/*
* On the given BRIN index, summarize the heap page range that corresponds
* to the heap block number given.
*
* This routine can run in parallel with insertions into the heap. To avoid
* missing those values from the summary tuple, we first insert a placeholder
* index tuple into the index, then execute the heap scan; transactions
* concurrent with the scan update the placeholder tuple. After the scan, we
* union the placeholder tuple with the one computed by this routine. The
* update of the index value happens in a loop, so that if somebody updates
* the placeholder tuple after we read it, we detect the case and try again.
* This ensures that the concurrently inserted tuples are not lost.
*
* A further corner case is this routine being asked to summarize the partial
* range at the end of the table. heapNumBlocks is the (possibly outdated)
* table size; if we notice that the requested range lies beyond that size,
* we re-compute the table size after inserting the placeholder tuple, to
* avoid missing pages that were appended recently.
*/
static void
summarize_range(IndexInfo *indexInfo, BrinBuildState *state, Relation heapRel,
BlockNumber heapBlk, BlockNumber heapNumBlks)
{
Buffer phbuf;
BrinTuple *phtup;
Size phsz;
OffsetNumber offset;
BlockNumber scanNumBlks;
/*
* Insert the placeholder tuple
*/
phbuf = InvalidBuffer;
phtup = brin_form_placeholder_tuple(state->bs_bdesc, heapBlk, &phsz);
offset = brin_doinsert(state->bs_irel, state->bs_pagesPerRange,
state->bs_rmAccess, &phbuf,
heapBlk, phtup, phsz);
/*
* Compute range end. We hold ShareUpdateExclusive lock on table, so it
* cannot shrink concurrently (but it can grow).
*/
Assert(heapBlk % state->bs_pagesPerRange == 0);
if (heapBlk + state->bs_pagesPerRange > heapNumBlks)
{
/*
* If we're asked to scan what we believe to be the final range on the
* table (i.e. a range that might be partial) we need to recompute our
* idea of what the latest page is after inserting the placeholder
* tuple. Anyone that grows the table later will update the
* placeholder tuple, so it doesn't matter that we won't scan these
* pages ourselves. Careful: the table might have been extended
* beyond the current range, so clamp our result.
*
* Fortunately, this should occur infrequently.
*/
scanNumBlks = Min(RelationGetNumberOfBlocks(heapRel) - heapBlk,
state->bs_pagesPerRange);
}
else
{
/* Easy case: range is known to be complete */
scanNumBlks = state->bs_pagesPerRange;
}
/*
* Execute the partial heap scan covering the heap blocks in the specified
* page range, summarizing the heap tuples in it. This scan stops just
* short of brinbuildCallback creating the new index entry.
*
* Note that it is critical we use the "any visible" mode of
* IndexBuildHeapRangeScan here: otherwise, we would miss tuples inserted
* by transactions that are still in progress, among other corner cases.
*/
state->bs_currRangeStart = heapBlk;
IndexBuildHeapRangeScan(heapRel, state->bs_irel, indexInfo, false, true,
heapBlk, scanNumBlks,
brinbuildCallback, (void *) state);
/*
* Now we update the values obtained by the scan with the placeholder
* tuple. We do this in a loop which only terminates if we're able to
* update the placeholder tuple successfully; if we are not, this means
* somebody else modified the placeholder tuple after we read it.
*/
for (;;)
{
BrinTuple *newtup;
Size newsize;
bool didupdate;
bool samepage;
CHECK_FOR_INTERRUPTS();
/*
* Update the summary tuple and try to update.
*/
newtup = brin_form_tuple(state->bs_bdesc,
heapBlk, state->bs_dtuple, &newsize);
samepage = brin_can_do_samepage_update(phbuf, phsz, newsize);
didupdate =
brin_doupdate(state->bs_irel, state->bs_pagesPerRange,
state->bs_rmAccess, heapBlk, phbuf, offset,
phtup, phsz, newtup, newsize, samepage);
brin_free_tuple(phtup);
brin_free_tuple(newtup);
/* If the update succeeded, we're done. */
if (didupdate)
break;
/*
* If the update didn't work, it might be because somebody updated the
* placeholder tuple concurrently. Extract the new version, union it
* with the values we have from the scan, and start over. (There are
* other reasons for the update to fail, but it's simple to treat them
* the same.)
*/
phtup = brinGetTupleForHeapBlock(state->bs_rmAccess, heapBlk, &phbuf,
&offset, &phsz, BUFFER_LOCK_SHARE,
NULL);
/* the placeholder tuple must exist */
if (phtup == NULL)
elog(ERROR, "missing placeholder tuple");
phtup = brin_copy_tuple(phtup, phsz);
LockBuffer(phbuf, BUFFER_LOCK_UNLOCK);
/* merge it into the tuple from the heap scan */
union_tuples(state->bs_bdesc, state->bs_dtuple, phtup);
}
ReleaseBuffer(phbuf);
}
/*
* Summarize the given page range of the given index.
*
* This routine can run in parallel with insertions into the heap. To avoid
* missing those values from the summary tuple, we first insert a placeholder
* index tuple into the index, then execute the heap scan; transactions
* concurrent with the scan update the placeholder tuple. After the scan, we
* union the placeholder tuple with the one computed by this routine. The
* update of the index value happens in a loop, so that if somebody updates
* the placeholder tuple after we read it, we detect the case and try again.
* This ensures that the concurrently inserted tuples are not lost.
*/
static void
summarize_range(IndexInfo *indexInfo, BrinBuildState *state, Relation heapRel,
BlockNumber heapBlk, BlockNumber heapNumBlks)
{
Buffer phbuf;
BrinTuple *phtup;
Size phsz;
OffsetNumber offset;
BlockNumber scanNumBlks;
/*
* Insert the placeholder tuple
*/
phbuf = InvalidBuffer;
phtup = brin_form_placeholder_tuple(state->bs_bdesc, heapBlk, &phsz);
offset = brin_doinsert(state->bs_irel, state->bs_pagesPerRange,
state->bs_rmAccess, &phbuf,
heapBlk, phtup, phsz);
/*
* Execute the partial heap scan covering the heap blocks in the specified
* page range, summarizing the heap tuples in it. This scan stops just
* short of brinbuildCallback creating the new index entry.
*
* Note that it is critical we use the "any visible" mode of
* IndexBuildHeapRangeScan here: otherwise, we would miss tuples inserted
* by transactions that are still in progress, among other corner cases.
*/
state->bs_currRangeStart = heapBlk;
scanNumBlks = heapBlk + state->bs_pagesPerRange <= heapNumBlks ?
state->bs_pagesPerRange : heapNumBlks - heapBlk;
IndexBuildHeapRangeScan(heapRel, state->bs_irel, indexInfo, false, true,
heapBlk, scanNumBlks,
brinbuildCallback, (void *) state);
/*
* Now we update the values obtained by the scan with the placeholder
* tuple. We do this in a loop which only terminates if we're able to
* update the placeholder tuple successfully; if we are not, this means
* somebody else modified the placeholder tuple after we read it.
*/
for (;;)
{
BrinTuple *newtup;
Size newsize;
bool didupdate;
bool samepage;
CHECK_FOR_INTERRUPTS();
/*
* Update the summary tuple and try to update.
*/
newtup = brin_form_tuple(state->bs_bdesc,
heapBlk, state->bs_dtuple, &newsize);
samepage = brin_can_do_samepage_update(phbuf, phsz, newsize);
didupdate =
brin_doupdate(state->bs_irel, state->bs_pagesPerRange,
state->bs_rmAccess, heapBlk, phbuf, offset,
phtup, phsz, newtup, newsize, samepage);
brin_free_tuple(phtup);
brin_free_tuple(newtup);
/* If the update succeeded, we're done. */
if (didupdate)
break;
/*
* If the update didn't work, it might be because somebody updated the
* placeholder tuple concurrently. Extract the new version, union it
* with the values we have from the scan, and start over. (There are
* other reasons for the update to fail, but it's simple to treat them
* the same.)
*/
phtup = brinGetTupleForHeapBlock(state->bs_rmAccess, heapBlk, &phbuf,
&offset, &phsz, BUFFER_LOCK_SHARE,
NULL);
/* the placeholder tuple must exist */
if (phtup == NULL)
elog(ERROR, "missing placeholder tuple");
phtup = brin_copy_tuple(phtup, phsz);
LockBuffer(phbuf, BUFFER_LOCK_UNLOCK);
/* merge it into the tuple from the heap scan */
union_tuples(state->bs_bdesc, state->bs_dtuple, phtup);
}
ReleaseBuffer(phbuf);
}
/*
* 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);
}