mirror of
https://github.com/GreptimeTeam/greptimedb.git
synced 2026-10-16 08:52:30 +00:00
dennis zhuang
5cfdc30a69
RegionScanExec reported null_count = 0 and distinct_count = total_rows for every column of an append-only table. DataFusion answers count(col) and count(DISTINCT col) from these statistics, so both returned the row count. Keep the exact row count and an exact zero null count for non-nullable columns, so count(*) is still answered from statistics. Signed-off-by: Dennis Zhuang <killme2008@gmail.com>
68 lines
1.8 KiB
SQL
68 lines
1.8 KiB
SQL
-- count(col) and count(DISTINCT col) on append-only tables must not be answered
|
|
-- from row-count statistics, while count(*) still is.
|
|
CREATE TABLE n1 (ts TIMESTAMP TIME INDEX, v BIGINT, s STRING) WITH (append_mode='true');
|
|
|
|
INSERT INTO n1 VALUES (1000, 1, 'a'), (2000, NULL, 'a'), (3000, NULL, NULL), (4000, 4, 'b');
|
|
|
|
SELECT count(*), count(v), count(s), count(DISTINCT s) FROM n1;
|
|
|
|
SELECT count(v) FROM n1;
|
|
|
|
-- SQLNESS REPLACE (metrics.*) REDACTED
|
|
-- SQLNESS REPLACE (RoundRobinBatch.*) REDACTED
|
|
-- SQLNESS REPLACE (-+) -
|
|
-- SQLNESS REPLACE (\s\s+) _
|
|
-- SQLNESS REPLACE (peers.*) REDACTED
|
|
-- SQLNESS REPLACE region=\d+\(\d+,\s+\d+\) region=REDACTED
|
|
EXPLAIN ANALYZE SELECT count(*) FROM n1;
|
|
|
|
ADMIN FLUSH_TABLE('n1');
|
|
|
|
SELECT count(*), count(v), count(s), count(DISTINCT s) FROM n1;
|
|
|
|
-- SQLNESS REPLACE (metrics.*) REDACTED
|
|
-- SQLNESS REPLACE (RoundRobinBatch.*) REDACTED
|
|
-- SQLNESS REPLACE (-+) -
|
|
-- SQLNESS REPLACE (\s\s+) _
|
|
-- SQLNESS REPLACE (peers.*) REDACTED
|
|
-- SQLNESS REPLACE region=\d+\(\d+,\s+\d+\) region=REDACTED
|
|
EXPLAIN ANALYZE SELECT count(*) FROM n1;
|
|
|
|
DROP TABLE n1;
|
|
|
|
CREATE TABLE n2 (
|
|
host STRING,
|
|
ts TIMESTAMP TIME INDEX,
|
|
v BIGINT,
|
|
s STRING,
|
|
PRIMARY KEY (host)
|
|
)
|
|
PARTITION ON COLUMNS (host) (
|
|
host < 'm',
|
|
host >= 'm'
|
|
)
|
|
WITH (append_mode='true');
|
|
|
|
INSERT INTO n2 VALUES
|
|
('a', 1000, 1, 'a'),
|
|
('b', 2000, NULL, 'a'),
|
|
('x', 3000, NULL, NULL),
|
|
('y', 4000, 4, 'b');
|
|
|
|
-- count is pushed down to each region as a state aggregate.
|
|
SELECT count(v), count(s) FROM n2;
|
|
|
|
ADMIN FLUSH_TABLE('n2');
|
|
|
|
SELECT count(v), count(s) FROM n2;
|
|
|
|
-- SQLNESS REPLACE (metrics.*) REDACTED
|
|
-- SQLNESS REPLACE (RoundRobinBatch.*) REDACTED
|
|
-- SQLNESS REPLACE (-+) -
|
|
-- SQLNESS REPLACE (\s\s+) _
|
|
-- SQLNESS REPLACE (peers.*) REDACTED
|
|
-- SQLNESS REPLACE region=\d+\(\d+,\s+\d+\) region=REDACTED
|
|
EXPLAIN ANALYZE SELECT count(*) FROM n2;
|
|
|
|
DROP TABLE n2;
|