Files
greptimedb/tests/cases/standalone/common/flow/flow_call_df_func.sql
discord9 a0900f5b90 feat(flow): use batching mode&fix sqlness (#5903)
* feat: use flow batching engine

broken: try using logical plan

fix: use dummy catalog for logical plan

fix: insert plan exec&sqlness grpc addr

feat: use frontend instance in flownode in standalone

feat: flow type in metasrv&fix: flush flow out of sync& column name alias

tests: sqlness update

tests: sqlness flow rebuild udpate

chore: per review

refactor: keep chnl mgr

refactor: use catalog mgr for get table

tests: use valid sql

fix: add more check

refactor: put flow type determine to frontend

* chore: update proto

* chore: update proto to main branch

* fix: add locks for create/drop flow&docs: update docs

* feat: flush_flow flush all ranges now

* test: add align time window test

* docs: explain `nodeid` use in check task

* refactor: AddAutoColumnRewriter check for Projection

* refactor: per review

* fix: query without time window also clean dirty time window

* chore: better logging

* chore: add comments per review

* refactor: per review

* chore: per review

* chore: per review rename args

* refactor: per review partially

* chore: update docs

* chore: use better error variant

* chore: better error variant

* refactor: rename FlowWorkerManager to FlowStreamingEngine

* rename again

* refactor: per review

* chore: rebase after #5963 merged

* refactor: rename all flow_worker_manager occurs

* docs: rm resolved TODO
2025-04-23 15:12:16 +00:00

177 lines
6.0 KiB
SQL

CREATE TABLE numbers_input_df_func (
number INT,
ts TIMESTAMP DEFAULT CURRENT_TIMESTAMP,
PRIMARY KEY(number),
TIME INDEX(ts)
);
-- call `sum(abs(number))` where `abs` is DataFusion Function and `sum` is flow function
CREATE FLOW test_numbers_df_func
SINK TO out_num_cnt_df_func
AS
SELECT sum(abs(number)), date_bin(INTERVAL '1 second', ts, '2021-07-01 00:00:00') as time_window FROM numbers_input_df_func GROUP BY time_window;
-- SQLNESS REPLACE (ADMIN\sFLUSH_FLOW\('\w+'\)\s+\|\n\+-+\+\n\|\s+)[0-9]+\s+\| $1 FLOW_FLUSHED |
ADMIN FLUSH_FLOW('test_numbers_df_func');
INSERT INTO numbers_input_df_func
VALUES
(-20, "2021-07-01 00:00:00.200"),
(22, "2021-07-01 00:00:00.600");
-- flush flow to make sure that table is created and data is inserted
-- SQLNESS REPLACE (ADMIN\sFLUSH_FLOW\('\w+'\)\s+\|\n\+-+\+\n\|\s+)[0-9]+\s+\| $1 FLOW_FLUSHED |
ADMIN FLUSH_FLOW('test_numbers_df_func');
-- note that this quote-unquote column is a column-name, **not** a aggregation expr, generated by datafusion
SELECT "sum(abs(numbers_input_df_func.number))", time_window FROM out_num_cnt_df_func;
-- SQLNESS REPLACE (ADMIN\sFLUSH_FLOW\('\w+'\)\s+\|\n\+-+\+\n\|\s+)[0-9]+\s+\| $1 FLOW_FLUSHED |
ADMIN FLUSH_FLOW('test_numbers_df_func');
INSERT INTO numbers_input_df_func
VALUES
(23,"2021-07-01 00:00:01.000"),
(-24,"2021-07-01 00:00:01.500");
-- SQLNESS REPLACE (ADMIN\sFLUSH_FLOW\('\w+'\)\s+\|\n\+-+\+\n\|\s+)[0-9]+\s+\| $1 FLOW_FLUSHED |
ADMIN FLUSH_FLOW('test_numbers_df_func');
-- note that this quote-unquote column is a column-name, **not** a aggregation expr, generated by datafusion
SELECT "sum(abs(numbers_input_df_func.number))", time_window FROM out_num_cnt_df_func;
DROP FLOW test_numbers_df_func;
DROP TABLE numbers_input_df_func;
DROP TABLE out_num_cnt_df_func;
CREATE TABLE numbers_input_df_func (
number INT,
ts TIMESTAMP DEFAULT CURRENT_TIMESTAMP,
PRIMARY KEY(number),
TIME INDEX(ts)
);
-- call `abs(sum(number))`to make sure that calling `abs` function(impl by datafusion) on `sum` function(impl by flow) is working
CREATE FLOW test_numbers_df_func
SINK TO out_num_cnt_df_func
AS
SELECT abs(sum(number)), date_bin(INTERVAL '1 second', ts, '2021-07-01 00:00:00') as time_window FROM numbers_input_df_func GROUP BY time_window;
-- SQLNESS REPLACE (ADMIN\sFLUSH_FLOW\('\w+'\)\s+\|\n\+-+\+\n\|\s+)[0-9]+\s+\| $1 FLOW_FLUSHED |
ADMIN FLUSH_FLOW('test_numbers_df_func');
INSERT INTO numbers_input_df_func
VALUES
(-20, "2021-07-01 00:00:00.200"),
(22, "2021-07-01 00:00:00.600");
-- flush flow to make sure that table is created and data is inserted
-- SQLNESS REPLACE (ADMIN\sFLUSH_FLOW\('\w+'\)\s+\|\n\+-+\+\n\|\s+)[0-9]+\s+\| $1 FLOW_FLUSHED |
ADMIN FLUSH_FLOW('test_numbers_df_func');
SELECT "abs(sum(numbers_input_df_func.number))", time_window FROM out_num_cnt_df_func;
-- SQLNESS REPLACE (ADMIN\sFLUSH_FLOW\('\w+'\)\s+\|\n\+-+\+\n\|\s+)[0-9]+\s+\| $1 FLOW_FLUSHED |
ADMIN FLUSH_FLOW('test_numbers_df_func');
INSERT INTO numbers_input_df_func
VALUES
(23,"2021-07-01 00:00:01.000"),
(-24,"2021-07-01 00:00:01.500");
-- SQLNESS REPLACE (ADMIN\sFLUSH_FLOW\('\w+'\)\s+\|\n\+-+\+\n\|\s+)[0-9]+\s+\| $1 FLOW_FLUSHED |
ADMIN FLUSH_FLOW('test_numbers_df_func');
SELECT "abs(sum(numbers_input_df_func.number))", time_window FROM out_num_cnt_df_func;
DROP FLOW test_numbers_df_func;
DROP TABLE numbers_input_df_func;
DROP TABLE out_num_cnt_df_func;
-- test date_bin
CREATE TABLE numbers_input_df_func (
number INT,
ts TIMESTAMP DEFAULT CURRENT_TIMESTAMP,
PRIMARY KEY(number),
TIME INDEX(ts)
);
CREATE FLOW test_numbers_df_func
SINK TO out_num_cnt_df_func
AS
SELECT max(number) - min(number) as maxmin, date_bin(INTERVAL '1 second', ts, '2021-07-01 00:00:00'::Timestamp) as time_window FROM numbers_input_df_func GROUP BY time_window;
-- SQLNESS REPLACE (ADMIN\sFLUSH_FLOW\('\w+'\)\s+\|\n\+-+\+\n\|\s+)[0-9]+\s+\| $1 FLOW_FLUSHED |
ADMIN FLUSH_FLOW('test_numbers_df_func');
INSERT INTO numbers_input_df_func
VALUES
(20, "2021-07-01 00:00:00.200"),
(22, "2021-07-01 00:00:00.600");
-- SQLNESS REPLACE (ADMIN\sFLUSH_FLOW\('\w+'\)\s+\|\n\+-+\+\n\|\s+)[0-9]+\s+\| $1 FLOW_FLUSHED |
ADMIN FLUSH_FLOW('test_numbers_df_func');
SELECT maxmin, time_window FROM out_num_cnt_df_func;
-- SQLNESS REPLACE (ADMIN\sFLUSH_FLOW\('\w+'\)\s+\|\n\+-+\+\n\|\s+)[0-9]+\s+\| $1 FLOW_FLUSHED |
ADMIN FLUSH_FLOW('test_numbers_df_func');
INSERT INTO numbers_input_df_func
VALUES
(23,"2021-07-01 00:00:01.000"),
(24,"2021-07-01 00:00:01.500");
-- SQLNESS REPLACE (ADMIN\sFLUSH_FLOW\('\w+'\)\s+\|\n\+-+\+\n\|\s+)[0-9]+\s+\| $1 FLOW_FLUSHED |
ADMIN FLUSH_FLOW('test_numbers_df_func');
SELECT maxmin, time_window FROM out_num_cnt_df_func;
DROP FLOW test_numbers_df_func;
DROP TABLE numbers_input_df_func;
DROP TABLE out_num_cnt_df_func;
-- test date_trunc
CREATE TABLE numbers_input_df_func (
number INT,
ts TIMESTAMP DEFAULT CURRENT_TIMESTAMP,
PRIMARY KEY(number),
TIME INDEX(ts)
);
CREATE FLOW test_numbers_df_func
SINK TO out_num_cnt
AS
SELECT date_trunc('second', ts) as time_window, sum(number) as sum_num FROM numbers_input_df_func GROUP BY date_trunc('second', ts);
-- SQLNESS REPLACE (ADMIN\sFLUSH_FLOW\('\w+'\)\s+\|\n\+-+\+\n\|\s+)[0-9]+\s+\| $1 FLOW_FLUSHED |
ADMIN FLUSH_FLOW('test_numbers_df_func');
INSERT INTO numbers_input_df_func
VALUES
(20, "2021-07-01 00:00:00.200"),
(22, "2021-07-01 00:00:00.600");
-- SQLNESS REPLACE (ADMIN\sFLUSH_FLOW\('\w+'\)\s+\|\n\+-+\+\n\|\s+)[0-9]+\s+\| $1 FLOW_FLUSHED |
ADMIN FLUSH_FLOW('test_numbers_df_func');
SELECT time_window, sum_num FROM out_num_cnt;
-- SQLNESS REPLACE (ADMIN\sFLUSH_FLOW\('\w+'\)\s+\|\n\+-+\+\n\|\s+)[0-9]+\s+\| $1 FLOW_FLUSHED |
ADMIN FLUSH_FLOW('test_numbers_df_func');
INSERT INTO numbers_input_df_func
VALUES
(23,"2021-07-01 00:00:01.000"),
(24,"2021-07-01 00:00:01.500");
-- SQLNESS REPLACE (ADMIN\sFLUSH_FLOW\('\w+'\)\s+\|\n\+-+\+\n\|\s+)[0-9]+\s+\| $1 FLOW_FLUSHED |
ADMIN FLUSH_FLOW('test_numbers_df_func');
SELECT time_window, sum_num FROM out_num_cnt;
DROP FLOW test_numbers_df_func;
DROP TABLE numbers_input_df_func;
DROP TABLE out_num_cnt;