/*
* Place tuple on page and fills WAL record
*/
static void
entryPlaceToPage(GinBtree btree, Buffer buf, OffsetNumber off, XLogRecData **prdata)
{
Page page = BufferGetPage(buf);
static XLogRecData rdata[3];
OffsetNumber placed;
static ginxlogInsert data;
int cnt = 0;
*prdata = rdata;
data.updateBlkno = entryPreparePage(btree, page, off);
placed = PageAddItem(page, (Item) btree->entry, IndexTupleSize(btree->entry), off, false, false);
if (placed != off)
elog(ERROR, "failed to add item to index page in \"%s\"",
RelationGetRelationName(btree->index));
data.node = btree->index->rd_node;
data.blkno = BufferGetBlockNumber(buf);
data.offset = off;
data.nitem = 1;
data.isDelete = btree->isDelete;
data.isData = false;
data.isLeaf = GinPageIsLeaf(page) ? TRUE : FALSE;
/*
* Prevent full page write if child's split occurs. That is needed to
* remove incomplete splits while replaying WAL
*
* data.updateBlkno contains new block number (of newly created right
* page) for recently splited page.
*/
if (data.updateBlkno == InvalidBlockNumber)
{
rdata[0].buffer = buf;
rdata[0].buffer_std = TRUE;
rdata[0].data = NULL;
rdata[0].len = 0;
rdata[0].next = &rdata[1];
cnt++;
}
rdata[cnt].buffer = InvalidBuffer;
rdata[cnt].data = (char *) &data;
rdata[cnt].len = sizeof(ginxlogInsert);
rdata[cnt].next = &rdata[cnt + 1];
cnt++;
rdata[cnt].buffer = InvalidBuffer;
rdata[cnt].data = (char *) btree->entry;
rdata[cnt].len = IndexTupleSize(btree->entry);
rdata[cnt].next = NULL;
btree->entry = NULL;
}
/*
* Place tuple on page and fills WAL record
*
* If the tuple doesn't fit, returns false without modifying the page.
*
* On insertion to an internal node, in addition to inserting the given item,
* the downlink of the existing item at 'off' is updated to point to
* 'updateblkno'.
*/
static GinPlaceToPageRC
entryPlaceToPage(GinBtree btree, Buffer buf, GinBtreeStack *stack,
void *insertPayload, BlockNumber updateblkno,
XLogRecData **prdata, Page *newlpage, Page *newrpage)
{
GinBtreeEntryInsertData *insertData = insertPayload;
Page page = BufferGetPage(buf);
OffsetNumber off = stack->off;
OffsetNumber placed;
int cnt = 0;
/* these must be static so they can be returned to caller */
static XLogRecData rdata[3];
static ginxlogInsertEntry data;
/* quick exit if it doesn't fit */
if (!entryIsEnoughSpace(btree, buf, off, insertData))
{
entrySplitPage(btree, buf, stack, insertPayload, updateblkno,
prdata, newlpage, newrpage);
return SPLIT;
}
START_CRIT_SECTION();
*prdata = rdata;
entryPreparePage(btree, page, off, insertData, updateblkno);
placed = PageAddItem(page,
(Item) insertData->entry,
IndexTupleSize(insertData->entry),
off, false, false);
if (placed != off)
elog(ERROR, "failed to add item to index page in \"%s\"",
RelationGetRelationName(btree->index));
data.isDelete = insertData->isDelete;
data.offset = off;
rdata[cnt].buffer = buf;
rdata[cnt].buffer_std = true;
rdata[cnt].data = (char *) &data;
rdata[cnt].len = offsetof(ginxlogInsertEntry, tuple);
rdata[cnt].next = &rdata[cnt + 1];
cnt++;
rdata[cnt].buffer = buf;
rdata[cnt].buffer_std = true;
rdata[cnt].data = (char *) insertData->entry;
rdata[cnt].len = IndexTupleSize(insertData->entry);
rdata[cnt].next = NULL;
return INSERTED;
}
/*
* Place tuple on page and fills WAL record
*/
static void
entryPlaceToPage(RumBtree btree, Page page, OffsetNumber off)
{
OffsetNumber placed;
entryPreparePage(btree, page, off);
placed = PageAddItem(page, (Item) btree->entry, IndexTupleSize(btree->entry), off, false, false);
if (placed != off)
elog(ERROR, "failed to add item to index page in \"%s\"",
RelationGetRelationName(btree->index));
btree->entry = NULL;
}
/*
* Place tuple on page and fills WAL record
*
* If the tuple doesn't fit, returns false without modifying the page.
*
* On insertion to an internal node, in addition to inserting the given item,
* the downlink of the existing item at 'off' is updated to point to
* 'updateblkno'.
*
* On INSERTED, registers the buffer as buffer ID 0, with data.
* On SPLIT, returns rdata that represents the split pages in *prdata.
*/
static GinPlaceToPageRC
entryPlaceToPage(GinBtree btree, Buffer buf, GinBtreeStack *stack,
void *insertPayload, BlockNumber updateblkno,
Page *newlpage, Page *newrpage)
{
GinBtreeEntryInsertData *insertData = insertPayload;
Page page = BufferGetPage(buf, NULL, NULL, BGP_NO_SNAPSHOT_TEST);
OffsetNumber off = stack->off;
OffsetNumber placed;
/* this must be static so it can be returned to caller. */
static ginxlogInsertEntry data;
/* quick exit if it doesn't fit */
if (!entryIsEnoughSpace(btree, buf, off, insertData))
{
entrySplitPage(btree, buf, stack, insertPayload, updateblkno,
newlpage, newrpage);
return SPLIT;
}
START_CRIT_SECTION();
entryPreparePage(btree, page, off, insertData, updateblkno);
placed = PageAddItem(page,
(Item) insertData->entry,
IndexTupleSize(insertData->entry),
off, false, false);
if (placed != off)
elog(ERROR, "failed to add item to index page in \"%s\"",
RelationGetRelationName(btree->index));
if (RelationNeedsWAL(btree->index))
{
data.isDelete = insertData->isDelete;
data.offset = off;
XLogBeginInsert();
XLogRegisterBuffer(0, buf, REGBUF_STANDARD);
XLogRegisterBufData(0, (char *) &data,
offsetof(ginxlogInsertEntry, tuple));
XLogRegisterBufData(0, (char *) insertData->entry,
IndexTupleSize(insertData->entry));
}
return INSERTED;
}
/*
* Perform data insertion after beginPlaceToPage has decided it will fit.
*
* This is invoked within a critical section, and XLOG record creation (if
* needed) is already started. The target buffer is registered in slot 0.
*/
static void
entryExecPlaceToPage(GinBtree btree, Buffer buf, GinBtreeStack *stack,
void *insertPayload, BlockNumber updateblkno,
void *ptp_workspace)
{
GinBtreeEntryInsertData *insertData = insertPayload;
Page page = BufferGetPage(buf);
OffsetNumber off = stack->off;
OffsetNumber placed;
entryPreparePage(btree, page, off, insertData, updateblkno);
placed = PageAddItem(page,
(Item) insertData->entry,
IndexTupleSize(insertData->entry),
off, false, false);
if (placed != off)
elog(ERROR, "failed to add item to index page in \"%s\"",
RelationGetRelationName(btree->index));
if (RelationNeedsWAL(btree->index))
{
/*
* This must be static, because it has to survive until XLogInsert,
* and we can't palloc here. Ugly, but the XLogInsert infrastructure
* isn't reentrant anyway.
*/
static ginxlogInsertEntry data;
data.isDelete = insertData->isDelete;
data.offset = off;
XLogRegisterBufData(0, (char *) &data,
offsetof(ginxlogInsertEntry, tuple));
XLogRegisterBufData(0, (char *) insertData->entry,
IndexTupleSize(insertData->entry));
}
}
/*
* 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;
}
/*
* 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;
}
/*
* 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;
}
/*
* 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(RumBtree btree, Buffer lbuf, Buffer rbuf,
Page lPage, Page rPage, OffsetNumber off)
{
OffsetNumber i,
maxoff,
separator = InvalidOffsetNumber;
Size totalsize = 0;
Size lsize = 0,
size;
char *ptr;
IndexTuple itup,
leftrightmost = NULL;
Page page;
Page newlPage = PageGetTempPageCopy(lPage);
Size pageSize = PageGetPageSize(newlPage);
static char tupstore[2 * BLCKSZ];
entryPreparePage(btree, newlPage, off);
maxoff = PageGetMaxOffsetNumber(newlPage);
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(newlPage, PageGetItemId(newlPage, 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);
totalsize += size + sizeof(ItemIdData);
}
RumInitPage(rPage, RumPageGetOpaque(newlPage)->flags, pageSize);
RumInitPage(newlPage, RumPageGetOpaque(rPage)->flags, pageSize);
ptr = tupstore;
maxoff++;
lsize = 0;
page = newlPage;
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 = RumFormInteriorTuple(btree, leftrightmost, newlPage,
BufferGetBlockNumber(lbuf));
btree->rightblkno = BufferGetBlockNumber(rbuf);
return newlPage;
}
