/*
* Initializes the BitmapTableScanState, including creation of the
* scan description and the bitmapqualorig.
*/
BitmapTableScanState *
ExecInitBitmapTableScan(BitmapTableScan *node, EState *estate, int eflags)
{
/* check for unsupported flags */
Assert(!(eflags & (EXEC_FLAG_BACKWARD | EXEC_FLAG_MARK)));
/*
* Assert caller didn't ask for an unsafe snapshot --- see comments at
* head of file.
*
* MPP-4703: the MVCC-snapshot restriction is required for correct results.
* our test-mode may deliberately return incorrect results, but that's OK.
*/
Assert(IsMVCCSnapshot(estate->es_snapshot) || gp_select_invisible);
BitmapTableScanState *state = makeNode(BitmapTableScanState);
BitmapTableScanBegin(state, (Plan *) node, estate, eflags);
/*
* initialize child nodes
*
* We do this last because the child nodes will open indexscans on our
* relation's indexes, and we want to be sure we have acquired a lock on
* the relation first.
*/
outerPlanState(state) = ExecInitNode(outerPlan(node), estate, eflags);
initGpmonPktForBitmapTableScan((Plan *)node, &state->ss.ps.gpmon_pkt, estate);
return state;
}
/* ----------------
* index_fetch_heap - get the scan's next heap tuple
*
* The result is a visible heap tuple associated with the index TID most
* recently fetched by index_getnext_tid, or NULL if no more matching tuples
* exist. (There can be more than one matching tuple because of HOT chains,
* although when using an MVCC snapshot it should be impossible for more than
* one such tuple to exist.)
*
* On success, the buffer containing the heap tup is pinned (the pin will be
* dropped in a future index_getnext_tid, index_fetch_heap or index_endscan
* call).
*
* Note: caller must check scan->xs_recheck, and perform rechecking of the
* scan keys if required. We do not do that here because we don't have
* enough information to do it efficiently in the general case.
* ----------------
*/
HeapTuple
index_fetch_heap(IndexScanDesc scan)
{
ItemPointer tid = &scan->xs_ctup.t_self;
bool all_dead = false;
bool got_heap_tuple;
/* We can skip the buffer-switching logic if we're in mid-HOT chain. */
if (!scan->xs_continue_hot)
{
/* Switch to correct buffer if we don't have it already */
Buffer prev_buf = scan->xs_cbuf;
scan->xs_cbuf = ReleaseAndReadBuffer(scan->xs_cbuf,
scan->heapRelation,
ItemPointerGetBlockNumber(tid));
/*
* Prune page, but only if we weren't already on this page
*/
if (prev_buf != scan->xs_cbuf)
heap_page_prune_opt(scan->heapRelation, scan->xs_cbuf);
}
/* Obtain share-lock on the buffer so we can examine visibility */
LockBuffer(scan->xs_cbuf, BUFFER_LOCK_SHARE);
got_heap_tuple = heap_hot_search_buffer(tid, scan->heapRelation,
scan->xs_cbuf,
scan->xs_snapshot,
&scan->xs_ctup,
&all_dead,
!scan->xs_continue_hot);
LockBuffer(scan->xs_cbuf, BUFFER_LOCK_UNLOCK);
if (got_heap_tuple)
{
/*
* Only in a non-MVCC snapshot can more than one member of the HOT
* chain be visible.
*/
scan->xs_continue_hot = !IsMVCCSnapshot(scan->xs_snapshot);
pgstat_count_heap_fetch(scan->indexRelation);
return &scan->xs_ctup;
}
/* We've reached the end of the HOT chain. */
scan->xs_continue_hot = false;
/*
* If we scanned a whole HOT chain and found only dead tuples, tell index
* AM to kill its entry for that TID (this will take effect in the next
* amgettuple call, in index_getnext_tid). We do not do this when in
* recovery because it may violate MVCC to do so. See comments in
* RelationGetIndexScan().
*/
if (!scan->xactStartedInRecovery)
scan->kill_prior_tuple = all_dead;
return NULL;
}
void
table_scan_update_snapshot(TableScanDesc scan, Snapshot snapshot)
{
Assert(IsMVCCSnapshot(snapshot));
RegisterSnapshot(snapshot);
scan->rs_snapshot = snapshot;
scan->rs_temp_snap = true;
}
/*
* systable_recheck_tuple --- recheck visibility of most-recently-fetched tuple
*
* In particular, determine if this tuple would be visible to a catalog scan
* that started now. We don't handle the case of a non-MVCC scan snapshot,
* because no caller needs that yet.
*
* This is useful to test whether an object was deleted while we waited to
* acquire lock on it.
*
* Note: we don't actually *need* the tuple to be passed in, but it's a
* good crosscheck that the caller is interested in the right tuple.
*/
bool
systable_recheck_tuple(SysScanDesc sysscan, HeapTuple tup)
{
Snapshot freshsnap;
bool result;
/*
* Trust that LockBuffer() and HeapTupleSatisfiesMVCC() do not themselves
* acquire snapshots, so we need not register the snapshot. Those
* facilities are too low-level to have any business scanning tables.
*/
freshsnap = GetCatalogSnapshot(RelationGetRelid(sysscan->heap_rel));
if (sysscan->irel)
{
IndexScanDesc scan = sysscan->iscan;
Assert(IsMVCCSnapshot(scan->xs_snapshot));
Assert(tup == &scan->xs_ctup);
Assert(BufferIsValid(scan->xs_cbuf));
/* must hold a buffer lock to call HeapTupleSatisfiesVisibility */
LockBuffer(scan->xs_cbuf, BUFFER_LOCK_SHARE);
result = HeapTupleSatisfiesVisibility(tup, freshsnap, scan->xs_cbuf);
LockBuffer(scan->xs_cbuf, BUFFER_LOCK_UNLOCK);
}
else
{
HeapScanDesc scan = sysscan->scan;
Assert(IsMVCCSnapshot(scan->rs_snapshot));
Assert(tup == &scan->rs_ctup);
Assert(BufferIsValid(scan->rs_cbuf));
/* must hold a buffer lock to call HeapTupleSatisfiesVisibility */
LockBuffer(scan->rs_cbuf, BUFFER_LOCK_SHARE);
result = HeapTupleSatisfiesVisibility(tup, freshsnap, scan->rs_cbuf);
LockBuffer(scan->rs_cbuf, BUFFER_LOCK_UNLOCK);
}
return result;
}
Size
table_parallelscan_estimate(Relation rel, Snapshot snapshot)
{
Size sz = 0;
if (IsMVCCSnapshot(snapshot))
sz = add_size(sz, EstimateSnapshotSpace(snapshot));
else
Assert(snapshot == SnapshotAny);
sz = add_size(sz, rel->rd_tableam->parallelscan_estimate(rel));
return sz;
}
/* ----------------
* index_restrpos - restore a scan position
*
* NOTE: this only restores the internal scan state of the index AM.
* The current result tuple (scan->xs_ctup) doesn't change. See comments
* for ExecRestrPos().
*
* NOTE: in the presence of HOT chains, mark/restore only works correctly
* if the scan's snapshot is MVCC-safe; that ensures that there's at most one
* returnable tuple in each HOT chain, and so restoring the prior state at the
* granularity of the index AM is sufficient. Since the only current user
* of mark/restore functionality is nodeMergejoin.c, this effectively means
* that merge-join plans only work for MVCC snapshots. This could be fixed
* if necessary, but for now it seems unimportant.
* ----------------
*/
void
index_restrpos(IndexScanDesc scan)
{
Assert(IsMVCCSnapshot(scan->xs_snapshot));
SCAN_CHECKS;
CHECK_SCAN_PROCEDURE(amrestrpos);
scan->xs_continue_hot = false;
scan->kill_prior_tuple = false; /* for safety */
scan->indexRelation->rd_amroutine->amrestrpos(scan);
}
/* ----------------
* index_restrpos - restore a scan position
*
* NOTE: this only restores the internal scan state of the index AM.
* The current result tuple (scan->xs_ctup) doesn't change. See comments
* for ExecRestrPos().
*
* NOTE: in the presence of HOT chains, mark/restore only works correctly
* if the scan's snapshot is MVCC-safe; that ensures that there's at most one
* returnable tuple in each HOT chain, and so restoring the prior state at the
* granularity of the index AM is sufficient. Since the only current user
* of mark/restore functionality is nodeMergejoin.c, this effectively means
* that merge-join plans only work for MVCC snapshots. This could be fixed
* if necessary, but for now it seems unimportant.
* ----------------
*/
void
index_restrpos(IndexScanDesc scan)
{
FmgrInfo *procedure;
Assert(IsMVCCSnapshot(scan->xs_snapshot));
SCAN_CHECKS;
GET_SCAN_PROCEDURE(amrestrpos);
scan->xs_continue_hot = false;
scan->kill_prior_tuple = false; /* for safety */
FunctionCall1(procedure, PointerGetDatum(scan));
}
void
table_parallelscan_initialize(Relation rel, ParallelTableScanDesc pscan,
Snapshot snapshot)
{
Size snapshot_off = rel->rd_tableam->parallelscan_initialize(rel, pscan);
pscan->phs_snapshot_off = snapshot_off;
if (IsMVCCSnapshot(snapshot))
{
SerializeSnapshot(snapshot, (char *) pscan + pscan->phs_snapshot_off);
pscan->phs_snapshot_any = false;
}
else
{
Assert(snapshot == SnapshotAny);
pscan->phs_snapshot_any = true;
}
}
/* ----------------------------------------------------------------
* ExecInitBitmapHeapScan
*
* Initializes the scan's state information.
* ----------------------------------------------------------------
*/
BitmapHeapScanState *
ExecInitBitmapHeapScan(BitmapHeapScan *node, EState *estate, int eflags)
{
BitmapHeapScanState *scanstate;
Relation currentRelation;
/* check for unsupported flags */
Assert(!(eflags & (EXEC_FLAG_BACKWARD | EXEC_FLAG_MARK)));
/*
* Assert caller didn't ask for an unsafe snapshot --- see comments at
* head of file.
*/
Assert(IsMVCCSnapshot(estate->es_snapshot));
/*
* create state structure
*/
scanstate = makeNode(BitmapHeapScanState);
scanstate->ss.ps.plan = (Plan *) node;
scanstate->ss.ps.state = estate;
scanstate->tbm = NULL;
scanstate->tbmiterator = NULL;
scanstate->tbmres = NULL;
scanstate->prefetch_iterator = NULL;
scanstate->prefetch_pages = 0;
scanstate->prefetch_target = 0;
/*
* Miscellaneous initialization
*
* create expression context for node
*/
ExecAssignExprContext(estate, &scanstate->ss.ps);
scanstate->ss.ps.ps_TupFromTlist = false;
/*
* initialize child expressions
*/
scanstate->ss.ps.targetlist = (List *)
ExecInitExpr((Expr *) node->scan.plan.targetlist,
(PlanState *) scanstate);
scanstate->ss.ps.qual = (List *)
ExecInitExpr((Expr *) node->scan.plan.qual,
(PlanState *) scanstate);
scanstate->bitmapqualorig = (List *)
ExecInitExpr((Expr *) node->bitmapqualorig,
(PlanState *) scanstate);
/*
* tuple table initialization
*/
ExecInitResultTupleSlot(estate, &scanstate->ss.ps);
ExecInitScanTupleSlot(estate, &scanstate->ss);
/*
* open the base relation and acquire appropriate lock on it.
*/
currentRelation = ExecOpenScanRelation(estate, node->scan.scanrelid);
scanstate->ss.ss_currentRelation = currentRelation;
/*
* Even though we aren't going to do a conventional seqscan, it is useful
* to create a HeapScanDesc --- most of the fields in it are usable.
*/
scanstate->ss.ss_currentScanDesc = heap_beginscan_bm(currentRelation,
estate->es_snapshot,
0,
NULL);
/*
* get the scan type from the relation descriptor.
*/
ExecAssignScanType(&scanstate->ss, RelationGetDescr(currentRelation));
/*
* Initialize result tuple type and projection info.
*/
ExecAssignResultTypeFromTL(&scanstate->ss.ps);
ExecAssignScanProjectionInfo(&scanstate->ss);
/*
* initialize child nodes
*
* We do this last because the child nodes will open indexscans on our
* relation's indexes, and we want to be sure we have acquired a lock on
* the relation first.
*/
outerPlanState(scanstate) = ExecInitNode(outerPlan(node), estate, eflags);
/*
* all done.
*/
return scanstate;
}
/* ----------------------------------------------------------------
* ExecInitBitmapHeapScan
*
* Initializes the scan's state information.
* ----------------------------------------------------------------
*/
BitmapHeapScanState *
ExecInitBitmapHeapScan(BitmapHeapScan *node, EState *estate, int eflags)
{
BitmapHeapScanState *scanstate;
Relation currentRelation;
int io_concurrency;
/* check for unsupported flags */
Assert(!(eflags & (EXEC_FLAG_BACKWARD | EXEC_FLAG_MARK)));
/*
* Assert caller didn't ask for an unsafe snapshot --- see comments at
* head of file.
*/
Assert(IsMVCCSnapshot(estate->es_snapshot));
/*
* create state structure
*/
scanstate = makeNode(BitmapHeapScanState);
scanstate->ss.ps.plan = (Plan *) node;
scanstate->ss.ps.state = estate;
scanstate->tbm = NULL;
scanstate->tbmiterator = NULL;
scanstate->tbmres = NULL;
scanstate->exact_pages = 0;
scanstate->lossy_pages = 0;
scanstate->prefetch_iterator = NULL;
scanstate->prefetch_pages = 0;
scanstate->prefetch_target = 0;
/* may be updated below */
scanstate->prefetch_maximum = target_prefetch_pages;
/*
* Miscellaneous initialization
*
* create expression context for node
*/
ExecAssignExprContext(estate, &scanstate->ss.ps);
scanstate->ss.ps.ps_TupFromTlist = false;
/*
* initialize child expressions
*/
scanstate->ss.ps.targetlist = (List *)
ExecInitExpr((Expr *) node->scan.plan.targetlist,
(PlanState *) scanstate);
scanstate->ss.ps.qual = (List *)
ExecInitExpr((Expr *) node->scan.plan.qual,
(PlanState *) scanstate);
scanstate->bitmapqualorig = (List *)
ExecInitExpr((Expr *) node->bitmapqualorig,
(PlanState *) scanstate);
/*
* tuple table initialization
*/
ExecInitResultTupleSlot(estate, &scanstate->ss.ps);
ExecInitScanTupleSlot(estate, &scanstate->ss);
/*
* open the base relation and acquire appropriate lock on it.
*/
currentRelation = ExecOpenScanRelation(estate, node->scan.scanrelid, eflags);
/*
* Determine the maximum for prefetch_target. If the tablespace has a
* specific IO concurrency set, use that to compute the corresponding
* maximum value; otherwise, we already initialized to the value computed
* by the GUC machinery.
*/
io_concurrency =
get_tablespace_io_concurrency(currentRelation->rd_rel->reltablespace);
if (io_concurrency != effective_io_concurrency)
{
double maximum;
if (ComputeIoConcurrency(io_concurrency, &maximum))
scanstate->prefetch_maximum = rint(maximum);
}
scanstate->ss.ss_currentRelation = currentRelation;
/*
* Even though we aren't going to do a conventional seqscan, it is useful
* to create a HeapScanDesc --- most of the fields in it are usable.
*/
scanstate->ss.ss_currentScanDesc = heap_beginscan_bm(currentRelation,
estate->es_snapshot,
0,
NULL);
/*
* get the scan type from the relation descriptor.
*/
ExecAssignScanType(&scanstate->ss, RelationGetDescr(currentRelation));
/*
* Initialize result tuple type and projection info.
*/
ExecAssignResultTypeFromTL(&scanstate->ss.ps);
ExecAssignScanProjectionInfo(&scanstate->ss);
/*
* initialize child nodes
*
* We do this last because the child nodes will open indexscans on our
* relation's indexes, and we want to be sure we have acquired a lock on
* the relation first.
*/
outerPlanState(scanstate) = ExecInitNode(outerPlan(node), estate, eflags);
/*
* all done.
*/
return scanstate;
}
/* ----------------
* index_getnext - get the next heap tuple from a scan
*
* The result is the next heap tuple satisfying the scan keys and the
* snapshot, or NULL if no more matching tuples exist. On success,
* the buffer containing the heap tuple is pinned (the pin will be dropped
* at the next index_getnext or index_endscan).
*
* Note: caller must check scan->xs_recheck, and perform rechecking of the
* scan keys if required. We do not do that here because we don't have
* enough information to do it efficiently in the general case.
* ----------------
*/
HeapTuple
index_getnext(IndexScanDesc scan, ScanDirection direction)
{
HeapTuple heapTuple = &scan->xs_ctup;
ItemPointer tid = &heapTuple->t_self;
FmgrInfo *procedure;
SCAN_CHECKS;
GET_SCAN_PROCEDURE(amgettuple);
Assert(TransactionIdIsValid(RecentGlobalXmin));
/*
* We always reset xs_hot_dead; if we are here then either we are just
* starting the scan, or we previously returned a visible tuple, and in
* either case it's inappropriate to kill the prior index entry.
*/
scan->xs_hot_dead = false;
for (;;)
{
OffsetNumber offnum;
bool at_chain_start;
Page dp;
if (scan->xs_next_hot != InvalidOffsetNumber)
{
/*
* We are resuming scan of a HOT chain after having returned an
* earlier member. Must still hold pin on current heap page.
*/
Assert(BufferIsValid(scan->xs_cbuf));
Assert(ItemPointerGetBlockNumber(tid) ==
BufferGetBlockNumber(scan->xs_cbuf));
Assert(TransactionIdIsValid(scan->xs_prev_xmax));
offnum = scan->xs_next_hot;
at_chain_start = false;
scan->xs_next_hot = InvalidOffsetNumber;
}
else
{
bool found;
Buffer prev_buf;
/*
* If we scanned a whole HOT chain and found only dead tuples,
* tell index AM to kill its entry for that TID. We do not do this
* when in recovery because it may violate MVCC to do so. see
* comments in RelationGetIndexScan().
*/
if (!scan->xactStartedInRecovery)
scan->kill_prior_tuple = scan->xs_hot_dead;
/*
* The AM's gettuple proc finds the next index entry matching the
* scan keys, and puts the TID in xs_ctup.t_self (ie, *tid). It
* should also set scan->xs_recheck, though we pay no attention to
* that here.
*/
found = DatumGetBool(FunctionCall2(procedure,
PointerGetDatum(scan),
Int32GetDatum(direction)));
/* Reset kill flag immediately for safety */
scan->kill_prior_tuple = false;
/* If we're out of index entries, break out of outer loop */
if (!found)
break;
pgstat_count_index_tuples(scan->indexRelation, 1);
/* Switch to correct buffer if we don't have it already */
prev_buf = scan->xs_cbuf;
scan->xs_cbuf = ReleaseAndReadBuffer(scan->xs_cbuf,
scan->heapRelation,
ItemPointerGetBlockNumber(tid));
/*
* Prune page, but only if we weren't already on this page
*/
if (prev_buf != scan->xs_cbuf)
heap_page_prune_opt(scan->heapRelation, scan->xs_cbuf,
RecentGlobalXmin);
/* Prepare to scan HOT chain starting at index-referenced offnum */
offnum = ItemPointerGetOffsetNumber(tid);
at_chain_start = true;
/* We don't know what the first tuple's xmin should be */
scan->xs_prev_xmax = InvalidTransactionId;
/* Initialize flag to detect if all entries are dead */
scan->xs_hot_dead = true;
}
/* Obtain share-lock on the buffer so we can examine visibility */
LockBuffer(scan->xs_cbuf, BUFFER_LOCK_SHARE);
dp = (Page) BufferGetPage(scan->xs_cbuf);
/* Scan through possible multiple members of HOT-chain */
for (;;)
{
ItemId lp;
ItemPointer ctid;
bool valid;
/* check for bogus TID */
if (offnum < FirstOffsetNumber ||
offnum > PageGetMaxOffsetNumber(dp))
break;
lp = PageGetItemId(dp, offnum);
/* check for unused, dead, or redirected items */
if (!ItemIdIsNormal(lp))
{
/* We should only see a redirect at start of chain */
if (ItemIdIsRedirected(lp) && at_chain_start)
{
/* Follow the redirect */
offnum = ItemIdGetRedirect(lp);
at_chain_start = false;
continue;
}
/* else must be end of chain */
break;
}
/*
* We must initialize all of *heapTuple (ie, scan->xs_ctup) since
* it is returned to the executor on success.
*/
heapTuple->t_data = (HeapTupleHeader) PageGetItem(dp, lp);
heapTuple->t_len = ItemIdGetLength(lp);
ItemPointerSetOffsetNumber(tid, offnum);
heapTuple->t_tableOid = RelationGetRelid(scan->heapRelation);
ctid = &heapTuple->t_data->t_ctid;
/*
* Shouldn't see a HEAP_ONLY tuple at chain start. (This test
* should be unnecessary, since the chain root can't be removed
* while we have pin on the index entry, but let's make it
* anyway.)
*/
if (at_chain_start && HeapTupleIsHeapOnly(heapTuple))
break;
/*
* The xmin should match the previous xmax value, else chain is
* broken. (Note: this test is not optional because it protects
* us against the case where the prior chain member's xmax aborted
* since we looked at it.)
*/
if (TransactionIdIsValid(scan->xs_prev_xmax) &&
!TransactionIdEquals(scan->xs_prev_xmax,
HeapTupleHeaderGetXmin(heapTuple->t_data)))
break;
/* If it's visible per the snapshot, we must return it */
valid = HeapTupleSatisfiesVisibility(heapTuple, scan->xs_snapshot,
scan->xs_cbuf);
CheckForSerializableConflictOut(valid, scan->heapRelation,
heapTuple, scan->xs_cbuf);
if (valid)
{
/*
* If the snapshot is MVCC, we know that it could accept at
* most one member of the HOT chain, so we can skip examining
* any more members. Otherwise, check for continuation of the
* HOT-chain, and set state for next time.
*/
if (IsMVCCSnapshot(scan->xs_snapshot)
&& !IsolationIsSerializable())
scan->xs_next_hot = InvalidOffsetNumber;
else if (HeapTupleIsHotUpdated(heapTuple))
{
Assert(ItemPointerGetBlockNumber(ctid) ==
ItemPointerGetBlockNumber(tid));
scan->xs_next_hot = ItemPointerGetOffsetNumber(ctid);
scan->xs_prev_xmax = HeapTupleHeaderGetXmax(heapTuple->t_data);
}
else
scan->xs_next_hot = InvalidOffsetNumber;
PredicateLockTuple(scan->heapRelation, heapTuple);
LockBuffer(scan->xs_cbuf, BUFFER_LOCK_UNLOCK);
pgstat_count_heap_fetch(scan->indexRelation);
return heapTuple;
}
/*
* If we can't see it, maybe no one else can either. Check to see
* if the tuple is dead to all transactions. If we find that all
* the tuples in the HOT chain are dead, we'll signal the index AM
* to not return that TID on future indexscans.
*/
if (scan->xs_hot_dead &&
HeapTupleSatisfiesVacuum(heapTuple->t_data, RecentGlobalXmin,
scan->xs_cbuf) != HEAPTUPLE_DEAD)
scan->xs_hot_dead = false;
/*
* Check to see if HOT chain continues past this tuple; if so
* fetch the next offnum (we don't bother storing it into
* xs_next_hot, but must store xs_prev_xmax), and loop around.
*/
if (HeapTupleIsHotUpdated(heapTuple))
{
Assert(ItemPointerGetBlockNumber(ctid) ==
ItemPointerGetBlockNumber(tid));
offnum = ItemPointerGetOffsetNumber(ctid);
at_chain_start = false;
scan->xs_prev_xmax = HeapTupleHeaderGetXmax(heapTuple->t_data);
}
else
break; /* end of chain */
} /* loop over a single HOT chain */
LockBuffer(scan->xs_cbuf, BUFFER_LOCK_UNLOCK);
/* Loop around to ask index AM for another TID */
scan->xs_next_hot = InvalidOffsetNumber;
}
/* Release any held pin on a heap page */
if (BufferIsValid(scan->xs_cbuf))
{
ReleaseBuffer(scan->xs_cbuf);
scan->xs_cbuf = InvalidBuffer;
}
return NULL; /* failure exit */
}
/* ----------------
* index_getnext - get the next heap tuple from a scan
*
* The result is the next heap tuple satisfying the scan keys and the
* snapshot, or NULL if no more matching tuples exist. On success,
* the buffer containing the heap tuple is pinned (the pin will be dropped
* at the next index_getnext or index_endscan).
*
* Note: caller must check scan->xs_recheck, and perform rechecking of the
* scan keys if required. We do not do that here because we don't have
* enough information to do it efficiently in the general case.
* ----------------
*/
HeapTuple
index_getnext(IndexScanDesc scan, ScanDirection direction)
{
HeapTuple heapTuple = &scan->xs_ctup;
ItemPointer tid = &heapTuple->t_self;
FmgrInfo *procedure;
bool all_dead = false;
SCAN_CHECKS;
GET_SCAN_PROCEDURE(amgettuple);
Assert(TransactionIdIsValid(RecentGlobalXmin));
for (;;)
{
bool got_heap_tuple;
if (scan->xs_continue_hot)
{
/*
* We are resuming scan of a HOT chain after having returned an
* earlier member. Must still hold pin on current heap page.
*/
Assert(BufferIsValid(scan->xs_cbuf));
Assert(ItemPointerGetBlockNumber(tid) ==
BufferGetBlockNumber(scan->xs_cbuf));
}
else
{
bool found;
Buffer prev_buf;
/*
* If we scanned a whole HOT chain and found only dead tuples,
* tell index AM to kill its entry for that TID. We do not do this
* when in recovery because it may violate MVCC to do so. see
* comments in RelationGetIndexScan().
*/
if (!scan->xactStartedInRecovery)
scan->kill_prior_tuple = all_dead;
/*
* The AM's gettuple proc finds the next index entry matching the
* scan keys, and puts the TID in xs_ctup.t_self (ie, *tid). It
* should also set scan->xs_recheck, though we pay no attention to
* that here.
*/
found = DatumGetBool(FunctionCall2(procedure,
PointerGetDatum(scan),
Int32GetDatum(direction)));
/* Reset kill flag immediately for safety */
scan->kill_prior_tuple = false;
/* If we're out of index entries, break out of outer loop */
if (!found)
break;
pgstat_count_index_tuples(scan->indexRelation, 1);
/* Switch to correct buffer if we don't have it already */
prev_buf = scan->xs_cbuf;
scan->xs_cbuf = ReleaseAndReadBuffer(scan->xs_cbuf,
scan->heapRelation,
ItemPointerGetBlockNumber(tid));
/*
* Prune page, but only if we weren't already on this page
*/
if (prev_buf != scan->xs_cbuf)
heap_page_prune_opt(scan->heapRelation, scan->xs_cbuf,
RecentGlobalXmin);
}
/* Obtain share-lock on the buffer so we can examine visibility */
LockBuffer(scan->xs_cbuf, BUFFER_LOCK_SHARE);
got_heap_tuple = heap_hot_search_buffer(tid, scan->heapRelation,
scan->xs_cbuf,
scan->xs_snapshot,
&scan->xs_ctup,
&all_dead,
!scan->xs_continue_hot);
LockBuffer(scan->xs_cbuf, BUFFER_LOCK_UNLOCK);
if (got_heap_tuple)
{
/*
* Only in a non-MVCC snapshot can more than one member of the
* HOT chain be visible.
*/
scan->xs_continue_hot = !IsMVCCSnapshot(scan->xs_snapshot);
pgstat_count_heap_fetch(scan->indexRelation);
return heapTuple;
}
/* Loop around to ask index AM for another TID */
scan->xs_continue_hot = false;
}
/* Release any held pin on a heap page */
if (BufferIsValid(scan->xs_cbuf))
{
ReleaseBuffer(scan->xs_cbuf);
scan->xs_cbuf = InvalidBuffer;
}
return NULL; /* failure exit */
}
/* ----------------------------------------------------------------
* ExecInitBitmapHeapScan
*
* Initializes the scan's state information.
* ----------------------------------------------------------------
*/
BitmapHeapScanState *
ExecInitBitmapHeapScan(BitmapHeapScan *node, EState *estate, int eflags)
{
BitmapHeapScanState *scanstate;
Relation currentRelation;
/* check for unsupported flags */
Assert(!(eflags & (EXEC_FLAG_BACKWARD | EXEC_FLAG_MARK)));
/*
* Assert caller didn't ask for an unsafe snapshot --- see comments at
* head of file.
*/
Assert(IsMVCCSnapshot(estate->es_snapshot));
/*
* create state structure
*/
scanstate = makeNode(BitmapHeapScanState);
scanstate->ss.ps.plan = (Plan *) node;
scanstate->ss.ps.state = estate;
scanstate->tbm = NULL;
scanstate->tbmres = NULL;
/*
* Miscellaneous initialization
*
* create expression context for node
*/
ExecAssignExprContext(estate, &scanstate->ss.ps);
scanstate->ss.ps.ps_TupFromTlist = false;
/*
* initialize child expressions
*/
scanstate->ss.ps.targetlist = (List *)
ExecInitExpr((Expr *) node->scan.plan.targetlist,
(PlanState *) scanstate);
scanstate->ss.ps.qual = (List *)
ExecInitExpr((Expr *) node->scan.plan.qual,
(PlanState *) scanstate);
scanstate->bitmapqualorig = (List *)
ExecInitExpr((Expr *) node->bitmapqualorig,
(PlanState *) scanstate);
#define BITMAPHEAPSCAN_NSLOTS 2
/*
* tuple table initialization
*/
ExecInitResultTupleSlot(estate, &scanstate->ss.ps);
ExecInitScanTupleSlot(estate, &scanstate->ss);
/*
* open the base relation and acquire appropriate lock on it.
*/
currentRelation = ExecOpenScanRelation(estate, node->scan.scanrelid);
scanstate->ss.ss_currentRelation = currentRelation;
/*
* Even though we aren't going to do a conventional seqscan, it is useful
* to create a HeapScanDesc --- this checks the relation size and sets up
* statistical infrastructure for us.
*/
scanstate->ss.ss_currentScanDesc = heap_beginscan(currentRelation,
estate->es_snapshot,
0,
NULL);
/*
* One problem is that heap_beginscan counts a "sequential scan" start,
* when we actually aren't doing any such thing. Reverse out the added
* scan count. (Eventually we may want to count bitmap scans separately.)
*/
pgstat_discount_heap_scan(&scanstate->ss.ss_currentScanDesc->rs_pgstat_info);
/*
* get the scan type from the relation descriptor.
*/
ExecAssignScanType(&scanstate->ss, RelationGetDescr(currentRelation));
/*
* Initialize result tuple type and projection info.
*/
ExecAssignResultTypeFromTL(&scanstate->ss.ps);
ExecAssignScanProjectionInfo(&scanstate->ss);
/*
* initialize child nodes
*
* We do this last because the child nodes will open indexscans on our
* relation's indexes, and we want to be sure we have acquired a lock on
* the relation first.
*/
outerPlanState(scanstate) = ExecInitNode(outerPlan(node), estate, eflags);
/*
* all done.
*/
return scanstate;
}
/* ----------------------------------------------------------------
* ExecInitBitmapHeapScan
*
* Initializes the scan's state information.
* ----------------------------------------------------------------
*/
BitmapHeapScanState *
ExecInitBitmapHeapScan(BitmapHeapScan *node, EState *estate, int eflags)
{
BitmapHeapScanState *scanstate;
Relation currentRelation;
int io_concurrency;
/* check for unsupported flags */
Assert(!(eflags & (EXEC_FLAG_BACKWARD | EXEC_FLAG_MARK)));
/*
* Assert caller didn't ask for an unsafe snapshot --- see comments at
* head of file.
*/
Assert(IsMVCCSnapshot(estate->es_snapshot));
/*
* create state structure
*/
scanstate = makeNode(BitmapHeapScanState);
scanstate->ss.ps.plan = (Plan *) node;
scanstate->ss.ps.state = estate;
scanstate->ss.ps.ExecProcNode = ExecBitmapHeapScan;
scanstate->tbm = NULL;
scanstate->tbmiterator = NULL;
scanstate->tbmres = NULL;
scanstate->skip_fetch = false;
scanstate->vmbuffer = InvalidBuffer;
scanstate->pvmbuffer = InvalidBuffer;
scanstate->exact_pages = 0;
scanstate->lossy_pages = 0;
scanstate->prefetch_iterator = NULL;
scanstate->prefetch_pages = 0;
scanstate->prefetch_target = 0;
/* may be updated below */
scanstate->prefetch_maximum = target_prefetch_pages;
scanstate->pscan_len = 0;
scanstate->initialized = false;
scanstate->shared_tbmiterator = NULL;
scanstate->shared_prefetch_iterator = NULL;
scanstate->pstate = NULL;
/*
* We can potentially skip fetching heap pages if we do not need any
* columns of the table, either for checking non-indexable quals or for
* returning data. This test is a bit simplistic, as it checks the
* stronger condition that there's no qual or return tlist at all. But in
* most cases it's probably not worth working harder than that.
*/
scanstate->can_skip_fetch = (node->scan.plan.qual == NIL &&
node->scan.plan.targetlist == NIL);
/*
* Miscellaneous initialization
*
* create expression context for node
*/
ExecAssignExprContext(estate, &scanstate->ss.ps);
/*
* open the scan relation
*/
currentRelation = ExecOpenScanRelation(estate, node->scan.scanrelid, eflags);
/*
* initialize child nodes
*/
outerPlanState(scanstate) = ExecInitNode(outerPlan(node), estate, eflags);
/*
* get the scan type from the relation descriptor.
*/
ExecInitScanTupleSlot(estate, &scanstate->ss,
RelationGetDescr(currentRelation),
&TTSOpsBufferHeapTuple);
/*
* Initialize result type and projection.
*/
ExecInitResultTypeTL(&scanstate->ss.ps);
ExecAssignScanProjectionInfo(&scanstate->ss);
/*
* initialize child expressions
*/
scanstate->ss.ps.qual =
ExecInitQual(node->scan.plan.qual, (PlanState *) scanstate);
scanstate->bitmapqualorig =
ExecInitQual(node->bitmapqualorig, (PlanState *) scanstate);
/*
* Determine the maximum for prefetch_target. If the tablespace has a
* specific IO concurrency set, use that to compute the corresponding
* maximum value; otherwise, we already initialized to the value computed
* by the GUC machinery.
*/
io_concurrency =
get_tablespace_io_concurrency(currentRelation->rd_rel->reltablespace);
if (io_concurrency != effective_io_concurrency)
{
double maximum;
if (ComputeIoConcurrency(io_concurrency, &maximum))
scanstate->prefetch_maximum = rint(maximum);
}
scanstate->ss.ss_currentRelation = currentRelation;
/*
* Even though we aren't going to do a conventional seqscan, it is useful
* to create a HeapScanDesc --- most of the fields in it are usable.
*/
scanstate->ss.ss_currentScanDesc = heap_beginscan_bm(currentRelation,
estate->es_snapshot,
0,
NULL);
/*
* all done.
*/
return scanstate;
}
