/*
* Process an index tuple. Runs the tuple down the tree until we reach a leaf
* page or node buffer, and inserts the tuple there. Returns true if we have
* to stop buffer emptying process (because one of child buffers can't take
* index tuples anymore).
*/
static bool
gistProcessItup(GISTBuildState *buildstate, IndexTuple itup,
BlockNumber startblkno, int startlevel)
{
GISTSTATE *giststate = buildstate->giststate;
GISTBuildBuffers *gfbb = buildstate->gfbb;
Relation indexrel = buildstate->indexrel;
BlockNumber childblkno;
Buffer buffer;
bool result = false;
BlockNumber blkno;
int level;
OffsetNumber downlinkoffnum = InvalidOffsetNumber;
BlockNumber parentblkno = InvalidBlockNumber;
CHECK_FOR_INTERRUPTS();
/*
* Loop until we reach a leaf page (level == 0) or a level with buffers
* (not including the level we start at, because we would otherwise make
* no progress).
*/
blkno = startblkno;
level = startlevel;
for (;;)
{
ItemId iid;
IndexTuple idxtuple,
newtup;
Page page;
OffsetNumber childoffnum;
/* Have we reached a level with buffers? */
if (LEVEL_HAS_BUFFERS(level, gfbb) && level != startlevel)
break;
/* Have we reached a leaf page? */
if (level == 0)
break;
/*
* Nope. Descend down to the next level then. Choose a child to
* descend down to.
*/
buffer = ReadBuffer(indexrel, blkno);
LockBuffer(buffer, GIST_EXCLUSIVE);
page = (Page) BufferGetPage(buffer);
childoffnum = gistchoose(indexrel, page, itup, giststate);
iid = PageGetItemId(page, childoffnum);
idxtuple = (IndexTuple) PageGetItem(page, iid);
childblkno = ItemPointerGetBlockNumber(&(idxtuple->t_tid));
if (level > 1)
gistMemorizeParent(buildstate, childblkno, blkno);
/*
* Check that the key representing the target child node is consistent
* with the key we're inserting. Update it if it's not.
*/
newtup = gistgetadjusted(indexrel, idxtuple, itup, giststate);
if (newtup)
{
blkno = gistbufferinginserttuples(buildstate, buffer, level,
&newtup, 1, childoffnum,
InvalidBlockNumber, InvalidOffsetNumber);
/* gistbufferinginserttuples() released the buffer */
}
else
UnlockReleaseBuffer(buffer);
/* Descend to the child */
parentblkno = blkno;
blkno = childblkno;
downlinkoffnum = childoffnum;
Assert(level > 0);
level--;
}
if (LEVEL_HAS_BUFFERS(level, gfbb))
{
/*
* We've reached level with buffers. Place the index tuple to the
* buffer, and add the buffer to the emptying queue if it overflows.
*/
GISTNodeBuffer *childNodeBuffer;
/* Find the buffer or create a new one */
childNodeBuffer = gistGetNodeBuffer(gfbb, giststate, blkno, level);
/* Add index tuple to it */
gistPushItupToNodeBuffer(gfbb, childNodeBuffer, itup);
if (BUFFER_OVERFLOWED(childNodeBuffer, gfbb))
result = true;
}
else
{
/*
* We've reached a leaf page. Place the tuple here.
*/
Assert(level == 0);
buffer = ReadBuffer(indexrel, blkno);
LockBuffer(buffer, GIST_EXCLUSIVE);
gistbufferinginserttuples(buildstate, buffer, level,
&itup, 1, InvalidOffsetNumber,
parentblkno, downlinkoffnum);
/* gistbufferinginserttuples() released the buffer */
}
return result;
}
/*
* Process an index tuple. Runs the tuple down the tree until we reach a leaf
* page or node buffer, and inserts the tuple there. Returns true if we have
* to stop buffer emptying process (because one of child buffers can't take
* index tuples anymore).
*/
static bool
gistProcessItup(GISTBuildState *buildstate, IndexTuple itup,
GISTBufferingInsertStack *startparent)
{
GISTSTATE *giststate = buildstate->giststate;
GISTBuildBuffers *gfbb = buildstate->gfbb;
Relation indexrel = buildstate->indexrel;
GISTBufferingInsertStack *path;
BlockNumber childblkno;
Buffer buffer;
bool result = false;
/*
* NULL passed in startparent means that we start index tuple processing
* from the root.
*/
if (!startparent)
path = gfbb->rootitem;
else
path = startparent;
/*
* Loop until we reach a leaf page (level == 0) or a level with buffers
* (not including the level we start at, because we would otherwise make
* no progress).
*/
for (;;)
{
ItemId iid;
IndexTuple idxtuple,
newtup;
Page page;
OffsetNumber childoffnum;
GISTBufferingInsertStack *parent;
/* Have we reached a level with buffers? */
if (LEVEL_HAS_BUFFERS(path->level, gfbb) && path != startparent)
break;
/* Have we reached a leaf page? */
if (path->level == 0)
break;
/*
* Nope. Descend down to the next level then. Choose a child to
* descend down to.
*/
buffer = ReadBuffer(indexrel, path->blkno);
LockBuffer(buffer, GIST_EXCLUSIVE);
page = (Page) BufferGetPage(buffer);
childoffnum = gistchoose(indexrel, page, itup, giststate);
iid = PageGetItemId(page, childoffnum);
idxtuple = (IndexTuple) PageGetItem(page, iid);
childblkno = ItemPointerGetBlockNumber(&(idxtuple->t_tid));
/*
* Check that the key representing the target child node is consistent
* with the key we're inserting. Update it if it's not.
*/
newtup = gistgetadjusted(indexrel, idxtuple, itup, giststate);
if (newtup)
gistbufferinginserttuples(buildstate, buffer, &newtup, 1,
childoffnum, path);
UnlockReleaseBuffer(buffer);
/* Create new path item representing current page */
parent = path;
path = (GISTBufferingInsertStack *) MemoryContextAlloc(gfbb->context,
sizeof(GISTBufferingInsertStack));
path->parent = parent;
path->level = parent->level - 1;
path->blkno = childblkno;
path->downlinkoffnum = childoffnum;
path->refCount = 0; /* it's unreferenced for now */
/* Adjust reference count of parent */
if (parent)
parent->refCount++;
}
if (LEVEL_HAS_BUFFERS(path->level, gfbb))
{
/*
* We've reached level with buffers. Place the index tuple to the
* buffer, and add the buffer to the emptying queue if it overflows.
*/
GISTNodeBuffer *childNodeBuffer;
/* Find the buffer or create a new one */
childNodeBuffer = gistGetNodeBuffer(gfbb, giststate, path->blkno,
path->downlinkoffnum, path->parent);
/* Add index tuple to it */
gistPushItupToNodeBuffer(gfbb, childNodeBuffer, itup);
if (BUFFER_OVERFLOWED(childNodeBuffer, gfbb))
result = true;
}
else
{
/*
* We've reached a leaf page. Place the tuple here.
*/
buffer = ReadBuffer(indexrel, path->blkno);
LockBuffer(buffer, GIST_EXCLUSIVE);
gistbufferinginserttuples(buildstate, buffer, &itup, 1,
InvalidOffsetNumber, path);
UnlockReleaseBuffer(buffer);
}
/*
* Free unreferenced path items, if any. Path item may be referenced by
* node buffer.
*/
gistFreeUnreferencedPath(path);
return result;
}
static void
gistfindleaf(GISTInsertState *state, GISTSTATE *giststate)
{
ItemId iid;
IndexTuple idxtuple;
GISTPageOpaque opaque;
MIRROREDLOCK_BUFMGR_MUST_ALREADY_BE_HELD;
/*
* walk down, We don't lock page for a long time, but so we should be
* ready to recheck path in a bad case... We remember, that page->lsn
* should never be invalid.
*/
for (;;)
{
if (XLogRecPtrIsInvalid(state->stack->lsn))
state->stack->buffer = ReadBuffer(state->r, state->stack->blkno);
LockBuffer(state->stack->buffer, GIST_SHARE);
gistcheckpage(state->r, state->stack->buffer);
state->stack->page = (Page) BufferGetPage(state->stack->buffer);
opaque = GistPageGetOpaque(state->stack->page);
state->stack->lsn = PageGetLSN(state->stack->page);
Assert(state->r->rd_istemp || !XLogRecPtrIsInvalid(state->stack->lsn));
if (state->stack->blkno != GIST_ROOT_BLKNO &&
XLByteLT(state->stack->parent->lsn, opaque->nsn))
{
/*
* caused split non-root page is detected, go up to parent to
* choose best child
*/
UnlockReleaseBuffer(state->stack->buffer);
state->stack = state->stack->parent;
continue;
}
if (!GistPageIsLeaf(state->stack->page))
{
/*
* This is an internal page, so continue to walk down the tree. We
* find the child node that has the minimum insertion penalty and
* recursively invoke ourselves to modify that node. Once the
* recursive call returns, we may need to adjust the parent node
* for two reasons: the child node split, or the key in this node
* needs to be adjusted for the newly inserted key below us.
*/
GISTInsertStack *item = (GISTInsertStack *) palloc0(sizeof(GISTInsertStack));
state->stack->childoffnum = gistchoose(state->r, state->stack->page, state->itup[0], giststate);
iid = PageGetItemId(state->stack->page, state->stack->childoffnum);
idxtuple = (IndexTuple) PageGetItem(state->stack->page, iid);
item->blkno = ItemPointerGetBlockNumber(&(idxtuple->t_tid));
LockBuffer(state->stack->buffer, GIST_UNLOCK);
item->parent = state->stack;
item->child = NULL;
if (state->stack)
state->stack->child = item;
state->stack = item;
}
else
{
/* be carefull, during unlock/lock page may be changed... */
LockBuffer(state->stack->buffer, GIST_UNLOCK);
LockBuffer(state->stack->buffer, GIST_EXCLUSIVE);
state->stack->page = (Page) BufferGetPage(state->stack->buffer);
opaque = GistPageGetOpaque(state->stack->page);
if (state->stack->blkno == GIST_ROOT_BLKNO)
{
/*
* the only page can become inner instead of leaf is a root
* page, so for root we should recheck it
*/
if (!GistPageIsLeaf(state->stack->page))
{
/*
* very rarely situation: during unlock/lock index with
* number of pages = 1 was increased
*/
LockBuffer(state->stack->buffer, GIST_UNLOCK);
continue;
}
/*
* we don't need to check root split, because checking
* leaf/inner is enough to recognize split for root
*/
}
else if (XLByteLT(state->stack->parent->lsn, opaque->nsn))
{
/*
* detecting split during unlock/lock, so we should find
* better child on parent
*/
/* forget buffer */
UnlockReleaseBuffer(state->stack->buffer);
state->stack = state->stack->parent;
continue;
}
state->stack->lsn = PageGetLSN(state->stack->page);
/* ok we found a leaf page and it X-locked */
break;
}
}
/* now state->stack->(page, buffer and blkno) points to leaf page */
}
/*
* Workhouse routine for doing insertion into a GiST index. Note that
* this routine assumes it is invoked in a short-lived memory context,
* so it does not bother releasing palloc'd allocations.
*/
void
gistdoinsert(Relation r, IndexTuple itup, Size freespace, GISTSTATE *giststate)
{
ItemId iid;
IndexTuple idxtuple;
GISTInsertStack firststack;
GISTInsertStack *stack;
GISTInsertState state;
bool xlocked = false;
memset(&state, 0, sizeof(GISTInsertState));
state.freespace = freespace;
state.r = r;
/* Start from the root */
firststack.blkno = GIST_ROOT_BLKNO;
firststack.lsn = 0;
firststack.parent = NULL;
firststack.downlinkoffnum = InvalidOffsetNumber;
state.stack = stack = &firststack;
/*
* Walk down along the path of smallest penalty, updating the parent
* pointers with the key we're inserting as we go. If we crash in the
* middle, the tree is consistent, although the possible parent updates
* were a waste.
*/
for (;;)
{
if (XLogRecPtrIsInvalid(stack->lsn))
stack->buffer = ReadBuffer(state.r, stack->blkno);
/*
* Be optimistic and grab shared lock first. Swap it for an exclusive
* lock later if we need to update the page.
*/
if (!xlocked)
{
LockBuffer(stack->buffer, GIST_SHARE);
gistcheckpage(state.r, stack->buffer);
}
stack->page = (Page) BufferGetPage(stack->buffer);
stack->lsn = PageGetLSN(stack->page);
Assert(!RelationNeedsWAL(state.r) || !XLogRecPtrIsInvalid(stack->lsn));
/*
* If this page was split but the downlink was never inserted to the
* parent because the inserting backend crashed before doing that, fix
* that now.
*/
if (GistFollowRight(stack->page))
{
if (!xlocked)
{
LockBuffer(stack->buffer, GIST_UNLOCK);
LockBuffer(stack->buffer, GIST_EXCLUSIVE);
xlocked = true;
/* someone might've completed the split when we unlocked */
if (!GistFollowRight(stack->page))
continue;
}
gistfixsplit(&state, giststate);
UnlockReleaseBuffer(stack->buffer);
xlocked = false;
state.stack = stack = stack->parent;
continue;
}
if (stack->blkno != GIST_ROOT_BLKNO &&
stack->parent->lsn < GistPageGetNSN(stack->page))
{
/*
* Concurrent split detected. There's no guarantee that the
* downlink for this page is consistent with the tuple we're
* inserting anymore, so go back to parent and rechoose the best
* child.
*/
UnlockReleaseBuffer(stack->buffer);
xlocked = false;
state.stack = stack = stack->parent;
continue;
}
if (!GistPageIsLeaf(stack->page))
{
/*
* This is an internal page so continue to walk down the tree.
* Find the child node that has the minimum insertion penalty.
*/
BlockNumber childblkno;
IndexTuple newtup;
GISTInsertStack *item;
OffsetNumber downlinkoffnum;
downlinkoffnum = gistchoose(state.r, stack->page, itup, giststate);
iid = PageGetItemId(stack->page, downlinkoffnum);
idxtuple = (IndexTuple) PageGetItem(stack->page, iid);
childblkno = ItemPointerGetBlockNumber(&(idxtuple->t_tid));
/*
* Check that it's not a leftover invalid tuple from pre-9.1
*/
if (GistTupleIsInvalid(idxtuple))
ereport(ERROR,
(errmsg("index \"%s\" contains an inner tuple marked as invalid",
RelationGetRelationName(r)),
errdetail("This is caused by an incomplete page split at crash recovery before upgrading to PostgreSQL 9.1."),
errhint("Please REINDEX it.")));
/*
* Check that the key representing the target child node is
* consistent with the key we're inserting. Update it if it's not.
*/
newtup = gistgetadjusted(state.r, idxtuple, itup, giststate);
if (newtup)
{
/*
* Swap shared lock for an exclusive one. Beware, the page may
* change while we unlock/lock the page...
*/
if (!xlocked)
{
LockBuffer(stack->buffer, GIST_UNLOCK);
LockBuffer(stack->buffer, GIST_EXCLUSIVE);
xlocked = true;
stack->page = (Page) BufferGetPage(stack->buffer);
if (PageGetLSN(stack->page) != stack->lsn)
{
/* the page was changed while we unlocked it, retry */
continue;
}
}
/*
* Update the tuple.
*
* We still hold the lock after gistinserttuple(), but it
* might have to split the page to make the updated tuple fit.
* In that case the updated tuple might migrate to the other
* half of the split, so we have to go back to the parent and
* descend back to the half that's a better fit for the new
* tuple.
*/
if (gistinserttuple(&state, stack, giststate, newtup,
downlinkoffnum))
{
/*
* If this was a root split, the root page continues to be
* the parent and the updated tuple went to one of the
* child pages, so we just need to retry from the root
* page.
*/
if (stack->blkno != GIST_ROOT_BLKNO)
{
UnlockReleaseBuffer(stack->buffer);
xlocked = false;
state.stack = stack = stack->parent;
}
continue;
}
}
LockBuffer(stack->buffer, GIST_UNLOCK);
xlocked = false;
/* descend to the chosen child */
item = (GISTInsertStack *) palloc0(sizeof(GISTInsertStack));
item->blkno = childblkno;
item->parent = stack;
item->downlinkoffnum = downlinkoffnum;
state.stack = stack = item;
}
else
{
/*
* Leaf page. Insert the new key. We've already updated all the
* parents on the way down, but we might have to split the page if
* it doesn't fit. gistinserthere() will take care of that.
*/
/*
* Swap shared lock for an exclusive one. Be careful, the page may
* change while we unlock/lock the page...
*/
if (!xlocked)
{
LockBuffer(stack->buffer, GIST_UNLOCK);
LockBuffer(stack->buffer, GIST_EXCLUSIVE);
xlocked = true;
stack->page = (Page) BufferGetPage(stack->buffer);
stack->lsn = PageGetLSN(stack->page);
if (stack->blkno == GIST_ROOT_BLKNO)
{
/*
* the only page that can become inner instead of leaf is
* the root page, so for root we should recheck it
*/
if (!GistPageIsLeaf(stack->page))
{
/*
* very rare situation: during unlock/lock index with
* number of pages = 1 was increased
*/
LockBuffer(stack->buffer, GIST_UNLOCK);
xlocked = false;
continue;
}
/*
* we don't need to check root split, because checking
* leaf/inner is enough to recognize split for root
*/
}
else if (GistFollowRight(stack->page) ||
stack->parent->lsn < GistPageGetNSN(stack->page))
{
/*
* The page was split while we momentarily unlocked the
* page. Go back to parent.
*/
UnlockReleaseBuffer(stack->buffer);
xlocked = false;
state.stack = stack = stack->parent;
continue;
}
}
/* now state.stack->(page, buffer and blkno) points to leaf page */
gistinserttuple(&state, stack, giststate, itup,
InvalidOffsetNumber);
LockBuffer(stack->buffer, GIST_UNLOCK);
/* Release any pins we might still hold before exiting */
for (; stack; stack = stack->parent)
ReleaseBuffer(stack->buffer);
break;
}
}
}
static int
gistlayerinsert(Relation r, BlockNumber blkno,
IndexTuple **itup, /* in - out, has compressed entry */
int *len, /* in - out */
InsertIndexResult *res, /* out */
GISTSTATE *giststate)
{
Buffer buffer;
Page page;
OffsetNumber child;
int ret;
GISTPageOpaque opaque;
buffer = ReadBuffer(r, blkno);
page = (Page) BufferGetPage(buffer);
opaque = (GISTPageOpaque) PageGetSpecialPointer(page);
if (!(opaque->flags & F_LEAF))
{
/* internal page, so we must walk on tree */
/* len IS equal 1 */
ItemId iid;
BlockNumber nblkno;
ItemPointerData oldtid;
IndexTuple oldtup;
child = gistchoose(r, page, *(*itup), giststate);
iid = PageGetItemId(page, child);
oldtup = (IndexTuple) PageGetItem(page, iid);
nblkno = ItemPointerGetBlockNumber(&(oldtup->t_tid));
/*
* After this call: 1. if child page was splited, then itup
* contains keys for each page 2. if child page wasn't splited,
* then itup contains additional for adjustment of current key
*/
ret = gistlayerinsert(r, nblkno, itup, len, res, giststate);
/* nothing inserted in child */
if (!(ret & INSERTED))
{
ReleaseBuffer(buffer);
return 0x00;
}
/* child does not splited */
if (!(ret & SPLITED))
{
IndexTuple newtup = gistgetadjusted(r, oldtup, (*itup)[0], giststate);
if (!newtup)
{
/* not need to update key */
ReleaseBuffer(buffer);
return 0x00;
}
pfree((*itup)[0]); /* !!! */
(*itup)[0] = newtup;
}
/* key is modified, so old version must be deleted */
ItemPointerSet(&oldtid, blkno, child);
gistdelete(r, &oldtid);
/*
* if child was splitted, new key for child will be inserted in
* the end list of child, so we must say to any scans that page is
* changed beginning from 'child' offset
*/
if (ret & SPLITED)
gistadjscans(r, GISTOP_SPLIT, blkno, child);
}
ret = INSERTED;
if (gistnospace(page, (*itup), *len))
{
/* no space for insertion */
IndexTuple *itvec,
*newitup;
int tlen,
oldlen;
ret |= SPLITED;
itvec = gistreadbuffer(buffer, &tlen);
itvec = gistjoinvector(itvec, &tlen, (*itup), *len);
oldlen = *len;
newitup = gistSplit(r, buffer, itvec, &tlen, giststate,
(opaque->flags & F_LEAF) ? res : NULL); /* res only for
* inserting in leaf */
ReleaseBuffer(buffer);
do
pfree((*itup)[oldlen - 1]);
while ((--oldlen) > 0);
pfree((*itup));
pfree(itvec);
*itup = newitup;
*len = tlen; /* now tlen >= 2 */
}
else
{
/* enogth space */
OffsetNumber off,
l;
off = (PageIsEmpty(page)) ?
FirstOffsetNumber
:
OffsetNumberNext(PageGetMaxOffsetNumber(page));
l = gistwritebuffer(r, page, (*itup), *len, off);
WriteBuffer(buffer);
/*
* set res if insert into leaf page, in this case, len = 1 always
*/
if (res && (opaque->flags & F_LEAF))
ItemPointerSet(&((*res)->pointerData), blkno, l);
if (*len > 1)
{ /* previous insert ret & SPLITED != 0 */
int i;
/*
* child was splited, so we must form union for insertion in
* parent
*/
IndexTuple newtup = gistunion(r, (*itup), *len, giststate);
ItemPointerSet(&(newtup->t_tid), blkno, 1);
for (i = 0; i < *len; i++)
pfree((*itup)[i]);
(*itup)[0] = newtup;
*len = 1;
}
}
return ret;
}