that someone has just added to the relation and not yet
* been able to initialize (see RelationGetBufferForTuple). To
* protect against that, release the buffer lock, grab the
* relation extension lock momentarily, and re-lock the buffer. If
* the page is still uninitialized by then, it must be left over
* from a crashed backend, and we can initialize it.
*
* We don't really need the relation lock when this is a new or
* temp relation, but it's probably not worth the code space to
* check that, since this surely isn't a critical path.
*
* Note: the comparable code in vacuum.c need not worry because
* it's got exclusive lock on the whole relation.
*/
LockBuffer(buf, BUFFER_LOCK_UNLOCK);
LockRelationForExtension(onerel, ExclusiveLock);
UnlockRelationForExtension(onerel, ExclusiveLock);
LockBufferForCleanup(buf);
if (PageIsNew(page))
{
ereport(WARNING,
(errmsg("relation \"%s\" page %u is uninitialized --- fixing",
relname, blkno)));
PageInit(page, BufferGetPageSize(buf), 0);
empty_pages++;
}
freespace = PageGetHeapFreeSpace(page);
MarkBufferDirty(buf);
UnlockReleaseBuffer(buf);
RecordPageWithFreeSpace(onerel, blkno, freespace);
continue;
}
if (PageIsEmpty(page))
{
empty_pages++;
freespace = PageGetHeapFreeSpace(page);
/* empty pages are always all-visible */
if (!PageIsAllVisible(page))
{
PageSetAllVisible(page);
MarkBufferDirty(buf);
visibilitymap_set(onerel, blkno, InvalidXLogRecPtr, vmbuffer,
InvalidTransactionId);
}
UnlockReleaseBuffer(buf);
RecordPageWithFreeSpace(onerel, blkno, freespace);
continue;
}
/*
* Prune all HOT-update chains in this page.
*
* We count tuples removed by the pruning step as removed by VACUUM.
*/
tups_vacuumed += heap_page_prune(onerel, buf, OldestXmin, false,
&vacrelstats->latestRemovedXid);
/*
* Now scan the page to collect vacuumable items and check for tuples
* requiring freezing.
*/
all_visible = true;
has_dead_tuples = false;
nfrozen = 0;
hastup = false;
prev_dead_count = vacrelstats->num_dead_tuples;
maxoff = PageGetMaxOffsetNumber(page);
for (offnum = FirstOffsetNumber;
offnum <= maxoff;
offnum = OffsetNumberNext(offnum))
{
ItemId itemid;
itemid = PageGetItemId(page, offnum);
/* Unused items require no processing, but we count 'em */
if (!ItemIdIsUsed(itemid))
{
nunused += 1;
continue;
}
/* Redirect items mustn't be touched */
if (ItemIdIsRedirected(itemid))
{
hastup = true; /* this page won't be truncatable */
continue;
}
ItemPointerSet(&(tuple.t_self), blkno, offnum);
/*
* DEAD item pointers are to be vacuumed normally; but we don't
* count them in tups_vacuumed, else we'd be double-counting (at
* least in the common case where heap_page_prune() just freed up
* a non-HOT tuple).
*/
if (ItemIdIsDead(itemid))
{
lazy_record_dead_tuple(vacrelstats, &(tuple.t_self));
all_visible = false;
continue;
}
Assert(ItemIdIsNormal(itemid));
tuple.t_data = (HeapTupleHeader) PageGetItem(page, itemid);
tuple.t_len = ItemIdGetLength(itemid);
tupgone = false;
switch (HeapTupleSatisfiesVacuum(tuple.t_data, OldestXmin, buf))
{
case HEAPTUPLE_DEAD:
/*
* Ordinarily, DEAD tuples would have been removed by
* heap_page_prune(), but it's possible that the tuple
* state changed since heap_page_prune() looked. In
* particular an INSERT_IN_PROGRESS tuple could have
* changed to DEAD if the inserter aborted. So this
* cannot be considered an error condition.
*
* If the tuple is HOT-updated then it must only be
* removed by a prune operation; so we keep it just as if
* it were RECENTLY_DEAD. Also, if it's a heap-only
* tuple, we choose to keep it, because it'll be a lot
* cheaper to get rid of it in the next pruning pass than
* to treat it like an indexed tuple.
*/
if (HeapTupleIsHotUpdated(&tuple) ||
HeapTupleIsHeapOnly(&tuple))
nkeep += 1;
else
tupgone = true; /* we can delete the tuple */
all_visible = false;
break;
case HEAPTUPLE_LIVE:
/* Tuple is good --- but let's do some validity checks */
if (onerel->rd_rel->relhasoids &&
!OidIsValid(HeapTupleGetOid(&tuple)))
elog(WARNING, "relation \"%s\" TID %u/%u: OID is invalid",
relname, blkno, offnum);
/*
* 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 HEAP_XMIN_COMMITTED hint bit is set because of
* that.
*/
if (all_visible)
{
TransactionId xmin;
if (!(tuple.t_data->t_infomask & HEAP_XMIN_COMMITTED))
{
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, OldestXmin))
{
all_visible = false;
break;
}
/* Track newest xmin on page. */
if (TransactionIdFollows(xmin, visibility_cutoff_xid))
visibility_cutoff_xid = xmin;
}
break;
case HEAPTUPLE_RECENTLY_DEAD:
/*
* If tuple is recently deleted then we must not remove it
* from relation.
*/
nkeep += 1;
all_visible = false;
break;
case HEAPTUPLE_INSERT_IN_PROGRESS:
/* This is an expected case during concurrent vacuum */
all_visible = false;
break;
case HEAPTUPLE_DELETE_IN_PROGRESS:
/* This is an expected case during concurrent vacuum */
all_visible = false;
break;
default:
elog(ERROR, "unexpected HeapTupleSatisfiesVacuum result");
break;
}
if (tupgone)
{
lazy_record_dead_tuple(vacrelstats, &(tuple.t_self));
HeapTupleHeaderAdvanceLatestRemovedXid(tuple.t_data,
&vacrelstats->latestRemovedXid);
tups_vacuumed += 1;
has_dead_tuples = true;
}
else
{
num_tuples += 1;
hastup = true;
/*
* Each non-removable tuple must be checked to see if it needs
* freezing. Note we already have exclusive buffer lock.
*/
if (heap_freeze_tuple(tuple.t_data, FreezeLimit))
frozen[nfrozen++] = offnum;
}
} /* scan along page */
/*
* If we froze any tuples, mark the buffer dirty, and write a WAL
* record recording the changes. We must log the changes to be
* crash-safe against future truncation of CLOG.
*/
if (nfrozen > 0)
{
MarkBufferDirty(buf);
if (RelationNeedsWAL(onerel))
{
XLogRecPtr recptr;
recptr = log_heap_freeze(onerel, buf, FreezeLimit,
frozen, nfrozen);
PageSetLSN(page, recptr);
PageSetTLI(page, ThisTimeLineID);
}
}
/*
* If there are no indexes then we can vacuum the page right now
* instead of doing a second scan.
*/
if (nindexes == 0 &&
vacrelstats->num_dead_tuples > 0)
{
/* Remove tuples from heap */
lazy_vacuum_page(onerel, blkno, buf, 0, vacrelstats);
/*
* Forget the now-vacuumed tuples, and press on, but be careful
* not to reset latestRemovedXid since we want that value to be
* valid.
*/
vacrelstats->num_dead_tuples = 0;
vacuumed_pages++;
}
freespace = PageGetHeapFreeSpace(page);
/* mark page all-visible, if appropriate */
if (all_visible)
{
if (!PageIsAllVisible(page))
{
PageSetAllVisible(page);
MarkBufferDirty(buf);
visibilitymap_set(onerel, blkno, InvalidXLogRecPtr, vmbuffer,
visibility_cutoff_xid);
}
else if (!all_visible_according_to_vm)
{
/*
* 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. Set the visibility map bit as well so that we get
* back in sync.
*/
visibilitymap_set(onerel, blkno, InvalidXLogRecPtr, vmbuffer,
visibility_cutoff_xid);
}
}
/*
* 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 we checked it and before we took the buffer
* content lock, so we must recheck before jumping to the conclusion
* that something bad has happened.
*/
else if (all_visible_according_to_vm && !PageIsAllVisible(page)
&& visibilitymap_test(onerel, blkno, &vmbuffer))
{
elog(WARNING, "page is not marked all-visible but visibility map bit is set in relation \"%s\" page %u",
relname, blkno);
visibilitymap_clear(onerel, blkno, vmbuffer);
}
/*
* It's possible for the value returned by GetOldestXmin() 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
* GetOldestXmin() 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 dead tuples on a page with PD_ALL_VISIBLE
* set, however.
*/
else if (PageIsAllVisible(page) && has_dead_tuples)
{
elog(WARNING, "page containing dead tuples is marked as all-visible in relation \"%s\" page %u",
relname, blkno);
PageClearAllVisible(page);
MarkBufferDirty(buf);
visibilitymap_clear(onerel, blkno, vmbuffer);
}
UnlockReleaseBuffer(buf);
/* Remember the location of the last page with nonremovable tuples */
if (hastup)
vacrelstats->nonempty_pages = blkno + 1;
/*
* If we remembered any tuples for deletion, then the page will be
* visited again by lazy_vacuum_heap, which will compute and record
* its post-compaction free space. If not, then we're done with this
* page, so remember its free space as-is. (This path will always be
* taken if there are no indexes.)
*/
if (vacrelstats->num_dead_tuples == prev_dead_count)
RecordPageWithFreeSpace(onerel, blkno, freespace);
}
/* save stats for use later */
vacrelstats->scanned_tuples = num_tuples;
vacrelstats->tuples_deleted = tups_vacuumed;
/* now we can compute the new value for pg_class.reltuples */
vacrelstats->new_rel_tuples = vac_estimate_reltuples(onerel, false,
nblocks,
vacrelstats->scanned_pages,
num_tuples);
/*
* Release any remaining pin on visibility map page.
*/
if (BufferIsValid(vmbuffer))
{
ReleaseBuffer(vmbuffer);
vmbuffer = InvalidBuffer;
}
/* If any tuples need to be deleted, perform final vacuum cycle */
/* XXX put a threshold on min number of tuples here? */
if (vacrelstats->num_dead_tuples > 0)
{
/* Log cleanup info before we touch indexes */
vacuum_log_cleanup_info(onerel, vacrelstats);
/* Remove index entries */
for (i = 0; i < nindexes; i++)
lazy_vacuum_index(Irel[i],
&indstats[i],
vacrelstats);
/* Remove tuples from heap */
lazy_vacuum_heap(onerel, vacrelstats);
vacrelstats->num_index_scans++;
}
/* Do post-vacuum cleanup and statistics update for each index */
for (i = 0; i < nindexes; i++)
lazy_cleanup_index(Irel[i], indstats[i], vacrelstats);
/* If no indexes, make log report that lazy_vacuum_heap would've made */
if (vacuumed_pages)
ereport(elevel,
(errmsg("\"%s\": removed %.0f row versions in %u pages",
RelationGetRelationName(onerel),
tups_vacuumed, vacuumed_pages)));
ereport(elevel,
(errmsg("\"%s\": found %.0f removable, %.0f nonremovable row versions in %u out of %u pages",
RelationGetRelationName(onerel),
tups_vacuumed, num_tuples,
vacrelstats->scanned_pages, nblocks),
errdetail("%.0f dead row versions cannot be removed yet.\n"
"There were %.0f unused item pointers.\n"
"%u pages are entirely empty.\n"
"%s.",
nkeep,
nunused,
empty_pages,
pg_rusage_show(&ru0))));
}
