/*
* _hash_binsearch_last
*
* Same as above, except that if there are multiple matching items in the
* page, we return the offset of the last one instead of the first one,
* and the possible range of outputs is 0..maxoffset not 1..maxoffset+1.
* This is handy for starting a new page in a backwards scan.
*/
OffsetNumber
_hash_binsearch_last(Page page, uint32 hash_value)
{
OffsetNumber upper;
OffsetNumber lower;
/* Loop invariant: lower <= desired place <= upper */
upper = PageGetMaxOffsetNumber(page);
lower = FirstOffsetNumber - 1;
while (upper > lower)
{
IndexTuple itup;
OffsetNumber off;
uint32 hashkey;
off = (upper + lower + 1) / 2;
Assert(OffsetNumberIsValid(off));
itup = (IndexTuple) PageGetItem(page, PageGetItemId(page, off));
hashkey = _hash_get_indextuple_hashkey(itup);
if (hashkey > hash_value)
upper = off - 1;
else
lower = off;
}
return lower;
}
/*
* Decode multiple posting list segments into an array of item pointers.
* The number of items is returned in *ndecoded_out. The segments are stored
* one after each other, with total size 'len' bytes.
*/
ItemPointer
ginPostingListDecodeAllSegments(GinPostingList *segment, int len, int *ndecoded_out)
{
ItemPointer result;
int nallocated;
uint64 val;
char *endseg = ((char *) segment) + len;
int ndecoded;
unsigned char *ptr;
unsigned char *endptr;
/*
* Guess an initial size of the array.
*/
nallocated = segment->nbytes * 2 + 1;
result = palloc(nallocated * sizeof(ItemPointerData));
ndecoded = 0;
while ((char *) segment < endseg)
{
/* enlarge output array if needed */
if (ndecoded >= nallocated)
{
nallocated *= 2;
result = repalloc(result, nallocated * sizeof(ItemPointerData));
}
/* copy the first item */
Assert(OffsetNumberIsValid(ItemPointerGetOffsetNumber(&segment->first)));
Assert(ndecoded == 0 || ginCompareItemPointers(&segment->first, &result[ndecoded - 1]) > 0);
result[ndecoded] = segment->first;
ndecoded++;
val = itemptr_to_uint64(&segment->first);
ptr = segment->bytes;
endptr = segment->bytes + segment->nbytes;
while (ptr < endptr)
{
/* enlarge output array if needed */
if (ndecoded >= nallocated)
{
nallocated *= 2;
result = repalloc(result, nallocated * sizeof(ItemPointerData));
}
val += decode_varbyte(&ptr);
uint64_to_itemptr(val, &result[ndecoded]);
ndecoded++;
}
segment = GinNextPostingListSegment(segment);
}
if (ndecoded_out)
*ndecoded_out = ndecoded;
return result;
}
/*
* Complete the incomplete split of state->stack->page.
*/
static void
gistfixsplit(GISTInsertState *state, GISTSTATE *giststate)
{
GISTInsertStack *stack = state->stack;
Buffer buf;
Page page;
List *splitinfo = NIL;
elog(LOG, "fixing incomplete split in index \"%s\", block %u",
RelationGetRelationName(state->r), stack->blkno);
Assert(GistFollowRight(stack->page));
Assert(OffsetNumberIsValid(stack->downlinkoffnum));
buf = stack->buffer;
/*
* Read the chain of split pages, following the rightlinks. Construct a
* downlink tuple for each page.
*/
for (;;)
{
GISTPageSplitInfo *si = palloc(sizeof(GISTPageSplitInfo));
IndexTuple downlink;
page = BufferGetPage(buf);
/* Form the new downlink tuples to insert to parent */
downlink = gistformdownlink(state->r, buf, giststate, stack);
si->buf = buf;
si->downlink = downlink;
splitinfo = lappend(splitinfo, si);
if (GistFollowRight(page))
{
/* lock next page */
buf = ReadBuffer(state->r, GistPageGetOpaque(page)->rightlink);
LockBuffer(buf, GIST_EXCLUSIVE);
}
else
break;
}
/* Insert the downlinks */
gistfinishsplit(state, stack, giststate, splitinfo, false);
}
/*
* PageAddItemExtended
*
* Add an item to a page. Return value is the offset at which it was
* inserted, or InvalidOffsetNumber if the item is not inserted for any
* reason. A WARNING is issued indicating the reason for the refusal.
*
* offsetNumber must be either InvalidOffsetNumber to specify finding a
* free item pointer, or a value between FirstOffsetNumber and one past
* the last existing item, to specify using that particular item pointer.
*
* If offsetNumber is valid and flag PAI_OVERWRITE is set, we just store
* the item at the specified offsetNumber, which must be either a
* currently-unused item pointer, or one past the last existing item.
*
* If offsetNumber is valid and flag PAI_OVERWRITE is not set, insert
* the item at the specified offsetNumber, moving existing items later
* in the array to make room.
*
* If offsetNumber is not valid, then assign a slot by finding the first
* one that is both unused and deallocated.
*
* If flag PAI_IS_HEAP is set, we enforce that there can't be more than
* MaxHeapTuplesPerPage line pointers on the page.
*
* !!! EREPORT(ERROR) IS DISALLOWED HERE !!!
*/
OffsetNumber
PageAddItemExtended(Page page,
Item item,
Size size,
OffsetNumber offsetNumber,
int flags)
{
PageHeader phdr = (PageHeader) page;
Size alignedSize;
int lower;
int upper;
ItemId itemId;
OffsetNumber limit;
bool needshuffle = false;
/*
* Be wary about corrupted page pointers
*/
if (phdr->pd_lower < SizeOfPageHeaderData ||
phdr->pd_lower > phdr->pd_upper ||
phdr->pd_upper > phdr->pd_special ||
phdr->pd_special > BLCKSZ)
ereport(PANIC,
(errcode(ERRCODE_DATA_CORRUPTED),
errmsg("corrupted page pointers: lower = %u, upper = %u, special = %u",
phdr->pd_lower, phdr->pd_upper, phdr->pd_special)));
/*
* Select offsetNumber to place the new item at
*/
limit = OffsetNumberNext(PageGetMaxOffsetNumber(page));
/* was offsetNumber passed in? */
if (OffsetNumberIsValid(offsetNumber))
{
/* yes, check it */
if ((flags & PAI_OVERWRITE) != 0)
{
if (offsetNumber < limit)
{
itemId = PageGetItemId(phdr, offsetNumber);
if (ItemIdIsUsed(itemId) || ItemIdHasStorage(itemId))
{
elog(WARNING, "will not overwrite a used ItemId");
return InvalidOffsetNumber;
}
}
}
else
{
if (offsetNumber < limit)
needshuffle = true; /* need to move existing linp's */
}
}
else
{
/* offsetNumber was not passed in, so find a free slot */
/* if no free slot, we'll put it at limit (1st open slot) */
if (PageHasFreeLinePointers(phdr))
{
/*
* Look for "recyclable" (unused) ItemId. We check for no storage
* as well, just to be paranoid --- unused items should never have
* storage.
*/
for (offsetNumber = 1; offsetNumber < limit; offsetNumber++)
{
itemId = PageGetItemId(phdr, offsetNumber);
if (!ItemIdIsUsed(itemId) && !ItemIdHasStorage(itemId))
break;
}
if (offsetNumber >= limit)
{
/* the hint is wrong, so reset it */
PageClearHasFreeLinePointers(phdr);
}
}
else
{
/* don't bother searching if hint says there's no free slot */
offsetNumber = limit;
}
}
/* Reject placing items beyond the first unused line pointer */
if (offsetNumber > limit)
{
elog(WARNING, "specified item offset is too large");
return InvalidOffsetNumber;
}
/* Reject placing items beyond heap boundary, if heap */
if ((flags & PAI_IS_HEAP) != 0 && offsetNumber > MaxHeapTuplesPerPage)
{
elog(WARNING, "can't put more than MaxHeapTuplesPerPage items in a heap page");
return InvalidOffsetNumber;
}
/*
* Compute new lower and upper pointers for page, see if it'll fit.
*
* Note: do arithmetic as signed ints, to avoid mistakes if, say,
* alignedSize > pd_upper.
*/
if (offsetNumber == limit || needshuffle)
lower = phdr->pd_lower + sizeof(ItemIdData);
else
lower = phdr->pd_lower;
alignedSize = MAXALIGN(size);
upper = (int) phdr->pd_upper - (int) alignedSize;
if (lower > upper)
return InvalidOffsetNumber;
/*
* OK to insert the item. First, shuffle the existing pointers if needed.
*/
itemId = PageGetItemId(phdr, offsetNumber);
if (needshuffle)
memmove(itemId + 1, itemId,
(limit - offsetNumber) * sizeof(ItemIdData));
/* set the item pointer */
ItemIdSetNormal(itemId, upper, size);
/*
* Items normally contain no uninitialized bytes. Core bufpage consumers
* conform, but this is not a necessary coding rule; a new index AM could
* opt to depart from it. However, data type input functions and other
* C-language functions that synthesize datums should initialize all
* bytes; datumIsEqual() relies on this. Testing here, along with the
* similar check in printtup(), helps to catch such mistakes.
*
* Values of the "name" type retrieved via index-only scans may contain
* uninitialized bytes; see comment in btrescan(). Valgrind will report
* this as an error, but it is safe to ignore.
*/
VALGRIND_CHECK_MEM_IS_DEFINED(item, size);
/* copy the item's data onto the page */
memcpy((char *) page + upper, item, size);
/* adjust page header */
phdr->pd_lower = (LocationIndex) lower;
phdr->pd_upper = (LocationIndex) upper;
return offsetNumber;
}
/*
* Place tuples from 'itup' to 'buffer'. If 'oldoffnum' is valid, the tuple
* at that offset is atomically removed along with inserting the new tuples.
* This is used to replace a tuple with a new one.
*
* If 'leftchildbuf' is valid, we're inserting the downlink for the page
* to the right of 'leftchildbuf', or updating the downlink for 'leftchildbuf'.
* F_FOLLOW_RIGHT flag on 'leftchildbuf' is cleared and NSN is set.
*
* If 'markfollowright' is true and the page is split, the left child is
* marked with F_FOLLOW_RIGHT flag. That is the normal case. During buffered
* index build, however, there is no concurrent access and the page splitting
* is done in a slightly simpler fashion, and false is passed.
*
* If there is not enough room on the page, it is split. All the split
* pages are kept pinned and locked and returned in *splitinfo, the caller
* is responsible for inserting the downlinks for them. However, if
* 'buffer' is the root page and it needs to be split, gistplacetopage()
* performs the split as one atomic operation, and *splitinfo is set to NIL.
* In that case, we continue to hold the root page locked, and the child
* pages are released; note that new tuple(s) are *not* on the root page
* but in one of the new child pages.
*
* If 'newblkno' is not NULL, returns the block number of page the first
* new/updated tuple was inserted to. Usually it's the given page, but could
* be its right sibling if the page was split.
*
* Returns 'true' if the page was split, 'false' otherwise.
*/
bool
gistplacetopage(Relation rel, Size freespace, GISTSTATE *giststate,
Buffer buffer,
IndexTuple *itup, int ntup, OffsetNumber oldoffnum,
BlockNumber *newblkno,
Buffer leftchildbuf,
List **splitinfo,
bool markfollowright)
{
BlockNumber blkno = BufferGetBlockNumber(buffer);
Page page = BufferGetPage(buffer);
bool is_leaf = (GistPageIsLeaf(page)) ? true : false;
XLogRecPtr recptr;
int i;
bool is_split;
/*
* Refuse to modify a page that's incompletely split. This should not
* happen because we finish any incomplete splits while we walk down the
* tree. However, it's remotely possible that another concurrent inserter
* splits a parent page, and errors out before completing the split. We
* will just throw an error in that case, and leave any split we had in
* progress unfinished too. The next insert that comes along will clean up
* the mess.
*/
if (GistFollowRight(page))
elog(ERROR, "concurrent GiST page split was incomplete");
*splitinfo = NIL;
/*
* if isupdate, remove old key: This node's key has been modified, either
* because a child split occurred or because we needed to adjust our key
* for an insert in a child node. Therefore, remove the old version of
* this node's key.
*
* for WAL replay, in the non-split case we handle this by setting up a
* one-element todelete array; in the split case, it's handled implicitly
* because the tuple vector passed to gistSplit won't include this tuple.
*/
is_split = gistnospace(page, itup, ntup, oldoffnum, freespace);
if (is_split)
{
/* no space for insertion */
IndexTuple *itvec;
int tlen;
SplitedPageLayout *dist = NULL,
*ptr;
BlockNumber oldrlink = InvalidBlockNumber;
GistNSN oldnsn = 0;
SplitedPageLayout rootpg;
bool is_rootsplit;
is_rootsplit = (blkno == GIST_ROOT_BLKNO);
/*
* Form index tuples vector to split. If we're replacing an old tuple,
* remove the old version from the vector.
*/
itvec = gistextractpage(page, &tlen);
if (OffsetNumberIsValid(oldoffnum))
{
/* on inner page we should remove old tuple */
int pos = oldoffnum - FirstOffsetNumber;
tlen--;
if (pos != tlen)
memmove(itvec + pos, itvec + pos + 1, sizeof(IndexTuple) * (tlen - pos));
}
itvec = gistjoinvector(itvec, &tlen, itup, ntup);
dist = gistSplit(rel, page, itvec, tlen, giststate);
/*
* Set up pages to work with. Allocate new buffers for all but the
* leftmost page. The original page becomes the new leftmost page, and
* is just replaced with the new contents.
*
* For a root-split, allocate new buffers for all child pages, the
* original page is overwritten with new root page containing
* downlinks to the new child pages.
*/
ptr = dist;
if (!is_rootsplit)
{
/* save old rightlink and NSN */
oldrlink = GistPageGetOpaque(page)->rightlink;
oldnsn = GistPageGetNSN(page);
dist->buffer = buffer;
dist->block.blkno = BufferGetBlockNumber(buffer);
dist->page = PageGetTempPageCopySpecial(BufferGetPage(buffer));
/* clean all flags except F_LEAF */
GistPageGetOpaque(dist->page)->flags = (is_leaf) ? F_LEAF : 0;
ptr = ptr->next;
}
for (; ptr; ptr = ptr->next)
{
/* Allocate new page */
ptr->buffer = gistNewBuffer(rel);
GISTInitBuffer(ptr->buffer, (is_leaf) ? F_LEAF : 0);
ptr->page = BufferGetPage(ptr->buffer);
ptr->block.blkno = BufferGetBlockNumber(ptr->buffer);
}
/*
* Now that we know which blocks the new pages go to, set up downlink
* tuples to point to them.
*/
for (ptr = dist; ptr; ptr = ptr->next)
{
ItemPointerSetBlockNumber(&(ptr->itup->t_tid), ptr->block.blkno);
GistTupleSetValid(ptr->itup);
}
/*
* If this is a root split, we construct the new root page with the
* downlinks here directly, instead of requiring the caller to insert
* them. Add the new root page to the list along with the child pages.
*/
if (is_rootsplit)
{
IndexTuple *downlinks;
int ndownlinks = 0;
int i;
rootpg.buffer = buffer;
rootpg.page = PageGetTempPageCopySpecial(BufferGetPage(rootpg.buffer));
GistPageGetOpaque(rootpg.page)->flags = 0;
/* Prepare a vector of all the downlinks */
for (ptr = dist; ptr; ptr = ptr->next)
ndownlinks++;
downlinks = palloc(sizeof(IndexTuple) * ndownlinks);
for (i = 0, ptr = dist; ptr; ptr = ptr->next)
downlinks[i++] = ptr->itup;
rootpg.block.blkno = GIST_ROOT_BLKNO;
rootpg.block.num = ndownlinks;
rootpg.list = gistfillitupvec(downlinks, ndownlinks,
&(rootpg.lenlist));
rootpg.itup = NULL;
rootpg.next = dist;
dist = &rootpg;
}
else
{
/* Prepare split-info to be returned to caller */
for (ptr = dist; ptr; ptr = ptr->next)
{
GISTPageSplitInfo *si = palloc(sizeof(GISTPageSplitInfo));
si->buf = ptr->buffer;
si->downlink = ptr->itup;
*splitinfo = lappend(*splitinfo, si);
}
}
/*
* Fill all pages. All the pages are new, ie. freshly allocated empty
* pages, or a temporary copy of the old page.
*/
for (ptr = dist; ptr; ptr = ptr->next)
{
char *data = (char *) (ptr->list);
for (i = 0; i < ptr->block.num; i++)
{
IndexTuple thistup = (IndexTuple) data;
if (PageAddItem(ptr->page, (Item) data, IndexTupleSize(thistup), i + FirstOffsetNumber, false, false) == InvalidOffsetNumber)
elog(ERROR, "failed to add item to index page in \"%s\"", RelationGetRelationName(rel));
/*
* If this is the first inserted/updated tuple, let the caller
* know which page it landed on.
*/
if (newblkno && ItemPointerEquals(&thistup->t_tid, &(*itup)->t_tid))
*newblkno = ptr->block.blkno;
data += IndexTupleSize(thistup);
}
/* Set up rightlinks */
if (ptr->next && ptr->block.blkno != GIST_ROOT_BLKNO)
GistPageGetOpaque(ptr->page)->rightlink =
ptr->next->block.blkno;
else
GistPageGetOpaque(ptr->page)->rightlink = oldrlink;
/*
* Mark the all but the right-most page with the follow-right
* flag. It will be cleared as soon as the downlink is inserted
* into the parent, but this ensures that if we error out before
* that, the index is still consistent. (in buffering build mode,
* any error will abort the index build anyway, so this is not
* needed.)
*/
if (ptr->next && !is_rootsplit && markfollowright)
GistMarkFollowRight(ptr->page);
else
GistClearFollowRight(ptr->page);
/*
* Copy the NSN of the original page to all pages. The
* F_FOLLOW_RIGHT flags ensure that scans will follow the
* rightlinks until the downlinks are inserted.
*/
GistPageSetNSN(ptr->page, oldnsn);
}
START_CRIT_SECTION();
/*
* Must mark buffers dirty before XLogInsert, even though we'll still
* be changing their opaque fields below.
*/
for (ptr = dist; ptr; ptr = ptr->next)
MarkBufferDirty(ptr->buffer);
if (BufferIsValid(leftchildbuf))
MarkBufferDirty(leftchildbuf);
/*
* The first page in the chain was a temporary working copy meant to
* replace the old page. Copy it over the old page.
*/
PageRestoreTempPage(dist->page, BufferGetPage(dist->buffer));
dist->page = BufferGetPage(dist->buffer);
/* Write the WAL record */
if (RelationNeedsWAL(rel))
recptr = gistXLogSplit(rel->rd_node, blkno, is_leaf,
dist, oldrlink, oldnsn, leftchildbuf,
markfollowright);
else
recptr = gistGetFakeLSN(rel);
for (ptr = dist; ptr; ptr = ptr->next)
{
PageSetLSN(ptr->page, recptr);
}
/*
* Return the new child buffers to the caller.
*
* If this was a root split, we've already inserted the downlink
* pointers, in the form of a new root page. Therefore we can release
* all the new buffers, and keep just the root page locked.
*/
if (is_rootsplit)
{
for (ptr = dist->next; ptr; ptr = ptr->next)
UnlockReleaseBuffer(ptr->buffer);
}
}
else
{
/*
* Enough space. We also get here if ntuples==0.
*/
START_CRIT_SECTION();
if (OffsetNumberIsValid(oldoffnum))
PageIndexTupleDelete(page, oldoffnum);
gistfillbuffer(page, itup, ntup, InvalidOffsetNumber);
MarkBufferDirty(buffer);
if (BufferIsValid(leftchildbuf))
MarkBufferDirty(leftchildbuf);
if (RelationNeedsWAL(rel))
{
OffsetNumber ndeloffs = 0,
deloffs[1];
if (OffsetNumberIsValid(oldoffnum))
{
deloffs[0] = oldoffnum;
ndeloffs = 1;
}
recptr = gistXLogUpdate(rel->rd_node, buffer,
deloffs, ndeloffs, itup, ntup,
leftchildbuf);
PageSetLSN(page, recptr);
}
else
{
recptr = gistGetFakeLSN(rel);
PageSetLSN(page, recptr);
}
if (newblkno)
*newblkno = blkno;
}
/*
* If we inserted the downlink for a child page, set NSN and clear
* F_FOLLOW_RIGHT flag on the left child, so that concurrent scans know to
* follow the rightlink if and only if they looked at the parent page
* before we inserted the downlink.
*
* Note that we do this *after* writing the WAL record. That means that
* the possible full page image in the WAL record does not include these
* changes, and they must be replayed even if the page is restored from
* the full page image. There's a chicken-and-egg problem: if we updated
* the child pages first, we wouldn't know the recptr of the WAL record
* we're about to write.
*/
if (BufferIsValid(leftchildbuf))
{
Page leftpg = BufferGetPage(leftchildbuf);
GistPageSetNSN(leftpg, recptr);
GistClearFollowRight(leftpg);
PageSetLSN(leftpg, recptr);
}
END_CRIT_SECTION();
return is_split;
}
/*
* Prune specified item pointer or a HOT chain originating at that item.
*
* If the item is an index-referenced tuple (i.e. not a heap-only tuple),
* the HOT chain is pruned by removing all DEAD tuples at the start of the HOT
* chain. We also prune any RECENTLY_DEAD tuples preceding a DEAD tuple.
* This is OK because a RECENTLY_DEAD tuple preceding a DEAD tuple is really
* DEAD, the OldestXmin test is just too coarse to detect it.
*
* The root line pointer is redirected to the tuple immediately after the
* latest DEAD tuple. If all tuples in the chain are DEAD, the root line
* pointer is marked LP_DEAD. (This includes the case of a DEAD simple
* tuple, which we treat as a chain of length 1.)
*
* OldestXmin is the cutoff XID used to identify dead tuples.
*
* We don't actually change the page here, except perhaps for hint-bit updates
* caused by HeapTupleSatisfiesVacuum. We just add entries to the arrays in
* prstate showing the changes to be made. Items to be redirected are added
* to the redirected[] array (two entries per redirection); items to be set to
* LP_DEAD state are added to nowdead[]; and items to be set to LP_UNUSED
* state are added to nowunused[].
*
* If redirect_move is true, we intend to get rid of redirecting line pointers,
* not just make redirection entries.
*
* Returns the number of tuples (to be) deleted from the page.
*/
static int
heap_prune_chain(Relation relation, Buffer buffer, OffsetNumber rootoffnum,
TransactionId OldestXmin,
PruneState *prstate,
bool redirect_move)
{
int ndeleted = 0;
Page dp = (Page) BufferGetPage(buffer);
TransactionId priorXmax = InvalidTransactionId;
ItemId rootlp;
HeapTupleHeader htup;
OffsetNumber latestdead = InvalidOffsetNumber,
redirect_target = InvalidOffsetNumber,
maxoff = PageGetMaxOffsetNumber(dp),
offnum;
OffsetNumber chainitems[MaxHeapTuplesPerPage];
int nchain = 0,
i;
rootlp = PageGetItemId(dp, rootoffnum);
/*
* If it's a heap-only tuple, then it is not the start of a HOT chain.
*/
if (ItemIdIsNormal(rootlp))
{
htup = (HeapTupleHeader) PageGetItem(dp, rootlp);
if (HeapTupleHeaderIsHeapOnly(htup))
{
/*
* If the tuple is DEAD and doesn't chain to anything else, mark
* it unused immediately. (If it does chain, we can only remove
* it as part of pruning its chain.)
*
* We need this primarily to handle aborted HOT updates, that is,
* XMIN_INVALID heap-only tuples. Those might not be linked to by
* any chain, since the parent tuple might be re-updated before
* any pruning occurs. So we have to be able to reap them
* separately from chain-pruning. (Note that
* HeapTupleHeaderIsHotUpdated will never return true for an
* XMIN_INVALID tuple, so this code will work even when there were
* sequential updates within the aborted transaction.)
*
* Note that we might first arrive at a dead heap-only tuple
* either here or while following a chain below. Whichever path
* gets there first will mark the tuple unused.
*/
if (HeapTupleSatisfiesVacuum(relation, htup, OldestXmin, buffer)
== HEAPTUPLE_DEAD && !HeapTupleHeaderIsHotUpdated(htup))
{
heap_prune_record_unused(prstate, rootoffnum);
ndeleted++;
}
/* Nothing more to do */
return ndeleted;
}
}
/* Start from the root tuple */
offnum = rootoffnum;
/* while not end of the chain */
for (;;)
{
ItemId lp;
bool tupdead,
recent_dead;
/* Some sanity checks */
if (offnum < FirstOffsetNumber || offnum > maxoff)
break;
/* If item is already processed, stop --- it must not be same chain */
if (prstate->marked[offnum])
break;
lp = PageGetItemId(dp, offnum);
/* Unused item obviously isn't part of the chain */
if (!ItemIdIsUsed(lp))
break;
/*
* If we are looking at the redirected root line pointer, jump to the
* first normal tuple in the chain. If we find a redirect somewhere
* else, stop --- it must not be same chain.
*/
if (ItemIdIsRedirected(lp))
{
if (nchain > 0)
break; /* not at start of chain */
chainitems[nchain++] = offnum;
offnum = ItemIdGetRedirect(rootlp);
continue;
}
/*
* Likewise, a dead item pointer can't be part of the chain. (We
* already eliminated the case of dead root tuple outside this
* function.)
*/
if (ItemIdIsDead(lp))
break;
Assert(ItemIdIsNormal(lp));
htup = (HeapTupleHeader) PageGetItem(dp, lp);
/*
* Check the tuple XMIN against prior XMAX, if any
*/
if (TransactionIdIsValid(priorXmax) &&
!TransactionIdEquals(HeapTupleHeaderGetXmin(htup), priorXmax))
break;
/*
* OK, this tuple is indeed a member of the chain.
*/
chainitems[nchain++] = offnum;
/*
* Check tuple's visibility status.
*/
tupdead = recent_dead = false;
switch (HeapTupleSatisfiesVacuum(relation, htup, OldestXmin, buffer))
{
case HEAPTUPLE_DEAD:
tupdead = true;
break;
case HEAPTUPLE_RECENTLY_DEAD:
recent_dead = true;
/*
* This tuple may soon become DEAD. Update the hint field so
* that the page is reconsidered for pruning in future.
*/
heap_prune_record_prunable(prstate,
HeapTupleHeaderGetXmax(htup));
break;
case HEAPTUPLE_DELETE_IN_PROGRESS:
/*
* This tuple may soon become DEAD. Update the hint field so
* that the page is reconsidered for pruning in future.
*/
heap_prune_record_prunable(prstate,
HeapTupleHeaderGetXmax(htup));
break;
case HEAPTUPLE_LIVE:
case HEAPTUPLE_INSERT_IN_PROGRESS:
/*
* If we wanted to optimize for aborts, we might consider
* marking the page prunable when we see INSERT_IN_PROGRESS.
* But we don't. See related decisions about when to mark the
* page prunable in heapam.c.
*/
break;
default:
elog(ERROR, "unexpected HeapTupleSatisfiesVacuum result");
break;
}
/*
* Remember the last DEAD tuple seen. We will advance past
* RECENTLY_DEAD tuples just in case there's a DEAD one after them;
* but we can't advance past anything else. (XXX is it really worth
* continuing to scan beyond RECENTLY_DEAD? The case where we will
* find another DEAD tuple is a fairly unusual corner case.)
*/
if (tupdead)
latestdead = offnum;
else if (!recent_dead)
break;
/*
* If the tuple is not HOT-updated, then we are at the end of this
* HOT-update chain.
*/
if (!HeapTupleHeaderIsHotUpdated(htup))
break;
/*
* Advance to next chain member.
*/
Assert(ItemPointerGetBlockNumber(&htup->t_ctid) ==
BufferGetBlockNumber(buffer));
offnum = ItemPointerGetOffsetNumber(&htup->t_ctid);
priorXmax = HeapTupleHeaderGetXmax(htup);
}
/*
* If we found a DEAD tuple in the chain, adjust the HOT chain so that all
* the DEAD tuples at the start of the chain are removed and the root line
* pointer is appropriately redirected.
*/
if (OffsetNumberIsValid(latestdead))
{
/*
* Mark as unused each intermediate item that we are able to remove
* from the chain.
*
* When the previous item is the last dead tuple seen, we are at the
* right candidate for redirection.
*/
for (i = 1; (i < nchain) && (chainitems[i - 1] != latestdead); i++)
{
heap_prune_record_unused(prstate, chainitems[i]);
ndeleted++;
}
/*
* If the root entry had been a normal tuple, we are deleting it, so
* count it in the result. But changing a redirect (even to DEAD
* state) doesn't count.
*/
if (ItemIdIsNormal(rootlp))
ndeleted++;
/*
* If the DEAD tuple is at the end of the chain, the entire chain is
* dead and the root line pointer can be marked dead. Otherwise just
* redirect the root to the correct chain member.
*/
if (i >= nchain)
heap_prune_record_dead(prstate, rootoffnum);
else
{
heap_prune_record_redirect(prstate, rootoffnum, chainitems[i]);
/* If the redirection will be a move, need more processing */
if (redirect_move)
redirect_target = chainitems[i];
}
}
else if (nchain < 2 && ItemIdIsRedirected(rootlp))
{
/*
* We found a redirect item that doesn't point to a valid follow-on
* item. This can happen if the loop in heap_page_prune caused us to
* visit the dead successor of a redirect item before visiting the
* redirect item. We can clean up by setting the redirect item to
* DEAD state.
*/
heap_prune_record_dead(prstate, rootoffnum);
}
else if (redirect_move && ItemIdIsRedirected(rootlp))
{
/*
* If we desire to eliminate LP_REDIRECT items by moving tuples, make
* a redirection entry for each redirected root item; this will cause
* heap_page_prune_execute to actually do the move. (We get here only
* when there are no DEAD tuples in the chain; otherwise the
* redirection entry was made above.)
*/
heap_prune_record_redirect(prstate, rootoffnum, chainitems[1]);
redirect_target = chainitems[1];
}
/*
* If we are going to implement a redirect by moving tuples, we have to
* issue a cache invalidation against the redirection target tuple,
* because its CTID will be effectively changed by the move. Note that
* CacheInvalidateHeapTuple only queues the request, it doesn't send it;
* if we fail before reaching EndNonTransactionalInvalidation, nothing
* happens and no harm is done.
*/
if (OffsetNumberIsValid(redirect_target))
{
ItemId firstlp = PageGetItemId(dp, redirect_target);
HeapTupleData firsttup;
Assert(ItemIdIsNormal(firstlp));
/* Set up firsttup to reference the tuple at its existing CTID */
firsttup.t_data = (HeapTupleHeader) PageGetItem(dp, firstlp);
firsttup.t_len = ItemIdGetLength(firstlp);
ItemPointerSet(&firsttup.t_self,
BufferGetBlockNumber(buffer),
redirect_target);
CacheInvalidateHeapTuple(relation, &firsttup);
}
return ndeleted;
}
/*
* PageAddItem
*
* Add an item to a page. Return value is offset at which it was
* inserted, or InvalidOffsetNumber if there's not room to insert.
*
* If overwrite is true, we just store the item at the specified
* offsetNumber (which must be either a currently-unused item pointer,
* or one past the last existing item). Otherwise,
* if offsetNumber is valid and <= current max offset in the page,
* insert item into the array at that position by shuffling ItemId's
* down to make room.
* If offsetNumber is not valid, then assign one by finding the first
* one that is both unused and deallocated.
*
* If is_heap is true, we enforce that there can't be more than
* MaxHeapTuplesPerPage line pointers on the page.
*
* !!! EREPORT(ERROR) IS DISALLOWED HERE !!!
*/
OffsetNumber
PageAddItem(Page page,
Item item,
Size size,
OffsetNumber offsetNumber,
bool overwrite,
bool is_heap)
{
PageHeader phdr = (PageHeader) page;
Size alignedSize;
int lower;
int upper;
ItemId itemId;
OffsetNumber limit;
bool needshuffle = false;
/*
* Be wary about corrupted page pointers
*/
if (phdr->pd_lower < SizeOfPageHeaderData ||
phdr->pd_lower > phdr->pd_upper ||
phdr->pd_upper > phdr->pd_special ||
phdr->pd_special > BLCKSZ)
ereport(PANIC,
(errcode(ERRCODE_DATA_CORRUPTED),
errmsg("corrupted page pointers: lower = %u, upper = %u, special = %u",
phdr->pd_lower, phdr->pd_upper, phdr->pd_special)));
/*
* Select offsetNumber to place the new item at
*/
limit = OffsetNumberNext(PageGetMaxOffsetNumber(page));
/* was offsetNumber passed in? */
if (OffsetNumberIsValid(offsetNumber))
{
/* yes, check it */
if (overwrite)
{
if (offsetNumber < limit)
{
itemId = PageGetItemId(phdr, offsetNumber);
if (ItemIdIsUsed(itemId) || ItemIdHasStorage(itemId))
{
elog(WARNING, "will not overwrite a used ItemId");
return InvalidOffsetNumber;
}
}
}
else
{
if (offsetNumber < limit)
needshuffle = true; /* need to move existing linp's */
}
}
else
{
/* offsetNumber was not passed in, so find a free slot */
/* if no free slot, we'll put it at limit (1st open slot) */
if (PageHasFreeLinePointers(phdr))
{
/*
* Look for "recyclable" (unused) ItemId. We check for no storage
* as well, just to be paranoid --- unused items should never have
* storage.
*/
for (offsetNumber = 1; offsetNumber < limit; offsetNumber++)
{
itemId = PageGetItemId(phdr, offsetNumber);
if (!ItemIdIsUsed(itemId) && !ItemIdHasStorage(itemId))
break;
}
if (offsetNumber >= limit)
{
/* the hint is wrong, so reset it */
PageClearHasFreeLinePointers(phdr);
}
}
else
{
/* don't bother searching if hint says there's no free slot */
offsetNumber = limit;
}
}
if (offsetNumber > limit)
{
elog(WARNING, "specified item offset is too large");
return InvalidOffsetNumber;
}
if (is_heap && offsetNumber > MaxHeapTuplesPerPage)
{
elog(WARNING, "can't put more than MaxHeapTuplesPerPage items in a heap page");
return InvalidOffsetNumber;
}
/*
* Compute new lower and upper pointers for page, see if it'll fit.
*
* Note: do arithmetic as signed ints, to avoid mistakes if, say,
* alignedSize > pd_upper.
*/
if (offsetNumber == limit || needshuffle)
lower = phdr->pd_lower + sizeof(ItemIdData);
else
lower = phdr->pd_lower;
alignedSize = MAXALIGN(size);
upper = (int) phdr->pd_upper - (int) alignedSize;
if (lower > upper)
return InvalidOffsetNumber;
/*
* OK to insert the item. First, shuffle the existing pointers if needed.
*/
itemId = PageGetItemId(phdr, offsetNumber);
if (needshuffle)
memmove(itemId + 1, itemId,
(limit - offsetNumber) * sizeof(ItemIdData));
/* set the item pointer */
ItemIdSetNormal(itemId, upper, size);
/* copy the item's data onto the page */
memcpy((char *) page + upper, item, size);
/* adjust page header */
phdr->pd_lower = (LocationIndex) lower;
phdr->pd_upper = (LocationIndex) upper;
return offsetNumber;
}
/*
* Fetch a tuples that matchs the search key; this can be invoked
* either to fetch the first such tuple or subsequent matching
* tuples. Returns true iff a matching tuple was found.
*/
static int
gistnext(IndexScanDesc scan, ScanDirection dir, ItemPointer tids,
int maxtids, bool ignore_killed_tuples)
{
MIRROREDLOCK_BUFMGR_DECLARE;
Page p;
OffsetNumber n;
GISTScanOpaque so;
GISTSearchStack *stk;
IndexTuple it;
GISTPageOpaque opaque;
int ntids = 0;
so = (GISTScanOpaque) scan->opaque;
// -------- MirroredLock ----------
MIRROREDLOCK_BUFMGR_LOCK;
if ( so->qual_ok == false )
return 0;
if (ItemPointerIsValid(&so->curpos) == false)
{
/* Being asked to fetch the first entry, so start at the root */
Assert(so->curbuf == InvalidBuffer);
Assert(so->stack == NULL);
so->curbuf = ReadBuffer(scan->indexRelation, GIST_ROOT_BLKNO);
stk = so->stack = (GISTSearchStack *) palloc0(sizeof(GISTSearchStack));
stk->next = NULL;
stk->block = GIST_ROOT_BLKNO;
pgstat_count_index_scan(scan->indexRelation);
}
else if (so->curbuf == InvalidBuffer)
{
MIRROREDLOCK_BUFMGR_UNLOCK;
// -------- MirroredLock ----------
return 0;
}
/*
* check stored pointers from last visit
*/
if ( so->nPageData > 0 )
{
while( ntids < maxtids && so->curPageData < so->nPageData )
{
tids[ ntids ] = scan->xs_ctup.t_self = so->pageData[ so->curPageData ].heapPtr;
ItemPointerSet(&(so->curpos),
BufferGetBlockNumber(so->curbuf),
so->pageData[ so->curPageData ].pageOffset);
so->curPageData ++;
ntids++;
}
if ( ntids == maxtids )
{
MIRROREDLOCK_BUFMGR_UNLOCK;
// -------- MirroredLock ----------
return ntids;
}
/*
* Go to the next page
*/
stk = so->stack->next;
pfree(so->stack);
so->stack = stk;
/* If we're out of stack entries, we're done */
if (so->stack == NULL)
{
ReleaseBuffer(so->curbuf);
so->curbuf = InvalidBuffer;
MIRROREDLOCK_BUFMGR_UNLOCK;
// -------- MirroredLock ----------
return ntids;
}
so->curbuf = ReleaseAndReadBuffer(so->curbuf,
scan->indexRelation,
stk->block);
}
for (;;)
{
/* First of all, we need lock buffer */
Assert(so->curbuf != InvalidBuffer);
LockBuffer(so->curbuf, GIST_SHARE);
gistcheckpage(scan->indexRelation, so->curbuf);
p = BufferGetPage(so->curbuf);
opaque = GistPageGetOpaque(p);
/* remember lsn to identify page changed for tuple's killing */
so->stack->lsn = PageGetLSN(p);
/* check page split, occured from last visit or visit to parent */
if (!XLogRecPtrIsInvalid(so->stack->parentlsn) &&
XLByteLT(so->stack->parentlsn, opaque->nsn) &&
opaque->rightlink != InvalidBlockNumber /* sanity check */ &&
(so->stack->next == NULL || so->stack->next->block != opaque->rightlink) /* check if already
added */ )
{
/* detect page split, follow right link to add pages */
stk = (GISTSearchStack *) palloc(sizeof(GISTSearchStack));
stk->next = so->stack->next;
stk->block = opaque->rightlink;
stk->parentlsn = so->stack->parentlsn;
memset(&(stk->lsn), 0, sizeof(GistNSN));
so->stack->next = stk;
}
/* if page is empty, then just skip it */
if (PageIsEmpty(p))
{
LockBuffer(so->curbuf, GIST_UNLOCK);
stk = so->stack->next;
pfree(so->stack);
so->stack = stk;
if (so->stack == NULL)
{
ReleaseBuffer(so->curbuf);
so->curbuf = InvalidBuffer;
MIRROREDLOCK_BUFMGR_UNLOCK;
// -------- MirroredLock ----------
return ntids;
}
so->curbuf = ReleaseAndReadBuffer(so->curbuf, scan->indexRelation,
stk->block);
continue;
}
if (ScanDirectionIsBackward(dir))
n = PageGetMaxOffsetNumber(p);
else
n = FirstOffsetNumber;
/* wonderful, we can look at page */
so->nPageData = so->curPageData = 0;
for (;;)
{
n = gistfindnext(scan, n, dir);
if (!OffsetNumberIsValid(n))
{
while( ntids < maxtids && so->curPageData < so->nPageData )
{
tids[ ntids ] = scan->xs_ctup.t_self =
so->pageData[ so->curPageData ].heapPtr;
ItemPointerSet(&(so->curpos),
BufferGetBlockNumber(so->curbuf),
so->pageData[ so->curPageData ].pageOffset);
so->curPageData ++;
ntids++;
}
if ( ntids == maxtids )
{
LockBuffer(so->curbuf, GIST_UNLOCK);
MIRROREDLOCK_BUFMGR_UNLOCK;
// -------- MirroredLock ----------
return ntids;
}
/*
* We ran out of matching index entries on the current page,
* so pop the top stack entry and use it to continue the
* search.
*/
LockBuffer(so->curbuf, GIST_UNLOCK);
stk = so->stack->next;
pfree(so->stack);
so->stack = stk;
/* If we're out of stack entries, we're done */
if (so->stack == NULL)
{
ReleaseBuffer(so->curbuf);
so->curbuf = InvalidBuffer;
MIRROREDLOCK_BUFMGR_UNLOCK;
// -------- MirroredLock ----------
return ntids;
}
so->curbuf = ReleaseAndReadBuffer(so->curbuf,
scan->indexRelation,
stk->block);
/* XXX go up */
break;
}
if (GistPageIsLeaf(p))
{
/*
* We've found a matching index entry in a leaf page, so
* return success. Note that we keep "curbuf" pinned so that
* we can efficiently resume the index scan later.
*/
if (!(ignore_killed_tuples && ItemIdIsDead(PageGetItemId(p, n))))
{
it = (IndexTuple) PageGetItem(p, PageGetItemId(p, n));
so->pageData[ so->nPageData ].heapPtr = it->t_tid;
so->pageData[ so->nPageData ].pageOffset = n;
so->nPageData ++;
}
}
else
{
/*
* We've found an entry in an internal node whose key is
* consistent with the search key, so push it to stack
*/
stk = (GISTSearchStack *) palloc(sizeof(GISTSearchStack));
it = (IndexTuple) PageGetItem(p, PageGetItemId(p, n));
stk->block = ItemPointerGetBlockNumber(&(it->t_tid));
memset(&(stk->lsn), 0, sizeof(GistNSN));
stk->parentlsn = so->stack->lsn;
stk->next = so->stack->next;
so->stack->next = stk;
}
if (ScanDirectionIsBackward(dir))
n = OffsetNumberPrev(n);
else
n = OffsetNumberNext(n);
}
}
MIRROREDLOCK_BUFMGR_UNLOCK;
// -------- MirroredLock ----------
return ntids;
}
