/*
* Per-heap-tuple callback for IndexBuildHeapScan.
*
* Note we don't worry about the page range at the end of the table here; it is
* present in the build state struct after we're called the last time, but not
* inserted into the index. Caller must ensure to do so, if appropriate.
*/
static void
brinbuildCallback(Relation index,
HeapTuple htup,
Datum *values,
bool *isnull,
bool tupleIsAlive,
void *brstate)
{
BrinBuildState *state = (BrinBuildState *) brstate;
BlockNumber thisblock;
int i;
thisblock = ItemPointerGetBlockNumber(&htup->t_self);
/*
* If we're in a block that belongs to a future range, summarize what
* we've got and start afresh. Note the scan might have skipped many
* pages, if they were devoid of live tuples; make sure to insert index
* tuples for those too.
*/
while (thisblock > state->bs_currRangeStart + state->bs_pagesPerRange - 1)
{
BRIN_elog((DEBUG2,
"brinbuildCallback: completed a range: %u--%u",
state->bs_currRangeStart,
state->bs_currRangeStart + state->bs_pagesPerRange));
/* create the index tuple and insert it */
form_and_insert_tuple(state);
/* set state to correspond to the next range */
state->bs_currRangeStart += state->bs_pagesPerRange;
/* re-initialize state for it */
brin_memtuple_initialize(state->bs_dtuple, state->bs_bdesc);
}
/* Accumulate the current tuple into the running state */
for (i = 0; i < state->bs_bdesc->bd_tupdesc->natts; i++)
{
FmgrInfo *addValue;
BrinValues *col;
Form_pg_attribute attr = TupleDescAttr(state->bs_bdesc->bd_tupdesc, i);
col = &state->bs_dtuple->bt_columns[i];
addValue = index_getprocinfo(index, i + 1,
BRIN_PROCNUM_ADDVALUE);
/*
* Update dtuple state, if and as necessary.
*/
FunctionCall4Coll(addValue,
attr->attcollation,
PointerGetDatum(state->bs_bdesc),
PointerGetDatum(col),
values[i], isnull[i]);
}
}
/*
* gistindex_keytest() -- does this index tuple satisfy the scan key(s)?
*
* The index tuple might represent either a heap tuple or a lower index page,
* depending on whether the containing page is a leaf page or not.
*
* On success return for a heap tuple, *recheck_p is set to indicate
* whether recheck is needed. We recheck if any of the consistent() functions
* request it. recheck is not interesting when examining a non-leaf entry,
* since we must visit the lower index page if there's any doubt.
*
* If we are doing an ordered scan, so->distances[] is filled with distance
* data from the distance() functions before returning success.
*
* We must decompress the key in the IndexTuple before passing it to the
* sk_funcs (which actually are the opclass Consistent or Distance methods).
*
* Note that this function is always invoked in a short-lived memory context,
* so we don't need to worry about cleaning up allocated memory, either here
* or in the implementation of any Consistent or Distance methods.
*/
static bool
gistindex_keytest(IndexScanDesc scan,
IndexTuple tuple,
Page page,
OffsetNumber offset,
bool *recheck_p)
{
GISTScanOpaque so = (GISTScanOpaque) scan->opaque;
GISTSTATE *giststate = so->giststate;
ScanKey key = scan->keyData;
int keySize = scan->numberOfKeys;
double *distance_p;
Relation r = scan->indexRelation;
*recheck_p = false;
/*
* If it's a leftover invalid tuple from pre-9.1, treat it as a match with
* minimum possible distances. This means we'll always follow it to the
* referenced page.
*
* GPDB: the virtual TIDs created for AO tables use the full range of
* offset numbers from 0 to 65535. So a tuple on leaf page that looks like
* an invalid tuple, is actually ok.
*/
if (!GistPageIsLeaf(page) && GistTupleIsInvalid(tuple))
{
int i;
for (i = 0; i < scan->numberOfOrderBys; i++)
so->distances[i] = -get_float8_infinity();
return true;
}
/* Check whether it matches according to the Consistent functions */
while (keySize > 0)
{
Datum datum;
bool isNull;
datum = index_getattr(tuple,
key->sk_attno,
giststate->tupdesc,
&isNull);
if (key->sk_flags & SK_ISNULL)
{
/*
* On non-leaf page we can't conclude that child hasn't NULL
* values because of assumption in GiST: union (VAL, NULL) is VAL.
* But if on non-leaf page key IS NULL, then all children are
* NULL.
*/
if (key->sk_flags & SK_SEARCHNULL)
{
if (GistPageIsLeaf(page) && !isNull)
return false;
}
else
{
Assert(key->sk_flags & SK_SEARCHNOTNULL);
if (isNull)
return false;
}
}
else if (isNull)
{
return false;
}
else
{
Datum test;
bool recheck;
GISTENTRY de;
gistdentryinit(giststate, key->sk_attno - 1, &de,
datum, r, page, offset,
FALSE, isNull);
/*
* Call the Consistent function to evaluate the test. The
* arguments are the index datum (as a GISTENTRY*), the comparison
* datum, the comparison operator's strategy number and subtype
* from pg_amop, and the recheck flag.
*
* (Presently there's no need to pass the subtype since it'll
* always be zero, but might as well pass it for possible future
* use.)
*
* We initialize the recheck flag to true (the safest assumption)
* in case the Consistent function forgets to set it.
*/
recheck = true;
test = FunctionCall5Coll(&key->sk_func,
key->sk_collation,
PointerGetDatum(&de),
key->sk_argument,
Int32GetDatum(key->sk_strategy),
ObjectIdGetDatum(key->sk_subtype),
PointerGetDatum(&recheck));
if (!DatumGetBool(test))
return false;
*recheck_p |= recheck;
}
key++;
keySize--;
}
/* OK, it passes --- now let's compute the distances */
key = scan->orderByData;
distance_p = so->distances;
keySize = scan->numberOfOrderBys;
while (keySize > 0)
{
Datum datum;
bool isNull;
datum = index_getattr(tuple,
key->sk_attno,
giststate->tupdesc,
&isNull);
if ((key->sk_flags & SK_ISNULL) || isNull)
{
/* Assume distance computes as null and sorts to the end */
*distance_p = get_float8_infinity();
}
else
{
Datum dist;
GISTENTRY de;
gistdentryinit(giststate, key->sk_attno - 1, &de,
datum, r, page, offset,
FALSE, isNull);
/*
* Call the Distance function to evaluate the distance. The
* arguments are the index datum (as a GISTENTRY*), the comparison
* datum, and the ordering operator's strategy number and subtype
* from pg_amop.
*
* (Presently there's no need to pass the subtype since it'll
* always be zero, but might as well pass it for possible future
* use.)
*
* Note that Distance functions don't get a recheck argument. We
* can't tolerate lossy distance calculations on leaf tuples;
* there is no opportunity to re-sort the tuples afterwards.
*/
dist = FunctionCall4Coll(&key->sk_func,
key->sk_collation,
PointerGetDatum(&de),
key->sk_argument,
Int32GetDatum(key->sk_strategy),
ObjectIdGetDatum(key->sk_subtype));
*distance_p = DatumGetFloat8(dist);
}
key++;
distance_p++;
keySize--;
}
return true;
}
/*
* A tuple in the heap is being inserted. To keep a brin index up to date,
* we need to obtain the relevant index tuple and compare its stored values
* with those of the new tuple. If the tuple values are not consistent with
* the summary tuple, we need to update the index tuple.
*
* If the range is not currently summarized (i.e. the revmap returns NULL for
* it), there's nothing to do.
*/
bool
brininsert(Relation idxRel, Datum *values, bool *nulls,
ItemPointer heaptid, Relation heapRel,
IndexUniqueCheck checkUnique)
{
BlockNumber pagesPerRange;
BrinDesc *bdesc = NULL;
BrinRevmap *revmap;
Buffer buf = InvalidBuffer;
MemoryContext tupcxt = NULL;
MemoryContext oldcxt = NULL;
revmap = brinRevmapInitialize(idxRel, &pagesPerRange, NULL);
for (;;)
{
bool need_insert = false;
OffsetNumber off;
BrinTuple *brtup;
BrinMemTuple *dtup;
BlockNumber heapBlk;
int keyno;
CHECK_FOR_INTERRUPTS();
heapBlk = ItemPointerGetBlockNumber(heaptid);
/* normalize the block number to be the first block in the range */
heapBlk = (heapBlk / pagesPerRange) * pagesPerRange;
brtup = brinGetTupleForHeapBlock(revmap, heapBlk, &buf, &off, NULL,
BUFFER_LOCK_SHARE, NULL);
/* if range is unsummarized, there's nothing to do */
if (!brtup)
break;
/* First time through? */
if (bdesc == NULL)
{
bdesc = brin_build_desc(idxRel);
tupcxt = AllocSetContextCreate(CurrentMemoryContext,
"brininsert cxt",
ALLOCSET_DEFAULT_SIZES);
oldcxt = MemoryContextSwitchTo(tupcxt);
}
dtup = brin_deform_tuple(bdesc, brtup);
/*
* Compare the key values of the new tuple to the stored index values;
* our deformed tuple will get updated if the new tuple doesn't fit
* the original range (note this means we can't break out of the loop
* early). Make a note of whether this happens, so that we know to
* insert the modified tuple later.
*/
for (keyno = 0; keyno < bdesc->bd_tupdesc->natts; keyno++)
{
Datum result;
BrinValues *bval;
FmgrInfo *addValue;
bval = &dtup->bt_columns[keyno];
addValue = index_getprocinfo(idxRel, keyno + 1,
BRIN_PROCNUM_ADDVALUE);
result = FunctionCall4Coll(addValue,
idxRel->rd_indcollation[keyno],
PointerGetDatum(bdesc),
PointerGetDatum(bval),
values[keyno],
nulls[keyno]);
/* if that returned true, we need to insert the updated tuple */
need_insert |= DatumGetBool(result);
}
if (!need_insert)
{
/*
* The tuple is consistent with the new values, so there's nothing
* to do.
*/
LockBuffer(buf, BUFFER_LOCK_UNLOCK);
}
else
{
Page page = BufferGetPage(buf);
ItemId lp = PageGetItemId(page, off);
Size origsz;
BrinTuple *origtup;
Size newsz;
BrinTuple *newtup;
bool samepage;
/*
* Make a copy of the old tuple, so that we can compare it after
* re-acquiring the lock.
*/
origsz = ItemIdGetLength(lp);
origtup = brin_copy_tuple(brtup, origsz);
/*
* Before releasing the lock, check if we can attempt a same-page
* update. Another process could insert a tuple concurrently in
* the same page though, so downstream we must be prepared to cope
* if this turns out to not be possible after all.
*/
newtup = brin_form_tuple(bdesc, heapBlk, dtup, &newsz);
samepage = brin_can_do_samepage_update(buf, origsz, newsz);
LockBuffer(buf, BUFFER_LOCK_UNLOCK);
/*
* Try to update the tuple. If this doesn't work for whatever
* reason, we need to restart from the top; the revmap might be
* pointing at a different tuple for this block now, so we need to
* recompute to ensure both our new heap tuple and the other
* inserter's are covered by the combined tuple. It might be that
* we don't need to update at all.
*/
if (!brin_doupdate(idxRel, pagesPerRange, revmap, heapBlk,
buf, off, origtup, origsz, newtup, newsz,
samepage))
{
/* no luck; start over */
MemoryContextResetAndDeleteChildren(tupcxt);
continue;
}
}
/* success! */
break;
}
brinRevmapTerminate(revmap);
if (BufferIsValid(buf))
ReleaseBuffer(buf);
if (bdesc != NULL)
{
brin_free_desc(bdesc);
MemoryContextSwitchTo(oldcxt);
MemoryContextDelete(tupcxt);
}
return false;
}
/*
* 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);
}
/*
* 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;
}
