Merge #42250 #42999

42250: storage/engine: introduce a datadriven framework to run MVCC tests r=itsbilal,petermattis a=knz

Previously MVCC tests were hand-coded in Go.
This was making it hard(er) to introduce new tests or modify existing
tests.

This commit improves upon this situation by introducing a new
datadriven test, `TestMVCCHistories`, which runs MVCC
tests written using a DSL:

```
begin_txn      t=<name> [ts=<int>[,<int>]]
remove_txn     t=<name>
resolve_intent t=<name> k=<key> [status=<txnstatus>]
restart_txn    t=<name>
update_txn     t=<name> t2=<name>
step_txn       t=<name> [n=<int>]
advance_txn    t=<name> ts=<int>[,<int>]
txn_status     t=<name> status=<txnstatus>

check_intent   k=<key> [none]

put       [t=<name>] [ts=<int>[,<int>]] [resolve] k=<key> v=<string> [raw]
cput      [t=<name>] [ts=<int>[,<int>]] [resolve] k=<key> v=<string> [raw] [cond=<string>]
increment [t=<name>] [ts=<int>[,<int>]] [resolve] k=<key> [inc=<val>]
del       [t=<name>] [ts=<int>[,<int>]] [resolve] k=<key>
get       [t=<name>] [ts=<int>[,<int>]] [resolve] k=<key> [inconsistent] [tombstones]
scan      [t=<name>] [ts=<int>[,<int>]] [resolve] k=<key> [end=<key>] [inconsistent] [tombstones] [reverse]

merge     [ts=<int>[,<int>]] k=<key> v=<string> [raw]

clear_range    k=<key> end=<key>
```

Where `<key>` can be a simple string, or a string
prefixed by the following characters:

- `=foo` means exactly key `foo`
- `+foo` means `Key(foo).Next()`
- `-foo` means `Key(foo).PrefixEnd()`

Additionally, the pseudo-command `with` enables sharing
a group of arguments between multiple commands, for example:

```
with t=A
   begin_txn
   with k=a
     put v=b
     resolve_intent
```

Release note: None

42999: colexec: cfetcher errors on setup when indexed column contains unhandled type r=yuzefovich a=rohany

Fixes #42994.

Indexed columns are always decoded by the fetcher, even if they are unneeded.
This PR adds the check to cfetcher initialization to error out if an indexed
column is of an unneeded type.

Release note (bug fix): Fixed a bug where scanning an index of an unsupported
type with the vectorized engine would lead to an internal error.

Co-authored-by: Raphael 'kena' Poss <[email protected]>
Co-authored-by: Rohan Yadav <[email protected]>

pkg/sql/colexec/cfetcher.go

@@ -265,15 +265,6 @@ func (rf *cFetcher) Init(
 	}
 	sort.Sort(m)
 	colDescriptors := tableArgs.Cols
-	typs := make([]coltypes.T, len(colDescriptors))
-	for i := range typs {
-		typs[i] = typeconv.FromColumnType(&colDescriptors[i].Type)
-		if typs[i] == coltypes.Unhandled && tableArgs.ValNeededForCol.Contains(i) {
-			// Only return an error if the type is unhandled and needed. If not needed,
-			// a placeholder Vec will be created.
-			return errors.Errorf("unhandled type %+v", &colDescriptors[i].Type)
-		}
-	}
 	table := cTableInfo{
 		spans:            tableArgs.Spans,
 		desc:             tableArgs.Desc,
@@ -288,6 +279,29 @@ func (rf *cFetcher) Init(
 		extraValColOrdinals:    oldTable.extraValColOrdinals[:0],
 		allExtraValColOrdinals: oldTable.allExtraValColOrdinals[:0],
 	}
+
+	// All columns that are part of the index key will be decoded when reading a key. Since some types
+	// are not supported by the vectorized engine, we should error out during setup if some needed columns
+	// or columns we decode always will be attempted to be decoded.
+	typs := make([]coltypes.T, len(colDescriptors))
+	var indexedCols util.FastIntSet
+	for _, colID := range tableArgs.Index.ColumnIDs {
+		indexedCols.Add(int(colID))
+	}
+	if cHasExtraCols(&table) {
+		for _, colID := range tableArgs.Index.ExtraColumnIDs {
+			indexedCols.Add(int(colID))
+		}
+	}
+	for i := range typs {
+		typs[i] = typeconv.FromColumnType(&colDescriptors[i].Type)
+		if typs[i] == coltypes.Unhandled && (tableArgs.ValNeededForCol.Contains(i) || indexedCols.Contains(int(colDescriptors[i].ID))) {
+			// Only return an error if the type is unhandled and needed. If not needed,
+			// a placeholder Vec will be created.
+			return errors.Errorf("unhandled type %+v", &colDescriptors[i].Type)
+		}
+	}
+
 	rf.machine.batch = allocator.NewMemBatch(typs)
 	rf.machine.colvecs = rf.machine.batch.ColVecs()
 

pkg/sql/logictest/testdata/logic_test/vectorize

@@ -1006,3 +1006,13 @@ SELECT * FROM t_42816 ORDER BY a OFFSET 1020 LIMIT 10
 1023
 1024
 1025
+
+# Regression test for #42994
+statement ok
+CREATE TABLE t42994 (a int primary key, b bit, index i (a, b));
+INSERT INTO t42994 VALUES (1, 1::BIT);
+
+query I
+SELECT a FROM t42994@i
+----
+1