timeSeriesLastTwoSamples

도입 버전: v25.6.0 PromQL과 유사한 irate 및 idelta 계산을 위해 시계열 데이터를 리샘플링하는 집계 함수입니다. 이 집계 함수는 시계열 데이터를 타임스탬프와 값의 쌍으로 받아 최대 2개의 최신 샘플만 저장합니다. 이 집계 함수는 그리드에 정렬된 타임스탬프에 대해 리샘플링된 시계열 데이터를 저장하는 구체화된 뷰(Materialized View) 및 집계 테이블과 함께 사용하도록 설계되었습니다. 집계 테이블은 각 정렬된 타임스탬프에 대해 마지막 2개의 값만 저장합니다. 따라서 원시 테이블에 저장된 데이터보다 훨씬 적은 데이터만 읽고도 PromQL과 유사한 irate 및 idelta를 계산할 수 있습니다.

이 함수는 실험적 기능이므로 allow_experimental_ts_to_grid_aggregate_function=true를 설정하여 활성화하십시오.

구문

timeSeriesLastTwoSamples(timestamp, value)

인수

timestamp — 샘플의 타임스탬프입니다. DateTime 또는 DateTime64 또는 (U)Int* 또는 Int*
value — 해당 타임스탬프에 대응하는 시계열 값입니다. Float32 또는 Float64

반환 값 길이가 0~2인 동일 길이의 배열 쌍을 반환합니다. 첫 번째 배열에는 샘플링된 시계열의 타임스탬프가 들어 있고, 두 번째 배열에는 이에 대응하는 시계열 값이 들어 있습니다. Tuple(Array(DateTime), Array(Float64)) 예시 원시 데이터용 예시 테이블과 리샘플링된 데이터를 저장하기 위한 테이블

Query

SET allow_experimental_time_series_aggregate_functions = 1;
-- Table for raw data
CREATE TABLE t_raw_timeseries
(
    metric_id UInt64,
    timestamp DateTime64(3, 'UTC') CODEC(DoubleDelta, ZSTD),
    value Float64 CODEC(DoubleDelta)
)
ENGINE = MergeTree()
ORDER BY (metric_id, timestamp);

-- Table with data re-sampled to bigger (15 sec) time steps
CREATE TABLE t_resampled_timeseries_15_sec
(
    metric_id UInt64,
    grid_timestamp DateTime('UTC') CODEC(DoubleDelta, ZSTD), -- Timestamp aligned to 15 sec
    samples AggregateFunction(timeSeriesLastTwoSamples, DateTime64(3, 'UTC'), Float64)
)
ENGINE = AggregatingMergeTree()
ORDER BY (metric_id, grid_timestamp);

-- MV for populating re-sampled table
CREATE MATERIALIZED VIEW mv_resampled_timeseries TO t_resampled_timeseries_15_sec
(
    metric_id UInt64,
    grid_timestamp DateTime('UTC') CODEC(DoubleDelta, ZSTD),
    samples AggregateFunction(timeSeriesLastTwoSamples, DateTime64(3, 'UTC'), Float64)
)
AS SELECT
    metric_id,
    ceil(toUnixTimestamp(timestamp + interval 999 millisecond) / 15, 0) * 15 AS grid_timestamp, -- Round timestamp up to the next grid point
    initializeAggregation('timeSeriesLastTwoSamplesState', timestamp, value) AS samples
FROM t_raw_timeseries
ORDER BY metric_id, grid_timestamp;

-- Insert some data
INSERT INTO t_raw_timeseries(metric_id, timestamp, value) SELECT number%10 AS metric_id, '2024-12-12 12:00:00'::DateTime64(3, 'UTC') + interval ((number/10)%100)*900 millisecond as timestamp, number%3+number%29 AS value FROM numbers(1000);

-- Check raw data
SELECT *
FROM t_raw_timeseries
WHERE metric_id = 3 AND timestamp BETWEEN '2024-12-12 12:00:12' AND '2024-12-12 12:00:31'
ORDER BY metric_id, timestamp;

Response

  2024-12-12 12:00:12.870    29
  2024-12-12 12:00:13.770    8
  2024-12-12 12:00:14.670    19
  2024-12-12 12:00:15.570    30
  2024-12-12 12:00:16.470    9
  2024-12-12 12:00:17.370    20
  2024-12-12 12:00:18.270    2
  2024-12-12 12:00:19.170    10
  2024-12-12 12:00:20.070    21
  2024-12-12 12:00:20.970    3
  2024-12-12 12:00:21.870    11
  2024-12-12 12:00:22.770    22
  2024-12-12 12:00:23.670    4
  2024-12-12 12:00:24.570    12
  2024-12-12 12:00:25.470    23
  2024-12-12 12:00:26.370    5
  2024-12-12 12:00:27.270    13
  2024-12-12 12:00:28.170    24
  2024-12-12 12:00:29.069    6
  2024-12-12 12:00:29.969    14
  2024-12-12 12:00:30.869    25

타임스탬프 ‘2024-12-12 12:00:15’ 및 ‘2024-12-12 12:00:30’의 마지막 2개 샘플 쿼리

Query

SET allow_experimental_time_series_aggregate_functions = 1;
-- Table for raw data
CREATE TABLE t_raw_timeseries
(
    metric_id UInt64,
    timestamp DateTime64(3, 'UTC') CODEC(DoubleDelta, ZSTD),
    value Float64 CODEC(DoubleDelta)
)
ENGINE = MergeTree()
ORDER BY (metric_id, timestamp);

-- Table with data re-sampled to bigger (15 sec) time steps
CREATE TABLE t_resampled_timeseries_15_sec
(
    metric_id UInt64,
    grid_timestamp DateTime('UTC') CODEC(DoubleDelta, ZSTD), -- Timestamp aligned to 15 sec
    samples AggregateFunction(timeSeriesLastTwoSamples, DateTime64(3, 'UTC'), Float64)
)
ENGINE = AggregatingMergeTree()
ORDER BY (metric_id, grid_timestamp);

-- MV for populating re-sampled table
CREATE MATERIALIZED VIEW mv_resampled_timeseries TO t_resampled_timeseries_15_sec
(
    metric_id UInt64,
    grid_timestamp DateTime('UTC') CODEC(DoubleDelta, ZSTD),
    samples AggregateFunction(timeSeriesLastTwoSamples, DateTime64(3, 'UTC'), Float64)
)
AS SELECT
    metric_id,
    ceil(toUnixTimestamp(timestamp + interval 999 millisecond) / 15, 0) * 15 AS grid_timestamp, -- Round timestamp up to the next grid point
    initializeAggregation('timeSeriesLastTwoSamplesState', timestamp, value) AS samples
FROM t_raw_timeseries
ORDER BY metric_id, grid_timestamp;

-- Insert some data
INSERT INTO t_raw_timeseries(metric_id, timestamp, value) SELECT number%10 AS metric_id, '2024-12-12 12:00:00'::DateTime64(3, 'UTC') + interval ((number/10)%100)*900 millisecond as timestamp, number%3+number%29 AS value FROM numbers(1000);

-- Check re-sampled data
SELECT metric_id, grid_timestamp, (finalizeAggregation(samples).1 as timestamp, finalizeAggregation(samples).2 as value)
FROM t_resampled_timeseries_15_sec
WHERE metric_id = 3 AND grid_timestamp BETWEEN '2024-12-12 12:00:15' AND '2024-12-12 12:00:30'
ORDER BY metric_id, grid_timestamp;

Response

3    2024-12-12 12:00:15    (['2024-12-12 12:00:14.670','2024-12-12 12:00:13.770'],[19,8])
3    2024-12-12 12:00:30    (['2024-12-12 12:00:29.969','2024-12-12 12:00:29.069'],[14,6])

원시 데이터로부터 idelta 및 irate 계산

Query

SET allow_experimental_time_series_aggregate_functions = 1;
-- Table for raw data
CREATE TABLE t_raw_timeseries
(
    metric_id UInt64,
    timestamp DateTime64(3, 'UTC') CODEC(DoubleDelta, ZSTD),
    value Float64 CODEC(DoubleDelta)
)
ENGINE = MergeTree()
ORDER BY (metric_id, timestamp);

-- Insert some data
INSERT INTO t_raw_timeseries(metric_id, timestamp, value) SELECT number%10 AS metric_id, '2024-12-12 12:00:00'::DateTime64(3, 'UTC') + interval ((number/10)%100)*900 millisecond as timestamp, number%3+number%29 AS value FROM numbers(1000);

-- The aggregated table stores only last 2 values for each 15-second aligned timestamp.
-- This allows to calculate PromQL-like irate and idelta by reading much less data then is stored in the raw table.

WITH
    '2024-12-12 12:00:15'::DateTime64(3,'UTC') AS start_ts,       -- start of timestamp grid
    start_ts + INTERVAL 60 SECOND AS end_ts,   -- end of timestamp grid
    15 AS step_seconds,   -- step of timestamp grid
    45 AS window_seconds  -- "staleness" window
SELECT
    metric_id,
    timeSeriesInstantDeltaToGrid(start_ts, end_ts, step_seconds, window_seconds)(timestamp, value),
    timeSeriesInstantRateToGrid(start_ts, end_ts, step_seconds, window_seconds)(timestamp, value)
FROM t_raw_timeseries
WHERE metric_id = 3 AND timestamp BETWEEN start_ts - interval window_seconds seconds AND end_ts
GROUP BY metric_id;

Response

3    [11,8,-18,8,11]    [12.222222222222221,8.88888888888889,1.1111111111111112,8.88888888888889,12.222222222222221]

리샘플링된 데이터에서 idelta 및 irate 계산

Query

SET allow_experimental_time_series_aggregate_functions = 1;
-- Table for raw data
CREATE TABLE t_raw_timeseries
(
    metric_id UInt64,
    timestamp DateTime64(3, 'UTC') CODEC(DoubleDelta, ZSTD),
    value Float64 CODEC(DoubleDelta)
)
ENGINE = MergeTree()
ORDER BY (metric_id, timestamp);

-- Table with data re-sampled to bigger (15 sec) time steps
CREATE TABLE t_resampled_timeseries_15_sec
(
    metric_id UInt64,
    grid_timestamp DateTime('UTC') CODEC(DoubleDelta, ZSTD), -- Timestamp aligned to 15 sec
    samples AggregateFunction(timeSeriesLastTwoSamples, DateTime64(3, 'UTC'), Float64)
)
ENGINE = AggregatingMergeTree()
ORDER BY (metric_id, grid_timestamp);

-- MV for populating re-sampled table
CREATE MATERIALIZED VIEW mv_resampled_timeseries TO t_resampled_timeseries_15_sec
(
    metric_id UInt64,
    grid_timestamp DateTime('UTC') CODEC(DoubleDelta, ZSTD),
    samples AggregateFunction(timeSeriesLastTwoSamples, DateTime64(3, 'UTC'), Float64)
)
AS SELECT
    metric_id,
    ceil(toUnixTimestamp(timestamp + interval 999 millisecond) / 15, 0) * 15 AS grid_timestamp, -- Round timestamp up to the next grid point
    initializeAggregation('timeSeriesLastTwoSamplesState', timestamp, value) AS samples
FROM t_raw_timeseries
ORDER BY metric_id, grid_timestamp;

-- Insert some data
INSERT INTO t_raw_timeseries(metric_id, timestamp, value) SELECT number%10 AS metric_id, '2024-12-12 12:00:00'::DateTime64(3, 'UTC') + interval ((number/10)%100)*900 millisecond as timestamp, number%3+number%29 AS value FROM numbers(1000);

WITH
    '2024-12-12 12:00:15'::DateTime64(3,'UTC') AS start_ts,       -- start of timestamp grid
    start_ts + INTERVAL 60 SECOND AS end_ts,   -- end of timestamp grid
    15 AS step_seconds,   -- step of timestamp grid
    45 AS window_seconds  -- "staleness" window
SELECT
    metric_id,
    timeSeriesInstantDeltaToGrid(start_ts, end_ts, step_seconds, window_seconds)(timestamps, values),
    timeSeriesInstantRateToGrid(start_ts, end_ts, step_seconds, window_seconds)(timestamps, values)
FROM (
    SELECT
        metric_id,
        finalizeAggregation(samples).1 AS timestamps,
        finalizeAggregation(samples).2 AS values
    FROM t_resampled_timeseries_15_sec
    WHERE metric_id = 3 AND grid_timestamp BETWEEN start_ts - interval window_seconds seconds AND end_ts
)
GROUP BY metric_id;

Response

3    [11,8,-18,8,11]    [12.222222222222221,8.88888888888889,1.1111111111111112,8.88888888888889,12.222222222222221]

​timeSeriesLastTwoSamples

timeSeriesLastTwoSamples