This is an automated email from the ASF dual-hosted git repository.
jianliangqi pushed a commit to branch master
in repository https://gitbox.apache.org/repos/asf/doris.git
The following commit(s) were added to refs/heads/master by this push:
new 28f7ed3193f [Fix](inverted index) fix wrong opt for pk no need read
data (#36618)
28f7ed3193f is described below
commit 28f7ed3193fe1d25c29ca2e2940398cc8c656df0
Author: airborne12 <[email protected]>
AuthorDate: Fri Jun 21 15:16:01 2024 +0800
[Fix](inverted index) fix wrong opt for pk no need read data (#36618)
The optimization to avoid reading data for primary keys (PK) in
segment_iterator can lead to incorrect results when there are function
expressions involving the same PK column in the predicate.
---
be/src/olap/rowset/segment_v2/segment_iterator.cpp | 3 +
.../test_pk_no_need_read_data.out | 13 +++++
.../test_pk_no_need_read_data.groovy | 66 ++++++++++++++++++++++
3 files changed, 82 insertions(+)
diff --git a/be/src/olap/rowset/segment_v2/segment_iterator.cpp
b/be/src/olap/rowset/segment_v2/segment_iterator.cpp
index f0c3f8f4920..2eee1e7e620 100644
--- a/be/src/olap/rowset/segment_v2/segment_iterator.cpp
+++ b/be/src/olap/rowset/segment_v2/segment_iterator.cpp
@@ -2851,6 +2851,9 @@ bool SegmentIterator::_no_need_read_key_data(ColumnId
cid, vectorized::MutableCo
if (cids.contains(cid)) {
return false;
}
+ if
(_column_pred_in_remaining_vconjunct.contains(_opts.tablet_schema->column(cid).name()))
{
+ return false;
+ }
if (column->is_nullable()) {
auto* nullable_col_ptr =
reinterpret_cast<vectorized::ColumnNullable*>(column.get());
diff --git
a/regression-test/data/inverted_index_p0/test_pk_no_need_read_data.out
b/regression-test/data/inverted_index_p0/test_pk_no_need_read_data.out
new file mode 100644
index 00000000000..b38181b1845
--- /dev/null
+++ b/regression-test/data/inverted_index_p0/test_pk_no_need_read_data.out
@@ -0,0 +1,13 @@
+-- This file is automatically generated. You should know what you did if you
want to edit this
+-- !select_0 --
+1
+
+-- !select_1 --
+1
+
+-- !select_2 --
+1
+
+-- !select_3 --
+1
+
diff --git
a/regression-test/suites/inverted_index_p0/test_pk_no_need_read_data.groovy
b/regression-test/suites/inverted_index_p0/test_pk_no_need_read_data.groovy
new file mode 100644
index 00000000000..4aa969debda
--- /dev/null
+++ b/regression-test/suites/inverted_index_p0/test_pk_no_need_read_data.groovy
@@ -0,0 +1,66 @@
+// Licensed to the Apache Software Foundation (ASF) under one
+// or more contributor license agreements. See the NOTICE file
+// distributed with this work for additional information
+// regarding copyright ownership. The ASF licenses this file
+// to you 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, WITHOUT WARRANTIES OR CONDITIONS OF ANY
+// KIND, either express or implied. See the License for the
+// specific language governing permissions and limitations
+// under the License.
+suite("test_pk_no_need_read_data", "p0"){
+ def table1 = "test_pk_no_need_read_data"
+
+ sql "drop table if exists ${table1}"
+
+ sql """
+ CREATE TABLE IF NOT EXISTS `${table1}` (
+ `date` date NULL COMMENT "",
+ `city` varchar(20) NULL COMMENT "",
+ `addr` varchar(20) NULL COMMENT "",
+ `name` varchar(20) NULL COMMENT "",
+ `compy` varchar(20) NULL COMMENT "",
+ `n` int NULL COMMENT "",
+ INDEX idx_city(city) USING INVERTED,
+ INDEX idx_addr(addr) USING INVERTED PROPERTIES("parser"="english"),
+ INDEX idx_n(n) USING INVERTED
+ ) ENGINE=OLAP
+ DUPLICATE KEY(`date`)
+ COMMENT "OLAP"
+ DISTRIBUTED BY HASH(`date`) BUCKETS 1
+ PROPERTIES (
+ "replication_allocation" = "tag.location.default: 1",
+ "in_memory" = "false",
+ "storage_format" = "V2"
+ )
+ """
+
+ sql """insert into ${table1} values
+ ('2017-10-01',null,'addr qie3','yy','lj',100),
+ ('2018-10-01',null,'hehe',null,'lala',200),
+ ('2019-10-01','beijing','addr xuanwu','wugui',null,300),
+ ('2020-10-01','beijing','addr fengtai','fengtai1','fengtai2',null),
+ ('2021-10-01','beijing','addr chaoyang','wangjing','donghuqu',500),
+ ('2022-10-01','shanghai','hehe',null,'haha',null),
+ ('2023-10-01','tengxun','qie','addr gg','lj',null),
+ ('2024-10-01','tengxun2','qie',null,'lj',800)
+ """
+
+ // case1: enable count on index
+ sql "set enable_count_on_index_pushdown = true"
+
+ qt_select_0 "SELECT COUNT() FROM ${table1} WHERE date='2017-10-01'"
+ qt_select_1 "SELECT COUNT() FROM ${table1} WHERE year(date)='2017'"
+
+ // case1: disable count on index
+ sql "set enable_count_on_index_pushdown = false"
+
+ qt_select_2 "SELECT COUNT() FROM ${table1} WHERE date='2017-10-01'"
+ qt_select_3 "SELECT COUNT() FROM ${table1} WHERE year(date)='2017'"
+}
\ No newline at end of file
---------------------------------------------------------------------
To unsubscribe, e-mail: [email protected]
For additional commands, e-mail: [email protected]
