/*
* SQL-callable function to scan through an index and summarize all ranges
* that are not currently summarized.
*/
Datum
brin_summarize_new_values(PG_FUNCTION_ARGS)
{
Oid indexoid = PG_GETARG_OID(0);
Oid heapoid;
Relation indexRel;
Relation heapRel;
double numSummarized = 0;
/*
* We must lock table before index to avoid deadlocks. However, if the
* passed indexoid isn't an index then IndexGetRelation() will fail.
* Rather than emitting a not-very-helpful error message, postpone
* complaining, expecting that the is-it-an-index test below will fail.
*/
heapoid = IndexGetRelation(indexoid, true);
if (OidIsValid(heapoid))
heapRel = heap_open(heapoid, ShareUpdateExclusiveLock);
else
heapRel = NULL;
indexRel = index_open(indexoid, ShareUpdateExclusiveLock);
/* Must be a BRIN index */
if (indexRel->rd_rel->relkind != RELKIND_INDEX ||
indexRel->rd_rel->relam != BRIN_AM_OID)
ereport(ERROR,
(errcode(ERRCODE_WRONG_OBJECT_TYPE),
errmsg("\"%s\" is not a BRIN index",
RelationGetRelationName(indexRel))));
/* User must own the index (comparable to privileges needed for VACUUM) */
if (!pg_class_ownercheck(indexoid, GetUserId()))
aclcheck_error(ACLCHECK_NOT_OWNER, ACL_KIND_CLASS,
RelationGetRelationName(indexRel));
/*
* Since we did the IndexGetRelation call above without any lock, it's
* barely possible that a race against an index drop/recreation could have
* netted us the wrong table. Recheck.
*/
if (heapRel == NULL || heapoid != IndexGetRelation(indexoid, false))
ereport(ERROR,
(errcode(ERRCODE_UNDEFINED_TABLE),
errmsg("could not open parent table of index %s",
RelationGetRelationName(indexRel))));
/* OK, do it */
brinsummarize(indexRel, heapRel, &numSummarized, NULL);
relation_close(indexRel, ShareUpdateExclusiveLock);
relation_close(heapRel, ShareUpdateExclusiveLock);
PG_RETURN_INT32((int32) numSummarized);
}
/*
* This routine is in charge of "vacuuming" a BRIN index: we just summarize
* ranges that are currently unsummarized.
*/
IndexBulkDeleteResult *
brinvacuumcleanup(IndexVacuumInfo *info, IndexBulkDeleteResult *stats)
{
Relation heapRel;
/* No-op in ANALYZE ONLY mode */
if (info->analyze_only)
return stats;
if (!stats)
stats = (IndexBulkDeleteResult *) palloc0(sizeof(IndexBulkDeleteResult));
stats->num_pages = RelationGetNumberOfBlocks(info->index);
/* rest of stats is initialized by zeroing */
heapRel = heap_open(IndexGetRelation(RelationGetRelid(info->index), false),
AccessShareLock);
brin_vacuum_scan(info->index, info->strategy);
brinsummarize(info->index, heapRel,
&stats->num_index_tuples, &stats->num_index_tuples);
heap_close(heapRel, AccessShareLock);
return stats;
}
/*
* This routine is in charge of "vacuuming" a BRIN index: we just summarize
* ranges that are currently unsummarized.
*/
Datum
brinvacuumcleanup(PG_FUNCTION_ARGS)
{
IndexVacuumInfo *info = (IndexVacuumInfo *) PG_GETARG_POINTER(0);
IndexBulkDeleteResult *stats =
(IndexBulkDeleteResult *) PG_GETARG_POINTER(1);
Relation heapRel;
/* No-op in ANALYZE ONLY mode */
if (info->analyze_only)
PG_RETURN_POINTER(stats);
if (!stats)
stats = (IndexBulkDeleteResult *) palloc0(sizeof(IndexBulkDeleteResult));
stats->num_pages = RelationGetNumberOfBlocks(info->index);
/* rest of stats is initialized by zeroing */
heapRel = heap_open(IndexGetRelation(RelationGetRelid(info->index), false),
AccessShareLock);
brinsummarize(info->index, heapRel,
&stats->num_index_tuples, &stats->num_index_tuples);
heap_close(heapRel, AccessShareLock);
PG_RETURN_POINTER(stats);
}
/*
* SQL-callable function to scan through an index and summarize all ranges
* that are not currently summarized.
*/
Datum
brin_summarize_new_values(PG_FUNCTION_ARGS)
{
Oid indexoid = PG_GETARG_OID(0);
Relation indexRel;
Relation heapRel;
double numSummarized = 0;
heapRel = heap_open(IndexGetRelation(indexoid, false),
ShareUpdateExclusiveLock);
indexRel = index_open(indexoid, ShareUpdateExclusiveLock);
brinsummarize(indexRel, heapRel, &numSummarized, NULL);
relation_close(indexRel, ShareUpdateExclusiveLock);
relation_close(heapRel, ShareUpdateExclusiveLock);
PG_RETURN_INT32((int32) numSummarized);
}
/*
* Execute the index scan.
*
* This works by reading index TIDs from the revmap, and obtaining the index
* tuples pointed to by them; the summary values in the index tuples are
* compared to the scan keys. We return into the TID bitmap all the pages in
* ranges corresponding to index tuples that match the scan keys.
*
* If a TID from the revmap is read as InvalidTID, we know that range is
* unsummarized. Pages in those ranges need to be returned regardless of scan
* keys.
*/
int64
bringetbitmap(IndexScanDesc scan, TIDBitmap *tbm)
{
Relation idxRel = scan->indexRelation;
Buffer buf = InvalidBuffer;
BrinDesc *bdesc;
Oid heapOid;
Relation heapRel;
BrinOpaque *opaque;
BlockNumber nblocks;
BlockNumber heapBlk;
int totalpages = 0;
FmgrInfo *consistentFn;
MemoryContext oldcxt;
MemoryContext perRangeCxt;
opaque = (BrinOpaque *) scan->opaque;
bdesc = opaque->bo_bdesc;
pgstat_count_index_scan(idxRel);
/*
* We need to know the size of the table so that we know how long to
* iterate on the revmap.
*/
heapOid = IndexGetRelation(RelationGetRelid(idxRel), false);
heapRel = heap_open(heapOid, AccessShareLock);
nblocks = RelationGetNumberOfBlocks(heapRel);
heap_close(heapRel, AccessShareLock);
/*
* Make room for the consistent support procedures of indexed columns. We
* don't look them up here; we do that lazily the first time we see a scan
* key reference each of them. We rely on zeroing fn_oid to InvalidOid.
*/
consistentFn = palloc0(sizeof(FmgrInfo) * bdesc->bd_tupdesc->natts);
/*
* Setup and use a per-range memory context, which is reset every time we
* loop below. This avoids having to free the tuples within the loop.
*/
perRangeCxt = AllocSetContextCreate(CurrentMemoryContext,
"bringetbitmap cxt",
ALLOCSET_DEFAULT_SIZES);
oldcxt = MemoryContextSwitchTo(perRangeCxt);
/*
* Now scan the revmap. We start by querying for heap page 0,
* incrementing by the number of pages per range; this gives us a full
* view of the table.
*/
for (heapBlk = 0; heapBlk < nblocks; heapBlk += opaque->bo_pagesPerRange)
{
bool addrange;
BrinTuple *tup;
OffsetNumber off;
Size size;
CHECK_FOR_INTERRUPTS();
MemoryContextResetAndDeleteChildren(perRangeCxt);
tup = brinGetTupleForHeapBlock(opaque->bo_rmAccess, heapBlk, &buf,
&off, &size, BUFFER_LOCK_SHARE,
scan->xs_snapshot);
if (tup)
{
tup = brin_copy_tuple(tup, size);
LockBuffer(buf, BUFFER_LOCK_UNLOCK);
}
/*
* For page ranges with no indexed tuple, we must return the whole
* range; otherwise, compare it to the scan keys.
*/
if (tup == NULL)
{
addrange = true;
}
else
{
BrinMemTuple *dtup;
dtup = brin_deform_tuple(bdesc, tup);
if (dtup->bt_placeholder)
{
/*
* Placeholder tuples are always returned, regardless of the
* values stored in them.
*/
addrange = true;
}
else
{
int keyno;
/*
* Compare scan keys with summary values stored for the range.
* If scan keys are matched, the page range must be added to
* the bitmap. We initially assume the range needs to be
* added; in particular this serves the case where there are
* no keys.
*/
addrange = true;
for (keyno = 0; keyno < scan->numberOfKeys; keyno++)
{
ScanKey key = &scan->keyData[keyno];
AttrNumber keyattno = key->sk_attno;
BrinValues *bval = &dtup->bt_columns[keyattno - 1];
Datum add;
/*
* The collation of the scan key must match the collation
* used in the index column (but only if the search is not
* IS NULL/ IS NOT NULL). Otherwise we shouldn't be using
* this index ...
*/
Assert((key->sk_flags & SK_ISNULL) ||
(key->sk_collation ==
bdesc->bd_tupdesc->attrs[keyattno - 1]->attcollation));
/* First time this column? look up consistent function */
if (consistentFn[keyattno - 1].fn_oid == InvalidOid)
{
FmgrInfo *tmp;
tmp = index_getprocinfo(idxRel, keyattno,
BRIN_PROCNUM_CONSISTENT);
fmgr_info_copy(&consistentFn[keyattno - 1], tmp,
CurrentMemoryContext);
}
/*
* Check whether the scan key is consistent with the page
* range values; if so, have the pages in the range added
* to the output bitmap.
*
* When there are multiple scan keys, failure to meet the
* criteria for a single one of them is enough to discard
* the range as a whole, so break out of the loop as soon
* as a false return value is obtained.
*/
add = FunctionCall3Coll(&consistentFn[keyattno - 1],
key->sk_collation,
PointerGetDatum(bdesc),
PointerGetDatum(bval),
PointerGetDatum(key));
addrange = DatumGetBool(add);
if (!addrange)
break;
}
}
}
/* add the pages in the range to the output bitmap, if needed */
if (addrange)
{
BlockNumber pageno;
for (pageno = heapBlk;
pageno <= heapBlk + opaque->bo_pagesPerRange - 1;
pageno++)
{
MemoryContextSwitchTo(oldcxt);
tbm_add_page(tbm, pageno);
totalpages++;
MemoryContextSwitchTo(perRangeCxt);
}
}
}
MemoryContextSwitchTo(oldcxt);
MemoryContextDelete(perRangeCxt);
if (buf != InvalidBuffer)
ReleaseBuffer(buf);
/*
* XXX We have an approximation of the number of *pages* that our scan
* returns, but we don't have a precise idea of the number of heap tuples
* involved.
*/
return totalpages * 10;
}
/*
* SQL-callable interface to mark a range as no longer summarized
*/
Datum
brin_desummarize_range(PG_FUNCTION_ARGS)
{
Oid indexoid = PG_GETARG_OID(0);
int64 heapBlk64 = PG_GETARG_INT64(1);
BlockNumber heapBlk;
Oid heapoid;
Relation heapRel;
Relation indexRel;
bool done;
if (RecoveryInProgress())
ereport(ERROR,
(errcode(ERRCODE_OBJECT_NOT_IN_PREREQUISITE_STATE),
errmsg("recovery is in progress"),
errhint("BRIN control functions cannot be executed during recovery.")));
if (heapBlk64 > MaxBlockNumber || heapBlk64 < 0)
{
char *blk = psprintf(INT64_FORMAT, heapBlk64);
ereport(ERROR,
(errcode(ERRCODE_NUMERIC_VALUE_OUT_OF_RANGE),
errmsg("block number out of range: %s", blk)));
}
heapBlk = (BlockNumber) heapBlk64;
/*
* We must lock table before index to avoid deadlocks. However, if the
* passed indexoid isn't an index then IndexGetRelation() will fail.
* Rather than emitting a not-very-helpful error message, postpone
* complaining, expecting that the is-it-an-index test below will fail.
*/
heapoid = IndexGetRelation(indexoid, true);
if (OidIsValid(heapoid))
heapRel = table_open(heapoid, ShareUpdateExclusiveLock);
else
heapRel = NULL;
indexRel = index_open(indexoid, ShareUpdateExclusiveLock);
/* Must be a BRIN index */
if (indexRel->rd_rel->relkind != RELKIND_INDEX ||
indexRel->rd_rel->relam != BRIN_AM_OID)
ereport(ERROR,
(errcode(ERRCODE_WRONG_OBJECT_TYPE),
errmsg("\"%s\" is not a BRIN index",
RelationGetRelationName(indexRel))));
/* User must own the index (comparable to privileges needed for VACUUM) */
if (!pg_class_ownercheck(indexoid, GetUserId()))
aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_INDEX,
RelationGetRelationName(indexRel));
/*
* Since we did the IndexGetRelation call above without any lock, it's
* barely possible that a race against an index drop/recreation could have
* netted us the wrong table. Recheck.
*/
if (heapRel == NULL || heapoid != IndexGetRelation(indexoid, false))
ereport(ERROR,
(errcode(ERRCODE_UNDEFINED_TABLE),
errmsg("could not open parent table of index %s",
RelationGetRelationName(indexRel))));
/* the revmap does the hard work */
do
{
done = brinRevmapDesummarizeRange(indexRel, heapBlk);
}
while (!done);
relation_close(indexRel, ShareUpdateExclusiveLock);
relation_close(heapRel, ShareUpdateExclusiveLock);
PG_RETURN_VOID();
}
/*
* index_drop
*
* NOTE: this routine should now only be called through performDeletion(),
* else associated dependencies won't be cleaned up.
*/
void
index_drop(Oid indexId)
{
Oid heapId;
Relation userHeapRelation;
Relation userIndexRelation;
Relation indexRelation;
HeapTuple tuple;
int i;
Assert(OidIsValid(indexId));
/*
* To drop an index safely, we must grab exclusive lock on its parent
* table; otherwise there could be other backends using the index!
* Exclusive lock on the index alone is insufficient because another
* backend might be in the midst of devising a query plan that will
* use the index. The parser and planner take care to hold an
* appropriate lock on the parent table while working, but having them
* hold locks on all the indexes too seems overly complex. We do grab
* exclusive lock on the index too, just to be safe. Both locks must
* be held till end of transaction, else other backends will still see
* this index in pg_index.
*/
heapId = IndexGetRelation(indexId);
userHeapRelation = heap_open(heapId, AccessExclusiveLock);
userIndexRelation = index_open(indexId);
LockRelation(userIndexRelation, AccessExclusiveLock);
/*
* fix RELATION relation
*/
DeleteRelationTuple(indexId);
/*
* fix ATTRIBUTE relation
*/
DeleteAttributeTuples(indexId);
/*
* fix INDEX relation
*/
indexRelation = heap_openr(IndexRelationName, RowExclusiveLock);
tuple = SearchSysCache(INDEXRELID,
ObjectIdGetDatum(indexId),
0, 0, 0);
if (!HeapTupleIsValid(tuple))
elog(ERROR, "cache lookup failed for index %u", indexId);
simple_heap_delete(indexRelation, &tuple->t_self);
ReleaseSysCache(tuple);
heap_close(indexRelation, RowExclusiveLock);
/*
* flush buffer cache and physically remove the file
*/
i = FlushRelationBuffers(userIndexRelation, (BlockNumber) 0);
if (i < 0)
elog(ERROR, "FlushRelationBuffers returned %d", i);
smgrunlink(DEFAULT_SMGR, userIndexRelation);
/*
* We are presently too lazy to attempt to compute the new correct
* value of relhasindex (the next VACUUM will fix it if necessary). So
* there is no need to update the pg_class tuple for the owning
* relation. But we must send out a shared-cache-inval notice on the
* owning relation to ensure other backends update their relcache
* lists of indexes.
*/
CacheInvalidateRelcache(heapId);
/*
* Close rels, but keep locks
*/
index_close(userIndexRelation);
heap_close(userHeapRelation, NoLock);
RelationForgetRelation(indexId);
}