/*
* visibilitymap_set - set a bit on a previously pinned page
*
* recptr is the LSN of the XLOG record we're replaying, if we're in recovery,
* or InvalidXLogRecPtr in normal running. The page LSN is advanced to the
* one provided; in normal running, we generate a new XLOG record and set the
* page LSN to that value. cutoff_xid is the largest xmin on the page being
* marked all-visible; it is needed for Hot Standby, and can be
* InvalidTransactionId if the page contains no tuples.
*
* Caller is expected to set the heap page's PD_ALL_VISIBLE bit before calling
* this function. Except in recovery, caller should also pass the heap
* buffer. When checksums are enabled and we're not in recovery, we must add
* the heap buffer to the WAL chain to protect it from being torn.
*
* You must pass a buffer containing the correct map page to this function.
* Call visibilitymap_pin first to pin the right one. This function doesn't do
* any I/O.
*/
void
visibilitymap_set(Relation rel, BlockNumber heapBlk, Buffer heapBuf,
XLogRecPtr recptr, Buffer vmBuf, TransactionId cutoff_xid)
{
BlockNumber mapBlock = HEAPBLK_TO_MAPBLOCK(heapBlk);
uint32 mapByte = HEAPBLK_TO_MAPBYTE(heapBlk);
uint8 mapBit = HEAPBLK_TO_MAPBIT(heapBlk);
Page page;
char *map;
#ifdef TRACE_VISIBILITYMAP
elog(DEBUG1, "vm_set %s %d", RelationGetRelationName(rel), heapBlk);
#endif
Assert(InRecovery || XLogRecPtrIsInvalid(recptr));
Assert(InRecovery || BufferIsValid(heapBuf));
/* Check that we have the right heap page pinned, if present */
if (BufferIsValid(heapBuf) && BufferGetBlockNumber(heapBuf) != heapBlk)
elog(ERROR, "wrong heap buffer passed to visibilitymap_set");
/* Check that we have the right VM page pinned */
if (!BufferIsValid(vmBuf) || BufferGetBlockNumber(vmBuf) != mapBlock)
elog(ERROR, "wrong VM buffer passed to visibilitymap_set");
page = BufferGetPage(vmBuf);
map = PageGetContents(page);
LockBuffer(vmBuf, BUFFER_LOCK_EXCLUSIVE);
if (!(map[mapByte] & (1 << mapBit)))
{
START_CRIT_SECTION();
map[mapByte] |= (1 << mapBit);
MarkBufferDirty(vmBuf);
if (RelationNeedsWAL(rel))
{
if (XLogRecPtrIsInvalid(recptr))
{
Assert(!InRecovery);
recptr = log_heap_visible(rel->rd_node, heapBuf, vmBuf,
cutoff_xid);
/*
* If data checksums are enabled, we need to protect the heap
* page from being torn.
*/
if (DataChecksumsEnabled())
{
Page heapPage = BufferGetPage(heapBuf);
/* caller is expected to set PD_ALL_VISIBLE first */
Assert(PageIsAllVisible(heapPage));
PageSetLSN(heapPage, recptr);
}
}
PageSetLSN(page, recptr);
}
END_CRIT_SECTION();
}
LockBuffer(vmBuf, BUFFER_LOCK_UNLOCK);
}
static void
spgRedoAddNode(XLogRecPtr lsn, XLogRecord *record)
{
char *ptr = XLogRecGetData(record);
spgxlogAddNode *xldata = (spgxlogAddNode *) ptr;
SpGistInnerTuple innerTuple;
SpGistState state;
Buffer buffer;
Page page;
int bbi;
/* we assume this is adequately aligned */
ptr += sizeof(spgxlogAddNode);
innerTuple = (SpGistInnerTuple) ptr;
fillFakeState(&state, xldata->stateSrc);
if (xldata->blknoNew == InvalidBlockNumber)
{
/* update in place */
Assert(xldata->blknoParent == InvalidBlockNumber);
if (!(record->xl_info & XLR_BKP_BLOCK_1))
{
buffer = XLogReadBuffer(xldata->node, xldata->blkno, false);
if (BufferIsValid(buffer))
{
page = BufferGetPage(buffer);
if (!XLByteLE(lsn, PageGetLSN(page)))
{
PageIndexTupleDelete(page, xldata->offnum);
if (PageAddItem(page, (Item) innerTuple, innerTuple->size,
xldata->offnum,
false, false) != xldata->offnum)
elog(ERROR, "failed to add item of size %u to SPGiST index page",
innerTuple->size);
PageSetLSN(page, lsn);
PageSetTLI(page, ThisTimeLineID);
MarkBufferDirty(buffer);
}
UnlockReleaseBuffer(buffer);
}
}
}
else
{
/* Install new tuple first so redirect is valid */
if (!(record->xl_info & XLR_BKP_BLOCK_2))
{
buffer = XLogReadBuffer(xldata->node, xldata->blknoNew,
xldata->newPage);
if (BufferIsValid(buffer))
{
page = BufferGetPage(buffer);
if (xldata->newPage)
SpGistInitBuffer(buffer, 0);
if (!XLByteLE(lsn, PageGetLSN(page)))
{
addOrReplaceTuple(page, (Item) innerTuple,
innerTuple->size, xldata->offnumNew);
PageSetLSN(page, lsn);
PageSetTLI(page, ThisTimeLineID);
MarkBufferDirty(buffer);
}
UnlockReleaseBuffer(buffer);
}
}
/* Delete old tuple, replacing it with redirect or placeholder tuple */
if (!(record->xl_info & XLR_BKP_BLOCK_1))
{
buffer = XLogReadBuffer(xldata->node, xldata->blkno, false);
if (BufferIsValid(buffer))
{
page = BufferGetPage(buffer);
if (!XLByteLE(lsn, PageGetLSN(page)))
{
SpGistDeadTuple dt;
if (state.isBuild)
dt = spgFormDeadTuple(&state, SPGIST_PLACEHOLDER,
InvalidBlockNumber,
InvalidOffsetNumber);
else
dt = spgFormDeadTuple(&state, SPGIST_REDIRECT,
xldata->blknoNew,
xldata->offnumNew);
PageIndexTupleDelete(page, xldata->offnum);
if (PageAddItem(page, (Item) dt, dt->size,
xldata->offnum,
false, false) != xldata->offnum)
elog(ERROR, "failed to add item of size %u to SPGiST index page",
dt->size);
if (state.isBuild)
SpGistPageGetOpaque(page)->nPlaceholder++;
else
SpGistPageGetOpaque(page)->nRedirection++;
PageSetLSN(page, lsn);
PageSetTLI(page, ThisTimeLineID);
MarkBufferDirty(buffer);
}
UnlockReleaseBuffer(buffer);
}
}
/*
* Update parent downlink. Since parent could be in either of the
* previous two buffers, it's a bit tricky to determine which BKP bit
* applies.
*/
if (xldata->blknoParent == xldata->blkno)
bbi = 0;
else if (xldata->blknoParent == xldata->blknoNew)
bbi = 1;
else
bbi = 2;
if (!(record->xl_info & XLR_SET_BKP_BLOCK(bbi)))
{
buffer = XLogReadBuffer(xldata->node, xldata->blknoParent, false);
if (BufferIsValid(buffer))
{
page = BufferGetPage(buffer);
if (!XLByteLE(lsn, PageGetLSN(page)))
{
SpGistInnerTuple innerTuple;
innerTuple = (SpGistInnerTuple) PageGetItem(page,
PageGetItemId(page, xldata->offnumParent));
spgUpdateNodeLink(innerTuple, xldata->nodeI,
xldata->blknoNew, xldata->offnumNew);
PageSetLSN(page, lsn);
PageSetTLI(page, ThisTimeLineID);
MarkBufferDirty(buffer);
}
UnlockReleaseBuffer(buffer);
}
}
}
}
static void
spgRedoPickSplit(XLogRecPtr lsn, XLogRecord *record)
{
char *ptr = XLogRecGetData(record);
spgxlogPickSplit *xldata = (spgxlogPickSplit *) ptr;
SpGistInnerTuple innerTuple;
SpGistState state;
OffsetNumber *toDelete;
OffsetNumber *toInsert;
uint8 *leafPageSelect;
Buffer srcBuffer;
Buffer destBuffer;
Page page;
int bbi;
int i;
fillFakeState(&state, xldata->stateSrc);
ptr += MAXALIGN(sizeof(spgxlogPickSplit));
innerTuple = (SpGistInnerTuple) ptr;
ptr += innerTuple->size;
toDelete = (OffsetNumber *) ptr;
ptr += MAXALIGN(sizeof(OffsetNumber) * xldata->nDelete);
toInsert = (OffsetNumber *) ptr;
ptr += MAXALIGN(sizeof(OffsetNumber) * xldata->nInsert);
leafPageSelect = (uint8 *) ptr;
ptr += MAXALIGN(sizeof(uint8) * xldata->nInsert);
/* now ptr points to the list of leaf tuples */
/*
* It's a bit tricky to identify which pages have been handled as
* full-page images, so we explicitly count each referenced buffer.
*/
bbi = 0;
if (xldata->blknoSrc == SPGIST_HEAD_BLKNO)
{
/* when splitting root, we touch it only in the guise of new inner */
srcBuffer = InvalidBuffer;
}
else if (xldata->initSrc)
{
/* just re-init the source page */
srcBuffer = XLogReadBuffer(xldata->node, xldata->blknoSrc, true);
Assert(BufferIsValid(srcBuffer));
page = (Page) BufferGetPage(srcBuffer);
SpGistInitBuffer(srcBuffer, SPGIST_LEAF);
/* don't update LSN etc till we're done with it */
}
else
{
/* delete the specified tuples from source page */
if (!(record->xl_info & XLR_SET_BKP_BLOCK(bbi)))
{
srcBuffer = XLogReadBuffer(xldata->node, xldata->blknoSrc, false);
if (BufferIsValid(srcBuffer))
{
page = BufferGetPage(srcBuffer);
if (!XLByteLE(lsn, PageGetLSN(page)))
{
/*
* We have it a bit easier here than in doPickSplit(),
* because we know the inner tuple's location already,
* so we can inject the correct redirection tuple now.
*/
if (!state.isBuild)
spgPageIndexMultiDelete(&state, page,
toDelete, xldata->nDelete,
SPGIST_REDIRECT,
SPGIST_PLACEHOLDER,
xldata->blknoInner,
xldata->offnumInner);
else
spgPageIndexMultiDelete(&state, page,
toDelete, xldata->nDelete,
SPGIST_PLACEHOLDER,
SPGIST_PLACEHOLDER,
InvalidBlockNumber,
InvalidOffsetNumber);
/* don't update LSN etc till we're done with it */
}
}
}
else
srcBuffer = InvalidBuffer;
bbi++;
}
/* try to access dest page if any */
if (xldata->blknoDest == InvalidBlockNumber)
{
destBuffer = InvalidBuffer;
}
else if (xldata->initDest)
{
/* just re-init the dest page */
destBuffer = XLogReadBuffer(xldata->node, xldata->blknoDest, true);
Assert(BufferIsValid(destBuffer));
page = (Page) BufferGetPage(destBuffer);
SpGistInitBuffer(destBuffer, SPGIST_LEAF);
/* don't update LSN etc till we're done with it */
}
else
{
if (!(record->xl_info & XLR_SET_BKP_BLOCK(bbi)))
destBuffer = XLogReadBuffer(xldata->node, xldata->blknoDest, false);
else
destBuffer = InvalidBuffer;
bbi++;
}
/* restore leaf tuples to src and/or dest page */
for (i = 0; i < xldata->nInsert; i++)
{
SpGistLeafTuple lt = (SpGistLeafTuple) ptr;
Buffer leafBuffer;
ptr += lt->size;
leafBuffer = leafPageSelect[i] ? destBuffer : srcBuffer;
if (!BufferIsValid(leafBuffer))
continue; /* no need to touch this page */
page = BufferGetPage(leafBuffer);
if (!XLByteLE(lsn, PageGetLSN(page)))
{
addOrReplaceTuple(page, (Item) lt, lt->size, toInsert[i]);
}
}
/* Now update src and dest page LSNs */
if (BufferIsValid(srcBuffer))
{
page = BufferGetPage(srcBuffer);
if (!XLByteLE(lsn, PageGetLSN(page)))
{
PageSetLSN(page, lsn);
PageSetTLI(page, ThisTimeLineID);
MarkBufferDirty(srcBuffer);
}
UnlockReleaseBuffer(srcBuffer);
}
if (BufferIsValid(destBuffer))
{
page = BufferGetPage(destBuffer);
if (!XLByteLE(lsn, PageGetLSN(page)))
{
PageSetLSN(page, lsn);
PageSetTLI(page, ThisTimeLineID);
MarkBufferDirty(destBuffer);
}
UnlockReleaseBuffer(destBuffer);
}
/* restore new inner tuple */
if (!(record->xl_info & XLR_SET_BKP_BLOCK(bbi)))
{
Buffer buffer = XLogReadBuffer(xldata->node, xldata->blknoInner,
xldata->initInner);
if (BufferIsValid(buffer))
{
page = BufferGetPage(buffer);
if (xldata->initInner)
SpGistInitBuffer(buffer, 0);
if (!XLByteLE(lsn, PageGetLSN(page)))
{
addOrReplaceTuple(page, (Item) innerTuple, innerTuple->size,
xldata->offnumInner);
/* if inner is also parent, update link while we're here */
if (xldata->blknoInner == xldata->blknoParent)
{
SpGistInnerTuple parent;
parent = (SpGistInnerTuple) PageGetItem(page,
PageGetItemId(page, xldata->offnumParent));
spgUpdateNodeLink(parent, xldata->nodeI,
xldata->blknoInner, xldata->offnumInner);
}
PageSetLSN(page, lsn);
PageSetTLI(page, ThisTimeLineID);
MarkBufferDirty(buffer);
}
UnlockReleaseBuffer(buffer);
}
}
bbi++;
/* update parent downlink, unless we did it above */
if (xldata->blknoParent == InvalidBlockNumber)
{
/* no parent cause we split the root */
Assert(xldata->blknoInner == SPGIST_HEAD_BLKNO);
}
else if (xldata->blknoInner != xldata->blknoParent)
{
if (!(record->xl_info & XLR_SET_BKP_BLOCK(bbi)))
{
Buffer buffer = XLogReadBuffer(xldata->node, xldata->blknoParent, false);
if (BufferIsValid(buffer))
{
page = BufferGetPage(buffer);
if (!XLByteLE(lsn, PageGetLSN(page)))
{
SpGistInnerTuple parent;
parent = (SpGistInnerTuple) PageGetItem(page,
PageGetItemId(page, xldata->offnumParent));
spgUpdateNodeLink(parent, xldata->nodeI,
xldata->blknoInner, xldata->offnumInner);
PageSetLSN(page, lsn);
PageSetTLI(page, ThisTimeLineID);
MarkBufferDirty(buffer);
}
UnlockReleaseBuffer(buffer);
}
}
}
}
/*
* redo any page update (except page split)
*/
static void
gistRedoPageUpdateRecord(XLogRecPtr lsn, XLogRecord *record)
{
char *begin = XLogRecGetData(record);
gistxlogPageUpdate *xldata = (gistxlogPageUpdate *) begin;
Buffer buffer;
Page page;
char *data;
/*
* We need to acquire and hold lock on target page while updating the left
* child page. If we have a full-page image of target page, getting the
* lock is a side-effect of restoring that image. Note that even if the
* target page no longer exists, we'll still attempt to replay the change
* on the child page.
*/
if (record->xl_info & XLR_BKP_BLOCK(0))
buffer = RestoreBackupBlock(lsn, record, 0, false, true);
else
buffer = XLogReadBuffer(xldata->node, xldata->blkno, false);
/* Fix follow-right data on left child page */
if (BlockNumberIsValid(xldata->leftchild))
gistRedoClearFollowRight(lsn, record, 1,
xldata->node, xldata->leftchild);
/* Done if target page no longer exists */
if (!BufferIsValid(buffer))
return;
/* nothing more to do if page was backed up (and no info to do it with) */
if (record->xl_info & XLR_BKP_BLOCK(0))
{
UnlockReleaseBuffer(buffer);
return;
}
page = (Page) BufferGetPage(buffer);
/* nothing more to do if change already applied */
if (lsn <= PageGetLSN(page))
{
UnlockReleaseBuffer(buffer);
return;
}
data = begin + sizeof(gistxlogPageUpdate);
/* Delete old tuples */
if (xldata->ntodelete > 0)
{
int i;
OffsetNumber *todelete = (OffsetNumber *) data;
data += sizeof(OffsetNumber) * xldata->ntodelete;
for (i = 0; i < xldata->ntodelete; i++)
PageIndexTupleDelete(page, todelete[i]);
if (GistPageIsLeaf(page))
GistMarkTuplesDeleted(page);
}
/* add tuples */
if (data - begin < record->xl_len)
{
OffsetNumber off = (PageIsEmpty(page)) ? FirstOffsetNumber :
OffsetNumberNext(PageGetMaxOffsetNumber(page));
while (data - begin < record->xl_len)
{
IndexTuple itup = (IndexTuple) data;
Size sz = IndexTupleSize(itup);
OffsetNumber l;
data += sz;
l = PageAddItem(page, (Item) itup, sz, off, false, false);
if (l == InvalidOffsetNumber)
elog(ERROR, "failed to add item to GiST index page, size %d bytes",
(int) sz);
off++;
}
}
else
{
/*
* special case: leafpage, nothing to insert, nothing to delete, then
* vacuum marks page
*/
if (GistPageIsLeaf(page) && xldata->ntodelete == 0)
GistClearTuplesDeleted(page);
}
if (!GistPageIsLeaf(page) &&
PageGetMaxOffsetNumber(page) == InvalidOffsetNumber &&
xldata->blkno == GIST_ROOT_BLKNO)
{
/*
* all links on non-leaf root page was deleted by vacuum full, so root
* page becomes a leaf
*/
GistPageSetLeaf(page);
}
GistPageGetOpaque(page)->rightlink = InvalidBlockNumber;
PageSetLSN(page, lsn);
MarkBufferDirty(buffer);
UnlockReleaseBuffer(buffer);
}
/*
* A tuple in the heap is being inserted. To keep a brin index up to date,
* we need to obtain the relevant index tuple and compare its stored values
* with those of the new tuple. If the tuple values are not consistent with
* the summary tuple, we need to update the index tuple.
*
* If the range is not currently summarized (i.e. the revmap returns NULL for
* it), there's nothing to do.
*/
bool
brininsert(Relation idxRel, Datum *values, bool *nulls,
ItemPointer heaptid, Relation heapRel,
IndexUniqueCheck checkUnique)
{
BlockNumber pagesPerRange;
BrinDesc *bdesc = NULL;
BrinRevmap *revmap;
Buffer buf = InvalidBuffer;
MemoryContext tupcxt = NULL;
MemoryContext oldcxt = NULL;
revmap = brinRevmapInitialize(idxRel, &pagesPerRange, NULL);
for (;;)
{
bool need_insert = false;
OffsetNumber off;
BrinTuple *brtup;
BrinMemTuple *dtup;
BlockNumber heapBlk;
int keyno;
CHECK_FOR_INTERRUPTS();
heapBlk = ItemPointerGetBlockNumber(heaptid);
/* normalize the block number to be the first block in the range */
heapBlk = (heapBlk / pagesPerRange) * pagesPerRange;
brtup = brinGetTupleForHeapBlock(revmap, heapBlk, &buf, &off, NULL,
BUFFER_LOCK_SHARE, NULL);
/* if range is unsummarized, there's nothing to do */
if (!brtup)
break;
/* First time through? */
if (bdesc == NULL)
{
bdesc = brin_build_desc(idxRel);
tupcxt = AllocSetContextCreate(CurrentMemoryContext,
"brininsert cxt",
ALLOCSET_DEFAULT_SIZES);
oldcxt = MemoryContextSwitchTo(tupcxt);
}
dtup = brin_deform_tuple(bdesc, brtup);
/*
* Compare the key values of the new tuple to the stored index values;
* our deformed tuple will get updated if the new tuple doesn't fit
* the original range (note this means we can't break out of the loop
* early). Make a note of whether this happens, so that we know to
* insert the modified tuple later.
*/
for (keyno = 0; keyno < bdesc->bd_tupdesc->natts; keyno++)
{
Datum result;
BrinValues *bval;
FmgrInfo *addValue;
bval = &dtup->bt_columns[keyno];
addValue = index_getprocinfo(idxRel, keyno + 1,
BRIN_PROCNUM_ADDVALUE);
result = FunctionCall4Coll(addValue,
idxRel->rd_indcollation[keyno],
PointerGetDatum(bdesc),
PointerGetDatum(bval),
values[keyno],
nulls[keyno]);
/* if that returned true, we need to insert the updated tuple */
need_insert |= DatumGetBool(result);
}
if (!need_insert)
{
/*
* The tuple is consistent with the new values, so there's nothing
* to do.
*/
LockBuffer(buf, BUFFER_LOCK_UNLOCK);
}
else
{
Page page = BufferGetPage(buf);
ItemId lp = PageGetItemId(page, off);
Size origsz;
BrinTuple *origtup;
Size newsz;
BrinTuple *newtup;
bool samepage;
/*
* Make a copy of the old tuple, so that we can compare it after
* re-acquiring the lock.
*/
origsz = ItemIdGetLength(lp);
origtup = brin_copy_tuple(brtup, origsz);
/*
* Before releasing the lock, check if we can attempt a same-page
* update. Another process could insert a tuple concurrently in
* the same page though, so downstream we must be prepared to cope
* if this turns out to not be possible after all.
*/
newtup = brin_form_tuple(bdesc, heapBlk, dtup, &newsz);
samepage = brin_can_do_samepage_update(buf, origsz, newsz);
LockBuffer(buf, BUFFER_LOCK_UNLOCK);
/*
* Try to update the tuple. If this doesn't work for whatever
* reason, we need to restart from the top; the revmap might be
* pointing at a different tuple for this block now, so we need to
* recompute to ensure both our new heap tuple and the other
* inserter's are covered by the combined tuple. It might be that
* we don't need to update at all.
*/
if (!brin_doupdate(idxRel, pagesPerRange, revmap, heapBlk,
buf, off, origtup, origsz, newtup, newsz,
samepage))
{
/* no luck; start over */
MemoryContextResetAndDeleteChildren(tupcxt);
continue;
}
}
/* success! */
break;
}
brinRevmapTerminate(revmap);
if (BufferIsValid(buf))
ReleaseBuffer(buf);
if (bdesc != NULL)
{
brin_free_desc(bdesc);
MemoryContextSwitchTo(oldcxt);
MemoryContextDelete(tupcxt);
}
return false;
}
/*
* _bt_search() -- Search the tree for a particular scankey,
* or more precisely for the first leaf page it could be on.
*
* The passed scankey must be an insertion-type scankey (see nbtree/README),
* but it can omit the rightmost column(s) of the index.
*
* When nextkey is false (the usual case), we are looking for the first
* item >= scankey. When nextkey is true, we are looking for the first
* item strictly greater than scankey.
*
* Return value is a stack of parent-page pointers. *bufP is set to the
* address of the leaf-page buffer, which is read-locked and pinned.
* No locks are held on the parent pages, however!
*
* NOTE that the returned buffer is read-locked regardless of the access
* parameter. However, access = BT_WRITE will allow an empty root page
* to be created and returned. When access = BT_READ, an empty index
* will result in *bufP being set to InvalidBuffer.
*/
BTStack
_bt_search(Relation rel, int keysz, ScanKey scankey, bool nextkey,
Buffer *bufP, int access)
{
BTStack stack_in = NULL;
/* Get the root page to start with */
*bufP = _bt_getroot(rel, access);
/* If index is empty and access = BT_READ, no root page is created. */
if (!BufferIsValid(*bufP))
return (BTStack) NULL;
/* Loop iterates once per level descended in the tree */
for (;;)
{
Page page;
BTPageOpaque opaque;
OffsetNumber offnum;
ItemId itemid;
IndexTuple itup;
BlockNumber blkno;
BlockNumber par_blkno;
BTStack new_stack;
/*
* Race -- the page we just grabbed may have split since we read its
* pointer in the parent (or metapage). If it has, we may need to
* move right to its new sibling. Do that.
*/
*bufP = _bt_moveright(rel, *bufP, keysz, scankey, nextkey, BT_READ);
/* if this is a leaf page, we're done */
page = BufferGetPage(*bufP);
opaque = (BTPageOpaque) PageGetSpecialPointer(page);
if (P_ISLEAF(opaque))
break;
/*
* Find the appropriate item on the internal page, and get the child
* page that it points to.
*/
offnum = _bt_binsrch(rel, *bufP, keysz, scankey, nextkey);
itemid = PageGetItemId(page, offnum);
itup = (IndexTuple) PageGetItem(page, itemid);
blkno = ItemPointerGetBlockNumber(&(itup->t_tid));
par_blkno = BufferGetBlockNumber(*bufP);
/*
* We need to save the location of the index entry we chose in the
* parent page on a stack. In case we split the tree, we'll use the
* stack to work back up to the parent page. We also save the actual
* downlink (TID) to uniquely identify the index entry, in case it
* moves right while we're working lower in the tree. See the paper
* by Lehman and Yao for how this is detected and handled. (We use the
* child link to disambiguate duplicate keys in the index -- Lehman
* and Yao disallow duplicate keys.)
*/
new_stack = (BTStack) palloc(sizeof(BTStackData));
new_stack->bts_blkno = par_blkno;
new_stack->bts_offset = offnum;
memcpy(&new_stack->bts_btentry, itup, sizeof(IndexTupleData));
new_stack->bts_parent = stack_in;
/* drop the read lock on the parent page, acquire one on the child */
*bufP = _bt_relandgetbuf(rel, *bufP, blkno, BT_READ);
/* okay, all set to move down a level */
stack_in = new_stack;
}
return stack_in;
}
/*
* Write WAL record of a page split.
*/
XLogRecPtr
gistXLogSplit(RelFileNode node, BlockNumber blkno, bool page_is_leaf,
SplitedPageLayout *dist,
BlockNumber origrlink, GistNSN orignsn,
Buffer leftchildbuf, bool markfollowright)
{
XLogRecData *rdata;
gistxlogPageSplit xlrec;
SplitedPageLayout *ptr;
int npage = 0,
cur;
XLogRecPtr recptr;
for (ptr = dist; ptr; ptr = ptr->next)
npage++;
rdata = (XLogRecData *) palloc(sizeof(XLogRecData) * (npage * 2 + 2));
xlrec.node = node;
xlrec.origblkno = blkno;
xlrec.origrlink = origrlink;
xlrec.orignsn = orignsn;
xlrec.origleaf = page_is_leaf;
xlrec.npage = (uint16) npage;
xlrec.leftchild =
BufferIsValid(leftchildbuf) ? BufferGetBlockNumber(leftchildbuf) : InvalidBlockNumber;
xlrec.markfollowright = markfollowright;
rdata[0].data = (char *) &xlrec;
rdata[0].len = sizeof(gistxlogPageSplit);
rdata[0].buffer = InvalidBuffer;
cur = 1;
/*
* Include a full page image of the child buf. (only necessary if a
* checkpoint happened since the child page was split)
*/
if (BufferIsValid(leftchildbuf))
{
rdata[cur - 1].next = &(rdata[cur]);
rdata[cur].data = NULL;
rdata[cur].len = 0;
rdata[cur].buffer = leftchildbuf;
rdata[cur].buffer_std = true;
cur++;
}
for (ptr = dist; ptr; ptr = ptr->next)
{
rdata[cur - 1].next = &(rdata[cur]);
rdata[cur].buffer = InvalidBuffer;
rdata[cur].data = (char *) &(ptr->block);
rdata[cur].len = sizeof(gistxlogPage);
cur++;
rdata[cur - 1].next = &(rdata[cur]);
rdata[cur].buffer = InvalidBuffer;
rdata[cur].data = (char *) (ptr->list);
rdata[cur].len = ptr->lenlist;
cur++;
}
rdata[cur - 1].next = NULL;
recptr = XLogInsert(RM_GIST_ID, XLOG_GIST_PAGE_SPLIT, rdata);
pfree(rdata);
return recptr;
}
/*
* Scan a complete BRIN index, and summarize each page range that's not already
* summarized. The index and heap must have been locked by caller in at
* least ShareUpdateExclusiveLock mode.
*
* For each new index tuple inserted, *numSummarized (if not NULL) is
* incremented; for each existing tuple, numExisting (if not NULL) is
* incremented.
*/
static void
brinsummarize(Relation index, Relation heapRel, double *numSummarized,
double *numExisting)
{
BrinRevmap *revmap;
BrinBuildState *state = NULL;
IndexInfo *indexInfo = NULL;
BlockNumber heapNumBlocks;
BlockNumber heapBlk;
BlockNumber pagesPerRange;
Buffer buf;
revmap = brinRevmapInitialize(index, &pagesPerRange);
/*
* Scan the revmap to find unsummarized items.
*/
buf = InvalidBuffer;
heapNumBlocks = RelationGetNumberOfBlocks(heapRel);
for (heapBlk = 0; heapBlk < heapNumBlocks; heapBlk += pagesPerRange)
{
BrinTuple *tup;
OffsetNumber off;
CHECK_FOR_INTERRUPTS();
tup = brinGetTupleForHeapBlock(revmap, heapBlk, &buf, &off, NULL,
BUFFER_LOCK_SHARE);
if (tup == NULL)
{
/* no revmap entry for this heap range. Summarize it. */
if (state == NULL)
{
/* first time through */
Assert(!indexInfo);
state = initialize_brin_buildstate(index, revmap,
pagesPerRange);
indexInfo = BuildIndexInfo(index);
/*
* We only have ShareUpdateExclusiveLock on the table, and
* therefore other sessions may insert tuples into the range
* we're going to scan. This is okay, because we take
* additional precautions to avoid losing the additional
* tuples; see comments in summarize_range. Set the
* concurrent flag, which causes IndexBuildHeapRangeScan to
* use a snapshot other than SnapshotAny, and silences
* warnings emitted there.
*/
indexInfo->ii_Concurrent = true;
/*
* If using transaction-snapshot mode, it would be possible
* for another transaction to insert a tuple that's not
* visible to our snapshot if we have already acquired one,
* when in snapshot-isolation mode; therefore, disallow this
* from running in such a transaction unless a snapshot hasn't
* been acquired yet.
*
* This code is called by VACUUM and
* brin_summarize_new_values. Have the error message mention
* the latter because VACUUM cannot run in a transaction and
* thus cannot cause this issue.
*/
if (IsolationUsesXactSnapshot() && FirstSnapshotSet)
ereport(ERROR,
(errcode(ERRCODE_INVALID_TRANSACTION_STATE),
errmsg("brin_summarize_new_values() cannot run in a transaction that has already obtained a snapshot")));
}
summarize_range(indexInfo, state, heapRel, heapBlk);
/* and re-initialize state for the next range */
brin_memtuple_initialize(state->bs_dtuple, state->bs_bdesc);
if (numSummarized)
*numSummarized += 1.0;
}
else
{
if (numExisting)
*numExisting += 1.0;
LockBuffer(buf, BUFFER_LOCK_UNLOCK);
}
}
if (BufferIsValid(buf))
ReleaseBuffer(buf);
/* free resources */
brinRevmapTerminate(revmap);
if (state)
terminate_brin_buildstate(state);
}
/*
* A tuple in the heap is being inserted. To keep a brin index up to date,
* we need to obtain the relevant index tuple and compare its stored values
* with those of the new tuple. If the tuple values are not consistent with
* the summary tuple, we need to update the index tuple.
*
* If the range is not currently summarized (i.e. the revmap returns NULL for
* it), there's nothing to do.
*/
Datum
brininsert(PG_FUNCTION_ARGS)
{
Relation idxRel = (Relation) PG_GETARG_POINTER(0);
Datum *values = (Datum *) PG_GETARG_POINTER(1);
bool *nulls = (bool *) PG_GETARG_POINTER(2);
ItemPointer heaptid = (ItemPointer) PG_GETARG_POINTER(3);
/* we ignore the rest of our arguments */
BlockNumber pagesPerRange;
BrinDesc *bdesc = NULL;
BrinRevmap *revmap;
Buffer buf = InvalidBuffer;
MemoryContext tupcxt = NULL;
MemoryContext oldcxt = NULL;
revmap = brinRevmapInitialize(idxRel, &pagesPerRange);
for (;;)
{
bool need_insert = false;
OffsetNumber off;
BrinTuple *brtup;
BrinMemTuple *dtup;
BlockNumber heapBlk;
int keyno;
#ifdef USE_ASSERT_CHECKING
BrinTuple *tmptup;
BrinMemTuple *tmpdtup;
Size tmpsiz;
#endif
CHECK_FOR_INTERRUPTS();
heapBlk = ItemPointerGetBlockNumber(heaptid);
/* normalize the block number to be the first block in the range */
heapBlk = (heapBlk / pagesPerRange) * pagesPerRange;
brtup = brinGetTupleForHeapBlock(revmap, heapBlk, &buf, &off, NULL,
BUFFER_LOCK_SHARE);
/* if range is unsummarized, there's nothing to do */
if (!brtup)
break;
/* First time through? */
if (bdesc == NULL)
{
bdesc = brin_build_desc(idxRel);
tupcxt = AllocSetContextCreate(CurrentMemoryContext,
"brininsert cxt",
ALLOCSET_DEFAULT_MINSIZE,
ALLOCSET_DEFAULT_INITSIZE,
ALLOCSET_DEFAULT_MAXSIZE);
oldcxt = MemoryContextSwitchTo(tupcxt);
}
dtup = brin_deform_tuple(bdesc, brtup);
#ifdef USE_ASSERT_CHECKING
{
/*
* When assertions are enabled, we use this as an opportunity to
* test the "union" method, which would otherwise be used very
* rarely: first create a placeholder tuple, and addValue the
* value we just got into it. Then union the existing index tuple
* with the updated placeholder tuple. The tuple resulting from
* that union should be identical to the one resulting from the
* regular operation (straight addValue) below.
*
* Here we create the tuple to compare with; the actual comparison
* is below.
*/
tmptup = brin_form_placeholder_tuple(bdesc, heapBlk, &tmpsiz);
tmpdtup = brin_deform_tuple(bdesc, tmptup);
for (keyno = 0; keyno < bdesc->bd_tupdesc->natts; keyno++)
{
BrinValues *bval;
FmgrInfo *addValue;
bval = &tmpdtup->bt_columns[keyno];
addValue = index_getprocinfo(idxRel, keyno + 1,
BRIN_PROCNUM_ADDVALUE);
FunctionCall4Coll(addValue,
idxRel->rd_indcollation[keyno],
PointerGetDatum(bdesc),
PointerGetDatum(bval),
values[keyno],
nulls[keyno]);
}
union_tuples(bdesc, tmpdtup, brtup);
tmpdtup->bt_placeholder = dtup->bt_placeholder;
tmptup = brin_form_tuple(bdesc, heapBlk, tmpdtup, &tmpsiz);
}
#endif
/*
* Compare the key values of the new tuple to the stored index values;
* our deformed tuple will get updated if the new tuple doesn't fit
* the original range (note this means we can't break out of the loop
* early). Make a note of whether this happens, so that we know to
* insert the modified tuple later.
*/
for (keyno = 0; keyno < bdesc->bd_tupdesc->natts; keyno++)
{
Datum result;
BrinValues *bval;
FmgrInfo *addValue;
bval = &dtup->bt_columns[keyno];
addValue = index_getprocinfo(idxRel, keyno + 1,
BRIN_PROCNUM_ADDVALUE);
result = FunctionCall4Coll(addValue,
idxRel->rd_indcollation[keyno],
PointerGetDatum(bdesc),
PointerGetDatum(bval),
values[keyno],
nulls[keyno]);
/* if that returned true, we need to insert the updated tuple */
need_insert |= DatumGetBool(result);
}
#ifdef USE_ASSERT_CHECKING
{
/*
* Now we can compare the tuple produced by the union function
* with the one from plain addValue.
*/
BrinTuple *cmptup;
Size cmpsz;
cmptup = brin_form_tuple(bdesc, heapBlk, dtup, &cmpsz);
Assert(brin_tuples_equal(tmptup, tmpsiz, cmptup, cmpsz));
}
#endif
if (!need_insert)
{
/*
* The tuple is consistent with the new values, so there's nothing
* to do.
*/
LockBuffer(buf, BUFFER_LOCK_UNLOCK);
}
else
{
Page page = BufferGetPage(buf);
ItemId lp = PageGetItemId(page, off);
Size origsz;
BrinTuple *origtup;
Size newsz;
BrinTuple *newtup;
bool samepage;
/*
* Make a copy of the old tuple, so that we can compare it after
* re-acquiring the lock.
*/
origsz = ItemIdGetLength(lp);
origtup = brin_copy_tuple(brtup, origsz);
/*
* Before releasing the lock, check if we can attempt a same-page
* update. Another process could insert a tuple concurrently in
* the same page though, so downstream we must be prepared to cope
* if this turns out to not be possible after all.
*/
newtup = brin_form_tuple(bdesc, heapBlk, dtup, &newsz);
samepage = brin_can_do_samepage_update(buf, origsz, newsz);
LockBuffer(buf, BUFFER_LOCK_UNLOCK);
/*
* Try to update the tuple. If this doesn't work for whatever
* reason, we need to restart from the top; the revmap might be
* pointing at a different tuple for this block now, so we need to
* recompute to ensure both our new heap tuple and the other
* inserter's are covered by the combined tuple. It might be that
* we don't need to update at all.
*/
if (!brin_doupdate(idxRel, pagesPerRange, revmap, heapBlk,
buf, off, origtup, origsz, newtup, newsz,
samepage))
{
/* no luck; start over */
MemoryContextResetAndDeleteChildren(tupcxt);
continue;
}
}
/* success! */
break;
}
brinRevmapTerminate(revmap);
if (BufferIsValid(buf))
ReleaseBuffer(buf);
if (bdesc != NULL)
{
brin_free_desc(bdesc);
MemoryContextSwitchTo(oldcxt);
MemoryContextDelete(tupcxt);
}
return BoolGetDatum(false);
}
/*
* _hash_step() -- step to the next valid item in a scan in the bucket.
*
* If no valid record exists in the requested direction, return
* false. Else, return true and set the hashso_curpos for the
* scan to the right thing.
*
* 'bufP' points to the current buffer, which is pinned and read-locked.
* On success exit, we have pin and read-lock on whichever page
* contains the right item; on failure, we have released all buffers.
*/
bool
_hash_step(IndexScanDesc scan, Buffer *bufP, ScanDirection dir)
{
Relation rel = scan->indexRelation;
HashScanOpaque so = (HashScanOpaque) scan->opaque;
ItemPointer current;
Buffer buf;
Page page;
HashPageOpaque opaque;
OffsetNumber maxoff;
OffsetNumber offnum;
BlockNumber blkno;
IndexTuple itup;
current = &(so->hashso_curpos);
buf = *bufP;
_hash_checkpage(rel, buf, LH_BUCKET_PAGE | LH_OVERFLOW_PAGE);
page = BufferGetPage(buf);
opaque = (HashPageOpaque) PageGetSpecialPointer(page);
/*
* If _hash_step is called from _hash_first, current will not be valid, so
* we can't dereference it. However, in that case, we presumably want to
* start at the beginning/end of the page...
*/
maxoff = PageGetMaxOffsetNumber(page);
if (ItemPointerIsValid(current))
offnum = ItemPointerGetOffsetNumber(current);
else
offnum = InvalidOffsetNumber;
/*
* 'offnum' now points to the last tuple we examined (if any).
*
* continue to step through tuples until: 1) we get to the end of the
* bucket chain or 2) we find a valid tuple.
*/
do
{
switch (dir)
{
case ForwardScanDirection:
if (offnum != InvalidOffsetNumber)
offnum = OffsetNumberNext(offnum); /* move forward */
else
{
/* new page, locate starting position by binary search */
offnum = _hash_binsearch(page, so->hashso_sk_hash);
}
for (;;)
{
/*
* check if we're still in the range of items with the
* target hash key
*/
if (offnum <= maxoff)
{
Assert(offnum >= FirstOffsetNumber);
itup = (IndexTuple) PageGetItem(page, PageGetItemId(page, offnum));
if (so->hashso_sk_hash == _hash_get_indextuple_hashkey(itup))
break; /* yes, so exit for-loop */
}
/*
* ran off the end of this page, try the next
*/
_hash_readnext(rel, &buf, &page, &opaque);
if (BufferIsValid(buf))
{
maxoff = PageGetMaxOffsetNumber(page);
offnum = _hash_binsearch(page, so->hashso_sk_hash);
}
else
{
/* end of bucket */
itup = NULL;
break; /* exit for-loop */
}
}
break;
case BackwardScanDirection:
if (offnum != InvalidOffsetNumber)
offnum = OffsetNumberPrev(offnum); /* move back */
else
{
/* new page, locate starting position by binary search */
offnum = _hash_binsearch_last(page, so->hashso_sk_hash);
}
for (;;)
{
/*
* check if we're still in the range of items with the
* target hash key
*/
if (offnum >= FirstOffsetNumber)
{
Assert(offnum <= maxoff);
itup = (IndexTuple) PageGetItem(page, PageGetItemId(page, offnum));
if (so->hashso_sk_hash == _hash_get_indextuple_hashkey(itup))
break; /* yes, so exit for-loop */
}
/*
* ran off the end of this page, try the next
*/
_hash_readprev(rel, &buf, &page, &opaque);
if (BufferIsValid(buf))
{
maxoff = PageGetMaxOffsetNumber(page);
offnum = _hash_binsearch_last(page, so->hashso_sk_hash);
}
else
{
/* end of bucket */
itup = NULL;
break; /* exit for-loop */
}
}
break;
default:
/* NoMovementScanDirection */
/* this should not be reached */
itup = NULL;
break;
}
if (itup == NULL)
{
/* we ran off the end of the bucket without finding a match */
*bufP = so->hashso_curbuf = InvalidBuffer;
ItemPointerSetInvalid(current);
return false;
}
/* check the tuple quals, loop around if not met */
} while (!_hash_checkqual(scan, itup));
/* if we made it to here, we've found a valid tuple */
blkno = BufferGetBlockNumber(buf);
*bufP = so->hashso_curbuf = buf;
ItemPointerSet(current, blkno, offnum);
return true;
}
/** @brief Acquire a buffer.
@param ulBlock Block number to acquire.
@param uFlags BFLAG_ values for the operation.
@param ppBuffer On success, populated with the acquired buffer.
@return A negated ::REDSTATUS code indicating the operation result.
@retval 0 Operation was successful.
@retval -RED_EIO A disk I/O error occurred.
@retval -RED_EINVAL Invalid parameters.
@retval -RED_EBUSY All buffers are referenced.
*/
REDSTATUS RedBufferGet(
uint32_t ulBlock,
uint16_t uFlags,
void **ppBuffer)
{
REDSTATUS ret = 0;
uint8_t bIdx;
if((ulBlock >= gpRedVolume->ulBlockCount) || ((uFlags & BFLAG_MASK) != uFlags) || (ppBuffer == NULL))
{
REDERROR();
ret = -RED_EINVAL;
}
else
{
if(BufferFind(ulBlock, &bIdx))
{
/* Error if the buffer exists and BFLAG_NEW was specified, since
the new flag is used when a block is newly allocated/created, so
the block was previously free and and there should never be an
existing buffer for a free block.
Error if the buffer exists but does not have the same type as
was requested.
*/
if( ((uFlags & BFLAG_NEW) != 0U)
|| ((uFlags & BFLAG_META_MASK) != (gBufCtx.aHead[bIdx].uFlags & BFLAG_META_MASK)))
{
CRITICAL_ERROR();
ret = -RED_EFUBAR;
}
}
else if(gBufCtx.uNumUsed == REDCONF_BUFFER_COUNT)
{
/* The MINIMUM_BUFFER_COUNT is supposed to ensure that no operation
ever runs out of buffers, so this should never happen.
*/
CRITICAL_ERROR();
ret = -RED_EBUSY;
}
else
{
BUFFERHEAD *pHead;
/* Search for the least recently used buffer which is not
referenced.
*/
for(bIdx = (uint8_t)(REDCONF_BUFFER_COUNT - 1U); bIdx > 0U; bIdx--)
{
if(gBufCtx.aHead[gBufCtx.abMRU[bIdx]].bRefCount == 0U)
{
break;
}
}
bIdx = gBufCtx.abMRU[bIdx];
pHead = &gBufCtx.aHead[bIdx];
if(pHead->bRefCount == 0U)
{
/* If the LRU buffer is valid and dirty, write it out before
repurposing it.
*/
if(((pHead->uFlags & BFLAG_DIRTY) != 0U) && (pHead->ulBlock != BBLK_INVALID))
{
#if REDCONF_READ_ONLY == 1
CRITICAL_ERROR();
ret = -RED_EFUBAR;
#else
ret = BufferWrite(bIdx);
#endif
}
}
else
{
/* All the buffers are used, which should have been caught by
checking gBufCtx.uNumUsed.
*/
CRITICAL_ERROR();
ret = -RED_EBUSY;
}
if(ret == 0)
{
if((uFlags & BFLAG_NEW) == 0U)
{
/* Invalidate the LRU buffer. If the read fails, we do not
want the buffer head to continue to refer to the old
block number, since the read, even if it fails, may have
partially overwritten the buffer data (consider the case
where block size exceeds sector size, and some but not
all of the sectors are read successfully), and if the
buffer were to be used subsequently with its partially
erroneous contents, bad things could happen.
*/
pHead->ulBlock = BBLK_INVALID;
ret = RedIoRead(gbRedVolNum, ulBlock, 1U, gBufCtx.b.aabBuffer[bIdx]);
if((ret == 0) && ((uFlags & BFLAG_META) != 0U))
{
if(!BufferIsValid(gBufCtx.b.aabBuffer[bIdx], uFlags))
{
/* A corrupt metadata node is usually a critical
error. The master block is an exception since
it might be invalid because the volume is not
mounted; that condition is expected and should
not result in an assertion.
*/
CRITICAL_ASSERT((uFlags & BFLAG_META_MASTER) == BFLAG_META_MASTER);
ret = -RED_EIO;
}
}
#ifdef REDCONF_ENDIAN_SWAP
if(ret == 0)
{
BufferEndianSwap(gBufCtx.b.aabBuffer[bIdx], uFlags);
}
#endif
}
else
{
RedMemSet(gBufCtx.b.aabBuffer[bIdx], 0U, REDCONF_BLOCK_SIZE);
}
}
if(ret == 0)
{
pHead->bVolNum = gbRedVolNum;
pHead->ulBlock = ulBlock;
pHead->uFlags = 0U;
}
}
/* Reference the buffer, update its flags, and promote it to MRU. This
happens both when BufferFind() found an existing buffer for the
block and when the LRU buffer was repurposed to create a buffer for
the block.
*/
if(ret == 0)
{
BUFFERHEAD *pHead = &gBufCtx.aHead[bIdx];
pHead->bRefCount++;
if(pHead->bRefCount == 1U)
{
gBufCtx.uNumUsed++;
}
/* BFLAG_NEW tells this function to zero the buffer instead of
reading it from disk; it has no meaning later on, and thus is
not saved.
*/
pHead->uFlags |= (uFlags & (~BFLAG_NEW));
BufferMakeMRU(bIdx);
*ppBuffer = gBufCtx.b.aabBuffer[bIdx];
}
}
return ret;
}
/*
* Place tuples from 'itup' to 'buffer'. If 'oldoffnum' is valid, the tuple
* at that offset is atomically removed along with inserting the new tuples.
* This is used to replace a tuple with a new one.
*
* If 'leftchildbuf' is valid, we're inserting the downlink for the page
* to the right of 'leftchildbuf', or updating the downlink for 'leftchildbuf'.
* F_FOLLOW_RIGHT flag on 'leftchildbuf' is cleared and NSN is set.
*
* If 'markfollowright' is true and the page is split, the left child is
* marked with F_FOLLOW_RIGHT flag. That is the normal case. During buffered
* index build, however, there is no concurrent access and the page splitting
* is done in a slightly simpler fashion, and false is passed.
*
* If there is not enough room on the page, it is split. All the split
* pages are kept pinned and locked and returned in *splitinfo, the caller
* is responsible for inserting the downlinks for them. However, if
* 'buffer' is the root page and it needs to be split, gistplacetopage()
* performs the split as one atomic operation, and *splitinfo is set to NIL.
* In that case, we continue to hold the root page locked, and the child
* pages are released; note that new tuple(s) are *not* on the root page
* but in one of the new child pages.
*
* If 'newblkno' is not NULL, returns the block number of page the first
* new/updated tuple was inserted to. Usually it's the given page, but could
* be its right sibling if the page was split.
*
* Returns 'true' if the page was split, 'false' otherwise.
*/
bool
gistplacetopage(Relation rel, Size freespace, GISTSTATE *giststate,
Buffer buffer,
IndexTuple *itup, int ntup, OffsetNumber oldoffnum,
BlockNumber *newblkno,
Buffer leftchildbuf,
List **splitinfo,
bool markfollowright)
{
BlockNumber blkno = BufferGetBlockNumber(buffer);
Page page = BufferGetPage(buffer);
bool is_leaf = (GistPageIsLeaf(page)) ? true : false;
XLogRecPtr recptr;
int i;
bool is_split;
/*
* Refuse to modify a page that's incompletely split. This should not
* happen because we finish any incomplete splits while we walk down the
* tree. However, it's remotely possible that another concurrent inserter
* splits a parent page, and errors out before completing the split. We
* will just throw an error in that case, and leave any split we had in
* progress unfinished too. The next insert that comes along will clean up
* the mess.
*/
if (GistFollowRight(page))
elog(ERROR, "concurrent GiST page split was incomplete");
*splitinfo = NIL;
/*
* if isupdate, remove old key: This node's key has been modified, either
* because a child split occurred or because we needed to adjust our key
* for an insert in a child node. Therefore, remove the old version of
* this node's key.
*
* for WAL replay, in the non-split case we handle this by setting up a
* one-element todelete array; in the split case, it's handled implicitly
* because the tuple vector passed to gistSplit won't include this tuple.
*/
is_split = gistnospace(page, itup, ntup, oldoffnum, freespace);
if (is_split)
{
/* no space for insertion */
IndexTuple *itvec;
int tlen;
SplitedPageLayout *dist = NULL,
*ptr;
BlockNumber oldrlink = InvalidBlockNumber;
GistNSN oldnsn = 0;
SplitedPageLayout rootpg;
bool is_rootsplit;
int npage;
is_rootsplit = (blkno == GIST_ROOT_BLKNO);
/*
* Form index tuples vector to split. If we're replacing an old tuple,
* remove the old version from the vector.
*/
itvec = gistextractpage(page, &tlen);
if (OffsetNumberIsValid(oldoffnum))
{
/* on inner page we should remove old tuple */
int pos = oldoffnum - FirstOffsetNumber;
tlen--;
if (pos != tlen)
memmove(itvec + pos, itvec + pos + 1, sizeof(IndexTuple) * (tlen - pos));
}
itvec = gistjoinvector(itvec, &tlen, itup, ntup);
dist = gistSplit(rel, page, itvec, tlen, giststate);
/*
* Check that split didn't produce too many pages.
*/
npage = 0;
for (ptr = dist; ptr; ptr = ptr->next)
npage++;
/* in a root split, we'll add one more page to the list below */
if (is_rootsplit)
npage++;
if (npage > GIST_MAX_SPLIT_PAGES)
elog(ERROR, "GiST page split into too many halves (%d, maximum %d)",
npage, GIST_MAX_SPLIT_PAGES);
/*
* Set up pages to work with. Allocate new buffers for all but the
* leftmost page. The original page becomes the new leftmost page, and
* is just replaced with the new contents.
*
* For a root-split, allocate new buffers for all child pages, the
* original page is overwritten with new root page containing
* downlinks to the new child pages.
*/
ptr = dist;
if (!is_rootsplit)
{
/* save old rightlink and NSN */
oldrlink = GistPageGetOpaque(page)->rightlink;
oldnsn = GistPageGetNSN(page);
dist->buffer = buffer;
dist->block.blkno = BufferGetBlockNumber(buffer);
dist->page = PageGetTempPageCopySpecial(BufferGetPage(buffer));
/* clean all flags except F_LEAF */
GistPageGetOpaque(dist->page)->flags = (is_leaf) ? F_LEAF : 0;
ptr = ptr->next;
}
for (; ptr; ptr = ptr->next)
{
/* Allocate new page */
ptr->buffer = gistNewBuffer(rel);
GISTInitBuffer(ptr->buffer, (is_leaf) ? F_LEAF : 0);
ptr->page = BufferGetPage(ptr->buffer);
ptr->block.blkno = BufferGetBlockNumber(ptr->buffer);
}
/*
* Now that we know which blocks the new pages go to, set up downlink
* tuples to point to them.
*/
for (ptr = dist; ptr; ptr = ptr->next)
{
ItemPointerSetBlockNumber(&(ptr->itup->t_tid), ptr->block.blkno);
GistTupleSetValid(ptr->itup);
}
/*
* If this is a root split, we construct the new root page with the
* downlinks here directly, instead of requiring the caller to insert
* them. Add the new root page to the list along with the child pages.
*/
if (is_rootsplit)
{
IndexTuple *downlinks;
int ndownlinks = 0;
int i;
rootpg.buffer = buffer;
rootpg.page = PageGetTempPageCopySpecial(BufferGetPage(rootpg.buffer));
GistPageGetOpaque(rootpg.page)->flags = 0;
/* Prepare a vector of all the downlinks */
for (ptr = dist; ptr; ptr = ptr->next)
ndownlinks++;
downlinks = palloc(sizeof(IndexTuple) * ndownlinks);
for (i = 0, ptr = dist; ptr; ptr = ptr->next)
downlinks[i++] = ptr->itup;
rootpg.block.blkno = GIST_ROOT_BLKNO;
rootpg.block.num = ndownlinks;
rootpg.list = gistfillitupvec(downlinks, ndownlinks,
&(rootpg.lenlist));
rootpg.itup = NULL;
rootpg.next = dist;
dist = &rootpg;
}
else
{
/* Prepare split-info to be returned to caller */
for (ptr = dist; ptr; ptr = ptr->next)
{
GISTPageSplitInfo *si = palloc(sizeof(GISTPageSplitInfo));
si->buf = ptr->buffer;
si->downlink = ptr->itup;
*splitinfo = lappend(*splitinfo, si);
}
}
/*
* Fill all pages. All the pages are new, ie. freshly allocated empty
* pages, or a temporary copy of the old page.
*/
for (ptr = dist; ptr; ptr = ptr->next)
{
char *data = (char *) (ptr->list);
for (i = 0; i < ptr->block.num; i++)
{
IndexTuple thistup = (IndexTuple) data;
if (PageAddItem(ptr->page, (Item) data, IndexTupleSize(thistup), i + FirstOffsetNumber, false, false) == InvalidOffsetNumber)
elog(ERROR, "failed to add item to index page in \"%s\"", RelationGetRelationName(rel));
/*
* If this is the first inserted/updated tuple, let the caller
* know which page it landed on.
*/
if (newblkno && ItemPointerEquals(&thistup->t_tid, &(*itup)->t_tid))
*newblkno = ptr->block.blkno;
data += IndexTupleSize(thistup);
}
/* Set up rightlinks */
if (ptr->next && ptr->block.blkno != GIST_ROOT_BLKNO)
GistPageGetOpaque(ptr->page)->rightlink =
ptr->next->block.blkno;
else
GistPageGetOpaque(ptr->page)->rightlink = oldrlink;
/*
* Mark the all but the right-most page with the follow-right
* flag. It will be cleared as soon as the downlink is inserted
* into the parent, but this ensures that if we error out before
* that, the index is still consistent. (in buffering build mode,
* any error will abort the index build anyway, so this is not
* needed.)
*/
if (ptr->next && !is_rootsplit && markfollowright)
GistMarkFollowRight(ptr->page);
else
GistClearFollowRight(ptr->page);
/*
* Copy the NSN of the original page to all pages. The
* F_FOLLOW_RIGHT flags ensure that scans will follow the
* rightlinks until the downlinks are inserted.
*/
GistPageSetNSN(ptr->page, oldnsn);
}
START_CRIT_SECTION();
/*
* Must mark buffers dirty before XLogInsert, even though we'll still
* be changing their opaque fields below.
*/
for (ptr = dist; ptr; ptr = ptr->next)
MarkBufferDirty(ptr->buffer);
if (BufferIsValid(leftchildbuf))
MarkBufferDirty(leftchildbuf);
/*
* The first page in the chain was a temporary working copy meant to
* replace the old page. Copy it over the old page.
*/
PageRestoreTempPage(dist->page, BufferGetPage(dist->buffer));
dist->page = BufferGetPage(dist->buffer);
/* Write the WAL record */
if (RelationNeedsWAL(rel))
recptr = gistXLogSplit(rel->rd_node, blkno, is_leaf,
dist, oldrlink, oldnsn, leftchildbuf,
markfollowright);
else
recptr = gistGetFakeLSN(rel);
for (ptr = dist; ptr; ptr = ptr->next)
{
PageSetLSN(ptr->page, recptr);
}
/*
* Return the new child buffers to the caller.
*
* If this was a root split, we've already inserted the downlink
* pointers, in the form of a new root page. Therefore we can release
* all the new buffers, and keep just the root page locked.
*/
if (is_rootsplit)
{
for (ptr = dist->next; ptr; ptr = ptr->next)
UnlockReleaseBuffer(ptr->buffer);
}
}
else
{
/*
* Enough space. We also get here if ntuples==0.
*/
START_CRIT_SECTION();
if (OffsetNumberIsValid(oldoffnum))
PageIndexTupleDelete(page, oldoffnum);
gistfillbuffer(page, itup, ntup, InvalidOffsetNumber);
MarkBufferDirty(buffer);
if (BufferIsValid(leftchildbuf))
MarkBufferDirty(leftchildbuf);
if (RelationNeedsWAL(rel))
{
OffsetNumber ndeloffs = 0,
deloffs[1];
if (OffsetNumberIsValid(oldoffnum))
{
deloffs[0] = oldoffnum;
ndeloffs = 1;
}
recptr = gistXLogUpdate(rel->rd_node, buffer,
deloffs, ndeloffs, itup, ntup,
leftchildbuf);
PageSetLSN(page, recptr);
}
else
{
recptr = gistGetFakeLSN(rel);
PageSetLSN(page, recptr);
}
if (newblkno)
*newblkno = blkno;
}
/*
* If we inserted the downlink for a child page, set NSN and clear
* F_FOLLOW_RIGHT flag on the left child, so that concurrent scans know to
* follow the rightlink if and only if they looked at the parent page
* before we inserted the downlink.
*
* Note that we do this *after* writing the WAL record. That means that
* the possible full page image in the WAL record does not include these
* changes, and they must be replayed even if the page is restored from
* the full page image. There's a chicken-and-egg problem: if we updated
* the child pages first, we wouldn't know the recptr of the WAL record
* we're about to write.
*/
if (BufferIsValid(leftchildbuf))
{
Page leftpg = BufferGetPage(leftchildbuf);
GistPageSetNSN(leftpg, recptr);
GistClearFollowRight(leftpg);
PageSetLSN(leftpg, recptr);
}
END_CRIT_SECTION();
return is_split;
}
static bool
rtnext(IndexScanDesc s, ScanDirection dir)
{
Page p;
OffsetNumber n;
RTreePageOpaque po;
RTreeScanOpaque so;
so = (RTreeScanOpaque) s->opaque;
if (!ItemPointerIsValid(&(s->currentItemData)))
{
/* first call: start at the root */
Assert(BufferIsValid(so->curbuf) == false);
so->curbuf = ReadBuffer(s->indexRelation, P_ROOT);
pgstat_count_index_scan(&s->xs_pgstat_info);
}
p = BufferGetPage(so->curbuf);
po = (RTreePageOpaque) PageGetSpecialPointer(p);
if (!ItemPointerIsValid(&(s->currentItemData)))
{
/* first call: start at first/last offset */
if (ScanDirectionIsForward(dir))
n = FirstOffsetNumber;
else
n = PageGetMaxOffsetNumber(p);
}
else
{
/* go on to the next offset */
n = ItemPointerGetOffsetNumber(&(s->currentItemData));
if (ScanDirectionIsForward(dir))
n = OffsetNumberNext(n);
else
n = OffsetNumberPrev(n);
}
for (;;)
{
IndexTuple it;
RTSTACK *stk;
n = findnext(s, n, dir);
/* no match on this page, so read in the next stack entry */
if (n == InvalidOffsetNumber)
{
/* if out of stack entries, we're done */
if (so->s_stack == NULL)
{
ReleaseBuffer(so->curbuf);
so->curbuf = InvalidBuffer;
return false;
}
stk = so->s_stack;
so->curbuf = ReleaseAndReadBuffer(so->curbuf, s->indexRelation,
stk->rts_blk);
p = BufferGetPage(so->curbuf);
po = (RTreePageOpaque) PageGetSpecialPointer(p);
if (ScanDirectionIsBackward(dir))
n = OffsetNumberPrev(stk->rts_child);
else
n = OffsetNumberNext(stk->rts_child);
so->s_stack = stk->rts_parent;
pfree(stk);
continue;
}
if (po->flags & F_LEAF)
{
ItemPointerSet(&(s->currentItemData),
BufferGetBlockNumber(so->curbuf),
n);
it = (IndexTuple) PageGetItem(p, PageGetItemId(p, n));
s->xs_ctup.t_self = it->t_tid;
return true;
}
else
{
BlockNumber blk;
stk = (RTSTACK *) palloc(sizeof(RTSTACK));
stk->rts_child = n;
stk->rts_blk = BufferGetBlockNumber(so->curbuf);
stk->rts_parent = so->s_stack;
so->s_stack = stk;
it = (IndexTuple) PageGetItem(p, PageGetItemId(p, n));
blk = ItemPointerGetBlockNumber(&(it->t_tid));
/*
* Note that we release the pin on the page as we descend down the
* tree, even though there's a good chance we'll eventually need
* to re-read the buffer later in this scan. This may or may not
* be optimal, but it doesn't seem likely to make a huge
* performance difference either way.
*/
so->curbuf = ReleaseAndReadBuffer(so->curbuf, s->indexRelation, blk);
p = BufferGetPage(so->curbuf);
po = (RTreePageOpaque) PageGetSpecialPointer(p);
if (ScanDirectionIsBackward(dir))
n = PageGetMaxOffsetNumber(p);
else
n = FirstOffsetNumber;
}
}
}
/*
* visibilitymap_truncate - truncate the visibility map
*
* The caller must hold AccessExclusiveLock on the relation, to ensure that
* other backends receive the smgr invalidation event that this function sends
* before they access the VM again.
*
* nheapblocks is the new size of the heap.
*/
void
visibilitymap_truncate(Relation rel, BlockNumber nheapblocks)
{
BlockNumber newnblocks;
/* last remaining block, byte, and bit */
BlockNumber truncBlock = HEAPBLK_TO_MAPBLOCK(nheapblocks);
uint32 truncByte = HEAPBLK_TO_MAPBYTE(nheapblocks);
uint8 truncBit = HEAPBLK_TO_MAPBIT(nheapblocks);
#ifdef TRACE_VISIBILITYMAP
elog(DEBUG1, "vm_truncate %s %d", RelationGetRelationName(rel), nheapblocks);
#endif
RelationOpenSmgr(rel);
/*
* If no visibility map has been created yet for this relation, there's
* nothing to truncate.
*/
if (!smgrexists(rel->rd_smgr, VISIBILITYMAP_FORKNUM))
return;
/*
* Unless the new size is exactly at a visibility map page boundary, the
* tail bits in the last remaining map page, representing truncated heap
* blocks, need to be cleared. This is not only tidy, but also necessary
* because we don't get a chance to clear the bits if the heap is extended
* again.
*/
if (truncByte != 0 || truncBit != 0)
{
Buffer mapBuffer;
Page page;
char *map;
newnblocks = truncBlock + 1;
mapBuffer = vm_readbuf(rel, truncBlock, false);
if (!BufferIsValid(mapBuffer))
{
/* nothing to do, the file was already smaller */
return;
}
page = BufferGetPage(mapBuffer);
map = PageGetContents(page);
LockBuffer(mapBuffer, BUFFER_LOCK_EXCLUSIVE);
/* Clear out the unwanted bytes. */
MemSet(&map[truncByte + 1], 0, MAPSIZE - (truncByte + 1));
/*
* Mask out the unwanted bits of the last remaining byte.
*
* ((1 << 0) - 1) = 00000000 ((1 << 1) - 1) = 00000001 ... ((1 << 6) -
* 1) = 00111111 ((1 << 7) - 1) = 01111111
*/
map[truncByte] &= (1 << truncBit) - 1;
MarkBufferDirty(mapBuffer);
UnlockReleaseBuffer(mapBuffer);
}
else
newnblocks = truncBlock;
if (smgrnblocks(rel->rd_smgr, VISIBILITYMAP_FORKNUM) <= newnblocks)
{
/* nothing to do, the file was already smaller than requested size */
return;
}
/* Truncate the unused VM pages, and send smgr inval message */
smgrtruncate(rel->rd_smgr, VISIBILITYMAP_FORKNUM, newnblocks);
/*
* We might as well update the local smgr_vm_nblocks setting. smgrtruncate
* sent an smgr cache inval message, which will cause other backends to
* invalidate their copy of smgr_vm_nblocks, and this one too at the next
* command boundary. But this ensures it isn't outright wrong until then.
*/
if (rel->rd_smgr)
rel->rd_smgr->smgr_vm_nblocks = newnblocks;
}
/*
* _bt_endpoint() -- Find the first or last page in the index, and scan
* from there to the first key satisfying all the quals.
*
* This is used by _bt_first() to set up a scan when we've determined
* that the scan must start at the beginning or end of the index (for
* a forward or backward scan respectively). Exit conditions are the
* same as for _bt_first().
*/
static bool
_bt_endpoint(IndexScanDesc scan, ScanDirection dir)
{
Relation rel = scan->indexRelation;
BTScanOpaque so = (BTScanOpaque) scan->opaque;
Buffer buf;
Page page;
BTPageOpaque opaque;
OffsetNumber start;
BTScanPosItem *currItem;
/*
* Scan down to the leftmost or rightmost leaf page. This is a simplified
* version of _bt_search(). We don't maintain a stack since we know we
* won't need it.
*/
buf = _bt_get_endpoint(rel, 0, ScanDirectionIsBackward(dir));
if (!BufferIsValid(buf))
{
/*
* Empty index. Lock the whole relation, as nothing finer to lock
* exists.
*/
PredicateLockRelation(rel, scan->xs_snapshot);
so->currPos.buf = InvalidBuffer;
return false;
}
PredicateLockPage(rel, BufferGetBlockNumber(buf), scan->xs_snapshot);
page = BufferGetPage(buf);
opaque = (BTPageOpaque) PageGetSpecialPointer(page);
Assert(P_ISLEAF(opaque));
if (ScanDirectionIsForward(dir))
{
/* There could be dead pages to the left, so not this: */
/* Assert(P_LEFTMOST(opaque)); */
start = P_FIRSTDATAKEY(opaque);
}
else if (ScanDirectionIsBackward(dir))
{
Assert(P_RIGHTMOST(opaque));
start = PageGetMaxOffsetNumber(page);
}
else
{
elog(ERROR, "invalid scan direction: %d", (int) dir);
start = 0; /* keep compiler quiet */
}
/* remember which buffer we have pinned */
so->currPos.buf = buf;
/* initialize moreLeft/moreRight appropriately for scan direction */
if (ScanDirectionIsForward(dir))
{
so->currPos.moreLeft = false;
so->currPos.moreRight = true;
}
else
{
so->currPos.moreLeft = true;
so->currPos.moreRight = false;
}
so->numKilled = 0; /* just paranoia */
so->markItemIndex = -1; /* ditto */
/*
* Now load data from the first page of the scan.
*/
if (!_bt_readpage(scan, dir, start))
{
/*
* There's no actually-matching data on this page. Try to advance to
* the next page. Return false if there's no matching data at all.
*/
if (!_bt_steppage(scan, dir))
return false;
}
/* Drop the lock, but not pin, on the current page */
LockBuffer(so->currPos.buf, BUFFER_LOCK_UNLOCK);
/* OK, itemIndex says what to return */
currItem = &so->currPos.items[so->currPos.itemIndex];
scan->xs_ctup.t_self = currItem->heapTid;
if (scan->xs_want_itup)
scan->xs_itup = (IndexTuple) (so->currTuples + currItem->tupleOffset);
return true;
}
/*
* hashgettuple() -- Get the next tuple in the scan.
*/
Datum
hashgettuple(PG_FUNCTION_ARGS)
{
IndexScanDesc scan = (IndexScanDesc) PG_GETARG_POINTER(0);
ScanDirection dir = (ScanDirection) PG_GETARG_INT32(1);
HashScanOpaque so = (HashScanOpaque) scan->opaque;
Relation rel = scan->indexRelation;
Page page;
OffsetNumber offnum;
bool res;
/*
* We hold pin but not lock on current buffer while outside the hash AM.
* Reacquire the read lock here.
*/
if (BufferIsValid(so->hashso_curbuf))
_hash_chgbufaccess(rel, so->hashso_curbuf, HASH_NOLOCK, HASH_READ);
/*
* If we've already initialized this scan, we can just advance it in the
* appropriate direction. If we haven't done so yet, we call a routine to
* get the first item in the scan.
*/
if (ItemPointerIsValid(&(scan->currentItemData)))
{
/*
* Check to see if we should kill the previously-fetched tuple.
*/
if (scan->kill_prior_tuple)
{
/*
* Yes, so mark it by setting the LP_DELETE bit in the item flags.
*/
offnum = ItemPointerGetOffsetNumber(&(scan->currentItemData));
page = BufferGetPage(so->hashso_curbuf);
PageGetItemId(page, offnum)->lp_flags |= LP_DELETE;
/*
* Since this can be redone later if needed, it's treated the same
* as a commit-hint-bit status update for heap tuples: we mark the
* buffer dirty but don't make a WAL log entry.
*/
SetBufferCommitInfoNeedsSave(so->hashso_curbuf);
}
/*
* Now continue the scan.
*/
res = _hash_next(scan, dir);
}
else
res = _hash_first(scan, dir);
/*
* Skip killed tuples if asked to.
*/
if (scan->ignore_killed_tuples)
{
while (res)
{
offnum = ItemPointerGetOffsetNumber(&(scan->currentItemData));
page = BufferGetPage(so->hashso_curbuf);
if (!ItemIdDeleted(PageGetItemId(page, offnum)))
break;
res = _hash_next(scan, dir);
}
}
/* Release read lock on current buffer, but keep it pinned */
if (BufferIsValid(so->hashso_curbuf))
_hash_chgbufaccess(rel, so->hashso_curbuf, HASH_READ, HASH_NOLOCK);
PG_RETURN_BOOL(res);
}
/*
* _bt_first() -- Find the first item in a scan.
*
* We need to be clever about the direction of scan, the search
* conditions, and the tree ordering. We find the first item (or,
* if backwards scan, the last item) in the tree that satisfies the
* qualifications in the scan key. On success exit, the page containing
* the current index tuple is pinned but not locked, and data about
* the matching tuple(s) on the page has been loaded into so->currPos.
* scan->xs_ctup.t_self is set to the heap TID of the current tuple,
* and if requested, scan->xs_itup points to a copy of the index tuple.
*
* If there are no matching items in the index, we return FALSE, with no
* pins or locks held.
*
* Note that scan->keyData[], and the so->keyData[] scankey built from it,
* are both search-type scankeys (see nbtree/README for more about this).
* Within this routine, we build a temporary insertion-type scankey to use
* in locating the scan start position.
*/
bool
_bt_first(IndexScanDesc scan, ScanDirection dir)
{
Relation rel = scan->indexRelation;
BTScanOpaque so = (BTScanOpaque) scan->opaque;
Buffer buf;
BTStack stack;
OffsetNumber offnum;
StrategyNumber strat;
bool nextkey;
bool goback;
ScanKey startKeys[INDEX_MAX_KEYS];
ScanKeyData scankeys[INDEX_MAX_KEYS];
ScanKeyData notnullkeys[INDEX_MAX_KEYS];
int keysCount = 0;
int i;
StrategyNumber strat_total;
BTScanPosItem *currItem;
pgstat_count_index_scan(rel);
/*
* Examine the scan keys and eliminate any redundant keys; also mark the
* keys that must be matched to continue the scan.
*/
_bt_preprocess_keys(scan);
/*
* Quit now if _bt_preprocess_keys() discovered that the scan keys can
* never be satisfied (eg, x == 1 AND x > 2).
*/
if (!so->qual_ok)
return false;
/*----------
* Examine the scan keys to discover where we need to start the scan.
*
* We want to identify the keys that can be used as starting boundaries;
* these are =, >, or >= keys for a forward scan or =, <, <= keys for
* a backwards scan. We can use keys for multiple attributes so long as
* the prior attributes had only =, >= (resp. =, <=) keys. Once we accept
* a > or < boundary or find an attribute with no boundary (which can be
* thought of as the same as "> -infinity"), we can't use keys for any
* attributes to its right, because it would break our simplistic notion
* of what initial positioning strategy to use.
*
* When the scan keys include cross-type operators, _bt_preprocess_keys
* may not be able to eliminate redundant keys; in such cases we will
* arbitrarily pick a usable one for each attribute. This is correct
* but possibly not optimal behavior. (For example, with keys like
* "x >= 4 AND x >= 5" we would elect to scan starting at x=4 when
* x=5 would be more efficient.) Since the situation only arises given
* a poorly-worded query plus an incomplete opfamily, live with it.
*
* When both equality and inequality keys appear for a single attribute
* (again, only possible when cross-type operators appear), we *must*
* select one of the equality keys for the starting point, because
* _bt_checkkeys() will stop the scan as soon as an equality qual fails.
* For example, if we have keys like "x >= 4 AND x = 10" and we elect to
* start at x=4, we will fail and stop before reaching x=10. If multiple
* equality quals survive preprocessing, however, it doesn't matter which
* one we use --- by definition, they are either redundant or
* contradictory.
*
* Any regular (not SK_SEARCHNULL) key implies a NOT NULL qualifier.
* If the index stores nulls at the end of the index we'll be starting
* from, and we have no boundary key for the column (which means the key
* we deduced NOT NULL from is an inequality key that constrains the other
* end of the index), then we cons up an explicit SK_SEARCHNOTNULL key to
* use as a boundary key. If we didn't do this, we might find ourselves
* traversing a lot of null entries at the start of the scan.
*
* In this loop, row-comparison keys are treated the same as keys on their
* first (leftmost) columns. We'll add on lower-order columns of the row
* comparison below, if possible.
*
* The selected scan keys (at most one per index column) are remembered by
* storing their addresses into the local startKeys[] array.
*----------
*/
strat_total = BTEqualStrategyNumber;
if (so->numberOfKeys > 0)
{
AttrNumber curattr;
ScanKey chosen;
ScanKey impliesNN;
ScanKey cur;
/*
* chosen is the so-far-chosen key for the current attribute, if any.
* We don't cast the decision in stone until we reach keys for the
* next attribute.
*/
curattr = 1;
chosen = NULL;
/* Also remember any scankey that implies a NOT NULL constraint */
impliesNN = NULL;
/*
* Loop iterates from 0 to numberOfKeys inclusive; we use the last
* pass to handle after-last-key processing. Actual exit from the
* loop is at one of the "break" statements below.
*/
for (cur = so->keyData, i = 0;; cur++, i++)
{
if (i >= so->numberOfKeys || cur->sk_attno != curattr)
{
/*
* Done looking at keys for curattr. If we didn't find a
* usable boundary key, see if we can deduce a NOT NULL key.
*/
if (chosen == NULL && impliesNN != NULL &&
((impliesNN->sk_flags & SK_BT_NULLS_FIRST) ?
ScanDirectionIsForward(dir) :
ScanDirectionIsBackward(dir)))
{
/* Yes, so build the key in notnullkeys[keysCount] */
chosen = ¬nullkeys[keysCount];
ScanKeyEntryInitialize(chosen,
(SK_SEARCHNOTNULL | SK_ISNULL |
(impliesNN->sk_flags &
(SK_BT_DESC | SK_BT_NULLS_FIRST))),
curattr,
((impliesNN->sk_flags & SK_BT_NULLS_FIRST) ?
BTGreaterStrategyNumber :
BTLessStrategyNumber),
InvalidOid,
InvalidOid,
InvalidOid,
(Datum) 0);
}
/*
* If we still didn't find a usable boundary key, quit; else
* save the boundary key pointer in startKeys.
*/
if (chosen == NULL)
break;
startKeys[keysCount++] = chosen;
/*
* Adjust strat_total, and quit if we have stored a > or <
* key.
*/
strat = chosen->sk_strategy;
if (strat != BTEqualStrategyNumber)
{
strat_total = strat;
if (strat == BTGreaterStrategyNumber ||
strat == BTLessStrategyNumber)
break;
}
/*
* Done if that was the last attribute, or if next key is not
* in sequence (implying no boundary key is available for the
* next attribute).
*/
if (i >= so->numberOfKeys ||
cur->sk_attno != curattr + 1)
break;
/*
* Reset for next attr.
*/
curattr = cur->sk_attno;
chosen = NULL;
impliesNN = NULL;
}
/*
* Can we use this key as a starting boundary for this attr?
*
* If not, does it imply a NOT NULL constraint? (Because
* SK_SEARCHNULL keys are always assigned BTEqualStrategyNumber,
* *any* inequality key works for that; we need not test.)
*/
switch (cur->sk_strategy)
{
case BTLessStrategyNumber:
case BTLessEqualStrategyNumber:
if (chosen == NULL)
{
if (ScanDirectionIsBackward(dir))
chosen = cur;
else
impliesNN = cur;
}
break;
case BTEqualStrategyNumber:
/* override any non-equality choice */
chosen = cur;
break;
case BTGreaterEqualStrategyNumber:
case BTGreaterStrategyNumber:
if (chosen == NULL)
{
if (ScanDirectionIsForward(dir))
chosen = cur;
else
impliesNN = cur;
}
break;
}
}
}
/*
* If we found no usable boundary keys, we have to start from one end of
* the tree. Walk down that edge to the first or last key, and scan from
* there.
*/
if (keysCount == 0)
return _bt_endpoint(scan, dir);
/*
* We want to start the scan somewhere within the index. Set up an
* insertion scankey we can use to search for the boundary point we
* identified above. The insertion scankey is built in the local
* scankeys[] array, using the keys identified by startKeys[].
*/
Assert(keysCount <= INDEX_MAX_KEYS);
for (i = 0; i < keysCount; i++)
{
ScanKey cur = startKeys[i];
Assert(cur->sk_attno == i + 1);
if (cur->sk_flags & SK_ROW_HEADER)
{
/*
* Row comparison header: look to the first row member instead.
*
* The member scankeys are already in insertion format (ie, they
* have sk_func = 3-way-comparison function), but we have to watch
* out for nulls, which _bt_preprocess_keys didn't check. A null
* in the first row member makes the condition unmatchable, just
* like qual_ok = false.
*/
ScanKey subkey = (ScanKey) DatumGetPointer(cur->sk_argument);
Assert(subkey->sk_flags & SK_ROW_MEMBER);
if (subkey->sk_flags & SK_ISNULL)
return false;
memcpy(scankeys + i, subkey, sizeof(ScanKeyData));
/*
* If the row comparison is the last positioning key we accepted,
* try to add additional keys from the lower-order row members.
* (If we accepted independent conditions on additional index
* columns, we use those instead --- doesn't seem worth trying to
* determine which is more restrictive.) Note that this is OK
* even if the row comparison is of ">" or "<" type, because the
* condition applied to all but the last row member is effectively
* ">=" or "<=", and so the extra keys don't break the positioning
* scheme. But, by the same token, if we aren't able to use all
* the row members, then the part of the row comparison that we
* did use has to be treated as just a ">=" or "<=" condition, and
* so we'd better adjust strat_total accordingly.
*/
if (i == keysCount - 1)
{
bool used_all_subkeys = false;
Assert(!(subkey->sk_flags & SK_ROW_END));
for (;;)
{
subkey++;
Assert(subkey->sk_flags & SK_ROW_MEMBER);
if (subkey->sk_attno != keysCount + 1)
break; /* out-of-sequence, can't use it */
if (subkey->sk_strategy != cur->sk_strategy)
break; /* wrong direction, can't use it */
if (subkey->sk_flags & SK_ISNULL)
break; /* can't use null keys */
Assert(keysCount < INDEX_MAX_KEYS);
memcpy(scankeys + keysCount, subkey, sizeof(ScanKeyData));
keysCount++;
if (subkey->sk_flags & SK_ROW_END)
{
used_all_subkeys = true;
break;
}
}
if (!used_all_subkeys)
{
switch (strat_total)
{
case BTLessStrategyNumber:
strat_total = BTLessEqualStrategyNumber;
break;
case BTGreaterStrategyNumber:
strat_total = BTGreaterEqualStrategyNumber;
break;
}
}
break; /* done with outer loop */
}
}
else
{
/*
* Ordinary comparison key. Transform the search-style scan key
* to an insertion scan key by replacing the sk_func with the
* appropriate btree comparison function.
*
* If scankey operator is not a cross-type comparison, we can use
* the cached comparison function; otherwise gotta look it up in
* the catalogs. (That can't lead to infinite recursion, since no
* indexscan initiated by syscache lookup will use cross-data-type
* operators.)
*
* We support the convention that sk_subtype == InvalidOid means
* the opclass input type; this is a hack to simplify life for
* ScanKeyInit().
*/
if (cur->sk_subtype == rel->rd_opcintype[i] ||
cur->sk_subtype == InvalidOid)
{
FmgrInfo *procinfo;
procinfo = index_getprocinfo(rel, cur->sk_attno, BTORDER_PROC);
ScanKeyEntryInitializeWithInfo(scankeys + i,
cur->sk_flags,
cur->sk_attno,
InvalidStrategy,
cur->sk_subtype,
cur->sk_collation,
procinfo,
cur->sk_argument);
}
else
{
RegProcedure cmp_proc;
cmp_proc = get_opfamily_proc(rel->rd_opfamily[i],
rel->rd_opcintype[i],
cur->sk_subtype,
BTORDER_PROC);
if (!RegProcedureIsValid(cmp_proc))
elog(ERROR, "missing support function %d(%u,%u) for attribute %d of index \"%s\"",
BTORDER_PROC, rel->rd_opcintype[i], cur->sk_subtype,
cur->sk_attno, RelationGetRelationName(rel));
ScanKeyEntryInitialize(scankeys + i,
cur->sk_flags,
cur->sk_attno,
InvalidStrategy,
cur->sk_subtype,
cur->sk_collation,
cmp_proc,
cur->sk_argument);
}
}
}
/*----------
* Examine the selected initial-positioning strategy to determine exactly
* where we need to start the scan, and set flag variables to control the
* code below.
*
* If nextkey = false, _bt_search and _bt_binsrch will locate the first
* item >= scan key. If nextkey = true, they will locate the first
* item > scan key.
*
* If goback = true, we will then step back one item, while if
* goback = false, we will start the scan on the located item.
*----------
*/
switch (strat_total)
{
case BTLessStrategyNumber:
/*
* Find first item >= scankey, then back up one to arrive at last
* item < scankey. (Note: this positioning strategy is only used
* for a backward scan, so that is always the correct starting
* position.)
*/
nextkey = false;
goback = true;
break;
case BTLessEqualStrategyNumber:
/*
* Find first item > scankey, then back up one to arrive at last
* item <= scankey. (Note: this positioning strategy is only used
* for a backward scan, so that is always the correct starting
* position.)
*/
nextkey = true;
goback = true;
break;
case BTEqualStrategyNumber:
/*
* If a backward scan was specified, need to start with last equal
* item not first one.
*/
if (ScanDirectionIsBackward(dir))
{
/*
* This is the same as the <= strategy. We will check at the
* end whether the found item is actually =.
*/
nextkey = true;
goback = true;
}
else
{
/*
* This is the same as the >= strategy. We will check at the
* end whether the found item is actually =.
*/
nextkey = false;
goback = false;
}
break;
case BTGreaterEqualStrategyNumber:
/*
* Find first item >= scankey. (This is only used for forward
* scans.)
*/
nextkey = false;
goback = false;
break;
case BTGreaterStrategyNumber:
/*
* Find first item > scankey. (This is only used for forward
* scans.)
*/
nextkey = true;
goback = false;
break;
default:
/* can't get here, but keep compiler quiet */
elog(ERROR, "unrecognized strat_total: %d", (int) strat_total);
return false;
}
/*
* Use the manufactured insertion scan key to descend the tree and
* position ourselves on the target leaf page.
*/
stack = _bt_search(rel, keysCount, scankeys, nextkey, &buf, BT_READ);
/* don't need to keep the stack around... */
_bt_freestack(stack);
/* remember which buffer we have pinned, if any */
so->currPos.buf = buf;
if (!BufferIsValid(buf))
{
/*
* We only get here if the index is completely empty. Lock relation
* because nothing finer to lock exists.
*/
PredicateLockRelation(rel, scan->xs_snapshot);
return false;
}
else
PredicateLockPage(rel, BufferGetBlockNumber(buf),
scan->xs_snapshot);
/* initialize moreLeft/moreRight appropriately for scan direction */
if (ScanDirectionIsForward(dir))
{
so->currPos.moreLeft = false;
so->currPos.moreRight = true;
}
else
{
so->currPos.moreLeft = true;
so->currPos.moreRight = false;
}
so->numKilled = 0; /* just paranoia */
so->markItemIndex = -1; /* ditto */
/* position to the precise item on the page */
offnum = _bt_binsrch(rel, buf, keysCount, scankeys, nextkey);
/*
* If nextkey = false, we are positioned at the first item >= scan key, or
* possibly at the end of a page on which all the existing items are less
* than the scan key and we know that everything on later pages is greater
* than or equal to scan key.
*
* If nextkey = true, we are positioned at the first item > scan key, or
* possibly at the end of a page on which all the existing items are less
* than or equal to the scan key and we know that everything on later
* pages is greater than scan key.
*
* The actually desired starting point is either this item or the prior
* one, or in the end-of-page case it's the first item on the next page or
* the last item on this page. Adjust the starting offset if needed. (If
* this results in an offset before the first item or after the last one,
* _bt_readpage will report no items found, and then we'll step to the
* next page as needed.)
*/
if (goback)
offnum = OffsetNumberPrev(offnum);
/*
* Now load data from the first page of the scan.
*/
if (!_bt_readpage(scan, dir, offnum))
{
/*
* There's no actually-matching data on this page. Try to advance to
* the next page. Return false if there's no matching data at all.
*/
if (!_bt_steppage(scan, dir))
return false;
}
/* Drop the lock, but not pin, on the current page */
LockBuffer(so->currPos.buf, BUFFER_LOCK_UNLOCK);
/* OK, itemIndex says what to return */
currItem = &so->currPos.items[so->currPos.itemIndex];
scan->xs_ctup.t_self = currItem->heapTid;
if (scan->xs_want_itup)
scan->xs_itup = (IndexTuple) (so->currTuples + currItem->tupleOffset);
return true;
}
/*
* hashgetmulti() -- get multiple tuples at once
*
* This is a somewhat generic implementation: it avoids lock reacquisition
* overhead, but there's no smarts about picking especially good stopping
* points such as index page boundaries.
*/
Datum
hashgetmulti(PG_FUNCTION_ARGS)
{
IndexScanDesc scan = (IndexScanDesc) PG_GETARG_POINTER(0);
ItemPointer tids = (ItemPointer) PG_GETARG_POINTER(1);
int32 max_tids = PG_GETARG_INT32(2);
int32 *returned_tids = (int32 *) PG_GETARG_POINTER(3);
HashScanOpaque so = (HashScanOpaque) scan->opaque;
Relation rel = scan->indexRelation;
bool res = true;
int32 ntids = 0;
/*
* We hold pin but not lock on current buffer while outside the hash AM.
* Reacquire the read lock here.
*/
if (BufferIsValid(so->hashso_curbuf))
_hash_chgbufaccess(rel, so->hashso_curbuf, HASH_NOLOCK, HASH_READ);
while (ntids < max_tids)
{
/*
* Start scan, or advance to next tuple.
*/
if (ItemPointerIsValid(&(scan->currentItemData)))
res = _hash_next(scan, ForwardScanDirection);
else
res = _hash_first(scan, ForwardScanDirection);
/*
* Skip killed tuples if asked to.
*/
if (scan->ignore_killed_tuples)
{
while (res)
{
Page page;
OffsetNumber offnum;
offnum = ItemPointerGetOffsetNumber(&(scan->currentItemData));
page = BufferGetPage(so->hashso_curbuf);
if (!ItemIdDeleted(PageGetItemId(page, offnum)))
break;
res = _hash_next(scan, ForwardScanDirection);
}
}
if (!res)
break;
/* Save tuple ID, and continue scanning */
tids[ntids] = scan->xs_ctup.t_self;
ntids++;
}
/* Release read lock on current buffer, but keep it pinned */
if (BufferIsValid(so->hashso_curbuf))
_hash_chgbufaccess(rel, so->hashso_curbuf, HASH_READ, HASH_NOLOCK);
*returned_tids = ntids;
PG_RETURN_BOOL(res);
}
static void
gistRedoPageSplitRecord(XLogRecPtr lsn, XLogRecord *record)
{
gistxlogPageSplit *xldata = (gistxlogPageSplit *) XLogRecGetData(record);
PageSplitRecord xlrec;
Buffer firstbuffer = InvalidBuffer;
Buffer buffer;
Page page;
int i;
bool isrootsplit = false;
decodePageSplitRecord(&xlrec, record);
/*
* We must hold lock on the first-listed page throughout the action,
* including while updating the left child page (if any). We can unlock
* remaining pages in the list as soon as they've been written, because
* there is no path for concurrent queries to reach those pages without
* first visiting the first-listed page.
*/
/* loop around all pages */
for (i = 0; i < xlrec.data->npage; i++)
{
NewPage *newpage = xlrec.page + i;
int flags;
if (newpage->header->blkno == GIST_ROOT_BLKNO)
{
Assert(i == 0);
isrootsplit = true;
}
buffer = XLogReadBuffer(xlrec.data->node, newpage->header->blkno, true);
Assert(BufferIsValid(buffer));
page = (Page) BufferGetPage(buffer);
/* ok, clear buffer */
if (xlrec.data->origleaf && newpage->header->blkno != GIST_ROOT_BLKNO)
flags = F_LEAF;
else
flags = 0;
GISTInitBuffer(buffer, flags);
/* and fill it */
gistfillbuffer(page, newpage->itup, newpage->header->num, FirstOffsetNumber);
if (newpage->header->blkno == GIST_ROOT_BLKNO)
{
GistPageGetOpaque(page)->rightlink = InvalidBlockNumber;
GistPageSetNSN(page, xldata->orignsn);
GistClearFollowRight(page);
}
else
{
if (i < xlrec.data->npage - 1)
GistPageGetOpaque(page)->rightlink = xlrec.page[i + 1].header->blkno;
else
GistPageGetOpaque(page)->rightlink = xldata->origrlink;
GistPageSetNSN(page, xldata->orignsn);
if (i < xlrec.data->npage - 1 && !isrootsplit &&
xldata->markfollowright)
GistMarkFollowRight(page);
else
GistClearFollowRight(page);
}
PageSetLSN(page, lsn);
MarkBufferDirty(buffer);
if (i == 0)
firstbuffer = buffer;
else
UnlockReleaseBuffer(buffer);
}
/* Fix follow-right data on left child page, if any */
if (BlockNumberIsValid(xldata->leftchild))
gistRedoClearFollowRight(lsn, record, 0,
xldata->node, xldata->leftchild);
/* Finally, release lock on the first page */
UnlockReleaseBuffer(firstbuffer);
}
/*
* _hash_addovflpage
*
* Add an overflow page to the bucket whose last page is pointed to by 'buf'.
*
* On entry, the caller must hold a pin but no lock on 'buf'. The pin is
* dropped before exiting (we assume the caller is not interested in 'buf'
* anymore) if not asked to retain. The pin will be retained only for the
* primary bucket. The returned overflow page will be pinned and
* write-locked; it is guaranteed to be empty.
*
* The caller must hold a pin, but no lock, on the metapage buffer.
* That buffer is returned in the same state.
*
* NB: since this could be executed concurrently by multiple processes,
* one should not assume that the returned overflow page will be the
* immediate successor of the originally passed 'buf'. Additional overflow
* pages might have been added to the bucket chain in between.
*/
Buffer
_hash_addovflpage(Relation rel, Buffer metabuf, Buffer buf, bool retain_pin)
{
Buffer ovflbuf;
Page page;
Page ovflpage;
HashPageOpaque pageopaque;
HashPageOpaque ovflopaque;
HashMetaPage metap;
Buffer mapbuf = InvalidBuffer;
Buffer newmapbuf = InvalidBuffer;
BlockNumber blkno;
uint32 orig_firstfree;
uint32 splitnum;
uint32 *freep = NULL;
uint32 max_ovflpg;
uint32 bit;
uint32 bitmap_page_bit;
uint32 first_page;
uint32 last_bit;
uint32 last_page;
uint32 i,
j;
bool page_found = false;
/*
* Write-lock the tail page. Here, we need to maintain locking order such
* that, first acquire the lock on tail page of bucket, then on meta page
* to find and lock the bitmap page and if it is found, then lock on meta
* page is released, then finally acquire the lock on new overflow buffer.
* We need this locking order to avoid deadlock with backends that are
* doing inserts.
*
* Note: We could have avoided locking many buffers here if we made two
* WAL records for acquiring an overflow page (one to allocate an overflow
* page and another to add it to overflow bucket chain). However, doing
* so can leak an overflow page, if the system crashes after allocation.
* Needless to say, it is better to have a single record from a
* performance point of view as well.
*/
LockBuffer(buf, BUFFER_LOCK_EXCLUSIVE);
/* probably redundant... */
_hash_checkpage(rel, buf, LH_BUCKET_PAGE | LH_OVERFLOW_PAGE);
/* loop to find current tail page, in case someone else inserted too */
for (;;)
{
BlockNumber nextblkno;
page = BufferGetPage(buf);
pageopaque = (HashPageOpaque) PageGetSpecialPointer(page);
nextblkno = pageopaque->hasho_nextblkno;
if (!BlockNumberIsValid(nextblkno))
break;
/* we assume we do not need to write the unmodified page */
if (retain_pin)
{
/* pin will be retained only for the primary bucket page */
Assert((pageopaque->hasho_flag & LH_PAGE_TYPE) == LH_BUCKET_PAGE);
LockBuffer(buf, BUFFER_LOCK_UNLOCK);
}
else
_hash_relbuf(rel, buf);
retain_pin = false;
buf = _hash_getbuf(rel, nextblkno, HASH_WRITE, LH_OVERFLOW_PAGE);
}
/* Get exclusive lock on the meta page */
LockBuffer(metabuf, BUFFER_LOCK_EXCLUSIVE);
_hash_checkpage(rel, metabuf, LH_META_PAGE);
metap = HashPageGetMeta(BufferGetPage(metabuf));
/* start search at hashm_firstfree */
orig_firstfree = metap->hashm_firstfree;
first_page = orig_firstfree >> BMPG_SHIFT(metap);
bit = orig_firstfree & BMPG_MASK(metap);
i = first_page;
j = bit / BITS_PER_MAP;
bit &= ~(BITS_PER_MAP - 1);
/* outer loop iterates once per bitmap page */
for (;;)
{
BlockNumber mapblkno;
Page mappage;
uint32 last_inpage;
/* want to end search with the last existing overflow page */
splitnum = metap->hashm_ovflpoint;
max_ovflpg = metap->hashm_spares[splitnum] - 1;
last_page = max_ovflpg >> BMPG_SHIFT(metap);
last_bit = max_ovflpg & BMPG_MASK(metap);
if (i > last_page)
break;
Assert(i < metap->hashm_nmaps);
mapblkno = metap->hashm_mapp[i];
if (i == last_page)
last_inpage = last_bit;
else
last_inpage = BMPGSZ_BIT(metap) - 1;
/* Release exclusive lock on metapage while reading bitmap page */
LockBuffer(metabuf, BUFFER_LOCK_UNLOCK);
mapbuf = _hash_getbuf(rel, mapblkno, HASH_WRITE, LH_BITMAP_PAGE);
mappage = BufferGetPage(mapbuf);
freep = HashPageGetBitmap(mappage);
for (; bit <= last_inpage; j++, bit += BITS_PER_MAP)
{
if (freep[j] != ALL_SET)
{
page_found = true;
/* Reacquire exclusive lock on the meta page */
LockBuffer(metabuf, BUFFER_LOCK_EXCLUSIVE);
/* convert bit to bit number within page */
bit += _hash_firstfreebit(freep[j]);
bitmap_page_bit = bit;
/* convert bit to absolute bit number */
bit += (i << BMPG_SHIFT(metap));
/* Calculate address of the recycled overflow page */
blkno = bitno_to_blkno(metap, bit);
/* Fetch and init the recycled page */
ovflbuf = _hash_getinitbuf(rel, blkno);
goto found;
}
}
/* No free space here, try to advance to next map page */
_hash_relbuf(rel, mapbuf);
mapbuf = InvalidBuffer;
i++;
j = 0; /* scan from start of next map page */
bit = 0;
/* Reacquire exclusive lock on the meta page */
LockBuffer(metabuf, BUFFER_LOCK_EXCLUSIVE);
}
/*
* No free pages --- have to extend the relation to add an overflow page.
* First, check to see if we have to add a new bitmap page too.
*/
if (last_bit == (uint32) (BMPGSZ_BIT(metap) - 1))
{
/*
* We create the new bitmap page with all pages marked "in use".
* Actually two pages in the new bitmap's range will exist
* immediately: the bitmap page itself, and the following page which
* is the one we return to the caller. Both of these are correctly
* marked "in use". Subsequent pages do not exist yet, but it is
* convenient to pre-mark them as "in use" too.
*/
bit = metap->hashm_spares[splitnum];
/* metapage already has a write lock */
if (metap->hashm_nmaps >= HASH_MAX_BITMAPS)
ereport(ERROR,
(errcode(ERRCODE_PROGRAM_LIMIT_EXCEEDED),
errmsg("out of overflow pages in hash index \"%s\"",
RelationGetRelationName(rel))));
newmapbuf = _hash_getnewbuf(rel, bitno_to_blkno(metap, bit), MAIN_FORKNUM);
}
else
{
/*
* Nothing to do here; since the page will be past the last used page,
* we know its bitmap bit was preinitialized to "in use".
*/
}
/* Calculate address of the new overflow page */
bit = BufferIsValid(newmapbuf) ?
metap->hashm_spares[splitnum] + 1 : metap->hashm_spares[splitnum];
blkno = bitno_to_blkno(metap, bit);
/*
* Fetch the page with _hash_getnewbuf to ensure smgr's idea of the
* relation length stays in sync with ours. XXX It's annoying to do this
* with metapage write lock held; would be better to use a lock that
* doesn't block incoming searches.
*
* It is okay to hold two buffer locks here (one on tail page of bucket
* and other on new overflow page) since there cannot be anyone else
* contending for access to ovflbuf.
*/
ovflbuf = _hash_getnewbuf(rel, blkno, MAIN_FORKNUM);
found:
/*
* Do the update. No ereport(ERROR) until changes are logged. We want to
* log the changes for bitmap page and overflow page together to avoid
* loss of pages in case the new page is added.
*/
START_CRIT_SECTION();
if (page_found)
{
Assert(BufferIsValid(mapbuf));
/* mark page "in use" in the bitmap */
SETBIT(freep, bitmap_page_bit);
MarkBufferDirty(mapbuf);
}
else
{
/* update the count to indicate new overflow page is added */
metap->hashm_spares[splitnum]++;
if (BufferIsValid(newmapbuf))
{
_hash_initbitmapbuffer(newmapbuf, metap->hashm_bmsize, false);
MarkBufferDirty(newmapbuf);
/* add the new bitmap page to the metapage's list of bitmaps */
metap->hashm_mapp[metap->hashm_nmaps] = BufferGetBlockNumber(newmapbuf);
metap->hashm_nmaps++;
metap->hashm_spares[splitnum]++;
}
MarkBufferDirty(metabuf);
/*
* for new overflow page, we don't need to explicitly set the bit in
* bitmap page, as by default that will be set to "in use".
*/
}
/*
* Adjust hashm_firstfree to avoid redundant searches. But don't risk
* changing it if someone moved it while we were searching bitmap pages.
*/
if (metap->hashm_firstfree == orig_firstfree)
{
metap->hashm_firstfree = bit + 1;
MarkBufferDirty(metabuf);
}
/* initialize new overflow page */
ovflpage = BufferGetPage(ovflbuf);
ovflopaque = (HashPageOpaque) PageGetSpecialPointer(ovflpage);
ovflopaque->hasho_prevblkno = BufferGetBlockNumber(buf);
ovflopaque->hasho_nextblkno = InvalidBlockNumber;
ovflopaque->hasho_bucket = pageopaque->hasho_bucket;
ovflopaque->hasho_flag = LH_OVERFLOW_PAGE;
ovflopaque->hasho_page_id = HASHO_PAGE_ID;
MarkBufferDirty(ovflbuf);
/* logically chain overflow page to previous page */
pageopaque->hasho_nextblkno = BufferGetBlockNumber(ovflbuf);
MarkBufferDirty(buf);
/* XLOG stuff */
if (RelationNeedsWAL(rel))
{
XLogRecPtr recptr;
xl_hash_add_ovfl_page xlrec;
xlrec.bmpage_found = page_found;
xlrec.bmsize = metap->hashm_bmsize;
XLogBeginInsert();
XLogRegisterData((char *) &xlrec, SizeOfHashAddOvflPage);
XLogRegisterBuffer(0, ovflbuf, REGBUF_WILL_INIT);
XLogRegisterBufData(0, (char *) &pageopaque->hasho_bucket, sizeof(Bucket));
XLogRegisterBuffer(1, buf, REGBUF_STANDARD);
if (BufferIsValid(mapbuf))
{
XLogRegisterBuffer(2, mapbuf, REGBUF_STANDARD);
XLogRegisterBufData(2, (char *) &bitmap_page_bit, sizeof(uint32));
}
if (BufferIsValid(newmapbuf))
XLogRegisterBuffer(3, newmapbuf, REGBUF_WILL_INIT);
XLogRegisterBuffer(4, metabuf, REGBUF_STANDARD);
XLogRegisterBufData(4, (char *) &metap->hashm_firstfree, sizeof(uint32));
recptr = XLogInsert(RM_HASH_ID, XLOG_HASH_ADD_OVFL_PAGE);
PageSetLSN(BufferGetPage(ovflbuf), recptr);
PageSetLSN(BufferGetPage(buf), recptr);
if (BufferIsValid(mapbuf))
PageSetLSN(BufferGetPage(mapbuf), recptr);
if (BufferIsValid(newmapbuf))
PageSetLSN(BufferGetPage(newmapbuf), recptr);
PageSetLSN(BufferGetPage(metabuf), recptr);
}
END_CRIT_SECTION();
if (retain_pin)
LockBuffer(buf, BUFFER_LOCK_UNLOCK);
else
_hash_relbuf(rel, buf);
if (BufferIsValid(mapbuf))
_hash_relbuf(rel, mapbuf);
LockBuffer(metabuf, BUFFER_LOCK_UNLOCK);
if (BufferIsValid(newmapbuf))
_hash_relbuf(rel, newmapbuf);
return ovflbuf;
}
/*
* Write XLOG record describing a page update. The update can include any
* number of deletions and/or insertions of tuples on a single index page.
*
* If this update inserts a downlink for a split page, also record that
* the F_FOLLOW_RIGHT flag on the child page is cleared and NSN set.
*
* Note that both the todelete array and the tuples are marked as belonging
* to the target buffer; they need not be stored in XLOG if XLogInsert decides
* to log the whole buffer contents instead. Also, we take care that there's
* at least one rdata item referencing the buffer, even when ntodelete and
* ituplen are both zero; this ensures that XLogInsert knows about the buffer.
*/
XLogRecPtr
gistXLogUpdate(RelFileNode node, Buffer buffer,
OffsetNumber *todelete, int ntodelete,
IndexTuple *itup, int ituplen,
Buffer leftchildbuf)
{
XLogRecData *rdata;
gistxlogPageUpdate xlrec;
int cur,
i;
XLogRecPtr recptr;
rdata = (XLogRecData *) palloc(sizeof(XLogRecData) * (3 + ituplen));
xlrec.node = node;
xlrec.blkno = BufferGetBlockNumber(buffer);
xlrec.ntodelete = ntodelete;
xlrec.leftchild =
BufferIsValid(leftchildbuf) ? BufferGetBlockNumber(leftchildbuf) : InvalidBlockNumber;
rdata[0].data = (char *) &xlrec;
rdata[0].len = sizeof(gistxlogPageUpdate);
rdata[0].buffer = InvalidBuffer;
rdata[0].next = &(rdata[1]);
rdata[1].data = (char *) todelete;
rdata[1].len = sizeof(OffsetNumber) * ntodelete;
rdata[1].buffer = buffer;
rdata[1].buffer_std = true;
cur = 2;
/* new tuples */
for (i = 0; i < ituplen; i++)
{
rdata[cur - 1].next = &(rdata[cur]);
rdata[cur].data = (char *) (itup[i]);
rdata[cur].len = IndexTupleSize(itup[i]);
rdata[cur].buffer = buffer;
rdata[cur].buffer_std = true;
cur++;
}
/*
* Include a full page image of the child buf. (only necessary if a
* checkpoint happened since the child page was split)
*/
if (BufferIsValid(leftchildbuf))
{
rdata[cur - 1].next = &(rdata[cur]);
rdata[cur].data = NULL;
rdata[cur].len = 0;
rdata[cur].buffer = leftchildbuf;
rdata[cur].buffer_std = true;
cur++;
}
rdata[cur - 1].next = NULL;
recptr = XLogInsert(RM_GIST_ID, XLOG_GIST_PAGE_UPDATE, rdata);
pfree(rdata);
return recptr;
}
/*
* _hash_freeovflpage() -
*
* Remove this overflow page from its bucket's chain, and mark the page as
* free. On entry, ovflbuf is write-locked; it is released before exiting.
*
* Add the tuples (itups) to wbuf in this function. We could do that in the
* caller as well, but the advantage of doing it here is we can easily write
* the WAL for XLOG_HASH_SQUEEZE_PAGE operation. Addition of tuples and
* removal of overflow page has to done as an atomic operation, otherwise
* during replay on standby users might find duplicate records.
*
* Since this function is invoked in VACUUM, we provide an access strategy
* parameter that controls fetches of the bucket pages.
*
* Returns the block number of the page that followed the given page
* in the bucket, or InvalidBlockNumber if no following page.
*
* NB: caller must not hold lock on metapage, nor on page, that's next to
* ovflbuf in the bucket chain. We don't acquire the lock on page that's
* prior to ovflbuf in chain if it is same as wbuf because the caller already
* has a lock on same.
*/
BlockNumber
_hash_freeovflpage(Relation rel, Buffer bucketbuf, Buffer ovflbuf,
Buffer wbuf, IndexTuple *itups, OffsetNumber *itup_offsets,
Size *tups_size, uint16 nitups,
BufferAccessStrategy bstrategy)
{
HashMetaPage metap;
Buffer metabuf;
Buffer mapbuf;
BlockNumber ovflblkno;
BlockNumber prevblkno;
BlockNumber blkno;
BlockNumber nextblkno;
BlockNumber writeblkno;
HashPageOpaque ovflopaque;
Page ovflpage;
Page mappage;
uint32 *freep;
uint32 ovflbitno;
int32 bitmappage,
bitmapbit;
Bucket bucket PG_USED_FOR_ASSERTS_ONLY;
Buffer prevbuf = InvalidBuffer;
Buffer nextbuf = InvalidBuffer;
bool update_metap = false;
/* Get information from the doomed page */
_hash_checkpage(rel, ovflbuf, LH_OVERFLOW_PAGE);
ovflblkno = BufferGetBlockNumber(ovflbuf);
ovflpage = BufferGetPage(ovflbuf);
ovflopaque = (HashPageOpaque) PageGetSpecialPointer(ovflpage);
nextblkno = ovflopaque->hasho_nextblkno;
prevblkno = ovflopaque->hasho_prevblkno;
writeblkno = BufferGetBlockNumber(wbuf);
bucket = ovflopaque->hasho_bucket;
/*
* Fix up the bucket chain. this is a doubly-linked list, so we must fix
* up the bucket chain members behind and ahead of the overflow page being
* deleted. Concurrency issues are avoided by using lock chaining as
* described atop hashbucketcleanup.
*/
if (BlockNumberIsValid(prevblkno))
{
if (prevblkno == writeblkno)
prevbuf = wbuf;
else
prevbuf = _hash_getbuf_with_strategy(rel,
prevblkno,
HASH_WRITE,
LH_BUCKET_PAGE | LH_OVERFLOW_PAGE,
bstrategy);
}
if (BlockNumberIsValid(nextblkno))
nextbuf = _hash_getbuf_with_strategy(rel,
nextblkno,
HASH_WRITE,
LH_OVERFLOW_PAGE,
bstrategy);
/* Note: bstrategy is intentionally not used for metapage and bitmap */
/* Read the metapage so we can determine which bitmap page to use */
metabuf = _hash_getbuf(rel, HASH_METAPAGE, HASH_READ, LH_META_PAGE);
metap = HashPageGetMeta(BufferGetPage(metabuf));
/* Identify which bit to set */
ovflbitno = _hash_ovflblkno_to_bitno(metap, ovflblkno);
bitmappage = ovflbitno >> BMPG_SHIFT(metap);
bitmapbit = ovflbitno & BMPG_MASK(metap);
if (bitmappage >= metap->hashm_nmaps)
elog(ERROR, "invalid overflow bit number %u", ovflbitno);
blkno = metap->hashm_mapp[bitmappage];
/* Release metapage lock while we access the bitmap page */
LockBuffer(metabuf, BUFFER_LOCK_UNLOCK);
/* read the bitmap page to clear the bitmap bit */
mapbuf = _hash_getbuf(rel, blkno, HASH_WRITE, LH_BITMAP_PAGE);
mappage = BufferGetPage(mapbuf);
freep = HashPageGetBitmap(mappage);
Assert(ISSET(freep, bitmapbit));
/* Get write-lock on metapage to update firstfree */
LockBuffer(metabuf, BUFFER_LOCK_EXCLUSIVE);
/* This operation needs to log multiple tuples, prepare WAL for that */
if (RelationNeedsWAL(rel))
XLogEnsureRecordSpace(HASH_XLOG_FREE_OVFL_BUFS, 4 + nitups);
START_CRIT_SECTION();
/*
* we have to insert tuples on the "write" page, being careful to preserve
* hashkey ordering. (If we insert many tuples into the same "write" page
* it would be worth qsort'ing them).
*/
if (nitups > 0)
{
_hash_pgaddmultitup(rel, wbuf, itups, itup_offsets, nitups);
MarkBufferDirty(wbuf);
}
/*
* Reinitialize the freed overflow page. Just zeroing the page won't
* work, because WAL replay routines expect pages to be initialized. See
* explanation of RBM_NORMAL mode atop XLogReadBufferExtended. We are
* careful to make the special space valid here so that tools like
* pageinspect won't get confused.
*/
_hash_pageinit(ovflpage, BufferGetPageSize(ovflbuf));
ovflopaque = (HashPageOpaque) PageGetSpecialPointer(ovflpage);
ovflopaque->hasho_prevblkno = InvalidBlockNumber;
ovflopaque->hasho_nextblkno = InvalidBlockNumber;
ovflopaque->hasho_bucket = -1;
ovflopaque->hasho_flag = LH_UNUSED_PAGE;
ovflopaque->hasho_page_id = HASHO_PAGE_ID;
MarkBufferDirty(ovflbuf);
if (BufferIsValid(prevbuf))
{
Page prevpage = BufferGetPage(prevbuf);
HashPageOpaque prevopaque = (HashPageOpaque) PageGetSpecialPointer(prevpage);
Assert(prevopaque->hasho_bucket == bucket);
prevopaque->hasho_nextblkno = nextblkno;
MarkBufferDirty(prevbuf);
}
if (BufferIsValid(nextbuf))
{
Page nextpage = BufferGetPage(nextbuf);
HashPageOpaque nextopaque = (HashPageOpaque) PageGetSpecialPointer(nextpage);
Assert(nextopaque->hasho_bucket == bucket);
nextopaque->hasho_prevblkno = prevblkno;
MarkBufferDirty(nextbuf);
}
/* Clear the bitmap bit to indicate that this overflow page is free */
CLRBIT(freep, bitmapbit);
MarkBufferDirty(mapbuf);
/* if this is now the first free page, update hashm_firstfree */
if (ovflbitno < metap->hashm_firstfree)
{
metap->hashm_firstfree = ovflbitno;
update_metap = true;
MarkBufferDirty(metabuf);
}
/* XLOG stuff */
if (RelationNeedsWAL(rel))
{
xl_hash_squeeze_page xlrec;
XLogRecPtr recptr;
int i;
xlrec.prevblkno = prevblkno;
xlrec.nextblkno = nextblkno;
xlrec.ntups = nitups;
xlrec.is_prim_bucket_same_wrt = (wbuf == bucketbuf);
xlrec.is_prev_bucket_same_wrt = (wbuf == prevbuf);
XLogBeginInsert();
XLogRegisterData((char *) &xlrec, SizeOfHashSqueezePage);
/*
* bucket buffer needs to be registered to ensure that we can acquire
* a cleanup lock on it during replay.
*/
if (!xlrec.is_prim_bucket_same_wrt)
XLogRegisterBuffer(0, bucketbuf, REGBUF_STANDARD | REGBUF_NO_IMAGE);
XLogRegisterBuffer(1, wbuf, REGBUF_STANDARD);
if (xlrec.ntups > 0)
{
XLogRegisterBufData(1, (char *) itup_offsets,
nitups * sizeof(OffsetNumber));
for (i = 0; i < nitups; i++)
XLogRegisterBufData(1, (char *) itups[i], tups_size[i]);
}
XLogRegisterBuffer(2, ovflbuf, REGBUF_STANDARD);
/*
* If prevpage and the writepage (block in which we are moving tuples
* from overflow) are same, then no need to separately register
* prevpage. During replay, we can directly update the nextblock in
* writepage.
*/
if (BufferIsValid(prevbuf) && !xlrec.is_prev_bucket_same_wrt)
XLogRegisterBuffer(3, prevbuf, REGBUF_STANDARD);
if (BufferIsValid(nextbuf))
XLogRegisterBuffer(4, nextbuf, REGBUF_STANDARD);
XLogRegisterBuffer(5, mapbuf, REGBUF_STANDARD);
XLogRegisterBufData(5, (char *) &bitmapbit, sizeof(uint32));
if (update_metap)
{
XLogRegisterBuffer(6, metabuf, REGBUF_STANDARD);
XLogRegisterBufData(6, (char *) &metap->hashm_firstfree, sizeof(uint32));
}
recptr = XLogInsert(RM_HASH_ID, XLOG_HASH_SQUEEZE_PAGE);
PageSetLSN(BufferGetPage(wbuf), recptr);
PageSetLSN(BufferGetPage(ovflbuf), recptr);
if (BufferIsValid(prevbuf) && !xlrec.is_prev_bucket_same_wrt)
PageSetLSN(BufferGetPage(prevbuf), recptr);
if (BufferIsValid(nextbuf))
PageSetLSN(BufferGetPage(nextbuf), recptr);
PageSetLSN(BufferGetPage(mapbuf), recptr);
if (update_metap)
PageSetLSN(BufferGetPage(metabuf), recptr);
}
END_CRIT_SECTION();
/* release previous bucket if it is not same as write bucket */
if (BufferIsValid(prevbuf) && prevblkno != writeblkno)
_hash_relbuf(rel, prevbuf);
if (BufferIsValid(ovflbuf))
_hash_relbuf(rel, ovflbuf);
if (BufferIsValid(nextbuf))
_hash_relbuf(rel, nextbuf);
_hash_relbuf(rel, mapbuf);
_hash_relbuf(rel, metabuf);
return nextblkno;
}
/*
* Scan a complete BRIN index, and summarize each page range that's not already
* summarized. The index and heap must have been locked by caller in at
* least ShareUpdateExclusiveLock mode.
*
* For each new index tuple inserted, *numSummarized (if not NULL) is
* incremented; for each existing tuple, *numExisting (if not NULL) is
* incremented.
*/
static void
brinsummarize(Relation index, Relation heapRel, double *numSummarized,
double *numExisting)
{
BrinRevmap *revmap;
BrinBuildState *state = NULL;
IndexInfo *indexInfo = NULL;
BlockNumber heapNumBlocks;
BlockNumber pagesPerRange;
Buffer buf;
BlockNumber startBlk;
revmap = brinRevmapInitialize(index, &pagesPerRange, NULL);
/* determine range of pages to process: always start from the beginning */
heapNumBlocks = RelationGetNumberOfBlocks(heapRel);
startBlk = 0;
/*
* Scan the revmap to find unsummarized items.
*/
buf = InvalidBuffer;
for (; startBlk < heapNumBlocks; startBlk += pagesPerRange)
{
BrinTuple *tup;
OffsetNumber off;
/*
* Go away now if we think the next range is partial.
*/
if (startBlk + pagesPerRange > heapNumBlocks)
break;
CHECK_FOR_INTERRUPTS();
tup = brinGetTupleForHeapBlock(revmap, startBlk, &buf, &off, NULL,
BUFFER_LOCK_SHARE, NULL);
if (tup == NULL)
{
/* no revmap entry for this heap range. Summarize it. */
if (state == NULL)
{
/* first time through */
Assert(!indexInfo);
state = initialize_brin_buildstate(index, revmap,
pagesPerRange);
indexInfo = BuildIndexInfo(index);
}
summarize_range(indexInfo, state, heapRel, startBlk, heapNumBlocks);
/* and re-initialize state for the next range */
brin_memtuple_initialize(state->bs_dtuple, state->bs_bdesc);
if (numSummarized)
*numSummarized += 1.0;
}
else
{
if (numExisting)
*numExisting += 1.0;
LockBuffer(buf, BUFFER_LOCK_UNLOCK);
}
}
if (BufferIsValid(buf))
ReleaseBuffer(buf);
/* free resources */
brinRevmapTerminate(revmap);
if (state)
{
terminate_brin_buildstate(state);
pfree(indexInfo);
}
}
/*
* _bt_readpage() -- Load data from current index page into so->currPos
*
* Caller must have pinned and read-locked so->currPos.buf; the buffer's state
* is not changed here. Also, currPos.moreLeft and moreRight must be valid;
* they are updated as appropriate. All other fields of so->currPos are
* initialized from scratch here.
*
* We scan the current page starting at offnum and moving in the indicated
* direction. All items matching the scan keys are loaded into currPos.items.
* moreLeft or moreRight (as appropriate) is cleared if _bt_checkkeys reports
* that there can be no more matching tuples in the current scan direction.
*
* Returns true if any matching items found on the page, false if none.
*/
static bool
_bt_readpage(IndexScanDesc scan, ScanDirection dir, OffsetNumber offnum)
{
BTScanOpaque so = (BTScanOpaque) scan->opaque;
Page page;
BTPageOpaque opaque;
OffsetNumber minoff;
OffsetNumber maxoff;
int itemIndex;
IndexTuple itup;
bool continuescan;
/* we must have the buffer pinned and locked */
Assert(BufferIsValid(so->currPos.buf));
page = BufferGetPage(so->currPos.buf);
opaque = (BTPageOpaque) PageGetSpecialPointer(page);
minoff = P_FIRSTDATAKEY(opaque);
maxoff = PageGetMaxOffsetNumber(page);
/*
* we must save the page's right-link while scanning it; this tells us
* where to step right to after we're done with these items. There is no
* corresponding need for the left-link, since splits always go right.
*/
so->currPos.nextPage = opaque->btpo_next;
/* initialize tuple workspace to empty */
so->currPos.nextTupleOffset = 0;
if (ScanDirectionIsForward(dir))
{
/* load items[] in ascending order */
itemIndex = 0;
offnum = Max(offnum, minoff);
while (offnum <= maxoff)
{
itup = _bt_checkkeys(scan, page, offnum, dir, &continuescan);
if (itup != NULL)
{
/* tuple passes all scan key conditions, so remember it */
_bt_saveitem(so, itemIndex, offnum, itup);
itemIndex++;
}
if (!continuescan)
{
/* there can't be any more matches, so stop */
so->currPos.moreRight = false;
break;
}
offnum = OffsetNumberNext(offnum);
}
Assert(itemIndex <= MaxIndexTuplesPerPage);
so->currPos.firstItem = 0;
so->currPos.lastItem = itemIndex - 1;
so->currPos.itemIndex = 0;
}
else
{
/* load items[] in descending order */
itemIndex = MaxIndexTuplesPerPage;
offnum = Min(offnum, maxoff);
while (offnum >= minoff)
{
itup = _bt_checkkeys(scan, page, offnum, dir, &continuescan);
if (itup != NULL)
{
/* tuple passes all scan key conditions, so remember it */
itemIndex--;
_bt_saveitem(so, itemIndex, offnum, itup);
}
if (!continuescan)
{
/* there can't be any more matches, so stop */
so->currPos.moreLeft = false;
break;
}
offnum = OffsetNumberPrev(offnum);
}
Assert(itemIndex >= 0);
so->currPos.firstItem = itemIndex;
so->currPos.lastItem = MaxIndexTuplesPerPage - 1;
so->currPos.itemIndex = MaxIndexTuplesPerPage - 1;
}
return (so->currPos.firstItem <= so->currPos.lastItem);
}
static void
spgRedoMoveLeafs(XLogRecPtr lsn, XLogRecord *record)
{
char *ptr = XLogRecGetData(record);
spgxlogMoveLeafs *xldata = (spgxlogMoveLeafs *) ptr;
SpGistState state;
OffsetNumber *toDelete;
OffsetNumber *toInsert;
int nInsert;
Buffer buffer;
Page page;
fillFakeState(&state, xldata->stateSrc);
nInsert = xldata->replaceDead ? 1 : xldata->nMoves + 1;
ptr += MAXALIGN(sizeof(spgxlogMoveLeafs));
toDelete = (OffsetNumber *) ptr;
ptr += MAXALIGN(sizeof(OffsetNumber) * xldata->nMoves);
toInsert = (OffsetNumber *) ptr;
ptr += MAXALIGN(sizeof(OffsetNumber) * nInsert);
/* now ptr points to the list of leaf tuples */
/* Insert tuples on the dest page (do first, so redirect is valid) */
if (!(record->xl_info & XLR_BKP_BLOCK_2))
{
buffer = XLogReadBuffer(xldata->node, xldata->blknoDst,
xldata->newPage);
if (BufferIsValid(buffer))
{
page = BufferGetPage(buffer);
if (xldata->newPage)
SpGistInitBuffer(buffer, SPGIST_LEAF);
if (!XLByteLE(lsn, PageGetLSN(page)))
{
int i;
for (i = 0; i < nInsert; i++)
{
SpGistLeafTuple lt = (SpGistLeafTuple) ptr;
addOrReplaceTuple(page, (Item) lt, lt->size, toInsert[i]);
ptr += lt->size;
}
PageSetLSN(page, lsn);
PageSetTLI(page, ThisTimeLineID);
MarkBufferDirty(buffer);
}
UnlockReleaseBuffer(buffer);
}
}
/* Delete tuples from the source page, inserting a redirection pointer */
if (!(record->xl_info & XLR_BKP_BLOCK_1))
{
buffer = XLogReadBuffer(xldata->node, xldata->blknoSrc, false);
if (BufferIsValid(buffer))
{
page = BufferGetPage(buffer);
if (!XLByteLE(lsn, PageGetLSN(page)))
{
spgPageIndexMultiDelete(&state, page, toDelete, xldata->nMoves,
state.isBuild ? SPGIST_PLACEHOLDER : SPGIST_REDIRECT,
SPGIST_PLACEHOLDER,
xldata->blknoDst,
toInsert[nInsert - 1]);
PageSetLSN(page, lsn);
PageSetTLI(page, ThisTimeLineID);
MarkBufferDirty(buffer);
}
UnlockReleaseBuffer(buffer);
}
}
/* And update the parent downlink */
if (!(record->xl_info & XLR_BKP_BLOCK_3))
{
buffer = XLogReadBuffer(xldata->node, xldata->blknoParent, false);
if (BufferIsValid(buffer))
{
page = BufferGetPage(buffer);
if (!XLByteLE(lsn, PageGetLSN(page)))
{
SpGistInnerTuple tuple;
tuple = (SpGistInnerTuple) PageGetItem(page,
PageGetItemId(page, xldata->offnumParent));
spgUpdateNodeLink(tuple, xldata->nodeI,
xldata->blknoDst, toInsert[nInsert - 1]);
PageSetLSN(page, lsn);
PageSetTLI(page, ThisTimeLineID);
MarkBufferDirty(buffer);
}
UnlockReleaseBuffer(buffer);
}
}
}
/*
* _bt_steppage() -- Step to next page containing valid data for scan
*
* On entry, so->currPos.buf must be pinned and read-locked. We'll drop
* the lock and pin before moving to next page.
*
* On success exit, we hold pin and read-lock on the next interesting page,
* and so->currPos is updated to contain data from that page.
*
* If there are no more matching records in the given direction, we drop all
* locks and pins, set so->currPos.buf to InvalidBuffer, and return FALSE.
*/
static bool
_bt_steppage(IndexScanDesc scan, ScanDirection dir)
{
BTScanOpaque so = (BTScanOpaque) scan->opaque;
Relation rel;
Page page;
BTPageOpaque opaque;
/* we must have the buffer pinned and locked */
Assert(BufferIsValid(so->currPos.buf));
/* Before leaving current page, deal with any killed items */
if (so->numKilled > 0)
_bt_killitems(scan, true);
/*
* Before we modify currPos, make a copy of the page data if there was a
* mark position that needs it.
*/
if (so->markItemIndex >= 0)
{
/* bump pin on current buffer for assignment to mark buffer */
IncrBufferRefCount(so->currPos.buf);
memcpy(&so->markPos, &so->currPos,
offsetof(BTScanPosData, items[1]) +
so->currPos.lastItem * sizeof(BTScanPosItem));
if (so->markTuples)
memcpy(so->markTuples, so->currTuples,
so->currPos.nextTupleOffset);
so->markPos.itemIndex = so->markItemIndex;
so->markItemIndex = -1;
}
rel = scan->indexRelation;
if (ScanDirectionIsForward(dir))
{
/* Walk right to the next page with data */
/* We must rely on the previously saved nextPage link! */
BlockNumber blkno = so->currPos.nextPage;
/* Remember we left a page with data */
so->currPos.moreLeft = true;
for (;;)
{
/* release the previous buffer */
_bt_relbuf(rel, so->currPos.buf);
so->currPos.buf = InvalidBuffer;
/* if we're at end of scan, give up */
if (blkno == P_NONE || !so->currPos.moreRight)
return false;
/* check for interrupts while we're not holding any buffer lock */
CHECK_FOR_INTERRUPTS();
/* step right one page */
so->currPos.buf = _bt_getbuf(rel, blkno, BT_READ);
/* check for deleted page */
page = BufferGetPage(so->currPos.buf);
opaque = (BTPageOpaque) PageGetSpecialPointer(page);
if (!P_IGNORE(opaque))
{
PredicateLockPage(rel, blkno, scan->xs_snapshot);
/* see if there are any matches on this page */
/* note that this will clear moreRight if we can stop */
if (_bt_readpage(scan, dir, P_FIRSTDATAKEY(opaque)))
break;
}
/* nope, keep going */
blkno = opaque->btpo_next;
}
}
else
{
/* Remember we left a page with data */
so->currPos.moreRight = true;
/*
* Walk left to the next page with data. This is much more complex
* than the walk-right case because of the possibility that the page
* to our left splits while we are in flight to it, plus the
* possibility that the page we were on gets deleted after we leave
* it. See nbtree/README for details.
*/
for (;;)
{
/* Done if we know there are no matching keys to the left */
if (!so->currPos.moreLeft)
{
_bt_relbuf(rel, so->currPos.buf);
so->currPos.buf = InvalidBuffer;
return false;
}
/* Step to next physical page */
so->currPos.buf = _bt_walk_left(rel, so->currPos.buf);
/* if we're physically at end of index, return failure */
if (so->currPos.buf == InvalidBuffer)
return false;
/*
* Okay, we managed to move left to a non-deleted page. Done if
* it's not half-dead and contains matching tuples. Else loop back
* and do it all again.
*/
page = BufferGetPage(so->currPos.buf);
opaque = (BTPageOpaque) PageGetSpecialPointer(page);
if (!P_IGNORE(opaque))
{
PredicateLockPage(rel, BufferGetBlockNumber(so->currPos.buf), scan->xs_snapshot);
/* see if there are any matches on this page */
/* note that this will clear moreLeft if we can stop */
if (_bt_readpage(scan, dir, PageGetMaxOffsetNumber(page)))
break;
}
}
}
return true;
}
static void
spgRedoSplitTuple(XLogRecPtr lsn, XLogRecord *record)
{
char *ptr = XLogRecGetData(record);
spgxlogSplitTuple *xldata = (spgxlogSplitTuple *) ptr;
SpGistInnerTuple prefixTuple;
SpGistInnerTuple postfixTuple;
Buffer buffer;
Page page;
/* we assume this is adequately aligned */
ptr += sizeof(spgxlogSplitTuple);
prefixTuple = (SpGistInnerTuple) ptr;
ptr += prefixTuple->size;
postfixTuple = (SpGistInnerTuple) ptr;
/* insert postfix tuple first to avoid dangling link */
if (xldata->blknoPostfix != xldata->blknoPrefix &&
!(record->xl_info & XLR_BKP_BLOCK_2))
{
buffer = XLogReadBuffer(xldata->node, xldata->blknoPostfix,
xldata->newPage);
if (BufferIsValid(buffer))
{
page = BufferGetPage(buffer);
if (xldata->newPage)
SpGistInitBuffer(buffer, 0);
if (!XLByteLE(lsn, PageGetLSN(page)))
{
addOrReplaceTuple(page, (Item) postfixTuple,
postfixTuple->size, xldata->offnumPostfix);
PageSetLSN(page, lsn);
PageSetTLI(page, ThisTimeLineID);
MarkBufferDirty(buffer);
}
UnlockReleaseBuffer(buffer);
}
}
/* now handle the original page */
if (!(record->xl_info & XLR_BKP_BLOCK_1))
{
buffer = XLogReadBuffer(xldata->node, xldata->blknoPrefix, false);
if (BufferIsValid(buffer))
{
page = BufferGetPage(buffer);
if (!XLByteLE(lsn, PageGetLSN(page)))
{
PageIndexTupleDelete(page, xldata->offnumPrefix);
if (PageAddItem(page, (Item) prefixTuple, prefixTuple->size,
xldata->offnumPrefix, false, false) != xldata->offnumPrefix)
elog(ERROR, "failed to add item of size %u to SPGiST index page",
prefixTuple->size);
if (xldata->blknoPostfix == xldata->blknoPrefix)
addOrReplaceTuple(page, (Item) postfixTuple,
postfixTuple->size,
xldata->offnumPostfix);
PageSetLSN(page, lsn);
PageSetTLI(page, ThisTimeLineID);
MarkBufferDirty(buffer);
}
UnlockReleaseBuffer(buffer);
}
}
}
/*
* _bt_get_endpoint() -- Find the first or last page on a given tree level
*
* If the index is empty, we will return InvalidBuffer; any other failure
* condition causes ereport(). We will not return a dead page.
*
* The returned buffer is pinned and read-locked.
*/
Buffer
_bt_get_endpoint(Relation rel, uint32 level, bool rightmost)
{
Buffer buf;
Page page;
BTPageOpaque opaque;
OffsetNumber offnum;
BlockNumber blkno;
IndexTuple itup;
/*
* If we are looking for a leaf page, okay to descend from fast root;
* otherwise better descend from true root. (There is no point in being
* smarter about intermediate levels.)
*/
if (level == 0)
buf = _bt_getroot(rel, BT_READ);
else
buf = _bt_gettrueroot(rel);
if (!BufferIsValid(buf))
return InvalidBuffer;
page = BufferGetPage(buf);
opaque = (BTPageOpaque) PageGetSpecialPointer(page);
for (;;)
{
/*
* If we landed on a deleted page, step right to find a live page
* (there must be one). Also, if we want the rightmost page, step
* right if needed to get to it (this could happen if the page split
* since we obtained a pointer to it).
*/
while (P_IGNORE(opaque) ||
(rightmost && !P_RIGHTMOST(opaque)))
{
blkno = opaque->btpo_next;
if (blkno == P_NONE)
elog(ERROR, "fell off the end of index \"%s\"",
RelationGetRelationName(rel));
buf = _bt_relandgetbuf(rel, buf, blkno, BT_READ);
page = BufferGetPage(buf);
opaque = (BTPageOpaque) PageGetSpecialPointer(page);
}
/* Done? */
if (opaque->btpo.level == level)
break;
if (opaque->btpo.level < level)
elog(ERROR, "btree level %u not found in index \"%s\"",
level, RelationGetRelationName(rel));
/* Descend to leftmost or rightmost child page */
if (rightmost)
offnum = PageGetMaxOffsetNumber(page);
else
offnum = P_FIRSTDATAKEY(opaque);
itup = (IndexTuple) PageGetItem(page, PageGetItemId(page, offnum));
blkno = ItemPointerGetBlockNumber(&(itup->t_tid));
buf = _bt_relandgetbuf(rel, buf, blkno, BT_READ);
page = BufferGetPage(buf);
opaque = (BTPageOpaque) PageGetSpecialPointer(page);
}
return buf;
}
static void
spgRedoVacuumLeaf(XLogRecPtr lsn, XLogRecord *record)
{
char *ptr = XLogRecGetData(record);
spgxlogVacuumLeaf *xldata = (spgxlogVacuumLeaf *) ptr;
OffsetNumber *toDead;
OffsetNumber *toPlaceholder;
OffsetNumber *moveSrc;
OffsetNumber *moveDest;
OffsetNumber *chainSrc;
OffsetNumber *chainDest;
SpGistState state;
Buffer buffer;
Page page;
int i;
fillFakeState(&state, xldata->stateSrc);
ptr += sizeof(spgxlogVacuumLeaf);
toDead = (OffsetNumber *) ptr;
ptr += sizeof(OffsetNumber) * xldata->nDead;
toPlaceholder = (OffsetNumber *) ptr;
ptr += sizeof(OffsetNumber) * xldata->nPlaceholder;
moveSrc = (OffsetNumber *) ptr;
ptr += sizeof(OffsetNumber) * xldata->nMove;
moveDest = (OffsetNumber *) ptr;
ptr += sizeof(OffsetNumber) * xldata->nMove;
chainSrc = (OffsetNumber *) ptr;
ptr += sizeof(OffsetNumber) * xldata->nChain;
chainDest = (OffsetNumber *) ptr;
if (!(record->xl_info & XLR_BKP_BLOCK_1))
{
buffer = XLogReadBuffer(xldata->node, xldata->blkno, false);
if (BufferIsValid(buffer))
{
page = BufferGetPage(buffer);
if (!XLByteLE(lsn, PageGetLSN(page)))
{
spgPageIndexMultiDelete(&state, page,
toDead, xldata->nDead,
SPGIST_DEAD, SPGIST_DEAD,
InvalidBlockNumber,
InvalidOffsetNumber);
spgPageIndexMultiDelete(&state, page,
toPlaceholder, xldata->nPlaceholder,
SPGIST_PLACEHOLDER, SPGIST_PLACEHOLDER,
InvalidBlockNumber,
InvalidOffsetNumber);
/* see comments in vacuumLeafPage() */
for (i = 0; i < xldata->nMove; i++)
{
ItemId idSrc = PageGetItemId(page, moveSrc[i]);
ItemId idDest = PageGetItemId(page, moveDest[i]);
ItemIdData tmp;
tmp = *idSrc;
*idSrc = *idDest;
*idDest = tmp;
}
spgPageIndexMultiDelete(&state, page,
moveSrc, xldata->nMove,
SPGIST_PLACEHOLDER, SPGIST_PLACEHOLDER,
InvalidBlockNumber,
InvalidOffsetNumber);
for (i = 0; i < xldata->nChain; i++)
{
SpGistLeafTuple lt;
lt = (SpGistLeafTuple) PageGetItem(page,
PageGetItemId(page, chainSrc[i]));
Assert(lt->tupstate == SPGIST_LIVE);
lt->nextOffset = chainDest[i];
}
PageSetLSN(page, lsn);
PageSetTLI(page, ThisTimeLineID);
MarkBufferDirty(buffer);
}
UnlockReleaseBuffer(buffer);
}
}
}
/*
* _hash_step() -- step to the next valid item in a scan in the bucket.
*
* If no valid record exists in the requested direction, return
* false. Else, return true and set the hashso_curpos for the
* scan to the right thing.
*
* 'bufP' points to the current buffer, which is pinned and read-locked.
* On success exit, we have pin and read-lock on whichever page
* contains the right item; on failure, we have released all buffers.
*/
bool
_hash_step(IndexScanDesc scan, Buffer *bufP, ScanDirection dir)
{
Relation rel = scan->indexRelation;
HashScanOpaque so = (HashScanOpaque) scan->opaque;
ItemPointer current;
Buffer buf;
Page page;
HashPageOpaque opaque;
OffsetNumber maxoff;
OffsetNumber offnum;
BlockNumber blkno;
IndexTuple itup;
current = &(so->hashso_curpos);
buf = *bufP;
_hash_checkpage(rel, buf, LH_BUCKET_PAGE | LH_OVERFLOW_PAGE);
page = BufferGetPage(buf);
opaque = (HashPageOpaque) PageGetSpecialPointer(page);
/*
* If _hash_step is called from _hash_first, current will not be valid, so
* we can't dereference it. However, in that case, we presumably want to
* start at the beginning/end of the page...
*/
maxoff = PageGetMaxOffsetNumber(page);
if (ItemPointerIsValid(current))
offnum = ItemPointerGetOffsetNumber(current);
else
offnum = InvalidOffsetNumber;
/*
* 'offnum' now points to the last tuple we have seen (if any).
*
* continue to step through tuples until: 1) we get to the end of the
* bucket chain or 2) we find a valid tuple.
*/
do
{
switch (dir)
{
case ForwardScanDirection:
if (offnum != InvalidOffsetNumber)
offnum = OffsetNumberNext(offnum); /* move forward */
else
offnum = FirstOffsetNumber; /* new page */
while (offnum > maxoff)
{
/*
* either this page is empty (maxoff ==
* InvalidOffsetNumber) or we ran off the end.
*/
_hash_readnext(rel, &buf, &page, &opaque);
if (BufferIsValid(buf))
{
maxoff = PageGetMaxOffsetNumber(page);
offnum = FirstOffsetNumber;
}
else
{
/* end of bucket */
maxoff = offnum = InvalidOffsetNumber;
break; /* exit while */
}
}
break;
case BackwardScanDirection:
if (offnum != InvalidOffsetNumber)
offnum = OffsetNumberPrev(offnum); /* move back */
else
offnum = maxoff; /* new page */
while (offnum < FirstOffsetNumber)
{
/*
* either this page is empty (offnum ==
* InvalidOffsetNumber) or we ran off the end.
*/
_hash_readprev(rel, &buf, &page, &opaque);
if (BufferIsValid(buf))
maxoff = offnum = PageGetMaxOffsetNumber(page);
else
{
/* end of bucket */
maxoff = offnum = InvalidOffsetNumber;
break; /* exit while */
}
}
break;
default:
/* NoMovementScanDirection */
/* this should not be reached */
break;
}
/* we ran off the end of the world without finding a match */
if (offnum == InvalidOffsetNumber)
{
*bufP = so->hashso_curbuf = InvalidBuffer;
ItemPointerSetInvalid(current);
return false;
}
/* get ready to check this tuple */
itup = (IndexTuple) PageGetItem(page, PageGetItemId(page, offnum));
} while (!_hash_checkqual(scan, itup));
/* if we made it to here, we've found a valid tuple */
blkno = BufferGetBlockNumber(buf);
*bufP = so->hashso_curbuf = buf;
ItemPointerSet(current, blkno, offnum);
return true;
}
