Cherry-pick series of BRIN + AO commits until 63d916b0c3

contrib/pageinspect/Makefile

@@ -14,7 +14,7 @@ OBJS = \
 	rawpage.o
 
 EXTENSION = pageinspect
-DATA =  pageinspect--1.8--1.9.sql \
+DATA = pageinspect--1.8--1.9.sql \
 	pageinspect--1.7--1.8.sql pageinspect--1.6--1.7.sql \
 	pageinspect--1.5.sql pageinspect--1.5--1.6.sql \
 	pageinspect--1.4--1.5.sql pageinspect--1.3--1.4.sql \

contrib/pageinspect/brinfuncs.c

@@ -22,16 +22,20 @@
 #include "lib/stringinfo.h"
 #include "miscadmin.h"
 #include "pageinspect.h"
+#include "storage/bufmgr.h"
 #include "utils/array.h"
 #include "utils/builtins.h"
 #include "utils/lsyscache.h"
 #include "utils/rel.h"
+#include "miscadmin.h"
 
 PG_FUNCTION_INFO_V1(brin_page_type);
 PG_FUNCTION_INFO_V1(brin_page_items);
 PG_FUNCTION_INFO_V1(brin_metapage_info);
 PG_FUNCTION_INFO_V1(brin_revmap_data);
-PG_FUNCTION_INFO_V1(brin_upper_data);
+
+/* GPDB specific */
+PG_FUNCTION_INFO_V1(brin_revmap_chain);
 
 #define IS_BRIN(r) ((r)->rd_rel->relam == BRIN_AM_OID)
 
@@ -82,9 +86,6 @@ brin_page_type(PG_FUNCTION_ARGS)
 		case BRIN_PAGETYPE_REGULAR:
 			type = "regular";
 			break;
-		case BRIN_PAGETYPE_UPPER:
-			type = "upper";
-			break;
 		default:
 			type = psprintf("unknown (%02x)", BrinPageType(page));
 			break;
@@ -365,8 +366,11 @@ brin_metapage_info(PG_FUNCTION_ARGS)
 	Page		page;
 	BrinMetaPageData *meta;
 	TupleDesc	tupdesc;
-	Datum		values[4];
-	bool		nulls[4];
+	Datum		values[8];
+	bool		nulls[8];
+	Datum 	   *firstrevmappages;
+	Datum	   *lastrevmappages;
+	Datum	   *lastrevmappagenums;
 	HeapTuple	htup;
 
 	if (!superuser())
@@ -392,6 +396,41 @@ brin_metapage_info(PG_FUNCTION_ARGS)
 	values[2] = Int32GetDatum(meta->pagesPerRange);
 	values[3] = Int64GetDatum(meta->lastRevmapPage);
 
+	/* GPDB specific fields */
+	values[4] = Int64GetDatum(meta->isAo);
+	if (!meta->isAo)
+	{
+		nulls[5] = true;
+		nulls[6] = true;
+		nulls[7] = true;
+	}
+	else
+	{
+		firstrevmappages = palloc(sizeof(Datum) * MAX_AOREL_CONCURRENCY);
+		lastrevmappages = palloc(sizeof(Datum) * MAX_AOREL_CONCURRENCY);
+		lastrevmappagenums = palloc(sizeof(Datum) * MAX_AOREL_CONCURRENCY);
+
+		for (int i = 0; i < MAX_AOREL_CONCURRENCY; i++)
+		{
+			firstrevmappages[i] = UInt32GetDatum(meta->aoChainInfo[i].firstPage);
+			lastrevmappages[i] = UInt32GetDatum(meta->aoChainInfo[i].lastPage);
+			lastrevmappagenums[i] = UInt32GetDatum(meta->aoChainInfo[i].lastLogicalPageNum);
+		}
+
+		values[5] = PointerGetDatum(construct_array(firstrevmappages,
+													MAX_AOREL_CONCURRENCY,
+													INT8OID,
+													sizeof(int64), true, 'i'));
+		values[6] = PointerGetDatum(construct_array(lastrevmappages,
+													MAX_AOREL_CONCURRENCY,
+													INT8OID,
+													sizeof(int64), true, 'i'));
+		values[7] = PointerGetDatum(construct_array(lastrevmappagenums,
+													MAX_AOREL_CONCURRENCY,
+													INT8OID,
+													sizeof(int64), true, 'i'));
+	}
+
 	htup = heap_form_tuple(tupdesc, values, nulls);
 
 	PG_RETURN_DATUM(HeapTupleGetDatum(htup));
@@ -454,62 +493,69 @@ brin_revmap_data(PG_FUNCTION_ARGS)
 	SRF_RETURN_DONE(fctx);
 }
 
-
 /*
- * Return the BlockNumber array stored in a BRIN upper page
+ * GPDB: Returns the chain of revmap block numbers for a given segno (aka block
+ * sequence).
  */
 Datum
-brin_upper_data(PG_FUNCTION_ARGS)
+brin_revmap_chain(PG_FUNCTION_ARGS)
 {
-	struct
-	{
-		BlockNumber *blks;
-		int			idx;
-	}		   *state;
-	FuncCallContext *fctx;
-	ItemPointerData *tid;
+	bytea 				*raw_page = PG_GETARG_BYTEA_P(0);
+	Oid 				indexRelid = PG_GETARG_OID(1);
+	int 				segno = PG_GETARG_UINT32(2);
+	Page  				metapage;
+	BrinMetaPageData 	*meta;
+	ArrayBuildState 	*astate = NULL;
+	BlockNumber			currRevmapBlk;
+
+	Relation indexRel = index_open(indexRelid, AccessShareLock);
 
 	if (!superuser())
 		ereport(ERROR,
 				(errcode(ERRCODE_INSUFFICIENT_PRIVILEGE),
-						(errmsg("must be superuser to use raw page functions"))));
-
-	if (SRF_IS_FIRSTCALL())
-	{
-		bytea	   *raw_page = PG_GETARG_BYTEA_P(0);
-		MemoryContext mctx;
-		Page		page;
-
-		/* minimally verify the page we got */
-		page = verify_brin_page(raw_page, BRIN_PAGETYPE_UPPER, "upper");
+					(errmsg("must be superuser to use raw page functions"))));
 
-		/* create a function context for cross-call persistence */
-		fctx = SRF_FIRSTCALL_INIT();
-
-		/* switch to memory context appropriate for multiple function calls */
-		mctx = MemoryContextSwitchTo(fctx->multi_call_memory_ctx);
+	if (!IS_BRIN(indexRel))
+		ereport(ERROR,
+				(errcode(ERRCODE_WRONG_OBJECT_TYPE),
+					errmsg("\"%s\" is not a %s index",
+						   RelationGetRelationName(indexRel), "BRIN")));
 
-		state = palloc(sizeof(*state));
-		state->blks = ((RevmapUpperBlockContents *) PageGetContents(page))->rm_blocks;
-		state->idx = 0;
+	if (segno < 0 || segno > AOTupleId_MaxSegmentFileNum)
+		ereport(ERROR,
+				(errcode(ERRCODE_INVALID_PARAMETER_VALUE),
+					errmsg("\"%u\" is not a valid segno value (valid values are in [0,127])",
+						   segno)));
 
-		fctx->user_fctx = state;
+	metapage = verify_brin_page(raw_page, BRIN_PAGETYPE_META, "metapage");
 
-		MemoryContextSwitchTo(mctx);
+	if (PageIsNew(metapage))
+	{
+		index_close(indexRel, AccessShareLock);
+		PG_RETURN_NULL();
 	}
 
-	fctx = SRF_PERCALL_SETUP();
-	state = fctx->user_fctx;
+	meta = (BrinMetaPageData *) PageGetContents(metapage);
+	currRevmapBlk = meta->aoChainInfo[segno].firstPage;
+	while (currRevmapBlk != InvalidBlockNumber)
+	{
+		/* Look at the chain link to see what the next revmap blknum is */
+		Buffer curr;
 
+		astate = accumArrayResult(astate, UInt32GetDatum(currRevmapBlk), false,
+								  INT8OID, CurrentMemoryContext);
 
-	if (state->idx < REVMAP_UPPER_PAGE_MAXITEMS)
-	{
-		tid = (ItemPointerData*) palloc(sizeof(ItemPointerData));
-		ItemPointerSetBlockNumber(tid, (BlockNumber) state->blks[state->idx++]);
-		ItemPointerSetOffsetNumber(tid, (OffsetNumber) 0);
-		SRF_RETURN_NEXT(fctx, PointerGetDatum(tid));
+		curr = ReadBuffer(indexRel, currRevmapBlk);
+		LockBuffer(curr, BUFFER_LOCK_SHARE);
+		currRevmapBlk = BrinNextRevmapPage(BufferGetPage(curr));
+		UnlockReleaseBuffer(curr);
 	}
 
-	SRF_RETURN_DONE(fctx);
-}
+	index_close(indexRel, AccessShareLock);
 
+	if (astate)
+		PG_RETURN_DATUM(makeArrayResult(astate,
+										CurrentMemoryContext));
+	else
+		PG_RETURN_NULL();
+}

contrib/pageinspect/pageinspect--1.5.sql

@@ -213,15 +213,6 @@ RETURNS SETOF tid
 AS 'MODULE_PATHNAME', 'brin_revmap_data'
 LANGUAGE C STRICT PARALLEL SAFE;
 
---
--- brin_upper_data()
---
-CREATE FUNCTION brin_upper_data(IN page bytea,
-    OUT pages tid)
-    RETURNS SETOF tid
-AS 'MODULE_PATHNAME', 'brin_upper_data'
-LANGUAGE C STRICT PARALLEL SAFE;
-
 --
 -- brin_page_items()
 --

contrib/pageinspect/pageinspect--1.8--1.9.sql

@@ -135,3 +135,24 @@ CREATE FUNCTION brin_page_items(IN page bytea, IN index_oid regclass,
 RETURNS SETOF record
 AS 'MODULE_PATHNAME', 'brin_page_items'
 LANGUAGE C STRICT PARALLEL SAFE;
+-- brin_metapage_info()
+--
+DROP FUNCTION brin_metapage_info(IN page bytea, OUT magic text,
+                                 OUT version integer, OUT pagesperrange integer, OUT lastrevmappage bigint);
+CREATE FUNCTION brin_metapage_info(IN page bytea, OUT magic text,
+                                   OUT version integer, OUT pagesperrange integer, OUT lastrevmappage bigint,
+                                   /* GPDB specific for AO/CO tables */
+                                   OUT isAo boolean,
+                                   OUT firstrevmappages bigint[],
+                                   OUT lastrevmappages bigint[],
+                                   OUT lastrevmappagenums bigint[])
+AS 'MODULE_PATHNAME', 'brin_metapage_info'
+LANGUAGE C STRICT PARALLEL SAFE;
+
+--
+-- brin_revmap_chain()
+--
+CREATE FUNCTION brin_revmap_chain(IN page bytea, IN indexrelid regclass, IN segno int)
+    RETURNS bigint[]
+AS 'MODULE_PATHNAME', 'brin_revmap_chain'
+    LANGUAGE C STRICT PARALLEL SAFE;

src/backend/access/aocs/aocsam_handler.c

@@ -1849,14 +1849,13 @@ aoco_index_build_range_scan(Relation heapRelation,
 	while (aoco_getnextslot(&aocoscan->rs_base, ForwardScanDirection, slot))
 	{
 		bool		tupleIsAlive;
-		BlockNumber		blockno;
 		AOTupleId 	*aoTupleId;
+		BlockNumber currblockno = ItemPointerGetBlockNumber(&slot->tts_tid);
 
 		CHECK_FOR_INTERRUPTS();
-		blockno = ItemPointerGetBlockNumber(&slot->tts_tid);
-		if (blockno != lastBlock)
+		if (currblockno != lastBlock)
 		{
-			lastBlock = blockno;
+			lastBlock = currblockno;
 			++blockcounts;
 		}
 
@@ -1865,8 +1864,8 @@ aoco_index_build_range_scan(Relation heapRelation,
 		 * we scan the whole table, and throw away tuples that are not in the
 		 * range. That's clearly very inefficient.
 		 */
-		if (blockno < start_blockno ||
-			(numblocks != InvalidBlockNumber && blockno >= numblocks))
+		if (currblockno < start_blockno ||
+			(numblocks != InvalidBlockNumber && currblockno >= (start_blockno + numblocks)))
 			continue;
 
 		/* Report scan progress, if asked to. */

src/backend/access/appendonly/appendonlyam_handler.c

@@ -1692,6 +1692,7 @@ appendonly_index_build_range_scan(Relation heapRelation,
 	{
 		bool		tupleIsAlive;
 		AOTupleId 	*aoTupleId;
+		BlockNumber currblockno = ItemPointerGetBlockNumber(&slot->tts_tid);
 
 		CHECK_FOR_INTERRUPTS();
 
@@ -1700,8 +1701,8 @@ appendonly_index_build_range_scan(Relation heapRelation,
 		 * we scan the whole table, and throw away tuples that are not in the
 		 * range. That's clearly very inefficient.
 		 */
-		if (ItemPointerGetBlockNumber(&slot->tts_tid) < start_blockno ||
-			(numblocks != InvalidBlockNumber && ItemPointerGetBlockNumber(&slot->tts_tid) >= numblocks))
+		if (currblockno < start_blockno ||
+			(numblocks != InvalidBlockNumber && currblockno >= (start_blockno + numblocks)))
 			continue;
 
 		if (progress)