/*
* Visibility map information for a single block of a relation, plus the
* page-level information for the same block.
*/
Datum
pg_visibility(PG_FUNCTION_ARGS)
{
Oid relid = PG_GETARG_OID(0);
int64 blkno = PG_GETARG_INT64(1);
int32 mapbits;
Relation rel;
Buffer vmbuffer = InvalidBuffer;
Buffer buffer;
Page page;
TupleDesc tupdesc;
Datum values[3];
bool nulls[3];
rel = relation_open(relid, AccessShareLock);
if (blkno < 0 || blkno > MaxBlockNumber)
ereport(ERROR,
(errcode(ERRCODE_INVALID_PARAMETER_VALUE),
errmsg("invalid block number")));
tupdesc = pg_visibility_tupdesc(false, true);
MemSet(nulls, 0, sizeof(nulls));
mapbits = (int32) visibilitymap_get_status(rel, blkno, &vmbuffer);
if (vmbuffer != InvalidBuffer)
ReleaseBuffer(vmbuffer);
values[0] = BoolGetDatum((mapbits & VISIBILITYMAP_ALL_VISIBLE) != 0);
values[1] = BoolGetDatum((mapbits & VISIBILITYMAP_ALL_FROZEN) != 0);
buffer = ReadBuffer(rel, blkno);
LockBuffer(buffer, BUFFER_LOCK_SHARE);
page = BufferGetPage(buffer, NULL, NULL, BGP_NO_SNAPSHOT_TEST);
values[2] = BoolGetDatum(PageIsAllVisible(page));
UnlockReleaseBuffer(buffer);
relation_close(rel, AccessShareLock);
PG_RETURN_DATUM(HeapTupleGetDatum(heap_form_tuple(tupdesc, values, nulls)));
}
/*
* lazy_scan_heap() -- scan an open heap relation
*
* This routine sets commit status bits, builds lists of dead tuples
* and pages with free space, and calculates statistics on the number
* of live tuples in the heap. When done, or when we run low on space
* for dead-tuple TIDs, invoke vacuuming of indexes and heap.
*
* If there are no indexes then we just vacuum each dirty page as we
* process it, since there's no point in gathering many tuples.
*/
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.
*/
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;
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();
vacrelstats->scanned_pages++;
/*
* 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)
{
/* 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++;
}
buf = ReadBufferExtended(onerel, MAIN_FORKNUM, blkno,
RBM_NORMAL, vac_strategy);
/* We need buffer cleanup lock so that we can prune HOT chains. */
LockBufferForCleanup(buf);
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);
if (!PageIsAllVisible(page))
{
PageSetAllVisible(page);
SetBufferCommitInfoNeedsSave(buf);
}
LockBuffer(buf, BUFFER_LOCK_UNLOCK);
/* Update the visibility map */
if (!all_visible_according_to_vm)
{
visibilitymap_pin(onerel, blkno, &vmbuffer);
LockBuffer(buf, BUFFER_LOCK_SHARE);
if (PageIsAllVisible(page))
visibilitymap_set(onerel, blkno, PageGetLSN(page), &vmbuffer);
LockBuffer(buf, BUFFER_LOCK_UNLOCK);
}
ReleaseBuffer(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;
}
}
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,
InvalidBuffer))
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);
/* Update the all-visible flag on the page */
if (!PageIsAllVisible(page) && all_visible)
{
PageSetAllVisible(page);
SetBufferCommitInfoNeedsSave(buf);
}
/*
* 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);
SetBufferCommitInfoNeedsSave(buf);
/*
* Normally, we would drop the lock on the heap page before
* updating the visibility map, but since this case shouldn't
* happen anyway, don't worry about that.
*/
visibilitymap_clear(onerel, blkno);
}
LockBuffer(buf, BUFFER_LOCK_UNLOCK);
/* Update the visibility map */
if (!all_visible_according_to_vm && all_visible)
{
visibilitymap_pin(onerel, blkno, &vmbuffer);
LockBuffer(buf, BUFFER_LOCK_SHARE);
if (PageIsAllVisible(page))
visibilitymap_set(onerel, blkno, PageGetLSN(page), &vmbuffer);
LockBuffer(buf, BUFFER_LOCK_UNLOCK);
}
ReleaseBuffer(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);
/* 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++;
}
/* Release the pin on the visibility map page */
if (BufferIsValid(vmbuffer))
{
ReleaseBuffer(vmbuffer);
vmbuffer = InvalidBuffer;
}
/* 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))));
}
/*
* visibilitymap_set - set a bit on a previously pinned page
*
* recptr is the LSN of the XLOG record we're replaying, if we're in recovery,
* or InvalidXLogRecPtr in normal running. The page LSN is advanced to the
* one provided; in normal running, we generate a new___ XLOG record and set the
* page LSN to that value. cutoff_xid is the largest xmin on the page being
* marked all-visible; it is needed for Hot Standby, and can be
* InvalidTransactionId if the page contains no tuples.
*
* Caller is expected to set the heap page's PD_ALL_VISIBLE bit before calling
* this function. Except in recovery, caller should also pass the heap
* buffer. When checksums are enabled and we're not in recovery, we must add
* the heap buffer to the WAL chain to protect it from being torn.
*
* You must pass a buffer containing the correct map page to this function.
* Call visibilitymap_pin first to pin the right one. This function doesn't do
* any I/O.
*/
void
visibilitymap_set(Relation rel, BlockNumber heapBlk, Buffer heapBuf,
XLogRecPtr recptr, Buffer vmBuf, TransactionId cutoff_xid)
{
BlockNumber mapBlock = HEAPBLK_TO_MAPBLOCK(heapBlk);
uint32 mapByte = HEAPBLK_TO_MAPBYTE(heapBlk);
uint8 mapBit = HEAPBLK_TO_MAPBIT(heapBlk);
Page page;
char *map;
#ifdef TRACE_VISIBILITYMAP
elog(DEBUG1, "vm_set %s %d", RelationGetRelationName(rel), heapBlk);
#endif
Assert(InRecovery || XLogRecPtrIsInvalid(recptr));
Assert(InRecovery || BufferIsValid(heapBuf));
/* Check that we have the right heap page pinned, if present */
if (BufferIsValid(heapBuf) && BufferGetBlockNumber(heapBuf) != heapBlk)
elog(ERROR, "wrong heap buffer passed to visibilitymap_set");
/* Check that we have the right VM page pinned */
if (!BufferIsValid(vmBuf) || BufferGetBlockNumber(vmBuf) != mapBlock)
elog(ERROR, "wrong VM buffer passed to visibilitymap_set");
page = BufferGetPage(vmBuf);
map = PageGetContents(page);
LockBuffer(vmBuf, BUFFER_LOCK_EXCLUSIVE);
if (!(map[mapByte] & (1 << mapBit)))
{
START_CRIT_SECTION();
map[mapByte] |= (1 << mapBit);
MarkBufferDirty(vmBuf);
if (RelationNeedsWAL(rel))
{
if (XLogRecPtrIsInvalid(recptr))
{
Assert(!InRecovery);
recptr = log_heap_visible(rel->rd_node, heapBuf, vmBuf,
cutoff_xid);
/*
* If data checksums are enabled (or wal_log_hints=on), we
* need to protect the heap page from being torn.
*/
if (XLogHintBitIsNeeded())
{
Page heapPage = BufferGetPage(heapBuf);
/* caller is expected to set PD_ALL_VISIBLE first */
Assert(PageIsAllVisible(heapPage));
PageSetLSN(heapPage, recptr);
}
}
PageSetLSN(page, recptr);
}
END_CRIT_SECTION();
}
LockBuffer(vmBuf, BUFFER_LOCK_UNLOCK);
}
/*
* RelationGetBufferForTuple
*
* Returns pinned and exclusive-locked buffer of a page in given relation
* with free space >= given len.
*
* If otherBuffer is not InvalidBuffer, then it references a previously
* pinned buffer of another page in the same relation; on return, this
* buffer will also be exclusive-locked. (This case is used by heap_update;
* the otherBuffer contains the tuple being updated.)
*
* The reason for passing otherBuffer is that if two backends are doing
* concurrent heap_update operations, a deadlock could occur if they try
* to lock the same two buffers in opposite orders. To ensure that this
* can't happen, we impose the rule that buffers of a relation must be
* locked in increasing page number order. This is most conveniently done
* by having RelationGetBufferForTuple lock them both, with suitable care
* for ordering.
*
* NOTE: it is unlikely, but not quite impossible, for otherBuffer to be the
* same buffer we select for insertion of the new tuple (this could only
* happen if space is freed in that page after heap_update finds there's not
* enough there). In that case, the page will be pinned and locked only once.
*
* For the vmbuffer and vmbuffer_other arguments, we avoid deadlock by
* locking them only after locking the corresponding heap page, and taking
* no further lwlocks while they are locked.
*
* We normally use FSM to help us find free space. However,
* if HEAP_INSERT_SKIP_FSM is specified, we just append a new empty page to
* the end of the relation if the tuple won't fit on the current target page.
* This can save some cycles when we know the relation is new and doesn't
* contain useful amounts of free space.
*
* HEAP_INSERT_SKIP_FSM is also useful for non-WAL-logged additions to a
* relation, if the caller holds exclusive lock and is careful to invalidate
* relation's smgr_targblock before the first insertion --- that ensures that
* all insertions will occur into newly added pages and not be intermixed
* with tuples from other transactions. That way, a crash can't risk losing
* any committed data of other transactions. (See heap_insert's comments
* for additional constraints needed for safe usage of this behavior.)
*
* The caller can also provide a BulkInsertState object to optimize many
* insertions into the same relation. This keeps a pin on the current
* insertion target page (to save pin/unpin cycles) and also passes a
* BULKWRITE buffer selection strategy object to the buffer manager.
* Passing NULL for bistate selects the default behavior.
*
* We always try to avoid filling existing pages further than the fillfactor.
* This is OK since this routine is not consulted when updating a tuple and
* keeping it on the same page, which is the scenario fillfactor is meant
* to reserve space for.
*
* ereport(ERROR) is allowed here, so this routine *must* be called
* before any (unlogged) changes are made in buffer pool.
*/
Buffer
RelationGetBufferForTuple(Relation relation, Size len,
Buffer otherBuffer, int options,
BulkInsertState bistate,
Buffer *vmbuffer, Buffer *vmbuffer_other)
{
bool use_fsm = !(options & HEAP_INSERT_SKIP_FSM);
Buffer buffer = InvalidBuffer;
Page page;
Size pageFreeSpace,
saveFreeSpace;
BlockNumber targetBlock,
otherBlock;
bool needLock;
len = MAXALIGN(len); /* be conservative */
/* Bulk insert is not supported for updates, only inserts. */
Assert(otherBuffer == InvalidBuffer || !bistate);
/*
* If we're gonna fail for oversize tuple, do it right away
*/
if (len > MaxHeapTupleSize)
ereport(ERROR,
(errcode(ERRCODE_PROGRAM_LIMIT_EXCEEDED),
errmsg("row is too big: size %lu, maximum size %lu",
(unsigned long) len,
(unsigned long) MaxHeapTupleSize)));
/* Compute desired extra freespace due to fillfactor option */
saveFreeSpace = RelationGetTargetPageFreeSpace(relation,
HEAP_DEFAULT_FILLFACTOR);
if (otherBuffer != InvalidBuffer)
otherBlock = BufferGetBlockNumber(otherBuffer);
else
otherBlock = InvalidBlockNumber; /* just to keep compiler quiet */
/*
* We first try to put the tuple on the same page we last inserted a tuple
* on, as cached in the BulkInsertState or relcache entry. If that
* doesn't work, we ask the Free Space Map to locate a suitable page.
* Since the FSM's info might be out of date, we have to be prepared to
* loop around and retry multiple times. (To insure this isn't an infinite
* loop, we must update the FSM with the correct amount of free space on
* each page that proves not to be suitable.) If the FSM has no record of
* a page with enough free space, we give up and extend the relation.
*
* When use_fsm is false, we either put the tuple onto the existing target
* page or extend the relation.
*/
if (len + saveFreeSpace > MaxHeapTupleSize)
{
/* can't fit, don't bother asking FSM */
targetBlock = InvalidBlockNumber;
use_fsm = false;
}
else if (bistate && bistate->current_buf != InvalidBuffer)
targetBlock = BufferGetBlockNumber(bistate->current_buf);
else
targetBlock = RelationGetTargetBlock(relation);
if (targetBlock == InvalidBlockNumber && use_fsm)
{
/*
* We have no cached target page, so ask the FSM for an initial
* target.
*/
targetBlock = GetPageWithFreeSpace(relation, len + saveFreeSpace);
/*
* If the FSM knows nothing of the rel, try the last page before we
* give up and extend. This avoids one-tuple-per-page syndrome during
* bootstrapping or in a recently-started system.
*/
if (targetBlock == InvalidBlockNumber)
{
BlockNumber nblocks = RelationGetNumberOfBlocks(relation);
if (nblocks > 0)
targetBlock = nblocks - 1;
}
}
while (targetBlock != InvalidBlockNumber)
{
/*
* Read and exclusive-lock the target block, as well as the other
* block if one was given, taking suitable care with lock ordering and
* the possibility they are the same block.
*
* If the page-level all-visible flag is set, caller will need to
* clear both that and the corresponding visibility map bit. However,
* by the time we return, we'll have x-locked the buffer, and we don't
* want to do any I/O while in that state. So we check the bit here
* before taking the lock, and pin the page if it appears necessary.
* Checking without the lock creates a risk of getting the wrong
* answer, so we'll have to recheck after acquiring the lock.
*/
if (otherBuffer == InvalidBuffer)
{
/* easy case */
buffer = ReadBufferBI(relation, targetBlock, bistate);
if (PageIsAllVisible(BufferGetPage(buffer)))
visibilitymap_pin(relation, targetBlock, vmbuffer);
LockBuffer(buffer, BUFFER_LOCK_EXCLUSIVE);
}
else if (otherBlock == targetBlock)
{
/* also easy case */
buffer = otherBuffer;
if (PageIsAllVisible(BufferGetPage(buffer)))
visibilitymap_pin(relation, targetBlock, vmbuffer);
LockBuffer(buffer, BUFFER_LOCK_EXCLUSIVE);
}
else if (otherBlock < targetBlock)
{
/* lock other buffer first */
buffer = ReadBuffer(relation, targetBlock);
if (PageIsAllVisible(BufferGetPage(buffer)))
visibilitymap_pin(relation, targetBlock, vmbuffer);
LockBuffer(otherBuffer, BUFFER_LOCK_EXCLUSIVE);
LockBuffer(buffer, BUFFER_LOCK_EXCLUSIVE);
}
else
{
/* lock target buffer first */
buffer = ReadBuffer(relation, targetBlock);
if (PageIsAllVisible(BufferGetPage(buffer)))
visibilitymap_pin(relation, targetBlock, vmbuffer);
LockBuffer(buffer, BUFFER_LOCK_EXCLUSIVE);
LockBuffer(otherBuffer, BUFFER_LOCK_EXCLUSIVE);
}
/*
* We now have the target page (and the other buffer, if any) pinned
* and locked. However, since our initial PageIsAllVisible checks
* were performed before acquiring the lock, the results might now be
* out of date, either for the selected victim buffer, or for the
* other buffer passed by the caller. In that case, we'll need to
* give up our locks, go get the pin(s) we failed to get earlier, and
* re-lock. That's pretty painful, but hopefully shouldn't happen
* often.
*
* Note that there's a small possibility that we didn't pin the page
* above but still have the correct page pinned anyway, either because
* we've already made a previous pass through this loop, or because
* caller passed us the right page anyway.
*
* Note also that it's possible that by the time we get the pin and
* retake the buffer locks, the visibility map bit will have been
* cleared by some other backend anyway. In that case, we'll have
* done a bit of extra work for no gain, but there's no real harm
* done.
*/
if (otherBuffer == InvalidBuffer || buffer <= otherBuffer)
GetVisibilityMapPins(relation, buffer, otherBuffer,
targetBlock, otherBlock, vmbuffer,
vmbuffer_other);
else
GetVisibilityMapPins(relation, otherBuffer, buffer,
otherBlock, targetBlock, vmbuffer_other,
vmbuffer);
/*
* Now we can check to see if there's enough free space here. If so,
* we're done.
*/
page = BufferGetPage(buffer);
pageFreeSpace = PageGetHeapFreeSpace(page);
if (len + saveFreeSpace <= pageFreeSpace)
{
/* use this page as future insert target, too */
RelationSetTargetBlock(relation, targetBlock);
return buffer;
}
/*
* Not enough space, so we must give up our page locks and pin (if
* any) and prepare to look elsewhere. We don't care which order we
* unlock the two buffers in, so this can be slightly simpler than the
* code above.
*/
LockBuffer(buffer, BUFFER_LOCK_UNLOCK);
if (otherBuffer == InvalidBuffer)
ReleaseBuffer(buffer);
else if (otherBlock != targetBlock)
{
LockBuffer(otherBuffer, BUFFER_LOCK_UNLOCK);
ReleaseBuffer(buffer);
}
/* Without FSM, always fall out of the loop and extend */
if (!use_fsm)
break;
/*
* Update FSM as to condition of this page, and ask for another page
* to try.
*/
targetBlock = RecordAndGetPageWithFreeSpace(relation,
targetBlock,
pageFreeSpace,
len + saveFreeSpace);
}
/*
* Have to extend the relation.
*
* We have to use a lock to ensure no one else is extending the rel at the
* same time, else we will both try to initialize the same new page. We
* can skip locking for new or temp relations, however, since no one else
* could be accessing them.
*/
needLock = !RELATION_IS_LOCAL(relation);
if (needLock)
LockRelationForExtension(relation, ExclusiveLock);
/*
* XXX This does an lseek - rather expensive - but at the moment it is the
* only way to accurately determine how many blocks are in a relation. Is
* it worth keeping an accurate file length in shared memory someplace,
* rather than relying on the kernel to do it for us?
*/
buffer = ReadBufferBI(relation, P_NEW, bistate);
/*
* We can be certain that locking the otherBuffer first is OK, since it
* must have a lower page number.
*/
if (otherBuffer != InvalidBuffer)
LockBuffer(otherBuffer, BUFFER_LOCK_EXCLUSIVE);
/*
* Now acquire lock on the new page.
*/
LockBuffer(buffer, BUFFER_LOCK_EXCLUSIVE);
/*
* Release the file-extension lock; it's now OK for someone else to extend
* the relation some more. Note that we cannot release this lock before
* we have buffer lock on the new page, or we risk a race condition
* against vacuumlazy.c --- see comments therein.
*/
if (needLock)
UnlockRelationForExtension(relation, ExclusiveLock);
/*
* We need to initialize the empty new page. Double-check that it really
* is empty (this should never happen, but if it does we don't want to
* risk wiping out valid data).
*/
page = BufferGetPage(buffer);
if (!PageIsNew(page))
elog(ERROR, "page %u of relation \"%s\" should be empty but is not",
BufferGetBlockNumber(buffer),
RelationGetRelationName(relation));
PageInit(page, BufferGetPageSize(buffer), 0);
if (len > PageGetHeapFreeSpace(page))
{
/* We should not get here given the test at the top */
elog(PANIC, "tuple is too big: size %lu", (unsigned long) len);
}
/*
* Remember the new page as our target for future insertions.
*
* XXX should we enter the new page into the free space map immediately,
* or just keep it for this backend's exclusive use in the short run
* (until VACUUM sees it)? Seems to depend on whether you expect the
* current backend to make more insertions or not, which is probably a
* good bet most of the time. So for now, don't add it to FSM yet.
*/
RelationSetTargetBlock(relation, BufferGetBlockNumber(buffer));
return buffer;
}
/*
* Collect visibility data about a relation.
*
* Checks relkind of relid and will throw an error if the relation does not
* have a VM.
*/
static vbits *
collect_visibility_data(Oid relid, bool include_pd)
{
Relation rel;
BlockNumber nblocks;
vbits *info;
BlockNumber blkno;
Buffer vmbuffer = InvalidBuffer;
BufferAccessStrategy bstrategy = GetAccessStrategy(BAS_BULKREAD);
rel = relation_open(relid, AccessShareLock);
/* Only some relkinds have a visibility map */
check_relation_relkind(rel);
nblocks = RelationGetNumberOfBlocks(rel);
info = palloc0(offsetof(vbits, bits) + nblocks);
info->next = 0;
info->count = nblocks;
for (blkno = 0; blkno < nblocks; ++blkno)
{
int32 mapbits;
/* Make sure we are interruptible. */
CHECK_FOR_INTERRUPTS();
/* Get map info. */
mapbits = (int32) visibilitymap_get_status(rel, blkno, &vmbuffer);
if ((mapbits & VISIBILITYMAP_ALL_VISIBLE) != 0)
info->bits[blkno] |= (1 << 0);
if ((mapbits & VISIBILITYMAP_ALL_FROZEN) != 0)
info->bits[blkno] |= (1 << 1);
/*
* Page-level data requires reading every block, so only get it if the
* caller needs it. Use a buffer access strategy, too, to prevent
* cache-trashing.
*/
if (include_pd)
{
Buffer buffer;
Page page;
buffer = ReadBufferExtended(rel, MAIN_FORKNUM, blkno, RBM_NORMAL,
bstrategy);
LockBuffer(buffer, BUFFER_LOCK_SHARE);
page = BufferGetPage(buffer);
if (PageIsAllVisible(page))
info->bits[blkno] |= (1 << 2);
UnlockReleaseBuffer(buffer);
}
}
/* Clean up. */
if (vmbuffer != InvalidBuffer)
ReleaseBuffer(vmbuffer);
relation_close(rel, AccessShareLock);
return info;
}
