plan: fix a bug when using correlated column as index #7357
There are no files selected for viewing
This file contains bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
This file contains bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
This file contains bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
This file contains bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
| Original file line number | Diff line number | Diff line change |
|---|---|---|
|
|
@@ -484,14 +484,15 @@ func (path *accessPath) splitCorColAccessCondFromFilters() (access, remained []e | |
| for i := path.eqCondCount; i < len(path.idxCols); i++ { | ||
| matched := false | ||
| for j, filter := range path.tableFilters { | ||
| if used[j] || !isColEqCorColOrConstant(filter, path.idxCols[i]) { | ||
|
There was a problem hiding this comment. It's better to add a UT for function There was a problem hiding this comment. I think this function is not big enough and not special enough to add test that tests this method seperately. There was a problem hiding this comment. If we have UT for this function, even without the integration test you added in this PR, we can avoid this bug in the very beginning. You can see the advantage of unit test through Wikipedia: https://en.wikipedia.org/wiki/Unit_testing#Advantages |
||
| continue | ||
| } | ||
| matched = true | ||
| access[i-path.eqCondCount] = filter | ||
| if path.idxColLens[i] == types.UnspecifiedLength { | ||
| used[j] = true | ||
| } | ||
| break | ||
| } | ||
| if !matched { | ||
| access = access[:i-path.eqCondCount] | ||
|
|
||
This file contains bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
| Original file line number | Diff line number | Diff line change |
|---|---|---|
| @@ -0,0 +1,197 @@ | ||
| // Copyright 2016 PingCAP, Inc. | ||
|
|
||
| // | ||
| // Licensed under the Apache License, Version 2.0 (the "License"); | ||
| // you may not use this file except in compliance with the License. | ||
| // You may obtain a copy of the License at | ||
| // | ||
| // http://www.apache.org/licenses/LICENSE-2.0 | ||
| // | ||
| // Unless required by applicable law or agreed to in writing, software | ||
| // distributed under the License is distributed on an "AS IS" BASIS, | ||
| // See the License for the specific language governing permissions and | ||
| // limitations under the License. | ||
|
|
||
| package plan | ||
|
|
||
| import ( | ||
| "fmt" | ||
|
|
||
| "github.com/juju/errors" | ||
| . "github.com/pingcap/check" | ||
| "github.com/pingcap/tidb/ast" | ||
| "github.com/pingcap/tidb/expression" | ||
| "github.com/pingcap/tidb/model" | ||
| "github.com/pingcap/tidb/mysql" | ||
| "github.com/pingcap/tidb/sessionctx" | ||
| "github.com/pingcap/tidb/types" | ||
| "github.com/pingcap/tidb/util/testleak" | ||
| ) | ||
|
|
||
| var _ = Suite(&testUnitTestSuit{}) | ||
|
|
||
| type testUnitTestSuit struct { | ||
| ctx sessionctx.Context | ||
| } | ||
|
|
||
| func (s *testUnitTestSuit) SetUpSuite(c *C) { | ||
| s.ctx = mockContext() | ||
| } | ||
|
|
||
| func (s *testUnitTestSuit) newTypeWithFlen(typeByte byte, flen int) *types.FieldType { | ||
| tp := types.NewFieldType(typeByte) | ||
| tp.Flen = flen | ||
| return tp | ||
| } | ||
|
|
||
| func (s *testUnitTestSuit) SubstituteCol2CorCol(expr expression.Expression, colIDs map[int]struct{}) (expression.Expression, error) { | ||
|
There was a problem hiding this comment. We do no need to return error? |
||
| switch x := expr.(type) { | ||
| case *expression.ScalarFunction: | ||
| newArgs := make([]expression.Expression, 0, len(x.GetArgs())) | ||
| for _, arg := range x.GetArgs() { | ||
| newArg, err := s.SubstituteCol2CorCol(arg, colIDs) | ||
| if err != nil { | ||
| return nil, errors.Trace(err) | ||
| } | ||
| newArgs = append(newArgs, newArg) | ||
| } | ||
| newSf := expression.NewFunctionInternal(x.GetCtx(), x.FuncName.L, x.GetType(), newArgs...) | ||
| return newSf, nil | ||
| case *expression.Column: | ||
| if _, ok := colIDs[x.UniqueID]; ok { | ||
| return &expression.CorrelatedColumn{Column: *x}, nil | ||
| } | ||
| default: | ||
|
There was a problem hiding this comment. redundant default？ line#66 is enough. |
||
| return x, nil | ||
| } | ||
| return expr, nil | ||
| } | ||
|
|
||
| func (s *testUnitTestSuit) TestIndexPathSplitCorColCond(c *C) { | ||
| defer testleak.AfterTest(c)() | ||
| totalSchema := expression.NewSchema() | ||
| totalSchema.Append(&expression.Column{ | ||
| ColName: model.NewCIStr("a"), | ||
|
There was a problem hiding this comment. I think a better way is to: s/a/col1/
s/b/col2/
s/c/col3/
s/d/col4/
s/e/col5/It helps us understanding the test case. |
||
| UniqueID: 1, | ||
| RetType: types.NewFieldType(mysql.TypeLonglong), | ||
| }) | ||
| totalSchema.Append(&expression.Column{ | ||
| ColName: model.NewCIStr("b"), | ||
| UniqueID: 2, | ||
| RetType: types.NewFieldType(mysql.TypeLonglong), | ||
| }) | ||
| totalSchema.Append(&expression.Column{ | ||
| ColName: model.NewCIStr("c"), | ||
| UniqueID: 3, | ||
| RetType: s.newTypeWithFlen(mysql.TypeVarchar, 10), | ||
| }) | ||
| totalSchema.Append(&expression.Column{ | ||
| ColName: model.NewCIStr("d"), | ||
| UniqueID: 4, | ||
| RetType: s.newTypeWithFlen(mysql.TypeVarchar, 10), | ||
| }) | ||
| totalSchema.Append(&expression.Column{ | ||
| ColName: model.NewCIStr("e"), | ||
| UniqueID: 5, | ||
| RetType: types.NewFieldType(mysql.TypeLonglong), | ||
| }) | ||
| testCases := []struct { | ||
| expr string | ||
| corColIDs []int | ||
| idxColIDs []int | ||
| idxColLens []int | ||
| access string | ||
| remained string | ||
| }{ | ||
| { | ||
| expr: "a = b", | ||
| corColIDs: []int{2}, | ||
| idxColIDs: []int{1}, | ||
| idxColLens: []int{types.UnspecifiedLength}, | ||
| access: "[eq(a, b)]", | ||
| remained: "[]", | ||
| }, | ||
| { | ||
| expr: "a = e and b = 1", | ||
| corColIDs: []int{5}, | ||
| idxColIDs: []int{1, 2}, | ||
| idxColLens: []int{types.UnspecifiedLength, types.UnspecifiedLength}, | ||
| access: "[eq(a, e) eq(b, 1)]", | ||
| remained: "[]", | ||
| }, | ||
| { | ||
| expr: "a = e and b = 1", | ||
| corColIDs: []int{5}, | ||
| idxColIDs: []int{2, 1}, | ||
| idxColLens: []int{types.UnspecifiedLength, types.UnspecifiedLength}, | ||
| access: "[eq(b, 1) eq(a, e)]", | ||
| remained: "[]", | ||
| }, | ||
| { | ||
| expr: "a = e and b = 1", | ||
| corColIDs: []int{5}, | ||
| idxColIDs: []int{1}, | ||
| idxColLens: []int{types.UnspecifiedLength}, | ||
| access: "[eq(a, e)]", | ||
| remained: "[eq(b, 1)]", | ||
| }, | ||
| { | ||
| expr: "b = 1 and a = e", | ||
| corColIDs: []int{5}, | ||
| idxColIDs: []int{1}, | ||
| idxColLens: []int{types.UnspecifiedLength}, | ||
| access: "[eq(a, e)]", | ||
| remained: "[eq(b, 1)]", | ||
| }, | ||
| { | ||
| expr: "a = b and c = d and e = 1", | ||
| corColIDs: []int{2, 4}, | ||
| idxColIDs: []int{1, 3}, | ||
| idxColLens: []int{types.UnspecifiedLength, types.UnspecifiedLength}, | ||
| access: "[eq(a, b) eq(c, d)]", | ||
| remained: "[eq(e, 1)]", | ||
| }, | ||
| { | ||
| expr: "a = b and c = d and e = 1", | ||
| corColIDs: []int{2, 4}, | ||
| idxColIDs: []int{1, 3}, | ||
| idxColLens: []int{types.UnspecifiedLength, 2}, | ||
| access: "[eq(a, b) eq(c, d)]", | ||
| remained: "[eq(c, d) eq(e, 1)]", | ||
| }, | ||
| { | ||
| expr: `a = e and c = "a" and b = e`, | ||
| corColIDs: []int{5}, | ||
| idxColIDs: []int{1, 2, 3}, | ||
| idxColLens: []int{types.UnspecifiedLength, types.UnspecifiedLength, types.UnspecifiedLength}, | ||
| access: "[eq(a, e) eq(b, e) eq(c, a)]", | ||
| remained: "[]", | ||
| }, | ||
| } | ||
| for _, tt := range testCases { | ||
| comment := Commentf("failed at case:\nexpr: %v\ncorColIDs: %v\nidxColIDs: %v\nidxColLens: %v\naccess: %v\nremained: %v\n", tt.expr, tt.corColIDs, tt.idxColIDs, tt.idxColLens, tt.access, tt.remained) | ||
| filters, err := expression.ParseSimpleExprsWithSchema(s.ctx, tt.expr, totalSchema) | ||
| if sf, ok := filters[0].(*expression.ScalarFunction); ok && sf.FuncName.L == ast.LogicAnd { | ||
| filters = expression.FlattenCNFConditions(sf) | ||
| } | ||
| c.Assert(err, IsNil, comment) | ||
| trueFilters := make([]expression.Expression, 0, len(filters)) | ||
| idMap := make(map[int]struct{}) | ||
| for _, id := range tt.corColIDs { | ||
| idMap[id] = struct{}{} | ||
| } | ||
| for _, filter := range filters { | ||
| trueFilter, err := s.SubstituteCol2CorCol(filter, idMap) | ||
| c.Assert(err, IsNil, comment) | ||
| trueFilters = append(trueFilters, trueFilter) | ||
| } | ||
| path := accessPath{ | ||
| eqCondCount: 0, | ||
| tableFilters: trueFilters, | ||
| idxCols: expression.FindColumnsByUniqueIDs(totalSchema.Columns, tt.idxColIDs), | ||
| idxColLens: tt.idxColLens, | ||
| } | ||
| access, remained := path.splitCorColAccessCondFromFilters() | ||
| c.Assert(fmt.Sprintf("%s", access), Equals, tt.access, comment) | ||
| c.Assert(fmt.Sprintf("%s", remained), Equals, tt.remained, comment) | ||
| } | ||
| } | ||
Add this suggestion to a batch that can be applied as a single commit.
This suggestion is invalid because no changes were made to the code.
Suggestions cannot be applied while the pull request is closed.
Suggestions cannot be applied while viewing a subset of changes.
Only one suggestion per line can be applied in a batch.
Add this suggestion to a batch that can be applied as a single commit.
Applying suggestions on deleted lines is not supported.
You must change the existing code in this line in order to create a valid suggestion.
Outdated suggestions cannot be applied.
This suggestion has been applied or marked resolved.
Suggestions cannot be applied from pending reviews.
Suggestions cannot be applied on multi-line comments.
Suggestions cannot be applied while the pull request is queued to merge.
Suggestion cannot be applied right now. Please check back later.
There was a problem hiding this comment.
Choose a reason for hiding this comment
The reason will be displayed to describe this comment to others. Learn more.
This check can be removed. we can make this function to find all the columns in the unique id list.
There was a problem hiding this comment.
Choose a reason for hiding this comment
The reason will be displayed to describe this comment to others. Learn more.
But we still need this check. In such case, we need to return nil or a full slice?
There was a problem hiding this comment.
Choose a reason for hiding this comment
The reason will be displayed to describe this comment to others. Learn more.
The function caller can check whether there is any column can not be found in
colsby:There was a problem hiding this comment.
Choose a reason for hiding this comment
The reason will be displayed to describe this comment to others. Learn more.
Another consideration is, this function is only used in the test currently, all the column identified by
idscan be found incols. We can extend this function in the future when we meet more complicated scenarios. For now, I think we'd better to keep it simple.