/*
* Initialize state for a BRIN index scan.
*
* We read the metapage here to determine the pages-per-range number that this
* index was built with. Note that since this cannot be changed while we're
* holding lock on index, it's not necessary to recompute it during brinrescan.
*/
IndexScanDesc
brinbeginscan(Relation r, int nkeys, int norderbys)
{
IndexScanDesc scan;
BrinOpaque *opaque;
scan = RelationGetIndexScan(r, nkeys, norderbys);
opaque = (BrinOpaque *) palloc(sizeof(BrinOpaque));
opaque->bo_rmAccess = brinRevmapInitialize(r, &opaque->bo_pagesPerRange,
scan->xs_snapshot);
opaque->bo_bdesc = brin_build_desc(r);
scan->opaque = opaque;
return scan;
}
/*
* Initialize state for a BRIN index scan.
*
* We read the metapage here to determine the pages-per-range number that this
* index was built with. Note that since this cannot be changed while we're
* holding lock on index, it's not necessary to recompute it during brinrescan.
*/
Datum
brinbeginscan(PG_FUNCTION_ARGS)
{
Relation r = (Relation) PG_GETARG_POINTER(0);
int nkeys = PG_GETARG_INT32(1);
int norderbys = PG_GETARG_INT32(2);
IndexScanDesc scan;
BrinOpaque *opaque;
scan = RelationGetIndexScan(r, nkeys, norderbys);
opaque = (BrinOpaque *) palloc(sizeof(BrinOpaque));
opaque->bo_rmAccess = brinRevmapInitialize(r, &opaque->bo_pagesPerRange);
opaque->bo_bdesc = brin_build_desc(r);
scan->opaque = opaque;
PG_RETURN_POINTER(scan);
}
/*
* brinbuild() -- build a new BRIN index.
*/
IndexBuildResult *
brinbuild(Relation heap, Relation index, IndexInfo *indexInfo)
{
ereport(LOG,(errmsg("brinbuild start")));
IndexBuildResult *result;
double reltuples;
double idxtuples;
BrinRevmap *revmap;
BrinBuildState *state;
Buffer meta;
BlockNumber pagesPerRange;
/*
* We expect to be called exactly once for any index relation.
*/
if (RelationGetNumberOfBlocks(index) != 0)
elog(ERROR, "index \"%s\" already contains data",
RelationGetRelationName(index));
/*
* Critical section not required, because on error the creation of the
* whole relation will be rolled back.
*/
meta = ReadBuffer(index, P_NEW);
Assert(BufferGetBlockNumber(meta) == BRIN_METAPAGE_BLKNO);
LockBuffer(meta, BUFFER_LOCK_EXCLUSIVE);
brin_metapage_init(BufferGetPage(meta), BrinGetPagesPerRange(index),
BRIN_CURRENT_VERSION);
MarkBufferDirty(meta);
if (RelationNeedsWAL(index))
{
xl_brin_createidx xlrec;
XLogRecPtr recptr;
Page page;
xlrec.version = BRIN_CURRENT_VERSION;
xlrec.pagesPerRange = BrinGetPagesPerRange(index);
XLogBeginInsert();
XLogRegisterData((char *) &xlrec, SizeOfBrinCreateIdx);
XLogRegisterBuffer(0, meta, REGBUF_WILL_INIT);
recptr = XLogInsert(RM_BRIN_ID, XLOG_BRIN_CREATE_INDEX);
page = BufferGetPage(meta);
PageSetLSN(page, recptr);
}
UnlockReleaseBuffer(meta);
/*
* Initialize our state, including the deformed tuple state.
*/
revmap = brinRevmapInitialize(index, &pagesPerRange, NULL);
state = initialize_brin_buildstate(index, revmap, pagesPerRange);
/*
* Now scan the relation. No syncscan allowed here because we want the
* heap blocks in physical order.
*/
reltuples = IndexBuildHeapScan(heap, index, indexInfo, false,
brinbuildCallback, (void *) state);
/* process the final batch */
form_and_insert_tuple(state);
/* release resources */
idxtuples = state->bs_numtuples;
brinRevmapTerminate(state->bs_rmAccess);
terminate_brin_buildstate(state);
/*
* Return statistics
*/
result = (IndexBuildResult *) palloc(sizeof(IndexBuildResult));
result->heap_tuples = reltuples;
result->index_tuples = idxtuples;
ereport(LOG,(errmsg("brinbuild stop")));
return result;
}
/*
* 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;
}
/*
* Scan a complete BRIN index, and summarize each page range that's not already
* summarized. The index and heap must have been locked by caller in at
* least ShareUpdateExclusiveLock mode.
*
* For each new index tuple inserted, *numSummarized (if not NULL) is
* incremented; for each existing tuple, *numExisting (if not NULL) is
* incremented.
*/
static void
brinsummarize(Relation index, Relation heapRel, double *numSummarized,
double *numExisting)
{
BrinRevmap *revmap;
BrinBuildState *state = NULL;
IndexInfo *indexInfo = NULL;
BlockNumber heapNumBlocks;
BlockNumber heapBlk;
BlockNumber pagesPerRange;
Buffer buf;
revmap = brinRevmapInitialize(index, &pagesPerRange, NULL);
/*
* Scan the revmap to find unsummarized items.
*/
buf = InvalidBuffer;
heapNumBlocks = RelationGetNumberOfBlocks(heapRel);
for (heapBlk = 0; heapBlk < heapNumBlocks; heapBlk += pagesPerRange)
{
BrinTuple *tup;
OffsetNumber off;
CHECK_FOR_INTERRUPTS();
tup = brinGetTupleForHeapBlock(revmap, heapBlk, &buf, &off, NULL,
BUFFER_LOCK_SHARE, NULL);
if (tup == NULL)
{
/* no revmap entry for this heap range. Summarize it. */
if (state == NULL)
{
/* first time through */
Assert(!indexInfo);
state = initialize_brin_buildstate(index, revmap,
pagesPerRange);
indexInfo = BuildIndexInfo(index);
}
summarize_range(indexInfo, state, heapRel, heapBlk, heapNumBlocks);
/* and re-initialize state for the next range */
brin_memtuple_initialize(state->bs_dtuple, state->bs_bdesc);
if (numSummarized)
*numSummarized += 1.0;
}
else
{
if (numExisting)
*numExisting += 1.0;
LockBuffer(buf, BUFFER_LOCK_UNLOCK);
}
}
if (BufferIsValid(buf))
ReleaseBuffer(buf);
/* free resources */
brinRevmapTerminate(revmap);
if (state)
{
terminate_brin_buildstate(state);
pfree(indexInfo);
}
}
/*
* 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);
}
/*
* Scan a complete BRIN index, and summarize each page range that's not already
* summarized. The index and heap must have been locked by caller in at
* least ShareUpdateExclusiveLock mode.
*
* For each new index tuple inserted, *numSummarized (if not NULL) is
* incremented; for each existing tuple, numExisting (if not NULL) is
* incremented.
*/
static void
brinsummarize(Relation index, Relation heapRel, double *numSummarized,
double *numExisting)
{
BrinRevmap *revmap;
BrinBuildState *state = NULL;
IndexInfo *indexInfo = NULL;
BlockNumber heapNumBlocks;
BlockNumber heapBlk;
BlockNumber pagesPerRange;
Buffer buf;
revmap = brinRevmapInitialize(index, &pagesPerRange);
/*
* Scan the revmap to find unsummarized items.
*/
buf = InvalidBuffer;
heapNumBlocks = RelationGetNumberOfBlocks(heapRel);
for (heapBlk = 0; heapBlk < heapNumBlocks; heapBlk += pagesPerRange)
{
BrinTuple *tup;
OffsetNumber off;
CHECK_FOR_INTERRUPTS();
tup = brinGetTupleForHeapBlock(revmap, heapBlk, &buf, &off, NULL,
BUFFER_LOCK_SHARE);
if (tup == NULL)
{
/* no revmap entry for this heap range. Summarize it. */
if (state == NULL)
{
/* first time through */
Assert(!indexInfo);
state = initialize_brin_buildstate(index, revmap,
pagesPerRange);
indexInfo = BuildIndexInfo(index);
/*
* We only have ShareUpdateExclusiveLock on the table, and
* therefore other sessions may insert tuples into the range
* we're going to scan. This is okay, because we take
* additional precautions to avoid losing the additional
* tuples; see comments in summarize_range. Set the
* concurrent flag, which causes IndexBuildHeapRangeScan to
* use a snapshot other than SnapshotAny, and silences
* warnings emitted there.
*/
indexInfo->ii_Concurrent = true;
/*
* If using transaction-snapshot mode, it would be possible
* for another transaction to insert a tuple that's not
* visible to our snapshot if we have already acquired one,
* when in snapshot-isolation mode; therefore, disallow this
* from running in such a transaction unless a snapshot hasn't
* been acquired yet.
*
* This code is called by VACUUM and
* brin_summarize_new_values. Have the error message mention
* the latter because VACUUM cannot run in a transaction and
* thus cannot cause this issue.
*/
if (IsolationUsesXactSnapshot() && FirstSnapshotSet)
ereport(ERROR,
(errcode(ERRCODE_INVALID_TRANSACTION_STATE),
errmsg("brin_summarize_new_values() cannot run in a transaction that has already obtained a snapshot")));
}
summarize_range(indexInfo, state, heapRel, heapBlk);
/* and re-initialize state for the next range */
brin_memtuple_initialize(state->bs_dtuple, state->bs_bdesc);
if (numSummarized)
*numSummarized += 1.0;
}
else
{
if (numExisting)
*numExisting += 1.0;
LockBuffer(buf, BUFFER_LOCK_UNLOCK);
}
}
if (BufferIsValid(buf))
ReleaseBuffer(buf);
/* free resources */
brinRevmapTerminate(revmap);
if (state)
terminate_brin_buildstate(state);
}
/*
* 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;
}
/*
* Summarize page ranges that are not already summarized. If pageRange is
* BRIN_ALL_BLOCKRANGES then the whole table is scanned; otherwise, only the
* page range containing the given heap page number is scanned.
* If include_partial is true, then the partial range at the end of the table
* is summarized, otherwise not.
*
* For each new index tuple inserted, *numSummarized (if not NULL) is
* incremented; for each existing tuple, *numExisting (if not NULL) is
* incremented.
*/
static void
brinsummarize(Relation index, Relation heapRel, BlockNumber pageRange,
bool include_partial, double *numSummarized, double *numExisting)
{
BrinRevmap *revmap;
BrinBuildState *state = NULL;
IndexInfo *indexInfo = NULL;
BlockNumber heapNumBlocks;
BlockNumber pagesPerRange;
Buffer buf;
BlockNumber startBlk;
revmap = brinRevmapInitialize(index, &pagesPerRange, NULL);
/* determine range of pages to process */
heapNumBlocks = RelationGetNumberOfBlocks(heapRel);
if (pageRange == BRIN_ALL_BLOCKRANGES)
startBlk = 0;
else
{
startBlk = (pageRange / pagesPerRange) * pagesPerRange;
heapNumBlocks = Min(heapNumBlocks, startBlk + pagesPerRange);
}
if (startBlk > heapNumBlocks)
{
/* Nothing to do if start point is beyond end of table */
brinRevmapTerminate(revmap);
return;
}
/*
* Scan the revmap to find unsummarized items.
*/
buf = InvalidBuffer;
for (; startBlk < heapNumBlocks; startBlk += pagesPerRange)
{
BrinTuple *tup;
OffsetNumber off;
/*
* Unless requested to summarize even a partial range, go away now if
* we think the next range is partial. Caller would pass true when it
* is typically run once bulk data loading is done
* (brin_summarize_new_values), and false when it is typically the
* result of arbitrarily-scheduled maintenance command (vacuuming).
*/
if (!include_partial &&
(startBlk + pagesPerRange > heapNumBlocks))
break;
CHECK_FOR_INTERRUPTS();
tup = brinGetTupleForHeapBlock(revmap, startBlk, &buf, &off, NULL,
BUFFER_LOCK_SHARE, NULL);
if (tup == NULL)
{
/* no revmap entry for this heap range. Summarize it. */
if (state == NULL)
{
/* first time through */
Assert(!indexInfo);
state = initialize_brin_buildstate(index, revmap,
pagesPerRange);
indexInfo = BuildIndexInfo(index);
}
summarize_range(indexInfo, state, heapRel, startBlk, heapNumBlocks);
/* and re-initialize state for the next range */
brin_memtuple_initialize(state->bs_dtuple, state->bs_bdesc);
if (numSummarized)
*numSummarized += 1.0;
}
else
{
if (numExisting)
*numExisting += 1.0;
LockBuffer(buf, BUFFER_LOCK_UNLOCK);
}
}
if (BufferIsValid(buf))
ReleaseBuffer(buf);
/* free resources */
brinRevmapTerminate(revmap);
if (state)
{
terminate_brin_buildstate(state);
pfree(indexInfo);
}
}
