0002_warm_updates_v7.patch
application/octet-stream
Filename: 0002_warm_updates_v7.patch
Type: application/octet-stream
Part: 2
Patch
Format: unified
Series: patch v7
| File | + | − |
|---|---|---|
| contrib/bloom/blutils.c | 1 | 0 |
| src/backend/access/brin/brin.c | 1 | 0 |
| src/backend/access/gist/gist.c | 1 | 0 |
| src/backend/access/hash/hash.c | 3 | 2 |
| src/backend/access/hash/hashsearch.c | 5 | 0 |
| src/backend/access/hash/hashutil.c | 110 | 0 |
| src/backend/access/heap/heapam.c | 270 | 15 |
| src/backend/access/heap/pruneheap.c | 38 | 1 |
| src/backend/access/heap/README.WARM | 271 | 0 |
| src/backend/access/index/genam.c | 1 | 1 |
| src/backend/access/index/indexam.c | 73 | 16 |
| src/backend/access/nbtree/nbtinsert.c | 140 | 91 |
| src/backend/access/nbtree/nbtree.c | 5 | 2 |
| src/backend/access/nbtree/nbtutils.c | 104 | 0 |
| src/backend/access/spgist/spgutils.c | 1 | 0 |
| src/backend/catalog/index.c | 15 | 0 |
| src/backend/catalog/system_views.sql | 3 | 1 |
| src/backend/commands/constraint.c | 3 | 1 |
| src/backend/commands/copy.c | 3 | 0 |
| src/backend/commands/vacuumlazy.c | 17 | 0 |
| src/backend/executor/execIndexing.c | 14 | 1 |
| src/backend/executor/nodeBitmapHeapscan.c | 15 | 2 |
| src/backend/executor/nodeIndexonlyscan.c | 20 | 0 |
| src/backend/executor/nodeIndexscan.c | 5 | 3 |
| src/backend/executor/nodeModifyTable.c | 25 | 2 |
| src/backend/postmaster/pgstat.c | 6 | 1 |
| src/backend/utils/adt/pgstatfuncs.c | 33 | 0 |
| src/backend/utils/cache/relcache.c | 32 | 3 |
| src/backend/utils/misc/guc.c | 11 | 0 |
| src/include/access/amapi.h | 5 | 0 |
| src/include/access/hash.h | 4 | 0 |
| src/include/access/heapam.h | 6 | 3 |
| src/include/access/heapam_xlog.h | 7 | 2 |
| src/include/access/htup_details.h | 27 | 2 |
| src/include/access/nbtree.h | 2 | 0 |
| src/include/access/relscan.h | 2 | 1 |
| src/include/catalog/pg_proc.h | 4 | 0 |
| src/include/executor/executor.h | 1 | 0 |
| src/include/executor/nodeIndexscan.h | 1 | 0 |
| src/include/nodes/execnodes.h | 1 | 0 |
| src/include/pgstat.h | 3 | 1 |
| src/include/storage/itemid.h | 30 | 1 |
| src/include/utils/relcache.h | 2 | 1 |
| src/include/utils/rel.h | 3 | 0 |
| src/test/regress/expected/rules.out | 9 | 3 |
| src/test/regress/expected/warm.out | 51 | 0 |
| src/test/regress/parallel_schedule | 2 | 0 |
| src/test/regress/sql/warm.sql | 15 | 0 |
diff --git a/contrib/bloom/blutils.c b/contrib/bloom/blutils.c
index b68a0d1..b95275f 100644
--- a/contrib/bloom/blutils.c
+++ b/contrib/bloom/blutils.c
@@ -138,6 +138,7 @@ blhandler(PG_FUNCTION_ARGS)
amroutine->amendscan = blendscan;
amroutine->ammarkpos = NULL;
amroutine->amrestrpos = NULL;
+ amroutine->amrecheck = NULL;
PG_RETURN_POINTER(amroutine);
}
diff --git a/src/backend/access/brin/brin.c b/src/backend/access/brin/brin.c
index 1b45a4c..ba3fffb 100644
--- a/src/backend/access/brin/brin.c
+++ b/src/backend/access/brin/brin.c
@@ -111,6 +111,7 @@ brinhandler(PG_FUNCTION_ARGS)
amroutine->amendscan = brinendscan;
amroutine->ammarkpos = NULL;
amroutine->amrestrpos = NULL;
+ amroutine->amrecheck = NULL;
PG_RETURN_POINTER(amroutine);
}
diff --git a/src/backend/access/gist/gist.c b/src/backend/access/gist/gist.c
index b8aa9bc..491e411 100644
--- a/src/backend/access/gist/gist.c
+++ b/src/backend/access/gist/gist.c
@@ -88,6 +88,7 @@ gisthandler(PG_FUNCTION_ARGS)
amroutine->amendscan = gistendscan;
amroutine->ammarkpos = NULL;
amroutine->amrestrpos = NULL;
+ amroutine->amrecheck = NULL;
PG_RETURN_POINTER(amroutine);
}
diff --git a/src/backend/access/hash/hash.c b/src/backend/access/hash/hash.c
index 6806e32..2026004 100644
--- a/src/backend/access/hash/hash.c
+++ b/src/backend/access/hash/hash.c
@@ -85,6 +85,7 @@ hashhandler(PG_FUNCTION_ARGS)
amroutine->amendscan = hashendscan;
amroutine->ammarkpos = NULL;
amroutine->amrestrpos = NULL;
+ amroutine->amrecheck = hashrecheck;
PG_RETURN_POINTER(amroutine);
}
@@ -265,6 +266,8 @@ hashgettuple(IndexScanDesc scan, ScanDirection dir)
OffsetNumber offnum;
ItemPointer current;
bool res;
+ IndexTuple itup;
+
/* Hash indexes are always lossy since we store only the hash code */
scan->xs_recheck = true;
@@ -302,8 +305,6 @@ hashgettuple(IndexScanDesc scan, ScanDirection dir)
offnum <= maxoffnum;
offnum = OffsetNumberNext(offnum))
{
- IndexTuple itup;
-
itup = (IndexTuple) PageGetItem(page, PageGetItemId(page, offnum));
if (ItemPointerEquals(&(so->hashso_heappos), &(itup->t_tid)))
break;
diff --git a/src/backend/access/hash/hashsearch.c b/src/backend/access/hash/hashsearch.c
index 8d43b38..05b078f 100644
--- a/src/backend/access/hash/hashsearch.c
+++ b/src/backend/access/hash/hashsearch.c
@@ -59,6 +59,8 @@ _hash_next(IndexScanDesc scan, ScanDirection dir)
itup = (IndexTuple) PageGetItem(page, PageGetItemId(page, offnum));
so->hashso_heappos = itup->t_tid;
+ if (scan->xs_want_itup)
+ scan->xs_itup = itup;
return true;
}
@@ -407,6 +409,9 @@ _hash_first(IndexScanDesc scan, ScanDirection dir)
itup = (IndexTuple) PageGetItem(page, PageGetItemId(page, offnum));
so->hashso_heappos = itup->t_tid;
+ if (scan->xs_want_itup)
+ scan->xs_itup = itup;
+
return true;
}
diff --git a/src/backend/access/hash/hashutil.c b/src/backend/access/hash/hashutil.c
index fa9cbdc..6897985 100644
--- a/src/backend/access/hash/hashutil.c
+++ b/src/backend/access/hash/hashutil.c
@@ -17,8 +17,12 @@
#include "access/hash.h"
#include "access/reloptions.h"
#include "access/relscan.h"
+#include "catalog/index.h"
+#include "executor/executor.h"
+#include "nodes/execnodes.h"
#include "utils/lsyscache.h"
#include "utils/rel.h"
+#include "utils/datum.h"
#define CALC_NEW_BUCKET(old_bucket, lowmask) \
old_bucket | (lowmask + 1)
@@ -446,3 +450,109 @@ _hash_get_newbucket_from_oldbucket(Relation rel, Bucket old_bucket,
return new_bucket;
}
+
+/*
+ * Recheck if the heap tuple satisfies the key stored in the index tuple
+ */
+bool
+hashrecheck(Relation indexRel, IndexTuple indexTuple,
+ Relation heapRel, HeapTuple heapTuple)
+{
+ IndexInfo *indexInfo;
+ EState *estate;
+ ExprContext *econtext;
+ TupleTableSlot *slot;
+ Datum values[INDEX_MAX_KEYS];
+ bool isnull[INDEX_MAX_KEYS];
+ Datum values2[INDEX_MAX_KEYS];
+ bool isnull2[INDEX_MAX_KEYS];
+ int i;
+ bool equal;
+ int natts = indexRel->rd_rel->relnatts;
+ Form_pg_attribute att;
+
+ indexInfo = BuildIndexInfo(indexRel);
+
+ /*
+ * The heap tuple must be put into a slot for FormIndexDatum.
+ */
+ slot = MakeSingleTupleTableSlot(RelationGetDescr(heapRel));
+
+ ExecStoreTuple(heapTuple, slot, InvalidBuffer, false);
+
+ /*
+ * Typically the index won't have expressions, but if it does we need an
+ * EState to evaluate them. We need it for exclusion constraints too,
+ * even if they are just on simple columns.
+ */
+ if (indexInfo->ii_Expressions != NIL ||
+ indexInfo->ii_ExclusionOps != NULL)
+ {
+ estate = CreateExecutorState();
+ econtext = GetPerTupleExprContext(estate);
+ econtext->ecxt_scantuple = slot;
+ }
+ else
+ estate = NULL;
+
+ /*
+ * Form the index values and isnull flags for the index entry that we need
+ * to check.
+ *
+ * Note: if the index uses functions that are not as immutable as they are
+ * supposed to be, this could produce an index tuple different from the
+ * original. The index AM can catch such errors by verifying that it
+ * finds a matching index entry with the tuple's TID. For exclusion
+ * constraints we check this in check_exclusion_constraint().
+ */
+ FormIndexDatum(indexInfo, slot, estate, values, isnull);
+
+ /*
+ * HASH indexes compute a hash value of the key and store that in the
+ * index. So we must first obtain the hash of the value obtained from the
+ * heap and then do a comparison
+ */
+ _hash_convert_tuple(indexRel, values, isnull, values2, isnull2);
+
+ equal = true;
+ for (i = 1; i <= natts; i++)
+ {
+ Datum indxvalue;
+ bool indxisnull;
+
+ indxvalue = index_getattr(indexTuple, i, indexRel->rd_att, &indxisnull);
+
+ /*
+ * If both are NULL then they are equal
+ */
+ if (isnull2[i - 1] && indxisnull)
+ continue;
+
+ /*
+ * If either is NULL then they are not equal
+ */
+ if (isnull2[i - 1] || indxisnull)
+ {
+ equal = false;
+ break;
+ }
+
+ /*
+ * Now do a raw memory comparison
+ */
+ att = indexRel->rd_att->attrs[i - 1];
+ if (!datumIsEqual(values2[i - 1], indxvalue, att->attbyval,
+ att->attlen))
+ {
+ equal = false;
+ break;
+ }
+ }
+
+ if (estate != NULL)
+ FreeExecutorState(estate);
+
+ ExecDropSingleTupleTableSlot(slot);
+
+ return equal;
+}
diff --git a/src/backend/access/heap/README.WARM b/src/backend/access/heap/README.WARM
new file mode 100644
index 0000000..f793570
--- /dev/null
+++ b/src/backend/access/heap/README.WARM
@@ -0,0 +1,271 @@
+src/backend/access/heap/README.WARM
+
+Write Amplification Reduction Method (WARM)
+===========================================
+
+The Heap Only Tuple (HOT) feature greatly eliminated redudant index
+entries and allowed re-use of the dead space occupied by previously
+updated or deleted tuples (see src/backend/access/heap/README.HOT)
+
+One of the necessary conditions for satisfying HOT update is that the
+update must not change a column used in any of the indexes on the table.
+The condition is sometimes hard to meet, especially for complex
+workloads with several indexes on large yet frequently updated tables.
+Worse, sometimes only one or two index columns may be updated, but the
+regular non-HOT update will still insert a new index entry in every
+index on the table, irrespective of whether the key pertaining to the
+index changed or not.
+
+WARM is a technique devised to address these problems.
+
+
+Update Chains With Multiple Index Entries Pointing to the Root
+--------------------------------------------------------------
+
+When a non-HOT update is caused by an index key change, a new index
+entry must be inserted for the changed index. But if the index key
+hasn't changed for other indexes, we don't really need to insert a new
+entry. Even though the existing index entry is pointing to the old
+tuple, the new tuple is reachable via the t_ctid chain. To keep things
+simple, a WARM update requires that the heap block must have enough
+space to store the new version of the tuple. This is same as HOT
+updates.
+
+In WARM, we ensure that every index entry always points to the root of
+the WARM chain. In fact, a WARM chain looks exactly like a HOT chain
+except for the fact that there could be multiple index entries pointing
+to the root of the chain. So when new entry is inserted in an index for
+updated tuple, and if we are doing a WARM update, the new entry is made
+point to the root of the WARM chain.
+
+For example, if we have a table with two columns and two indexes on each
+of the column. When a tuple is first inserted the table, we have exactly
+one index entry pointing to the tuple from both indexes.
+
+ lp [1]
+ [1111, aaaa]
+
+ Index1's entry (1111) points to 1
+ Index2's entry (aaaa) also points to 1
+
+Now if the tuple's second column is updated and if there is room on the
+page, we perform a WARM update. To do so, Index1 does not get any new
+entry and Index2's new entry will still point to the root tuple of the
+chain.
+
+ lp [1] [2]
+ [1111, aaaa]->[111, bbbb]
+
+ Index1's entry (1111) points to 1
+ Index2's old entry (aaaa) points to 1
+ Index2's new entry (bbbb) also points to 1
+
+"A update chain which has more than one index entries pointing to its
+root line pointer is called WARM chain and the action that creates a
+WARM chain is called WARM update."
+
+Since all indexes always point to the root of the WARM chain, even when
+there are more than one index entries, WARM chains can be pruned and
+dead tuples can be removed without a need to do corresponding index
+cleanup.
+
+While this solves the problem of pruning dead tuples from a HOT/WARM
+chain, it also opens up a new technical challenge because now we have a
+situation where a heap tuple is reachable from multiple index entries,
+each having a different index key. While MVCC still ensures that only
+valid tuples are returned, a tuple with a wrong index key may be
+returned because of wrong index entries. In the above example, tuple
+[1111, bbbb] is reachable from both keys (aaaa) as well as (bbbb). For
+this reason, tuples returned from a WARM chain must always be rechecked
+for index key-match.
+
+Recheck Index Key Againt Heap Tuple
+-----------------------------------
+
+Since every Index AM has it's own notion of index tuples, each Index AM
+must implement its own method to recheck heap tuples. For example, a
+hash index stores the hash value of the column and hence recheck routine
+for hash AM must first compute the hash value of the heap attribute and
+then compare it against the value stored in the index tuple.
+
+The patch currently implement recheck routines for hash and btree
+indexes. If the table has an index which doesn't support recheck
+routine, WARM updates are disabled on such tables.
+
+Problem With Duplicate (key, ctid) Index Entries
+------------------------------------------------
+
+The index-key recheck logic works as long as there are no duplicate
+index keys, both pointing to the same WARM chain. In that case, the same
+valid tuple will be reachable via multiple index keys, yet satisfying
+the index key checks. In the above example, if the tuple [1111, bbbb] is
+again updated to [1111, aaaa] and if we insert a new index entry (aaaa)
+pointing to the root line pointer, we will end up with the following
+structure:
+
+ lp [1] [2] [3]
+ [1111, aaaa]->[1111, bbbb]->[1111, aaaa]
+
+ Index1's entry (1111) points to 1
+ Index2's oldest entry (aaaa) points to 1
+ Index2's old entry (bbbb) also points to 1
+ Index2's new entry (aaaa) also points to 1
+
+We must solve this problem to ensure that the same tuple is not
+reachable via multiple index pointers. There are couple of ways to
+address this issue:
+
+1. Do not allow WARM update to a tuple from a WARM chain. This
+guarantees that there can never be duplicate index entries to the same
+root line pointer because we must have checked for old and new index
+keys while doing the first WARM update.
+
+2. Do not allow duplicate (key, ctid) index pointers. In the above
+example, since (aaaa, 1) already exists in the index, we must not insert
+a duplicate index entry.
+
+The patch currently implements 1 i.e. do not do WARM updates to a tuple
+from a WARM chain. HOT updates are fine because they do not add a new
+index entry.
+
+Even with the restriction, this is a significant improvement because the
+number of regular UPDATEs are curtailed down to half.
+
+Expression and Partial Indexes
+------------------------------
+
+Expressions may evaluate to the same value even if the underlying column
+values have changed. A simple example is an index on "lower(col)" which
+will return the same value if the new heap value only differs in the
+case sensitivity. So we can not solely rely on the heap column check to
+decide whether or not to insert a new index entry for expression
+indexes. Similarly, for partial indexes, the predicate expression must
+be evaluated to decide whether or not to cause a new index entry when
+columns referred in the predicate expressions change.
+
+(None of these things are currently implemented and we squarely disallow
+WARM update if a column from expression indexes or predicate has
+changed).
+
+
+Efficiently Finding the Root Line Pointer
+-----------------------------------------
+
+During WARM update, we must be able to find the root line pointer of the
+tuple being updated. It must be noted that the t_ctid field in the heap
+tuple header is usually used to find the next tuple in the update chain.
+But the tuple that we are updating, must be the last tuple in the update
+chain. In such cases, the c_tid field usually points the tuple itself.
+So in theory, we could use the t_ctid to store additional information in
+the last tuple of the update chain, if the information about the tuple
+being the last tuple is stored elsewhere.
+
+We now utilize another bit from t_infomask2 to explicitly identify that
+this is the last tuple in the update chain.
+
+HEAP_LATEST_TUPLE - When this bit is set, the tuple is the last tuple in
+the update chain. The OffsetNumber part of t_ctid points to the root
+line pointer of the chain when HEAP_LATEST_TUPLE flag is set.
+
+If UPDATE operation is aborted, the last tuple in the update chain
+becomes dead. The root line pointer information stored in the tuple
+which remains the last valid tuple in the chain is also lost. In such
+rare cases, the root line pointer must be found in a hard way by
+scanning the entire heap page.
+
+Tracking WARM Chains
+--------------------
+
+The old and every subsequent tuple in the chain is marked with a special
+HEAP_WARM_TUPLE flag. We use the last remaining bit in t_infomask2 to
+store this information.
+
+When a tuple is returned from a WARM chain, the caller must do
+additional checks to ensure that the tuple matches the index key. Even
+if the tuple comes precedes the WARM update in the chain, it must still
+be rechecked for the index key match (case when old tuple is returned by
+the new index key). So we must follow the update chain everytime to the
+end to see check if this is a WARM chain.
+
+When the old updated tuple is retired and the root line pointer is
+converted into a redirected line pointer, we can copy the information
+about WARM chain to the redirected line pointer by storing a special
+value in the lp_len field of the line pointer. This will handle the most
+common case where a WARM chain is replaced by a redirect line pointer
+and a single tuple in the chain.
+
+Converting WARM chains back to HOT chains (VACUUM ?)
+----------------------------------------------------
+
+The current implementation of WARM allows only one WARM update per
+chain. This simplifies the design and addresses certain issues around
+duplicate scans. But this also implies that the benefit of WARM will be
+no more than 50%, which is still significant, but if we could return
+WARM chains back to normal status, we could do far more WARM updates.
+
+A distinct property of a WARM chain is that at least one index has more
+than one live index entries pointing to the root of the chain. In other
+words, if we can remove duplicate entry from every index or conclusively
+prove that there are no duplicate index entries for the root line
+pointer, the chain can again be marked as HOT.
+
+Here is one idea:
+
+A WARM chain has two parts, separated by the tuple that caused WARM
+update. All tuples in each part has matching index keys, but certain
+index keys may not match between these two parts. Lets say we mark heap
+tuples in each part with a special Red-Blue flag. The same flag is
+replicated in the index tuples. For example, when new rows are inserted
+in a table, they are marked with Blue flag and the index entries
+associated with those rows are also marked with Blue flag. When a row is
+WARM updated, the new version is marked with Red flag and the new index
+entry created by the update is also marked with Red flag.
+
+
+Heap chain: [1] [2] [3] [4]
+ [aaaa, 1111]B -> [aaaa, 1111]B -> [bbbb, 1111]R -> [bbbb, 1111]R
+
+Index1: (aaaa)B points to 1 (satisfies only tuples marked with B)
+ (bbbb)R points to 1 (satisfies only tuples marked with R)
+
+Index2: (1111)B points to 1 (satisfied bith B and R tuples)
+
+
+It's clear that for indexes with Red and Blue pointers, a heap tuple
+with Blue flag will be reachable from Blue pointer and that with Red
+flag will be reachable from Red pointer. But for indexes which did not
+create a new entry, both Blue and Red tuples will be reachable from Blue
+pointer (there is no Red pointer in such indexes). So, as a side note,
+matching Red and Blue flags is not enough from index scan perspective.
+
+During first heap scan of VACUUM, we look for tuples with
+HEAP_WARM_TUPLE set. If all live tuples in the chain are either marked
+with Blue flag or Red flag (but no mix of Red and Blue), then the chain
+is a candidate for HOT conversion. We remember the root line pointer
+and Red-Blue flag of the WARM chain in a separate array.
+
+If we have a Red WARM chain, then our goal is to remove Blue pointers
+and vice versa. But there is a catch. For Index2 above, there is only
+Blue pointer and that must not be removed. IOW we should remove Blue
+pointer iff a Red pointer exists. Since index vacuum may visit Red and
+Blue pointers in any order, I think we will need another index pass to
+remove dead index pointers. So in the first index pass we check which
+WARM candidates have 2 index pointers. In the second pass, we remove the
+dead pointer and reset Red flag is the surviving index pointer is Red.
+
+During the second heap scan, we fix WARM chain by clearing
+HEAP_WARM_TUPLE flag and also reset Red flag to Blue.
+
+There are some more problems around aborted vacuums. For example, if
+vacuum aborts after changing Red index flag to Blue but before removing
+the other Blue pointer, we will end up with two Blue pointers to a Red
+WARM chain. But since the HEAP_WARM_TUPLE flag on the heap tuple is
+still set, further WARM updates to the chain will be blocked. I guess we
+will need some special handling for case with multiple Blue pointers. We
+can either leave these WARM chains alone and let them die with a
+subsequent non-WARM update or must apply heap-recheck logic during index
+vacuum to find the dead pointer. Given that vacuum-aborts are not
+common, I am inclined to leave this case unhandled. We must still check
+for presence of multiple Blue pointers and ensure that we don't
+accidently remove either of the Blue pointers and not clear WARM chains
+either.
diff --git a/src/backend/access/heap/heapam.c b/src/backend/access/heap/heapam.c
index a22aae7..082bd1f 100644
--- a/src/backend/access/heap/heapam.c
+++ b/src/backend/access/heap/heapam.c
@@ -1957,6 +1957,76 @@ heap_fetch(Relation relation,
}
/*
+ * Check if the HOT chain is originating or continuing at tid ever became a
+ * WARM chain, even if the actual UPDATE operation finally aborted.
+ */
+static void
+hot_check_warm_chain(Page dp, ItemPointer tid, bool *recheck)
+{
+ TransactionId prev_xmax = InvalidTransactionId;
+ OffsetNumber offnum;
+ HeapTupleData heapTuple;
+
+ if (*recheck == true)
+ return;
+
+ offnum = ItemPointerGetOffsetNumber(tid);
+ heapTuple.t_self = *tid;
+ /* Scan through possible multiple members of HOT-chain */
+ for (;;)
+ {
+ ItemId lp;
+
+ /* check for bogus TID */
+ if (offnum < FirstOffsetNumber || offnum > PageGetMaxOffsetNumber(dp))
+ break;
+
+ lp = PageGetItemId(dp, offnum);
+
+ /* check for unused, dead, or redirected items */
+ if (!ItemIdIsNormal(lp))
+ break;
+
+ heapTuple.t_data = (HeapTupleHeader) PageGetItem(dp, lp);
+ ItemPointerSetOffsetNumber(&heapTuple.t_self, offnum);
+
+ /*
+ * The xmin should match the previous xmax value, else chain is
+ * broken.
+ */
+ if (TransactionIdIsValid(prev_xmax) &&
+ !TransactionIdEquals(prev_xmax,
+ HeapTupleHeaderGetXmin(heapTuple.t_data)))
+ break;
+
+
+ /*
+ * Presence of either WARM or WARM updated tuple signals possible
+ * breakage and the caller must recheck tuple returned from this chain
+ * for index satisfaction
+ */
+ if (HeapTupleHeaderIsHeapWarmTuple(heapTuple.t_data))
+ {
+ *recheck = true;
+ break;
+ }
+
+ /*
+ * Check to see if HOT chain continues past this tuple; if so fetch
+ * the next offnum and loop around.
+ */
+ if (HeapTupleIsHotUpdated(&heapTuple))
+ {
+ offnum = ItemPointerGetOffsetNumber(&heapTuple.t_data->t_ctid);
+ prev_xmax = HeapTupleHeaderGetUpdateXid(heapTuple.t_data);
+ }
+ else
+ break; /* end of chain */
+ }
+
+}
+
+/*
* heap_hot_search_buffer - search HOT chain for tuple satisfying snapshot
*
* On entry, *tid is the TID of a tuple (either a simple tuple, or the root
@@ -1976,11 +2046,14 @@ heap_fetch(Relation relation,
* Unlike heap_fetch, the caller must already have pin and (at least) share
* lock on the buffer; it is still pinned/locked at exit. Also unlike
* heap_fetch, we do not report any pgstats count; caller may do so if wanted.
+ *
+ * recheck should be set false on entry by caller, will be set true on exit
+ * if a WARM tuple is encountered.
*/
bool
heap_hot_search_buffer(ItemPointer tid, Relation relation, Buffer buffer,
Snapshot snapshot, HeapTuple heapTuple,
- bool *all_dead, bool first_call)
+ bool *all_dead, bool first_call, bool *recheck)
{
Page dp = (Page) BufferGetPage(buffer);
TransactionId prev_xmax = InvalidTransactionId;
@@ -2022,6 +2095,16 @@ heap_hot_search_buffer(ItemPointer tid, Relation relation, Buffer buffer,
/* Follow the redirect */
offnum = ItemIdGetRedirect(lp);
at_chain_start = false;
+
+ /* Check if it's a WARM chain */
+ if (recheck && *recheck == false)
+ {
+ if (ItemIdIsHeapWarm(lp))
+ {
+ *recheck = true;
+ Assert(!IsSystemRelation(relation));
+ }
+ }
continue;
}
/* else must be end of chain */
@@ -2034,9 +2117,12 @@ heap_hot_search_buffer(ItemPointer tid, Relation relation, Buffer buffer,
ItemPointerSetOffsetNumber(&heapTuple->t_self, offnum);
/*
- * Shouldn't see a HEAP_ONLY tuple at chain start.
+ * Shouldn't see a HEAP_ONLY tuple at chain start, unless we are
+ * dealing with a WARM updated tuple in which case deferred triggers
+ * may request to fetch a WARM tuple from middle of a chain.
*/
- if (at_chain_start && HeapTupleIsHeapOnly(heapTuple))
+ if (at_chain_start && HeapTupleIsHeapOnly(heapTuple) &&
+ !HeapTupleIsHeapWarmTuple(heapTuple))
break;
/*
@@ -2049,6 +2135,22 @@ heap_hot_search_buffer(ItemPointer tid, Relation relation, Buffer buffer,
break;
/*
+ * Check if there exists a WARM tuple somewhere down the chain and set
+ * recheck to TRUE.
+ *
+ * XXX This is not very efficient right now, and we should look for
+ * possible improvements here
+ */
+ if (recheck && *recheck == false)
+ {
+ hot_check_warm_chain(dp, &heapTuple->t_self, recheck);
+
+ /* WARM is not supported on system tables yet */
+ if (*recheck == true)
+ Assert(!IsSystemRelation(relation));
+ }
+
+ /*
* When first_call is true (and thus, skip is initially false) we'll
* return the first tuple we find. But on later passes, heapTuple
* will initially be pointing to the tuple we returned last time.
@@ -2121,18 +2223,41 @@ heap_hot_search_buffer(ItemPointer tid, Relation relation, Buffer buffer,
*/
bool
heap_hot_search(ItemPointer tid, Relation relation, Snapshot snapshot,
- bool *all_dead)
+ bool *all_dead, bool *recheck, Buffer *cbuffer,
+ HeapTuple heapTuple)
{
bool result;
Buffer buffer;
- HeapTupleData heapTuple;
+ ItemPointerData ret_tid = *tid;
buffer = ReadBuffer(relation, ItemPointerGetBlockNumber(tid));
LockBuffer(buffer, BUFFER_LOCK_SHARE);
- result = heap_hot_search_buffer(tid, relation, buffer, snapshot,
- &heapTuple, all_dead, true);
- LockBuffer(buffer, BUFFER_LOCK_UNLOCK);
- ReleaseBuffer(buffer);
+ result = heap_hot_search_buffer(&ret_tid, relation, buffer, snapshot,
+ heapTuple, all_dead, true, recheck);
+
+ /*
+ * If we are returning a potential candidate tuple from this chain and the
+ * caller has requested for "recheck" hint, keep the buffer locked and
+ * pinned. The caller must release the lock and pin on the buffer in all
+ * such cases
+ */
+ if (!result || !recheck || !(*recheck))
+ {
+ LockBuffer(buffer, BUFFER_LOCK_UNLOCK);
+ ReleaseBuffer(buffer);
+ }
+
+ /*
+ * Set the caller supplied tid with the actual location of the tuple being
+ * returned
+ */
+ if (result)
+ {
+ *tid = ret_tid;
+ if (cbuffer)
+ *cbuffer = buffer;
+ }
+
return result;
}
@@ -3439,13 +3564,15 @@ simple_heap_delete(Relation relation, ItemPointer tid)
HTSU_Result
heap_update(Relation relation, ItemPointer otid, HeapTuple newtup,
CommandId cid, Snapshot crosscheck, bool wait,
- HeapUpdateFailureData *hufd, LockTupleMode *lockmode)
+ HeapUpdateFailureData *hufd, LockTupleMode *lockmode,
+ Bitmapset **modified_attrsp, bool *warm_update)
{
HTSU_Result result;
TransactionId xid = GetCurrentTransactionId();
Bitmapset *hot_attrs;
Bitmapset *key_attrs;
Bitmapset *id_attrs;
+ Bitmapset *exprindx_attrs;
Bitmapset *interesting_attrs;
Bitmapset *modified_attrs;
ItemId lp;
@@ -3468,6 +3595,7 @@ heap_update(Relation relation, ItemPointer otid, HeapTuple newtup,
bool have_tuple_lock = false;
bool iscombo;
bool use_hot_update = false;
+ bool use_warm_update = false;
bool key_intact;
bool all_visible_cleared = false;
bool all_visible_cleared_new = false;
@@ -3492,6 +3620,10 @@ heap_update(Relation relation, ItemPointer otid, HeapTuple newtup,
(errcode(ERRCODE_INVALID_TRANSACTION_STATE),
errmsg("cannot update tuples during a parallel operation")));
+ /* Assume no-warm update */
+ if (warm_update)
+ *warm_update = false;
+
/*
* Fetch the list of attributes to be checked for various operations.
*
@@ -3513,10 +3645,13 @@ heap_update(Relation relation, ItemPointer otid, HeapTuple newtup,
key_attrs = RelationGetIndexAttrBitmap(relation, INDEX_ATTR_BITMAP_KEY);
id_attrs = RelationGetIndexAttrBitmap(relation,
INDEX_ATTR_BITMAP_IDENTITY_KEY);
+ exprindx_attrs = RelationGetIndexAttrBitmap(relation,
+ INDEX_ATTR_BITMAP_EXPR_PREDICATE);
+
interesting_attrs = bms_add_members(NULL, hot_attrs);
interesting_attrs = bms_add_members(interesting_attrs, key_attrs);
interesting_attrs = bms_add_members(interesting_attrs, id_attrs);
-
+ interesting_attrs = bms_add_members(interesting_attrs, exprindx_attrs);
block = ItemPointerGetBlockNumber(otid);
offnum = ItemPointerGetOffsetNumber(otid);
@@ -3568,6 +3703,9 @@ heap_update(Relation relation, ItemPointer otid, HeapTuple newtup,
modified_attrs = HeapDetermineModifiedColumns(relation, interesting_attrs,
&oldtup, newtup);
+ if (modified_attrsp)
+ *modified_attrsp = bms_copy(modified_attrs);
+
/*
* If we're not updating any "key" column, we can grab a weaker lock type.
* This allows for more concurrency when we are running simultaneously
@@ -3818,6 +3956,7 @@ l2:
bms_free(hot_attrs);
bms_free(key_attrs);
bms_free(id_attrs);
+ bms_free(exprindx_attrs);
bms_free(modified_attrs);
bms_free(interesting_attrs);
return result;
@@ -4126,6 +4265,36 @@ l2:
*/
if (!bms_overlap(modified_attrs, hot_attrs))
use_hot_update = true;
+ else
+ {
+ /*
+ * If no WARM updates yet on this chain, let this update be a WARM
+ * update.
+ *
+ * We check for both warm and warm updated tuples since if the
+ * previous WARM update aborted, we may still have added
+ * another index entry for this HOT chain. In such situations, we
+ * must not attempt a WARM update until duplicate (key, CTID) index
+ * entry issue is sorted out
+ *
+ * XXX Later we'll add more checks to ensure WARM chains can
+ * further be WARM updated. This is probably good to do first rounf
+ * of tests of remaining functionality
+ *
+ * XXX Disable WARM updates on system tables. There is nothing in
+ * principle that stops us from supporting this. But it would
+ * require API change to propogate the changed columns back to the
+ * caller so that CatalogUpdateIndexes() can avoid adding new
+ * entries to indexes that are not changed by update. This will be
+ * fixed once basic patch is tested. !!FIXME
+ */
+ if (relation->rd_supportswarm &&
+ !bms_overlap(modified_attrs, exprindx_attrs) &&
+ !bms_is_subset(hot_attrs, modified_attrs) &&
+ !HeapTupleIsHeapWarmTuple(&oldtup) &&
+ !IsSystemRelation(relation))
+ use_warm_update = true;
+ }
}
else
{
@@ -4168,6 +4337,21 @@ l2:
HeapTupleSetHeapOnly(heaptup);
/* Mark the caller's copy too, in case different from heaptup */
HeapTupleSetHeapOnly(newtup);
+
+ /*
+ * Even if we are doing a HOT update, we must carry forward the WARM
+ * flag because we may have already inserted another index entry
+ * pointing to our root and a third entry may create duplicates
+ *
+ * XXX This should be revisited if we get index (key, CTID) duplicate
+ * detection mechanism in place
+ */
+ if (HeapTupleIsHeapWarmTuple(&oldtup))
+ {
+ HeapTupleSetHeapWarmTuple(heaptup);
+ HeapTupleSetHeapWarmTuple(newtup);
+ }
+
/*
* For HOT (or WARM) updated tuples, we store the offset of the root
* line pointer of this chain in the ip_posid field of the new tuple.
@@ -4183,12 +4367,38 @@ l2:
ItemPointerGetOffsetNumber(&(oldtup.t_self)),
&root_offnum);
}
+ else if (use_warm_update)
+ {
+ Assert(!IsSystemRelation(relation));
+
+ /* Mark the old tuple as HOT-updated */
+ HeapTupleSetHotUpdated(&oldtup);
+ HeapTupleSetHeapWarmTuple(&oldtup);
+ /* And mark the new tuple as heap-only */
+ HeapTupleSetHeapOnly(heaptup);
+ HeapTupleSetHeapWarmTuple(heaptup);
+ /* Mark the caller's copy too, in case different from heaptup */
+ HeapTupleSetHeapOnly(newtup);
+ HeapTupleSetHeapWarmTuple(newtup);
+ if (HeapTupleHeaderHasRootOffset(oldtup.t_data))
+ root_offnum = HeapTupleHeaderGetRootOffset(oldtup.t_data);
+ else
+ heap_get_root_tuple_one(page,
+ ItemPointerGetOffsetNumber(&(oldtup.t_self)),
+ &root_offnum);
+
+ /* Let the caller know we did a WARM update */
+ if (warm_update)
+ *warm_update = true;
+ }
else
{
/* Make sure tuples are correctly marked as not-HOT */
HeapTupleClearHotUpdated(&oldtup);
HeapTupleClearHeapOnly(heaptup);
HeapTupleClearHeapOnly(newtup);
+ HeapTupleClearHeapWarmTuple(heaptup);
+ HeapTupleClearHeapWarmTuple(newtup);
root_offnum = InvalidOffsetNumber;
}
@@ -4307,7 +4517,10 @@ l2:
if (have_tuple_lock)
UnlockTupleTuplock(relation, &(oldtup.t_self), *lockmode);
- pgstat_count_heap_update(relation, use_hot_update);
+ /*
+ * Count HOT and WARM updates separately
+ */
+ pgstat_count_heap_update(relation, use_hot_update, use_warm_update);
/*
* If heaptup is a private copy, release it. Don't forget to copy t_self
@@ -4456,7 +4669,7 @@ simple_heap_update(Relation relation, ItemPointer otid, HeapTuple tup)
result = heap_update(relation, otid, tup,
GetCurrentCommandId(true), InvalidSnapshot,
true /* wait for commit */ ,
- &hufd, &lockmode);
+ &hufd, &lockmode, NULL, NULL);
switch (result)
{
case HeapTupleSelfUpdated:
@@ -7354,6 +7567,7 @@ log_heap_cleanup_info(RelFileNode rnode, TransactionId latestRemovedXid)
XLogRecPtr
log_heap_clean(Relation reln, Buffer buffer,
OffsetNumber *redirected, int nredirected,
+ OffsetNumber *warm, int nwarm,
OffsetNumber *nowdead, int ndead,
OffsetNumber *nowunused, int nunused,
TransactionId latestRemovedXid)
@@ -7367,6 +7581,7 @@ log_heap_clean(Relation reln, Buffer buffer,
xlrec.latestRemovedXid = latestRemovedXid;
xlrec.nredirected = nredirected;
xlrec.ndead = ndead;
+ xlrec.nwarm = nwarm;
XLogBeginInsert();
XLogRegisterData((char *) &xlrec, SizeOfHeapClean);
@@ -7389,6 +7604,10 @@ log_heap_clean(Relation reln, Buffer buffer,
XLogRegisterBufData(0, (char *) nowdead,
ndead * sizeof(OffsetNumber));
+ if (nwarm > 0)
+ XLogRegisterBufData(0, (char *) warm,
+ nwarm * sizeof(OffsetNumber));
+
if (nunused > 0)
XLogRegisterBufData(0, (char *) nowunused,
nunused * sizeof(OffsetNumber));
@@ -7494,6 +7713,7 @@ log_heap_update(Relation reln, Buffer oldbuf,
bool need_tuple_data = RelationIsLogicallyLogged(reln);
bool init;
int bufflags;
+ bool warm_update = false;
/* Caller should not call me on a non-WAL-logged relation */
Assert(RelationNeedsWAL(reln));
@@ -7505,6 +7725,9 @@ log_heap_update(Relation reln, Buffer oldbuf,
else
info = XLOG_HEAP_UPDATE;
+ if (HeapTupleIsHeapWarmTuple(newtup))
+ warm_update = true;
+
/*
* If the old and new tuple are on the same page, we only need to log the
* parts of the new tuple that were changed. That saves on the amount of
@@ -7578,6 +7801,8 @@ log_heap_update(Relation reln, Buffer oldbuf,
xlrec.flags |= XLH_UPDATE_CONTAINS_OLD_KEY;
}
}
+ if (warm_update)
+ xlrec.flags |= XLH_UPDATE_WARM_UPDATE;
/* If new tuple is the single and first tuple on page... */
if (ItemPointerGetOffsetNumber(&(newtup->t_self)) == FirstOffsetNumber &&
@@ -7945,24 +8170,38 @@ heap_xlog_clean(XLogReaderState *record)
OffsetNumber *redirected;
OffsetNumber *nowdead;
OffsetNumber *nowunused;
+ OffsetNumber *warm;
int nredirected;
int ndead;
int nunused;
+ int nwarm;
+ int i;
Size datalen;
+ bool warmchain[MaxHeapTuplesPerPage + 1];
redirected = (OffsetNumber *) XLogRecGetBlockData(record, 0, &datalen);
nredirected = xlrec->nredirected;
ndead = xlrec->ndead;
+ nwarm = xlrec->nwarm;
+
end = (OffsetNumber *) ((char *) redirected + datalen);
nowdead = redirected + (nredirected * 2);
- nowunused = nowdead + ndead;
- nunused = (end - nowunused);
+ warm = nowdead + ndead;
+ nowunused = warm + nwarm;
+
+ nunused = (end - warm);
Assert(nunused >= 0);
+ memset(warmchain, 0, sizeof (warmchain));
+ for (i = 0; i < nwarm; i++)
+ warmchain[warm[i]] = true;
+
+
/* Update all item pointers per the record, and repair fragmentation */
heap_page_prune_execute(buffer,
redirected, nredirected,
+ warmchain,
nowdead, ndead,
nowunused, nunused);
@@ -8549,16 +8788,22 @@ heap_xlog_update(XLogReaderState *record, bool hot_update)
Size freespace = 0;
XLogRedoAction oldaction;
XLogRedoAction newaction;
+ bool warm_update = false;
/* initialize to keep the compiler quiet */
oldtup.t_data = NULL;
oldtup.t_len = 0;
+ if (xlrec->flags & XLH_UPDATE_WARM_UPDATE)
+ warm_update = true;
+
XLogRecGetBlockTag(record, 0, &rnode, NULL, &newblk);
if (XLogRecGetBlockTag(record, 1, NULL, NULL, &oldblk))
{
/* HOT updates are never done across pages */
Assert(!hot_update);
+ /* WARM updates are never done across pages */
+ Assert(!warm_update);
}
else
oldblk = newblk;
@@ -8618,6 +8863,11 @@ heap_xlog_update(XLogReaderState *record, bool hot_update)
&htup->t_infomask2);
HeapTupleHeaderSetXmax(htup, xlrec->old_xmax);
HeapTupleHeaderSetCmax(htup, FirstCommandId, false);
+
+ /* Mark the old tuple has a WARM tuple */
+ if (warm_update)
+ HeapTupleHeaderSetHeapWarmTuple(htup);
+
/* Set forward chain link in t_ctid */
HeapTupleHeaderSetNextCtid(htup, ItemPointerGetBlockNumber(&newtid),
ItemPointerGetOffsetNumber(&newtid));
@@ -8753,6 +9003,11 @@ heap_xlog_update(XLogReaderState *record, bool hot_update)
HeapTupleHeaderSetXmin(htup, XLogRecGetXid(record));
HeapTupleHeaderSetCmin(htup, FirstCommandId);
HeapTupleHeaderSetXmax(htup, xlrec->new_xmax);
+
+ /* Mark the new tuple has a WARM tuple */
+ if (warm_update)
+ HeapTupleHeaderSetHeapWarmTuple(htup);
+
/* Make sure there is no forward chain link in t_ctid */
HeapTupleHeaderSetHeapLatest(htup);
diff --git a/src/backend/access/heap/pruneheap.c b/src/backend/access/heap/pruneheap.c
index 7c2231a..d71a297 100644
--- a/src/backend/access/heap/pruneheap.c
+++ b/src/backend/access/heap/pruneheap.c
@@ -36,12 +36,19 @@ typedef struct
int nredirected; /* numbers of entries in arrays below */
int ndead;
int nunused;
+ int nwarm;
/* arrays that accumulate indexes of items to be changed */
OffsetNumber redirected[MaxHeapTuplesPerPage * 2];
OffsetNumber nowdead[MaxHeapTuplesPerPage];
OffsetNumber nowunused[MaxHeapTuplesPerPage];
+ OffsetNumber warm[MaxHeapTuplesPerPage];
/* marked[i] is TRUE if item i is entered in one of the above arrays */
bool marked[MaxHeapTuplesPerPage + 1];
+ /*
+ * warmchain[i] is TRUE if item is becoming redirected lp and points a WARM
+ * chain
+ */
+ bool warmchain[MaxHeapTuplesPerPage + 1];
} PruneState;
/* Local functions */
@@ -54,6 +61,8 @@ static void heap_prune_record_redirect(PruneState *prstate,
OffsetNumber offnum, OffsetNumber rdoffnum);
static void heap_prune_record_dead(PruneState *prstate, OffsetNumber offnum);
static void heap_prune_record_unused(PruneState *prstate, OffsetNumber offnum);
+static void heap_prune_record_warmupdate(PruneState *prstate,
+ OffsetNumber offnum);
static void heap_get_root_tuples_internal(Page page,
OffsetNumber target_offnum, OffsetNumber *root_offsets);
@@ -203,8 +212,9 @@ heap_page_prune(Relation relation, Buffer buffer, TransactionId OldestXmin,
*/
prstate.new_prune_xid = InvalidTransactionId;
prstate.latestRemovedXid = *latestRemovedXid;
- prstate.nredirected = prstate.ndead = prstate.nunused = 0;
+ prstate.nredirected = prstate.ndead = prstate.nunused = prstate.nwarm = 0;
memset(prstate.marked, 0, sizeof(prstate.marked));
+ memset(prstate.warmchain, 0, sizeof(prstate.marked));
/* Scan the page */
maxoff = PageGetMaxOffsetNumber(page);
@@ -241,6 +251,7 @@ heap_page_prune(Relation relation, Buffer buffer, TransactionId OldestXmin,
*/
heap_page_prune_execute(buffer,
prstate.redirected, prstate.nredirected,
+ prstate.warmchain,
prstate.nowdead, prstate.ndead,
prstate.nowunused, prstate.nunused);
@@ -268,6 +279,7 @@ heap_page_prune(Relation relation, Buffer buffer, TransactionId OldestXmin,
recptr = log_heap_clean(relation, buffer,
prstate.redirected, prstate.nredirected,
+ prstate.warm, prstate.nwarm,
prstate.nowdead, prstate.ndead,
prstate.nowunused, prstate.nunused,
prstate.latestRemovedXid);
@@ -479,6 +491,12 @@ heap_prune_chain(Relation relation, Buffer buffer, OffsetNumber rootoffnum,
!TransactionIdEquals(HeapTupleHeaderGetXmin(htup), priorXmax))
break;
+ if (HeapTupleHeaderIsHeapWarmTuple(htup))
+ {
+ Assert(!IsSystemRelation(relation));
+ heap_prune_record_warmupdate(prstate, rootoffnum);
+ }
+
/*
* OK, this tuple is indeed a member of the chain.
*/
@@ -668,6 +686,18 @@ heap_prune_record_unused(PruneState *prstate, OffsetNumber offnum)
prstate->marked[offnum] = true;
}
+/* Record item pointer which is a root of a WARM chain */
+static void
+heap_prune_record_warmupdate(PruneState *prstate, OffsetNumber offnum)
+{
+ Assert(prstate->nwarm < MaxHeapTuplesPerPage);
+ if (prstate->warmchain[offnum])
+ return;
+ prstate->warm[prstate->nwarm] = offnum;
+ prstate->nwarm++;
+ prstate->warmchain[offnum] = true;
+}
+
/*
* Perform the actual page changes needed by heap_page_prune.
@@ -681,6 +711,7 @@ heap_prune_record_unused(PruneState *prstate, OffsetNumber offnum)
void
heap_page_prune_execute(Buffer buffer,
OffsetNumber *redirected, int nredirected,
+ bool *warmchain,
OffsetNumber *nowdead, int ndead,
OffsetNumber *nowunused, int nunused)
{
@@ -697,6 +728,12 @@ heap_page_prune_execute(Buffer buffer,
ItemId fromlp = PageGetItemId(page, fromoff);
ItemIdSetRedirect(fromlp, tooff);
+
+ /*
+ * Save information about WARM chains in the item itself
+ */
+ if (warmchain[fromoff])
+ ItemIdSetHeapWarm(fromlp);
}
/* Update all now-dead line pointers */
diff --git a/src/backend/access/index/genam.c b/src/backend/access/index/genam.c
index 65c941d..4f9fb12 100644
--- a/src/backend/access/index/genam.c
+++ b/src/backend/access/index/genam.c
@@ -99,7 +99,7 @@ RelationGetIndexScan(Relation indexRelation, int nkeys, int norderbys)
else
scan->orderByData = NULL;
- scan->xs_want_itup = false; /* may be set later */
+ scan->xs_want_itup = true; /* hack for now to always get index tuple */
/*
* During recovery we ignore killed tuples and don't bother to kill them
diff --git a/src/backend/access/index/indexam.c b/src/backend/access/index/indexam.c
index 54b71cb..3f9a0cf 100644
--- a/src/backend/access/index/indexam.c
+++ b/src/backend/access/index/indexam.c
@@ -71,10 +71,12 @@
#include "access/xlog.h"
#include "catalog/catalog.h"
#include "catalog/index.h"
+#include "executor/executor.h"
#include "pgstat.h"
#include "storage/bufmgr.h"
#include "storage/lmgr.h"
#include "storage/predicate.h"
+#include "utils/datum.h"
#include "utils/snapmgr.h"
#include "utils/tqual.h"
@@ -228,6 +230,20 @@ index_beginscan(Relation heapRelation,
scan->heapRelation = heapRelation;
scan->xs_snapshot = snapshot;
+ /*
+ * If the index supports recheck, make sure that index tuple is saved
+ * during index scans.
+ *
+ * XXX Ideally, we should look at all indexes on the table and check if
+ * WARM is at all supported on the base table. If WARM is not supported
+ * then we don't need to do any recheck. RelationGetIndexAttrBitmap() does
+ * do that and sets rd_supportswarm after looking at all indexes, but we
+ * can't be sure if the function was called at this point and we can't call
+ * it now for the risk of deadlock.
+ */
+ if (indexRelation->rd_amroutine->amrecheck)
+ scan->xs_want_itup = true;
+
return scan;
}
@@ -409,7 +425,7 @@ index_getnext_tid(IndexScanDesc scan, ScanDirection direction)
/*
* The AM's amgettuple proc finds the next index entry matching the scan
* keys, and puts the TID into scan->xs_ctup.t_self. It should also set
- * scan->xs_recheck and possibly scan->xs_itup, though we pay no attention
+ * scan->xs_tuple_recheck and possibly scan->xs_itup, though we pay no attention
* to those fields here.
*/
found = scan->indexRelation->rd_amroutine->amgettuple(scan, direction);
@@ -448,7 +464,7 @@ index_getnext_tid(IndexScanDesc scan, ScanDirection direction)
* dropped in a future index_getnext_tid, index_fetch_heap or index_endscan
* call).
*
- * Note: caller must check scan->xs_recheck, and perform rechecking of the
+ * Note: caller must check scan->xs_tuple_recheck, and perform rechecking of the
* scan keys if required. We do not do that here because we don't have
* enough information to do it efficiently in the general case.
* ----------------
@@ -475,6 +491,15 @@ index_fetch_heap(IndexScanDesc scan)
*/
if (prev_buf != scan->xs_cbuf)
heap_page_prune_opt(scan->heapRelation, scan->xs_cbuf);
+
+ /*
+ * If we're not always re-checking, reset recheck for this tuple
+ */
+ if (!scan->xs_recheck)
+ scan->xs_tuple_recheck = false;
+ else
+ scan->xs_tuple_recheck = true;
+
}
/* Obtain share-lock on the buffer so we can examine visibility */
@@ -484,32 +509,64 @@ index_fetch_heap(IndexScanDesc scan)
scan->xs_snapshot,
&scan->xs_ctup,
&all_dead,
- !scan->xs_continue_hot);
+ !scan->xs_continue_hot,
+ &scan->xs_tuple_recheck);
LockBuffer(scan->xs_cbuf, BUFFER_LOCK_UNLOCK);
if (got_heap_tuple)
{
+ bool res = true;
+
+ /*
+ * Ok we got a tuple which satisfies the snapshot, but if its part of a
+ * WARM chain, we must do additional checks to ensure that we are
+ * indeed returning a correct tuple. Note that if the index AM does not
+ * implement amrecheck method, then we don't any additional checks
+ * since WARM must have been disabled on such tables
+ *
+ * XXX What happens when a new index which does not support amcheck is
+ * added to the table? Do we need to handle this case or is CREATE
+ * INDEX and CREATE INDEX CONCURRENTLY smart enough to handle this
+ * issue?
+ */
+ if (scan->xs_tuple_recheck &&
+ scan->xs_itup &&
+ scan->indexRelation->rd_amroutine->amrecheck)
+ {
+ LockBuffer(scan->xs_cbuf, BUFFER_LOCK_SHARE);
+ res = scan->indexRelation->rd_amroutine->amrecheck(
+ scan->indexRelation,
+ scan->xs_itup,
+ scan->heapRelation,
+ &scan->xs_ctup);
+ LockBuffer(scan->xs_cbuf, BUFFER_LOCK_UNLOCK);
+ }
+
/*
* Only in a non-MVCC snapshot can more than one member of the HOT
* chain be visible.
*/
scan->xs_continue_hot = !IsMVCCSnapshot(scan->xs_snapshot);
pgstat_count_heap_fetch(scan->indexRelation);
- return &scan->xs_ctup;
- }
- /* We've reached the end of the HOT chain. */
- scan->xs_continue_hot = false;
+ if (res)
+ return &scan->xs_ctup;
+ }
+ else
+ {
+ /* We've reached the end of the HOT chain. */
+ scan->xs_continue_hot = false;
- /*
- * If we scanned a whole HOT chain and found only dead tuples, tell index
- * AM to kill its entry for that TID (this will take effect in the next
- * amgettuple call, in index_getnext_tid). We do not do this when in
- * recovery because it may violate MVCC to do so. See comments in
- * RelationGetIndexScan().
- */
- if (!scan->xactStartedInRecovery)
- scan->kill_prior_tuple = all_dead;
+ /*
+ * If we scanned a whole HOT chain and found only dead tuples, tell index
+ * AM to kill its entry for that TID (this will take effect in the next
+ * amgettuple call, in index_getnext_tid). We do not do this when in
+ * recovery because it may violate MVCC to do so. See comments in
+ * RelationGetIndexScan().
+ */
+ if (!scan->xactStartedInRecovery)
+ scan->kill_prior_tuple = all_dead;
+ }
return NULL;
}
diff --git a/src/backend/access/nbtree/nbtinsert.c b/src/backend/access/nbtree/nbtinsert.c
index ef69290..e0afffd 100644
--- a/src/backend/access/nbtree/nbtinsert.c
+++ b/src/backend/access/nbtree/nbtinsert.c
@@ -19,11 +19,14 @@
#include "access/nbtree.h"
#include "access/transam.h"
#include "access/xloginsert.h"
+#include "catalog/index.h"
+#include "executor/executor.h"
#include "miscadmin.h"
+#include "nodes/execnodes.h"
#include "storage/lmgr.h"
#include "storage/predicate.h"
#include "utils/tqual.h"
-
+#include "utils/datum.h"
typedef struct
{
@@ -249,6 +252,9 @@ _bt_check_unique(Relation rel, IndexTuple itup, Relation heapRel,
BTPageOpaque opaque;
Buffer nbuf = InvalidBuffer;
bool found = false;
+ Buffer buffer;
+ HeapTupleData heapTuple;
+ bool recheck = false;
/* Assume unique until we find a duplicate */
*is_unique = true;
@@ -308,6 +314,8 @@ _bt_check_unique(Relation rel, IndexTuple itup, Relation heapRel,
curitup = (IndexTuple) PageGetItem(page, curitemid);
htid = curitup->t_tid;
+ recheck = false;
+
/*
* If we are doing a recheck, we expect to find the tuple we
* are rechecking. It's not a duplicate, but we have to keep
@@ -325,112 +333,153 @@ _bt_check_unique(Relation rel, IndexTuple itup, Relation heapRel,
* have just a single index entry for the entire chain.
*/
else if (heap_hot_search(&htid, heapRel, &SnapshotDirty,
- &all_dead))
+ &all_dead, &recheck, &buffer,
+ &heapTuple))
{
TransactionId xwait;
+ bool result = true;
/*
- * It is a duplicate. If we are only doing a partial
- * check, then don't bother checking if the tuple is being
- * updated in another transaction. Just return the fact
- * that it is a potential conflict and leave the full
- * check till later.
+ * If the tuple was WARM update, we may again see our own
+ * tuple. Since WARM updates don't create new index
+ * entries, our own tuple is only reachable via the old
+ * index pointer
*/
- if (checkUnique == UNIQUE_CHECK_PARTIAL)
+ if (checkUnique == UNIQUE_CHECK_EXISTING &&
+ ItemPointerCompare(&htid, &itup->t_tid) == 0)
{
- if (nbuf != InvalidBuffer)
- _bt_relbuf(rel, nbuf);
- *is_unique = false;
- return InvalidTransactionId;
+ found = true;
+ result = false;
+ if (recheck)
+ UnlockReleaseBuffer(buffer);
}
-
- /*
- * If this tuple is being updated by other transaction
- * then we have to wait for its commit/abort.
- */
- xwait = (TransactionIdIsValid(SnapshotDirty.xmin)) ?
- SnapshotDirty.xmin : SnapshotDirty.xmax;
-
- if (TransactionIdIsValid(xwait))
+ else if (recheck)
{
- if (nbuf != InvalidBuffer)
- _bt_relbuf(rel, nbuf);
- /* Tell _bt_doinsert to wait... */
- *speculativeToken = SnapshotDirty.speculativeToken;
- return xwait;
+ result = btrecheck(rel, curitup, heapRel, &heapTuple);
+ UnlockReleaseBuffer(buffer);
}
- /*
- * Otherwise we have a definite conflict. But before
- * complaining, look to see if the tuple we want to insert
- * is itself now committed dead --- if so, don't complain.
- * This is a waste of time in normal scenarios but we must
- * do it to support CREATE INDEX CONCURRENTLY.
- *
- * We must follow HOT-chains here because during
- * concurrent index build, we insert the root TID though
- * the actual tuple may be somewhere in the HOT-chain.
- * While following the chain we might not stop at the
- * exact tuple which triggered the insert, but that's OK
- * because if we find a live tuple anywhere in this chain,
- * we have a unique key conflict. The other live tuple is
- * not part of this chain because it had a different index
- * entry.
- */
- htid = itup->t_tid;
- if (heap_hot_search(&htid, heapRel, SnapshotSelf, NULL))
- {
- /* Normal case --- it's still live */
- }
- else
+ if (result)
{
/*
- * It's been deleted, so no error, and no need to
- * continue searching
+ * It is a duplicate. If we are only doing a partial
+ * check, then don't bother checking if the tuple is being
+ * updated in another transaction. Just return the fact
+ * that it is a potential conflict and leave the full
+ * check till later.
*/
- break;
- }
+ if (checkUnique == UNIQUE_CHECK_PARTIAL)
+ {
+ if (nbuf != InvalidBuffer)
+ _bt_relbuf(rel, nbuf);
+ *is_unique = false;
+ return InvalidTransactionId;
+ }
- /*
- * Check for a conflict-in as we would if we were going to
- * write to this page. We aren't actually going to write,
- * but we want a chance to report SSI conflicts that would
- * otherwise be masked by this unique constraint
- * violation.
- */
- CheckForSerializableConflictIn(rel, NULL, buf);
+ /*
+ * If this tuple is being updated by other transaction
+ * then we have to wait for its commit/abort.
+ */
+ xwait = (TransactionIdIsValid(SnapshotDirty.xmin)) ?
+ SnapshotDirty.xmin : SnapshotDirty.xmax;
+
+ if (TransactionIdIsValid(xwait))
+ {
+ if (nbuf != InvalidBuffer)
+ _bt_relbuf(rel, nbuf);
+ /* Tell _bt_doinsert to wait... */
+ *speculativeToken = SnapshotDirty.speculativeToken;
+ return xwait;
+ }
- /*
- * This is a definite conflict. Break the tuple down into
- * datums and report the error. But first, make sure we
- * release the buffer locks we're holding ---
- * BuildIndexValueDescription could make catalog accesses,
- * which in the worst case might touch this same index and
- * cause deadlocks.
- */
- if (nbuf != InvalidBuffer)
- _bt_relbuf(rel, nbuf);
- _bt_relbuf(rel, buf);
+ /*
+ * Otherwise we have a definite conflict. But before
+ * complaining, look to see if the tuple we want to insert
+ * is itself now committed dead --- if so, don't complain.
+ * This is a waste of time in normal scenarios but we must
+ * do it to support CREATE INDEX CONCURRENTLY.
+ *
+ * We must follow HOT-chains here because during
+ * concurrent index build, we insert the root TID though
+ * the actual tuple may be somewhere in the HOT-chain.
+ * While following the chain we might not stop at the
+ * exact tuple which triggered the insert, but that's OK
+ * because if we find a live tuple anywhere in this chain,
+ * we have a unique key conflict. The other live tuple is
+ * not part of this chain because it had a different index
+ * entry.
+ */
+ recheck = false;
+ ItemPointerCopy(&itup->t_tid, &htid);
+ if (heap_hot_search(&htid, heapRel, SnapshotSelf, NULL,
+ &recheck, &buffer, &heapTuple))
+ {
+ bool result = true;
+ if (recheck)
+ {
+ /*
+ * Recheck if the tuple actually satisfies the
+ * index key. Otherwise, we might be following
+ * a wrong index pointer and mustn't entertain
+ * this tuple
+ */
+ result = btrecheck(rel, itup, heapRel, &heapTuple);
+ UnlockReleaseBuffer(buffer);
+ }
+ if (!result)
+ break;
+ /* Normal case --- it's still live */
+ }
+ else
+ {
+ /*
+ * It's been deleted, so no error, and no need to
+ * continue searching
+ */
+ break;
+ }
- {
- Datum values[INDEX_MAX_KEYS];
- bool isnull[INDEX_MAX_KEYS];
- char *key_desc;
-
- index_deform_tuple(itup, RelationGetDescr(rel),
- values, isnull);
-
- key_desc = BuildIndexValueDescription(rel, values,
- isnull);
-
- ereport(ERROR,
- (errcode(ERRCODE_UNIQUE_VIOLATION),
- errmsg("duplicate key value violates unique constraint \"%s\"",
- RelationGetRelationName(rel)),
- key_desc ? errdetail("Key %s already exists.",
- key_desc) : 0,
- errtableconstraint(heapRel,
- RelationGetRelationName(rel))));
+ /*
+ * Check for a conflict-in as we would if we were going to
+ * write to this page. We aren't actually going to write,
+ * but we want a chance to report SSI conflicts that would
+ * otherwise be masked by this unique constraint
+ * violation.
+ */
+ CheckForSerializableConflictIn(rel, NULL, buf);
+
+ /*
+ * This is a definite conflict. Break the tuple down into
+ * datums and report the error. But first, make sure we
+ * release the buffer locks we're holding ---
+ * BuildIndexValueDescription could make catalog accesses,
+ * which in the worst case might touch this same index and
+ * cause deadlocks.
+ */
+ if (nbuf != InvalidBuffer)
+ _bt_relbuf(rel, nbuf);
+ _bt_relbuf(rel, buf);
+
+ {
+ Datum values[INDEX_MAX_KEYS];
+ bool isnull[INDEX_MAX_KEYS];
+ char *key_desc;
+
+ index_deform_tuple(itup, RelationGetDescr(rel),
+ values, isnull);
+
+ key_desc = BuildIndexValueDescription(rel, values,
+ isnull);
+
+ ereport(ERROR,
+ (errcode(ERRCODE_UNIQUE_VIOLATION),
+ errmsg("duplicate key value violates unique constraint \"%s\"",
+ RelationGetRelationName(rel)),
+ key_desc ? errdetail("Key %s already exists.",
+ key_desc) : 0,
+ errtableconstraint(heapRel,
+ RelationGetRelationName(rel))));
+ }
}
}
else if (all_dead)
diff --git a/src/backend/access/nbtree/nbtree.c b/src/backend/access/nbtree/nbtree.c
index 128744c..6b1236a 100644
--- a/src/backend/access/nbtree/nbtree.c
+++ b/src/backend/access/nbtree/nbtree.c
@@ -23,6 +23,7 @@
#include "access/xlog.h"
#include "catalog/index.h"
#include "commands/vacuum.h"
+#include "executor/nodeIndexscan.h"
#include "storage/indexfsm.h"
#include "storage/ipc.h"
#include "storage/lmgr.h"
@@ -117,6 +118,7 @@ bthandler(PG_FUNCTION_ARGS)
amroutine->amendscan = btendscan;
amroutine->ammarkpos = btmarkpos;
amroutine->amrestrpos = btrestrpos;
+ amroutine->amrecheck = btrecheck;
PG_RETURN_POINTER(amroutine);
}
@@ -292,8 +294,9 @@ btgettuple(IndexScanDesc scan, ScanDirection dir)
BTScanOpaque so = (BTScanOpaque) scan->opaque;
bool res;
- /* btree indexes are never lossy */
- scan->xs_recheck = false;
+ /* btree indexes are never lossy, except for WARM tuples */
+ scan->xs_recheck = indexscan_recheck;
+ scan->xs_tuple_recheck = indexscan_recheck;
/*
* If we have any array keys, initialize them during first call for a
diff --git a/src/backend/access/nbtree/nbtutils.c b/src/backend/access/nbtree/nbtutils.c
index 063c988..c9c0501 100644
--- a/src/backend/access/nbtree/nbtutils.c
+++ b/src/backend/access/nbtree/nbtutils.c
@@ -20,11 +20,15 @@
#include "access/nbtree.h"
#include "access/reloptions.h"
#include "access/relscan.h"
+#include "catalog/index.h"
+#include "executor/executor.h"
#include "miscadmin.h"
+#include "nodes/execnodes.h"
#include "utils/array.h"
#include "utils/lsyscache.h"
#include "utils/memutils.h"
#include "utils/rel.h"
+#include "utils/datum.h"
typedef struct BTSortArrayContext
@@ -2065,3 +2069,103 @@ btproperty(Oid index_oid, int attno,
return false; /* punt to generic code */
}
}
+
+/*
+ * Check if the index tuple's key matches the one computed from the given heap
+ * tuple's attribute
+ */
+bool
+btrecheck(Relation indexRel, IndexTuple indexTuple,
+ Relation heapRel, HeapTuple heapTuple)
+{
+ IndexInfo *indexInfo;
+ EState *estate;
+ ExprContext *econtext;
+ TupleTableSlot *slot;
+ Datum values[INDEX_MAX_KEYS];
+ bool isnull[INDEX_MAX_KEYS];
+ int i;
+ bool equal;
+ int natts = indexRel->rd_rel->relnatts;
+ Form_pg_attribute att;
+
+ /* Get IndexInfo for this index */
+ indexInfo = BuildIndexInfo(indexRel);
+
+ /*
+ * The heap tuple must be put into a slot for FormIndexDatum.
+ */
+ slot = MakeSingleTupleTableSlot(RelationGetDescr(heapRel));
+
+ ExecStoreTuple(heapTuple, slot, InvalidBuffer, false);
+
+ /*
+ * Typically the index won't have expressions, but if it does we need an
+ * EState to evaluate them. We need it for exclusion constraints too,
+ * even if they are just on simple columns.
+ */
+ if (indexInfo->ii_Expressions != NIL ||
+ indexInfo->ii_ExclusionOps != NULL)
+ {
+ estate = CreateExecutorState();
+ econtext = GetPerTupleExprContext(estate);
+ econtext->ecxt_scantuple = slot;
+ }
+ else
+ estate = NULL;
+
+ /*
+ * Form the index values and isnull flags for the index entry that we need
+ * to check.
+ *
+ * Note: if the index uses functions that are not as immutable as they are
+ * supposed to be, this could produce an index tuple different from the
+ * original. The index AM can catch such errors by verifying that it
+ * finds a matching index entry with the tuple's TID. For exclusion
+ * constraints we check this in check_exclusion_constraint().
+ */
+ FormIndexDatum(indexInfo, slot, estate, values, isnull);
+
+ equal = true;
+ for (i = 1; i <= natts; i++)
+ {
+ Datum indxvalue;
+ bool indxisnull;
+
+ indxvalue = index_getattr(indexTuple, i, indexRel->rd_att, &indxisnull);
+
+ /*
+ * If both are NULL, then they are equal
+ */
+ if (isnull[i - 1] && indxisnull)
+ continue;
+
+ /*
+ * If just one is NULL, then they are not equal
+ */
+ if (isnull[i - 1] || indxisnull)
+ {
+ equal = false;
+ break;
+ }
+
+ /*
+ * Now just do a raw memory comparison. If the index tuple was formed
+ * using this heap tuple, the computed index values must match
+ */
+ att = indexRel->rd_att->attrs[i - 1];
+ if (!datumIsEqual(values[i - 1], indxvalue, att->attbyval,
+ att->attlen))
+ {
+ equal = false;
+ break;
+ }
+ }
+
+ if (estate != NULL)
+ FreeExecutorState(estate);
+
+ ExecDropSingleTupleTableSlot(slot);
+
+ return equal;
+}
diff --git a/src/backend/access/spgist/spgutils.c b/src/backend/access/spgist/spgutils.c
index d570ae5..813b5c3 100644
--- a/src/backend/access/spgist/spgutils.c
+++ b/src/backend/access/spgist/spgutils.c
@@ -67,6 +67,7 @@ spghandler(PG_FUNCTION_ARGS)
amroutine->amendscan = spgendscan;
amroutine->ammarkpos = NULL;
amroutine->amrestrpos = NULL;
+ amroutine->amrecheck = NULL;
PG_RETURN_POINTER(amroutine);
}
diff --git a/src/backend/catalog/index.c b/src/backend/catalog/index.c
index 08b646d..e76e928 100644
--- a/src/backend/catalog/index.c
+++ b/src/backend/catalog/index.c
@@ -54,6 +54,7 @@
#include "nodes/makefuncs.h"
#include "nodes/nodeFuncs.h"
#include "optimizer/clauses.h"
+#include "optimizer/var.h"
#include "parser/parser.h"
#include "storage/bufmgr.h"
#include "storage/lmgr.h"
@@ -1691,6 +1692,20 @@ BuildIndexInfo(Relation index)
ii->ii_Concurrent = false;
ii->ii_BrokenHotChain = false;
+ /* build a bitmap of all table attributes referred by this index */
+ for (i = 0; i < ii->ii_NumIndexAttrs; i++)
+ {
+ AttrNumber attr = ii->ii_KeyAttrNumbers[i];
+ ii->ii_indxattrs = bms_add_member(ii->ii_indxattrs, attr -
+ FirstLowInvalidHeapAttributeNumber);
+ }
+
+ /* Collect all attributes used in expressions, too */
+ pull_varattnos((Node *) ii->ii_Expressions, 1, &ii->ii_indxattrs);
+
+ /* Collect all attributes in the index predicate, too */
+ pull_varattnos((Node *) ii->ii_Predicate, 1, &ii->ii_indxattrs);
+
return ii;
}
diff --git a/src/backend/catalog/system_views.sql b/src/backend/catalog/system_views.sql
index e011af1..97672a9 100644
--- a/src/backend/catalog/system_views.sql
+++ b/src/backend/catalog/system_views.sql
@@ -472,6 +472,7 @@ CREATE VIEW pg_stat_all_tables AS
pg_stat_get_tuples_updated(C.oid) AS n_tup_upd,
pg_stat_get_tuples_deleted(C.oid) AS n_tup_del,
pg_stat_get_tuples_hot_updated(C.oid) AS n_tup_hot_upd,
+ pg_stat_get_tuples_warm_updated(C.oid) AS n_tup_warm_upd,
pg_stat_get_live_tuples(C.oid) AS n_live_tup,
pg_stat_get_dead_tuples(C.oid) AS n_dead_tup,
pg_stat_get_mod_since_analyze(C.oid) AS n_mod_since_analyze,
@@ -502,7 +503,8 @@ CREATE VIEW pg_stat_xact_all_tables AS
pg_stat_get_xact_tuples_inserted(C.oid) AS n_tup_ins,
pg_stat_get_xact_tuples_updated(C.oid) AS n_tup_upd,
pg_stat_get_xact_tuples_deleted(C.oid) AS n_tup_del,
- pg_stat_get_xact_tuples_hot_updated(C.oid) AS n_tup_hot_upd
+ pg_stat_get_xact_tuples_hot_updated(C.oid) AS n_tup_hot_upd,
+ pg_stat_get_xact_tuples_warm_updated(C.oid) AS n_tup_warm_upd
FROM pg_class C LEFT JOIN
pg_index I ON C.oid = I.indrelid
LEFT JOIN pg_namespace N ON (N.oid = C.relnamespace)
diff --git a/src/backend/commands/constraint.c b/src/backend/commands/constraint.c
index 26f9114..997c8f5 100644
--- a/src/backend/commands/constraint.c
+++ b/src/backend/commands/constraint.c
@@ -40,6 +40,7 @@ unique_key_recheck(PG_FUNCTION_ARGS)
TriggerData *trigdata = (TriggerData *) fcinfo->context;
const char *funcname = "unique_key_recheck";
HeapTuple new_row;
+ HeapTupleData heapTuple;
ItemPointerData tmptid;
Relation indexRel;
IndexInfo *indexInfo;
@@ -102,7 +103,8 @@ unique_key_recheck(PG_FUNCTION_ARGS)
* removed.
*/
tmptid = new_row->t_self;
- if (!heap_hot_search(&tmptid, trigdata->tg_relation, SnapshotSelf, NULL))
+ if (!heap_hot_search(&tmptid, trigdata->tg_relation, SnapshotSelf, NULL,
+ NULL, NULL, &heapTuple))
{
/*
* All rows in the HOT chain are dead, so skip the check.
diff --git a/src/backend/commands/copy.c b/src/backend/commands/copy.c
index ec5d6f1..5e57cc9 100644
--- a/src/backend/commands/copy.c
+++ b/src/backend/commands/copy.c
@@ -2551,6 +2551,8 @@ CopyFrom(CopyState cstate)
if (resultRelInfo->ri_NumIndices > 0)
recheckIndexes = ExecInsertIndexTuples(slot,
&(tuple->t_self),
+ &(tuple->t_self),
+ NULL,
estate,
false,
NULL,
@@ -2669,6 +2671,7 @@ CopyFromInsertBatch(CopyState cstate, EState *estate, CommandId mycid,
ExecStoreTuple(bufferedTuples[i], myslot, InvalidBuffer, false);
recheckIndexes =
ExecInsertIndexTuples(myslot, &(bufferedTuples[i]->t_self),
+ &(bufferedTuples[i]->t_self), NULL,
estate, false, NULL, NIL);
ExecARInsertTriggers(estate, resultRelInfo,
bufferedTuples[i],
diff --git a/src/backend/commands/vacuumlazy.c b/src/backend/commands/vacuumlazy.c
index b5fb325..cd9b9a7 100644
--- a/src/backend/commands/vacuumlazy.c
+++ b/src/backend/commands/vacuumlazy.c
@@ -1468,6 +1468,7 @@ lazy_vacuum_page(Relation onerel, BlockNumber blkno, Buffer buffer,
recptr = log_heap_clean(onerel, buffer,
NULL, 0, NULL, 0,
+ NULL, 0,
unused, uncnt,
vacrelstats->latestRemovedXid);
PageSetLSN(page, recptr);
@@ -2128,6 +2129,22 @@ heap_page_is_all_visible(Relation rel, Buffer buf,
break;
}
+ /*
+ * If this tuple was ever WARM updated or is a WARM tuple,
+ * there could be multiple index entries pointing to the
+ * root of this chain. We can't do index-only scans for
+ * such tuples without verifying index key check. So mark
+ * the page as !all_visible
+ *
+ * XXX Should we look at the root line pointer and check if
+ * WARM flag is set there or checking for tuples in the
+ * chain is good enough?
+ */
+ if (HeapTupleHeaderIsHeapWarmTuple(tuple.t_data))
+ {
+ all_visible = false;
+ }
+
/* Track newest xmin on page. */
if (TransactionIdFollows(xmin, *visibility_cutoff_xid))
*visibility_cutoff_xid = xmin;
diff --git a/src/backend/executor/execIndexing.c b/src/backend/executor/execIndexing.c
index 882ce18..5fe6182 100644
--- a/src/backend/executor/execIndexing.c
+++ b/src/backend/executor/execIndexing.c
@@ -270,6 +270,8 @@ ExecCloseIndices(ResultRelInfo *resultRelInfo)
List *
ExecInsertIndexTuples(TupleTableSlot *slot,
ItemPointer tupleid,
+ ItemPointer root_tid,
+ Bitmapset *modified_attrs,
EState *estate,
bool noDupErr,
bool *specConflict,
@@ -324,6 +326,17 @@ ExecInsertIndexTuples(TupleTableSlot *slot,
if (!indexInfo->ii_ReadyForInserts)
continue;
+ /*
+ * If modified_attrs is set, we only insert index entries for those
+ * indexes whose column has changed. All other indexes can use their
+ * existing index pointers to look up the new tuple
+ */
+ if (modified_attrs)
+ {
+ if (!bms_overlap(modified_attrs, indexInfo->ii_indxattrs))
+ continue;
+ }
+
/* Check for partial index */
if (indexInfo->ii_Predicate != NIL)
{
@@ -389,7 +402,7 @@ ExecInsertIndexTuples(TupleTableSlot *slot,
index_insert(indexRelation, /* index relation */
values, /* array of index Datums */
isnull, /* null flags */
- tupleid, /* tid of heap tuple */
+ root_tid, /* tid of heap or root tuple */
heapRelation, /* heap relation */
checkUnique); /* type of uniqueness check to do */
diff --git a/src/backend/executor/nodeBitmapHeapscan.c b/src/backend/executor/nodeBitmapHeapscan.c
index 449aacb..ff77349 100644
--- a/src/backend/executor/nodeBitmapHeapscan.c
+++ b/src/backend/executor/nodeBitmapHeapscan.c
@@ -37,6 +37,7 @@
#include "access/relscan.h"
#include "access/transam.h"
+#include "access/valid.h"
#include "executor/execdebug.h"
#include "executor/nodeBitmapHeapscan.h"
#include "pgstat.h"
@@ -362,11 +363,23 @@ bitgetpage(HeapScanDesc scan, TBMIterateResult *tbmres)
OffsetNumber offnum = tbmres->offsets[curslot];
ItemPointerData tid;
HeapTupleData heapTuple;
+ bool recheck = false;
ItemPointerSet(&tid, page, offnum);
if (heap_hot_search_buffer(&tid, scan->rs_rd, buffer, snapshot,
- &heapTuple, NULL, true))
- scan->rs_vistuples[ntup++] = ItemPointerGetOffsetNumber(&tid);
+ &heapTuple, NULL, true, &recheck))
+ {
+ bool valid = true;
+
+ if (scan->rs_key)
+ HeapKeyTest(&heapTuple, RelationGetDescr(scan->rs_rd),
+ scan->rs_nkeys, scan->rs_key, valid);
+ if (valid)
+ scan->rs_vistuples[ntup++] = ItemPointerGetOffsetNumber(&tid);
+
+ if (recheck)
+ tbmres->recheck = true;
+ }
}
}
else
diff --git a/src/backend/executor/nodeIndexonlyscan.c b/src/backend/executor/nodeIndexonlyscan.c
index 4f6f91c..49bda34 100644
--- a/src/backend/executor/nodeIndexonlyscan.c
+++ b/src/backend/executor/nodeIndexonlyscan.c
@@ -141,6 +141,26 @@ IndexOnlyNext(IndexOnlyScanState *node)
* but it's not clear whether it's a win to do so. The next index
* entry might require a visit to the same heap page.
*/
+
+ /*
+ * If the index was lossy or the tuple was WARM, we have to recheck
+ * the index quals using the fetched tuple.
+ */
+ if (scandesc->xs_tuple_recheck)
+ {
+ ExecStoreTuple(tuple, /* tuple to store */
+ slot, /* slot to store in */
+ scandesc->xs_cbuf, /* buffer containing tuple */
+ false); /* don't pfree */
+ econtext->ecxt_scantuple = slot;
+ ResetExprContext(econtext);
+ if (!ExecQual(node->indexqual, econtext, false))
+ {
+ /* Fails recheck, so drop it and loop back for another */
+ InstrCountFiltered2(node, 1);
+ continue;
+ }
+ }
}
/*
diff --git a/src/backend/executor/nodeIndexscan.c b/src/backend/executor/nodeIndexscan.c
index 3143bd9..daa0826 100644
--- a/src/backend/executor/nodeIndexscan.c
+++ b/src/backend/executor/nodeIndexscan.c
@@ -39,6 +39,8 @@
#include "utils/memutils.h"
#include "utils/rel.h"
+bool indexscan_recheck = false;
+
/*
* When an ordering operator is used, tuples fetched from the index that
* need to be reordered are queued in a pairing heap, as ReorderTuples.
@@ -115,10 +117,10 @@ IndexNext(IndexScanState *node)
false); /* don't pfree */
/*
- * If the index was lossy, we have to recheck the index quals using
- * the fetched tuple.
+ * If the index was lossy or the tuple was WARM, we have to recheck
+ * the index quals using the fetched tuple.
*/
- if (scandesc->xs_recheck)
+ if (scandesc->xs_recheck || scandesc->xs_tuple_recheck)
{
econtext->ecxt_scantuple = slot;
ResetExprContext(econtext);
diff --git a/src/backend/executor/nodeModifyTable.c b/src/backend/executor/nodeModifyTable.c
index efb0c5e..3183db4 100644
--- a/src/backend/executor/nodeModifyTable.c
+++ b/src/backend/executor/nodeModifyTable.c
@@ -448,6 +448,7 @@ ExecInsert(ModifyTableState *mtstate,
/* insert index entries for tuple */
recheckIndexes = ExecInsertIndexTuples(slot, &(tuple->t_self),
+ &(tuple->t_self), NULL,
estate, true, &specConflict,
arbiterIndexes);
@@ -494,6 +495,7 @@ ExecInsert(ModifyTableState *mtstate,
/* insert index entries for tuple */
if (resultRelInfo->ri_NumIndices > 0)
recheckIndexes = ExecInsertIndexTuples(slot, &(tuple->t_self),
+ &(tuple->t_self), NULL,
estate, false, NULL,
arbiterIndexes);
}
@@ -824,6 +826,9 @@ ExecUpdate(ItemPointer tupleid,
HTSU_Result result;
HeapUpdateFailureData hufd;
List *recheckIndexes = NIL;
+ Bitmapset *modified_attrs = NULL;
+ ItemPointerData root_tid;
+ bool warm_update;
/*
* abort the operation if not running transactions
@@ -938,7 +943,7 @@ lreplace:;
estate->es_output_cid,
estate->es_crosscheck_snapshot,
true /* wait for commit */ ,
- &hufd, &lockmode);
+ &hufd, &lockmode, &modified_attrs, &warm_update);
switch (result)
{
case HeapTupleSelfUpdated:
@@ -1025,10 +1030,28 @@ lreplace:;
* the t_self field.
*
* If it's a HOT update, we mustn't insert new index entries.
+ *
+ * If it's a WARM update, then we must insert new entries with TID
+ * pointing to the root of the WARM chain.
*/
- if (resultRelInfo->ri_NumIndices > 0 && !HeapTupleIsHeapOnly(tuple))
+ if (resultRelInfo->ri_NumIndices > 0 &&
+ (!HeapTupleIsHeapOnly(tuple) || warm_update))
+ {
+ if (warm_update)
+ ItemPointerSet(&root_tid,
+ ItemPointerGetBlockNumber(&(tuple->t_self)),
+ HeapTupleHeaderGetRootOffset(tuple->t_data));
+ else
+ {
+ ItemPointerCopy(&tuple->t_self, &root_tid);
+ bms_free(modified_attrs);
+ modified_attrs = NULL;
+ }
recheckIndexes = ExecInsertIndexTuples(slot, &(tuple->t_self),
+ &root_tid,
+ modified_attrs,
estate, false, NULL, NIL);
+ }
}
if (canSetTag)
diff --git a/src/backend/postmaster/pgstat.c b/src/backend/postmaster/pgstat.c
index c7584cb..d89d37b 100644
--- a/src/backend/postmaster/pgstat.c
+++ b/src/backend/postmaster/pgstat.c
@@ -1823,7 +1823,7 @@ pgstat_count_heap_insert(Relation rel, int n)
* pgstat_count_heap_update - count a tuple update
*/
void
-pgstat_count_heap_update(Relation rel, bool hot)
+pgstat_count_heap_update(Relation rel, bool hot, bool warm)
{
PgStat_TableStatus *pgstat_info = rel->pgstat_info;
@@ -1841,6 +1841,8 @@ pgstat_count_heap_update(Relation rel, bool hot)
/* t_tuples_hot_updated is nontransactional, so just advance it */
if (hot)
pgstat_info->t_counts.t_tuples_hot_updated++;
+ else if (warm)
+ pgstat_info->t_counts.t_tuples_warm_updated++;
}
}
@@ -4083,6 +4085,7 @@ pgstat_get_tab_entry(PgStat_StatDBEntry *dbentry, Oid tableoid, bool create)
result->tuples_updated = 0;
result->tuples_deleted = 0;
result->tuples_hot_updated = 0;
+ result->tuples_warm_updated = 0;
result->n_live_tuples = 0;
result->n_dead_tuples = 0;
result->changes_since_analyze = 0;
@@ -5192,6 +5195,7 @@ pgstat_recv_tabstat(PgStat_MsgTabstat *msg, int len)
tabentry->tuples_updated = tabmsg->t_counts.t_tuples_updated;
tabentry->tuples_deleted = tabmsg->t_counts.t_tuples_deleted;
tabentry->tuples_hot_updated = tabmsg->t_counts.t_tuples_hot_updated;
+ tabentry->tuples_warm_updated = tabmsg->t_counts.t_tuples_warm_updated;
tabentry->n_live_tuples = tabmsg->t_counts.t_delta_live_tuples;
tabentry->n_dead_tuples = tabmsg->t_counts.t_delta_dead_tuples;
tabentry->changes_since_analyze = tabmsg->t_counts.t_changed_tuples;
@@ -5219,6 +5223,7 @@ pgstat_recv_tabstat(PgStat_MsgTabstat *msg, int len)
tabentry->tuples_updated += tabmsg->t_counts.t_tuples_updated;
tabentry->tuples_deleted += tabmsg->t_counts.t_tuples_deleted;
tabentry->tuples_hot_updated += tabmsg->t_counts.t_tuples_hot_updated;
+ tabentry->tuples_warm_updated += tabmsg->t_counts.t_tuples_warm_updated;
/* If table was truncated, first reset the live/dead counters */
if (tabmsg->t_counts.t_truncated)
{
diff --git a/src/backend/utils/adt/pgstatfuncs.c b/src/backend/utils/adt/pgstatfuncs.c
index 2d3cf9e..ef4f5b4 100644
--- a/src/backend/utils/adt/pgstatfuncs.c
+++ b/src/backend/utils/adt/pgstatfuncs.c
@@ -37,6 +37,7 @@ extern Datum pg_stat_get_tuples_inserted(PG_FUNCTION_ARGS);
extern Datum pg_stat_get_tuples_updated(PG_FUNCTION_ARGS);
extern Datum pg_stat_get_tuples_deleted(PG_FUNCTION_ARGS);
extern Datum pg_stat_get_tuples_hot_updated(PG_FUNCTION_ARGS);
+extern Datum pg_stat_get_tuples_warm_updated(PG_FUNCTION_ARGS);
extern Datum pg_stat_get_live_tuples(PG_FUNCTION_ARGS);
extern Datum pg_stat_get_dead_tuples(PG_FUNCTION_ARGS);
extern Datum pg_stat_get_mod_since_analyze(PG_FUNCTION_ARGS);
@@ -115,6 +116,7 @@ extern Datum pg_stat_get_xact_tuples_inserted(PG_FUNCTION_ARGS);
extern Datum pg_stat_get_xact_tuples_updated(PG_FUNCTION_ARGS);
extern Datum pg_stat_get_xact_tuples_deleted(PG_FUNCTION_ARGS);
extern Datum pg_stat_get_xact_tuples_hot_updated(PG_FUNCTION_ARGS);
+extern Datum pg_stat_get_xact_tuples_warm_updated(PG_FUNCTION_ARGS);
extern Datum pg_stat_get_xact_blocks_fetched(PG_FUNCTION_ARGS);
extern Datum pg_stat_get_xact_blocks_hit(PG_FUNCTION_ARGS);
@@ -245,6 +247,22 @@ pg_stat_get_tuples_hot_updated(PG_FUNCTION_ARGS)
Datum
+pg_stat_get_tuples_warm_updated(PG_FUNCTION_ARGS)
+{
+ Oid relid = PG_GETARG_OID(0);
+ int64 result;
+ PgStat_StatTabEntry *tabentry;
+
+ if ((tabentry = pgstat_fetch_stat_tabentry(relid)) == NULL)
+ result = 0;
+ else
+ result = (int64) (tabentry->tuples_warm_updated);
+
+ PG_RETURN_INT64(result);
+}
+
+
+Datum
pg_stat_get_live_tuples(PG_FUNCTION_ARGS)
{
Oid relid = PG_GETARG_OID(0);
@@ -1744,6 +1762,21 @@ pg_stat_get_xact_tuples_hot_updated(PG_FUNCTION_ARGS)
}
Datum
+pg_stat_get_xact_tuples_warm_updated(PG_FUNCTION_ARGS)
+{
+ Oid relid = PG_GETARG_OID(0);
+ int64 result;
+ PgStat_TableStatus *tabentry;
+
+ if ((tabentry = find_tabstat_entry(relid)) == NULL)
+ result = 0;
+ else
+ result = (int64) (tabentry->t_counts.t_tuples_warm_updated);
+
+ PG_RETURN_INT64(result);
+}
+
+Datum
pg_stat_get_xact_blocks_fetched(PG_FUNCTION_ARGS)
{
Oid relid = PG_GETARG_OID(0);
diff --git a/src/backend/utils/cache/relcache.c b/src/backend/utils/cache/relcache.c
index 79e0b1f..c6ef4e2 100644
--- a/src/backend/utils/cache/relcache.c
+++ b/src/backend/utils/cache/relcache.c
@@ -2030,6 +2030,7 @@ RelationDestroyRelation(Relation relation, bool remember_tupdesc)
list_free_deep(relation->rd_fkeylist);
list_free(relation->rd_indexlist);
bms_free(relation->rd_indexattr);
+ bms_free(relation->rd_exprindexattr);
bms_free(relation->rd_keyattr);
bms_free(relation->rd_idattr);
if (relation->rd_options)
@@ -4373,12 +4374,15 @@ Bitmapset *
RelationGetIndexAttrBitmap(Relation relation, IndexAttrBitmapKind attrKind)
{
Bitmapset *indexattrs; /* indexed columns */
+ Bitmapset *exprindexattrs; /* indexed columns in expression/prediacate
+ indexes */
Bitmapset *uindexattrs; /* columns in unique indexes */
Bitmapset *idindexattrs; /* columns in the replica identity */
List *indexoidlist;
Oid relreplindex;
ListCell *l;
MemoryContext oldcxt;
+ bool supportswarm = true;/* True if the table can be WARM updated */
/* Quick exit if we already computed the result. */
if (relation->rd_indexattr != NULL)
@@ -4391,6 +4395,8 @@ RelationGetIndexAttrBitmap(Relation relation, IndexAttrBitmapKind attrKind)
return bms_copy(relation->rd_keyattr);
case INDEX_ATTR_BITMAP_IDENTITY_KEY:
return bms_copy(relation->rd_idattr);
+ case INDEX_ATTR_BITMAP_EXPR_PREDICATE:
+ return bms_copy(relation->rd_exprindexattr);
default:
elog(ERROR, "unknown attrKind %u", attrKind);
}
@@ -4429,6 +4435,7 @@ RelationGetIndexAttrBitmap(Relation relation, IndexAttrBitmapKind attrKind)
* won't be returned at all by RelationGetIndexList.
*/
indexattrs = NULL;
+ exprindexattrs = NULL;
uindexattrs = NULL;
idindexattrs = NULL;
foreach(l, indexoidlist)
@@ -4474,19 +4481,38 @@ RelationGetIndexAttrBitmap(Relation relation, IndexAttrBitmapKind attrKind)
}
/* Collect all attributes used in expressions, too */
- pull_varattnos((Node *) indexInfo->ii_Expressions, 1, &indexattrs);
+ pull_varattnos((Node *) indexInfo->ii_Expressions, 1, &exprindexattrs);
/* Collect all attributes in the index predicate, too */
- pull_varattnos((Node *) indexInfo->ii_Predicate, 1, &indexattrs);
+ pull_varattnos((Node *) indexInfo->ii_Predicate, 1, &exprindexattrs);
+
+ /*
+ * indexattrs should include attributes referenced in index expressions
+ * and predicates too
+ */
+ indexattrs = bms_add_members(indexattrs, exprindexattrs);
+
+ /*
+ * Check if the index has amrecheck method defined. If the method is
+ * not defined, the index does not support WARM update. Completely
+ * disable WARM updates on such tables
+ */
+ if (!indexDesc->rd_amroutine->amrecheck)
+ supportswarm = false;
index_close(indexDesc, AccessShareLock);
}
list_free(indexoidlist);
+ /* Remember if the table can do WARM updates */
+ relation->rd_supportswarm = supportswarm;
+
/* Don't leak the old values of these bitmaps, if any */
bms_free(relation->rd_indexattr);
relation->rd_indexattr = NULL;
+ bms_free(relation->rd_exprindexattr);
+ relation->rd_exprindexattr = NULL;
bms_free(relation->rd_keyattr);
relation->rd_keyattr = NULL;
bms_free(relation->rd_idattr);
@@ -4502,7 +4528,8 @@ RelationGetIndexAttrBitmap(Relation relation, IndexAttrBitmapKind attrKind)
oldcxt = MemoryContextSwitchTo(CacheMemoryContext);
relation->rd_keyattr = bms_copy(uindexattrs);
relation->rd_idattr = bms_copy(idindexattrs);
- relation->rd_indexattr = bms_copy(indexattrs);
+ relation->rd_exprindexattr = bms_copy(exprindexattrs);
+ relation->rd_indexattr = bms_copy(bms_union(indexattrs, exprindexattrs));
MemoryContextSwitchTo(oldcxt);
/* We return our original working copy for caller to play with */
@@ -4514,6 +4541,8 @@ RelationGetIndexAttrBitmap(Relation relation, IndexAttrBitmapKind attrKind)
return uindexattrs;
case INDEX_ATTR_BITMAP_IDENTITY_KEY:
return idindexattrs;
+ case INDEX_ATTR_BITMAP_EXPR_PREDICATE:
+ return exprindexattrs;
default:
elog(ERROR, "unknown attrKind %u", attrKind);
return NULL;
diff --git a/src/backend/utils/misc/guc.c b/src/backend/utils/misc/guc.c
index 28ebcb6..2241ffb 100644
--- a/src/backend/utils/misc/guc.c
+++ b/src/backend/utils/misc/guc.c
@@ -112,6 +112,7 @@ extern char *default_tablespace;
extern char *temp_tablespaces;
extern bool ignore_checksum_failure;
extern bool synchronize_seqscans;
+extern bool indexscan_recheck;
#ifdef TRACE_SYNCSCAN
extern bool trace_syncscan;
@@ -1288,6 +1289,16 @@ static struct config_bool ConfigureNamesBool[] =
NULL, NULL, NULL
},
{
+ {"indexscan_recheck", PGC_USERSET, DEVELOPER_OPTIONS,
+ gettext_noop("Recheck heap rows returned from an index scan."),
+ NULL,
+ GUC_NOT_IN_SAMPLE
+ },
+ &indexscan_recheck,
+ false,
+ NULL, NULL, NULL
+ },
+ {
{"debug_deadlocks", PGC_SUSET, DEVELOPER_OPTIONS,
gettext_noop("Dumps information about all current locks when a deadlock timeout occurs."),
NULL,
diff --git a/src/include/access/amapi.h b/src/include/access/amapi.h
index 1036cca..37eaf76 100644
--- a/src/include/access/amapi.h
+++ b/src/include/access/amapi.h
@@ -13,6 +13,7 @@
#define AMAPI_H
#include "access/genam.h"
+#include "access/itup.h"
/*
* We don't wish to include planner header files here, since most of an index
@@ -137,6 +138,9 @@ typedef void (*ammarkpos_function) (IndexScanDesc scan);
/* restore marked scan position */
typedef void (*amrestrpos_function) (IndexScanDesc scan);
+/* recheck index tuple and heap tuple match */
+typedef bool (*amrecheck_function) (Relation indexRel, IndexTuple indexTuple,
+ Relation heapRel, HeapTuple heapTuple);
/*
* API struct for an index AM. Note this must be stored in a single palloc'd
@@ -196,6 +200,7 @@ typedef struct IndexAmRoutine
amendscan_function amendscan;
ammarkpos_function ammarkpos; /* can be NULL */
amrestrpos_function amrestrpos; /* can be NULL */
+ amrecheck_function amrecheck; /* can be NULL */
} IndexAmRoutine;
diff --git a/src/include/access/hash.h b/src/include/access/hash.h
index 6dfc41f..f1c73a0 100644
--- a/src/include/access/hash.h
+++ b/src/include/access/hash.h
@@ -389,4 +389,8 @@ extern void hashbucketcleanup(Relation rel, Bucket cur_bucket,
bool bucket_has_garbage,
IndexBulkDeleteCallback callback, void *callback_state);
+/* hash.c */
+extern bool hashrecheck(Relation indexRel, IndexTuple indexTuple,
+ Relation heapRel, HeapTuple heapTuple);
+
#endif /* HASH_H */
diff --git a/src/include/access/heapam.h b/src/include/access/heapam.h
index 81f7982..04ffd67 100644
--- a/src/include/access/heapam.h
+++ b/src/include/access/heapam.h
@@ -137,9 +137,10 @@ extern bool heap_fetch(Relation relation, Snapshot snapshot,
Relation stats_relation);
extern bool heap_hot_search_buffer(ItemPointer tid, Relation relation,
Buffer buffer, Snapshot snapshot, HeapTuple heapTuple,
- bool *all_dead, bool first_call);
+ bool *all_dead, bool first_call, bool *recheck);
extern bool heap_hot_search(ItemPointer tid, Relation relation,
- Snapshot snapshot, bool *all_dead);
+ Snapshot snapshot, bool *all_dead,
+ bool *recheck, Buffer *buffer, HeapTuple heapTuple);
extern void heap_get_latest_tid(Relation relation, Snapshot snapshot,
ItemPointer tid);
@@ -160,7 +161,8 @@ extern void heap_abort_speculative(Relation relation, HeapTuple tuple);
extern HTSU_Result heap_update(Relation relation, ItemPointer otid,
HeapTuple newtup,
CommandId cid, Snapshot crosscheck, bool wait,
- HeapUpdateFailureData *hufd, LockTupleMode *lockmode);
+ HeapUpdateFailureData *hufd, LockTupleMode *lockmode,
+ Bitmapset **modified_attrsp, bool *warm_update);
extern HTSU_Result heap_lock_tuple(Relation relation, HeapTuple tuple,
CommandId cid, LockTupleMode mode, LockWaitPolicy wait_policy,
bool follow_update,
@@ -186,6 +188,7 @@ extern int heap_page_prune(Relation relation, Buffer buffer,
bool report_stats, TransactionId *latestRemovedXid);
extern void heap_page_prune_execute(Buffer buffer,
OffsetNumber *redirected, int nredirected,
+ bool *warmchain,
OffsetNumber *nowdead, int ndead,
OffsetNumber *nowunused, int nunused);
extern void heap_get_root_tuple_one(Page page, OffsetNumber target_offnum,
diff --git a/src/include/access/heapam_xlog.h b/src/include/access/heapam_xlog.h
index 5a04561..ddc3a7a 100644
--- a/src/include/access/heapam_xlog.h
+++ b/src/include/access/heapam_xlog.h
@@ -80,6 +80,7 @@
#define XLH_UPDATE_CONTAINS_NEW_TUPLE (1<<4)
#define XLH_UPDATE_PREFIX_FROM_OLD (1<<5)
#define XLH_UPDATE_SUFFIX_FROM_OLD (1<<6)
+#define XLH_UPDATE_WARM_UPDATE (1<<7)
/* convenience macro for checking whether any form of old tuple was logged */
#define XLH_UPDATE_CONTAINS_OLD \
@@ -211,7 +212,9 @@ typedef struct xl_heap_update
* * for each redirected item: the item offset, then the offset redirected to
* * for each now-dead item: the item offset
* * for each now-unused item: the item offset
- * The total number of OffsetNumbers is therefore 2*nredirected+ndead+nunused.
+ * * for each now-warm item: the item offset
+ * The total number of OffsetNumbers is therefore
+ * 2*nredirected+ndead+nunused+nwarm.
* Note that nunused is not explicitly stored, but may be found by reference
* to the total record length.
*/
@@ -220,10 +223,11 @@ typedef struct xl_heap_clean
TransactionId latestRemovedXid;
uint16 nredirected;
uint16 ndead;
+ uint16 nwarm;
/* OFFSET NUMBERS are in the block reference 0 */
} xl_heap_clean;
-#define SizeOfHeapClean (offsetof(xl_heap_clean, ndead) + sizeof(uint16))
+#define SizeOfHeapClean (offsetof(xl_heap_clean, nwarm) + sizeof(uint16))
/*
* Cleanup_info is required in some cases during a lazy VACUUM.
@@ -384,6 +388,7 @@ extern XLogRecPtr log_heap_cleanup_info(RelFileNode rnode,
TransactionId latestRemovedXid);
extern XLogRecPtr log_heap_clean(Relation reln, Buffer buffer,
OffsetNumber *redirected, int nredirected,
+ OffsetNumber *warm, int nwarm,
OffsetNumber *nowdead, int ndead,
OffsetNumber *nowunused, int nunused,
TransactionId latestRemovedXid);
diff --git a/src/include/access/htup_details.h b/src/include/access/htup_details.h
index 4313eb9..09246b2 100644
--- a/src/include/access/htup_details.h
+++ b/src/include/access/htup_details.h
@@ -260,7 +260,8 @@ struct HeapTupleHeaderData
* information stored in t_infomask2:
*/
#define HEAP_NATTS_MASK 0x07FF /* 11 bits for number of attributes */
-/* bits 0x0800 are available */
+#define HEAP_WARM_TUPLE 0x0800 /* This tuple is a part of a WARM chain
+ */
#define HEAP_LATEST_TUPLE 0x1000 /*
* This is the last tuple in chain and
* ip_posid points to the root line
@@ -271,7 +272,7 @@ struct HeapTupleHeaderData
#define HEAP_HOT_UPDATED 0x4000 /* tuple was HOT-updated */
#define HEAP_ONLY_TUPLE 0x8000 /* this is heap-only tuple */
-#define HEAP2_XACT_MASK 0xF000 /* visibility-related bits */
+#define HEAP2_XACT_MASK 0xF800 /* visibility-related bits */
/*
@@ -510,6 +511,21 @@ do { \
(tup)->t_infomask2 & HEAP_ONLY_TUPLE \
)
+#define HeapTupleHeaderSetHeapWarmTuple(tup) \
+do { \
+ (tup)->t_infomask2 |= HEAP_WARM_TUPLE; \
+} while (0)
+
+#define HeapTupleHeaderClearHeapWarmTuple(tup) \
+do { \
+ (tup)->t_infomask2 &= ~HEAP_WARM_TUPLE; \
+} while (0)
+
+#define HeapTupleHeaderIsHeapWarmTuple(tup) \
+( \
+ ((tup)->t_infomask2 & HEAP_WARM_TUPLE) \
+)
+
#define HeapTupleHeaderSetHeapLatest(tup) \
( \
(tup)->t_infomask2 |= HEAP_LATEST_TUPLE \
@@ -771,6 +787,15 @@ struct MinimalTupleData
#define HeapTupleClearHeapOnly(tuple) \
HeapTupleHeaderClearHeapOnly((tuple)->t_data)
+#define HeapTupleIsHeapWarmTuple(tuple) \
+ HeapTupleHeaderIsHeapWarmTuple((tuple)->t_data)
+
+#define HeapTupleSetHeapWarmTuple(tuple) \
+ HeapTupleHeaderSetHeapWarmTuple((tuple)->t_data)
+
+#define HeapTupleClearHeapWarmTuple(tuple) \
+ HeapTupleHeaderClearHeapWarmTuple((tuple)->t_data)
+
#define HeapTupleGetOid(tuple) \
HeapTupleHeaderGetOid((tuple)->t_data)
diff --git a/src/include/access/nbtree.h b/src/include/access/nbtree.h
index c580f51..83af072 100644
--- a/src/include/access/nbtree.h
+++ b/src/include/access/nbtree.h
@@ -751,6 +751,8 @@ extern bytea *btoptions(Datum reloptions, bool validate);
extern bool btproperty(Oid index_oid, int attno,
IndexAMProperty prop, const char *propname,
bool *res, bool *isnull);
+extern bool btrecheck(Relation indexRel, IndexTuple indexTuple,
+ Relation heapRel, HeapTuple heapTuple);
/*
* prototypes for functions in nbtvalidate.c
diff --git a/src/include/access/relscan.h b/src/include/access/relscan.h
index de98dd6..da7ec84 100644
--- a/src/include/access/relscan.h
+++ b/src/include/access/relscan.h
@@ -111,7 +111,8 @@ typedef struct IndexScanDescData
HeapTupleData xs_ctup; /* current heap tuple, if any */
Buffer xs_cbuf; /* current heap buffer in scan, if any */
/* NB: if xs_cbuf is not InvalidBuffer, we hold a pin on that buffer */
- bool xs_recheck; /* T means scan keys must be rechecked */
+ bool xs_recheck; /* T means scan keys must be rechecked for each tuple */
+ bool xs_tuple_recheck; /* T means scan keys must be rechecked for current tuple */
/*
* When fetching with an ordering operator, the values of the ORDER BY
diff --git a/src/include/catalog/pg_proc.h b/src/include/catalog/pg_proc.h
index 047a1ce..31f295f 100644
--- a/src/include/catalog/pg_proc.h
+++ b/src/include/catalog/pg_proc.h
@@ -2734,6 +2734,8 @@ DATA(insert OID = 1933 ( pg_stat_get_tuples_deleted PGNSP PGUID 12 1 0 0 0 f f
DESCR("statistics: number of tuples deleted");
DATA(insert OID = 1972 ( pg_stat_get_tuples_hot_updated PGNSP PGUID 12 1 0 0 0 f f f f t f s r 1 0 20 "26" _null_ _null_ _null_ _null_ _null_ pg_stat_get_tuples_hot_updated _null_ _null_ _null_ ));
DESCR("statistics: number of tuples hot updated");
+DATA(insert OID = 3344 ( pg_stat_get_tuples_warm_updated PGNSP PGUID 12 1 0 0 0 f f f f t f s r 1 0 20 "26" _null_ _null_ _null_ _null_ _null_ pg_stat_get_tuples_warm_updated _null_ _null_ _null_ ));
+DESCR("statistics: number of tuples warm updated");
DATA(insert OID = 2878 ( pg_stat_get_live_tuples PGNSP PGUID 12 1 0 0 0 f f f f t f s r 1 0 20 "26" _null_ _null_ _null_ _null_ _null_ pg_stat_get_live_tuples _null_ _null_ _null_ ));
DESCR("statistics: number of live tuples");
DATA(insert OID = 2879 ( pg_stat_get_dead_tuples PGNSP PGUID 12 1 0 0 0 f f f f t f s r 1 0 20 "26" _null_ _null_ _null_ _null_ _null_ pg_stat_get_dead_tuples _null_ _null_ _null_ ));
@@ -2884,6 +2886,8 @@ DATA(insert OID = 3042 ( pg_stat_get_xact_tuples_deleted PGNSP PGUID 12 1 0 0
DESCR("statistics: number of tuples deleted in current transaction");
DATA(insert OID = 3043 ( pg_stat_get_xact_tuples_hot_updated PGNSP PGUID 12 1 0 0 0 f f f f t f v r 1 0 20 "26" _null_ _null_ _null_ _null_ _null_ pg_stat_get_xact_tuples_hot_updated _null_ _null_ _null_ ));
DESCR("statistics: number of tuples hot updated in current transaction");
+DATA(insert OID = 3343 ( pg_stat_get_xact_tuples_warm_updated PGNSP PGUID 12 1 0 0 0 f f f f t f v r 1 0 20 "26" _null_ _null_ _null_ _null_ _null_ pg_stat_get_xact_tuples_warm_updated _null_ _null_ _null_ ));
+DESCR("statistics: number of tuples warm updated in current transaction");
DATA(insert OID = 3044 ( pg_stat_get_xact_blocks_fetched PGNSP PGUID 12 1 0 0 0 f f f f t f v r 1 0 20 "26" _null_ _null_ _null_ _null_ _null_ pg_stat_get_xact_blocks_fetched _null_ _null_ _null_ ));
DESCR("statistics: number of blocks fetched in current transaction");
DATA(insert OID = 3045 ( pg_stat_get_xact_blocks_hit PGNSP PGUID 12 1 0 0 0 f f f f t f v r 1 0 20 "26" _null_ _null_ _null_ _null_ _null_ pg_stat_get_xact_blocks_hit _null_ _null_ _null_ ));
diff --git a/src/include/executor/executor.h b/src/include/executor/executor.h
index 136276b..e324deb 100644
--- a/src/include/executor/executor.h
+++ b/src/include/executor/executor.h
@@ -366,6 +366,7 @@ extern void UnregisterExprContextCallback(ExprContext *econtext,
extern void ExecOpenIndices(ResultRelInfo *resultRelInfo, bool speculative);
extern void ExecCloseIndices(ResultRelInfo *resultRelInfo);
extern List *ExecInsertIndexTuples(TupleTableSlot *slot, ItemPointer tupleid,
+ ItemPointer root_tid, Bitmapset *modified_attrs,
EState *estate, bool noDupErr, bool *specConflict,
List *arbiterIndexes);
extern bool ExecCheckIndexConstraints(TupleTableSlot *slot, EState *estate,
diff --git a/src/include/executor/nodeIndexscan.h b/src/include/executor/nodeIndexscan.h
index 194fadb..fe9c78e 100644
--- a/src/include/executor/nodeIndexscan.h
+++ b/src/include/executor/nodeIndexscan.h
@@ -38,4 +38,5 @@ extern bool ExecIndexEvalArrayKeys(ExprContext *econtext,
IndexArrayKeyInfo *arrayKeys, int numArrayKeys);
extern bool ExecIndexAdvanceArrayKeys(IndexArrayKeyInfo *arrayKeys, int numArrayKeys);
+extern bool indexscan_recheck;
#endif /* NODEINDEXSCAN_H */
diff --git a/src/include/nodes/execnodes.h b/src/include/nodes/execnodes.h
index 8004d85..3bf4b5f 100644
--- a/src/include/nodes/execnodes.h
+++ b/src/include/nodes/execnodes.h
@@ -61,6 +61,7 @@ typedef struct IndexInfo
NodeTag type;
int ii_NumIndexAttrs;
AttrNumber ii_KeyAttrNumbers[INDEX_MAX_KEYS];
+ Bitmapset *ii_indxattrs; /* bitmap of all columns used in this index */
List *ii_Expressions; /* list of Expr */
List *ii_ExpressionsState; /* list of ExprState */
List *ii_Predicate; /* list of Expr */
diff --git a/src/include/pgstat.h b/src/include/pgstat.h
index 152ff06..e0c8a90 100644
--- a/src/include/pgstat.h
+++ b/src/include/pgstat.h
@@ -105,6 +105,7 @@ typedef struct PgStat_TableCounts
PgStat_Counter t_tuples_updated;
PgStat_Counter t_tuples_deleted;
PgStat_Counter t_tuples_hot_updated;
+ PgStat_Counter t_tuples_warm_updated;
bool t_truncated;
PgStat_Counter t_delta_live_tuples;
@@ -625,6 +626,7 @@ typedef struct PgStat_StatTabEntry
PgStat_Counter tuples_updated;
PgStat_Counter tuples_deleted;
PgStat_Counter tuples_hot_updated;
+ PgStat_Counter tuples_warm_updated;
PgStat_Counter n_live_tuples;
PgStat_Counter n_dead_tuples;
@@ -1176,7 +1178,7 @@ pgstat_report_wait_end(void)
(pgStatBlockWriteTime += (n))
extern void pgstat_count_heap_insert(Relation rel, int n);
-extern void pgstat_count_heap_update(Relation rel, bool hot);
+extern void pgstat_count_heap_update(Relation rel, bool hot, bool warm);
extern void pgstat_count_heap_delete(Relation rel);
extern void pgstat_count_truncate(Relation rel);
extern void pgstat_update_heap_dead_tuples(Relation rel, int delta);
diff --git a/src/include/storage/itemid.h b/src/include/storage/itemid.h
index 509c577..8c9cc99 100644
--- a/src/include/storage/itemid.h
+++ b/src/include/storage/itemid.h
@@ -46,6 +46,12 @@ typedef ItemIdData *ItemId;
typedef uint16 ItemOffset;
typedef uint16 ItemLength;
+/*
+ * Special value used in lp_len to indicate that the chain starting at line
+ * pointer may contain WARM tuples. This must only be interpreted along with
+ * LP_REDIRECT flag
+ */
+#define SpecHeapWarmLen 0x1ffb
/* ----------------
* support macros
@@ -112,12 +118,15 @@ typedef uint16 ItemLength;
#define ItemIdIsDead(itemId) \
((itemId)->lp_flags == LP_DEAD)
+#define ItemIdIsHeapWarm(itemId) \
+ (((itemId)->lp_flags == LP_REDIRECT) && \
+ ((itemId)->lp_len == SpecHeapWarmLen))
/*
* ItemIdHasStorage
* True iff item identifier has associated storage.
*/
#define ItemIdHasStorage(itemId) \
- ((itemId)->lp_len != 0)
+ (!ItemIdIsRedirected(itemId) && (itemId)->lp_len != 0)
/*
* ItemIdSetUnused
@@ -168,6 +177,26 @@ typedef uint16 ItemLength;
)
/*
+ * ItemIdSetHeapWarm
+ * Set the item identifier to identify as starting of a WARM chain
+ *
+ * Note: Since all bits in lp_flags are currently used, we store a special
+ * value in lp_len field to indicate this state. This is required only for
+ * LP_REDIRECT tuple and lp_len field is unused for such line pointers.
+ */
+#define ItemIdSetHeapWarm(itemId) \
+do { \
+ AssertMacro((itemId)->lp_flags == LP_REDIRECT); \
+ (itemId)->lp_len = SpecHeapWarmLen; \
+} while (0)
+
+#define ItemIdClearHeapWarm(itemId) \
+( \
+ AssertMacro((itemId)->lp_flags == LP_REDIRECT); \
+ (itemId)->lp_len = 0; \
+)
+
+/*
* ItemIdMarkDead
* Set the item identifier to be DEAD, keeping its existing storage.
*
diff --git a/src/include/utils/rel.h b/src/include/utils/rel.h
index fa15f28..982bf4c 100644
--- a/src/include/utils/rel.h
+++ b/src/include/utils/rel.h
@@ -101,8 +101,11 @@ typedef struct RelationData
/* data managed by RelationGetIndexAttrBitmap: */
Bitmapset *rd_indexattr; /* identifies columns used in indexes */
+ Bitmapset *rd_exprindexattr; /* indentified columns used in expression or
+ predicate indexes */
Bitmapset *rd_keyattr; /* cols that can be ref'd by foreign keys */
Bitmapset *rd_idattr; /* included in replica identity index */
+ bool rd_supportswarm;/* True if the table can be WARM updated */
/*
* rd_options is set whenever rd_rel is loaded into the relcache entry.
diff --git a/src/include/utils/relcache.h b/src/include/utils/relcache.h
index 6ea7dd2..290e9b7 100644
--- a/src/include/utils/relcache.h
+++ b/src/include/utils/relcache.h
@@ -48,7 +48,8 @@ typedef enum IndexAttrBitmapKind
{
INDEX_ATTR_BITMAP_ALL,
INDEX_ATTR_BITMAP_KEY,
- INDEX_ATTR_BITMAP_IDENTITY_KEY
+ INDEX_ATTR_BITMAP_IDENTITY_KEY,
+ INDEX_ATTR_BITMAP_EXPR_PREDICATE
} IndexAttrBitmapKind;
extern Bitmapset *RelationGetIndexAttrBitmap(Relation relation,
diff --git a/src/test/regress/expected/rules.out b/src/test/regress/expected/rules.out
index 031e8c2..c416fe6 100644
--- a/src/test/regress/expected/rules.out
+++ b/src/test/regress/expected/rules.out
@@ -1705,6 +1705,7 @@ pg_stat_all_tables| SELECT c.oid AS relid,
pg_stat_get_tuples_updated(c.oid) AS n_tup_upd,
pg_stat_get_tuples_deleted(c.oid) AS n_tup_del,
pg_stat_get_tuples_hot_updated(c.oid) AS n_tup_hot_upd,
+ pg_stat_get_tuples_warm_updated(c.oid) AS n_tup_warm_upd,
pg_stat_get_live_tuples(c.oid) AS n_live_tup,
pg_stat_get_dead_tuples(c.oid) AS n_dead_tup,
pg_stat_get_mod_since_analyze(c.oid) AS n_mod_since_analyze,
@@ -1838,6 +1839,7 @@ pg_stat_sys_tables| SELECT pg_stat_all_tables.relid,
pg_stat_all_tables.n_tup_upd,
pg_stat_all_tables.n_tup_del,
pg_stat_all_tables.n_tup_hot_upd,
+ pg_stat_all_tables.n_tup_warm_upd,
pg_stat_all_tables.n_live_tup,
pg_stat_all_tables.n_dead_tup,
pg_stat_all_tables.n_mod_since_analyze,
@@ -1881,6 +1883,7 @@ pg_stat_user_tables| SELECT pg_stat_all_tables.relid,
pg_stat_all_tables.n_tup_upd,
pg_stat_all_tables.n_tup_del,
pg_stat_all_tables.n_tup_hot_upd,
+ pg_stat_all_tables.n_tup_warm_upd,
pg_stat_all_tables.n_live_tup,
pg_stat_all_tables.n_dead_tup,
pg_stat_all_tables.n_mod_since_analyze,
@@ -1918,7 +1921,8 @@ pg_stat_xact_all_tables| SELECT c.oid AS relid,
pg_stat_get_xact_tuples_inserted(c.oid) AS n_tup_ins,
pg_stat_get_xact_tuples_updated(c.oid) AS n_tup_upd,
pg_stat_get_xact_tuples_deleted(c.oid) AS n_tup_del,
- pg_stat_get_xact_tuples_hot_updated(c.oid) AS n_tup_hot_upd
+ pg_stat_get_xact_tuples_hot_updated(c.oid) AS n_tup_hot_upd,
+ pg_stat_get_xact_tuples_warm_updated(c.oid) AS n_tup_warm_upd
FROM ((pg_class c
LEFT JOIN pg_index i ON ((c.oid = i.indrelid)))
LEFT JOIN pg_namespace n ON ((n.oid = c.relnamespace)))
@@ -1934,7 +1938,8 @@ pg_stat_xact_sys_tables| SELECT pg_stat_xact_all_tables.relid,
pg_stat_xact_all_tables.n_tup_ins,
pg_stat_xact_all_tables.n_tup_upd,
pg_stat_xact_all_tables.n_tup_del,
- pg_stat_xact_all_tables.n_tup_hot_upd
+ pg_stat_xact_all_tables.n_tup_hot_upd,
+ pg_stat_xact_all_tables.n_tup_warm_upd
FROM pg_stat_xact_all_tables
WHERE ((pg_stat_xact_all_tables.schemaname = ANY (ARRAY['pg_catalog'::name, 'information_schema'::name])) OR (pg_stat_xact_all_tables.schemaname ~ '^pg_toast'::text));
pg_stat_xact_user_functions| SELECT p.oid AS funcid,
@@ -1956,7 +1961,8 @@ pg_stat_xact_user_tables| SELECT pg_stat_xact_all_tables.relid,
pg_stat_xact_all_tables.n_tup_ins,
pg_stat_xact_all_tables.n_tup_upd,
pg_stat_xact_all_tables.n_tup_del,
- pg_stat_xact_all_tables.n_tup_hot_upd
+ pg_stat_xact_all_tables.n_tup_hot_upd,
+ pg_stat_xact_all_tables.n_tup_warm_upd
FROM pg_stat_xact_all_tables
WHERE ((pg_stat_xact_all_tables.schemaname <> ALL (ARRAY['pg_catalog'::name, 'information_schema'::name])) AND (pg_stat_xact_all_tables.schemaname !~ '^pg_toast'::text));
pg_statio_all_indexes| SELECT c.oid AS relid,
diff --git a/src/test/regress/expected/warm.out b/src/test/regress/expected/warm.out
new file mode 100644
index 0000000..0aa1b83
--- /dev/null
+++ b/src/test/regress/expected/warm.out
@@ -0,0 +1,51 @@
+CREATE TABLE test_warm (a text unique, b text);
+CREATE INDEX test_warmindx ON test_warm (lower(a));
+INSERT INTO test_warm values ('test', 'foo');
+UPDATE test_warm SET a = 'TEST';
+select *, ctid from test_warm where lower(a) = 'test';
+ a | b | ctid
+------+-----+-------
+ TEST | foo | (0,2)
+(1 row)
+
+explain select * from test_warm where lower(a) = 'test';
+ QUERY PLAN
+----------------------------------------------------------------------------
+ Bitmap Heap Scan on test_warm (cost=4.18..12.65 rows=4 width=64)
+ Recheck Cond: (lower(a) = 'test'::text)
+ -> Bitmap Index Scan on test_warmindx (cost=0.00..4.18 rows=4 width=0)
+ Index Cond: (lower(a) = 'test'::text)
+(4 rows)
+
+select *, ctid from test_warm where lower(a) = 'test';
+ a | b | ctid
+------+-----+-------
+ TEST | foo | (0,2)
+(1 row)
+
+select *, ctid from test_warm where a = 'test';
+ a | b | ctid
+---+---+------
+(0 rows)
+
+select *, ctid from test_warm where a = 'TEST';
+ a | b | ctid
+------+-----+-------
+ TEST | foo | (0,2)
+(1 row)
+
+set enable_bitmapscan TO false;
+explain select * from test_warm where lower(a) = 'test';
+ QUERY PLAN
+---------------------------------------------------------------------------------
+ Index Scan using test_warmindx on test_warm (cost=0.15..20.22 rows=4 width=64)
+ Index Cond: (lower(a) = 'test'::text)
+(2 rows)
+
+select *, ctid from test_warm where lower(a) = 'test';
+ a | b | ctid
+------+-----+-------
+ TEST | foo | (0,2)
+(1 row)
+
+DROP TABLE test_warm;
diff --git a/src/test/regress/parallel_schedule b/src/test/regress/parallel_schedule
index 8641769..a610039 100644
--- a/src/test/regress/parallel_schedule
+++ b/src/test/regress/parallel_schedule
@@ -42,6 +42,8 @@ test: create_type
test: create_table
test: create_function_2
+test: warm
+
# ----------
# Load huge amounts of data
# We should split the data files into single files and then
diff --git a/src/test/regress/sql/warm.sql b/src/test/regress/sql/warm.sql
new file mode 100644
index 0000000..166ea37
--- /dev/null
+++ b/src/test/regress/sql/warm.sql
@@ -0,0 +1,15 @@
+CREATE TABLE test_warm (a text unique, b text);
+CREATE INDEX test_warmindx ON test_warm (lower(a));
+INSERT INTO test_warm values ('test', 'foo');
+UPDATE test_warm SET a = 'TEST';
+select *, ctid from test_warm where lower(a) = 'test';
+explain select * from test_warm where lower(a) = 'test';
+select *, ctid from test_warm where lower(a) = 'test';
+select *, ctid from test_warm where a = 'test';
+select *, ctid from test_warm where a = 'TEST';
+set enable_bitmapscan TO false;
+explain select * from test_warm where lower(a) = 'test';
+select *, ctid from test_warm where lower(a) = 'test';
+DROP TABLE test_warm;
+
+