Управление данными

CREATE TABLE default.otel_logs
(
...
)
ENGINE = MergeTree
PARTITION BY toDate(Timestamp)
ORDER BY (ServiceName, SeverityText, toUnixTimestamp(Timestamp), TraceId)

SELECT Timestamp::Date AS day,
         count() AS c
FROM otel_logs
GROUP BY day
ORDER BY c DESC

┌────────day─┬───────c─┐
│ 2019-01-22 │ 2333977 │
│ 2019-01-23 │ 2326694 │
│ 2019-01-26 │ 1986456 │
│ 2019-01-24 │ 1896255 │
│ 2019-01-25 │ 1821770 │
└────────────┴─────────┘

5 rows in set. Elapsed: 0.058 sec. Processed 10.37 million rows, 82.92 MB (177.96 million rows/s., 1.42 GB/s.)
Пиковое потребление памяти: 4.41 MiB.

SELECT DISTINCT partition
FROM system.parts
WHERE `table` = 'otel_logs'

┌─partition──┐
│ 2019-01-22 │
│ 2019-01-23 │
│ 2019-01-24 │
│ 2019-01-25 │
│ 2019-01-26 │
└────────────┘

5 rows in set. Elapsed: 0.005 sec.

CREATE TABLE otel_logs_archive AS otel_logs
--переместить данные в архивную таблицу
ALTER TABLE otel_logs
        (MOVE PARTITION tuple('2019-01-26') TO TABLE otel_logs_archive
--убедиться, что данные перемещены
SELECT
        Timestamp::Date AS day,
        count() AS c
FROM otel_logs
GROUP BY day
ORDER BY c DESC

┌────────day─┬───────c─┐
│ 2019-01-22 │ 2333977 │
│ 2019-01-23 │ 2326694 │
│ 2019-01-24 │ 1896255 │
│ 2019-01-25 │ 1821770 │
└────────────┴─────────┘

4 rows in set. Elapsed: 0.051 sec. Processed 8.38 million rows, 67.03 MB (163.52 million rows/s., 1.31 GB/s.)
потребление памяти: 4.40 MiB.

SELECT Timestamp::Date AS day,
        count() AS c
FROM otel_logs_archive
GROUP BY day
ORDER BY c DESC

┌────────day─┬───────c─┐
│ 2019-01-26 │ 1986456 │
└────────────┴─────────┘

1 строка в наборе. Elapsed: 0.024 sec. Processed 1.99 million rows, 15.89 MB (83.86 million rows/s., 670.87 MB/s.)
потребление памяти: 4.99 MiB.

ALTER TABLE otel_logs
        (DROP PARTITION tuple('2019-01-25'))

SELECT
        Timestamp::Date AS day,
        count() AS c
FROM otel_logs
GROUP BY day
ORDER BY c DESC

┌────────day─┬───────c─┐
│ 2019-01-22 │ 4667954 │
│ 2019-01-23 │ 4653388 │
│ 2019-01-24 │ 3792510 │
└────────────┴─────────┘

exporters:
 clickhouse:
   endpoint: tcp://localhost:9000?dial_timeout=10s&compress=lz4&async_insert=1
   ttl: 72h

PARTITION BY toDate(Timestamp)
ORDER BY (ServiceName, SpanName, toUnixTimestamp(Timestamp), TraceId)
TTL toDateTime(Timestamp) + toIntervalDay(4)
SETTINGS ttl_only_drop_parts = 1

CREATE TABLE otel_logs_v2
(
        `Body` String TTL Timestamp + INTERVAL 30 DAY,
        `Timestamp` DateTime,
        ...
)
ENGINE = MergeTree
ORDER BY (ServiceName, Timestamp)

CREATE TABLE default.otel_logs_v2
(
        `Body` String,
        `Timestamp` DateTime,
        `ServiceName` LowCardinality(String),
        `Status` UInt16,
        `RequestProtocol` LowCardinality(String),
        `RunTime` UInt32,
        `Size` UInt32,
        `UserAgent` String,
        `Referer` String,
        `RemoteUser` String,
        `RequestType` LowCardinality(String),
        `RequestPath` String,
        `RemoteAddress` IPv4,
        `RefererDomain` String,
        `RequestPage` String,
        `SeverityText` LowCardinality(String),
        `SeverityNumber` UInt8,
)
ENGINE = MergeTree
ORDER BY (ServiceName, Timestamp)
TTL Timestamp + INTERVAL 4 DAY RECOMPRESS CODEC(ZSTD(3))

CREATE TABLE default.otel_logs_v2
(
        `Body` String,
        `Timestamp` DateTime,
        `ServiceName` LowCardinality(String),
        `Status` UInt16,
        `RequestProtocol` LowCardinality(String),
        `RunTime` UInt32,
        `UserAgent` String,
        `Referer` String,
        `RemoteUser` String,
        `RequestType` LowCardinality(String),
        `RequestPath` String,
        `RemoteAddress` IPv4,
        `RefererDomain` String,
        `RequestPage` String,
        `SeverityText` LowCardinality(String),
        `SeverityNumber` UInt8
)
ENGINE = MergeTree
ORDER BY (ServiceName, Timestamp)

CREATE MATERIALIZED VIEW otel_logs_mv TO otel_logs_v2 AS
SELECT
        Body,
        Timestamp::DateTime AS Timestamp,
        ServiceName,
        LogAttributes['status']::UInt16 AS Status,
        LogAttributes['request_protocol'] AS RequestProtocol,
        LogAttributes['run_time'] AS RunTime,
        LogAttributes['user_agent'] AS UserAgent,
        LogAttributes['referer'] AS Referer,
        LogAttributes['remote_user'] AS RemoteUser,
        LogAttributes['request_type'] AS RequestType,
        LogAttributes['request_path'] AS RequestPath,
        LogAttributes['remote_addr'] AS RemoteAddress,
        domain(LogAttributes['referer']) AS RefererDomain,
        path(LogAttributes['request_path']) AS RequestPage,
        multiIf(Status::UInt64 > 500, 'CRITICAL', Status::UInt64 > 400, 'ERROR', Status::UInt64 > 300, 'WARNING', 'INFO') AS SeverityText,
        multiIf(Status::UInt64 > 500, 20, Status::UInt64 > 400, 17, Status::UInt64 > 300, 13, 9) AS SeverityNumber
FROM otel_logs

ALTER TABLE otel_logs_v2
        (ADD COLUMN `Size` UInt64 DEFAULT JSONExtractUInt(Body, 'size'))

SELECT Size
FROM otel_logs_v2
LIMIT 5

┌──Size─┐
│ 30577 │
│  5667 │
│  5379 │
│  1696 │
│ 41483 │
└───────┘

5 строк в наборе. Затрачено: 0.012 сек.

ALTER TABLE otel_logs_mv
        MODIFY QUERY
SELECT
        Body,
        Timestamp::DateTime AS Timestamp,
        ServiceName,
        LogAttributes['status']::UInt16 AS Status,
        LogAttributes['request_protocol'] AS RequestProtocol,
        LogAttributes['run_time'] AS RunTime,
        LogAttributes['size'] AS Size,
        LogAttributes['user_agent'] AS UserAgent,
        LogAttributes['referer'] AS Referer,
        LogAttributes['remote_user'] AS RemoteUser,
        LogAttributes['request_type'] AS RequestType,
        LogAttributes['request_path'] AS RequestPath,
        LogAttributes['remote_addr'] AS RemoteAddress,
        domain(LogAttributes['referer']) AS RefererDomain,
        path(LogAttributes['request_path']) AS RequestPage,
        multiIf(Status::UInt64 > 500, 'CRITICAL', Status::UInt64 > 400, 'ERROR', Status::UInt64 > 300,                 'WARNING', 'INFO') AS SeverityText,
        multiIf(Status::UInt64 > 500, 20, Status::UInt64 > 400, 17, Status::UInt64 > 300, 13, 9) AS SeverityNumber
FROM otel_logs

SELECT Status, count() AS c
FROM merge('otel_logs_v[2|3]')
GROUP BY Status
ORDER BY c DESC
LIMIT 5

┌─Status─┬────────c─┐
│   200  │ 38319300 │
│   304  │  1360912 │
│   302  │   799340 │
│   404  │   420044 │
│   301  │   270212 │
└────────┴──────────┘

5 rows in set. Elapsed: 0.137 sec. Processed 41.46 million rows, 82.92 MB (302.43 million rows/s., 604.85 MB/s.)

CREATE TABLE otel_logs_merged
ENGINE = Merge('default', 'otel_logs_v[2|3]')

SELECT Status, count() AS c
FROM otel_logs_merged
GROUP BY Status
ORDER BY c DESC
LIMIT 5

┌─Status─┬────────c─┐
│   200  │ 38319300 │
│   304  │  1360912 │
│   302  │   799340 │
│   404  │   420044 │
│   301  │   270212 │
└────────┴──────────┘

5 rows in set. Elapsed: 0.073 sec. Processed 41.46 million rows, 82.92 MB (565.43 million rows/s., 1.13 GB/s.)

CREATE TABLE otel_logs_merged_temp
ENGINE = Merge('default', 'otel_logs_v[2|3|4]')

EXCHANGE TABLE otel_logs_merged_temp AND otel_logs_merged

SELECT Status, count() AS c
FROM otel_logs_merged
GROUP BY Status
ORDER BY c DESC
LIMIT 5

┌─Status─┬────────c─┐
│   200  │ 39259996 │
│   304  │  1378564 │
│   302  │   820118 │
│   404  │   429220 │
│   301  │   276960 │
└────────┴──────────┘

5 rows in set. Elapsed: 0.068 sec. Processed 42.46 million rows, 84.92 MB (620.45 million rows/s., 1.24 GB/s.)