mirror of
https://github.com/GreptimeTeam/greptimedb.git
synced 2026-10-26 05:36:16 +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>
166 lines
4.4 KiB
Plaintext
166 lines
4.4 KiB
Plaintext
-- 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');
|
|
|
|
Affected Rows: 0
|
|
|
|
INSERT INTO n1 VALUES (1000, 1, 'a'), (2000, NULL, 'a'), (3000, NULL, NULL), (4000, 4, 'b');
|
|
|
|
Affected Rows: 4
|
|
|
|
SELECT count(*), count(v), count(s), count(DISTINCT s) FROM n1;
|
|
|
|
+----------+-------------+-------------+----------------------+
|
|
| count(*) | count(n1.v) | count(n1.s) | count(DISTINCT n1.s) |
|
|
+----------+-------------+-------------+----------------------+
|
|
| 4 | 2 | 3 | 2 |
|
|
+----------+-------------+-------------+----------------------+
|
|
|
|
SELECT count(v) FROM n1;
|
|
|
|
+-------------+
|
|
| count(n1.v) |
|
|
+-------------+
|
|
| 2 |
|
|
+-------------+
|
|
|
|
-- 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;
|
|
|
|
+-+-+-+
|
|
| stage | node | plan_|
|
|
+-+-+-+
|
|
| 0_| 0_|_CooperativeExec REDACTED
|
|
|_|_|_MergeScanExec: REDACTED
|
|
|_|_|_|
|
|
| 1_| 0_|_ProjectionExec: expr=[4 as count(*)] REDACTED
|
|
|_|_|_PlaceholderRowExec REDACTED
|
|
|_|_|_|
|
|
|_|_| Total rows: 1_|
|
|
+-+-+-+
|
|
|
|
ADMIN FLUSH_TABLE('n1');
|
|
|
|
+-------------------------+
|
|
| ADMIN FLUSH_TABLE('n1') |
|
|
+-------------------------+
|
|
| 0 |
|
|
+-------------------------+
|
|
|
|
SELECT count(*), count(v), count(s), count(DISTINCT s) FROM n1;
|
|
|
|
+----------+-------------+-------------+----------------------+
|
|
| count(*) | count(n1.v) | count(n1.s) | count(DISTINCT n1.s) |
|
|
+----------+-------------+-------------+----------------------+
|
|
| 4 | 2 | 3 | 2 |
|
|
+----------+-------------+-------------+----------------------+
|
|
|
|
-- 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;
|
|
|
|
+-+-+-+
|
|
| stage | node | plan_|
|
|
+-+-+-+
|
|
| 0_| 0_|_CooperativeExec REDACTED
|
|
|_|_|_MergeScanExec: REDACTED
|
|
|_|_|_|
|
|
| 1_| 0_|_ProjectionExec: expr=[4 as count(*)] REDACTED
|
|
|_|_|_PlaceholderRowExec REDACTED
|
|
|_|_|_|
|
|
|_|_| Total rows: 1_|
|
|
+-+-+-+
|
|
|
|
DROP TABLE n1;
|
|
|
|
Affected Rows: 0
|
|
|
|
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');
|
|
|
|
Affected Rows: 0
|
|
|
|
INSERT INTO n2 VALUES
|
|
('a', 1000, 1, 'a'),
|
|
('b', 2000, NULL, 'a'),
|
|
('x', 3000, NULL, NULL),
|
|
('y', 4000, 4, 'b');
|
|
|
|
Affected Rows: 4
|
|
|
|
-- count is pushed down to each region as a state aggregate.
|
|
SELECT count(v), count(s) FROM n2;
|
|
|
|
+-------------+-------------+
|
|
| count(n2.v) | count(n2.s) |
|
|
+-------------+-------------+
|
|
| 2 | 3 |
|
|
+-------------+-------------+
|
|
|
|
ADMIN FLUSH_TABLE('n2');
|
|
|
|
+-------------------------+
|
|
| ADMIN FLUSH_TABLE('n2') |
|
|
+-------------------------+
|
|
| 0 |
|
|
+-------------------------+
|
|
|
|
SELECT count(v), count(s) FROM n2;
|
|
|
|
+-------------+-------------+
|
|
| count(n2.v) | count(n2.s) |
|
|
+-------------+-------------+
|
|
| 2 | 3 |
|
|
+-------------+-------------+
|
|
|
|
-- 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;
|
|
|
|
+-+-+-+
|
|
| stage | node | plan_|
|
|
+-+-+-+
|
|
| 0_| 0_|_ProjectionExec: expr=[count(Int64(1))@0 as count(*)] REDACTED
|
|
|_|_|_AggregateExec: mode=Final, gby=[], aggr=[__count_merge(__count_state(n2.ts)) as count(Int64(1))] REDACTED
|
|
|_|_|_CoalescePartitionsExec REDACTED
|
|
|_|_|_AggregateExec: mode=Partial, gby=[], aggr=[__count_merge(__count_state(n2.ts)) as count(Int64(1))] REDACTED
|
|
|_|_|_RepartitionExec: partitioning=REDACTED
|
|
|_|_|_MergeScanExec: REDACTED
|
|
|_|_|_|
|
|
| 1_| 0_|_ProjectionExec: expr=[{count[count]:2} as __count_state(n2.ts)] REDACTED
|
|
|_|_|_PlaceholderRowExec REDACTED
|
|
|_|_|_|
|
|
| 1_| 1_|_ProjectionExec: expr=[{count[count]:2} as __count_state(n2.ts)] REDACTED
|
|
|_|_|_PlaceholderRowExec REDACTED
|
|
|_|_|_|
|
|
|_|_| Total rows: 1_|
|
|
+-+-+-+
|
|
|
|
DROP TABLE n2;
|
|
|
|
Affected Rows: 0
|
|
|