查询优化简明指南

-- 创建具有推断 schema 的表
CREATE TABLE trips_small_inferred
ORDER BY () EMPTY
AS SELECT * FROM s3('https://datasets-documentation.s3.eu-west-3.amazonaws.com/nyc-taxi/clickhouse-academy/nyc_taxi_2009-2010.parquet');

-- 将数据插入具有推断 schema 的表
INSERT INTO trips_small_inferred
SELECT *
FROM s3Cluster
('default','https://datasets-documentation.s3.eu-west-3.amazonaws.com/nyc-taxi/clickhouse-academy/nyc_taxi_2009-2010.parquet');

--- 显示推断出的表 schema
SHOW CREATE TABLE trips_small_inferred

Query id: d97361fd-c050-478e-b831-369469f0784d

CREATE TABLE nyc_taxi.trips_small_inferred
(
    `vendor_id` Nullable(String),
    `pickup_datetime` Nullable(DateTime64(6, 'UTC')),
    `dropoff_datetime` Nullable(DateTime64(6, 'UTC')),
    `passenger_count` Nullable(Int64),
    `trip_distance` Nullable(Float64),
    `ratecode_id` Nullable(String),
    `pickup_location_id` Nullable(String),
    `dropoff_location_id` Nullable(String),
    `payment_type` Nullable(Int64),
    `fare_amount` Nullable(Float64),
    `extra` Nullable(Float64),
    `mta_tax` Nullable(Float64),
    `tip_amount` Nullable(Float64),
    `tolls_amount` Nullable(Float64),
    `total_amount` Nullable(Float64)
)
ORDER BY tuple()

-- 查找过去 1 小时内 nyc_taxi 数据库中耗时最长的前 5 条查询
SELECT
    type,
    event_time,
    query_duration_ms,
    query,
    read_rows,
    tables
FROM clusterAllReplicas(default, system.query_log)
WHERE has(databases, 'nyc_taxi') AND (event_time >= (now() - toIntervalMinute(60))) AND type='QueryFinish'
ORDER BY query_duration_ms DESC
LIMIT 5
FORMAT VERTICAL

Query id: e3d48c9f-32bb-49a4-8303-080f59ed1835

Row 1:
──────
type:              QueryFinish
event_time:        2024-11-27 11:12:36
query_duration_ms: 2967
query:             WITH
  dateDiff('s', pickup_datetime, dropoff_datetime) as trip_time,
  trip_distance / trip_time * 3600 AS speed_mph
SELECT
  quantiles(0.5, 0.75, 0.9, 0.99)(trip_distance)
FROM
  nyc_taxi.trips_small_inferred
WHERE
  speed_mph > 30
FORMAT JSON
read_rows:         329044175
tables:            ['nyc_taxi.trips_small_inferred']

Row 2:
──────
type:              QueryFinish
event_time:        2024-11-27 11:11:33
query_duration_ms: 2026
query:             SELECT
    payment_type,
    COUNT() AS trip_count,
    formatReadableQuantity(SUM(trip_distance)) AS total_distance,
    AVG(total_amount) AS total_amount_avg,
    AVG(tip_amount) AS tip_amount_avg
FROM
    nyc_taxi.trips_small_inferred
WHERE
    pickup_datetime >= '2009-01-01' AND pickup_datetime < '2009-04-01'
GROUP BY
    payment_type
ORDER BY
    trip_count DESC;

read_rows:         329044175
tables:            ['nyc_taxi.trips_small_inferred']

Row 3:
──────
type:              QueryFinish
event_time:        2024-11-27 11:12:17
query_duration_ms: 1860
query:             SELECT
  avg(dateDiff('s', pickup_datetime, dropoff_datetime))
FROM nyc_taxi.trips_small_inferred
WHERE passenger_count = 1 or passenger_count = 2
FORMAT JSON
read_rows:         329044175
tables:            ['nyc_taxi.trips_small_inferred']

Row 4:
──────
type:              QueryFinish
event_time:        2024-11-27 11:12:31
query_duration_ms: 690
query:             SELECT avg(total_amount) FROM nyc_taxi.trips_small_inferred WHERE trip_distance > 5
FORMAT JSON
read_rows:         329044175
tables:            ['nyc_taxi.trips_small_inferred']

Row 5:
──────
type:              QueryFinish
event_time:        2024-11-27 11:12:44
query_duration_ms: 634
query:             SELECT
vendor_id,
avg(total_amount),
avg(trip_distance),
FROM
nyc_taxi.trips_small_inferred
GROUP BY vendor_id
ORDER BY 1 DESC
FORMAT JSON
read_rows:         329044175
tables:            ['nyc_taxi.trips_small_inferred']

-- 按内存使用量排序的热门查询
SELECT
    type,
    event_time,
    query_id,
    formatReadableSize(memory_usage) AS memory,
    ProfileEvents.Values[indexOf(ProfileEvents.Names, 'UserTimeMicroseconds')] AS userCPU,
    ProfileEvents.Values[indexOf(ProfileEvents.Names, 'SystemTimeMicroseconds')] AS systemCPU,
    (ProfileEvents['CachedReadBufferReadFromCacheMicroseconds']) / 1000000 AS FromCacheSeconds,
    (ProfileEvents['CachedReadBufferReadFromSourceMicroseconds']) / 1000000 AS FromSourceSeconds,
    normalized_query_hash
FROM clusterAllReplicas(default, system.query_log)
WHERE has(databases, 'nyc_taxi') AND (type='QueryFinish') AND ((event_time >= (now() - toIntervalDay(2))) AND (event_time <= now())) AND (user NOT ILIKE '%internal%')
ORDER BY memory_usage DESC
LIMIT 30

-- 禁用文件系统缓存
set enable_filesystem_cache = 0;

-- 运行查询 1
WITH
  dateDiff('s', pickup_datetime, dropoff_datetime) as trip_time,
  trip_distance / trip_time * 3600 AS speed_mph
SELECT
  quantiles(0.5, 0.75, 0.9, 0.99)(trip_distance)
FROM
  nyc_taxi.trips_small_inferred
WHERE
  speed_mph > 30
FORMAT JSON

----

1 row in set. Elapsed: 1.699 sec. Processed 329.04 million rows, 8.88 GB (193.72 million rows/s., 5.23 GB/s.)
峰值内存占用: 440.24 MiB.

-- 运行查询 2
SELECT
    payment_type,
    COUNT() AS trip_count,
    formatReadableQuantity(SUM(trip_distance)) AS total_distance,
    AVG(total_amount) AS total_amount_avg,
    AVG(tip_amount) AS tip_amount_avg
FROM
    nyc_taxi.trips_small_inferred
WHERE
    pickup_datetime >= '2009-01-01' AND pickup_datetime < '2009-04-01'
GROUP BY
    payment_type
ORDER BY
    trip_count DESC;

---

4 rows in set. Elapsed: 1.419 sec. Processed 329.04 million rows, 5.72 GB (231.86 million rows/s., 4.03 GB/s.)
峰值内存占用: 546.75 MiB.

-- 运行查询 3
SELECT
  avg(dateDiff('s', pickup_datetime, dropoff_datetime))
FROM nyc_taxi.trips_small_inferred
WHERE passenger_count = 1 or passenger_count = 2
FORMAT JSON

---

1 row in set. Elapsed: 1.414 sec. Processed 329.04 million rows, 8.88 GB (232.63 million rows/s., 6.28 GB/s.)
峰值内存占用: 451.53 MiB.

-- 统计表中的行数
SELECT count()
FROM nyc_taxi.trips_small_inferred

Query id: 733372c5-deaf-4719-94e3-261540933b23

   ┌───count()─┐
1. │ 329044175 │ -- 3.2904 亿
   └───────────┘

EXPLAIN indexes = 1
WITH
    dateDiff('s', pickup_datetime, dropoff_datetime) AS trip_time,
    (trip_distance / trip_time) * 3600 AS speed_mph
SELECT quantiles(0.5, 0.75, 0.9, 0.99)(trip_distance)
FROM nyc_taxi.trips_small_inferred
WHERE speed_mph > 30

Query id: f35c412a-edda-4089-914b-fa1622d69868

   ┌─explain─────────────────────────────────────────────┐
1. │ Expression ((Projection + Before ORDER BY))         │
2. │   Aggregating                                       │
3. │     Expression (Before GROUP BY)                    │
4. │       Filter (WHERE)                                │
5. │         ReadFromMergeTree (nyc_taxi.trips_small_inferred) │
   └─────────────────────────────────────────────────────┘

EXPLAIN PIPELINE
WITH
    dateDiff('s', pickup_datetime, dropoff_datetime) AS trip_time,
    (trip_distance / trip_time) * 3600 AS speed_mph
SELECT quantiles(0.5, 0.75, 0.9, 0.99)(trip_distance)
FROM nyc_taxi.trips_small_inferred
WHERE speed_mph > 30

Query id: c7e11e7b-d970-4e35-936c-ecfc24e3b879

    ┌─explain─────────────────────────────────────────────────────────────────────────────┐
 1. │ (Expression)                                                                        │
 2. │ ExpressionTransform × 59                                                            │
 3. │   (Aggregating)                                                                     │
 4. │   Resize 59 → 59                                                                    │
 5. │     AggregatingTransform × 59                                                       │
 6. │       StrictResize 59 → 59                                                          │
 7. │         (Expression)                                                                │
 8. │         ExpressionTransform × 59                                                    │
 9. │           (Filter)                                                                  │
10. │           FilterTransform × 59                                                      │
11. │             (ReadFromMergeTree)                                                     │
12. │             MergeTreeSelect(pool: PrefetchedReadPool, algorithm: Thread) × 59 0 → 1 │

-- 查找含空值的列
SELECT
    countIf(vendor_id IS NULL) AS vendor_id_nulls,
    countIf(pickup_datetime IS NULL) AS pickup_datetime_nulls,
    countIf(dropoff_datetime IS NULL) AS dropoff_datetime_nulls,
    countIf(passenger_count IS NULL) AS passenger_count_nulls,
    countIf(trip_distance IS NULL) AS trip_distance_nulls,
    countIf(fare_amount IS NULL) AS fare_amount_nulls,
    countIf(mta_tax IS NULL) AS mta_tax_nulls,
    countIf(tip_amount IS NULL) AS tip_amount_nulls,
    countIf(tolls_amount IS NULL) AS tolls_amount_nulls,
    countIf(total_amount IS NULL) AS total_amount_nulls,
    countIf(payment_type IS NULL) AS payment_type_nulls,
    countIf(pickup_location_id IS NULL) AS pickup_location_id_nulls,
    countIf(dropoff_location_id IS NULL) AS dropoff_location_id_nulls
FROM trips_small_inferred
FORMAT VERTICAL

Query id: 4a70fc5b-2501-41c8-813c-45ce241d85ae

Row 1:
──────
vendor_id_nulls:           0
pickup_datetime_nulls:     0
dropoff_datetime_nulls:    0
passenger_count_nulls:     0
trip_distance_nulls:       0
fare_amount_nulls:         0
mta_tax_nulls:             137946731
tip_amount_nulls:          0
tolls_amount_nulls:        0
total_amount_nulls:        0
payment_type_nulls:        69305
pickup_location_id_nulls:  0
dropoff_location_id_nulls: 0

-- 识别低基数列
SELECT
    uniq(ratecode_id),
    uniq(pickup_location_id),
    uniq(dropoff_location_id),
    uniq(vendor_id)
FROM trips_small_inferred
FORMAT VERTICAL

查询 id: d502c6a1-c9bc-4415-9d86-5de74dd6d932

行 1:
──────
uniq(ratecode_id):         6
uniq(pickup_location_id):  260
uniq(dropoff_location_id): 260
uniq(vendor_id):           3

-- 查找 payment_type 字段的最小值/最大值
SELECT
    min(payment_type),max(payment_type),
    min(passenger_count), max(passenger_count)
FROM trips_small_inferred

Query id: 4306a8e1-2a9c-4b06-97b4-4d902d2233eb

   ┌─min(payment_type)─┬─max(payment_type)─┐
1. │                 1 │                 4 │
   └───────────────────┴───────────────────┘

-- 创建使用优化数据结构的表
CREATE TABLE trips_small_no_pk
(
    `vendor_id` LowCardinality(String),
    `pickup_datetime` DateTime,
    `dropoff_datetime` DateTime,
    `passenger_count` UInt8,
    `trip_distance` Float32,
    `ratecode_id` LowCardinality(String),
    `pickup_location_id` LowCardinality(String),
    `dropoff_location_id` LowCardinality(String),
    `payment_type` Nullable(UInt8),
    `fare_amount` Decimal32(2),
    `extra` Decimal32(2),
    `mta_tax` Nullable(Decimal32(2)),
    `tip_amount` Decimal32(2),
    `tolls_amount` Decimal32(2),
    `total_amount` Decimal32(2)
)
ORDER BY tuple();

-- 插入数据
INSERT INTO trips_small_no_pk SELECT * FROM trips_small_inferred

SELECT
    `table`,
    formatReadableSize(sum(data_compressed_bytes) AS size) AS compressed,
    formatReadableSize(sum(data_uncompressed_bytes) AS usize) AS uncompressed,
    sum(rows) AS rows
FROM system.parts
WHERE (active = 1) AND ((`table` = 'trips_small_no_pk') OR (`table` = 'trips_small_inferred'))
GROUP BY
    database,
    `table`
ORDER BY size DESC

Query id: 72b5eb1c-ff33-4fdb-9d29-dd076ac6f532

   ┌─table────────────────┬─compressed─┬─uncompressed─┬──────rows─┐
1. │ trips_small_inferred │ 7.38 GiB   │ 37.41 GiB    │ 329044175 │
2. │ trips_small_no_pk    │ 4.89 GiB   │ 15.31 GiB    │ 329044175 │
   └──────────────────────┴────────────┴──────────────┴───────────┘

CREATE TABLE trips_small_pk
(
    `vendor_id` UInt8,
    `pickup_datetime` DateTime,
    `dropoff_datetime` DateTime,
    `passenger_count` UInt8,
    `trip_distance` Float32,
    `ratecode_id` LowCardinality(String),
    `pickup_location_id` UInt16,
    `dropoff_location_id` UInt16,
    `payment_type` Nullable(UInt8),
    `fare_amount` Decimal32(2),
    `extra` Decimal32(2),
    `mta_tax` Nullable(Decimal32(2)),
    `tip_amount` Decimal32(2),
    `tolls_amount` Decimal32(2),
    `total_amount` Decimal32(2)
)
PRIMARY KEY (passenger_count, pickup_datetime, dropoff_datetime);

-- 插入数据
INSERT INTO trips_small_pk SELECT * FROM trips_small_inferred

EXPLAIN indexes = 1
SELECT
    payment_type,
    COUNT() AS trip_count,
    formatReadableQuantity(SUM(trip_distance)) AS total_distance,
    AVG(total_amount) AS total_amount_avg,
    AVG(tip_amount) AS tip_amount_avg
FROM nyc_taxi.trips_small_pk
WHERE (pickup_datetime >= '2009-01-01') AND (pickup_datetime < '2009-04-01')
GROUP BY payment_type
ORDER BY trip_count DESC

Query id: 30116a77-ba86-4e9f-a9a2-a01670ad2e15

    ┌─explain──────────────────────────────────────────────────────────────────────────────────────────────────────────┐
 1. │ Expression ((Projection + Before ORDER BY [lifted up part]))                                                     │
 2. │   Sorting (Sorting for ORDER BY)                                                                                 │
 3. │     Expression (Before ORDER BY)                                                                                 │
 4. │       Aggregating                                                                                                │
 5. │         Expression (Before GROUP BY)                                                                             │
 6. │           Expression                                                                                             │
 7. │             ReadFromMergeTree (nyc_taxi.trips_small_pk)                                                          │
 8. │             Indexes:                                                                                             │
 9. │               PrimaryKey                                                                                         │
10. │                 Keys:                                                                                            │
11. │                   pickup_datetime                                                                                │
12. │                 Condition: and((pickup_datetime in (-Inf, 1238543999]), (pickup_datetime in [1230768000, +Inf))) │
13. │                 Parts: 9/9                                                                                       │
14. │                 Granules: 5061/40167                                                                             │
    └──────────────────────────────────────────────────────────────────────────────────────────────────────────────────┘