/* ----------------
* 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))
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 */
}
void
heap2_desc(StringInfo buf, XLogReaderState *record)
{
char *rec = XLogRecGetData(record);
uint8 info = XLogRecGetInfo(record) & ~XLR_INFO_MASK;
info &= XLOG_HEAP_OPMASK;
if (info == XLOG_HEAP2_CLEAN)
{
xl_heap_clean *xlrec = (xl_heap_clean *) rec;
appendStringInfo(buf, "remxid %u", xlrec->latestRemovedXid);
}
else if (info == XLOG_HEAP2_FREEZE_PAGE)
{
xl_heap_freeze_page *xlrec = (xl_heap_freeze_page *) rec;
appendStringInfo(buf, "cutoff xid %u ntuples %u",
xlrec->cutoff_xid, xlrec->ntuples);
}
else if (info == XLOG_HEAP2_CLEANUP_INFO)
{
xl_heap_cleanup_info *xlrec = (xl_heap_cleanup_info *) rec;
appendStringInfo(buf, "remxid %u", xlrec->latestRemovedXid);
}
else if (info == XLOG_HEAP2_VISIBLE)
{
xl_heap_visible *xlrec = (xl_heap_visible *) rec;
appendStringInfo(buf, "cutoff xid %u flags %d",
xlrec->cutoff_xid, xlrec->flags);
}
else if (info == XLOG_HEAP2_MULTI_INSERT)
{
xl_heap_multi_insert *xlrec = (xl_heap_multi_insert *) rec;
appendStringInfo(buf, "%d tuples", xlrec->ntuples);
}
else if (info == XLOG_HEAP2_LOCK_UPDATED)
{
xl_heap_lock_updated *xlrec = (xl_heap_lock_updated *) rec;
appendStringInfo(buf, "off %u: xmax %u: flags %u ",
xlrec->offnum, xlrec->xmax, xlrec->flags);
out_infobits(buf, xlrec->infobits_set);
}
else if (info == XLOG_HEAP2_NEW_CID)
{
xl_heap_new_cid *xlrec = (xl_heap_new_cid *) rec;
appendStringInfo(buf, "rel %u/%u/%u; tid %u/%u",
xlrec->target_node.spcNode,
xlrec->target_node.dbNode,
xlrec->target_node.relNode,
ItemPointerGetBlockNumber(&(xlrec->target_tid)),
ItemPointerGetOffsetNumber(&(xlrec->target_tid)));
appendStringInfo(buf, "; cmin: %u, cmax: %u, combo: %u",
xlrec->cmin, xlrec->cmax, xlrec->combocid);
}
}
/* ----------------------------------------------------------------
* IndexOnlyNext
*
* Retrieve a tuple from the IndexOnlyScan node's index.
* ----------------------------------------------------------------
*/
static TupleTableSlot *
IndexOnlyNext(IndexOnlyScanState *node)
{
EState *estate;
ExprContext *econtext;
ScanDirection direction;
IndexScanDesc scandesc;
TupleTableSlot *slot;
ItemPointer tid;
/*
* extract necessary information from index scan node
*/
estate = node->ss.ps.state;
direction = estate->es_direction;
/* flip direction if this is an overall backward scan */
if (ScanDirectionIsBackward(((IndexOnlyScan *) node->ss.ps.plan)->indexorderdir))
{
if (ScanDirectionIsForward(direction))
direction = BackwardScanDirection;
else if (ScanDirectionIsBackward(direction))
direction = ForwardScanDirection;
}
scandesc = node->ioss_ScanDesc;
econtext = node->ss.ps.ps_ExprContext;
slot = node->ss.ss_ScanTupleSlot;
/*
* OK, now that we have what we need, fetch the next tuple.
*/
while ((tid = index_getnext_tid(scandesc, direction)) != NULL)
{
HeapTuple tuple = NULL;
/*
* We can skip the heap fetch if the TID references a heap page on
* which all tuples are known visible to everybody. In any case,
* we'll use the index tuple not the heap tuple as the data source.
*
* Note on Memory Ordering Effects: visibilitymap_test does not lock
* the visibility map buffer, and therefore the result we read here
* could be slightly stale. However, it can't be stale enough to
* matter.
*
* We need to detect clearing a VM bit due to an insert right away,
* because the tuple is present in the index page but not visible. The
* reading of the TID by this scan (using a shared lock on the index
* buffer) is serialized with the insert of the TID into the index
* (using an exclusive lock on the index buffer). Because the VM bit
* is cleared before updating the index, and locking/unlocking of the
* index page acts as a full memory barrier, we are sure to see the
* cleared bit if we see a recently-inserted TID.
*
* Deletes do not update the index page (only VACUUM will clear out
* the TID), so the clearing of the VM bit by a delete is not
* serialized with this test below, and we may see a value that is
* significantly stale. However, we don't care about the delete right
* away, because the tuple is still visible until the deleting
* transaction commits or the statement ends (if it's our
* transaction). In either case, the lock on the VM buffer will have
* been released (acting as a write barrier) after clearing the bit.
* And for us to have a snapshot that includes the deleting
* transaction (making the tuple invisible), we must have acquired
* ProcArrayLock after that time, acting as a read barrier.
*
* It's worth going through this complexity to avoid needing to lock
* the VM buffer, which could cause significant contention.
*/
if (!visibilitymap_test(scandesc->heapRelation,
ItemPointerGetBlockNumber(tid),
&node->ioss_VMBuffer))
{
/*
* Rats, we have to visit the heap to check visibility.
*/
node->ioss_HeapFetches++;
tuple = index_fetch_heap(scandesc);
if (tuple == NULL)
continue; /* no visible tuple, try next index entry */
/*
* Only MVCC snapshots are supported here, so there should be no
* need to keep following the HOT chain once a visible entry has
* been found. If we did want to allow that, we'd need to keep
* more state to remember not to call index_getnext_tid next time.
*/
if (scandesc->xs_continue_hot)
elog(ERROR, "non-MVCC snapshots are not supported in index-only scans");
/*
* Note: at this point we are holding a pin on the heap page, as
* recorded in scandesc->xs_cbuf. We could release that pin now,
* but it's not clear whether it's a win to do so. The next index
* entry might require a visit to the same heap page.
*/
}
/*
* Fill the scan tuple slot with data from the index.
*/
StoreIndexTuple(slot, scandesc->xs_itup, scandesc->xs_itupdesc);
/*
* If the index was lossy, we have to recheck the index quals.
* (Currently, this can never happen, but we should support the case
* for possible future use, eg with GiST indexes.)
*/
if (scandesc->xs_recheck)
{
econtext->ecxt_scantuple = slot;
ResetExprContext(econtext);
if (!ExecQual(node->indexqual, econtext, false))
{
/* Fails recheck, so drop it and loop back for another */
InstrCountFiltered2(node, 1);
continue;
}
}
/*
* We don't currently support rechecking ORDER BY distances. (In
* principle, if the index can support retrieval of the originally
* indexed value, it should be able to produce an exact distance
* calculation too. So it's not clear that adding code here for
* recheck/re-sort would be worth the trouble. But we should at least
* throw an error if someone tries it.)
*/
if (scandesc->numberOfOrderBys > 0 && scandesc->xs_recheckorderby)
ereport(ERROR,
(errcode(ERRCODE_FEATURE_NOT_SUPPORTED),
errmsg("lossy distance functions are not supported in index-only scans")));
/*
* Predicate locks for index-only scans must be acquired at the page
* level when the heap is not accessed, since tuple-level predicate
* locks need the tuple's xmin value. If we had to visit the tuple
* anyway, then we already have the tuple-level lock and can skip the
* page lock.
*/
if (tuple == NULL)
PredicateLockPage(scandesc->heapRelation,
ItemPointerGetBlockNumber(tid),
estate->es_snapshot);
return slot;
}
/*
* if we get here it means the index scan failed so we are at the end of
* the scan..
*/
return ExecClearTuple(slot);
}
/*
* Bulk deletion of all index entries pointing to a set of heap tuples and
* check invalid tuples left after upgrade.
* The set of target tuples is specified via a callback routine that tells
* whether any given heap tuple (identified by ItemPointer) is being deleted.
*
* Result: a palloc'd struct containing statistical info for VACUUM displays.
*/
Datum
gistbulkdelete(PG_FUNCTION_ARGS)
{
IndexVacuumInfo *info = (IndexVacuumInfo *) PG_GETARG_POINTER(0);
IndexBulkDeleteResult *stats = (IndexBulkDeleteResult *) PG_GETARG_POINTER(1);
IndexBulkDeleteCallback callback = (IndexBulkDeleteCallback) PG_GETARG_POINTER(2);
void *callback_state = (void *) PG_GETARG_POINTER(3);
Relation rel = info->index;
GistBDItem *stack,
*ptr;
/* first time through? */
if (stats == NULL)
stats = (IndexBulkDeleteResult *) palloc0(sizeof(IndexBulkDeleteResult));
/* we'll re-count the tuples each time */
stats->estimated_count = false;
stats->num_index_tuples = 0;
stack = (GistBDItem *) palloc0(sizeof(GistBDItem));
stack->blkno = GIST_ROOT_BLKNO;
while (stack)
{
Buffer buffer;
Page page;
OffsetNumber i,
maxoff;
IndexTuple idxtuple;
ItemId iid;
buffer = ReadBufferExtended(rel, MAIN_FORKNUM, stack->blkno,
RBM_NORMAL, info->strategy);
LockBuffer(buffer, GIST_SHARE);
gistcheckpage(rel, buffer);
page = (Page) BufferGetPage(buffer);
if (GistPageIsLeaf(page))
{
OffsetNumber todelete[MaxOffsetNumber];
int ntodelete = 0;
LockBuffer(buffer, GIST_UNLOCK);
LockBuffer(buffer, GIST_EXCLUSIVE);
page = (Page) BufferGetPage(buffer);
if (stack->blkno == GIST_ROOT_BLKNO && !GistPageIsLeaf(page))
{
/* only the root can become non-leaf during relock */
UnlockReleaseBuffer(buffer);
/* one more check */
continue;
}
/*
* check for split proceeded after look at parent, we should check
* it after relock
*/
pushStackIfSplited(page, stack);
/*
* Remove deletable tuples from page
*/
maxoff = PageGetMaxOffsetNumber(page);
for (i = FirstOffsetNumber; i <= maxoff; i = OffsetNumberNext(i))
{
iid = PageGetItemId(page, i);
idxtuple = (IndexTuple) PageGetItem(page, iid);
if (callback(&(idxtuple->t_tid), callback_state))
{
todelete[ntodelete] = i - ntodelete;
ntodelete++;
stats->tuples_removed += 1;
}
else
stats->num_index_tuples += 1;
}
if (ntodelete)
{
START_CRIT_SECTION();
MarkBufferDirty(buffer);
for (i = 0; i < ntodelete; i++)
PageIndexTupleDelete(page, todelete[i]);
GistMarkTuplesDeleted(page);
if (RelationNeedsWAL(rel))
{
XLogRecPtr recptr;
recptr = gistXLogUpdate(rel->rd_node, buffer,
todelete, ntodelete,
NULL, 0, InvalidBuffer);
PageSetLSN(page, recptr);
PageSetTLI(page, ThisTimeLineID);
}
else
PageSetLSN(page, GetXLogRecPtrForTemp());
END_CRIT_SECTION();
}
}
else
{
/* check for split proceeded after look at parent */
pushStackIfSplited(page, stack);
maxoff = PageGetMaxOffsetNumber(page);
for (i = FirstOffsetNumber; i <= maxoff; i = OffsetNumberNext(i))
{
iid = PageGetItemId(page, i);
idxtuple = (IndexTuple) PageGetItem(page, iid);
ptr = (GistBDItem *) palloc(sizeof(GistBDItem));
ptr->blkno = ItemPointerGetBlockNumber(&(idxtuple->t_tid));
ptr->parentlsn = PageGetLSN(page);
ptr->next = stack->next;
stack->next = ptr;
if (GistTupleIsInvalid(idxtuple))
ereport(LOG,
(errmsg("index \"%s\" contains an inner tuple marked as invalid",
RelationGetRelationName(rel)),
errdetail("This is caused by an incomplete page split at crash recovery before upgrading to PostgreSQL 9.1."),
errhint("Please REINDEX it.")));
}
}
UnlockReleaseBuffer(buffer);
ptr = stack->next;
pfree(stack);
stack = ptr;
vacuum_delay_point();
}
PG_RETURN_POINTER(stats);
}
/*
* 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 autosummarization is enabled, check if we need to summarize the previous
* page range.
*
* If the range is not currently summarized (i.e. the revmap returns NULL for
* it), there's nothing to do for this tuple.
*/
bool
brininsert(Relation idxRel, Datum *values, bool *nulls,
ItemPointer heaptid, Relation heapRel,
IndexUniqueCheck checkUnique,
IndexInfo *indexInfo)
{
BlockNumber pagesPerRange;
BlockNumber origHeapBlk;
BlockNumber heapBlk;
BrinDesc *bdesc = (BrinDesc *) indexInfo->ii_AmCache;
BrinRevmap *revmap;
Buffer buf = InvalidBuffer;
MemoryContext tupcxt = NULL;
MemoryContext oldcxt = CurrentMemoryContext;
bool autosummarize = BrinGetAutoSummarize(idxRel);
revmap = brinRevmapInitialize(idxRel, &pagesPerRange, NULL);
/*
* origHeapBlk is the block number where the insertion occurred. heapBlk
* is the first block in the corresponding page range.
*/
origHeapBlk = ItemPointerGetBlockNumber(heaptid);
heapBlk = (origHeapBlk / pagesPerRange) * pagesPerRange;
for (;;)
{
bool need_insert = false;
OffsetNumber off;
BrinTuple *brtup;
BrinMemTuple *dtup;
int keyno;
CHECK_FOR_INTERRUPTS();
/*
* If auto-summarization is enabled and we just inserted the first
* tuple into the first block of a new non-first page range, request a
* summarization run of the previous range.
*/
if (autosummarize &&
heapBlk > 0 &&
heapBlk == origHeapBlk &&
ItemPointerGetOffsetNumber(heaptid) == FirstOffsetNumber)
{
BlockNumber lastPageRange = heapBlk - 1;
BrinTuple *lastPageTuple;
lastPageTuple =
brinGetTupleForHeapBlock(revmap, lastPageRange, &buf, &off,
NULL, BUFFER_LOCK_SHARE, NULL);
if (!lastPageTuple)
{
bool recorded;
recorded = AutoVacuumRequestWork(AVW_BRINSummarizeRange,
RelationGetRelid(idxRel),
lastPageRange);
if (!recorded)
ereport(LOG,
(errcode(ERRCODE_PROGRAM_LIMIT_EXCEEDED),
errmsg("request for BRIN range summarization for index \"%s\" page %u was not recorded",
RelationGetRelationName(idxRel),
lastPageRange)));
}
else
LockBuffer(buf, BUFFER_LOCK_UNLOCK);
}
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 in this statement? */
if (bdesc == NULL)
{
MemoryContextSwitchTo(indexInfo->ii_Context);
bdesc = brin_build_desc(idxRel);
indexInfo->ii_AmCache = (void *) bdesc;
MemoryContextSwitchTo(oldcxt);
}
/* First time through in this brininsert call? */
if (tupcxt == NULL)
{
tupcxt = AllocSetContextCreate(CurrentMemoryContext,
"brininsert cxt",
ALLOCSET_DEFAULT_SIZES);
MemoryContextSwitchTo(tupcxt);
}
dtup = brin_deform_tuple(bdesc, brtup, NULL);
/*
* 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, NULL, NULL);
/*
* 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);
MemoryContextSwitchTo(oldcxt);
if (tupcxt != NULL)
MemoryContextDelete(tupcxt);
return false;
}
void
heap_desc(StringInfo buf, XLogRecord *record)
{
char *rec = XLogRecGetData(record);
uint8 info = record->xl_info & ~XLR_INFO_MASK;
info &= XLOG_HEAP_OPMASK;
if (info == XLOG_HEAP_INSERT)
{
xl_heap_insert *xlrec = (xl_heap_insert *) rec;
out_target(buf, &(xlrec->target));
}
else if (info == XLOG_HEAP_DELETE)
{
xl_heap_delete *xlrec = (xl_heap_delete *) rec;
out_target(buf, &(xlrec->target));
appendStringInfoChar(buf, ' ');
out_infobits(buf, xlrec->infobits_set);
}
else if (info == XLOG_HEAP_UPDATE)
{
xl_heap_update *xlrec = (xl_heap_update *) rec;
out_target(buf, &(xlrec->target));
appendStringInfo(buf, " xmax %u ", xlrec->old_xmax);
out_infobits(buf, xlrec->old_infobits_set);
appendStringInfo(buf, "; new tid %u/%u xmax %u",
ItemPointerGetBlockNumber(&(xlrec->newtid)),
ItemPointerGetOffsetNumber(&(xlrec->newtid)),
xlrec->new_xmax);
}
else if (info == XLOG_HEAP_HOT_UPDATE)
{
xl_heap_update *xlrec = (xl_heap_update *) rec;
out_target(buf, &(xlrec->target));
appendStringInfo(buf, " xmax %u ", xlrec->old_xmax);
out_infobits(buf, xlrec->old_infobits_set);
appendStringInfo(buf, "; new tid %u/%u xmax %u",
ItemPointerGetBlockNumber(&(xlrec->newtid)),
ItemPointerGetOffsetNumber(&(xlrec->newtid)),
xlrec->new_xmax);
}
else if (info == XLOG_HEAP_LOCK)
{
xl_heap_lock *xlrec = (xl_heap_lock *) rec;
appendStringInfo(buf, "xid %u: ", xlrec->locking_xid);
out_target(buf, &(xlrec->target));
appendStringInfoChar(buf, ' ');
out_infobits(buf, xlrec->infobits_set);
}
else if (info == XLOG_HEAP_INPLACE)
{
xl_heap_inplace *xlrec = (xl_heap_inplace *) rec;
out_target(buf, &(xlrec->target));
}
}
/*
* Updates the stack so that child->parent is the correct parent of the
* child. child->parent must be exclusively locked on entry, and will
* remain so at exit, but it might not be the same page anymore.
*/
static void
gistFindCorrectParent(Relation r, GISTInsertStack *child)
{
GISTInsertStack *parent = child->parent;
gistcheckpage(r, parent->buffer);
parent->page = (Page) BufferGetPage(parent->buffer);
/* here we don't need to distinguish between split and page update */
if (child->downlinkoffnum == InvalidOffsetNumber ||
parent->lsn != PageGetLSN(parent->page))
{
/* parent is changed, look child in right links until found */
OffsetNumber i,
maxoff;
ItemId iid;
IndexTuple idxtuple;
GISTInsertStack *ptr;
while (true)
{
maxoff = PageGetMaxOffsetNumber(parent->page);
for (i = FirstOffsetNumber; i <= maxoff; i = OffsetNumberNext(i))
{
iid = PageGetItemId(parent->page, i);
idxtuple = (IndexTuple) PageGetItem(parent->page, iid);
if (ItemPointerGetBlockNumber(&(idxtuple->t_tid)) == child->blkno)
{
/* yes!!, found */
child->downlinkoffnum = i;
return;
}
}
parent->blkno = GistPageGetOpaque(parent->page)->rightlink;
UnlockReleaseBuffer(parent->buffer);
if (parent->blkno == InvalidBlockNumber)
{
/*
* End of chain and still didn't find parent. It's a very-very
* rare situation when root splited.
*/
break;
}
parent->buffer = ReadBuffer(r, parent->blkno);
LockBuffer(parent->buffer, GIST_EXCLUSIVE);
gistcheckpage(r, parent->buffer);
parent->page = (Page) BufferGetPage(parent->buffer);
}
/*
* awful!!, we need search tree to find parent ... , but before we
* should release all old parent
*/
ptr = child->parent->parent; /* child->parent already released
* above */
while (ptr)
{
ReleaseBuffer(ptr->buffer);
ptr = ptr->parent;
}
/* ok, find new path */
ptr = parent = gistFindPath(r, child->blkno, &child->downlinkoffnum);
/* read all buffers as expected by caller */
/* note we don't lock them or gistcheckpage them here! */
while (ptr)
{
ptr->buffer = ReadBuffer(r, ptr->blkno);
ptr->page = (Page) BufferGetPage(ptr->buffer);
ptr = ptr->parent;
}
/* install new chain of parents to stack */
child->parent = parent;
/* make recursive call to normal processing */
LockBuffer(child->parent->buffer, GIST_EXCLUSIVE);
gistFindCorrectParent(r, child);
}
return;
}
/*
* _bt_pagedel() -- Delete a page from the b-tree, if legal to do so.
*
* This action unlinks the page from the b-tree structure, removing all
* pointers leading to it --- but not touching its own left and right links.
* The page cannot be physically reclaimed right away, since other processes
* may currently be trying to follow links leading to the page; they have to
* be allowed to use its right-link to recover. See nbtree/README.
*
* On entry, the target buffer must be pinned and locked (either read or write
* lock is OK). This lock and pin will be dropped before exiting.
*
* The "stack" argument can be a search stack leading (approximately) to the
* target page, or NULL --- outside callers typically pass NULL since they
* have not done such a search, but internal recursion cases pass the stack
* to avoid duplicated search effort.
*
* Returns the number of pages successfully deleted (zero if page cannot
* be deleted now; could be more than one if parent pages were deleted too).
*
* NOTE: this leaks memory. Rather than trying to clean up everything
* carefully, it's better to run it in a temp context that can be reset
* frequently.
*/
int
_bt_pagedel(Relation rel, Buffer buf, BTStack stack)
{
int result;
BlockNumber target,
leftsib,
rightsib,
parent;
OffsetNumber poffset,
maxoff;
uint32 targetlevel,
ilevel;
ItemId itemid;
IndexTuple targetkey,
itup;
ScanKey itup_scankey;
Buffer lbuf,
rbuf,
pbuf;
bool parent_half_dead;
bool parent_one_child;
bool rightsib_empty;
Buffer metabuf = InvalidBuffer;
Page metapg = NULL;
BTMetaPageData *metad = NULL;
Page page;
BTPageOpaque opaque;
/*
* We can never delete rightmost pages nor root pages. While at it, check
* that page is not already deleted and is empty.
*/
page = BufferGetPage(buf);
opaque = (BTPageOpaque) PageGetSpecialPointer(page);
if (P_RIGHTMOST(opaque) || P_ISROOT(opaque) || P_ISDELETED(opaque) ||
P_FIRSTDATAKEY(opaque) <= PageGetMaxOffsetNumber(page))
{
/* Should never fail to delete a half-dead page */
Assert(!P_ISHALFDEAD(opaque));
_bt_relbuf(rel, buf);
return 0;
}
/*
* Save info about page, including a copy of its high key (it must have
* one, being non-rightmost).
*/
target = BufferGetBlockNumber(buf);
targetlevel = opaque->btpo.level;
leftsib = opaque->btpo_prev;
itemid = PageGetItemId(page, P_HIKEY);
targetkey = CopyIndexTuple((IndexTuple) PageGetItem(page, itemid));
/*
* To avoid deadlocks, we'd better drop the target page lock before going
* further.
*/
_bt_relbuf(rel, buf);
/*
* We need an approximate pointer to the page's parent page. We use the
* standard search mechanism to search for the page's high key; this will
* give us a link to either the current parent or someplace to its left
* (if there are multiple equal high keys). In recursion cases, the
* caller already generated a search stack and we can just re-use that
* work.
*/
if (stack == NULL)
{
if (!InRecovery)
{
/* we need an insertion scan key to do our search, so build one */
itup_scankey = _bt_mkscankey(rel, targetkey);
/* find the leftmost leaf page containing this key */
stack = _bt_search(rel, rel->rd_rel->relnatts, itup_scankey, false,
&lbuf, BT_READ);
/* don't need a pin on that either */
_bt_relbuf(rel, lbuf);
/*
* If we are trying to delete an interior page, _bt_search did
* more than we needed. Locate the stack item pointing to our
* parent level.
*/
ilevel = 0;
for (;;)
{
if (stack == NULL)
elog(ERROR, "not enough stack items");
if (ilevel == targetlevel)
break;
stack = stack->bts_parent;
ilevel++;
}
}
else
{
/*
* During WAL recovery, we can't use _bt_search (for one reason,
* it might invoke user-defined comparison functions that expect
* facilities not available in recovery mode). Instead, just set
* up a dummy stack pointing to the left end of the parent tree
* level, from which _bt_getstackbuf will walk right to the parent
* page. Painful, but we don't care too much about performance in
* this scenario.
*/
pbuf = _bt_get_endpoint(rel, targetlevel + 1, false);
stack = (BTStack) palloc(sizeof(BTStackData));
stack->bts_blkno = BufferGetBlockNumber(pbuf);
stack->bts_offset = InvalidOffsetNumber;
/* bts_btentry will be initialized below */
stack->bts_parent = NULL;
_bt_relbuf(rel, pbuf);
}
}
/*
* We cannot delete a page that is the rightmost child of its immediate
* parent, unless it is the only child --- in which case the parent has to
* be deleted too, and the same condition applies recursively to it. We
* have to check this condition all the way up before trying to delete. We
* don't need to re-test when deleting a non-leaf page, though.
*/
if (targetlevel == 0 &&
!_bt_parent_deletion_safe(rel, target, stack))
return 0;
/*
* We have to lock the pages we need to modify in the standard order:
* moving right, then up. Else we will deadlock against other writers.
*
* So, we need to find and write-lock the current left sibling of the
* target page. The sibling that was current a moment ago could have
* split, so we may have to move right. This search could fail if either
* the sibling or the target page was deleted by someone else meanwhile;
* if so, give up. (Right now, that should never happen, since page
* deletion is only done in VACUUM and there shouldn't be multiple VACUUMs
* concurrently on the same table.)
*/
if (leftsib != P_NONE)
{
lbuf = _bt_getbuf(rel, leftsib, BT_WRITE);
page = BufferGetPage(lbuf);
opaque = (BTPageOpaque) PageGetSpecialPointer(page);
while (P_ISDELETED(opaque) || opaque->btpo_next != target)
{
/* step right one page */
leftsib = opaque->btpo_next;
_bt_relbuf(rel, lbuf);
if (leftsib == P_NONE)
{
elog(LOG, "no left sibling (concurrent deletion?) in \"%s\"",
RelationGetRelationName(rel));
return 0;
}
lbuf = _bt_getbuf(rel, leftsib, BT_WRITE);
page = BufferGetPage(lbuf);
opaque = (BTPageOpaque) PageGetSpecialPointer(page);
}
}
else
lbuf = InvalidBuffer;
/*
* Next write-lock the target page itself. It should be okay to take just
* a write lock not a superexclusive lock, since no scans would stop on an
* empty page.
*/
buf = _bt_getbuf(rel, target, BT_WRITE);
page = BufferGetPage(buf);
opaque = (BTPageOpaque) PageGetSpecialPointer(page);
/*
* Check page is still empty etc, else abandon deletion. The empty check
* is necessary since someone else might have inserted into it while we
* didn't have it locked; the others are just for paranoia's sake.
*/
if (P_RIGHTMOST(opaque) || P_ISROOT(opaque) || P_ISDELETED(opaque) ||
P_FIRSTDATAKEY(opaque) <= PageGetMaxOffsetNumber(page))
{
_bt_relbuf(rel, buf);
if (BufferIsValid(lbuf))
_bt_relbuf(rel, lbuf);
return 0;
}
if (opaque->btpo_prev != leftsib)
elog(ERROR, "left link changed unexpectedly in block %u of index \"%s\"",
target, RelationGetRelationName(rel));
/*
* And next write-lock the (current) right sibling.
*/
rightsib = opaque->btpo_next;
rbuf = _bt_getbuf(rel, rightsib, BT_WRITE);
page = BufferGetPage(rbuf);
opaque = (BTPageOpaque) PageGetSpecialPointer(page);
if (opaque->btpo_prev != target)
elog(ERROR, "right sibling's left-link doesn't match: "
"block %u links to %u instead of expected %u in index \"%s\"",
rightsib, opaque->btpo_prev, target,
RelationGetRelationName(rel));
/*
* Next find and write-lock the current parent of the target page. This is
* essentially the same as the corresponding step of splitting.
*/
ItemPointerSet(&(stack->bts_btentry.t_tid), target, P_HIKEY);
pbuf = _bt_getstackbuf(rel, stack, BT_WRITE);
if (pbuf == InvalidBuffer)
elog(ERROR, "failed to re-find parent key in index \"%s\" for deletion target page %u",
RelationGetRelationName(rel), target);
parent = stack->bts_blkno;
poffset = stack->bts_offset;
/*
* If the target is the rightmost child of its parent, then we can't
* delete, unless it's also the only child --- in which case the parent
* changes to half-dead status. The "can't delete" case should have been
* detected by _bt_parent_deletion_safe, so complain if we see it now.
*/
page = BufferGetPage(pbuf);
opaque = (BTPageOpaque) PageGetSpecialPointer(page);
maxoff = PageGetMaxOffsetNumber(page);
parent_half_dead = false;
parent_one_child = false;
if (poffset >= maxoff)
{
if (poffset == P_FIRSTDATAKEY(opaque))
parent_half_dead = true;
else
elog(ERROR, "failed to delete rightmost child %u of block %u in index \"%s\"",
target, parent, RelationGetRelationName(rel));
}
else
{
/* Will there be exactly one child left in this parent? */
if (OffsetNumberNext(P_FIRSTDATAKEY(opaque)) == maxoff)
parent_one_child = true;
}
/*
* If we are deleting the next-to-last page on the target's level, then
* the rightsib is a candidate to become the new fast root. (In theory, it
* might be possible to push the fast root even further down, but the odds
* of doing so are slim, and the locking considerations daunting.)
*
* We don't support handling this in the case where the parent is becoming
* half-dead, even though it theoretically could occur.
*
* We can safely acquire a lock on the metapage here --- see comments for
* _bt_newroot().
*/
if (leftsib == P_NONE && !parent_half_dead)
{
page = BufferGetPage(rbuf);
opaque = (BTPageOpaque) PageGetSpecialPointer(page);
Assert(opaque->btpo.level == targetlevel);
if (P_RIGHTMOST(opaque))
{
/* rightsib will be the only one left on the level */
metabuf = _bt_getbuf(rel, BTREE_METAPAGE, BT_WRITE);
metapg = BufferGetPage(metabuf);
metad = BTPageGetMeta(metapg);
/*
* The expected case here is btm_fastlevel == targetlevel+1; if
* the fastlevel is <= targetlevel, something is wrong, and we
* choose to overwrite it to fix it.
*/
if (metad->btm_fastlevel > targetlevel + 1)
{
/* no update wanted */
_bt_relbuf(rel, metabuf);
metabuf = InvalidBuffer;
}
}
}
/*
* Check that the parent-page index items we're about to delete/overwrite
* contain what we expect. This can fail if the index has become
* corrupt for some reason. We want to throw any error before entering
* the critical section --- otherwise it'd be a PANIC.
*
* The test on the target item is just an Assert because _bt_getstackbuf
* should have guaranteed it has the expected contents. The test on the
* next-child downlink is known to sometimes fail in the field, though.
*/
page = BufferGetPage(pbuf);
opaque = (BTPageOpaque) PageGetSpecialPointer(page);
#ifdef USE_ASSERT_CHECKING
itemid = PageGetItemId(page, poffset);
itup = (IndexTuple) PageGetItem(page, itemid);
Assert(ItemPointerGetBlockNumber(&(itup->t_tid)) == target);
#endif
if (!parent_half_dead)
{
OffsetNumber nextoffset;
nextoffset = OffsetNumberNext(poffset);
itemid = PageGetItemId(page, nextoffset);
itup = (IndexTuple) PageGetItem(page, itemid);
if (ItemPointerGetBlockNumber(&(itup->t_tid)) != rightsib)
elog(ERROR, "right sibling %u of block %u is not next child %u of block %u in index \"%s\"",
rightsib, target, ItemPointerGetBlockNumber(&(itup->t_tid)),
parent, RelationGetRelationName(rel));
}
/*
* Here we begin doing the deletion.
*/
/* No ereport(ERROR) until changes are logged */
START_CRIT_SECTION();
/*
* Update parent. The normal case is a tad tricky because we want to
* delete the target's downlink and the *following* key. Easiest way is
* to copy the right sibling's downlink over the target downlink, and then
* delete the following item.
*/
if (parent_half_dead)
{
PageIndexTupleDelete(page, poffset);
opaque->btpo_flags |= BTP_HALF_DEAD;
}
else
{
OffsetNumber nextoffset;
itemid = PageGetItemId(page, poffset);
itup = (IndexTuple) PageGetItem(page, itemid);
ItemPointerSet(&(itup->t_tid), rightsib, P_HIKEY);
nextoffset = OffsetNumberNext(poffset);
PageIndexTupleDelete(page, nextoffset);
}
/*
* Update siblings' side-links. Note the target page's side-links will
* continue to point to the siblings. Asserts here are just rechecking
* things we already verified above.
*/
if (BufferIsValid(lbuf))
{
page = BufferGetPage(lbuf);
opaque = (BTPageOpaque) PageGetSpecialPointer(page);
Assert(opaque->btpo_next == target);
opaque->btpo_next = rightsib;
}
page = BufferGetPage(rbuf);
opaque = (BTPageOpaque) PageGetSpecialPointer(page);
Assert(opaque->btpo_prev == target);
opaque->btpo_prev = leftsib;
rightsib_empty = (P_FIRSTDATAKEY(opaque) > PageGetMaxOffsetNumber(page));
/*
* Mark the page itself deleted. It can be recycled when all current
* transactions are gone.
*/
page = BufferGetPage(buf);
opaque = (BTPageOpaque) PageGetSpecialPointer(page);
opaque->btpo_flags &= ~BTP_HALF_DEAD;
opaque->btpo_flags |= BTP_DELETED;
opaque->btpo.xact = ReadNewTransactionId();
/* And update the metapage, if needed */
if (BufferIsValid(metabuf))
{
metad->btm_fastroot = rightsib;
metad->btm_fastlevel = targetlevel;
MarkBufferDirty(metabuf);
}
/* Must mark buffers dirty before XLogInsert */
MarkBufferDirty(pbuf);
MarkBufferDirty(rbuf);
MarkBufferDirty(buf);
if (BufferIsValid(lbuf))
MarkBufferDirty(lbuf);
/* XLOG stuff */
if (!rel->rd_istemp)
{
xl_btree_delete_page xlrec;
xl_btree_metadata xlmeta;
uint8 xlinfo;
XLogRecPtr recptr;
XLogRecData rdata[5];
XLogRecData *nextrdata;
xlrec.target.node = rel->rd_node;
ItemPointerSet(&(xlrec.target.tid), parent, poffset);
xlrec.deadblk = target;
xlrec.leftblk = leftsib;
xlrec.rightblk = rightsib;
xlrec.btpo_xact = opaque->btpo.xact;
rdata[0].data = (char *) &xlrec;
rdata[0].len = SizeOfBtreeDeletePage;
rdata[0].buffer = InvalidBuffer;
rdata[0].next = nextrdata = &(rdata[1]);
if (BufferIsValid(metabuf))
{
xlmeta.root = metad->btm_root;
xlmeta.level = metad->btm_level;
xlmeta.fastroot = metad->btm_fastroot;
xlmeta.fastlevel = metad->btm_fastlevel;
nextrdata->data = (char *) &xlmeta;
nextrdata->len = sizeof(xl_btree_metadata);
nextrdata->buffer = InvalidBuffer;
nextrdata->next = nextrdata + 1;
nextrdata++;
xlinfo = XLOG_BTREE_DELETE_PAGE_META;
}
else if (parent_half_dead)
xlinfo = XLOG_BTREE_DELETE_PAGE_HALF;
else
xlinfo = XLOG_BTREE_DELETE_PAGE;
nextrdata->data = NULL;
nextrdata->len = 0;
nextrdata->next = nextrdata + 1;
nextrdata->buffer = pbuf;
nextrdata->buffer_std = true;
nextrdata++;
nextrdata->data = NULL;
nextrdata->len = 0;
nextrdata->buffer = rbuf;
nextrdata->buffer_std = true;
nextrdata->next = NULL;
if (BufferIsValid(lbuf))
{
nextrdata->next = nextrdata + 1;
nextrdata++;
nextrdata->data = NULL;
nextrdata->len = 0;
nextrdata->buffer = lbuf;
nextrdata->buffer_std = true;
nextrdata->next = NULL;
}
recptr = XLogInsert(RM_BTREE_ID, xlinfo, rdata);
if (BufferIsValid(metabuf))
{
PageSetLSN(metapg, recptr);
PageSetTLI(metapg, ThisTimeLineID);
}
page = BufferGetPage(pbuf);
PageSetLSN(page, recptr);
PageSetTLI(page, ThisTimeLineID);
page = BufferGetPage(rbuf);
PageSetLSN(page, recptr);
PageSetTLI(page, ThisTimeLineID);
page = BufferGetPage(buf);
PageSetLSN(page, recptr);
PageSetTLI(page, ThisTimeLineID);
if (BufferIsValid(lbuf))
{
page = BufferGetPage(lbuf);
PageSetLSN(page, recptr);
PageSetTLI(page, ThisTimeLineID);
}
}
END_CRIT_SECTION();
/* release metapage; send out relcache inval if metapage changed */
if (BufferIsValid(metabuf))
{
CacheInvalidateRelcache(rel);
_bt_relbuf(rel, metabuf);
}
/* can always release leftsib immediately */
if (BufferIsValid(lbuf))
_bt_relbuf(rel, lbuf);
/*
* If parent became half dead, recurse to delete it. Otherwise, if right
* sibling is empty and is now the last child of the parent, recurse to
* try to delete it. (These cases cannot apply at the same time, though
* the second case might itself recurse to the first.)
*
* When recursing to parent, we hold the lock on the target page until
* done. This delays any insertions into the keyspace that was just
* effectively reassigned to the parent's right sibling. If we allowed
* that, and there were enough such insertions before we finish deleting
* the parent, page splits within that keyspace could lead to inserting
* out-of-order keys into the grandparent level. It is thought that that
* wouldn't have any serious consequences, but it still seems like a
* pretty bad idea.
*/
if (parent_half_dead)
{
/* recursive call will release pbuf */
_bt_relbuf(rel, rbuf);
result = _bt_pagedel(rel, pbuf, stack->bts_parent) + 1;
_bt_relbuf(rel, buf);
}
else if (parent_one_child && rightsib_empty)
{
_bt_relbuf(rel, pbuf);
_bt_relbuf(rel, buf);
/* recursive call will release rbuf */
result = _bt_pagedel(rel, rbuf, stack) + 1;
}
else
{
_bt_relbuf(rel, pbuf);
_bt_relbuf(rel, buf);
_bt_relbuf(rel, rbuf);
result = 1;
}
return result;
}
/*
* Workhouse routine for doing insertion into a GiST index. Note that
* this routine assumes it is invoked in a short-lived memory context,
* so it does not bother releasing palloc'd allocations.
*/
void
gistdoinsert(Relation r, IndexTuple itup, Size freespace, GISTSTATE *giststate)
{
ItemId iid;
IndexTuple idxtuple;
GISTInsertStack firststack;
GISTInsertStack *stack;
GISTInsertState state;
bool xlocked = false;
memset(&state, 0, sizeof(GISTInsertState));
state.freespace = freespace;
state.r = r;
/* Start from the root */
firststack.blkno = GIST_ROOT_BLKNO;
firststack.lsn = 0;
firststack.parent = NULL;
firststack.downlinkoffnum = InvalidOffsetNumber;
state.stack = stack = &firststack;
/*
* Walk down along the path of smallest penalty, updating the parent
* pointers with the key we're inserting as we go. If we crash in the
* middle, the tree is consistent, although the possible parent updates
* were a waste.
*/
for (;;)
{
if (XLogRecPtrIsInvalid(stack->lsn))
stack->buffer = ReadBuffer(state.r, stack->blkno);
/*
* Be optimistic and grab shared lock first. Swap it for an exclusive
* lock later if we need to update the page.
*/
if (!xlocked)
{
LockBuffer(stack->buffer, GIST_SHARE);
gistcheckpage(state.r, stack->buffer);
}
stack->page = (Page) BufferGetPage(stack->buffer);
stack->lsn = PageGetLSN(stack->page);
Assert(!RelationNeedsWAL(state.r) || !XLogRecPtrIsInvalid(stack->lsn));
/*
* If this page was split but the downlink was never inserted to the
* parent because the inserting backend crashed before doing that, fix
* that now.
*/
if (GistFollowRight(stack->page))
{
if (!xlocked)
{
LockBuffer(stack->buffer, GIST_UNLOCK);
LockBuffer(stack->buffer, GIST_EXCLUSIVE);
xlocked = true;
/* someone might've completed the split when we unlocked */
if (!GistFollowRight(stack->page))
continue;
}
gistfixsplit(&state, giststate);
UnlockReleaseBuffer(stack->buffer);
xlocked = false;
state.stack = stack = stack->parent;
continue;
}
if (stack->blkno != GIST_ROOT_BLKNO &&
stack->parent->lsn < GistPageGetNSN(stack->page))
{
/*
* Concurrent split detected. There's no guarantee that the
* downlink for this page is consistent with the tuple we're
* inserting anymore, so go back to parent and rechoose the best
* child.
*/
UnlockReleaseBuffer(stack->buffer);
xlocked = false;
state.stack = stack = stack->parent;
continue;
}
if (!GistPageIsLeaf(stack->page))
{
/*
* This is an internal page so continue to walk down the tree.
* Find the child node that has the minimum insertion penalty.
*/
BlockNumber childblkno;
IndexTuple newtup;
GISTInsertStack *item;
OffsetNumber downlinkoffnum;
downlinkoffnum = gistchoose(state.r, stack->page, itup, giststate);
iid = PageGetItemId(stack->page, downlinkoffnum);
idxtuple = (IndexTuple) PageGetItem(stack->page, iid);
childblkno = ItemPointerGetBlockNumber(&(idxtuple->t_tid));
/*
* Check that it's not a leftover invalid tuple from pre-9.1
*/
if (GistTupleIsInvalid(idxtuple))
ereport(ERROR,
(errmsg("index \"%s\" contains an inner tuple marked as invalid",
RelationGetRelationName(r)),
errdetail("This is caused by an incomplete page split at crash recovery before upgrading to PostgreSQL 9.1."),
errhint("Please REINDEX it.")));
/*
* Check that the key representing the target child node is
* consistent with the key we're inserting. Update it if it's not.
*/
newtup = gistgetadjusted(state.r, idxtuple, itup, giststate);
if (newtup)
{
/*
* Swap shared lock for an exclusive one. Beware, the page may
* change while we unlock/lock the page...
*/
if (!xlocked)
{
LockBuffer(stack->buffer, GIST_UNLOCK);
LockBuffer(stack->buffer, GIST_EXCLUSIVE);
xlocked = true;
stack->page = (Page) BufferGetPage(stack->buffer);
if (PageGetLSN(stack->page) != stack->lsn)
{
/* the page was changed while we unlocked it, retry */
continue;
}
}
/*
* Update the tuple.
*
* We still hold the lock after gistinserttuple(), but it
* might have to split the page to make the updated tuple fit.
* In that case the updated tuple might migrate to the other
* half of the split, so we have to go back to the parent and
* descend back to the half that's a better fit for the new
* tuple.
*/
if (gistinserttuple(&state, stack, giststate, newtup,
downlinkoffnum))
{
/*
* If this was a root split, the root page continues to be
* the parent and the updated tuple went to one of the
* child pages, so we just need to retry from the root
* page.
*/
if (stack->blkno != GIST_ROOT_BLKNO)
{
UnlockReleaseBuffer(stack->buffer);
xlocked = false;
state.stack = stack = stack->parent;
}
continue;
}
}
LockBuffer(stack->buffer, GIST_UNLOCK);
xlocked = false;
/* descend to the chosen child */
item = (GISTInsertStack *) palloc0(sizeof(GISTInsertStack));
item->blkno = childblkno;
item->parent = stack;
item->downlinkoffnum = downlinkoffnum;
state.stack = stack = item;
}
else
{
/*
* Leaf page. Insert the new key. We've already updated all the
* parents on the way down, but we might have to split the page if
* it doesn't fit. gistinserthere() will take care of that.
*/
/*
* Swap shared lock for an exclusive one. Be careful, the page may
* change while we unlock/lock the page...
*/
if (!xlocked)
{
LockBuffer(stack->buffer, GIST_UNLOCK);
LockBuffer(stack->buffer, GIST_EXCLUSIVE);
xlocked = true;
stack->page = (Page) BufferGetPage(stack->buffer);
stack->lsn = PageGetLSN(stack->page);
if (stack->blkno == GIST_ROOT_BLKNO)
{
/*
* the only page that can become inner instead of leaf is
* the root page, so for root we should recheck it
*/
if (!GistPageIsLeaf(stack->page))
{
/*
* very rare situation: during unlock/lock index with
* number of pages = 1 was increased
*/
LockBuffer(stack->buffer, GIST_UNLOCK);
xlocked = false;
continue;
}
/*
* we don't need to check root split, because checking
* leaf/inner is enough to recognize split for root
*/
}
else if (GistFollowRight(stack->page) ||
stack->parent->lsn < GistPageGetNSN(stack->page))
{
/*
* The page was split while we momentarily unlocked the
* page. Go back to parent.
*/
UnlockReleaseBuffer(stack->buffer);
xlocked = false;
state.stack = stack = stack->parent;
continue;
}
}
/* now state.stack->(page, buffer and blkno) points to leaf page */
gistinserttuple(&state, stack, giststate, itup,
InvalidOffsetNumber);
LockBuffer(stack->buffer, GIST_UNLOCK);
/* Release any pins we might still hold before exiting */
for (; stack; stack = stack->parent)
ReleaseBuffer(stack->buffer);
break;
}
}
}
void
heap_desc(StringInfo buf, uint8 xl_info, char *rec)
{
uint8 info = xl_info & ~XLR_INFO_MASK;
info &= XLOG_HEAP_OPMASK;
if (info == XLOG_HEAP_INSERT)
{
xl_heap_insert *xlrec = (xl_heap_insert *) rec;
if (xl_info & XLOG_HEAP_INIT_PAGE)
appendStringInfoString(buf, "insert(init): ");
else
appendStringInfoString(buf, "insert: ");
out_target(buf, &(xlrec->target));
}
else if (info == XLOG_HEAP_DELETE)
{
xl_heap_delete *xlrec = (xl_heap_delete *) rec;
appendStringInfoString(buf, "delete: ");
out_target(buf, &(xlrec->target));
appendStringInfoChar(buf, ' ');
out_infobits(buf, xlrec->infobits_set);
}
else if (info == XLOG_HEAP_UPDATE)
{
xl_heap_update *xlrec = (xl_heap_update *) rec;
if (xl_info & XLOG_HEAP_INIT_PAGE)
appendStringInfoString(buf, "update(init): ");
else
appendStringInfoString(buf, "update: ");
out_target(buf, &(xlrec->target));
appendStringInfo(buf, " xmax %u ", xlrec->old_xmax);
out_infobits(buf, xlrec->old_infobits_set);
appendStringInfo(buf, "; new tid %u/%u xmax %u",
ItemPointerGetBlockNumber(&(xlrec->newtid)),
ItemPointerGetOffsetNumber(&(xlrec->newtid)),
xlrec->new_xmax);
}
else if (info == XLOG_HEAP_HOT_UPDATE)
{
xl_heap_update *xlrec = (xl_heap_update *) rec;
if (xl_info & XLOG_HEAP_INIT_PAGE) /* can this case happen? */
appendStringInfoString(buf, "hot_update(init): ");
else
appendStringInfoString(buf, "hot_update: ");
out_target(buf, &(xlrec->target));
appendStringInfo(buf, " xmax %u ", xlrec->old_xmax);
out_infobits(buf, xlrec->old_infobits_set);
appendStringInfo(buf, "; new tid %u/%u xmax %u",
ItemPointerGetBlockNumber(&(xlrec->newtid)),
ItemPointerGetOffsetNumber(&(xlrec->newtid)),
xlrec->new_xmax);
}
else if (info == XLOG_HEAP_NEWPAGE)
{
xl_heap_newpage *xlrec = (xl_heap_newpage *) rec;
appendStringInfo(buf, "newpage: rel %u/%u/%u; fork %u, blk %u",
xlrec->node.spcNode, xlrec->node.dbNode,
xlrec->node.relNode, xlrec->forknum,
xlrec->blkno);
}
else if (info == XLOG_HEAP_LOCK)
{
xl_heap_lock *xlrec = (xl_heap_lock *) rec;
appendStringInfo(buf, "lock %u: ", xlrec->locking_xid);
out_target(buf, &(xlrec->target));
appendStringInfoChar(buf, ' ');
out_infobits(buf, xlrec->infobits_set);
}
else if (info == XLOG_HEAP_INPLACE)
{
xl_heap_inplace *xlrec = (xl_heap_inplace *) rec;
appendStringInfoString(buf, "inplace: ");
out_target(buf, &(xlrec->target));
}
else
appendStringInfoString(buf, "UNKNOWN");
}
/* ----------------------------------------------------------------
* FunctionNext
*
* This is a workhorse for ExecFunctionScan
* ----------------------------------------------------------------
*/
static TupleTableSlot *
FunctionNext(FunctionScanState *node)
{
TupleTableSlot *slot;
EState *estate;
ScanDirection direction;
Tuplestorestate *tuplestorestate;
/*
* get information from the estate and scan state
*/
estate = node->ss.ps.state;
direction = estate->es_direction;
tuplestorestate = node->tuplestorestate;
/*
* If first time through, read all tuples from function and put them in a
* tuplestore. Subsequent calls just fetch tuples from tuplestore.
*/
if (tuplestorestate == NULL)
{
tuplestorestate = ExecMakeTableFunctionResult(
node->funcexpr,
node->ss.ps.ps_ExprContext,
node->tupdesc,
PlanStateOperatorMemKB( (PlanState *) node));
node->tuplestorestate = tuplestorestate;
/* CDB: Offer extra info for EXPLAIN ANALYZE. */
if (node->ss.ps.instrument)
{
/* Let the tuplestore share our Instrumentation object. */
tuplestore_set_instrument(tuplestorestate, node->ss.ps.instrument);
/* Request a callback at end of query. */
node->ss.ps.cdbexplainfun = ExecFunctionScanExplainEnd;
}
}
/*
* Get the next tuple from tuplestore. Return NULL if no more tuples.
*/
slot = node->ss.ss_ScanTupleSlot;
if (tuplestore_gettupleslot(tuplestorestate,
ScanDirectionIsForward(direction),
slot))
{
/* CDB: Label each row with a synthetic ctid for subquery dedup. */
if (node->cdb_want_ctid)
{
HeapTuple tuple = ExecFetchSlotHeapTuple(slot);
/* Increment 48-bit row count */
node->cdb_fake_ctid.ip_posid++;
if (node->cdb_fake_ctid.ip_posid == 0)
ItemPointerSetBlockNumber(&node->cdb_fake_ctid,
1 + ItemPointerGetBlockNumber(&node->cdb_fake_ctid));
tuple->t_self = node->cdb_fake_ctid;
}
}
if (!TupIsNull(slot))
{
Gpmon_M_Incr_Rows_Out(GpmonPktFromFuncScanState(node));
CheckSendPlanStateGpmonPkt(&node->ss.ps);
}
else if (!node->ss.ps.delayEagerFree)
{
ExecEagerFreeFunctionScan((FunctionScanState *)(&node->ss.ps));
}
return slot;
}
/*
* 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);
}
/*
* _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;
}
/*
* _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))
{
/* empty index... */
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 \"%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", level);
/* 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;
}
/*
* Prune specified item pointer or a HOT chain originating at that item.
*
* If the item is an index-referenced tuple (i.e. not a heap-only tuple),
* the HOT chain is pruned by removing all DEAD tuples at the start of the HOT
* chain. We also prune any RECENTLY_DEAD tuples preceding a DEAD tuple.
* This is OK because a RECENTLY_DEAD tuple preceding a DEAD tuple is really
* DEAD, the OldestXmin test is just too coarse to detect it.
*
* The root line pointer is redirected to the tuple immediately after the
* latest DEAD tuple. If all tuples in the chain are DEAD, the root line
* pointer is marked LP_DEAD. (This includes the case of a DEAD simple
* tuple, which we treat as a chain of length 1.)
*
* OldestXmin is the cutoff XID used to identify dead tuples.
*
* We don't actually change the page here, except perhaps for hint-bit updates
* caused by HeapTupleSatisfiesVacuum. We just add entries to the arrays in
* prstate showing the changes to be made. Items to be redirected are added
* to the redirected[] array (two entries per redirection); items to be set to
* LP_DEAD state are added to nowdead[]; and items to be set to LP_UNUSED
* state are added to nowunused[].
*
* If redirect_move is true, we intend to get rid of redirecting line pointers,
* not just make redirection entries.
*
* Returns the number of tuples (to be) deleted from the page.
*/
static int
heap_prune_chain(Relation relation, Buffer buffer, OffsetNumber rootoffnum,
TransactionId OldestXmin,
PruneState *prstate,
bool redirect_move)
{
int ndeleted = 0;
Page dp = (Page) BufferGetPage(buffer);
TransactionId priorXmax = InvalidTransactionId;
ItemId rootlp;
HeapTupleHeader htup;
OffsetNumber latestdead = InvalidOffsetNumber,
redirect_target = InvalidOffsetNumber,
maxoff = PageGetMaxOffsetNumber(dp),
offnum;
OffsetNumber chainitems[MaxHeapTuplesPerPage];
int nchain = 0,
i;
rootlp = PageGetItemId(dp, rootoffnum);
/*
* If it's a heap-only tuple, then it is not the start of a HOT chain.
*/
if (ItemIdIsNormal(rootlp))
{
htup = (HeapTupleHeader) PageGetItem(dp, rootlp);
if (HeapTupleHeaderIsHeapOnly(htup))
{
/*
* If the tuple is DEAD and doesn't chain to anything else, mark
* it unused immediately. (If it does chain, we can only remove
* it as part of pruning its chain.)
*
* We need this primarily to handle aborted HOT updates, that is,
* XMIN_INVALID heap-only tuples. Those might not be linked to by
* any chain, since the parent tuple might be re-updated before
* any pruning occurs. So we have to be able to reap them
* separately from chain-pruning. (Note that
* HeapTupleHeaderIsHotUpdated will never return true for an
* XMIN_INVALID tuple, so this code will work even when there were
* sequential updates within the aborted transaction.)
*
* Note that we might first arrive at a dead heap-only tuple
* either here or while following a chain below. Whichever path
* gets there first will mark the tuple unused.
*/
if (HeapTupleSatisfiesVacuum(relation, htup, OldestXmin, buffer)
== HEAPTUPLE_DEAD && !HeapTupleHeaderIsHotUpdated(htup))
{
heap_prune_record_unused(prstate, rootoffnum);
ndeleted++;
}
/* Nothing more to do */
return ndeleted;
}
}
/* Start from the root tuple */
offnum = rootoffnum;
/* while not end of the chain */
for (;;)
{
ItemId lp;
bool tupdead,
recent_dead;
/* Some sanity checks */
if (offnum < FirstOffsetNumber || offnum > maxoff)
break;
/* If item is already processed, stop --- it must not be same chain */
if (prstate->marked[offnum])
break;
lp = PageGetItemId(dp, offnum);
/* Unused item obviously isn't part of the chain */
if (!ItemIdIsUsed(lp))
break;
/*
* If we are looking at the redirected root line pointer, jump to the
* first normal tuple in the chain. If we find a redirect somewhere
* else, stop --- it must not be same chain.
*/
if (ItemIdIsRedirected(lp))
{
if (nchain > 0)
break; /* not at start of chain */
chainitems[nchain++] = offnum;
offnum = ItemIdGetRedirect(rootlp);
continue;
}
/*
* Likewise, a dead item pointer can't be part of the chain. (We
* already eliminated the case of dead root tuple outside this
* function.)
*/
if (ItemIdIsDead(lp))
break;
Assert(ItemIdIsNormal(lp));
htup = (HeapTupleHeader) PageGetItem(dp, lp);
/*
* Check the tuple XMIN against prior XMAX, if any
*/
if (TransactionIdIsValid(priorXmax) &&
!TransactionIdEquals(HeapTupleHeaderGetXmin(htup), priorXmax))
break;
/*
* OK, this tuple is indeed a member of the chain.
*/
chainitems[nchain++] = offnum;
/*
* Check tuple's visibility status.
*/
tupdead = recent_dead = false;
switch (HeapTupleSatisfiesVacuum(relation, htup, OldestXmin, buffer))
{
case HEAPTUPLE_DEAD:
tupdead = true;
break;
case HEAPTUPLE_RECENTLY_DEAD:
recent_dead = true;
/*
* This tuple may soon become DEAD. Update the hint field so
* that the page is reconsidered for pruning in future.
*/
heap_prune_record_prunable(prstate,
HeapTupleHeaderGetXmax(htup));
break;
case HEAPTUPLE_DELETE_IN_PROGRESS:
/*
* This tuple may soon become DEAD. Update the hint field so
* that the page is reconsidered for pruning in future.
*/
heap_prune_record_prunable(prstate,
HeapTupleHeaderGetXmax(htup));
break;
case HEAPTUPLE_LIVE:
case HEAPTUPLE_INSERT_IN_PROGRESS:
/*
* If we wanted to optimize for aborts, we might consider
* marking the page prunable when we see INSERT_IN_PROGRESS.
* But we don't. See related decisions about when to mark the
* page prunable in heapam.c.
*/
break;
default:
elog(ERROR, "unexpected HeapTupleSatisfiesVacuum result");
break;
}
/*
* Remember the last DEAD tuple seen. We will advance past
* RECENTLY_DEAD tuples just in case there's a DEAD one after them;
* but we can't advance past anything else. (XXX is it really worth
* continuing to scan beyond RECENTLY_DEAD? The case where we will
* find another DEAD tuple is a fairly unusual corner case.)
*/
if (tupdead)
latestdead = offnum;
else if (!recent_dead)
break;
/*
* If the tuple is not HOT-updated, then we are at the end of this
* HOT-update chain.
*/
if (!HeapTupleHeaderIsHotUpdated(htup))
break;
/*
* Advance to next chain member.
*/
Assert(ItemPointerGetBlockNumber(&htup->t_ctid) ==
BufferGetBlockNumber(buffer));
offnum = ItemPointerGetOffsetNumber(&htup->t_ctid);
priorXmax = HeapTupleHeaderGetXmax(htup);
}
/*
* If we found a DEAD tuple in the chain, adjust the HOT chain so that all
* the DEAD tuples at the start of the chain are removed and the root line
* pointer is appropriately redirected.
*/
if (OffsetNumberIsValid(latestdead))
{
/*
* Mark as unused each intermediate item that we are able to remove
* from the chain.
*
* When the previous item is the last dead tuple seen, we are at the
* right candidate for redirection.
*/
for (i = 1; (i < nchain) && (chainitems[i - 1] != latestdead); i++)
{
heap_prune_record_unused(prstate, chainitems[i]);
ndeleted++;
}
/*
* If the root entry had been a normal tuple, we are deleting it, so
* count it in the result. But changing a redirect (even to DEAD
* state) doesn't count.
*/
if (ItemIdIsNormal(rootlp))
ndeleted++;
/*
* If the DEAD tuple is at the end of the chain, the entire chain is
* dead and the root line pointer can be marked dead. Otherwise just
* redirect the root to the correct chain member.
*/
if (i >= nchain)
heap_prune_record_dead(prstate, rootoffnum);
else
{
heap_prune_record_redirect(prstate, rootoffnum, chainitems[i]);
/* If the redirection will be a move, need more processing */
if (redirect_move)
redirect_target = chainitems[i];
}
}
else if (nchain < 2 && ItemIdIsRedirected(rootlp))
{
/*
* We found a redirect item that doesn't point to a valid follow-on
* item. This can happen if the loop in heap_page_prune caused us to
* visit the dead successor of a redirect item before visiting the
* redirect item. We can clean up by setting the redirect item to
* DEAD state.
*/
heap_prune_record_dead(prstate, rootoffnum);
}
else if (redirect_move && ItemIdIsRedirected(rootlp))
{
/*
* If we desire to eliminate LP_REDIRECT items by moving tuples,
* make a redirection entry for each redirected root item; this
* will cause heap_page_prune_execute to actually do the move.
* (We get here only when there are no DEAD tuples in the chain;
* otherwise the redirection entry was made above.)
*/
heap_prune_record_redirect(prstate, rootoffnum, chainitems[1]);
redirect_target = chainitems[1];
}
/*
* If we are going to implement a redirect by moving tuples, we have
* to issue a cache invalidation against the redirection target tuple,
* because its CTID will be effectively changed by the move. Note that
* CacheInvalidateHeapTuple only queues the request, it doesn't send it;
* if we fail before reaching EndNonTransactionalInvalidation, nothing
* happens and no harm is done.
*/
if (OffsetNumberIsValid(redirect_target))
{
ItemId firstlp = PageGetItemId(dp, redirect_target);
HeapTupleData firsttup;
Assert(ItemIdIsNormal(firstlp));
/* Set up firsttup to reference the tuple at its existing CTID */
firsttup.t_data = (HeapTupleHeader) PageGetItem(dp, firstlp);
firsttup.t_len = ItemIdGetLength(firstlp);
ItemPointerSet(&firsttup.t_self,
BufferGetBlockNumber(buffer),
redirect_target);
CacheInvalidateHeapTuple(relation, &firsttup);
}
return ndeleted;
}
/*
* Traverse the tree to find path from root page to specified "child" block.
*
* returns a new insertion stack, starting from the parent of "child", up
* to the root. *downlinkoffnum is set to the offset of the downlink in the
* direct parent of child.
*
* To prevent deadlocks, this should lock only one page at a time.
*/
static GISTInsertStack *
gistFindPath(Relation r, BlockNumber child, OffsetNumber *downlinkoffnum)
{
Page page;
Buffer buffer;
OffsetNumber i,
maxoff;
ItemId iid;
IndexTuple idxtuple;
List *fifo;
GISTInsertStack *top,
*ptr;
BlockNumber blkno;
top = (GISTInsertStack *) palloc0(sizeof(GISTInsertStack));
top->blkno = GIST_ROOT_BLKNO;
top->downlinkoffnum = InvalidOffsetNumber;
fifo = list_make1(top);
while (fifo != NIL)
{
/* Get next page to visit */
top = linitial(fifo);
fifo = list_delete_first(fifo);
buffer = ReadBuffer(r, top->blkno);
LockBuffer(buffer, GIST_SHARE);
gistcheckpage(r, buffer);
page = (Page) BufferGetPage(buffer);
if (GistPageIsLeaf(page))
{
/*
* Because we scan the index top-down, all the rest of the pages
* in the queue must be leaf pages as well.
*/
UnlockReleaseBuffer(buffer);
break;
}
top->lsn = PageGetLSN(page);
/*
* If F_FOLLOW_RIGHT is set, the page to the right doesn't have a
* downlink. This should not normally happen..
*/
if (GistFollowRight(page))
elog(ERROR, "concurrent GiST page split was incomplete");
if (top->parent && top->parent->lsn < GistPageGetNSN(page) &&
GistPageGetOpaque(page)->rightlink != InvalidBlockNumber /* sanity check */ )
{
/*
* Page was split while we looked elsewhere. We didn't see the
* downlink to the right page when we scanned the parent, so add
* it to the queue now.
*
* Put the right page ahead of the queue, so that we visit it
* next. That's important, because if this is the lowest internal
* level, just above leaves, we might already have queued up some
* leaf pages, and we assume that there can't be any non-leaf
* pages behind leaf pages.
*/
ptr = (GISTInsertStack *) palloc0(sizeof(GISTInsertStack));
ptr->blkno = GistPageGetOpaque(page)->rightlink;
ptr->downlinkoffnum = InvalidOffsetNumber;
ptr->parent = top->parent;
fifo = lcons(ptr, fifo);
}
maxoff = PageGetMaxOffsetNumber(page);
for (i = FirstOffsetNumber; i <= maxoff; i = OffsetNumberNext(i))
{
iid = PageGetItemId(page, i);
idxtuple = (IndexTuple) PageGetItem(page, iid);
blkno = ItemPointerGetBlockNumber(&(idxtuple->t_tid));
if (blkno == child)
{
/* Found it! */
UnlockReleaseBuffer(buffer);
*downlinkoffnum = i;
return top;
}
else
{
/* Append this child to the list of pages to visit later */
ptr = (GISTInsertStack *) palloc0(sizeof(GISTInsertStack));
ptr->blkno = blkno;
ptr->downlinkoffnum = i;
ptr->parent = top;
fifo = lappend(fifo, ptr);
}
}
UnlockReleaseBuffer(buffer);
}
elog(ERROR, "failed to re-find parent of a page in index \"%s\", block %u",
RelationGetRelationName(r), child);
return NULL; /* keep compiler quiet */
}
/*
* Compute the list of TIDs to be visited, by evaluating the expressions
* for them.
*
* (The result is actually an array, not a list.)
*/
static void
TidListCreate(TidScanState *tidstate)
{
List *evalList = tidstate->tss_tidquals;
ExprContext *econtext = tidstate->ss.ps.ps_ExprContext;
BlockNumber nblocks;
ItemPointerData *tidList;
int numAllocTids;
int numTids;
ListCell *l;
/*
* We silently discard any TIDs that are out of range at the time of scan
* start. (Since we hold at least AccessShareLock on the table, it won't
* be possible for someone to truncate away the blocks we intend to
* visit.)
*/
nblocks = RelationGetNumberOfBlocks(tidstate->ss.ss_currentRelation);
/*
* We initialize the array with enough slots for the case that all quals
* are simple OpExprs or CurrentOfExprs. If there are any
* ScalarArrayOpExprs, we may have to enlarge the array.
*/
numAllocTids = list_length(evalList);
tidList = (ItemPointerData *)
palloc(numAllocTids * sizeof(ItemPointerData));
numTids = 0;
tidstate->tss_isCurrentOf = false;
foreach(l, evalList)
{
ExprState *exstate = (ExprState *) lfirst(l);
Expr *expr = exstate->expr;
ItemPointer itemptr;
bool isNull;
if (is_opclause(expr))
{
FuncExprState *fexstate = (FuncExprState *) exstate;
Node *arg1;
Node *arg2;
arg1 = get_leftop(expr);
arg2 = get_rightop(expr);
if (IsCTIDVar(arg1))
exstate = (ExprState *) lsecond(fexstate->args);
else if (IsCTIDVar(arg2))
exstate = (ExprState *) linitial(fexstate->args);
else
elog(ERROR, "could not identify CTID variable");
itemptr = (ItemPointer)
DatumGetPointer(ExecEvalExprSwitchContext(exstate,
econtext,
&isNull,
NULL));
if (!isNull &&
ItemPointerIsValid(itemptr) &&
ItemPointerGetBlockNumber(itemptr) < nblocks)
{
if (numTids >= numAllocTids)
{
numAllocTids *= 2;
tidList = (ItemPointerData *)
repalloc(tidList,
numAllocTids * sizeof(ItemPointerData));
}
tidList[numTids++] = *itemptr;
}
}
else if (expr && IsA(expr, ScalarArrayOpExpr))
{
ScalarArrayOpExprState *saexstate = (ScalarArrayOpExprState *) exstate;
Datum arraydatum;
ArrayType *itemarray;
Datum *ipdatums;
bool *ipnulls;
int ndatums;
int i;
exstate = (ExprState *) lsecond(saexstate->fxprstate.args);
arraydatum = ExecEvalExprSwitchContext(exstate,
econtext,
&isNull,
NULL);
if (isNull)
continue;
itemarray = DatumGetArrayTypeP(arraydatum);
deconstruct_array(itemarray,
TIDOID, SizeOfIptrData, false, 's',
&ipdatums, &ipnulls, &ndatums);
if (numTids + ndatums > numAllocTids)
{
numAllocTids = numTids + ndatums;
tidList = (ItemPointerData *)
repalloc(tidList,
numAllocTids * sizeof(ItemPointerData));
}
for (i = 0; i < ndatums; i++)
{
if (!ipnulls[i])
{
itemptr = (ItemPointer) DatumGetPointer(ipdatums[i]);
if (ItemPointerIsValid(itemptr) &&
ItemPointerGetBlockNumber(itemptr) < nblocks)
tidList[numTids++] = *itemptr;
}
}
pfree(ipdatums);
pfree(ipnulls);
}
else if (expr && IsA(expr, CurrentOfExpr))
{
CurrentOfExpr *cexpr = (CurrentOfExpr *) expr;
ItemPointerData cursor_tid;
if (execCurrentOf(cexpr, econtext,
RelationGetRelid(tidstate->ss.ss_currentRelation),
&cursor_tid))
{
if (numTids >= numAllocTids)
{
numAllocTids *= 2;
tidList = (ItemPointerData *)
repalloc(tidList,
numAllocTids * sizeof(ItemPointerData));
}
tidList[numTids++] = cursor_tid;
tidstate->tss_isCurrentOf = true;
}
}
else
elog(ERROR, "could not identify CTID expression");
}
/*
* Get the latestRemovedXid from the heap pages pointed at by the index
* tuples being deleted. See also btree_xlog_delete_get_latestRemovedXid,
* on which this function is based.
*/
static TransactionId
gistRedoDeleteRecordGetLatestRemovedXid(XLogReaderState *record)
{
gistxlogDelete *xlrec = (gistxlogDelete *) XLogRecGetData(record);
OffsetNumber *todelete;
Buffer ibuffer,
hbuffer;
Page ipage,
hpage;
RelFileNode rnode;
BlockNumber blkno;
ItemId iitemid,
hitemid;
IndexTuple itup;
HeapTupleHeader htuphdr;
BlockNumber hblkno;
OffsetNumber hoffnum;
TransactionId latestRemovedXid = InvalidTransactionId;
int i;
/*
* If there's nothing running on the standby we don't need to derive a
* full latestRemovedXid value, so use a fast path out of here. This
* returns InvalidTransactionId, and so will conflict with all HS
* transactions; but since we just worked out that that's zero people,
* it's OK.
*
* XXX There is a race condition here, which is that a new backend might
* start just after we look. If so, it cannot need to conflict, but this
* coding will result in throwing a conflict anyway.
*/
if (CountDBBackends(InvalidOid) == 0)
return latestRemovedXid;
/*
* In what follows, we have to examine the previous state of the index
* page, as well as the heap page(s) it points to. This is only valid if
* WAL replay has reached a consistent database state; which means that
* the preceding check is not just an optimization, but is *necessary*. We
* won't have let in any user sessions before we reach consistency.
*/
if (!reachedConsistency)
elog(PANIC, "gistRedoDeleteRecordGetLatestRemovedXid: cannot operate with inconsistent data");
/*
* Get index page. If the DB is consistent, this should not fail, nor
* should any of the heap page fetches below. If one does, we return
* InvalidTransactionId to cancel all HS transactions. That's probably
* overkill, but it's safe, and certainly better than panicking here.
*/
XLogRecGetBlockTag(record, 0, &rnode, NULL, &blkno);
ibuffer = XLogReadBufferExtended(rnode, MAIN_FORKNUM, blkno, RBM_NORMAL);
if (!BufferIsValid(ibuffer))
return InvalidTransactionId;
LockBuffer(ibuffer, BUFFER_LOCK_EXCLUSIVE);
ipage = (Page) BufferGetPage(ibuffer);
/*
* Loop through the deleted index items to obtain the TransactionId from
* the heap items they point to.
*/
todelete = (OffsetNumber *) ((char *) xlrec + SizeOfGistxlogDelete);
for (i = 0; i < xlrec->ntodelete; i++)
{
/*
* Identify the index tuple about to be deleted
*/
iitemid = PageGetItemId(ipage, todelete[i]);
itup = (IndexTuple) PageGetItem(ipage, iitemid);
/*
* Locate the heap page that the index tuple points at
*/
hblkno = ItemPointerGetBlockNumber(&(itup->t_tid));
hbuffer = XLogReadBufferExtended(xlrec->hnode, MAIN_FORKNUM, hblkno, RBM_NORMAL);
if (!BufferIsValid(hbuffer))
{
UnlockReleaseBuffer(ibuffer);
return InvalidTransactionId;
}
LockBuffer(hbuffer, BUFFER_LOCK_SHARE);
hpage = (Page) BufferGetPage(hbuffer);
/*
* Look up the heap tuple header that the index tuple points at by
* using the heap node supplied with the xlrec. We can't use
* heap_fetch, since it uses ReadBuffer rather than XLogReadBuffer.
* Note that we are not looking at tuple data here, just headers.
*/
hoffnum = ItemPointerGetOffsetNumber(&(itup->t_tid));
hitemid = PageGetItemId(hpage, hoffnum);
/*
* Follow any redirections until we find something useful.
*/
while (ItemIdIsRedirected(hitemid))
{
hoffnum = ItemIdGetRedirect(hitemid);
hitemid = PageGetItemId(hpage, hoffnum);
CHECK_FOR_INTERRUPTS();
}
/*
* If the heap item has storage, then read the header and use that to
* set latestRemovedXid.
*
* Some LP_DEAD items may not be accessible, so we ignore them.
*/
if (ItemIdHasStorage(hitemid))
{
htuphdr = (HeapTupleHeader) PageGetItem(hpage, hitemid);
HeapTupleHeaderAdvanceLatestRemovedXid(htuphdr, &latestRemovedXid);
}
else if (ItemIdIsDead(hitemid))
{
/*
* Conjecture: if hitemid is dead then it had xids before the xids
* marked on LP_NORMAL items. So we just ignore this item and move
* onto the next, for the purposes of calculating
* latestRemovedxids.
*/
}
else
Assert(!ItemIdIsUsed(hitemid));
UnlockReleaseBuffer(hbuffer);
}
UnlockReleaseBuffer(ibuffer);
/*
* If all heap tuples were LP_DEAD then we will be returning
* InvalidTransactionId here, which avoids conflicts. This matches
* existing logic which assumes that LP_DEAD tuples must already be older
* than the latestRemovedXid on the cleanup record that set them as
* LP_DEAD, hence must already have generated a conflict.
*/
return latestRemovedXid;
}
