static void
ginRedoDeleteListPages(XLogReaderState *record)
{
XLogRecPtr lsn = record->EndRecPtr;
ginxlogDeleteListPages *data = (ginxlogDeleteListPages *) XLogRecGetData(record);
Buffer metabuffer;
Page metapage;
int i;
metabuffer = XLogInitBufferForRedo(record, 0);
Assert(BufferGetBlockNumber(metabuffer) == GIN_METAPAGE_BLKNO);
metapage = BufferGetPage(metabuffer);
GinInitPage(metapage, GIN_META, BufferGetPageSize(metabuffer));
memcpy(GinPageGetMeta(metapage), &data->metadata, sizeof(GinMetaPageData));
PageSetLSN(metapage, lsn);
MarkBufferDirty(metabuffer);
/*
* In normal operation, shiftList() takes exclusive lock on all the
* pages-to-be-deleted simultaneously. During replay, however, it should
* be all right to lock them one at a time. This is dependent on the fact
* that we are deleting pages from the head of the list, and that readers
* share-lock the next page before releasing the one they are on. So we
* cannot get past a reader that is on, or due to visit, any page we are
* going to delete. New incoming readers will block behind our metapage
* lock and then see a fully updated page list.
*
* No full-page images are taken of the deleted pages. Instead, they are
* re-initialized as empty, deleted pages. Their right-links don't need to
* be preserved, because no new___ readers can see the pages, as explained
* above.
*/
for (i = 0; i < data->ndeleted; i++)
{
Buffer buffer;
Page page;
buffer = XLogInitBufferForRedo(record, i + 1);
page = BufferGetPage(buffer);
GinInitBuffer(buffer, GIN_DELETED);
PageSetLSN(page, lsn);
MarkBufferDirty(buffer);
UnlockReleaseBuffer(buffer);
}
UnlockReleaseBuffer(metabuffer);
}
void
GinInitMetabuffer(Buffer b)
{
GinMetaPageData *metadata;
Page page = BufferGetPage(b);
GinInitPage(page, GIN_META, BufferGetPageSize(b));
metadata = GinPageGetMeta(page);
metadata->head = metadata->tail = InvalidBlockNumber;
metadata->tailFreeSize = 0;
metadata->nPendingPages = 0;
metadata->nPendingHeapTuples = 0;
}
void
GinInitMetabuffer(Buffer b)
{
GinMetaPageData *metadata;
Page page = BufferGetPage(b);
GinInitPage(page, GIN_META, BufferGetPageSize(b));
metadata = GinPageGetMeta(page);
metadata->head = metadata->tail = InvalidBlockNumber;
metadata->tailFreeSize = 0;
metadata->nPendingPages = 0;
metadata->nPendingHeapTuples = 0;
metadata->nTotalPages = 0;
metadata->nEntryPages = 0;
metadata->nDataPages = 0;
metadata->nEntries = 0;
metadata->ginVersion = GIN_CURRENT_VERSION;
}
/*
* Split entry page and insert new data.
*
* Returns new temp pages to *newlpage and *newrpage.
* The original buffer is left untouched.
*/
static void
entrySplitPage(GinBtree btree, Buffer origbuf,
GinBtreeStack *stack,
GinBtreeEntryInsertData *insertData,
BlockNumber updateblkno,
Page *newlpage, Page *newrpage)
{
OffsetNumber off = stack->off;
OffsetNumber i,
maxoff,
separator = InvalidOffsetNumber;
Size totalsize = 0;
Size lsize = 0,
size;
char *ptr;
IndexTuple itup;
Page page;
Page lpage = PageGetTempPageCopy(BufferGetPage(origbuf));
Page rpage = PageGetTempPageCopy(BufferGetPage(origbuf));
Size pageSize = PageGetPageSize(lpage);
char tupstore[2 * BLCKSZ];
entryPreparePage(btree, lpage, off, insertData, updateblkno);
/*
* First, append all the existing tuples and the new tuple we're inserting
* one after another in a temporary workspace.
*/
maxoff = PageGetMaxOffsetNumber(lpage);
ptr = tupstore;
for (i = FirstOffsetNumber; i <= maxoff; i++)
{
if (i == off)
{
size = MAXALIGN(IndexTupleSize(insertData->entry));
memcpy(ptr, insertData->entry, size);
ptr += size;
totalsize += size + sizeof(ItemIdData);
}
itup = (IndexTuple) PageGetItem(lpage, PageGetItemId(lpage, i));
size = MAXALIGN(IndexTupleSize(itup));
memcpy(ptr, itup, size);
ptr += size;
totalsize += size + sizeof(ItemIdData);
}
if (off == maxoff + 1)
{
size = MAXALIGN(IndexTupleSize(insertData->entry));
memcpy(ptr, insertData->entry, size);
ptr += size;
totalsize += size + sizeof(ItemIdData);
}
/*
* Initialize the left and right pages, and copy all the tuples back to
* them.
*/
GinInitPage(rpage, GinPageGetOpaque(lpage)->flags, pageSize);
GinInitPage(lpage, GinPageGetOpaque(rpage)->flags, pageSize);
ptr = tupstore;
maxoff++;
lsize = 0;
page = lpage;
for (i = FirstOffsetNumber; i <= maxoff; i++)
{
itup = (IndexTuple) ptr;
/*
* Decide where to split. We try to equalize the pages' total data
* size, not number of tuples.
*/
if (lsize > totalsize / 2)
{
if (separator == InvalidOffsetNumber)
separator = i - 1;
page = rpage;
}
else
{
lsize += MAXALIGN(IndexTupleSize(itup)) + sizeof(ItemIdData);
}
if (PageAddItem(page, (Item) itup, IndexTupleSize(itup), InvalidOffsetNumber, false, false) == InvalidOffsetNumber)
elog(ERROR, "failed to add item to index page in \"%s\"",
RelationGetRelationName(btree->index));
ptr += MAXALIGN(IndexTupleSize(itup));
}
/* return temp pages to caller */
*newlpage = lpage;
*newrpage = rpage;
}
/*
* Insert a new item to a page.
*
* Returns true if the insertion was finished. On false, the page was split and
* the parent needs to be updated. (a root split returns true as it doesn't
* need any further action by the caller to complete)
*
* When inserting a downlink to a internal page, 'childbuf' contains the
* child page that was split. Its GIN_INCOMPLETE_SPLIT flag will be cleared
* atomically with the insert. Also, the existing item at the given location
* is updated to point to 'updateblkno'.
*
* stack->buffer is locked on entry, and is kept locked.
*/
static bool
ginPlaceToPage(GinBtree btree, GinBtreeStack *stack,
void *insertdata, BlockNumber updateblkno,
Buffer childbuf, GinStatsData *buildStats)
{
Page page = BufferGetPage(stack->buffer);
XLogRecData *payloadrdata;
bool fit;
uint16 xlflags = 0;
Page childpage = NULL;
if (GinPageIsData(page))
xlflags |= GIN_INSERT_ISDATA;
if (GinPageIsLeaf(page))
{
xlflags |= GIN_INSERT_ISLEAF;
Assert(!BufferIsValid(childbuf));
Assert(updateblkno == InvalidBlockNumber);
}
else
{
Assert(BufferIsValid(childbuf));
Assert(updateblkno != InvalidBlockNumber);
childpage = BufferGetPage(childbuf);
}
/*
* Try to put the incoming tuple on the page. If it doesn't fit,
* placeToPage method will return false and leave the page unmodified, and
* we'll have to split the page.
*/
START_CRIT_SECTION();
fit = btree->placeToPage(btree, stack->buffer, stack->off,
insertdata, updateblkno,
&payloadrdata);
if (fit)
{
MarkBufferDirty(stack->buffer);
/* An insert to an internal page finishes the split of the child. */
if (childbuf != InvalidBuffer)
{
GinPageGetOpaque(childpage)->flags &= ~GIN_INCOMPLETE_SPLIT;
MarkBufferDirty(childbuf);
}
if (RelationNeedsWAL(btree->index))
{
XLogRecPtr recptr;
XLogRecData rdata[3];
ginxlogInsert xlrec;
BlockIdData childblknos[2];
xlrec.node = btree->index->rd_node;
xlrec.blkno = BufferGetBlockNumber(stack->buffer);
xlrec.offset = stack->off;
xlrec.flags = xlflags;
rdata[0].buffer = InvalidBuffer;
rdata[0].data = (char *) &xlrec;
rdata[0].len = sizeof(ginxlogInsert);
/*
* Log information about child if this was an insertion of a
* downlink.
*/
if (childbuf != InvalidBuffer)
{
rdata[0].next = &rdata[1];
BlockIdSet(&childblknos[0], BufferGetBlockNumber(childbuf));
BlockIdSet(&childblknos[1], GinPageGetOpaque(childpage)->rightlink);
rdata[1].buffer = InvalidBuffer;
rdata[1].data = (char *) childblknos;
rdata[1].len = sizeof(BlockIdData) * 2;
rdata[1].next = &rdata[2];
rdata[2].buffer = childbuf;
rdata[2].buffer_std = false;
rdata[2].data = NULL;
rdata[2].len = 0;
rdata[2].next = payloadrdata;
}
else
rdata[0].next = payloadrdata;
recptr = XLogInsert(RM_GIN_ID, XLOG_GIN_INSERT, rdata);
PageSetLSN(page, recptr);
if (childbuf != InvalidBuffer)
PageSetLSN(childpage, recptr);
}
END_CRIT_SECTION();
return true;
}
else
{
/* Didn't fit, have to split */
Buffer rbuffer;
Page newlpage;
BlockNumber savedRightLink;
Page rpage;
XLogRecData rdata[2];
ginxlogSplit data;
Buffer lbuffer = InvalidBuffer;
Page newrootpg = NULL;
END_CRIT_SECTION();
rbuffer = GinNewBuffer(btree->index);
/* During index build, count the new page */
if (buildStats)
{
if (btree->isData)
buildStats->nDataPages++;
else
buildStats->nEntryPages++;
}
savedRightLink = GinPageGetOpaque(page)->rightlink;
/*
* newlpage is a pointer to memory page, it is not associated with a
* buffer. stack->buffer is not touched yet.
*/
newlpage = btree->splitPage(btree, stack->buffer, rbuffer, stack->off,
insertdata, updateblkno,
&payloadrdata);
data.node = btree->index->rd_node;
data.rblkno = BufferGetBlockNumber(rbuffer);
data.flags = xlflags;
if (childbuf != InvalidBuffer)
{
Page childpage = BufferGetPage(childbuf);
GinPageGetOpaque(childpage)->flags &= ~GIN_INCOMPLETE_SPLIT;
data.leftChildBlkno = BufferGetBlockNumber(childbuf);
data.rightChildBlkno = GinPageGetOpaque(childpage)->rightlink;
}
else
data.leftChildBlkno = data.rightChildBlkno = InvalidBlockNumber;
rdata[0].buffer = InvalidBuffer;
rdata[0].data = (char *) &data;
rdata[0].len = sizeof(ginxlogSplit);
if (childbuf != InvalidBuffer)
{
rdata[0].next = &rdata[1];
rdata[1].buffer = childbuf;
rdata[1].buffer_std = false;
rdata[1].data = NULL;
rdata[1].len = 0;
rdata[1].next = payloadrdata;
}
else
rdata[0].next = payloadrdata;
rpage = BufferGetPage(rbuffer);
if (stack->parent == NULL)
{
/*
* split root, so we need to allocate new left page and place
* pointer on root to left and right page
*/
lbuffer = GinNewBuffer(btree->index);
/* During index build, count the newly-added root page */
if (buildStats)
{
if (btree->isData)
buildStats->nDataPages++;
else
buildStats->nEntryPages++;
}
/*
* root never has a right-link, so we borrow the rrlink field to
* store the root block number.
*/
data.rrlink = BufferGetBlockNumber(stack->buffer);
data.lblkno = BufferGetBlockNumber(lbuffer);
data.flags |= GIN_SPLIT_ROOT;
GinPageGetOpaque(rpage)->rightlink = InvalidBlockNumber;
GinPageGetOpaque(newlpage)->rightlink = BufferGetBlockNumber(rbuffer);
/*
* Construct a new root page containing downlinks to the new left
* and right pages. (do this in a temporary copy first rather
* than overwriting the original page directly, so that we can still
* abort gracefully if this fails.)
*/
newrootpg = PageGetTempPage(rpage);
GinInitPage(newrootpg, GinPageGetOpaque(newlpage)->flags & ~GIN_LEAF, BLCKSZ);
btree->fillRoot(btree, newrootpg,
BufferGetBlockNumber(lbuffer), newlpage,
BufferGetBlockNumber(rbuffer), rpage);
}
else
{
/* split non-root page */
data.rrlink = savedRightLink;
data.lblkno = BufferGetBlockNumber(stack->buffer);
GinPageGetOpaque(rpage)->rightlink = savedRightLink;
GinPageGetOpaque(newlpage)->flags |= GIN_INCOMPLETE_SPLIT;
GinPageGetOpaque(newlpage)->rightlink = BufferGetBlockNumber(rbuffer);
}
/*
* Ok, we have the new contents of the left page in a temporary copy
* now (newlpage), and the newly-allocated right block has been filled
* in. The original page is still unchanged.
*
* If this is a root split, we also have a temporary page containing
* the new contents of the root. Copy the new left page to a
* newly-allocated block, and initialize the (original) root page the
* new copy. Otherwise, copy over the temporary copy of the new left
* page over the old left page.
*/
START_CRIT_SECTION();
MarkBufferDirty(rbuffer);
if (stack->parent == NULL)
{
PageRestoreTempPage(newlpage, BufferGetPage(lbuffer));
MarkBufferDirty(lbuffer);
newlpage = newrootpg;
}
PageRestoreTempPage(newlpage, BufferGetPage(stack->buffer));
MarkBufferDirty(stack->buffer);
/* write WAL record */
if (RelationNeedsWAL(btree->index))
{
XLogRecPtr recptr;
recptr = XLogInsert(RM_GIN_ID, XLOG_GIN_SPLIT, rdata);
PageSetLSN(BufferGetPage(stack->buffer), recptr);
PageSetLSN(rpage, recptr);
if (stack->parent == NULL)
PageSetLSN(BufferGetPage(lbuffer), recptr);
}
END_CRIT_SECTION();
/*
* We can release the lock on the right page now, but keep the
* original buffer locked.
*/
UnlockReleaseBuffer(rbuffer);
if (stack->parent == NULL)
UnlockReleaseBuffer(lbuffer);
/*
* If we split the root, we're done. Otherwise the split is not
* complete until the downlink for the new page has been inserted to
* the parent.
*/
if (stack->parent == NULL)
return true;
else
return false;
}
}
static void
ginRedoUpdateMetapage(XLogReaderState *record)
{
XLogRecPtr lsn = record->EndRecPtr;
ginxlogUpdateMeta *data = (ginxlogUpdateMeta *) XLogRecGetData(record);
Buffer metabuffer;
Page metapage;
Buffer buffer;
/*
* Restore the metapage. This is essentially the same as a full-page
* image, so restore the metapage unconditionally without looking at the
* LSN, to avoid torn page hazards.
*/
metabuffer = XLogInitBufferForRedo(record, 0);
Assert(BufferGetBlockNumber(metabuffer) == GIN_METAPAGE_BLKNO);
metapage = BufferGetPage(metabuffer);
GinInitPage(metapage, GIN_META, BufferGetPageSize(metabuffer));
memcpy(GinPageGetMeta(metapage), &data->metadata, sizeof(GinMetaPageData));
PageSetLSN(metapage, lsn);
MarkBufferDirty(metabuffer);
if (data->ntuples > 0)
{
/*
* insert into tail page
*/
if (XLogReadBufferForRedo(record, 1, &buffer) == BLK_NEEDS_REDO)
{
Page page = BufferGetPage(buffer);
OffsetNumber off;
int i;
Size tupsize;
char *payload;
IndexTuple tuples;
Size totaltupsize;
payload = XLogRecGetBlockData(record, 1, &totaltupsize);
tuples = (IndexTuple) payload;
if (PageIsEmpty(page))
off = FirstOffsetNumber;
else
off = OffsetNumberNext(PageGetMaxOffsetNumber(page));
for (i = 0; i < data->ntuples; i++)
{
tupsize = IndexTupleSize(tuples);
if (PageAddItem(page, (Item) tuples, tupsize, off,
false, false) == InvalidOffsetNumber)
elog(ERROR, "failed to add item to index page");
tuples = (IndexTuple) (((char *) tuples) + tupsize);
off++;
}
Assert(payload + totaltupsize == (char *) tuples);
/*
* Increase counter of heap tuples
*/
GinPageGetOpaque(page)->maxoff++;
PageSetLSN(page, lsn);
MarkBufferDirty(buffer);
}
if (BufferIsValid(buffer))
UnlockReleaseBuffer(buffer);
}
else if (data->prevTail != InvalidBlockNumber)
{
/*
* New tail
*/
if (XLogReadBufferForRedo(record, 1, &buffer) == BLK_NEEDS_REDO)
{
Page page = BufferGetPage(buffer);
GinPageGetOpaque(page)->rightlink = data->newRightlink;
PageSetLSN(page, lsn);
MarkBufferDirty(buffer);
}
if (BufferIsValid(buffer))
UnlockReleaseBuffer(buffer);
}
UnlockReleaseBuffer(metabuffer);
}
/*
* split page and fills WAL record. original buffer(lbuf) leaves untouched,
* returns shadow page of lbuf filled new data. In leaf page and build mode puts all
* ItemPointers to pages. Also, in build mode splits data by way to full fulled
* left page
*/
static Page
dataSplitPage(GinBtree btree, Buffer lbuf, Buffer rbuf, OffsetNumber off, XLogRecData **prdata)
{
char *ptr;
OffsetNumber separator;
ItemPointer bound;
Page lpage = PageGetTempPageCopy(BufferGetPage(lbuf));
ItemPointerData oldbound = *GinDataPageGetRightBound(lpage);
int sizeofitem = GinSizeOfDataPageItem(lpage);
OffsetNumber maxoff = GinPageGetOpaque(lpage)->maxoff;
Page rpage = BufferGetPage(rbuf);
Size pageSize = PageGetPageSize(lpage);
Size freeSpace;
uint32 nCopied = 1;
/* these must be static so they can be returned to caller */
static ginxlogSplit data;
static XLogRecData rdata[4];
static char vector[2 * BLCKSZ];
GinInitPage(rpage, GinPageGetOpaque(lpage)->flags, pageSize);
freeSpace = GinDataPageGetFreeSpace(rpage);
*prdata = rdata;
data.leftChildBlkno = (GinPageIsLeaf(lpage)) ?
InvalidOffsetNumber : PostingItemGetBlockNumber(&(btree->pitem));
data.updateBlkno = dataPrepareData(btree, lpage, off);
memcpy(vector, GinDataPageGetItem(lpage, FirstOffsetNumber),
maxoff * sizeofitem);
if (GinPageIsLeaf(lpage) && GinPageRightMost(lpage) && off > GinPageGetOpaque(lpage)->maxoff)
{
nCopied = 0;
while (btree->curitem < btree->nitem &&
maxoff * sizeof(ItemPointerData) < 2 * (freeSpace - sizeof(ItemPointerData)))
{
memcpy(vector + maxoff * sizeof(ItemPointerData),
btree->items + btree->curitem,
sizeof(ItemPointerData));
maxoff++;
nCopied++;
btree->curitem++;
}
}
else
{
ptr = vector + (off - 1) * sizeofitem;
if (maxoff + 1 - off != 0)
memmove(ptr + sizeofitem, ptr, (maxoff - off + 1) * sizeofitem);
if (GinPageIsLeaf(lpage))
{
memcpy(ptr, btree->items + btree->curitem, sizeofitem);
btree->curitem++;
}
else
memcpy(ptr, &(btree->pitem), sizeofitem);
maxoff++;
}
/*
* we suppose that during index creation table scaned from begin to end,
* so ItemPointers are monotonically increased..
*/
if (btree->isBuild && GinPageRightMost(lpage))
separator = freeSpace / sizeofitem;
else
separator = maxoff / 2;
GinInitPage(rpage, GinPageGetOpaque(lpage)->flags, pageSize);
GinInitPage(lpage, GinPageGetOpaque(rpage)->flags, pageSize);
memcpy(GinDataPageGetItem(lpage, FirstOffsetNumber), vector, separator * sizeofitem);
GinPageGetOpaque(lpage)->maxoff = separator;
memcpy(GinDataPageGetItem(rpage, FirstOffsetNumber),
vector + separator * sizeofitem, (maxoff - separator) * sizeofitem);
GinPageGetOpaque(rpage)->maxoff = maxoff - separator;
PostingItemSetBlockNumber(&(btree->pitem), BufferGetBlockNumber(lbuf));
if (GinPageIsLeaf(lpage))
btree->pitem.key = *(ItemPointerData *) GinDataPageGetItem(lpage,
GinPageGetOpaque(lpage)->maxoff);
else
btree->pitem.key = ((PostingItem *) GinDataPageGetItem(lpage,
GinPageGetOpaque(lpage)->maxoff))->key;
btree->rightblkno = BufferGetBlockNumber(rbuf);
/* set up right bound for left page */
bound = GinDataPageGetRightBound(lpage);
*bound = btree->pitem.key;
/* set up right bound for right page */
bound = GinDataPageGetRightBound(rpage);
*bound = oldbound;
data.node = btree->index->rd_node;
data.rootBlkno = InvalidBlockNumber;
data.lblkno = BufferGetBlockNumber(lbuf);
data.rblkno = BufferGetBlockNumber(rbuf);
data.separator = separator;
data.nitem = maxoff;
data.isData = TRUE;
data.isLeaf = GinPageIsLeaf(lpage) ? TRUE : FALSE;
data.isRootSplit = FALSE;
data.rightbound = oldbound;
rdata[0].buffer = InvalidBuffer;
rdata[0].data = (char *) &data;
rdata[0].len = sizeof(ginxlogSplit);
rdata[0].next = &rdata[1];
rdata[1].buffer = InvalidBuffer;
rdata[1].data = vector;
rdata[1].len = MAXALIGN(maxoff * sizeofitem);
rdata[1].next = NULL;
return lpage;
}
/*
* Insert a new item to a page.
*
* Returns true if the insertion was finished. On false, the page was split and
* the parent needs to be updated. (A root split returns true as it doesn't
* need any further action by the caller to complete.)
*
* When inserting a downlink to an internal page, 'childbuf' contains the
* child page that was split. Its GIN_INCOMPLETE_SPLIT flag will be cleared
* atomically with the insert. Also, the existing item at offset stack->off
* in the target page is updated to point to updateblkno.
*
* stack->buffer is locked on entry, and is kept locked.
* Likewise for childbuf, if given.
*/
static bool
ginPlaceToPage(GinBtree btree, GinBtreeStack *stack,
void *insertdata, BlockNumber updateblkno,
Buffer childbuf, GinStatsData *buildStats)
{
Page page = BufferGetPage(stack->buffer);
bool result;
GinPlaceToPageRC rc;
uint16 xlflags = 0;
Page childpage = NULL;
Page newlpage = NULL,
newrpage = NULL;
void *ptp_workspace = NULL;
XLogRecData payloadrdata[10];
MemoryContext tmpCxt;
MemoryContext oldCxt;
/*
* We do all the work of this function and its subfunctions in a temporary
* memory context. This avoids leakages and simplifies APIs, since some
* subfunctions allocate storage that has to survive until we've finished
* the WAL insertion.
*/
tmpCxt = AllocSetContextCreate(CurrentMemoryContext,
"ginPlaceToPage temporary context",
ALLOCSET_DEFAULT_MINSIZE,
ALLOCSET_DEFAULT_INITSIZE,
ALLOCSET_DEFAULT_MAXSIZE);
oldCxt = MemoryContextSwitchTo(tmpCxt);
if (GinPageIsData(page))
xlflags |= GIN_INSERT_ISDATA;
if (GinPageIsLeaf(page))
{
xlflags |= GIN_INSERT_ISLEAF;
Assert(!BufferIsValid(childbuf));
Assert(updateblkno == InvalidBlockNumber);
}
else
{
Assert(BufferIsValid(childbuf));
Assert(updateblkno != InvalidBlockNumber);
childpage = BufferGetPage(childbuf);
}
/*
* See if the incoming tuple will fit on the page. beginPlaceToPage will
* decide if the page needs to be split, and will compute the split
* contents if so. See comments for beginPlaceToPage and execPlaceToPage
* functions for more details of the API here.
*/
rc = btree->beginPlaceToPage(btree, stack->buffer, stack,
insertdata, updateblkno,
&ptp_workspace,
&newlpage, &newrpage,
payloadrdata);
if (rc == GPTP_NO_WORK)
{
/* Nothing to do */
result = true;
}
else if (rc == GPTP_INSERT)
{
/* It will fit, perform the insertion */
START_CRIT_SECTION();
/* Perform the page update, and set up WAL data about it */
btree->execPlaceToPage(btree, stack->buffer, stack,
insertdata, updateblkno,
ptp_workspace, payloadrdata);
MarkBufferDirty(stack->buffer);
/* An insert to an internal page finishes the split of the child. */
if (BufferIsValid(childbuf))
{
GinPageGetOpaque(childpage)->flags &= ~GIN_INCOMPLETE_SPLIT;
MarkBufferDirty(childbuf);
}
if (RelationNeedsWAL(btree->index))
{
XLogRecPtr recptr;
XLogRecData rdata[3];
ginxlogInsert xlrec;
BlockIdData childblknos[2];
xlrec.node = btree->index->rd_node;
xlrec.blkno = BufferGetBlockNumber(stack->buffer);
xlrec.flags = xlflags;
rdata[0].buffer = InvalidBuffer;
rdata[0].data = (char *) &xlrec;
rdata[0].len = sizeof(ginxlogInsert);
/*
* Log information about child if this was an insertion of a
* downlink.
*/
if (BufferIsValid(childbuf))
{
rdata[0].next = &rdata[1];
BlockIdSet(&childblknos[0], BufferGetBlockNumber(childbuf));
BlockIdSet(&childblknos[1], GinPageGetOpaque(childpage)->rightlink);
rdata[1].buffer = InvalidBuffer;
rdata[1].data = (char *) childblknos;
rdata[1].len = sizeof(BlockIdData) * 2;
rdata[1].next = &rdata[2];
rdata[2].buffer = childbuf;
rdata[2].buffer_std = true;
rdata[2].data = NULL;
rdata[2].len = 0;
rdata[2].next = payloadrdata;
}
else
rdata[0].next = payloadrdata;
recptr = XLogInsert(RM_GIN_ID, XLOG_GIN_INSERT, rdata);
PageSetLSN(page, recptr);
if (BufferIsValid(childbuf))
PageSetLSN(childpage, recptr);
}
END_CRIT_SECTION();
/* Insertion is complete. */
result = true;
}
else if (rc == GPTP_SPLIT)
{
/*
* Didn't fit, need to split. The split has been computed in newlpage
* and newrpage, which are pointers to palloc'd pages, not associated
* with buffers. stack->buffer is not touched yet.
*/
Buffer rbuffer;
BlockNumber savedRightLink;
ginxlogSplit data;
Buffer lbuffer = InvalidBuffer;
Page newrootpg = NULL;
/* Get a new index page to become the right page */
rbuffer = GinNewBuffer(btree->index);
/* During index build, count the new page */
if (buildStats)
{
if (btree->isData)
buildStats->nDataPages++;
else
buildStats->nEntryPages++;
}
savedRightLink = GinPageGetOpaque(page)->rightlink;
/* Begin setting up WAL record (which we might not use) */
data.node = btree->index->rd_node;
data.rblkno = BufferGetBlockNumber(rbuffer);
data.flags = xlflags;
if (BufferIsValid(childbuf))
{
data.leftChildBlkno = BufferGetBlockNumber(childbuf);
data.rightChildBlkno = GinPageGetOpaque(childpage)->rightlink;
}
else
data.leftChildBlkno = data.rightChildBlkno = InvalidBlockNumber;
if (stack->parent == NULL)
{
/*
* splitting the root, so we need to allocate new left page and
* place pointers to left and right page on root page.
*/
lbuffer = GinNewBuffer(btree->index);
/* During index build, count the new left page */
if (buildStats)
{
if (btree->isData)
buildStats->nDataPages++;
else
buildStats->nEntryPages++;
}
/*
* root never has a right-link, so we borrow the rrlink field to
* store the root block number.
*/
data.rrlink = BufferGetBlockNumber(stack->buffer);
data.lblkno = BufferGetBlockNumber(lbuffer);
data.flags |= GIN_SPLIT_ROOT;
GinPageGetOpaque(newrpage)->rightlink = InvalidBlockNumber;
GinPageGetOpaque(newlpage)->rightlink = BufferGetBlockNumber(rbuffer);
/*
* Construct a new root page containing downlinks to the new left
* and right pages. (Do this in a temporary copy rather than
* overwriting the original page directly, since we're not in the
* critical section yet.)
*/
newrootpg = PageGetTempPage(newrpage);
GinInitPage(newrootpg, GinPageGetOpaque(newlpage)->flags & ~(GIN_LEAF | GIN_COMPRESSED), BLCKSZ);
btree->fillRoot(btree, newrootpg,
BufferGetBlockNumber(lbuffer), newlpage,
BufferGetBlockNumber(rbuffer), newrpage);
}
else
{
/* splitting a non-root page */
data.rrlink = savedRightLink;
data.lblkno = BufferGetBlockNumber(stack->buffer);
GinPageGetOpaque(newrpage)->rightlink = savedRightLink;
GinPageGetOpaque(newlpage)->flags |= GIN_INCOMPLETE_SPLIT;
GinPageGetOpaque(newlpage)->rightlink = BufferGetBlockNumber(rbuffer);
}
/*
* OK, we have the new contents of the left page in a temporary copy
* now (newlpage), and likewise for the new contents of the
* newly-allocated right block. The original page is still unchanged.
*
* If this is a root split, we also have a temporary page containing
* the new contents of the root.
*/
START_CRIT_SECTION();
MarkBufferDirty(rbuffer);
MarkBufferDirty(stack->buffer);
/*
* Restore the temporary copies over the real buffers.
*/
if (stack->parent == NULL)
{
/* Splitting the root, three pages to update */
MarkBufferDirty(lbuffer);
memcpy(page, newrootpg, BLCKSZ);
memcpy(BufferGetPage(lbuffer), newlpage, BLCKSZ);
memcpy(BufferGetPage(rbuffer), newrpage, BLCKSZ);
}
else
{
/* Normal split, only two pages to update */
memcpy(page, newlpage, BLCKSZ);
memcpy(BufferGetPage(rbuffer), newrpage, BLCKSZ);
}
/* We also clear childbuf's INCOMPLETE_SPLIT flag, if passed */
if (BufferIsValid(childbuf))
{
GinPageGetOpaque(childpage)->flags &= ~GIN_INCOMPLETE_SPLIT;
MarkBufferDirty(childbuf);
}
/* write WAL record */
if (RelationNeedsWAL(btree->index))
{
XLogRecData rdata[2];
XLogRecPtr recptr;
rdata[0].buffer = InvalidBuffer;
rdata[0].data = (char *) &data;
rdata[0].len = sizeof(ginxlogSplit);
if (BufferIsValid(childbuf))
{
rdata[0].next = &rdata[1];
rdata[1].buffer = childbuf;
rdata[1].buffer_std = true;
rdata[1].data = NULL;
rdata[1].len = 0;
rdata[1].next = payloadrdata;
}
else
rdata[0].next = payloadrdata;
recptr = XLogInsert(RM_GIN_ID, XLOG_GIN_SPLIT, rdata);
PageSetLSN(page, recptr);
PageSetLSN(BufferGetPage(rbuffer), recptr);
if (stack->parent == NULL)
PageSetLSN(BufferGetPage(lbuffer), recptr);
if (BufferIsValid(childbuf))
PageSetLSN(childpage, recptr);
}
END_CRIT_SECTION();
/*
* We can release the locks/pins on the new pages now, but keep
* stack->buffer locked. childbuf doesn't get unlocked either.
*/
UnlockReleaseBuffer(rbuffer);
if (stack->parent == NULL)
UnlockReleaseBuffer(lbuffer);
/*
* If we split the root, we're done. Otherwise the split is not
* complete until the downlink for the new page has been inserted to
* the parent.
*/
result = (stack->parent == NULL);
}
else
{
elog(ERROR, "invalid return code from GIN placeToPage method: %d", rc);
result = false; /* keep compiler quiet */
}
/* Clean up temp context */
MemoryContextSwitchTo(oldCxt);
MemoryContextDelete(tmpCxt);
return result;
}
void
GinInitBuffer(Buffer b, uint32 f)
{
GinInitPage(BufferGetPage(b), f, BufferGetPageSize(b));
}
/*
* Place tuple and split page, original buffer(lbuf) leaves untouched,
* returns shadow pages filled with new data.
* Tuples are distributed between pages by equal size on its, not
* an equal number!
*/
static void
entrySplitPage(GinBtree btree, Buffer origbuf,
GinBtreeStack *stack,
void *insertPayload,
BlockNumber updateblkno, XLogRecData **prdata,
Page *newlpage, Page *newrpage)
{
GinBtreeEntryInsertData *insertData = insertPayload;
OffsetNumber off = stack->off;
OffsetNumber i,
maxoff,
separator = InvalidOffsetNumber;
Size totalsize = 0;
Size tupstoresize;
Size lsize = 0,
size;
char *ptr;
IndexTuple itup;
Page page;
Page lpage = PageGetTempPageCopy(BufferGetPage(origbuf));
Page rpage = PageGetTempPageCopy(BufferGetPage(origbuf));
Size pageSize = PageGetPageSize(lpage);
/* these must be static so they can be returned to caller */
static XLogRecData rdata[2];
static ginxlogSplitEntry data;
static char tupstore[2 * BLCKSZ];
*prdata = rdata;
entryPreparePage(btree, lpage, off, insertData, updateblkno);
/*
* First, append all the existing tuples and the new tuple we're inserting
* one after another in a temporary workspace.
*/
maxoff = PageGetMaxOffsetNumber(lpage);
ptr = tupstore;
for (i = FirstOffsetNumber; i <= maxoff; i++)
{
if (i == off)
{
size = MAXALIGN(IndexTupleSize(insertData->entry));
memcpy(ptr, insertData->entry, size);
ptr += size;
totalsize += size + sizeof(ItemIdData);
}
itup = (IndexTuple) PageGetItem(lpage, PageGetItemId(lpage, i));
size = MAXALIGN(IndexTupleSize(itup));
memcpy(ptr, itup, size);
ptr += size;
totalsize += size + sizeof(ItemIdData);
}
if (off == maxoff + 1)
{
size = MAXALIGN(IndexTupleSize(insertData->entry));
memcpy(ptr, insertData->entry, size);
ptr += size;
totalsize += size + sizeof(ItemIdData);
}
tupstoresize = ptr - tupstore;
/*
* Initialize the left and right pages, and copy all the tuples back to
* them.
*/
GinInitPage(rpage, GinPageGetOpaque(lpage)->flags, pageSize);
GinInitPage(lpage, GinPageGetOpaque(rpage)->flags, pageSize);
ptr = tupstore;
maxoff++;
lsize = 0;
page = lpage;
for (i = FirstOffsetNumber; i <= maxoff; i++)
{
itup = (IndexTuple) ptr;
if (lsize > totalsize / 2)
{
if (separator == InvalidOffsetNumber)
separator = i - 1;
page = rpage;
}
else
{
lsize += MAXALIGN(IndexTupleSize(itup)) + sizeof(ItemIdData);
}
if (PageAddItem(page, (Item) itup, IndexTupleSize(itup), InvalidOffsetNumber, false, false) == InvalidOffsetNumber)
elog(ERROR, "failed to add item to index page in \"%s\"",
RelationGetRelationName(btree->index));
ptr += MAXALIGN(IndexTupleSize(itup));
}
data.separator = separator;
data.nitem = maxoff;
rdata[0].buffer = InvalidBuffer;
rdata[0].data = (char *) &data;
rdata[0].len = sizeof(ginxlogSplitEntry);
rdata[0].next = &rdata[1];
rdata[1].buffer = InvalidBuffer;
rdata[1].data = tupstore;
rdata[1].len = tupstoresize;
rdata[1].next = NULL;
*newlpage = lpage;
*newrpage = rpage;
}
/*
* split page and fills WAL record. original buffer(lbuf) leaves untouched,
* returns shadow page of lbuf filled new data. In leaf page and build mode puts all
* ItemPointers to pages. Also, in build mode splits data by way to full fulled
* left page
*/
static Page
dataSplitPage(GinBtree btree, Buffer lbuf, Buffer rbuf, OffsetNumber off,
void *insertdata, BlockNumber updateblkno, XLogRecData **prdata)
{
char *ptr;
OffsetNumber separator;
ItemPointer bound;
Page lpage = PageGetTempPageCopy(BufferGetPage(lbuf));
bool isleaf = GinPageIsLeaf(lpage);
ItemPointerData oldbound = *GinDataPageGetRightBound(lpage);
int sizeofitem = GinSizeOfDataPageItem(lpage);
OffsetNumber maxoff = GinPageGetOpaque(lpage)->maxoff;
Page rpage = BufferGetPage(rbuf);
Size pageSize = PageGetPageSize(lpage);
Size freeSpace;
/* these must be static so they can be returned to caller */
static ginxlogSplitData data;
static XLogRecData rdata[2];
static char vector[2 * BLCKSZ];
GinInitPage(rpage, GinPageGetOpaque(lpage)->flags, pageSize);
freeSpace = GinDataPageGetFreeSpace(rpage);
*prdata = rdata;
/* Update existing downlink to point to next page (on internal page) */
if (!isleaf)
{
PostingItem *pitem = GinDataPageGetPostingItem(lpage, off);
PostingItemSetBlockNumber(pitem, updateblkno);
}
if (isleaf)
{
memcpy(vector,
GinDataPageGetItemPointer(lpage, FirstOffsetNumber),
maxoff * sizeof(ItemPointerData));
}
else
{
memcpy(vector,
GinDataPageGetPostingItem(lpage, FirstOffsetNumber),
maxoff * sizeof(PostingItem));
}
if (isleaf && GinPageRightMost(lpage) && off > GinPageGetOpaque(lpage)->maxoff)
{
/* append new items to the end */
GinBtreeDataLeafInsertData *items = insertdata;
while (items->curitem < items->nitem &&
maxoff * sizeof(ItemPointerData) < 2 * (freeSpace - sizeof(ItemPointerData)))
{
memcpy(vector + maxoff * sizeof(ItemPointerData),
items->items + items->curitem,
sizeof(ItemPointerData));
maxoff++;
items->curitem++;
}
}
else
{
ptr = vector + (off - 1) * sizeofitem;
if (maxoff + 1 - off != 0)
memmove(ptr + sizeofitem, ptr, (maxoff - off + 1) * sizeofitem);
if (isleaf)
{
GinBtreeDataLeafInsertData *items = insertdata;
memcpy(ptr, items->items + items->curitem, sizeofitem);
items->curitem++;
}
else
{
PostingItem *pitem = insertdata;
memcpy(ptr, pitem, sizeofitem);
}
maxoff++;
}
/*
* we assume that during index creation the table scanned from beginning
* to end, so ItemPointers are in monotonically increasing order.
*/
if (btree->isBuild && GinPageRightMost(lpage))
separator = freeSpace / sizeofitem;
else
separator = maxoff / 2;
GinInitPage(rpage, GinPageGetOpaque(lpage)->flags, pageSize);
GinInitPage(lpage, GinPageGetOpaque(rpage)->flags, pageSize);
if (isleaf)
memcpy(GinDataPageGetItemPointer(lpage, FirstOffsetNumber),
vector, separator * sizeof(ItemPointerData));
else
memcpy(GinDataPageGetPostingItem(lpage, FirstOffsetNumber),
vector, separator * sizeof(PostingItem));
GinPageGetOpaque(lpage)->maxoff = separator;
if (isleaf)
memcpy(GinDataPageGetItemPointer(rpage, FirstOffsetNumber),
vector + separator * sizeof(ItemPointerData),
(maxoff - separator) * sizeof(ItemPointerData));
else
memcpy(GinDataPageGetPostingItem(rpage, FirstOffsetNumber),
vector + separator * sizeof(PostingItem),
(maxoff - separator) * sizeof(PostingItem));
GinPageGetOpaque(rpage)->maxoff = maxoff - separator;
/* set up right bound for left page */
bound = GinDataPageGetRightBound(lpage);
if (GinPageIsLeaf(lpage))
*bound = *GinDataPageGetItemPointer(lpage,
GinPageGetOpaque(lpage)->maxoff);
else
*bound = GinDataPageGetPostingItem(lpage,
GinPageGetOpaque(lpage)->maxoff)->key;
/* set up right bound for right page */
bound = GinDataPageGetRightBound(rpage);
*bound = oldbound;
data.separator = separator;
data.nitem = maxoff;
data.rightbound = oldbound;
rdata[0].buffer = InvalidBuffer;
rdata[0].data = (char *) &data;
rdata[0].len = sizeof(ginxlogSplitData);
rdata[0].next = &rdata[1];
rdata[1].buffer = InvalidBuffer;
rdata[1].data = vector;
rdata[1].len = maxoff * sizeofitem;
rdata[1].next = NULL;
return lpage;
}
/*
* Place tuple and split page, original buffer(lbuf) leaves untouched,
* returns shadow page of lbuf filled new data.
* Tuples are distributed between pages by equal size on its, not
* an equal number!
*/
static Page
entrySplitPage(GinBtree btree, Buffer lbuf, Buffer rbuf, OffsetNumber off, XLogRecData **prdata)
{
static XLogRecData rdata[2];
OffsetNumber i,
maxoff,
separator = InvalidOffsetNumber;
Size totalsize = 0;
Size lsize = 0,
size;
static char tupstore[2 * BLCKSZ];
char *ptr;
IndexTuple itup,
leftrightmost = NULL;
static ginxlogSplit data;
Page page;
Page lpage = PageGetTempPageCopy(BufferGetPage(lbuf));
Page rpage = BufferGetPage(rbuf);
Size pageSize = PageGetPageSize(lpage);
*prdata = rdata;
data.leftChildBlkno = (GinPageIsLeaf(lpage)) ?
InvalidOffsetNumber : GinItemPointerGetBlockNumber(&(btree->entry->t_tid));
data.updateBlkno = entryPreparePage(btree, lpage, off);
maxoff = PageGetMaxOffsetNumber(lpage);
ptr = tupstore;
for (i = FirstOffsetNumber; i <= maxoff; i++)
{
if (i == off)
{
size = MAXALIGN(IndexTupleSize(btree->entry));
memcpy(ptr, btree->entry, size);
ptr += size;
totalsize += size + sizeof(ItemIdData);
}
itup = (IndexTuple) PageGetItem(lpage, PageGetItemId(lpage, i));
size = MAXALIGN(IndexTupleSize(itup));
memcpy(ptr, itup, size);
ptr += size;
totalsize += size + sizeof(ItemIdData);
}
if (off == maxoff + 1)
{
size = MAXALIGN(IndexTupleSize(btree->entry));
memcpy(ptr, btree->entry, size);
ptr += size;
totalsize += size + sizeof(ItemIdData);
}
GinInitPage(rpage, GinPageGetOpaque(lpage)->flags, pageSize);
GinInitPage(lpage, GinPageGetOpaque(rpage)->flags, pageSize);
ptr = tupstore;
maxoff++;
lsize = 0;
page = lpage;
for (i = FirstOffsetNumber; i <= maxoff; i++)
{
itup = (IndexTuple) ptr;
if (lsize > totalsize / 2)
{
if (separator == InvalidOffsetNumber)
separator = i - 1;
page = rpage;
}
else
{
leftrightmost = itup;
lsize += MAXALIGN(IndexTupleSize(itup)) + sizeof(ItemIdData);
}
if (PageAddItem(page, (Item) itup, IndexTupleSize(itup), InvalidOffsetNumber, false, false) == InvalidOffsetNumber)
elog(ERROR, "failed to add item to index page in \"%s\"",
RelationGetRelationName(btree->index));
ptr += MAXALIGN(IndexTupleSize(itup));
}
btree->entry = copyIndexTuple(leftrightmost, lpage);
ItemPointerSet(&(btree->entry)->t_tid, BufferGetBlockNumber(lbuf), InvalidOffsetNumber);
btree->rightblkno = BufferGetBlockNumber(rbuf);
data.node = btree->index->rd_node;
data.rootBlkno = InvalidBlockNumber;
data.lblkno = BufferGetBlockNumber(lbuf);
data.rblkno = BufferGetBlockNumber(rbuf);
data.separator = separator;
data.nitem = maxoff;
data.isData = FALSE;
data.isLeaf = GinPageIsLeaf(lpage) ? TRUE : FALSE;
data.isRootSplit = FALSE;
rdata[0].buffer = InvalidBuffer;
rdata[0].data = (char *) &data;
rdata[0].len = sizeof(ginxlogSplit);
rdata[0].next = &rdata[1];
rdata[1].buffer = InvalidBuffer;
rdata[1].data = tupstore;
rdata[1].len = MAXALIGN(totalsize);
rdata[1].next = NULL;
return lpage;
}
