From 4376bda3887b3e9b5918acac19890413d4414adc Mon Sep 17 00:00:00 2001
From: erthalion <9erthalion6@gmail.com>
Date: Sat, 15 Sep 2018 21:14:50 +0200
Subject: [PATCH v14] Index skip scan
Implementation of Index Skip Scan (see Loose Index Scan in the wiki [1])
on top of IndexOnlyScan. To make it suitable for both situations when
there are small number of distinct values and significant amount of
distinct values the following approach is taken - instead of searching
from the root for every value we're searching for then first on the
current page, and then if not found continue searching from the root.
Original patch and design were proposed by Thomas Munro [2], revived and
improved by Jesper Pedersen, and a bit adjusted by Dmitry Dolgov.
[1] https://wiki.postgresql.org/wiki/Loose_indexscan
[2] https://www.postgresql.org/message-id/flat/CADLWmXXbTSBxP-MzJuPAYSsL_2f0iPm5VWPbCvDbVvfX93FKkw%40mail.gmail.com
---
contrib/bloom/blutils.c | 1 +
doc/src/sgml/config.sgml | 16 ++
doc/src/sgml/indexam.sgml | 10 ++
doc/src/sgml/indices.sgml | 24 +++
src/backend/access/brin/brin.c | 1 +
src/backend/access/gin/ginutil.c | 1 +
src/backend/access/gist/gist.c | 1 +
src/backend/access/hash/hash.c | 1 +
src/backend/access/index/indexam.c | 16 ++
src/backend/access/nbtree/nbtree.c | 12 ++
src/backend/access/nbtree/nbtsearch.c | 249 ++++++++++++++++++++++++++
src/backend/access/spgist/spgutils.c | 1 +
src/backend/commands/explain.c | 12 ++
src/backend/executor/nodeIndexonlyscan.c | 22 +++
src/backend/nodes/copyfuncs.c | 1 +
src/backend/nodes/outfuncs.c | 1 +
src/backend/nodes/readfuncs.c | 1 +
src/backend/optimizer/path/costsize.c | 1 +
src/backend/optimizer/plan/createplan.c | 10 +-
src/backend/optimizer/plan/planner.c | 17 ++
src/backend/optimizer/util/pathnode.c | 40 +++++
src/backend/optimizer/util/plancat.c | 1 +
src/backend/utils/misc/guc.c | 9 +
src/backend/utils/misc/postgresql.conf.sample | 1 +
src/include/access/amapi.h | 5 +
src/include/access/genam.h | 1 +
src/include/access/nbtree.h | 5 +
src/include/nodes/execnodes.h | 4 +
src/include/nodes/pathnodes.h | 5 +
src/include/nodes/plannodes.h | 1 +
src/include/optimizer/cost.h | 1 +
src/include/optimizer/pathnode.h | 5 +
src/test/regress/expected/create_index.out | 1 +
src/test/regress/expected/select_distinct.out | 25 +++
src/test/regress/expected/sysviews.out | 3 +-
src/test/regress/sql/create_index.sql | 2 +
src/test/regress/sql/select_distinct.sql | 7 +
37 files changed, 510 insertions(+), 4 deletions(-)
diff --git a/contrib/bloom/blutils.c b/contrib/bloom/blutils.c
index d078dfbd46..c6ee2f5403 100644
--- a/contrib/bloom/blutils.c
+++ b/contrib/bloom/blutils.c
@@ -129,6 +129,7 @@ blhandler(PG_FUNCTION_ARGS)
amroutine->ambulkdelete = blbulkdelete;
amroutine->amvacuumcleanup = blvacuumcleanup;
amroutine->amcanreturn = NULL;
+ amroutine->amskip = NULL;
amroutine->amcostestimate = blcostestimate;
amroutine->amoptions = bloptions;
amroutine->amproperty = NULL;
diff --git a/doc/src/sgml/config.sgml b/doc/src/sgml/config.sgml
index d383de2512..fa8e60b121 100644
--- a/doc/src/sgml/config.sgml
+++ b/doc/src/sgml/config.sgml
@@ -4340,6 +4340,22 @@ ANY num_sync (
+ enable_indexskipscan (boolean)
+
+ enable_indexskipscan configuration parameter
+
+
+
+
+ Enables or disables the query planner's use of index-skip-scan plan
+ types (see ). This parameter requires
+ that enable_indexonlyscan is on.
+ The default is on.
+
+
+
+
enable_material (boolean)
diff --git a/doc/src/sgml/indexam.sgml b/doc/src/sgml/indexam.sgml
index 05102724ea..1b12ad9493 100644
--- a/doc/src/sgml/indexam.sgml
+++ b/doc/src/sgml/indexam.sgml
@@ -135,6 +135,7 @@ typedef struct IndexAmRoutine
amendscan_function amendscan;
ammarkpos_function ammarkpos; /* can be NULL */
amrestrpos_function amrestrpos; /* can be NULL */
+ amskip_function amskip; /* can be NULL */
/* interface functions to support parallel index scans */
amestimateparallelscan_function amestimateparallelscan; /* can be NULL */
@@ -666,6 +667,15 @@ amrestrpos (IndexScanDesc scan);
+bool
+amskip (IndexScanDesc scan, ScanDirection direction, int prefix);
+
+ Skip past all tuples where the first 'prefix' columns have the same value as
+ the last tuple returned in the current scan.
+
+
+
+
Size
amestimateparallelscan (void);
diff --git a/doc/src/sgml/indices.sgml b/doc/src/sgml/indices.sgml
index 3493f482b8..729990ae26 100644
--- a/doc/src/sgml/indices.sgml
+++ b/doc/src/sgml/indices.sgml
@@ -1233,6 +1233,30 @@ SELECT target FROM tests WHERE subject = 'some-subject' AND success;
and later will recognize such cases and allow index-only scans to be
generated, but older versions will not.
+
+
+ Index Skip Scans
+
+
+ index
+ index-skip scans
+
+
+ index-skip scan
+
+
+
+ In case if index scan is used to retrieve the distinct values of a column
+ efficiently, it can be not very efficient, since it requires to scan all
+ the equal values of a key. In such cases planner will consider apply index
+ skip scan approach, which is based on the idea of
+
+ Loose index scan. Rather than scanning all equal values of a key,
+ as soon as a new value is found, it will search for a larger value on the
+ same index page, and if not found, restart the search by looking for a
+ larger value. This is much faster when the index has many equal keys.
+
+
diff --git a/src/backend/access/brin/brin.c b/src/backend/access/brin/brin.c
index 8f008dd008..639c8d7115 100644
--- a/src/backend/access/brin/brin.c
+++ b/src/backend/access/brin/brin.c
@@ -108,6 +108,7 @@ brinhandler(PG_FUNCTION_ARGS)
amroutine->ambulkdelete = brinbulkdelete;
amroutine->amvacuumcleanup = brinvacuumcleanup;
amroutine->amcanreturn = NULL;
+ amroutine->amskip = NULL;
amroutine->amcostestimate = brincostestimate;
amroutine->amoptions = brinoptions;
amroutine->amproperty = NULL;
diff --git a/src/backend/access/gin/ginutil.c b/src/backend/access/gin/ginutil.c
index afc20232ac..36f32f15a4 100644
--- a/src/backend/access/gin/ginutil.c
+++ b/src/backend/access/gin/ginutil.c
@@ -61,6 +61,7 @@ ginhandler(PG_FUNCTION_ARGS)
amroutine->ambulkdelete = ginbulkdelete;
amroutine->amvacuumcleanup = ginvacuumcleanup;
amroutine->amcanreturn = NULL;
+ amroutine->amskip = NULL;
amroutine->amcostestimate = gincostestimate;
amroutine->amoptions = ginoptions;
amroutine->amproperty = NULL;
diff --git a/src/backend/access/gist/gist.c b/src/backend/access/gist/gist.c
index a746e911f3..5c938fa9fb 100644
--- a/src/backend/access/gist/gist.c
+++ b/src/backend/access/gist/gist.c
@@ -84,6 +84,7 @@ gisthandler(PG_FUNCTION_ARGS)
amroutine->ambulkdelete = gistbulkdelete;
amroutine->amvacuumcleanup = gistvacuumcleanup;
amroutine->amcanreturn = gistcanreturn;
+ amroutine->amskip = NULL;
amroutine->amcostestimate = gistcostestimate;
amroutine->amoptions = gistoptions;
amroutine->amproperty = gistproperty;
diff --git a/src/backend/access/hash/hash.c b/src/backend/access/hash/hash.c
index f1f01a0956..07d7eeda56 100644
--- a/src/backend/access/hash/hash.c
+++ b/src/backend/access/hash/hash.c
@@ -79,6 +79,7 @@ hashhandler(PG_FUNCTION_ARGS)
amroutine->ambulkdelete = hashbulkdelete;
amroutine->amvacuumcleanup = hashvacuumcleanup;
amroutine->amcanreturn = NULL;
+ amroutine->amskip = NULL;
amroutine->amcostestimate = hashcostestimate;
amroutine->amoptions = hashoptions;
amroutine->amproperty = NULL;
diff --git a/src/backend/access/index/indexam.c b/src/backend/access/index/indexam.c
index ae1c87ebad..9f7ebc633d 100644
--- a/src/backend/access/index/indexam.c
+++ b/src/backend/access/index/indexam.c
@@ -33,6 +33,7 @@
* index_can_return - does index support index-only scans?
* index_getprocid - get a support procedure OID
* index_getprocinfo - get a support procedure's lookup info
+ * index_skip - advance past duplicate key values in a scan
*
* NOTES
* This file contains the index_ routines which used
@@ -756,6 +757,21 @@ index_can_return(Relation indexRelation, int attno)
return indexRelation->rd_indam->amcanreturn(indexRelation, attno);
}
+/* ----------------
+ * index_skip
+ *
+ * Skip past all tuples where the first 'prefix' columns have the
+ * same value as the last tuple returned in the current scan.
+ * ----------------
+ */
+bool
+index_skip(IndexScanDesc scan, ScanDirection direction, int prefix)
+{
+ SCAN_CHECKS;
+
+ return scan->indexRelation->rd_indam->amskip(scan, direction, prefix);
+}
+
/* ----------------
* index_getprocid
*
diff --git a/src/backend/access/nbtree/nbtree.c b/src/backend/access/nbtree/nbtree.c
index ac6f1eb342..ee14f4cb2e 100644
--- a/src/backend/access/nbtree/nbtree.c
+++ b/src/backend/access/nbtree/nbtree.c
@@ -130,6 +130,7 @@ bthandler(PG_FUNCTION_ARGS)
amroutine->ambulkdelete = btbulkdelete;
amroutine->amvacuumcleanup = btvacuumcleanup;
amroutine->amcanreturn = btcanreturn;
+ amroutine->amskip = btskip;
amroutine->amcostestimate = btcostestimate;
amroutine->amoptions = btoptions;
amroutine->amproperty = btproperty;
@@ -378,6 +379,8 @@ btbeginscan(Relation rel, int nkeys, int norderbys)
*/
so->currTuples = so->markTuples = NULL;
+ so->skipScanKey = NULL;
+
scan->xs_itupdesc = RelationGetDescr(rel);
scan->opaque = so;
@@ -445,6 +448,15 @@ btrescan(IndexScanDesc scan, ScanKey scankey, int nscankeys,
_bt_preprocess_array_keys(scan);
}
+/*
+ * btskip() -- skip to the beginning of the next key prefix
+ */
+bool
+btskip(IndexScanDesc scan, ScanDirection direction, int prefix)
+{
+ return _bt_skip(scan, direction, prefix);
+}
+
/*
* btendscan() -- close down a scan
*/
diff --git a/src/backend/access/nbtree/nbtsearch.c b/src/backend/access/nbtree/nbtsearch.c
index 7ed4e01bd3..bd90330654 100644
--- a/src/backend/access/nbtree/nbtsearch.c
+++ b/src/backend/access/nbtree/nbtsearch.c
@@ -1378,6 +1378,255 @@ _bt_next(IndexScanDesc scan, ScanDirection dir)
return true;
}
+/*
+ * _bt_skip() -- Skip items that have the same prefix as the most recently
+ * fetched index tuple. The current position is set so that a subsequent call
+ * to _bt_next will fetch the first tuple that differs in the leading 'prefix'
+ * keys.
+ */
+bool
+_bt_skip(IndexScanDesc scan, ScanDirection dir, int prefix)
+{
+ BTScanOpaque so = (BTScanOpaque) scan->opaque;
+ BTStack stack;
+ Buffer buf;
+ OffsetNumber offnum;
+ BTScanPosItem *currItem;
+ Page page;
+ BTPageOpaque opaque;
+ OffsetNumber low, high, compare_offset;
+ Relation indexRel = scan->indexRelation;
+ int compare_value = ScanDirectionIsForward(dir) ? 0 : 1;
+
+ /* We want to return tuples, and we need a starting point */
+ Assert(scan->xs_want_itup);
+ Assert(scan->xs_itup);
+
+ /*
+ * If skipScanKey is NULL then we initialize it with _bt_mkscankey,
+ * otherwise we will just update the sk_flags / sk_argument elements
+ * in order to eliminate repeated free/realloc.
+ */
+ if (so->skipScanKey == NULL)
+ {
+ so->skipScanKey = _bt_mkscankey(indexRel, scan->xs_itup);
+ so->skipScanKey->keysz = prefix;
+ so->skipScanKey->scantid = NULL;
+ }
+ else
+ {
+ TupleDesc itupdesc;
+ int indnkeyatts;
+ int i;
+ ScanKey scankeys = so->skipScanKey->scankeys;
+
+ itupdesc = RelationGetDescr(indexRel);
+ indnkeyatts = IndexRelationGetNumberOfKeyAttributes(indexRel);
+ for (i = 0; i < indnkeyatts; i++)
+ {
+ Datum datum;
+ bool null;
+ int flags;
+
+ datum = index_getattr(scan->xs_itup, i + 1, itupdesc, &null);
+ flags = (null ? SK_ISNULL : 0) |
+ (indexRel->rd_indoption[i] << SK_BT_INDOPTION_SHIFT);
+ scankeys[i].sk_flags = flags;
+ scankeys[i].sk_argument = datum;
+ }
+ }
+
+ /* Check if the next unique key can be found within the current page */
+ if (BTScanPosIsValid(so->currPos))
+ {
+ buf = so->currPos.buf;
+
+ page = BufferGetPage(buf);
+ opaque = (BTPageOpaque) PageGetSpecialPointer(page);
+
+ low = P_FIRSTDATAKEY(opaque);
+ high = PageGetMaxOffsetNumber(page);
+ compare_offset = ScanDirectionIsForward(dir) ? high : low;
+
+ if(_bt_compare(scan->indexRelation,
+ so->skipScanKey, page, compare_offset) > compare_value)
+ {
+ bool keyFound = false;
+
+ LockBuffer(buf, BT_READ);
+ so->skipScanKey->nextkey = ScanDirectionIsForward(dir);
+ offnum = _bt_binsrch(scan->indexRelation, so->skipScanKey, buf);
+
+ /* Lock the page for SERIALIZABLE transactions */
+ PredicateLockPage(scan->indexRelation, BufferGetBlockNumber(buf),
+ scan->xs_snapshot);
+
+ /* We know in which direction to look */
+ _bt_initialize_more_data(so, dir);
+
+ if (ScanDirectionIsForward(dir))
+ {
+ /* Move back for _bt_next */
+ offnum = OffsetNumberPrev(offnum);
+ }
+
+ /* Now read the data */
+ keyFound = _bt_readpage(scan, dir, offnum);
+ _bt_drop_lock_and_maybe_pin(scan, &so->currPos);
+
+ if (keyFound)
+ {
+ /* set IndexTuple */
+ currItem = &so->currPos.items[so->currPos.itemIndex];
+ scan->xs_heaptid = currItem->heapTid;
+ if (scan->xs_want_itup)
+ scan->xs_itup = (IndexTuple) (so->currTuples + currItem->tupleOffset);
+ return true;
+ }
+ }
+ }
+
+ if (BTScanPosIsValid(so->currPos))
+ {
+ ReleaseBuffer(so->currPos.buf);
+ so->currPos.buf = InvalidBuffer;
+ }
+
+ /*
+ * We haven't found scan key within the current page, so let's scan from
+ * the root. Use _bt_search and _bt_binsrch to get the buffer and offset
+ * number
+ */
+ so->skipScanKey->nextkey = ScanDirectionIsForward(dir);
+ stack = _bt_search(scan->indexRelation, so->skipScanKey,
+ &buf, BT_READ, scan->xs_snapshot);
+ _bt_freestack(stack);
+ so->currPos.buf = buf;
+ if (ScanDirectionIsForward(dir))
+ {
+ so->skipScanKey->nextkey = ScanDirectionIsForward(dir);
+ offnum = _bt_binsrch(scan->indexRelation, so->skipScanKey, buf);
+ }
+ else
+ {
+ /* For backward scan finding offnum is more involved. It is wrong to
+ * just use binary search, since we will find the last item from the
+ * sequence of equal items, and we need the first one. Otherwise e.g.
+ * backward cursor scan will return an incorrect value. */
+ TupleDesc itupdesc;
+ int indnkeyatts;
+ int i;
+
+ so->skipScanKey->nextkey = ScanDirectionIsForward(dir);
+ offnum = _bt_binsrch(scan->indexRelation, so->skipScanKey, buf);
+ _bt_drop_lock_and_maybe_pin(scan, &so->currPos);
+
+ /* One step back to find a previous value */
+ if (_bt_next(scan, dir))
+ {
+ itupdesc = RelationGetDescr(indexRel);
+ indnkeyatts = IndexRelationGetNumberOfKeyAttributes(indexRel);
+ for (i = 0; i < indnkeyatts; i++)
+ {
+ Datum datum;
+ bool null;
+ int flags;
+ ScanKey scankeys = so->skipScanKey->scankeys;
+
+ datum = index_getattr(scan->xs_itup, i + 1, itupdesc, &null);
+ flags = (null ? SK_ISNULL : 0) |
+ (indexRel->rd_indoption[i] << SK_BT_INDOPTION_SHIFT);
+ scankeys[i].sk_flags = flags;
+ scankeys[i].sk_argument = datum;
+ }
+
+ /* And now find the last item from the sequence for the current,
+ * value with the intention do OffsetNumberNext. As a result we
+ * end up on a first element from the sequence. */
+ buf = so->currPos.buf;
+
+ page = BufferGetPage(buf);
+ opaque = (BTPageOpaque) PageGetSpecialPointer(page);
+
+ low = P_FIRSTDATAKEY(opaque);
+ high = PageGetMaxOffsetNumber(page);
+ compare_offset = ScanDirectionIsForward(dir) ? high : low;
+
+ if(_bt_compare(scan->indexRelation, so->skipScanKey,
+ page, compare_offset) > compare_value)
+ {
+ so->skipScanKey->nextkey = ScanDirectionIsForward(dir);
+ offnum = _bt_binsrch(scan->indexRelation, so->skipScanKey, buf);
+ }
+ else
+ {
+ ReleaseBuffer(so->currPos.buf);
+ so->currPos.buf = InvalidBuffer;
+
+ so->skipScanKey->nextkey = ScanDirectionIsForward(dir);
+ stack = _bt_search(scan->indexRelation, so->skipScanKey,
+ &buf, BT_READ, scan->xs_snapshot);
+ _bt_freestack(stack);
+ so->currPos.buf = buf;
+ so->skipScanKey->nextkey = ScanDirectionIsForward(dir);
+ offnum = _bt_binsrch(scan->indexRelation, so->skipScanKey, buf);
+ }
+ }
+ else
+ {
+ pfree(so->skipScanKey);
+ so->skipScanKey = NULL;
+ return false;
+ }
+ }
+
+ /* Lock the page for SERIALIZABLE transactions */
+ PredicateLockPage(scan->indexRelation, BufferGetBlockNumber(buf),
+ scan->xs_snapshot);
+
+ /* We know in which direction to look */
+ _bt_initialize_more_data(so, dir);
+
+ if (ScanDirectionIsForward(dir))
+ {
+ /* Move back for _bt_next */
+ offnum = OffsetNumberPrev(offnum);
+ }
+ else
+ {
+ offnum = OffsetNumberNext(offnum);
+ }
+
+ /* Now read the data */
+ if (!_bt_readpage(scan, dir, offnum))
+ {
+ /*
+ * There's no actually-matching data on this page. Try to advance to
+ * the next page. Return false if there's no matching data at all.
+ */
+ LockBuffer(so->currPos.buf, BUFFER_LOCK_UNLOCK);
+ if (!_bt_steppage(scan, dir))
+ {
+ pfree(so->skipScanKey);
+ so->skipScanKey = NULL;
+ return false;
+ }
+ }
+ else
+ {
+ /* Drop the lock, and maybe the pin, on the current page */
+ _bt_drop_lock_and_maybe_pin(scan, &so->currPos);
+ }
+
+ /* And set IndexTuple */
+ currItem = &so->currPos.items[so->currPos.itemIndex];
+ scan->xs_heaptid = currItem->heapTid;
+ if (scan->xs_want_itup)
+ scan->xs_itup = (IndexTuple) (so->currTuples + currItem->tupleOffset);
+
+ return true;
+}
+
/*
* _bt_readpage() -- Load data from current index page into so->currPos
*
diff --git a/src/backend/access/spgist/spgutils.c b/src/backend/access/spgist/spgutils.c
index 8e63c1fad2..a55bd5e9f5 100644
--- a/src/backend/access/spgist/spgutils.c
+++ b/src/backend/access/spgist/spgutils.c
@@ -64,6 +64,7 @@ spghandler(PG_FUNCTION_ARGS)
amroutine->ambulkdelete = spgbulkdelete;
amroutine->amvacuumcleanup = spgvacuumcleanup;
amroutine->amcanreturn = spgcanreturn;
+ amroutine->amskip = NULL;
amroutine->amcostestimate = spgcostestimate;
amroutine->amoptions = spgoptions;
amroutine->amproperty = spgproperty;
diff --git a/src/backend/commands/explain.c b/src/backend/commands/explain.c
index 1831ea81cf..c41995b247 100644
--- a/src/backend/commands/explain.c
+++ b/src/backend/commands/explain.c
@@ -1297,6 +1297,14 @@ ExplainNode(PlanState *planstate, List *ancestors,
{
IndexOnlyScan *indexonlyscan = (IndexOnlyScan *) plan;
+ if (indexonlyscan->skipPrefixSize > 0)
+ {
+ if (es->format != EXPLAIN_FORMAT_TEXT)
+ ExplainPropertyInteger("Distinct Prefix", NULL,
+ indexonlyscan->skipPrefixSize,
+ es);
+ }
+
ExplainIndexScanDetails(indexonlyscan->indexid,
indexonlyscan->indexorderdir,
es);
@@ -1519,6 +1527,10 @@ ExplainNode(PlanState *planstate, List *ancestors,
planstate, es);
break;
case T_IndexOnlyScan:
+ if (((IndexOnlyScan *) plan)->skipPrefixSize > 0)
+ {
+ ExplainPropertyText("Scan mode", "Skip scan", es);
+ }
show_scan_qual(((IndexOnlyScan *) plan)->indexqual,
"Index Cond", planstate, ancestors, es);
if (((IndexOnlyScan *) plan)->indexqual)
diff --git a/src/backend/executor/nodeIndexonlyscan.c b/src/backend/executor/nodeIndexonlyscan.c
index 2d954b722a..3adfce24f5 100644
--- a/src/backend/executor/nodeIndexonlyscan.c
+++ b/src/backend/executor/nodeIndexonlyscan.c
@@ -115,6 +115,24 @@ IndexOnlyNext(IndexOnlyScanState *node)
node->ioss_NumOrderByKeys);
}
+ /*
+ * Check if we need to skip to the next key prefix, because we've been
+ * asked to implement DISTINCT.
+ */
+ if (node->ioss_SkipPrefixSize > 0 && node->ioss_FirstTupleEmitted)
+ {
+ if (!index_skip(scandesc, direction, node->ioss_SkipPrefixSize))
+ {
+ /* Reached end of index. At this point currPos is invalidated,
+ * and we need to reset ioss_FirstTupleEmitted, since otherwise
+ * after going backwards, reaching the end of index, and going
+ * forward again we apply skip again. It would be incorrect and
+ * lead to an extra skipped item. */
+ node->ioss_FirstTupleEmitted = false;
+ return ExecClearTuple(slot);
+ }
+ }
+
/*
* OK, now that we have what we need, fetch the next tuple.
*/
@@ -253,6 +271,8 @@ IndexOnlyNext(IndexOnlyScanState *node)
ItemPointerGetBlockNumber(tid),
estate->es_snapshot);
+ node->ioss_FirstTupleEmitted = true;
+
return slot;
}
@@ -503,6 +523,8 @@ ExecInitIndexOnlyScan(IndexOnlyScan *node, EState *estate, int eflags)
indexstate->ss.ps.plan = (Plan *) node;
indexstate->ss.ps.state = estate;
indexstate->ss.ps.ExecProcNode = ExecIndexOnlyScan;
+ indexstate->ioss_SkipPrefixSize = node->skipPrefixSize;
+ indexstate->ioss_FirstTupleEmitted = false;
/*
* Miscellaneous initialization
diff --git a/src/backend/nodes/copyfuncs.c b/src/backend/nodes/copyfuncs.c
index 04cc15606d..41a006b5d2 100644
--- a/src/backend/nodes/copyfuncs.c
+++ b/src/backend/nodes/copyfuncs.c
@@ -515,6 +515,7 @@ _copyIndexOnlyScan(const IndexOnlyScan *from)
COPY_NODE_FIELD(indexorderby);
COPY_NODE_FIELD(indextlist);
COPY_SCALAR_FIELD(indexorderdir);
+ COPY_SCALAR_FIELD(skipPrefixSize);
return newnode;
}
diff --git a/src/backend/nodes/outfuncs.c b/src/backend/nodes/outfuncs.c
index 910a738c20..59923159ef 100644
--- a/src/backend/nodes/outfuncs.c
+++ b/src/backend/nodes/outfuncs.c
@@ -573,6 +573,7 @@ _outIndexOnlyScan(StringInfo str, const IndexOnlyScan *node)
WRITE_NODE_FIELD(indexorderby);
WRITE_NODE_FIELD(indextlist);
WRITE_ENUM_FIELD(indexorderdir, ScanDirection);
+ WRITE_INT_FIELD(skipPrefixSize);
}
static void
diff --git a/src/backend/nodes/readfuncs.c b/src/backend/nodes/readfuncs.c
index eff98febf1..90f9759a65 100644
--- a/src/backend/nodes/readfuncs.c
+++ b/src/backend/nodes/readfuncs.c
@@ -1805,6 +1805,7 @@ _readIndexOnlyScan(void)
READ_NODE_FIELD(indexorderby);
READ_NODE_FIELD(indextlist);
READ_ENUM_FIELD(indexorderdir, ScanDirection);
+ READ_INT_FIELD(skipPrefixSize);
READ_DONE();
}
diff --git a/src/backend/optimizer/path/costsize.c b/src/backend/optimizer/path/costsize.c
index 4b9be13f08..91a35e9beb 100644
--- a/src/backend/optimizer/path/costsize.c
+++ b/src/backend/optimizer/path/costsize.c
@@ -124,6 +124,7 @@ int max_parallel_workers_per_gather = 2;
bool enable_seqscan = true;
bool enable_indexscan = true;
bool enable_indexonlyscan = true;
+bool enable_indexskipscan = true;
bool enable_bitmapscan = true;
bool enable_tidscan = true;
bool enable_sort = true;
diff --git a/src/backend/optimizer/plan/createplan.c b/src/backend/optimizer/plan/createplan.c
index 979c3c212f..ccecbfdd13 100644
--- a/src/backend/optimizer/plan/createplan.c
+++ b/src/backend/optimizer/plan/createplan.c
@@ -178,7 +178,8 @@ static IndexOnlyScan *make_indexonlyscan(List *qptlist, List *qpqual,
Index scanrelid, Oid indexid,
List *indexqual, List *indexorderby,
List *indextlist,
- ScanDirection indexscandir);
+ ScanDirection indexscandir,
+ int skipprefix);
static BitmapIndexScan *make_bitmap_indexscan(Index scanrelid, Oid indexid,
List *indexqual,
List *indexqualorig);
@@ -2773,7 +2774,8 @@ create_indexscan_plan(PlannerInfo *root,
fixed_indexquals,
fixed_indexorderbys,
best_path->indexinfo->indextlist,
- best_path->indexscandir);
+ best_path->indexscandir,
+ best_path->indexskipprefix);
else
scan_plan = (Scan *) make_indexscan(tlist,
qpqual,
@@ -5049,7 +5051,8 @@ make_indexonlyscan(List *qptlist,
List *indexqual,
List *indexorderby,
List *indextlist,
- ScanDirection indexscandir)
+ ScanDirection indexscandir,
+ int skipPrefixSize)
{
IndexOnlyScan *node = makeNode(IndexOnlyScan);
Plan *plan = &node->scan.plan;
@@ -5064,6 +5067,7 @@ make_indexonlyscan(List *qptlist,
node->indexorderby = indexorderby;
node->indextlist = indextlist;
node->indexorderdir = indexscandir;
+ node->skipPrefixSize = skipPrefixSize;
return node;
}
diff --git a/src/backend/optimizer/plan/planner.c b/src/backend/optimizer/plan/planner.c
index e408e77d6f..3d6a8f78b6 100644
--- a/src/backend/optimizer/plan/planner.c
+++ b/src/backend/optimizer/plan/planner.c
@@ -4682,6 +4682,23 @@ create_distinct_paths(PlannerInfo *root,
path,
list_length(root->distinct_pathkeys),
numDistinctRows));
+
+ /* Also consider a skip scan, if possible. */
+ if (IsA(path, IndexPath) &&
+ path->pathtype == T_IndexOnlyScan &&
+ enable_indexskipscan &&
+ ((IndexPath *) path)->indexinfo->amcanskip &&
+ root->distinct_pathkeys != NIL)
+ {
+ int distinctPrefixKeys = list_length(root->distinct_pathkeys);
+
+ add_path(distinct_rel, (Path *)
+ create_skipscan_unique_path(root,
+ distinct_rel,
+ path,
+ distinctPrefixKeys,
+ numDistinctRows));
+ }
}
}
diff --git a/src/backend/optimizer/util/pathnode.c b/src/backend/optimizer/util/pathnode.c
index 56de8fc370..42363f5d54 100644
--- a/src/backend/optimizer/util/pathnode.c
+++ b/src/backend/optimizer/util/pathnode.c
@@ -2912,6 +2912,46 @@ create_upper_unique_path(PlannerInfo *root,
return pathnode;
}
+/*
+ * create_skipscan_unique_path
+ * Creates a pathnode the same as an existing IndexPath except based on
+ * skipping duplicate values. This may or may not be cheaper than using
+ * create_upper_unique_path.
+ *
+ * The input path must be an IndexPath for an index that supports amskip.
+ */
+IndexPath *
+create_skipscan_unique_path(PlannerInfo *root,
+ RelOptInfo *rel,
+ Path *basepath,
+ int distinctPrefixKeys,
+ double numGroups)
+{
+ IndexPath *pathnode = makeNode(IndexPath);
+
+ Assert(IsA(basepath, IndexPath));
+
+ /* We don't want to modify basepath, so make a copy. */
+ memcpy(pathnode, basepath, sizeof(IndexPath));
+
+ /* The size of the prefix we'll use for skipping. */
+ Assert(pathnode->indexinfo->amcanskip);
+ Assert(distinctPrefixKeys > 0);
+ Assert(distinctPrefixKeys <= list_length(pathnode->path.pathkeys));
+ pathnode->indexskipprefix = distinctPrefixKeys;
+
+ /*
+ * The cost to skip to each distinct value should be roughly the same as
+ * the cost of finding the first key times the number of distinct values
+ * we expect to find.
+ */
+ pathnode->path.startup_cost = basepath->startup_cost;
+ pathnode->path.total_cost = basepath->startup_cost * numGroups;
+ pathnode->path.rows = numGroups;
+
+ return pathnode;
+}
+
/*
* create_agg_path
* Creates a pathnode that represents performing aggregation/grouping
diff --git a/src/backend/optimizer/util/plancat.c b/src/backend/optimizer/util/plancat.c
index 702c4f89b8..aec39e9d19 100644
--- a/src/backend/optimizer/util/plancat.c
+++ b/src/backend/optimizer/util/plancat.c
@@ -270,6 +270,7 @@ get_relation_info(PlannerInfo *root, Oid relationObjectId, bool inhparent,
info->amoptionalkey = amroutine->amoptionalkey;
info->amsearcharray = amroutine->amsearcharray;
info->amsearchnulls = amroutine->amsearchnulls;
+ info->amcanskip = (amroutine->amskip != NULL);
info->amcanparallel = amroutine->amcanparallel;
info->amhasgettuple = (amroutine->amgettuple != NULL);
info->amhasgetbitmap = (amroutine->amgetbitmap != NULL);
diff --git a/src/backend/utils/misc/guc.c b/src/backend/utils/misc/guc.c
index aa564d153a..6ffdac16fa 100644
--- a/src/backend/utils/misc/guc.c
+++ b/src/backend/utils/misc/guc.c
@@ -905,6 +905,15 @@ static struct config_bool ConfigureNamesBool[] =
true,
NULL, NULL, NULL
},
+ {
+ {"enable_indexskipscan", PGC_USERSET, QUERY_TUNING_METHOD,
+ gettext_noop("Enables the planner's use of index-skip-scan plans."),
+ NULL
+ },
+ &enable_indexskipscan,
+ true,
+ NULL, NULL, NULL
+ },
{
{"enable_bitmapscan", PGC_USERSET, QUERY_TUNING_METHOD,
gettext_noop("Enables the planner's use of bitmap-scan plans."),
diff --git a/src/backend/utils/misc/postgresql.conf.sample b/src/backend/utils/misc/postgresql.conf.sample
index cccb5f145a..55da1df89c 100644
--- a/src/backend/utils/misc/postgresql.conf.sample
+++ b/src/backend/utils/misc/postgresql.conf.sample
@@ -347,6 +347,7 @@
#enable_hashjoin = on
#enable_indexscan = on
#enable_indexonlyscan = on
+#enable_indexskipscan = on
#enable_material = on
#enable_mergejoin = on
#enable_nestloop = on
diff --git a/src/include/access/amapi.h b/src/include/access/amapi.h
index 653ddc976b..082a9bb0d6 100644
--- a/src/include/access/amapi.h
+++ b/src/include/access/amapi.h
@@ -127,6 +127,10 @@ typedef void (*amrescan_function) (IndexScanDesc scan,
typedef bool (*amgettuple_function) (IndexScanDesc scan,
ScanDirection direction);
+/* skip past duplicates in a given prefix */
+typedef bool (*amskip_function) (IndexScanDesc scan,
+ ScanDirection dir, int prefix);
+
/* fetch all valid tuples */
typedef int64 (*amgetbitmap_function) (IndexScanDesc scan,
TIDBitmap *tbm);
@@ -221,6 +225,7 @@ typedef struct IndexAmRoutine
amendscan_function amendscan;
ammarkpos_function ammarkpos; /* can be NULL */
amrestrpos_function amrestrpos; /* can be NULL */
+ amskip_function amskip; /* can be NULL */
/* interface functions to support parallel index scans */
amestimateparallelscan_function amestimateparallelscan; /* can be NULL */
diff --git a/src/include/access/genam.h b/src/include/access/genam.h
index cad66513f6..a694e9a19b 100644
--- a/src/include/access/genam.h
+++ b/src/include/access/genam.h
@@ -172,6 +172,7 @@ extern IndexBulkDeleteResult *index_bulk_delete(IndexVacuumInfo *info,
extern IndexBulkDeleteResult *index_vacuum_cleanup(IndexVacuumInfo *info,
IndexBulkDeleteResult *stats);
extern bool index_can_return(Relation indexRelation, int attno);
+extern bool index_skip(IndexScanDesc scan, ScanDirection direction, int prefix);
extern RegProcedure index_getprocid(Relation irel, AttrNumber attnum,
uint16 procnum);
extern FmgrInfo *index_getprocinfo(Relation irel, AttrNumber attnum,
diff --git a/src/include/access/nbtree.h b/src/include/access/nbtree.h
index 473c6f2918..4fc0237389 100644
--- a/src/include/access/nbtree.h
+++ b/src/include/access/nbtree.h
@@ -654,6 +654,9 @@ typedef struct BTScanOpaqueData
*/
int markItemIndex; /* itemIndex, or -1 if not valid */
+ /* Work space for _bt_skip */
+ BTScanInsert skipScanKey; /* used to control skipping */
+
/* keep these last in struct for efficiency */
BTScanPosData currPos; /* current position data */
BTScanPosData markPos; /* marked position, if any */
@@ -758,6 +761,7 @@ extern OffsetNumber _bt_binsrch_insert(Relation rel, BTInsertState insertstate);
extern int32 _bt_compare(Relation rel, BTScanInsert key, Page page, OffsetNumber offnum);
extern bool _bt_first(IndexScanDesc scan, ScanDirection dir);
extern bool _bt_next(IndexScanDesc scan, ScanDirection dir);
+extern bool _bt_skip(IndexScanDesc scan, ScanDirection dir, int prefix);
extern Buffer _bt_get_endpoint(Relation rel, uint32 level, bool rightmost,
Snapshot snapshot);
@@ -782,6 +786,7 @@ extern void _bt_end_vacuum_callback(int code, Datum arg);
extern Size BTreeShmemSize(void);
extern void BTreeShmemInit(void);
extern bytea *btoptions(Datum reloptions, bool validate);
+extern bool btskip(IndexScanDesc scan, ScanDirection dir, int prefix);
extern bool btproperty(Oid index_oid, int attno,
IndexAMProperty prop, const char *propname,
bool *res, bool *isnull);
diff --git a/src/include/nodes/execnodes.h b/src/include/nodes/execnodes.h
index 869c303e15..a3505dd6a7 100644
--- a/src/include/nodes/execnodes.h
+++ b/src/include/nodes/execnodes.h
@@ -1395,6 +1395,8 @@ typedef struct IndexScanState
* RelationDesc index relation descriptor
* ScanDesc index scan descriptor
* VMBuffer buffer in use for visibility map testing, if any
+ * SkipPrefixSize number of keys for skip-based DISTINCT
+ * FirstTupleEmitted has the first tuple been emitted
* ioss_PscanLen Size of parallel index-only scan descriptor
* ----------------
*/
@@ -1413,6 +1415,8 @@ typedef struct IndexOnlyScanState
Relation ioss_RelationDesc;
struct IndexScanDescData *ioss_ScanDesc;
Buffer ioss_VMBuffer;
+ int ioss_SkipPrefixSize;
+ bool ioss_FirstTupleEmitted;
Size ioss_PscanLen;
} IndexOnlyScanState;
diff --git a/src/include/nodes/pathnodes.h b/src/include/nodes/pathnodes.h
index 253e0b7e48..653f3b174b 100644
--- a/src/include/nodes/pathnodes.h
+++ b/src/include/nodes/pathnodes.h
@@ -819,6 +819,7 @@ struct IndexOptInfo
bool amsearchnulls; /* can AM search for NULL/NOT NULL entries? */
bool amhasgettuple; /* does AM have amgettuple interface? */
bool amhasgetbitmap; /* does AM have amgetbitmap interface? */
+ bool amcanskip; /* can AM skip duplicate values? */
bool amcanparallel; /* does AM support parallel scan? */
/* Rather than include amapi.h here, we declare amcostestimate like this */
void (*amcostestimate) (); /* AM's cost estimator */
@@ -1155,6 +1156,9 @@ typedef struct Path
* we need not recompute them when considering using the same index in a
* bitmap index/heap scan (see BitmapHeapPath). The costs of the IndexPath
* itself represent the costs of an IndexScan or IndexOnlyScan plan type.
+ *
+ * 'indexskipprefix' represents the number of columns to consider for skip
+ * scans.
*----------
*/
typedef struct IndexPath
@@ -1167,6 +1171,7 @@ typedef struct IndexPath
ScanDirection indexscandir;
Cost indextotalcost;
Selectivity indexselectivity;
+ int indexskipprefix;
} IndexPath;
/*
diff --git a/src/include/nodes/plannodes.h b/src/include/nodes/plannodes.h
index 24740c31e3..148b8672f7 100644
--- a/src/include/nodes/plannodes.h
+++ b/src/include/nodes/plannodes.h
@@ -432,6 +432,7 @@ typedef struct IndexOnlyScan
List *indexorderby; /* list of index ORDER BY exprs */
List *indextlist; /* TargetEntry list describing index's cols */
ScanDirection indexorderdir; /* forward or backward or don't care */
+ int skipPrefixSize; /* the size of the prefix for distinct scans */
} IndexOnlyScan;
/* ----------------
diff --git a/src/include/optimizer/cost.h b/src/include/optimizer/cost.h
index ac6de0f6be..33c7a0a376 100644
--- a/src/include/optimizer/cost.h
+++ b/src/include/optimizer/cost.h
@@ -50,6 +50,7 @@ extern PGDLLIMPORT int max_parallel_workers_per_gather;
extern PGDLLIMPORT bool enable_seqscan;
extern PGDLLIMPORT bool enable_indexscan;
extern PGDLLIMPORT bool enable_indexonlyscan;
+extern PGDLLIMPORT bool enable_indexskipscan;
extern PGDLLIMPORT bool enable_bitmapscan;
extern PGDLLIMPORT bool enable_tidscan;
extern PGDLLIMPORT bool enable_sort;
diff --git a/src/include/optimizer/pathnode.h b/src/include/optimizer/pathnode.h
index 574bb85b50..2c480bc9c8 100644
--- a/src/include/optimizer/pathnode.h
+++ b/src/include/optimizer/pathnode.h
@@ -202,6 +202,11 @@ extern UpperUniquePath *create_upper_unique_path(PlannerInfo *root,
Path *subpath,
int numCols,
double numGroups);
+extern IndexPath *create_skipscan_unique_path(PlannerInfo *root,
+ RelOptInfo *rel,
+ Path *subpath,
+ int numCols,
+ double numGroups);
extern AggPath *create_agg_path(PlannerInfo *root,
RelOptInfo *rel,
Path *subpath,
diff --git a/src/test/regress/expected/create_index.out b/src/test/regress/expected/create_index.out
index cc3dda4c70..9d8d55eea2 100644
--- a/src/test/regress/expected/create_index.out
+++ b/src/test/regress/expected/create_index.out
@@ -19,6 +19,7 @@ CREATE INDEX tenk1_unique1 ON tenk1 USING btree(unique1 int4_ops);
CREATE INDEX tenk1_unique2 ON tenk1 USING btree(unique2 int4_ops);
CREATE INDEX tenk1_hundred ON tenk1 USING btree(hundred int4_ops);
CREATE INDEX tenk1_thous_tenthous ON tenk1 (thousand, tenthous);
+CREATE INDEX tenk1_four ON tenk1 (four);
CREATE INDEX tenk2_unique1 ON tenk2 USING btree(unique1 int4_ops);
CREATE INDEX tenk2_unique2 ON tenk2 USING btree(unique2 int4_ops);
CREATE INDEX tenk2_hundred ON tenk2 USING btree(hundred int4_ops);
diff --git a/src/test/regress/expected/select_distinct.out b/src/test/regress/expected/select_distinct.out
index f3696c6d1d..38c9bc4b9b 100644
--- a/src/test/regress/expected/select_distinct.out
+++ b/src/test/regress/expected/select_distinct.out
@@ -244,3 +244,28 @@ SELECT null IS NOT DISTINCT FROM null as "yes";
t
(1 row)
+-- index skip scan
+SELECT DISTINCT four FROM tenk1;
+ four
+------
+ 0
+ 1
+ 2
+ 3
+(4 rows)
+
+SELECT DISTINCT four FROM tenk1 WHERE four = 1;
+ four
+------
+ 1
+(1 row)
+
+EXPLAIN (VERBOSE, COSTS OFF)
+SELECT DISTINCT four FROM tenk1;
+ QUERY PLAN
+--------------------------------------------------
+ Index Only Scan using tenk1_four on public.tenk1
+ Output: four
+ Scan mode: Skip scan
+(3 rows)
+
diff --git a/src/test/regress/expected/sysviews.out b/src/test/regress/expected/sysviews.out
index a1c90eb905..bd3b373515 100644
--- a/src/test/regress/expected/sysviews.out
+++ b/src/test/regress/expected/sysviews.out
@@ -78,6 +78,7 @@ select name, setting from pg_settings where name like 'enable%';
enable_hashjoin | on
enable_indexonlyscan | on
enable_indexscan | on
+ enable_indexskipscan | on
enable_material | on
enable_mergejoin | on
enable_nestloop | on
@@ -89,7 +90,7 @@ select name, setting from pg_settings where name like 'enable%';
enable_seqscan | on
enable_sort | on
enable_tidscan | on
-(17 rows)
+(18 rows)
-- Test that the pg_timezone_names and pg_timezone_abbrevs views are
-- more-or-less working. We can't test their contents in any great detail
diff --git a/src/test/regress/sql/create_index.sql b/src/test/regress/sql/create_index.sql
index 15c0f1f5d1..296b07c1d4 100644
--- a/src/test/regress/sql/create_index.sql
+++ b/src/test/regress/sql/create_index.sql
@@ -26,6 +26,8 @@ CREATE INDEX tenk1_hundred ON tenk1 USING btree(hundred int4_ops);
CREATE INDEX tenk1_thous_tenthous ON tenk1 (thousand, tenthous);
+CREATE INDEX tenk1_four ON tenk1 (four);
+
CREATE INDEX tenk2_unique1 ON tenk2 USING btree(unique1 int4_ops);
CREATE INDEX tenk2_unique2 ON tenk2 USING btree(unique2 int4_ops);
diff --git a/src/test/regress/sql/select_distinct.sql b/src/test/regress/sql/select_distinct.sql
index a605e86449..992e8d7c4d 100644
--- a/src/test/regress/sql/select_distinct.sql
+++ b/src/test/regress/sql/select_distinct.sql
@@ -73,3 +73,10 @@ SELECT 1 IS NOT DISTINCT FROM 2 as "no";
SELECT 2 IS NOT DISTINCT FROM 2 as "yes";
SELECT 2 IS NOT DISTINCT FROM null as "no";
SELECT null IS NOT DISTINCT FROM null as "yes";
+
+-- index skip scan
+SELECT DISTINCT four FROM tenk1;
+SELECT DISTINCT four FROM tenk1 WHERE four = 1;
+
+EXPLAIN (VERBOSE, COSTS OFF)
+SELECT DISTINCT four FROM tenk1;
--
2.16.4