Skip to content
New issue

Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.

Sign up for GitHub

By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.

Already on GitHub? Sign in to your account

feat(optimizer): add kafka scan operator #16371

Merged
merged 5 commits into from
Apr 18, 2024
Merged

feat(optimizer): add kafka scan operator #16371

Show file tree
Hide file tree
Changes from all commits
Commits
Show all changes
5 commits
Select commit Hold shift + click to select a range
2df6169
add kafka scan
chenzl25 Apr 17, 2024
bd7c13c
Merge branch 'main' into dylan/add_kafka_scan
chenzl25 Apr 18, 2024
50d745c
fix
chenzl25 Apr 18, 2024
eb1da54
add asserts
chenzl25 Apr 18, 2024
3bf076a
refine tedt
chenzl25 Apr 18, 2024
File filter

Filter by extension

Filter by extension
Conversations
Failed to load comments.
Loading
Jump to
Jump to file
Failed to load files.
Loading
Diff view
Diff view
6 changes: 3 additions & 3 deletions e2e_test/streaming/aggregate/count_star.slt
View file
Open in desktop
Original file line number Diff line number Diff line change
@@ -1,3 +1,6 @@
statement ok
SET RW_IMPLICIT_FLUSH TO true;

statement ok
create table t (v int);

Expand All @@ -7,9 +10,6 @@ insert into t values (114), (514);
statement ok
create materialized view mv as select * from t;

statement ok
flush;

query I
select count(*) from t;
----
Expand Down
4 changes: 2 additions & 2 deletions src/frontend/planner_test/tests/testdata/output/batch_source.yaml
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -3,11 +3,11 @@
select * from s
logical_plan: |-
LogicalProject { exprs: [id, value] }
└─LogicalSource { source: s, columns: [id, value, _rw_kafka_timestamp, _row_id], time_range: (Unbounded, Unbounded) }
└─LogicalSource { source: s, columns: [id, value, _rw_kafka_timestamp, _row_id] }
batch_plan: |-
BatchExchange { order: [], dist: Single }
└─BatchProject { exprs: [id, value] }
└─BatchSource { source: s, columns: [id, value, _rw_kafka_timestamp, _row_id], filter: (None, None) }
└─BatchKafkaScan { source: s, columns: [id, value, _rw_kafka_timestamp, _row_id], filter: (None, None) }
create_source:
format: plain
encode: protobuf
Expand Down
2 changes: 1 addition & 1 deletion src/frontend/planner_test/tests/testdata/output/generated_columns.yaml
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -17,7 +17,7 @@
batch_plan: |-
BatchExchange { order: [], dist: Single }
└─BatchProject { exprs: [(v2 + 1:Int32) as $expr1] }
└─BatchSource { source: s1, columns: [v2, _row_id], filter: (None, None) }
└─BatchSource { source: s1, columns: [v2, _row_id] }
- name: select proctime()
sql: |
select proctime();
Expand Down
98 changes: 49 additions & 49 deletions src/frontend/planner_test/tests/testdata/output/nexmark_source.yaml
View file
Open in desktop

Large diffs are not rendered by default.

98 changes: 49 additions & 49 deletions src/frontend/planner_test/tests/testdata/output/nexmark_watermark.yaml
View file
Open in desktop

Large diffs are not rendered by default.

16 changes: 8 additions & 8 deletions src/frontend/planner_test/tests/testdata/output/share.yaml
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -27,10 +27,10 @@
└─BatchHashJoin { type: Inner, predicate: id = id, output: [] }
├─BatchExchange { order: [], dist: HashShard(id) }
│ └─BatchFilter { predicate: (initial_bid = 1:Int32) }
│ └─BatchSource { source: auction, columns: [id, item_name, description, initial_bid, reserve, date_time, expires, seller, category, extra, _row_id], filter: (None, None) }
│ └─BatchSource { source: auction, columns: [id, item_name, description, initial_bid, reserve, date_time, expires, seller, category, extra, _row_id] }
└─BatchExchange { order: [], dist: HashShard(id) }
└─BatchFilter { predicate: (initial_bid = 2:Int32) }
└─BatchSource { source: auction, columns: [id, item_name, description, initial_bid, reserve, date_time, expires, seller, category, extra, _row_id], filter: (None, None) }
└─BatchSource { source: auction, columns: [id, item_name, description, initial_bid, reserve, date_time, expires, seller, category, extra, _row_id] }
stream_plan: |-
StreamMaterialize { columns: [cnt], stream_key: [], pk_columns: [], pk_conflict: NoCheck }
└─StreamProject { exprs: [sum0(count)] }
Expand Down Expand Up @@ -92,7 +92,7 @@
│ └─LogicalProject { exprs: [window_start, auction] }
│ └─LogicalHopWindow { time_col: date_time, slide: 00:00:02, size: 00:00:10, output: all }
│ └─LogicalFilter { predicate: IsNotNull(date_time) }
│ └─LogicalSource { source: bid, columns: [auction, bidder, price, channel, url, date_time, extra, _row_id], time_range: (Unbounded, Unbounded) }
│ └─LogicalSource { source: bid, columns: [auction, bidder, price, channel, url, date_time, extra, _row_id] }
└─LogicalProject { exprs: [max(count), window_start] }
└─LogicalAgg { group_key: [window_start], aggs: [max(count)] }
└─LogicalProject { exprs: [window_start, count] }
Expand All @@ -101,7 +101,7 @@
└─LogicalProject { exprs: [auction, window_start] }
└─LogicalHopWindow { time_col: date_time, slide: 00:00:02, size: 00:00:10, output: all }
└─LogicalFilter { predicate: IsNotNull(date_time) }
└─LogicalSource { source: bid, columns: [auction, bidder, price, channel, url, date_time, extra, _row_id], time_range: (Unbounded, Unbounded) }
└─LogicalSource { source: bid, columns: [auction, bidder, price, channel, url, date_time, extra, _row_id] }
batch_plan: |-
BatchExchange { order: [], dist: Single }
└─BatchHashJoin { type: Inner, predicate: window_start = window_start AND (count >= max(count)), output: [auction, count] }
Expand All @@ -111,15 +111,15 @@
│ └─BatchExchange { order: [], dist: HashShard(auction) }
│ └─BatchProject { exprs: [auction, date_time] }
│ └─BatchFilter { predicate: IsNotNull(date_time) }
│ └─BatchSource { source: bid, columns: [auction, bidder, price, channel, url, date_time, extra, _row_id], filter: (None, None) }
│ └─BatchSource { source: bid, columns: [auction, bidder, price, channel, url, date_time, extra, _row_id] }
└─BatchHashAgg { group_key: [window_start], aggs: [max(count)] }
└─BatchExchange { order: [], dist: HashShard(window_start) }
└─BatchHashAgg { group_key: [auction, window_start], aggs: [count] }
└─BatchHopWindow { time_col: date_time, slide: 00:00:02, size: 00:00:10, output: [auction, window_start] }
└─BatchExchange { order: [], dist: HashShard(auction) }
└─BatchProject { exprs: [auction, date_time] }
└─BatchFilter { predicate: IsNotNull(date_time) }
└─BatchSource { source: bid, columns: [auction, bidder, price, channel, url, date_time, extra, _row_id], filter: (None, None) }
└─BatchSource { source: bid, columns: [auction, bidder, price, channel, url, date_time, extra, _row_id] }
stream_plan: |-
StreamMaterialize { columns: [auction, num, window_start(hidden), window_start#1(hidden)], stream_key: [auction, window_start], pk_columns: [auction, window_start], pk_conflict: NoCheck }
└─StreamProject { exprs: [auction, count, window_start, window_start] }
Expand Down Expand Up @@ -298,11 +298,11 @@
├─BatchExchange { order: [], dist: HashShard(id) }
│ └─BatchFilter { predicate: (initial_bid = 1:Int32) AND (AtTimeZone(date_time, 'UTC':Varchar) > '2021-03-31 23:59:59+00:00':Timestamptz) }
│ └─BatchProject { exprs: [id, initial_bid, date_time] }
│ └─BatchSource { source: auction, columns: [id, item_name, description, initial_bid, reserve, date_time, expires, seller, category, extra, _row_id], filter: (None, None) }
│ └─BatchSource { source: auction, columns: [id, item_name, description, initial_bid, reserve, date_time, expires, seller, category, extra, _row_id] }
└─BatchExchange { order: [], dist: HashShard(id) }
└─BatchFilter { predicate: (initial_bid = 2:Int32) }
└─BatchProject { exprs: [id, initial_bid, date_time] }
└─BatchSource { source: auction, columns: [id, item_name, description, initial_bid, reserve, date_time, expires, seller, category, extra, _row_id], filter: (None, None) }
└─BatchSource { source: auction, columns: [id, item_name, description, initial_bid, reserve, date_time, expires, seller, category, extra, _row_id] }
stream_plan: |-
StreamMaterialize { columns: [a_id, b_id, a_ts, b_ts, _row_id(hidden), _row_id#1(hidden)], stream_key: [_row_id, _row_id#1, a_id], pk_columns: [_row_id, _row_id#1, a_id], pk_conflict: NoCheck }
└─StreamExchange { dist: HashShard(id, _row_id, _row_id) }
Expand Down
8 changes: 4 additions & 4 deletions src/frontend/planner_test/tests/testdata/output/shared_source.yml
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -36,7 +36,7 @@
batch_plan: |-
BatchExchange { order: [], dist: Single }
└─BatchProject { exprs: [x, y] }
└─BatchSource { source: s, columns: [x, y, _rw_kafka_timestamp, _row_id], filter: (None, None) }
└─BatchKafkaScan { source: s, columns: [x, y, _rw_kafka_timestamp, _row_id], filter: (None, None) }
stream_plan: |-
StreamMaterialize { columns: [x, y, _row_id(hidden)], stream_key: [_row_id], pk_columns: [_row_id], pk_conflict: NoCheck }
└─StreamProject { exprs: [x, y, _row_id] }
Expand All @@ -52,7 +52,7 @@
batch_plan: |-
BatchExchange { order: [], dist: Single }
└─BatchProject { exprs: [x, y] }
└─BatchSource { source: s, columns: [x, y, _rw_kafka_timestamp, _row_id], filter: (None, None) }
└─BatchKafkaScan { source: s, columns: [x, y, _rw_kafka_timestamp, _row_id], filter: (None, None) }
stream_plan: |-
StreamMaterialize { columns: [x, y, _row_id(hidden)], stream_key: [_row_id], pk_columns: [_row_id], pk_conflict: NoCheck }
└─StreamProject { exprs: [x, y, _row_id] }
Expand All @@ -68,7 +68,7 @@
batch_plan: |-
BatchExchange { order: [], dist: Single }
└─BatchProject { exprs: [x, y] }
└─BatchSource { source: s, columns: [x, y, _rw_kafka_timestamp, _row_id], filter: (None, None) }
└─BatchKafkaScan { source: s, columns: [x, y, _rw_kafka_timestamp, _row_id], filter: (None, None) }
stream_plan: |-
StreamMaterialize { columns: [x, y, _row_id(hidden)], stream_key: [_row_id], pk_columns: [_row_id], pk_conflict: NoCheck }
└─StreamProject { exprs: [x, y, _row_id] }
Expand All @@ -84,7 +84,7 @@
batch_plan: |-
BatchExchange { order: [], dist: Single }
└─BatchProject { exprs: [x, y] }
└─BatchSource { source: s, columns: [x, y, _rw_kafka_timestamp, _row_id], filter: (None, None) }
└─BatchKafkaScan { source: s, columns: [x, y, _rw_kafka_timestamp, _row_id], filter: (None, None) }
stream_plan: |-
StreamMaterialize { columns: [x, y, _row_id(hidden)], stream_key: [_row_id], pk_columns: [_row_id], pk_conflict: NoCheck }
└─StreamProject { exprs: [x, y, _row_id] }
Expand Down
10 changes: 5 additions & 5 deletions src/frontend/planner_test/tests/testdata/output/subquery.yaml
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -486,21 +486,21 @@
└─LogicalJoin { type: LeftSemi, on: IsNotDistinctFrom(a1, a1), output: [] }
├─LogicalShare { id: 2 }
│ └─LogicalProject { exprs: [a1] }
│ └─LogicalSource { source: a, columns: [a1, a2, _row_id], time_range: (Unbounded, Unbounded) }
│ └─LogicalSource { source: a, columns: [a1, a2, _row_id] }
└─LogicalJoin { type: LeftSemi, on: IsNotDistinctFrom(a1, a1), output: all }
├─LogicalJoin { type: Inner, on: true, output: all }
│ ├─LogicalAgg { group_key: [a1], aggs: [] }
│ │ └─LogicalShare { id: 2 }
│ │ └─LogicalProject { exprs: [a1] }
│ │ └─LogicalSource { source: a, columns: [a1, a2, _row_id], time_range: (Unbounded, Unbounded) }
│ │ └─LogicalSource { source: a, columns: [a1, a2, _row_id] }
│ └─LogicalAgg { aggs: [] }
│ └─LogicalSource { source: b, columns: [b1, b2, _row_id], time_range: (Unbounded, Unbounded) }
│ └─LogicalSource { source: b, columns: [b1, b2, _row_id] }
└─LogicalJoin { type: Inner, on: true, output: [a1] }
├─LogicalAgg { group_key: [a1], aggs: [] }
│ └─LogicalShare { id: 2 }
│ └─LogicalProject { exprs: [a1] }
│ └─LogicalSource { source: a, columns: [a1, a2, _row_id], time_range: (Unbounded, Unbounded) }
└─LogicalSource { source: c, columns: [c1, c2, _row_id], time_range: (Unbounded, Unbounded) }
│ └─LogicalSource { source: a, columns: [a1, a2, _row_id] }
└─LogicalSource { source: c, columns: [c1, c2, _row_id] }
- name: test subquery in table function
sql: |
create table t(x int[], y int[], k int primary key);
Expand Down
Loading
Loading