feat: steppable aggr fn

poc: step aggr query

feat: mvp poc stuff

test: sqlness

chore: import missing

feat: support first/last_value

fix: check also include first/last value
This commit is contained in:
discord9
2025-06-08 19:19:11 +08:00
parent 12648f388a
commit 838d3ab04e
6 changed files with 856 additions and 8 deletions

View File

@@ -0,0 +1,409 @@
CREATE TABLE integers(
host STRING,
i BIGINT,
ts TIMESTAMP TIME INDEX
) PARTITION ON COLUMNS (host) (
host < '550-A',
host >= '550-A'
AND host < '550-W',
host >= '550-W'
);
Affected Rows: 0
INSERT INTO integers (host, i, ts) VALUES
('550-A', 1, '2023-01-01 00:00:00'),
('550-A', 2, '2023-01-01 01:00:00'),
('550-W', 3, '2023-01-01 02:00:00'),
('550-W', 4, '2023-01-01 03:00:00');
Affected Rows: 4
-- count
EXPLAIN SELECT
count(i)
FROM
integers;
+---------------+-------------------------------------------------------------------------------------------------------+
| plan_type | plan |
+---------------+-------------------------------------------------------------------------------------------------------+
| logical_plan | Aggregate: groupBy=[[]], aggr=[[sum(count(integers.i)) AS count(integers.i)]] |
| | MergeScan [is_placeholder=false, input=Aggregate: groupBy=[[]], aggr=[[count(integers.i)]] |
| | TableScan: integers] |
| physical_plan | AggregateExec: mode=Final, gby=[], aggr=[count(integers.i)] |
| | CoalescePartitionsExec |
| | AggregateExec: mode=Partial, gby=[], aggr=[count(integers.i)] |
| | MergeScanExec: peers=[4402341478400(1025, 0), 4402341478401(1025, 1), 4402341478402(1025, 2), ] |
| | |
+---------------+-------------------------------------------------------------------------------------------------------+
EXPLAIN SELECT
ts,
count(i)
FROM
integers
GROUP BY
ts;
+---------------+---------------------------------------------------------------------------------------------------------+
| plan_type | plan |
+---------------+---------------------------------------------------------------------------------------------------------+
| logical_plan | Aggregate: groupBy=[[integers.ts]], aggr=[[sum(count(integers.i)) AS count(integers.i)]] |
| | MergeScan [is_placeholder=false, input=Aggregate: groupBy=[[integers.ts]], aggr=[[count(integers.i)]] |
| | TableScan: integers] |
| physical_plan | AggregateExec: mode=FinalPartitioned, gby=[ts@0 as ts], aggr=[count(integers.i)] |
| | CoalesceBatchesExec: target_batch_size=8192 |
| | RepartitionExec: partitioning=Hash([ts@0], 20), input_partitions=20 |
| | AggregateExec: mode=Partial, gby=[ts@0 as ts], aggr=[count(integers.i)] |
| | MergeScanExec: peers=[4402341478400(1025, 0), 4402341478401(1025, 1), 4402341478402(1025, 2), ] |
| | |
+---------------+---------------------------------------------------------------------------------------------------------+
EXPLAIN SELECT
count(i)
FROM
integers
GROUP BY
ts;
+---------------+-----------------------------------------------------------------------------------------------------------+
| plan_type | plan |
+---------------+-----------------------------------------------------------------------------------------------------------+
| logical_plan | Projection: count(integers.i) |
| | Aggregate: groupBy=[[integers.ts]], aggr=[[sum(count(integers.i)) AS count(integers.i)]] |
| | MergeScan [is_placeholder=false, input=Aggregate: groupBy=[[integers.ts]], aggr=[[count(integers.i)]] |
| | TableScan: integers] |
| physical_plan | ProjectionExec: expr=[count(integers.i)@1 as count(integers.i)] |
| | AggregateExec: mode=FinalPartitioned, gby=[ts@0 as ts], aggr=[count(integers.i)] |
| | CoalesceBatchesExec: target_batch_size=8192 |
| | RepartitionExec: partitioning=Hash([ts@0], 20), input_partitions=20 |
| | AggregateExec: mode=Partial, gby=[ts@0 as ts], aggr=[count(integers.i)] |
| | MergeScanExec: peers=[4402341478400(1025, 0), 4402341478401(1025, 1), 4402341478402(1025, 2), ] |
| | |
+---------------+-----------------------------------------------------------------------------------------------------------+
-- sum
EXPLAIN SELECT
sum(i)
FROM
integers;
+---------------+-------------------------------------------------------------------------------------------------------+
| plan_type | plan |
+---------------+-------------------------------------------------------------------------------------------------------+
| logical_plan | Aggregate: groupBy=[[]], aggr=[[sum(sum(integers.i)) AS sum(integers.i)]] |
| | MergeScan [is_placeholder=false, input=Aggregate: groupBy=[[]], aggr=[[sum(integers.i)]] |
| | TableScan: integers] |
| physical_plan | AggregateExec: mode=Final, gby=[], aggr=[sum(integers.i)] |
| | CoalescePartitionsExec |
| | AggregateExec: mode=Partial, gby=[], aggr=[sum(integers.i)] |
| | MergeScanExec: peers=[4402341478400(1025, 0), 4402341478401(1025, 1), 4402341478402(1025, 2), ] |
| | |
+---------------+-------------------------------------------------------------------------------------------------------+
EXPLAIN SELECT
ts,
sum(i)
FROM
integers
GROUP BY
ts;
+---------------+---------------------------------------------------------------------------------------------------------+
| plan_type | plan |
+---------------+---------------------------------------------------------------------------------------------------------+
| logical_plan | Aggregate: groupBy=[[integers.ts]], aggr=[[sum(sum(integers.i)) AS sum(integers.i)]] |
| | MergeScan [is_placeholder=false, input=Aggregate: groupBy=[[integers.ts]], aggr=[[sum(integers.i)]] |
| | TableScan: integers] |
| physical_plan | AggregateExec: mode=FinalPartitioned, gby=[ts@0 as ts], aggr=[sum(integers.i)] |
| | CoalesceBatchesExec: target_batch_size=8192 |
| | RepartitionExec: partitioning=Hash([ts@0], 20), input_partitions=20 |
| | AggregateExec: mode=Partial, gby=[ts@0 as ts], aggr=[sum(integers.i)] |
| | MergeScanExec: peers=[4402341478400(1025, 0), 4402341478401(1025, 1), 4402341478402(1025, 2), ] |
| | |
+---------------+---------------------------------------------------------------------------------------------------------+
EXPLAIN SELECT
sum(i)
FROM
integers
GROUP BY
ts;
+---------------+-----------------------------------------------------------------------------------------------------------+
| plan_type | plan |
+---------------+-----------------------------------------------------------------------------------------------------------+
| logical_plan | Projection: sum(integers.i) |
| | Aggregate: groupBy=[[integers.ts]], aggr=[[sum(sum(integers.i)) AS sum(integers.i)]] |
| | MergeScan [is_placeholder=false, input=Aggregate: groupBy=[[integers.ts]], aggr=[[sum(integers.i)]] |
| | TableScan: integers] |
| physical_plan | ProjectionExec: expr=[sum(integers.i)@1 as sum(integers.i)] |
| | AggregateExec: mode=FinalPartitioned, gby=[ts@0 as ts], aggr=[sum(integers.i)] |
| | CoalesceBatchesExec: target_batch_size=8192 |
| | RepartitionExec: partitioning=Hash([ts@0], 20), input_partitions=20 |
| | AggregateExec: mode=Partial, gby=[ts@0 as ts], aggr=[sum(integers.i)] |
| | MergeScanExec: peers=[4402341478400(1025, 0), 4402341478401(1025, 1), 4402341478402(1025, 2), ] |
| | |
+---------------+-----------------------------------------------------------------------------------------------------------+
-- min
EXPLAIN SELECT
min(i)
FROM
integers;
+---------------+-------------------------------------------------------------------------------------------------------+
| plan_type | plan |
+---------------+-------------------------------------------------------------------------------------------------------+
| logical_plan | Aggregate: groupBy=[[]], aggr=[[min(min(integers.i)) AS min(integers.i)]] |
| | MergeScan [is_placeholder=false, input=Aggregate: groupBy=[[]], aggr=[[min(integers.i)]] |
| | TableScan: integers] |
| physical_plan | AggregateExec: mode=Final, gby=[], aggr=[min(integers.i)] |
| | CoalescePartitionsExec |
| | AggregateExec: mode=Partial, gby=[], aggr=[min(integers.i)] |
| | MergeScanExec: peers=[4402341478400(1025, 0), 4402341478401(1025, 1), 4402341478402(1025, 2), ] |
| | |
+---------------+-------------------------------------------------------------------------------------------------------+
EXPLAIN SELECT
ts,
min(i)
FROM
integers
GROUP BY
ts;
+---------------+---------------------------------------------------------------------------------------------------------+
| plan_type | plan |
+---------------+---------------------------------------------------------------------------------------------------------+
| logical_plan | Aggregate: groupBy=[[integers.ts]], aggr=[[min(min(integers.i)) AS min(integers.i)]] |
| | MergeScan [is_placeholder=false, input=Aggregate: groupBy=[[integers.ts]], aggr=[[min(integers.i)]] |
| | TableScan: integers] |
| physical_plan | AggregateExec: mode=FinalPartitioned, gby=[ts@0 as ts], aggr=[min(integers.i)] |
| | CoalesceBatchesExec: target_batch_size=8192 |
| | RepartitionExec: partitioning=Hash([ts@0], 20), input_partitions=20 |
| | AggregateExec: mode=Partial, gby=[ts@0 as ts], aggr=[min(integers.i)] |
| | MergeScanExec: peers=[4402341478400(1025, 0), 4402341478401(1025, 1), 4402341478402(1025, 2), ] |
| | |
+---------------+---------------------------------------------------------------------------------------------------------+
EXPLAIN SELECT
min(i)
FROM
integers
GROUP BY
ts;
+---------------+-----------------------------------------------------------------------------------------------------------+
| plan_type | plan |
+---------------+-----------------------------------------------------------------------------------------------------------+
| logical_plan | Projection: min(integers.i) |
| | Aggregate: groupBy=[[integers.ts]], aggr=[[min(min(integers.i)) AS min(integers.i)]] |
| | MergeScan [is_placeholder=false, input=Aggregate: groupBy=[[integers.ts]], aggr=[[min(integers.i)]] |
| | TableScan: integers] |
| physical_plan | ProjectionExec: expr=[min(integers.i)@1 as min(integers.i)] |
| | AggregateExec: mode=FinalPartitioned, gby=[ts@0 as ts], aggr=[min(integers.i)] |
| | CoalesceBatchesExec: target_batch_size=8192 |
| | RepartitionExec: partitioning=Hash([ts@0], 20), input_partitions=20 |
| | AggregateExec: mode=Partial, gby=[ts@0 as ts], aggr=[min(integers.i)] |
| | MergeScanExec: peers=[4402341478400(1025, 0), 4402341478401(1025, 1), 4402341478402(1025, 2), ] |
| | |
+---------------+-----------------------------------------------------------------------------------------------------------+
-- max
EXPLAIN SELECT
max(i)
FROM
integers;
+---------------+-------------------------------------------------------------------------------------------------------+
| plan_type | plan |
+---------------+-------------------------------------------------------------------------------------------------------+
| logical_plan | Aggregate: groupBy=[[]], aggr=[[max(max(integers.i)) AS max(integers.i)]] |
| | MergeScan [is_placeholder=false, input=Aggregate: groupBy=[[]], aggr=[[max(integers.i)]] |
| | TableScan: integers] |
| physical_plan | AggregateExec: mode=Final, gby=[], aggr=[max(integers.i)] |
| | CoalescePartitionsExec |
| | AggregateExec: mode=Partial, gby=[], aggr=[max(integers.i)] |
| | MergeScanExec: peers=[4402341478400(1025, 0), 4402341478401(1025, 1), 4402341478402(1025, 2), ] |
| | |
+---------------+-------------------------------------------------------------------------------------------------------+
EXPLAIN SELECT
ts,
max(i)
FROM
integers
GROUP BY
ts;
+---------------+---------------------------------------------------------------------------------------------------------+
| plan_type | plan |
+---------------+---------------------------------------------------------------------------------------------------------+
| logical_plan | Aggregate: groupBy=[[integers.ts]], aggr=[[max(max(integers.i)) AS max(integers.i)]] |
| | MergeScan [is_placeholder=false, input=Aggregate: groupBy=[[integers.ts]], aggr=[[max(integers.i)]] |
| | TableScan: integers] |
| physical_plan | AggregateExec: mode=FinalPartitioned, gby=[ts@0 as ts], aggr=[max(integers.i)] |
| | CoalesceBatchesExec: target_batch_size=8192 |
| | RepartitionExec: partitioning=Hash([ts@0], 20), input_partitions=20 |
| | AggregateExec: mode=Partial, gby=[ts@0 as ts], aggr=[max(integers.i)] |
| | MergeScanExec: peers=[4402341478400(1025, 0), 4402341478401(1025, 1), 4402341478402(1025, 2), ] |
| | |
+---------------+---------------------------------------------------------------------------------------------------------+
EXPLAIN SELECT
max(i)
FROM
integers
GROUP BY
ts;
+---------------+-----------------------------------------------------------------------------------------------------------+
| plan_type | plan |
+---------------+-----------------------------------------------------------------------------------------------------------+
| logical_plan | Projection: max(integers.i) |
| | Aggregate: groupBy=[[integers.ts]], aggr=[[max(max(integers.i)) AS max(integers.i)]] |
| | MergeScan [is_placeholder=false, input=Aggregate: groupBy=[[integers.ts]], aggr=[[max(integers.i)]] |
| | TableScan: integers] |
| physical_plan | ProjectionExec: expr=[max(integers.i)@1 as max(integers.i)] |
| | AggregateExec: mode=FinalPartitioned, gby=[ts@0 as ts], aggr=[max(integers.i)] |
| | CoalesceBatchesExec: target_batch_size=8192 |
| | RepartitionExec: partitioning=Hash([ts@0], 20), input_partitions=20 |
| | AggregateExec: mode=Partial, gby=[ts@0 as ts], aggr=[max(integers.i)] |
| | MergeScanExec: peers=[4402341478400(1025, 0), 4402341478401(1025, 1), 4402341478402(1025, 2), ] |
| | |
+---------------+-----------------------------------------------------------------------------------------------------------+
-- uddsketch_state
EXPLAIN SELECT
uddsketch_state(128, 0.01, i)
FROM
integers;
+---------------+--------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------+
| plan_type | plan |
+---------------+--------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------+
| logical_plan | Aggregate: groupBy=[[]], aggr=[[uddsketch_merge(Int64(128), Float64(0.01), uddsketch_state(Int64(128),Float64(0.01),integers.i)) AS uddsketch_state(Int64(128),Float64(0.01),integers.i)]] |
| | MergeScan [is_placeholder=false, input=Aggregate: groupBy=[[]], aggr=[[uddsketch_state(Int64(128), Float64(0.01), CAST(integers.i AS Float64))]] |
| | TableScan: integers] |
| physical_plan | AggregateExec: mode=Final, gby=[], aggr=[uddsketch_state(Int64(128),Float64(0.01),integers.i)] |
| | CoalescePartitionsExec |
| | AggregateExec: mode=Partial, gby=[], aggr=[uddsketch_state(Int64(128),Float64(0.01),integers.i)] |
| | MergeScanExec: peers=[4402341478400(1025, 0), 4402341478401(1025, 1), 4402341478402(1025, 2), ] |
| | |
+---------------+--------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------+
EXPLAIN SELECT
ts,
uddsketch_state(128, 0.01, i)
FROM
integers
GROUP BY
ts;
+---------------+-------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------+
| plan_type | plan |
+---------------+-------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------+
| logical_plan | Aggregate: groupBy=[[integers.ts]], aggr=[[uddsketch_merge(Int64(128), Float64(0.01), uddsketch_state(Int64(128),Float64(0.01),integers.i)) AS uddsketch_state(Int64(128),Float64(0.01),integers.i)]] |
| | MergeScan [is_placeholder=false, input=Aggregate: groupBy=[[integers.ts]], aggr=[[uddsketch_state(Int64(128), Float64(0.01), CAST(integers.i AS Float64))]] |
| | TableScan: integers] |
| physical_plan | AggregateExec: mode=FinalPartitioned, gby=[ts@0 as ts], aggr=[uddsketch_state(Int64(128),Float64(0.01),integers.i)] |
| | CoalesceBatchesExec: target_batch_size=8192 |
| | RepartitionExec: partitioning=Hash([ts@0], 20), input_partitions=20 |
| | AggregateExec: mode=Partial, gby=[ts@0 as ts], aggr=[uddsketch_state(Int64(128),Float64(0.01),integers.i)] |
| | MergeScanExec: peers=[4402341478400(1025, 0), 4402341478401(1025, 1), 4402341478402(1025, 2), ] |
| | |
+---------------+-------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------+
EXPLAIN SELECT
uddsketch_state(128, 0.01, i)
FROM
integers
GROUP BY
ts;
+---------------+---------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------+
| plan_type | plan |
+---------------+---------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------+
| logical_plan | Projection: uddsketch_state(Int64(128),Float64(0.01),integers.i) |
| | Aggregate: groupBy=[[integers.ts]], aggr=[[uddsketch_merge(Int64(128), Float64(0.01), uddsketch_state(Int64(128),Float64(0.01),integers.i)) AS uddsketch_state(Int64(128),Float64(0.01),integers.i)]] |
| | MergeScan [is_placeholder=false, input=Aggregate: groupBy=[[integers.ts]], aggr=[[uddsketch_state(Int64(128), Float64(0.01), CAST(integers.i AS Float64))]] |
| | TableScan: integers] |
| physical_plan | ProjectionExec: expr=[uddsketch_state(Int64(128),Float64(0.01),integers.i)@1 as uddsketch_state(Int64(128),Float64(0.01),integers.i)] |
| | AggregateExec: mode=FinalPartitioned, gby=[ts@0 as ts], aggr=[uddsketch_state(Int64(128),Float64(0.01),integers.i)] |
| | CoalesceBatchesExec: target_batch_size=8192 |
| | RepartitionExec: partitioning=Hash([ts@0], 20), input_partitions=20 |
| | AggregateExec: mode=Partial, gby=[ts@0 as ts], aggr=[uddsketch_state(Int64(128),Float64(0.01),integers.i)] |
| | MergeScanExec: peers=[4402341478400(1025, 0), 4402341478401(1025, 1), 4402341478402(1025, 2), ] |
| | |
+---------------+---------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------+
-- hll
EXPLAIN SELECT
hll(i)
FROM
integers;
+---------------+----------------------------------------------------------------------------------------------------------+
| plan_type | plan |
+---------------+----------------------------------------------------------------------------------------------------------+
| logical_plan | Aggregate: groupBy=[[]], aggr=[[hll_merge(hll(integers.i)) AS hll(integers.i)]] |
| | MergeScan [is_placeholder=false, input=Aggregate: groupBy=[[]], aggr=[[hll(CAST(integers.i AS Utf8))]] |
| | TableScan: integers] |
| physical_plan | AggregateExec: mode=Final, gby=[], aggr=[hll(integers.i)] |
| | CoalescePartitionsExec |
| | AggregateExec: mode=Partial, gby=[], aggr=[hll(integers.i)] |
| | MergeScanExec: peers=[4402341478400(1025, 0), 4402341478401(1025, 1), 4402341478402(1025, 2), ] |
| | |
+---------------+----------------------------------------------------------------------------------------------------------+
EXPLAIN SELECT
ts,
hll(i)
FROM
integers
GROUP BY
ts;
+---------------+---------------------------------------------------------------------------------------------------------------------+
| plan_type | plan |
+---------------+---------------------------------------------------------------------------------------------------------------------+
| logical_plan | Aggregate: groupBy=[[integers.ts]], aggr=[[hll_merge(hll(integers.i)) AS hll(integers.i)]] |
| | MergeScan [is_placeholder=false, input=Aggregate: groupBy=[[integers.ts]], aggr=[[hll(CAST(integers.i AS Utf8))]] |
| | TableScan: integers] |
| physical_plan | AggregateExec: mode=FinalPartitioned, gby=[ts@0 as ts], aggr=[hll(integers.i)] |
| | CoalesceBatchesExec: target_batch_size=8192 |
| | RepartitionExec: partitioning=Hash([ts@0], 20), input_partitions=20 |
| | AggregateExec: mode=Partial, gby=[ts@0 as ts], aggr=[hll(integers.i)] |
| | MergeScanExec: peers=[4402341478400(1025, 0), 4402341478401(1025, 1), 4402341478402(1025, 2), ] |
| | |
+---------------+---------------------------------------------------------------------------------------------------------------------+
EXPLAIN SELECT
hll(i)
FROM
integers
GROUP BY
ts;
+---------------+-----------------------------------------------------------------------------------------------------------------------+
| plan_type | plan |
+---------------+-----------------------------------------------------------------------------------------------------------------------+
| logical_plan | Projection: hll(integers.i) |
| | Aggregate: groupBy=[[integers.ts]], aggr=[[hll_merge(hll(integers.i)) AS hll(integers.i)]] |
| | MergeScan [is_placeholder=false, input=Aggregate: groupBy=[[integers.ts]], aggr=[[hll(CAST(integers.i AS Utf8))]] |
| | TableScan: integers] |
| physical_plan | ProjectionExec: expr=[hll(integers.i)@1 as hll(integers.i)] |
| | AggregateExec: mode=FinalPartitioned, gby=[ts@0 as ts], aggr=[hll(integers.i)] |
| | CoalesceBatchesExec: target_batch_size=8192 |
| | RepartitionExec: partitioning=Hash([ts@0], 20), input_partitions=20 |
| | AggregateExec: mode=Partial, gby=[ts@0 as ts], aggr=[hll(integers.i)] |
| | MergeScanExec: peers=[4402341478400(1025, 0), 4402341478401(1025, 1), 4402341478402(1025, 2), ] |
| | |
+---------------+-----------------------------------------------------------------------------------------------------------------------+
DROP TABLE integers;
Affected Rows: 0

View File

@@ -0,0 +1,144 @@
CREATE TABLE integers(
host STRING,
i BIGINT,
ts TIMESTAMP TIME INDEX
) PARTITION ON COLUMNS (host) (
host < '550-A',
host >= '550-A'
AND host < '550-W',
host >= '550-W'
);
INSERT INTO integers (host, i, ts) VALUES
('550-A', 1, '2023-01-01 00:00:00'),
('550-A', 2, '2023-01-01 01:00:00'),
('550-W', 3, '2023-01-01 02:00:00'),
('550-W', 4, '2023-01-01 03:00:00');
-- count
EXPLAIN SELECT
count(i)
FROM
integers;
EXPLAIN SELECT
ts,
count(i)
FROM
integers
GROUP BY
ts;
EXPLAIN SELECT
count(i)
FROM
integers
GROUP BY
ts;
-- sum
EXPLAIN SELECT
sum(i)
FROM
integers;
EXPLAIN SELECT
ts,
sum(i)
FROM
integers
GROUP BY
ts;
EXPLAIN SELECT
sum(i)
FROM
integers
GROUP BY
ts;
-- min
EXPLAIN SELECT
min(i)
FROM
integers;
EXPLAIN SELECT
ts,
min(i)
FROM
integers
GROUP BY
ts;
EXPLAIN SELECT
min(i)
FROM
integers
GROUP BY
ts;
-- max
EXPLAIN SELECT
max(i)
FROM
integers;
EXPLAIN SELECT
ts,
max(i)
FROM
integers
GROUP BY
ts;
EXPLAIN SELECT
max(i)
FROM
integers
GROUP BY
ts;
-- uddsketch_state
EXPLAIN SELECT
uddsketch_state(128, 0.01, i)
FROM
integers;
EXPLAIN SELECT
ts,
uddsketch_state(128, 0.01, i)
FROM
integers
GROUP BY
ts;
EXPLAIN SELECT
uddsketch_state(128, 0.01, i)
FROM
integers
GROUP BY
ts;
-- hll
EXPLAIN SELECT
hll(i)
FROM
integers;
EXPLAIN SELECT
ts,
hll(i)
FROM
integers
GROUP BY
ts;
EXPLAIN SELECT
hll(i)
FROM
integers
GROUP BY
ts;
DROP TABLE integers;

View File

@@ -0,0 +1,80 @@
CREATE TABLE integers(
host STRING,
i BIGINT,
ts TIMESTAMP TIME INDEX
) PARTITION ON COLUMNS (host) (
host < '550-A',
host >= '550-A'
AND host < '550-W',
host >= '550-W'
);
Affected Rows: 0
-- count
EXPLAIN SELECT
count(i)
FROM
integers;
+---------------+-------------------------------------------------------------------------------------------------------+
| plan_type | plan |
+---------------+-------------------------------------------------------------------------------------------------------+
| logical_plan | Aggregate: groupBy=[[]], aggr=[[sum(count(integers.i)) AS count(integers.i)]] |
| | MergeScan [is_placeholder=false, input=Aggregate: groupBy=[[]], aggr=[[count(integers.i)]] |
| | TableScan: integers] |
| physical_plan | AggregateExec: mode=Final, gby=[], aggr=[count(integers.i)] |
| | CoalescePartitionsExec |
| | AggregateExec: mode=Partial, gby=[], aggr=[count(integers.i)] |
| | MergeScanExec: peers=[4398046511104(1024, 0), 4398046511105(1024, 1), 4398046511106(1024, 2), ] |
| | |
+---------------+-------------------------------------------------------------------------------------------------------+
EXPLAIN SELECT
ts,
count(i)
FROM
integers
GROUP BY
ts;
+---------------+---------------------------------------------------------------------------------------------------------+
| plan_type | plan |
+---------------+---------------------------------------------------------------------------------------------------------+
| logical_plan | Aggregate: groupBy=[[integers.ts]], aggr=[[sum(count(integers.i)) AS count(integers.i)]] |
| | MergeScan [is_placeholder=false, input=Aggregate: groupBy=[[integers.ts]], aggr=[[count(integers.i)]] |
| | TableScan: integers] |
| physical_plan | AggregateExec: mode=FinalPartitioned, gby=[ts@0 as ts], aggr=[count(integers.i)] |
| | CoalesceBatchesExec: target_batch_size=8192 |
| | RepartitionExec: partitioning=Hash([ts@0], 20), input_partitions=20 |
| | AggregateExec: mode=Partial, gby=[ts@0 as ts], aggr=[count(integers.i)] |
| | MergeScanExec: peers=[4398046511104(1024, 0), 4398046511105(1024, 1), 4398046511106(1024, 2), ] |
| | |
+---------------+---------------------------------------------------------------------------------------------------------+
EXPLAIN SELECT
date_bin('1 hour'::INTERVAL, ts),
count(i)
FROM
integers
GROUP BY
date_bin('1 hour'::INTERVAL, ts);
+---------------+-------------------------------------------------------------------------------------------------------------------------------------------------------------------+
| plan_type | plan |
+---------------+-------------------------------------------------------------------------------------------------------------------------------------------------------------------+
| logical_plan | Aggregate: groupBy=[[date_bin(Utf8("1 hour"),integers.ts) AS date_bin(Utf8("1 hour"),integers.ts)]], aggr=[[sum(count(integers.i)) AS count(integers.i)]] |
| | MergeScan [is_placeholder=false, input=Aggregate: groupBy=[[date_bin(CAST(Utf8("1 hour") AS Interval(MonthDayNano)), integers.ts)]], aggr=[[count(integers.i)]] |
| | TableScan: integers] |
| physical_plan | AggregateExec: mode=FinalPartitioned, gby=[date_bin(Utf8("1 hour"),integers.ts)@0 as date_bin(Utf8("1 hour"),integers.ts)], aggr=[count(integers.i)] |
| | CoalesceBatchesExec: target_batch_size=8192 |
| | RepartitionExec: partitioning=Hash([date_bin(Utf8("1 hour"),integers.ts)@0], 20), input_partitions=20 |
| | AggregateExec: mode=Partial, gby=[date_bin(Utf8("1 hour"),integers.ts)@0 as date_bin(Utf8("1 hour"),integers.ts)], aggr=[count(integers.i)] |
| | MergeScanExec: peers=[4398046511104(1024, 0), 4398046511105(1024, 1), 4398046511106(1024, 2), ] |
| | |
+---------------+-------------------------------------------------------------------------------------------------------------------------------------------------------------------+
DROP TABLE integers;
Affected Rows: 0

View File

@@ -0,0 +1,34 @@
CREATE TABLE integers(
host STRING,
i BIGINT,
ts TIMESTAMP TIME INDEX
) PARTITION ON COLUMNS (host) (
host < '550-A',
host >= '550-A'
AND host < '550-W',
host >= '550-W'
);
-- count
EXPLAIN SELECT
count(i)
FROM
integers;
EXPLAIN SELECT
ts,
count(i)
FROM
integers
GROUP BY
ts;
EXPLAIN SELECT
date_bin('1 hour'::INTERVAL, ts),
count(i)
FROM
integers
GROUP BY
date_bin('1 hour'::INTERVAL, ts);
DROP TABLE integers;