[GLUTEN-7905][CH] Implete window's topk by aggregation
#7976
Conversation
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
|
Run Gluten Clickhouse CI on x86 |
|
Run Gluten Clickhouse CI on x86 |
|
Run Gluten Clickhouse CI on x86 |
|
Run Gluten Clickhouse CI on x86 |
|
A benchmark on following queries low cardinality partition keysinsert overwrite table dump_line
select l_orderkey, l_partkey, l_suppkey, l_linenumber from (
select l_orderkey, l_partkey, l_suppkey, l_linenumber, row_number() over (partition by l_suppkey order by l_orderkey, l_partkey) as r from tpch_pq.lineitem
) where r = 1;
high cardinality partition keys
0: jdbc:hive2://localhost:10000> insert overwrite table dump_line select l_orderkey, l_partkey, l_suppkey, l_linenumber from (select l_orderkey, l_partkey, l_suppkey, l_linenumber, row_number() over (partition by l_suppkey, l_orderkey order by l_partkey) as r from tpch_pq.lineitem) where r = 1;
+---------+
| Result |
+---------+
+---------+
No rows selected (41.441 seconds)
0: jdbc:hive2://localhost:10000> insert overwrite table dump_line select l_orderkey, l_partkey, l_suppkey, l_linenumber from (select l_orderkey, l_partkey, l_suppkey, l_linenumber, row_number() over (partition by l_suppkey, l_orderkey order by l_partkey) as r from tpch_pq.lineitem) where r = 1;
+---------+
| Result |
+---------+
+---------+
No rows selected (50.714 seconds)
|
|
Run Gluten Clickhouse CI on x86 |
|
Run Gluten Clickhouse CI on x86 |
|
Run Gluten Clickhouse CI on x86 |
|
Run Gluten Clickhouse CI on x86 |
|
Run Gluten Clickhouse CI on x86 |
|
Run Gluten Clickhouse CI on x86 |
|
Run Gluten Clickhouse CI on x86 |
|
Run Gluten Clickhouse CI on x86 |
|
Run Gluten Clickhouse CI on x86 |
|
For high cardinality partition keys, fallback to window. We have following result
0: jdbc:hive2://localhost:10000> insert overwrite table dump_line select l_orderkey, l_partkey, l_suppkey, l_linenumber from (select l_orderkey, l_partkey, l_suppkey, l_linenumber, row_number() over (partition by l_suppkey, l_orderkey order by l_partkey) as r from tpch_pq.lineitem) where r = 1;
+---------+
| Result |
+---------+
+---------+
No rows selected (26.549 seconds)
0: jdbc:hive2://localhost:10000> insert overwrite table dump_line select l_orderkey, l_partkey, l_suppkey, l_linenumber from (select l_orderkey, l_partkey, l_suppkey, l_linenumber, row_number() over (partition by l_suppkey, l_orderkey order by l_partkey) as r from tpch_pq.lineitem) where r = 1;
+---------+
| Result |
+---------+
+---------+
No rows selected (25.58 seconds)
|
|
Run Gluten Clickhouse CI on x86 |
|
Run Gluten Clickhouse CI on x86 |
|
Run Gluten Clickhouse CI on x86 |
|
Run Gluten Clickhouse CI on x86 |
|
Run Gluten Clickhouse CI on x86 |
|
Run Gluten Clickhouse CI on x86 |
|
Run Gluten Clickhouse CI on x86 |
liuneng1994
approved these changes
Nov 28, 2024
| * See the License for the specific language governing permissions and | ||
| * limitations under the License. | ||
| */ | ||
| #include <new> |
There was a problem hiding this comment.
it's auto included by vs. So annoying
|
|
||
| #include <Poco/Logger.h> | ||
| #include <Common/logger_useful.h> | ||
| #include "base/defines.h" |
| #include <Processors/IProcessor.h> | ||
| #include <Processors/QueryPlan/IQueryPlanStep.h> | ||
| #include <Processors/QueryPlan/ITransformingStep.h> | ||
| #include "Processors/Port.h" |
| #include <Processors/QueryPlan/QueryPlan.h> | ||
| #include <Poco/Logger.h> | ||
| #include <Common/logger_useful.h> | ||
| #include "Analyzer/IQueryTreeNode.h" |
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to 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.
What changes were proposed in this pull request?
(Please fill in changes proposed in this fix)
Fixes: #7905
This PR will use aggregation to calculate window's topk automatically when the partition keys are low cardinality ones.
How was this patch tested?
(Please explain how this patch was tested. E.g. unit tests, integration tests, manual tests)
unit tests
(If this patch involves UI changes, please attach a screenshot; otherwise, remove this)