/*
* Insert or replace a tuple in stack->buffer. If 'oldoffnum' is valid, the
* tuple at 'oldoffnum' is replaced, otherwise the tuple is inserted as new.
* 'stack' represents the path from the root to the page being updated.
*
* The caller must hold an exclusive lock on stack->buffer. The lock is still
* held on return, but the page might not contain the inserted tuple if the
* page was split. The function returns true if the page was split, false
* otherwise.
*/
static bool
gistinserttuple(GISTInsertState *state, GISTInsertStack *stack,
GISTSTATE *giststate, IndexTuple tuple, OffsetNumber oldoffnum)
{
return gistinserttuples(state, stack, giststate, &tuple, 1, oldoffnum,
InvalidBuffer, InvalidBuffer, false, false);
}
/*
* 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.
*/
static 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.xrecoff = 0;
firststack.parent = NULL;
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 &&
XLByteLT(stack->parent->lsn,
GistPageGetOpaque(stack->page)->nsn))
{
/*
* 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;
stack->childoffnum = gistchoose(state.r, stack->page, itup, giststate);
iid = PageGetItemId(stack->page, stack->childoffnum);
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 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 (!XLByteEQ(PageGetLSN(stack->page), stack->lsn))
{
/* the page was changed while we unlocked it, retry */
continue;
}
}
/*
* Update the tuple.
*
* gistinserthere() might have to split the page to make the
* updated tuple fit. It will adjust the stack so that after
* the call, we'll be holding a lock on the page containing
* the tuple, which might have moved right.
*
* Except if this causes a root split, gistinserthere()
* returns 'true'. In that case, stack only holds the new
* root, and the child page was released. Have to start
* all over.
*/
if (gistinserttuples(&state, stack, giststate, &newtup, 1,
stack->childoffnum, InvalidBuffer))
{
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;
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) ||
XLByteLT(stack->parent->lsn,
GistPageGetOpaque(stack->page)->nsn))
{
/*
* 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 */
gistinserttuples(&state, stack, giststate, &itup, 1,
InvalidOffsetNumber, InvalidBuffer);
LockBuffer(stack->buffer, GIST_UNLOCK);
/* Release any pins we might still hold before exiting */
for (; stack; stack = stack->parent)
ReleaseBuffer(stack->buffer);
break;
}
}
}
