/*
* RegisterSnapshotOnOwner
* As above, but use the specified resource owner
*/
Snapshot
RegisterSnapshotOnOwner(Snapshot snapshot, ResourceOwner owner)
{
Snapshot snap;
if (snapshot == InvalidSnapshot)
return InvalidSnapshot;
/* Static snapshot? Create a persistent copy */
snap = snapshot->copied ? snapshot : CopySnapshot(snapshot);
/* and tell resowner.c about it */
ResourceOwnerEnlargeSnapshots(owner);
snap->regd_count++;
ResourceOwnerRememberSnapshot(owner, snap);
if (snap->regd_count == 1)
pairingheap_add(&RegisteredSnapshots, &snap->ph_node);
return snap;
}
/*
* Scan all items on the GiST index page identified by *pageItem, and insert
* them into the queue (or directly to output areas)
*
* scan: index scan we are executing
* pageItem: search queue item identifying an index page to scan
* myDistances: distances array associated with pageItem, or NULL at the root
* tbm: if not NULL, gistgetbitmap's output bitmap
* ntids: if not NULL, gistgetbitmap's output tuple counter
*
* If tbm/ntids aren't NULL, we are doing an amgetbitmap scan, and heap
* tuples should be reported directly into the bitmap. If they are NULL,
* we're doing a plain or ordered indexscan. For a plain indexscan, heap
* tuple TIDs are returned into so->pageData[]. For an ordered indexscan,
* heap tuple TIDs are pushed into individual search queue items. In an
* index-only scan, reconstructed index tuples are returned along with the
* TIDs.
*
* If we detect that the index page has split since we saw its downlink
* in the parent, we push its new right sibling onto the queue so the
* sibling will be processed next.
*/
static void
gistScanPage(IndexScanDesc scan, GISTSearchItem *pageItem, double *myDistances,
TIDBitmap *tbm, int64 *ntids)
{
GISTScanOpaque so = (GISTScanOpaque) scan->opaque;
GISTSTATE *giststate = so->giststate;
Relation r = scan->indexRelation;
Buffer buffer;
Page page;
GISTPageOpaque opaque;
OffsetNumber maxoff;
OffsetNumber i;
MemoryContext oldcxt;
Assert(!GISTSearchItemIsHeap(*pageItem));
buffer = ReadBuffer(scan->indexRelation, pageItem->blkno);
LockBuffer(buffer, GIST_SHARE);
PredicateLockPage(r, BufferGetBlockNumber(buffer), scan->xs_snapshot);
gistcheckpage(scan->indexRelation, buffer);
page = BufferGetPage(buffer);
TestForOldSnapshot(scan->xs_snapshot, r, page);
opaque = GistPageGetOpaque(page);
/*
* Check if we need to follow the rightlink. We need to follow it if the
* page was concurrently split since we visited the parent (in which case
* parentlsn < nsn), or if the system crashed after a page split but
* before the downlink was inserted into the parent.
*/
if (!XLogRecPtrIsInvalid(pageItem->data.parentlsn) &&
(GistFollowRight(page) ||
pageItem->data.parentlsn < GistPageGetNSN(page)) &&
opaque->rightlink != InvalidBlockNumber /* sanity check */ )
{
/* There was a page split, follow right link to add pages */
GISTSearchItem *item;
/* This can't happen when starting at the root */
Assert(myDistances != NULL);
oldcxt = MemoryContextSwitchTo(so->queueCxt);
/* Create new GISTSearchItem for the right sibling index page */
item = palloc(SizeOfGISTSearchItem(scan->numberOfOrderBys));
item->blkno = opaque->rightlink;
item->data.parentlsn = pageItem->data.parentlsn;
/* Insert it into the queue using same distances as for this page */
memcpy(item->distances, myDistances,
sizeof(double) * scan->numberOfOrderBys);
pairingheap_add(so->queue, &item->phNode);
MemoryContextSwitchTo(oldcxt);
}
so->nPageData = so->curPageData = 0;
scan->xs_hitup = NULL; /* might point into pageDataCxt */
if (so->pageDataCxt)
MemoryContextReset(so->pageDataCxt);
/*
* We save the LSN of the page as we read it, so that we know whether it
* safe to apply LP_DEAD hints to the page later. This allows us to drop
* the pin for MVCC scans, which allows vacuum to avoid blocking.
*/
so->curPageLSN = BufferGetLSNAtomic(buffer);
/*
* check all tuples on page
*/
maxoff = PageGetMaxOffsetNumber(page);
for (i = FirstOffsetNumber; i <= maxoff; i = OffsetNumberNext(i))
{
ItemId iid = PageGetItemId(page, i);
IndexTuple it;
bool match;
bool recheck;
bool recheck_distances;
/*
* If the scan specifies not to return killed tuples, then we treat a
* killed tuple as not passing the qual.
*/
if (scan->ignore_killed_tuples && ItemIdIsDead(iid))
continue;
it = (IndexTuple) PageGetItem(page, iid);
/*
* Must call gistindex_keytest in tempCxt, and clean up any leftover
* junk afterward.
*/
oldcxt = MemoryContextSwitchTo(so->giststate->tempCxt);
match = gistindex_keytest(scan, it, page, i,
&recheck, &recheck_distances);
MemoryContextSwitchTo(oldcxt);
MemoryContextReset(so->giststate->tempCxt);
/* Ignore tuple if it doesn't match */
if (!match)
continue;
if (tbm && GistPageIsLeaf(page))
{
/*
* getbitmap scan, so just push heap tuple TIDs into the bitmap
* without worrying about ordering
*/
tbm_add_tuples(tbm, &it->t_tid, 1, recheck);
(*ntids)++;
}
else if (scan->numberOfOrderBys == 0 && GistPageIsLeaf(page))
{
/*
* Non-ordered scan, so report tuples in so->pageData[]
*/
so->pageData[so->nPageData].heapPtr = it->t_tid;
so->pageData[so->nPageData].recheck = recheck;
so->pageData[so->nPageData].offnum = i;
/*
* In an index-only scan, also fetch the data from the tuple. The
* reconstructed tuples are stored in pageDataCxt.
*/
if (scan->xs_want_itup)
{
oldcxt = MemoryContextSwitchTo(so->pageDataCxt);
so->pageData[so->nPageData].recontup =
gistFetchTuple(giststate, r, it);
MemoryContextSwitchTo(oldcxt);
}
so->nPageData++;
}
else
{
/*
* Must push item into search queue. We get here for any lower
* index page, and also for heap tuples if doing an ordered
* search.
*/
GISTSearchItem *item;
oldcxt = MemoryContextSwitchTo(so->queueCxt);
/* Create new GISTSearchItem for this item */
item = palloc(SizeOfGISTSearchItem(scan->numberOfOrderBys));
if (GistPageIsLeaf(page))
{
/* Creating heap-tuple GISTSearchItem */
item->blkno = InvalidBlockNumber;
item->data.heap.heapPtr = it->t_tid;
item->data.heap.recheck = recheck;
item->data.heap.recheckDistances = recheck_distances;
/*
* In an index-only scan, also fetch the data from the tuple.
*/
if (scan->xs_want_itup)
item->data.heap.recontup = gistFetchTuple(giststate, r, it);
}
else
{
/* Creating index-page GISTSearchItem */
item->blkno = ItemPointerGetBlockNumber(&it->t_tid);
/*
* LSN of current page is lsn of parent page for child. We
* only have a shared lock, so we need to get the LSN
* atomically.
*/
item->data.parentlsn = BufferGetLSNAtomic(buffer);
}
/* Insert it into the queue using new distance data */
memcpy(item->distances, so->distances,
sizeof(double) * scan->numberOfOrderBys);
pairingheap_add(so->queue, &item->phNode);
MemoryContextSwitchTo(oldcxt);
}
}
UnlockReleaseBuffer(buffer);
}
/*
* SetTransactionSnapshot
* Set the transaction's snapshot from an imported MVCC snapshot.
*
* Note that this is very closely tied to GetTransactionSnapshot --- it
* must take care of all the same considerations as the first-snapshot case
* in GetTransactionSnapshot.
*/
static void
SetTransactionSnapshot(Snapshot sourcesnap, TransactionId sourcexid,
PGPROC *sourceproc)
{
/* Caller should have checked this already */
Assert(!FirstSnapshotSet);
Assert(pairingheap_is_empty(&RegisteredSnapshots));
Assert(FirstXactSnapshot == NULL);
Assert(!HistoricSnapshotActive());
/*
* Even though we are not going to use the snapshot it computes, we must
* call GetSnapshotData, for two reasons: (1) to be sure that
* CurrentSnapshotData's XID arrays have been allocated, and (2) to update
* RecentXmin and RecentGlobalXmin. (We could alternatively include those
* two variables in exported snapshot files, but it seems better to have
* snapshot importers compute reasonably up-to-date values for them.)
*/
CurrentSnapshot = GetSnapshotData(&CurrentSnapshotData);
/*
* Now copy appropriate fields from the source snapshot.
*/
CurrentSnapshot->xmin = sourcesnap->xmin;
CurrentSnapshot->xmax = sourcesnap->xmax;
CurrentSnapshot->xcnt = sourcesnap->xcnt;
Assert(sourcesnap->xcnt <= GetMaxSnapshotXidCount());
memcpy(CurrentSnapshot->xip, sourcesnap->xip,
sourcesnap->xcnt * sizeof(TransactionId));
CurrentSnapshot->subxcnt = sourcesnap->subxcnt;
Assert(sourcesnap->subxcnt <= GetMaxSnapshotSubxidCount());
memcpy(CurrentSnapshot->subxip, sourcesnap->subxip,
sourcesnap->subxcnt * sizeof(TransactionId));
CurrentSnapshot->suboverflowed = sourcesnap->suboverflowed;
CurrentSnapshot->takenDuringRecovery = sourcesnap->takenDuringRecovery;
/* NB: curcid should NOT be copied, it's a local matter */
/*
* Now we have to fix what GetSnapshotData did with MyPgXact->xmin and
* TransactionXmin. There is a race condition: to make sure we are not
* causing the global xmin to go backwards, we have to test that the
* source transaction is still running, and that has to be done
* atomically. So let procarray.c do it.
*
* Note: in serializable mode, predicate.c will do this a second time. It
* doesn't seem worth contorting the logic here to avoid two calls,
* especially since it's not clear that predicate.c *must* do this.
*/
if (sourceproc != NULL)
{
if (!ProcArrayInstallRestoredXmin(CurrentSnapshot->xmin, sourceproc))
ereport(ERROR,
(errcode(ERRCODE_OBJECT_NOT_IN_PREREQUISITE_STATE),
errmsg("could not import the requested snapshot"),
errdetail("The source transaction is not running anymore.")));
}
else if (!ProcArrayInstallImportedXmin(CurrentSnapshot->xmin, sourcexid))
ereport(ERROR,
(errcode(ERRCODE_OBJECT_NOT_IN_PREREQUISITE_STATE),
errmsg("could not import the requested snapshot"),
errdetail("The source transaction %u is not running anymore.",
sourcexid)));
/*
* In transaction-snapshot mode, the first snapshot must live until end of
* xact, so we must make a copy of it. Furthermore, if we're running in
* serializable mode, predicate.c needs to do its own processing.
*/
if (IsolationUsesXactSnapshot())
{
if (IsolationIsSerializable())
SetSerializableTransactionSnapshot(CurrentSnapshot, sourcexid);
/* Make a saved copy */
CurrentSnapshot = CopySnapshot(CurrentSnapshot);
FirstXactSnapshot = CurrentSnapshot;
/* Mark it as "registered" in FirstXactSnapshot */
FirstXactSnapshot->regd_count++;
pairingheap_add(&RegisteredSnapshots, &FirstXactSnapshot->ph_node);
}
FirstSnapshotSet = true;
}
/*
* GetTransactionSnapshot
* Get the appropriate snapshot for a new query in a transaction.
*
* Note that the return value may point at static storage that will be modified
* by future calls and by CommandCounterIncrement(). Callers should call
* RegisterSnapshot or PushActiveSnapshot on the returned snap if it is to be
* used very long.
*/
Snapshot
GetTransactionSnapshot(void)
{
/*
* Return historic snapshot if doing logical decoding. We'll never need a
* non-historic transaction snapshot in this (sub-)transaction, so there's
* no need to be careful to set one up for later calls to
* GetTransactionSnapshot().
*/
if (HistoricSnapshotActive())
{
Assert(!FirstSnapshotSet);
return HistoricSnapshot;
}
/* First call in transaction? */
if (!FirstSnapshotSet)
{
Assert(pairingheap_is_empty(&RegisteredSnapshots));
Assert(FirstXactSnapshot == NULL);
if (IsInParallelMode())
elog(ERROR,
"cannot take query snapshot during a parallel operation");
/*
* In transaction-snapshot mode, the first snapshot must live until
* end of xact regardless of what the caller does with it, so we must
* make a copy of it rather than returning CurrentSnapshotData
* directly. Furthermore, if we're running in serializable mode,
* predicate.c needs to wrap the snapshot fetch in its own processing.
*/
if (IsolationUsesXactSnapshot())
{
/* First, create the snapshot in CurrentSnapshotData */
if (IsolationIsSerializable())
CurrentSnapshot = GetSerializableTransactionSnapshot(&CurrentSnapshotData);
else
CurrentSnapshot = GetSnapshotData(&CurrentSnapshotData);
/* Make a saved copy */
CurrentSnapshot = CopySnapshot(CurrentSnapshot);
FirstXactSnapshot = CurrentSnapshot;
/* Mark it as "registered" in FirstXactSnapshot */
FirstXactSnapshot->regd_count++;
pairingheap_add(&RegisteredSnapshots, &FirstXactSnapshot->ph_node);
}
else
CurrentSnapshot = GetSnapshotData(&CurrentSnapshotData);
/* Don't allow catalog snapshot to be older than xact snapshot. */
CatalogSnapshotStale = true;
FirstSnapshotSet = true;
return CurrentSnapshot;
}
if (IsolationUsesXactSnapshot())
return CurrentSnapshot;
/* Don't allow catalog snapshot to be older than xact snapshot. */
CatalogSnapshotStale = true;
CurrentSnapshot = GetSnapshotData(&CurrentSnapshotData);
return CurrentSnapshot;
}