/*
* btmarkpos() -- save current scan position
*/
Datum
btmarkpos(PG_FUNCTION_ARGS)
{
IndexScanDesc scan = (IndexScanDesc) PG_GETARG_POINTER(0);
BTScanOpaque so = (BTScanOpaque) scan->opaque;
/* we aren't holding any read locks, but gotta drop the pin */
if (BTScanPosIsValid(so->markPos))
{
ReleaseBuffer(so->markPos.buf);
so->markPos.buf = InvalidBuffer;
}
/*
* Just record the current itemIndex. If we later step to next page
* before releasing the marked position, _bt_steppage makes a full copy of
* the currPos struct in markPos. If (as often happens) the mark is moved
* before we leave the page, we don't have to do that work.
*/
if (BTScanPosIsValid(so->currPos))
so->markItemIndex = so->currPos.itemIndex;
else
so->markItemIndex = -1;
/* Also record the current positions of any array keys */
if (so->numArrayKeys)
_bt_mark_array_keys(scan);
PG_RETURN_VOID();
}
/*
* btmarkpos() -- save current scan position
*/
Datum
btmarkpos(PG_FUNCTION_ARGS)
{
MIRROREDLOCK_BUFMGR_VERIFY_NO_LOCK_LEAK_DECLARE;
IndexScanDesc scan = (IndexScanDesc) PG_GETARG_POINTER(0);
BTScanOpaque so = (BTScanOpaque) scan->opaque;
MIRROREDLOCK_BUFMGR_VERIFY_NO_LOCK_LEAK_ENTER;
/* we aren't holding any read locks, but gotta drop the pin */
if (BTScanPosIsValid(so->markPos))
{
ReleaseBuffer(so->markPos.buf);
so->markPos.buf = InvalidBuffer;
}
/*
* Just record the current itemIndex. If we later step to next page
* before releasing the marked position, _bt_steppage makes a full copy of
* the currPos struct in markPos. If (as often happens) the mark is moved
* before we leave the page, we don't have to do that work.
*/
if (BTScanPosIsValid(so->currPos))
so->markItemIndex = so->currPos.itemIndex;
else
so->markItemIndex = -1;
MIRROREDLOCK_BUFMGR_VERIFY_NO_LOCK_LEAK_EXIT;
PG_RETURN_VOID();
}
/*
* btendscan() -- close down a scan
*/
Datum
btendscan(PG_FUNCTION_ARGS)
{
IndexScanDesc scan = (IndexScanDesc) PG_GETARG_POINTER(0);
BTScanOpaque so = (BTScanOpaque) scan->opaque;
/* we aren't holding any read locks, but gotta drop the pins */
if (BTScanPosIsValid(so->currPos))
{
/* Before leaving current page, deal with any killed items */
if (so->numKilled > 0)
_bt_killitems(scan, false);
ReleaseBuffer(so->currPos.buf);
so->currPos.buf = InvalidBuffer;
}
if (BTScanPosIsValid(so->markPos))
{
ReleaseBuffer(so->markPos.buf);
so->markPos.buf = InvalidBuffer;
}
so->markItemIndex = -1;
if (so->killedItems != NULL)
pfree(so->killedItems);
if (so->keyData != NULL)
pfree(so->keyData);
pfree(so);
PG_RETURN_VOID();
}
/*
* btrescan() -- rescan an index relation
*/
Datum
btrescan(PG_FUNCTION_ARGS)
{
MIRROREDLOCK_BUFMGR_VERIFY_NO_LOCK_LEAK_DECLARE;
IndexScanDesc scan = (IndexScanDesc) PG_GETARG_POINTER(0);
ScanKey scankey = (ScanKey) PG_GETARG_POINTER(1);
BTScanOpaque so;
MIRROREDLOCK_BUFMGR_VERIFY_NO_LOCK_LEAK_ENTER;
so = (BTScanOpaque) scan->opaque;
if (so == NULL) /* if called from btbeginscan */
{
so = (BTScanOpaque) palloc(sizeof(BTScanOpaqueData));
so->currPos.buf = so->markPos.buf = InvalidBuffer;
if (scan->numberOfKeys > 0)
so->keyData = (ScanKey) palloc(scan->numberOfKeys * sizeof(ScanKeyData));
else
so->keyData = NULL;
so->killedItems = NULL; /* until needed */
so->numKilled = 0;
scan->opaque = so;
}
/* we aren't holding any read locks, but gotta drop the pins */
if (BTScanPosIsValid(so->currPos))
{
/* Before leaving current page, deal with any killed items */
if (so->numKilled > 0)
_bt_killitems(scan, false);
ReleaseBuffer(so->currPos.buf);
so->currPos.buf = InvalidBuffer;
}
if (BTScanPosIsValid(so->markPos))
{
ReleaseBuffer(so->markPos.buf);
so->markPos.buf = InvalidBuffer;
}
so->markItemIndex = -1;
/*
* Reset the scan keys. Note that keys ordering stuff moved to _bt_first.
* - vadim 05/05/97
*/
if (scankey && scan->numberOfKeys > 0)
memmove(scan->keyData,
scankey,
scan->numberOfKeys * sizeof(ScanKeyData));
so->numberOfKeys = 0; /* until _bt_preprocess_keys sets it */
MIRROREDLOCK_BUFMGR_VERIFY_NO_LOCK_LEAK_EXIT;
PG_RETURN_VOID();
}
/*
* btrestrpos() -- restore scan to last saved position
*/
void
btrestrpos(IndexScanDesc scan)
{
BTScanOpaque so = (BTScanOpaque) scan->opaque;
/* Restore the marked positions of any array keys */
if (so->numArrayKeys)
_bt_restore_array_keys(scan);
if (so->markItemIndex >= 0)
{
/*
* The scan has never moved to a new page since the last mark. Just
* restore the itemIndex.
*
* NB: In this case we can't count on anything in so->markPos to be
* accurate.
*/
so->currPos.itemIndex = so->markItemIndex;
}
else
{
/*
* The scan moved to a new page after last mark or restore, and we are
* now restoring to the marked page. We aren't holding any read
* locks, but if we're still holding the pin for the current position,
* we must drop it.
*/
if (BTScanPosIsValid(so->currPos))
{
/* Before leaving current page, deal with any killed items */
if (so->numKilled > 0)
_bt_killitems(scan);
BTScanPosUnpinIfPinned(so->currPos);
}
if (BTScanPosIsValid(so->markPos))
{
/* bump pin on mark buffer for assignment to current buffer */
if (BTScanPosIsPinned(so->markPos))
IncrBufferRefCount(so->markPos.buf);
memcpy(&so->currPos, &so->markPos,
offsetof(BTScanPosData, items[1]) +
so->markPos.lastItem * sizeof(BTScanPosItem));
if (so->currTuples)
memcpy(so->currTuples, so->markTuples,
so->markPos.nextTupleOffset);
}
else
BTScanPosInvalidate(so->currPos);
}
}
/*
* btmarkpos() -- save current scan position
*/
void
btmarkpos(IndexScanDesc scan)
{
BTScanOpaque so = (BTScanOpaque) scan->opaque;
/* There may be an old mark with a pin (but no lock). */
BTScanPosUnpinIfPinned(so->markPos);
/*
* Just record the current itemIndex. If we later step to next page
* before releasing the marked position, _bt_steppage makes a full copy of
* the currPos struct in markPos. If (as often happens) the mark is moved
* before we leave the page, we don't have to do that work.
*/
if (BTScanPosIsValid(so->currPos))
so->markItemIndex = so->currPos.itemIndex;
else
{
BTScanPosInvalidate(so->markPos);
so->markItemIndex = -1;
}
/* Also record the current positions of any array keys */
if (so->numArrayKeys)
_bt_mark_array_keys(scan);
}
/*
* btendscan() -- close down a scan
*/
void
btendscan(IndexScanDesc scan)
{
BTScanOpaque so = (BTScanOpaque) scan->opaque;
/* we aren't holding any read locks, but gotta drop the pins */
if (BTScanPosIsValid(so->currPos))
{
/* Before leaving current page, deal with any killed items */
if (so->numKilled > 0)
_bt_killitems(scan);
BTScanPosUnpinIfPinned(so->currPos);
}
so->markItemIndex = -1;
BTScanPosUnpinIfPinned(so->markPos);
/* No need to invalidate positions, the RAM is about to be freed. */
/* Release storage */
if (so->keyData != NULL)
pfree(so->keyData);
/* so->arrayKeyData and so->arrayKeys are in arrayContext */
if (so->arrayContext != NULL)
MemoryContextDelete(so->arrayContext);
if (so->killedItems != NULL)
pfree(so->killedItems);
if (so->currTuples != NULL)
pfree(so->currTuples);
/* so->markTuples should not be pfree'd, see btrescan */
pfree(so);
}
/*
* btrescan() -- rescan an index relation
*/
Datum
btrescan(PG_FUNCTION_ARGS)
{
IndexScanDesc scan = (IndexScanDesc) PG_GETARG_POINTER(0);
ScanKey scankey = (ScanKey) PG_GETARG_POINTER(1);
/* remaining arguments are ignored */
BTScanOpaque so = (BTScanOpaque) scan->opaque;
/* we aren't holding any read locks, but gotta drop the pins */
if (BTScanPosIsValid(so->currPos))
{
/* Before leaving current page, deal with any killed items */
if (so->numKilled > 0)
_bt_killitems(scan);
BTScanPosUnpinIfPinned(so->currPos);
BTScanPosInvalidate(so->currPos);
}
so->markItemIndex = -1;
BTScanPosUnpinIfPinned(so->markPos);
BTScanPosInvalidate(so->markPos);
/*
* Allocate tuple workspace arrays, if needed for an index-only scan and
* not already done in a previous rescan call. To save on palloc
* overhead, both workspaces are allocated as one palloc block; only this
* function and btendscan know that.
*
* NOTE: this data structure also makes it safe to return data from a
* "name" column, even though btree name_ops uses an underlying storage
* datatype of cstring. The risk there is that "name" is supposed to be
* padded to NAMEDATALEN, but the actual index tuple is probably shorter.
* However, since we only return data out of tuples sitting in the
* currTuples array, a fetch of NAMEDATALEN bytes can at worst pull some
* data out of the markTuples array --- running off the end of memory for
* a SIGSEGV is not possible. Yeah, this is ugly as sin, but it beats
* adding special-case treatment for name_ops elsewhere.
*/
if (scan->xs_want_itup && so->currTuples == NULL)
{
so->currTuples = (char *) palloc(BLCKSZ * 2);
so->markTuples = so->currTuples + BLCKSZ;
}
/*
* Reset the scan keys. Note that keys ordering stuff moved to _bt_first.
* - vadim 05/05/97
*/
if (scankey && scan->numberOfKeys > 0)
memmove(scan->keyData,
scankey,
scan->numberOfKeys * sizeof(ScanKeyData));
so->numberOfKeys = 0; /* until _bt_preprocess_keys sets it */
/* If any keys are SK_SEARCHARRAY type, set up array-key info */
_bt_preprocess_array_keys(scan);
PG_RETURN_VOID();
}
/*
* btrestrpos() -- restore scan to last saved position
*/
Datum
btrestrpos(PG_FUNCTION_ARGS)
{
IndexScanDesc scan = (IndexScanDesc) PG_GETARG_POINTER(0);
BTScanOpaque so = (BTScanOpaque) scan->opaque;
/* Restore the marked positions of any array keys */
if (so->numArrayKeys)
_bt_restore_array_keys(scan);
if (so->markItemIndex >= 0)
{
/*
* The mark position is on the same page we are currently on. Just
* restore the itemIndex.
*/
so->currPos.itemIndex = so->markItemIndex;
}
else
{
/* we aren't holding any read locks, but gotta drop the pin */
if (BTScanPosIsValid(so->currPos))
{
/* Before leaving current page, deal with any killed items */
if (so->numKilled > 0 &&
so->currPos.buf != so->markPos.buf)
_bt_killitems(scan, false);
ReleaseBuffer(so->currPos.buf);
so->currPos.buf = InvalidBuffer;
}
if (BTScanPosIsValid(so->markPos))
{
/* bump pin on mark buffer for assignment to current buffer */
IncrBufferRefCount(so->markPos.buf);
memcpy(&so->currPos, &so->markPos,
offsetof(BTScanPosData, items[1]) +
so->markPos.lastItem * sizeof(BTScanPosItem));
if (so->currTuples)
memcpy(so->currTuples, so->markTuples,
so->markPos.nextTupleOffset);
}
}
PG_RETURN_VOID();
}
/*
* btrestrpos() -- restore scan to last saved position
*/
Datum
btrestrpos(PG_FUNCTION_ARGS)
{
MIRROREDLOCK_BUFMGR_VERIFY_NO_LOCK_LEAK_DECLARE;
IndexScanDesc scan = (IndexScanDesc) PG_GETARG_POINTER(0);
BTScanOpaque so = (BTScanOpaque) scan->opaque;
MIRROREDLOCK_BUFMGR_VERIFY_NO_LOCK_LEAK_ENTER;
if (so->markItemIndex >= 0)
{
/*
* The mark position is on the same page we are currently on. Just
* restore the itemIndex.
*/
so->currPos.itemIndex = so->markItemIndex;
}
else
{
/* we aren't holding any read locks, but gotta drop the pin */
if (BTScanPosIsValid(so->currPos))
{
/* Before leaving current page, deal with any killed items */
if (so->numKilled > 0 &&
so->currPos.buf != so->markPos.buf)
_bt_killitems(scan, false);
ReleaseBuffer(so->currPos.buf);
so->currPos.buf = InvalidBuffer;
}
if (BTScanPosIsValid(so->markPos))
{
/* bump pin on mark buffer for assignment to current buffer */
IncrBufferRefCount(so->markPos.buf);
memcpy(&so->currPos, &so->markPos,
offsetof(BTScanPosData, items[1]) +
so->markPos.lastItem * sizeof(BTScanPosItem));
}
}
MIRROREDLOCK_BUFMGR_VERIFY_NO_LOCK_LEAK_EXIT;
PG_RETURN_VOID();
}
/*
* btgettuple() -- Get the next tuple in the scan.
*/
Datum
btgettuple(PG_FUNCTION_ARGS)
{
MIRROREDLOCK_BUFMGR_VERIFY_NO_LOCK_LEAK_DECLARE;
IndexScanDesc scan = (IndexScanDesc) PG_GETARG_POINTER(0);
ScanDirection dir = (ScanDirection) PG_GETARG_INT32(1);
BTScanOpaque so = (BTScanOpaque) scan->opaque;
bool res;
MIRROREDLOCK_BUFMGR_VERIFY_NO_LOCK_LEAK_ENTER;
/*
* 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 (BTScanPosIsValid(so->currPos))
{
/*
* Check to see if we should kill the previously-fetched tuple.
*/
if (scan->kill_prior_tuple)
{
/*
* Yes, remember it for later. (We'll deal with all such tuples
* at once right before leaving the index page.) The test for
* numKilled overrun is not just paranoia: if the caller reverses
* direction in the indexscan then the same item might get entered
* multiple times. It's not worth trying to optimize that, so we
* don't detect it, but instead just forget any excess entries.
*/
if (so->killedItems == NULL)
so->killedItems = (int *)
palloc(MaxIndexTuplesPerPage * sizeof(int));
if (so->numKilled < MaxIndexTuplesPerPage)
so->killedItems[so->numKilled++] = so->currPos.itemIndex;
}
/*
* Now continue the scan.
*/
res = _bt_next(scan, dir);
}
else
res = _bt_first(scan, dir);
MIRROREDLOCK_BUFMGR_VERIFY_NO_LOCK_LEAK_EXIT;
PG_RETURN_BOOL(res);
}
/*
* btendscan() -- close down a scan
*/
Datum
btendscan(PG_FUNCTION_ARGS)
{
IndexScanDesc scan = (IndexScanDesc) PG_GETARG_POINTER(0);
BTScanOpaque so = (BTScanOpaque) scan->opaque;
/* we aren't holding any read locks, but gotta drop the pins */
if (BTScanPosIsValid(so->currPos))
{
/* Before leaving current page, deal with any killed items */
if (so->numKilled > 0)
_bt_killitems(scan, false);
ReleaseBuffer(so->currPos.buf);
so->currPos.buf = InvalidBuffer;
}
if (BTScanPosIsValid(so->markPos))
{
ReleaseBuffer(so->markPos.buf);
so->markPos.buf = InvalidBuffer;
}
so->markItemIndex = -1;
/* Release storage */
if (so->keyData != NULL)
pfree(so->keyData);
/* so->arrayKeyData and so->arrayKeys are in arrayContext */
if (so->arrayContext != NULL)
MemoryContextDelete(so->arrayContext);
if (so->killedItems != NULL)
pfree(so->killedItems);
if (so->currTuples != NULL)
pfree(so->currTuples);
/* so->markTuples should not be pfree'd, see btrescan */
pfree(so);
PG_RETURN_VOID();
}
/*
* btrescan() -- rescan an index relation
*/
Datum
btrescan(PG_FUNCTION_ARGS)
{
IndexScanDesc scan = (IndexScanDesc) PG_GETARG_POINTER(0);
ScanKey scankey = (ScanKey) PG_GETARG_POINTER(1);
/* remaining arguments are ignored */
BTScanOpaque so = (BTScanOpaque) scan->opaque;
/* we aren't holding any read locks, but gotta drop the pins */
if (BTScanPosIsValid(so->currPos))
{
/* Before leaving current page, deal with any killed items */
if (so->numKilled > 0)
_bt_killitems(scan, false);
ReleaseBuffer(so->currPos.buf);
so->currPos.buf = InvalidBuffer;
}
if (BTScanPosIsValid(so->markPos))
{
ReleaseBuffer(so->markPos.buf);
so->markPos.buf = InvalidBuffer;
}
so->markItemIndex = -1;
/*
* Reset the scan keys. Note that keys ordering stuff moved to _bt_first.
* - vadim 05/05/97
*/
if (scankey && scan->numberOfKeys > 0)
memmove(scan->keyData,
scankey,
scan->numberOfKeys * sizeof(ScanKeyData));
so->numberOfKeys = 0; /* until _bt_preprocess_keys sets it */
PG_RETURN_VOID();
}
/*
* btgettuple() -- Get the next tuple in the scan.
*/
bool
btgettuple(IndexScanDesc scan, ScanDirection dir)
{
BTScanOpaque so = (BTScanOpaque) scan->opaque;
bool res;
/* btree indexes are never lossy */
scan->xs_recheck = false;
/*
* If we have any array keys, initialize them during first call for a
* scan. We can't do this in btrescan because we don't know the scan
* direction at that time.
*/
if (so->numArrayKeys && !BTScanPosIsValid(so->currPos))
{
/* punt if we have any unsatisfiable array keys */
if (so->numArrayKeys < 0)
return false;
_bt_start_array_keys(scan, dir);
}
/* This loop handles advancing to the next array elements, if any */
do
{
/*
* 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
* _bt_first() to get the first item in the scan.
*/
if (!BTScanPosIsValid(so->currPos))
res = _bt_first(scan, dir);
else
{
/*
* Check to see if we should kill the previously-fetched tuple.
*/
if (scan->kill_prior_tuple)
{
/*
* Yes, remember it for later. (We'll deal with all such
* tuples at once right before leaving the index page.) The
* test for numKilled overrun is not just paranoia: if the
* caller reverses direction in the indexscan then the same
* item might get entered multiple times. It's not worth
* trying to optimize that, so we don't detect it, but instead
* just forget any excess entries.
*/
if (so->killedItems == NULL)
so->killedItems = (int *)
palloc(MaxIndexTuplesPerPage * sizeof(int));
if (so->numKilled < MaxIndexTuplesPerPage)
so->killedItems[so->numKilled++] = so->currPos.itemIndex;
}
/*
* Now continue the scan.
*/
res = _bt_next(scan, dir);
}
/* If we have a tuple, return it ... */
if (res)
break;
/* ... otherwise see if we have more array keys to deal with */
} while (so->numArrayKeys && _bt_advance_array_keys(scan, dir));
return res;
}
/*
* btgetmulti() -- construct a HashBitmap.
*/
Datum
btgetmulti(PG_FUNCTION_ARGS)
{
MIRROREDLOCK_BUFMGR_VERIFY_NO_LOCK_LEAK_DECLARE;
IndexScanDesc scan = (IndexScanDesc) PG_GETARG_POINTER(0);
Node *n = (Node *)PG_GETARG_POINTER(1);
HashBitmap *hashBitmap;
BTScanOpaque so = (BTScanOpaque) scan->opaque;
bool res = true;
MIRROREDLOCK_BUFMGR_VERIFY_NO_LOCK_LEAK_ENTER;
if (n == NULL || IsA(n, StreamBitmap))
{
/* XXX should we use less than work_mem for this? */
hashBitmap = tbm_create(work_mem * 1024L);
}
else
{
hashBitmap = (HashBitmap *)n;
}
/* If we haven't started the scan yet, fetch the first page & tuple. */
if (!BTScanPosIsValid(so->currPos))
{
res = _bt_first(scan, ForwardScanDirection);
if (res)
{
/* Save tuple ID, and continue scanning */
tbm_add_tuples(hashBitmap, &(scan->xs_ctup.t_self), 1);
}
}
while (res)
{
/*
* Advance to next tuple within page. This is the same as the
* easy case in _bt_next().
*/
if (++so->currPos.itemIndex > so->currPos.lastItem)
{
/* let _bt_next do the heavy lifting */
res = _bt_next(scan, ForwardScanDirection);
if (!res)
break;
}
/* Save tuple ID, and continue scanning */
tbm_add_tuples(hashBitmap,
&(so->currPos.items[so->currPos.itemIndex].heapTid),
1);
}
if(n && IsA(n, StreamBitmap))
{
stream_add_node((StreamBitmap *)n,
tbm_create_stream_node(hashBitmap), BMS_OR);
PG_RETURN_POINTER(n);
}
MIRROREDLOCK_BUFMGR_VERIFY_NO_LOCK_LEAK_EXIT;
PG_RETURN_POINTER(hashBitmap);
}
/*
* btrestrpos() -- restore scan to last saved position
*/
Datum
btrestrpos(PG_FUNCTION_ARGS)
{
IndexScanDesc scan = (IndexScanDesc) PG_GETARG_POINTER(0);
BTScanOpaque so = (BTScanOpaque) scan->opaque;
/* Restore the marked positions of any array keys */
if (so->numArrayKeys)
_bt_restore_array_keys(scan);
if (so->markItemIndex >= 0)
{
/*
* The scan has never moved to a new___ page since the last mark. Just
* restore the itemIndex.
*
* NB: In this case we can't count on anything in so->markPos to be
* accurate.
*/
so->currPos.itemIndex = so->markItemIndex;
}
else if (so->currPos.currPage == so->markPos.currPage)
{
/*
* so->markItemIndex < 0 but mark and current positions are on the
* same page. This would be an unusual case, where the scan moved to
* a new___ index page after the mark, restored, and later restored again
* without moving off the marked page. It is not clear that this code
* can currently be reached, but it seems better to make this function
* robust for this case than to Assert() or elog() that it can't
* happen.
*
* We neither want to set so->markItemIndex >= 0 (because that could
* cause a later move to a new___ page to redo the memcpy() executions)
* nor re-execute the memcpy() functions for a restore within the same
* page. The previous restore to this page already set everything
* except markPos as it should be.
*/
so->currPos.itemIndex = so->markPos.itemIndex;
}
else
{
/*
* The scan moved to a new___ page after last mark or restore, and we are
* now restoring to the marked page. We aren't holding any read
* locks, but if we're still holding the pin for the current position,
* we must drop it.
*/
if (BTScanPosIsValid(so->currPos))
{
/* Before leaving current page, deal with any killed items */
if (so->numKilled > 0)
_bt_killitems(scan);
BTScanPosUnpinIfPinned(so->currPos);
}
if (BTScanPosIsValid(so->markPos))
{
/* bump pin on mark buffer for assignment to current buffer */
if (BTScanPosIsPinned(so->markPos))
IncrBufferRefCount(so->markPos.buf);
memcpy(&so->currPos, &so->markPos,
offsetof(BTScanPosData, items[1]) +
so->markPos.lastItem * sizeof(BTScanPosItem));
if (so->currTuples)
memcpy(so->currTuples, so->markTuples,
so->markPos.nextTupleOffset);
}
else
BTScanPosInvalidate(so->currPos);
}
PG_RETURN_VOID();
}