/*
* Inserts array of item pointers, may execute several tree scan (very rare)
*/
void
ginInsertItemPointers(GinPostingTreeScan *gdi,
ItemPointerData *items, uint32 nitem,
GinStatsData *buildStats)
{
BlockNumber rootBlkno = gdi->stack->blkno;
gdi->btree.items = items;
gdi->btree.nitem = nitem;
gdi->btree.curitem = 0;
while (gdi->btree.curitem < gdi->btree.nitem)
{
if (!gdi->stack)
gdi->stack = ginPrepareFindLeafPage(&gdi->btree, rootBlkno);
gdi->stack = ginFindLeafPage(&gdi->btree, gdi->stack);
if (gdi->btree.findItem(&(gdi->btree), gdi->stack))
{
/*
* gdi->btree.items[gdi->btree.curitem] already exists in index
*/
gdi->btree.curitem++;
LockBuffer(gdi->stack->buffer, GIN_UNLOCK);
freeGinBtreeStack(gdi->stack);
}
else
ginInsertValue(&(gdi->btree), gdi->stack, buildStats);
gdi->stack = NULL;
}
}
/*
* Inserts array of item pointers, may execute several tree scan (very rare)
*/
void
ginInsertItemPointers(Relation index, BlockNumber rootBlkno,
ItemPointerData *items, uint32 nitem,
GinStatsData *buildStats)
{
GinBtreeData btree;
GinBtreeDataLeafInsertData insertdata;
GinBtreeStack *stack;
ginPrepareDataScan(&btree, index, rootBlkno);
btree.isBuild = (buildStats != NULL);
insertdata.items = items;
insertdata.nitem = nitem;
insertdata.curitem = 0;
while (insertdata.curitem < insertdata.nitem)
{
/* search for the leaf page where the first item should go to */
btree.itemptr = insertdata.items[insertdata.curitem];
stack = ginFindLeafPage(&btree, false);
if (btree.findItem(&btree, stack))
{
/*
* Current item already exists in index.
*/
insertdata.curitem++;
LockBuffer(stack->buffer, GIN_UNLOCK);
freeGinBtreeStack(stack);
}
else
ginInsertValue(&btree, stack, &insertdata, buildStats);
}
}
/*
* Inserts only one entry to the index, but it can add more than 1 ItemPointer.
*/
static void
ginEntryInsert(Relation index, GinState *ginstate, Datum value, ItemPointerData *items, uint32 nitem, bool isBuild)
{
GinBtreeData btree;
GinBtreeStack *stack;
IndexTuple itup;
Page page;
prepareEntryScan(&btree, index, value, ginstate);
stack = ginFindLeafPage(&btree, NULL);
page = BufferGetPage(stack->buffer);
if (btree.findItem(&btree, stack))
{
/* found entry */
itup = (IndexTuple) PageGetItem(page, PageGetItemId(page, stack->off));
if (GinIsPostingTree(itup))
{
/* lock root of posting tree */
GinPostingTreeScan *gdi;
BlockNumber rootPostingTree = GinGetPostingTree(itup);
/* release all stack */
LockBuffer(stack->buffer, GIN_UNLOCK);
freeGinBtreeStack(stack);
/* insert into posting tree */
gdi = prepareScanPostingTree(index, rootPostingTree, FALSE);
gdi->btree.isBuild = isBuild;
insertItemPointer(gdi, items, nitem);
return;
}
itup = addItemPointersToTuple(index, ginstate, stack, itup, items, nitem, isBuild);
btree.isDelete = TRUE;
}
else
{
/* We suppose, that tuple can store at list one itempointer */
itup = GinFormTuple(ginstate, value, items, 1);
if (itup == NULL || IndexTupleSize(itup) >= GinMaxItemSize)
elog(ERROR, "huge tuple");
if (nitem > 1)
{
IndexTuple previtup = itup;
itup = addItemPointersToTuple(index, ginstate, stack, previtup, items + 1, nitem - 1, isBuild);
pfree(previtup);
}
}
btree.entry = itup;
ginInsertValue(&btree, stack);
pfree(itup);
}
/*
* Insert one or more heap TIDs associated with the given key value.
* This will either add a single key entry, or enlarge a pre-existing entry.
*
* During an index build, buildStats is non-null and the counters
* it contains should be incremented as needed.
*/
void
ginEntryInsert(GinState *ginstate,
OffsetNumber attnum, Datum key, GinNullCategory category,
ItemPointerData *items, uint32 nitem,
GinStatsData *buildStats)
{
GinBtreeData btree;
GinBtreeStack *stack;
IndexTuple itup;
Page page;
/* During index build, count the to-be-inserted entry */
if (buildStats)
buildStats->nEntries++;
ginPrepareEntryScan(&btree, attnum, key, category, ginstate);
stack = ginFindLeafPage(&btree, GIN_ROOT_BLKNO, false);
page = BufferGetPage(stack->buffer);
if (btree.findItem(&btree, stack))
{
/* found pre-existing entry */
itup = (IndexTuple) PageGetItem(page, PageGetItemId(page, stack->off));
if (GinIsPostingTree(itup))
{
/* add entries to existing posting tree */
BlockNumber rootPostingTree = GinGetPostingTree(itup);
/* release all stack */
LockBuffer(stack->buffer, GIN_UNLOCK);
freeGinBtreeStack(stack);
/* insert into posting tree */
ginInsertItemPointers(ginstate->index, rootPostingTree,
items, nitem,
buildStats);
return;
}
/* modify an existing leaf entry */
itup = addItemPointersToLeafTuple(ginstate, itup,
items, nitem, buildStats);
btree.isDelete = TRUE;
}
else
{
/* no match, so construct a new leaf entry */
itup = buildFreshLeafTuple(ginstate, attnum, key, category,
items, nitem, buildStats);
}
/* Insert the new or modified leaf tuple */
btree.entry = itup;
ginInsertValue(&btree, stack, buildStats);
pfree(itup);
}
/*
* Insert a value to tree described by stack.
*
* The value to be inserted is given in 'insertdata'. Its format depends
* on whether this is an entry or data tree, ginInsertValue just passes it
* through to the tree-specific callback function.
*
* During an index build, buildStats is non-null and the counters it contains
* are incremented as needed.
*
* NB: the passed-in stack is freed, as though by freeGinBtreeStack.
*/
void
ginInsertValue(GinBtree btree, GinBtreeStack *stack, void *insertdata,
GinStatsData *buildStats)
{
bool done;
/* If the leaf page was incompletely split, finish the split first */
if (GinPageIsIncompleteSplit(BufferGetPage(stack->buffer)))
ginFinishSplit(btree, stack, false, buildStats);
done = ginPlaceToPage(btree, stack,
insertdata, InvalidBlockNumber,
InvalidBuffer, buildStats);
if (done)
{
LockBuffer(stack->buffer, GIN_UNLOCK);
freeGinBtreeStack(stack);
}
else
ginFinishSplit(btree, stack, true, buildStats);
}
/*
* Insert value (stored in GinBtree) to tree described by stack
*
* During an index build, buildStats is non-null and the counters
* it contains should be incremented as needed.
*
* NB: the passed-in stack is freed, as though by freeGinBtreeStack.
*/
void
ginInsertValue(GinBtree btree, GinBtreeStack *stack, GinStatsData *buildStats)
{
GinBtreeStack *parent = stack;
BlockNumber rootBlkno = InvalidBuffer;
Page page,
rpage,
lpage;
/* remember root BlockNumber */
while (parent)
{
rootBlkno = parent->blkno;
parent = parent->parent;
}
while (stack)
{
XLogRecData *rdata;
BlockNumber savedRightLink;
page = BufferGetPage(stack->buffer);
savedRightLink = GinPageGetOpaque(page)->rightlink;
if (btree->isEnoughSpace(btree, stack->buffer, stack->off))
{
START_CRIT_SECTION();
btree->placeToPage(btree, stack->buffer, stack->off, &rdata);
MarkBufferDirty(stack->buffer);
if (RelationNeedsWAL(btree->index))
{
XLogRecPtr recptr;
recptr = XLogInsert(RM_GIN_ID, XLOG_GIN_INSERT, rdata);
PageSetLSN(page, recptr);
PageSetTLI(page, ThisTimeLineID);
}
LockBuffer(stack->buffer, GIN_UNLOCK);
END_CRIT_SECTION();
freeGinBtreeStack(stack);
return;
}
else
{
Buffer rbuffer = GinNewBuffer(btree->index);
Page newlpage;
/*
* newlpage is a pointer to memory page, it doesn't associate with
* buffer, stack->buffer should be untouched
*/
newlpage = btree->splitPage(btree, stack->buffer, rbuffer, stack->off, &rdata);
((ginxlogSplit *) (rdata->data))->rootBlkno = rootBlkno;
/* During index build, count the newly-split page */
if (buildStats)
{
if (btree->isData)
buildStats->nDataPages++;
else
buildStats->nEntryPages++;
}
parent = stack->parent;
if (parent == NULL)
{
/*
* split root, so we need to allocate new left page and place
* pointer on root to left and right page
*/
Buffer lbuffer = GinNewBuffer(btree->index);
((ginxlogSplit *) (rdata->data))->isRootSplit = TRUE;
((ginxlogSplit *) (rdata->data))->rrlink = InvalidBlockNumber;
page = BufferGetPage(stack->buffer);
lpage = BufferGetPage(lbuffer);
rpage = BufferGetPage(rbuffer);
GinPageGetOpaque(rpage)->rightlink = InvalidBlockNumber;
GinPageGetOpaque(newlpage)->rightlink = BufferGetBlockNumber(rbuffer);
((ginxlogSplit *) (rdata->data))->lblkno = BufferGetBlockNumber(lbuffer);
START_CRIT_SECTION();
GinInitBuffer(stack->buffer, GinPageGetOpaque(newlpage)->flags & ~GIN_LEAF);
PageRestoreTempPage(newlpage, lpage);
btree->fillRoot(btree, stack->buffer, lbuffer, rbuffer);
MarkBufferDirty(rbuffer);
MarkBufferDirty(lbuffer);
MarkBufferDirty(stack->buffer);
if (RelationNeedsWAL(btree->index))
{
XLogRecPtr recptr;
recptr = XLogInsert(RM_GIN_ID, XLOG_GIN_SPLIT, rdata);
PageSetLSN(page, recptr);
PageSetTLI(page, ThisTimeLineID);
PageSetLSN(lpage, recptr);
PageSetTLI(lpage, ThisTimeLineID);
PageSetLSN(rpage, recptr);
PageSetTLI(rpage, ThisTimeLineID);
}
UnlockReleaseBuffer(rbuffer);
UnlockReleaseBuffer(lbuffer);
LockBuffer(stack->buffer, GIN_UNLOCK);
END_CRIT_SECTION();
freeGinBtreeStack(stack);
/* During index build, count the newly-added root page */
if (buildStats)
{
if (btree->isData)
buildStats->nDataPages++;
else
buildStats->nEntryPages++;
}
return;
}
else
{
/* split non-root page */
((ginxlogSplit *) (rdata->data))->isRootSplit = FALSE;
((ginxlogSplit *) (rdata->data))->rrlink = savedRightLink;
lpage = BufferGetPage(stack->buffer);
rpage = BufferGetPage(rbuffer);
GinPageGetOpaque(rpage)->rightlink = savedRightLink;
GinPageGetOpaque(newlpage)->rightlink = BufferGetBlockNumber(rbuffer);
START_CRIT_SECTION();
PageRestoreTempPage(newlpage, lpage);
MarkBufferDirty(rbuffer);
MarkBufferDirty(stack->buffer);
if (RelationNeedsWAL(btree->index))
{
XLogRecPtr recptr;
recptr = XLogInsert(RM_GIN_ID, XLOG_GIN_SPLIT, rdata);
PageSetLSN(lpage, recptr);
PageSetTLI(lpage, ThisTimeLineID);
PageSetLSN(rpage, recptr);
PageSetTLI(rpage, ThisTimeLineID);
}
UnlockReleaseBuffer(rbuffer);
END_CRIT_SECTION();
}
}
btree->isDelete = FALSE;
/* search parent to lock */
LockBuffer(parent->buffer, GIN_EXCLUSIVE);
/* move right if it's needed */
page = BufferGetPage(parent->buffer);
while ((parent->off = btree->findChildPtr(btree, page, stack->blkno, parent->off)) == InvalidOffsetNumber)
{
BlockNumber rightlink = GinPageGetOpaque(page)->rightlink;
LockBuffer(parent->buffer, GIN_UNLOCK);
if (rightlink == InvalidBlockNumber)
{
/*
* rightmost page, but we don't find parent, we should use
* plain search...
*/
ginFindParents(btree, stack, rootBlkno);
parent = stack->parent;
page = BufferGetPage(parent->buffer);
break;
}
parent->blkno = rightlink;
parent->buffer = ReleaseAndReadBuffer(parent->buffer, btree->index, parent->blkno);
LockBuffer(parent->buffer, GIN_EXCLUSIVE);
page = BufferGetPage(parent->buffer);
}
UnlockReleaseBuffer(stack->buffer);
pfree(stack);
stack = parent;
}
}
/*
* Finish a split by inserting the downlink for the new page to parent.
*
* On entry, stack->buffer is exclusively locked.
*
* If freestack is true, all the buffers are released and unlocked as we
* crawl up the tree, and 'stack' is freed. Otherwise stack->buffer is kept
* locked, and stack is unmodified, except for possibly moving right to find
* the correct parent of page.
*/
static void
ginFinishSplit(GinBtree btree, GinBtreeStack *stack, bool freestack,
GinStatsData *buildStats)
{
Page page;
bool done;
bool first = true;
/*
* freestack == false when we encounter an incompletely split page during a
* scan, while freestack == true is used in the normal scenario that a
* split is finished right after the initial insert.
*/
if (!freestack)
elog(DEBUG1, "finishing incomplete split of block %u in gin index \"%s\"",
stack->blkno, RelationGetRelationName(btree->index));
/* this loop crawls up the stack until the insertion is complete */
do
{
GinBtreeStack *parent = stack->parent;
void *insertdata;
BlockNumber updateblkno;
/* search parent to lock */
LockBuffer(parent->buffer, GIN_EXCLUSIVE);
/*
* If the parent page was incompletely split, finish that split first,
* then continue with the current one.
*
* Note: we have to finish *all* incomplete splits we encounter, even
* if we have to move right. Otherwise we might choose as the target
* a page that has no downlink in the parent, and splitting it further
* would fail.
*/
if (GinPageIsIncompleteSplit(BufferGetPage(parent->buffer)))
ginFinishSplit(btree, parent, false, buildStats);
/* move right if it's needed */
page = BufferGetPage(parent->buffer);
while ((parent->off = btree->findChildPtr(btree, page, stack->blkno, parent->off)) == InvalidOffsetNumber)
{
if (GinPageRightMost(page))
{
/*
* rightmost page, but we don't find parent, we should use
* plain search...
*/
LockBuffer(parent->buffer, GIN_UNLOCK);
ginFindParents(btree, stack);
parent = stack->parent;
Assert(parent != NULL);
break;
}
parent->buffer = ginStepRight(parent->buffer, btree->index, GIN_EXCLUSIVE);
parent->blkno = BufferGetBlockNumber(parent->buffer);
page = BufferGetPage(parent->buffer);
if (GinPageIsIncompleteSplit(BufferGetPage(parent->buffer)))
ginFinishSplit(btree, parent, false, buildStats);
}
/* insert the downlink */
insertdata = btree->prepareDownlink(btree, stack->buffer);
updateblkno = GinPageGetOpaque(BufferGetPage(stack->buffer))->rightlink;
done = ginPlaceToPage(btree, parent,
insertdata, updateblkno,
stack->buffer, buildStats);
pfree(insertdata);
/*
* If the caller requested to free the stack, unlock and release the
* child buffer now. Otherwise keep it pinned and locked, but if we
* have to recurse up the tree, we can unlock the upper pages, only
* keeping the page at the bottom of the stack locked.
*/
if (!first || freestack)
LockBuffer(stack->buffer, GIN_UNLOCK);
if (freestack)
{
ReleaseBuffer(stack->buffer);
pfree(stack);
}
stack = parent;
first = false;
} while (!done);
/* unlock the parent */
LockBuffer(stack->buffer, GIN_UNLOCK);
if (freestack)
freeGinBtreeStack(stack);
}
/*
* Start* functions setup state of searches: find correct buffer and locks it,
* Stop* functions unlock buffer (but don't release!)
*/
static void
startScanEntry(Relation index, GinState *ginstate, GinScanEntry entry)
{
GinBtreeData btreeEntry;
GinBtreeStack *stackEntry;
Page page;
bool needUnlock = TRUE;
if (entry->master != NULL)
{
entry->isFinished = entry->master->isFinished;
return;
}
/*
* We should find entry, and begin scan of posting tree
* or just store posting list in memory
*/
prepareEntryScan(&btreeEntry, index, entry->entry, ginstate);
btreeEntry.searchMode = TRUE;
stackEntry = ginFindLeafPage(&btreeEntry, NULL);
page = BufferGetPage(stackEntry->buffer);
entry->isFinished = TRUE;
entry->buffer = InvalidBuffer;
entry->offset = InvalidOffsetNumber;
entry->list = NULL;
entry->nlist = 0;
entry->reduceResult = FALSE;
entry->predictNumberResult = 0;
if (btreeEntry.findItem(&btreeEntry, stackEntry))
{
IndexTuple itup = (IndexTuple) PageGetItem(page, PageGetItemId(page, stackEntry->off));
if (GinIsPostingTree(itup))
{
BlockNumber rootPostingTree = GinGetPostingTree(itup);
GinPostingTreeScan *gdi;
Page page;
LockBuffer(stackEntry->buffer, GIN_UNLOCK);
needUnlock = FALSE;
gdi = prepareScanPostingTree(index, rootPostingTree, TRUE);
entry->buffer = scanBeginPostingTree(gdi);
/*
* We keep buffer pinned because we need to prevent deletition
* page during scan. See GIN's vacuum implementation. RefCount
* is increased to keep buffer pinned after freeGinBtreeStack() call.
*/
IncrBufferRefCount(entry->buffer);
page = BufferGetPage(entry->buffer);
entry->predictNumberResult = gdi->stack->predictNumber * GinPageGetOpaque(page)->maxoff;
/*
* Keep page content in memory to prevent durable page locking
*/
entry->list = (ItemPointerData *) palloc( BLCKSZ );
entry->nlist = GinPageGetOpaque(page)->maxoff;
memcpy( entry->list, GinDataPageGetItem(page, FirstOffsetNumber),
GinPageGetOpaque(page)->maxoff * sizeof(ItemPointerData) );
LockBuffer(entry->buffer, GIN_UNLOCK);
freeGinBtreeStack(gdi->stack);
pfree(gdi);
entry->isFinished = FALSE;
}
else if (GinGetNPosting(itup) > 0)
{
entry->nlist = GinGetNPosting(itup);
entry->list = (ItemPointerData *) palloc(sizeof(ItemPointerData) * entry->nlist);
memcpy(entry->list, GinGetPosting(itup), sizeof(ItemPointerData) * entry->nlist);
entry->isFinished = FALSE;
}
}
if (needUnlock)
LockBuffer(stackEntry->buffer, GIN_UNLOCK);
freeGinBtreeStack(stackEntry);
}
/*
* Inserts only one entry to the index, but it can add more than 1 ItemPointer.
*
* During an index build, buildStats is non-null and the counters
* it contains should be incremented as needed.
*/
void
ginEntryInsert(Relation index, GinState *ginstate,
OffsetNumber attnum, Datum value,
ItemPointerData *items, uint32 nitem,
GinStatsData *buildStats)
{
GinBtreeData btree;
GinBtreeStack *stack;
IndexTuple itup;
Page page;
/* During index build, count the to-be-inserted entry */
if (buildStats)
buildStats->nEntries++;
ginPrepareEntryScan(&btree, index, attnum, value, ginstate);
stack = ginFindLeafPage(&btree, NULL);
page = BufferGetPage(stack->buffer);
if (btree.findItem(&btree, stack))
{
/* found entry */
itup = (IndexTuple) PageGetItem(page, PageGetItemId(page, stack->off));
if (GinIsPostingTree(itup))
{
/* lock root of posting tree */
GinPostingTreeScan *gdi;
BlockNumber rootPostingTree = GinGetPostingTree(itup);
/* release all stack */
LockBuffer(stack->buffer, GIN_UNLOCK);
freeGinBtreeStack(stack);
/* insert into posting tree */
gdi = ginPrepareScanPostingTree(index, rootPostingTree, FALSE);
gdi->btree.isBuild = (buildStats != NULL);
ginInsertItemPointer(gdi, items, nitem, buildStats);
pfree(gdi);
return;
}
itup = addItemPointersToTuple(index, ginstate, stack, itup,
items, nitem, buildStats);
btree.isDelete = TRUE;
}
else
{
/* We suppose that tuple can store at least one itempointer */
itup = GinFormTuple(index, ginstate, attnum, value, items, 1, true);
if (nitem > 1)
{
/* Add the rest, making a posting tree if necessary */
IndexTuple previtup = itup;
itup = addItemPointersToTuple(index, ginstate, stack, previtup,
items + 1, nitem - 1, buildStats);
pfree(previtup);
}
}
btree.entry = itup;
ginInsertValue(&btree, stack, buildStats);
pfree(itup);
}