Raksta tulkojums tika sagatavots speciÄli kursa studentiem
Pirms diviem gadiem es pavadīju
ClickHouse sastÄv no 170 tÅ«kstoÅ”iem C++ koda rindiÅu, neskaitot treÅ”o puÅ”u bibliotÄkas, un tÄ ir viena no mazÄkajÄm izplatÄ«tajÄm datu bÄzes kodu bÄzÄm. SalÄ«dzinÄjumam, SQLite neatbalsta izplatÄ«Å”anu un sastÄv no 235 tÅ«kstoÅ”iem C koda rindiÅu.Å Ä« rakstÄ«Å”anas brÄ«dÄ« ClickHouse ir snieguÅ”i ieguldÄ«jumu 207 inženieri, un pÄdÄjÄ laikÄ ir palielinÄjusies saistÄ«bu intensitÄte.
2017. gada martÄ ClickHouse sÄka diriÄ£Ät
Å ajÄ rakstÄ es apskatÄ«Å”u ClickHouse klastera veiktspÄju AWS EC2, izmantojot 36 kodolu procesorus un NVMe krÄtuvi.
ATJAUNINÄJUMS: nedÄļu pÄc Ŕīs ziÅas sÄkotnÄjÄs publicÄÅ”anas es atkÄrtoti veicu testu ar uzlabotu konfigurÄciju un sasniedzu daudz labÄkus rezultÄtus. Å Ä« ziÅa ir atjauninÄta, lai atspoguļotu Ŕīs izmaiÅas.
AWS EC2 klastera palaiŔana
Å im ierakstam izmantoÅ”u trÄ«s c5d.9xlarge EC2 gadÄ«jumus. Katrs no tiem satur 36 virtuÄlos procesorus, 72 GB RAM, 900 GB NVMe SSD atmiÅas un atbalsta 10 gigabitu tÄ«klu. Tie maksÄ 1,962 USD stundÄ katrs eu-west-1 reÄ£ionÄ, ja tie darbojas pÄc pieprasÄ«juma. KÄ operÄtÄjsistÄmu izmantoÅ”u Ubuntu Server 16.04 LTS.
UgunsmÅ«ris ir konfigurÄts tÄ, lai katra maŔīna varÄtu sazinÄties viena ar otru bez ierobežojumiem, un tikai mana IPv4 adrese ir iekļauta klastera baltajÄ sarakstÄ SSH.
NVMe disks ir darba gatavÄ«bas stÄvoklÄ«
Lai ClickHouse darbotos, es izveidoÅ”u failu sistÄmu EXT4 formÄtÄ NVMe diskdzinÄ« katrÄ no serveriem.
$ sudo mkfs -t ext4 /dev/nvme1n1
$ sudo mkdir /ch
$ sudo mount /dev/nvme1n1 /ch
Kad viss ir konfigurÄts, jÅ«s varat redzÄt stiprinÄjuma punktu un 783 GB pieejamo vietu katrÄ sistÄmÄ.
$ lsblk
NAME MAJ:MIN RM SIZE RO TYPE MOUNTPOINT
loop0 7:0 0 87.9M 1 loop /snap/core/5742
loop1 7:1 0 16.5M 1 loop /snap/amazon-ssm-agent/784
nvme0n1 259:1 0 8G 0 disk
āānvme0n1p1 259:2 0 8G 0 part /
nvme1n1 259:0 0 838.2G 0 disk /ch
$ df -h
Filesystem Size Used Avail Use% Mounted on
udev 35G 0 35G 0% /dev
tmpfs 6.9G 8.8M 6.9G 1% /run
/dev/nvme0n1p1 7.7G 967M 6.8G 13% /
tmpfs 35G 0 35G 0% /dev/shm
tmpfs 5.0M 0 5.0M 0% /run/lock
tmpfs 35G 0 35G 0% /sys/fs/cgroup
/dev/loop0 88M 88M 0 100% /snap/core/5742
/dev/loop1 17M 17M 0 100% /snap/amazon-ssm-agent/784
tmpfs 6.9G 0 6.9G 0% /run/user/1000
/dev/nvme1n1 825G 73M 783G 1% /ch
Datu kopa, ko izmantoÅ”u Å”ajÄ testÄ, ir datu izgÄztuve, ko esmu Ä£enerÄjis no 1.1 miljarda taksometra braucienu Å
ujorkÄ seÅ”u gadu laikÄ. BlogÄ
$ sudo apt update
$ sudo apt install awscli
$ aws configure
Es iestatÄ«Å”u klienta vienlaicÄ«go pieprasÄ«jumu ierobežojumu lÄ«dz 100, lai faili tiktu lejupielÄdÄti ÄtrÄk nekÄ noklusÄjuma iestatÄ«jumi.
$ aws configure set
default.s3.max_concurrent_requests
100
Es lejupielÄdÄÅ”u taksometru braucienu datu kopu no AWS S3 un saglabÄÅ”u to NVMe diskdzinÄ« pirmajÄ serverÄ«. Å Ä« datu kopa ir aptuveni 104 GB GZIP saspiestÄ CSV formÄtÄ.
$ sudo mkdir -p /ch/csv
$ sudo chown -R ubuntu /ch/csv
$ aws s3 sync s3://<bucket>/csv /ch/csv
ClickHouse uzstÄdÄ«Å”ana
Es instalÄÅ”u OpenJDK izplatÄ«Å”anu Java 8, jo tas ir nepiecieÅ”ams, lai palaistu Apache ZooKeeper, kas ir nepiecieÅ”ams izplatÄ«tai ClickHouse instalÄÅ”anai visÄs trÄ«s maŔīnÄs.
$ sudo apt update
$ sudo apt install
openjdk-8-jre
openjdk-8-jdk-headless
Tad es iestatīju vides mainīgo JAVA_HOME
.
$ sudo vi /etc/profile
export JAVA_HOME=/usr
$ source /etc/profile
PÄc tam es izmantoÅ”u Ubuntu pakotÅu pÄrvaldÄ«bas sistÄmu, lai instalÄtu ClickHouse 18.16.1, glances un ZooKeeper visÄs trÄ«s iekÄrtÄs.
$ sudo apt-key adv
--keyserver hkp://keyserver.ubuntu.com:80
--recv E0C56BD4
$ echo "deb http://repo.yandex.ru/clickhouse/deb/stable/ main/" |
sudo tee /etc/apt/sources.list.d/clickhouse.list
$ sudo apt-get update
$ sudo apt install
clickhouse-client
clickhouse-server
glances
zookeeperd
Es izveidoÅ”u ClickHouse direktoriju, kÄ arÄ« veiksim dažas konfigurÄcijas ignorÄÅ”anas visos trÄ«s serveros.
$ sudo mkdir /ch/clickhouse
$ sudo chown -R clickhouse /ch/clickhouse
$ sudo mkdir -p /etc/clickhouse-server/conf.d
$ sudo vi /etc/clickhouse-server/conf.d/taxis.conf
Å Ä«s ir konfigurÄcijas ignorÄÅ”anas iespÄjas, kuras es izmantoÅ”u.
<?xml version="1.0"?>
<yandex>
<listen_host>0.0.0.0</listen_host>
<path>/ch/clickhouse/</path>
<remote_servers>
<perftest_3shards>
<shard>
<replica>
<host>172.30.2.192</host>
<port>9000</port>
</replica>
</shard>
<shard>
<replica>
<host>172.30.2.162</host>
<port>9000</port>
</replica>
</shard>
<shard>
<replica>
<host>172.30.2.36</host>
<port>9000</port>
</replica>
</shard>
</perftest_3shards>
</remote_servers>
<zookeeper-servers>
<node>
<host>172.30.2.192</host>
<port>2181</port>
</node>
<node>
<host>172.30.2.162</host>
<port>2181</port>
</node>
<node>
<host>172.30.2.36</host>
<port>2181</port>
</node>
</zookeeper-servers>
<macros>
<shard>03</shard>
<replica>01</replica>
</macros>
</yandex>
PÄc tam es palaidÄ«Å”u ZooKeeper un ClickHouse serveri visÄs trÄ«s maŔīnÄs.
$ sudo /etc/init.d/zookeeper start
$ sudo service clickhouse-server start
Datu augÅ”upielÄde pakalpojumÄ ClickHouse
PirmajÄ serverÄ« es izveidoÅ”u ceļojumu tabulu (trips
), kurÄ tiks saglabÄta taksometru braucienu datu kopa, izmantojot žurnÄla programmu.
$ clickhouse-client --host=0.0.0.0
CREATE TABLE trips (
trip_id UInt32,
vendor_id String,
pickup_datetime DateTime,
dropoff_datetime Nullable(DateTime),
store_and_fwd_flag Nullable(FixedString(1)),
rate_code_id Nullable(UInt8),
pickup_longitude Nullable(Float64),
pickup_latitude Nullable(Float64),
dropoff_longitude Nullable(Float64),
dropoff_latitude Nullable(Float64),
passenger_count Nullable(UInt8),
trip_distance Nullable(Float64),
fare_amount Nullable(Float32),
extra Nullable(Float32),
mta_tax Nullable(Float32),
tip_amount Nullable(Float32),
tolls_amount Nullable(Float32),
ehail_fee Nullable(Float32),
improvement_surcharge Nullable(Float32),
total_amount Nullable(Float32),
payment_type Nullable(String),
trip_type Nullable(UInt8),
pickup Nullable(String),
dropoff Nullable(String),
cab_type Nullable(String),
precipitation Nullable(Int8),
snow_depth Nullable(Int8),
snowfall Nullable(Int8),
max_temperature Nullable(Int8),
min_temperature Nullable(Int8),
average_wind_speed Nullable(Int8),
pickup_nyct2010_gid Nullable(Int8),
pickup_ctlabel Nullable(String),
pickup_borocode Nullable(Int8),
pickup_boroname Nullable(String),
pickup_ct2010 Nullable(String),
pickup_boroct2010 Nullable(String),
pickup_cdeligibil Nullable(FixedString(1)),
pickup_ntacode Nullable(String),
pickup_ntaname Nullable(String),
pickup_puma Nullable(String),
dropoff_nyct2010_gid Nullable(UInt8),
dropoff_ctlabel Nullable(String),
dropoff_borocode Nullable(UInt8),
dropoff_boroname Nullable(String),
dropoff_ct2010 Nullable(String),
dropoff_boroct2010 Nullable(String),
dropoff_cdeligibil Nullable(String),
dropoff_ntacode Nullable(String),
dropoff_ntaname Nullable(String),
dropoff_puma Nullable(String)
) ENGINE = Log;
PÄc tam es izvilku un ielÄdÄju katru no CSV failiem ceļojuma tabulÄ (trips
). TÄlÄkais tika pabeigts 55 minÅ«tÄs un 10 sekundÄs. PÄc Ŕīs operÄcijas datu direktorija lielums bija 134 GB.
$ time (for FILENAME in /ch/csv/trips_x*.csv.gz; do
echo $FILENAME
gunzip -c $FILENAME |
clickhouse-client
--host=0.0.0.0
--query="INSERT INTO trips FORMAT CSV"
done)
ImportÄÅ”anas Ätrums bija 155 MB nesaspiesta CSV satura sekundÄ. Man ir aizdomas, ka tas notika GZIP dekompresijas vÄjÄs vietas dÄļ. IespÄjams, bÅ«tu bijis ÄtrÄk izpakot visus gzip failus paralÄli, izmantojot xargs, un pÄc tam ielÄdÄt izspiestos datus. TÄlÄk ir sniegts apraksts par to, kas tika ziÅots CSV importÄÅ”anas procesa laikÄ.
$ sudo glances
ip-172-30-2-200 (Ubuntu 16.04 64bit / Linux 4.4.0-1072-aws) Uptime: 0:11:42
CPU 8.2% nice: 0.0% LOAD 36-core MEM 9.8% active: 5.20G SWAP 0.0%
user: 6.0% irq: 0.0% 1 min: 2.24 total: 68.7G inactive: 61.0G total: 0
system: 0.9% iowait: 1.3% 5 min: 1.83 used: 6.71G buffers: 66.4M used: 0
idle: 91.8% steal: 0.0% 15 min: 1.01 free: 62.0G cached: 61.6G free: 0
NETWORK Rx/s Tx/s TASKS 370 (507 thr), 2 run, 368 slp, 0 oth sorted automatically by cpu_percent, flat view
ens5 136b 2Kb
lo 343Mb 343Mb CPU% MEM% VIRT RES PID USER NI S TIME+ IOR/s IOW/s Command
100.4 1.5 1.65G 1.06G 9909 ubuntu 0 S 1:01.33 0 0 clickhouse-client --host=0.0.0.0 --query=INSERT INTO trips FORMAT CSV
DISK I/O R/s W/s 85.1 0.0 4.65M 708K 9908 ubuntu 0 R 0:50.60 32M 0 gzip -d -c /ch/csv/trips_xac.csv.gz
loop0 0 0 54.9 5.1 8.14G 3.49G 8091 clickhous 0 S 1:44.23 0 45M /usr/bin/clickhouse-server --config=/etc/clickhouse-server/config.xml
loop1 0 0 4.5 0.0 0 0 319 root 0 S 0:07.50 1K 0 kworker/u72:2
nvme0n1 0 3K 2.3 0.0 91.1M 28.9M 9912 root 0 R 0:01.56 0 0 /usr/bin/python3 /usr/bin/glances
nvme0n1p1 0 3K 0.3 0.0 0 0 960 root -20 S 0:00.10 0 0 kworker/28:1H
nvme1n1 32.1M 495M 0.3 0.0 0 0 1058 root -20 S 0:00.90 0 0 kworker/23:1H
Pirms turpinÄÅ”anas es atbrÄ«voÅ”u vietu NVMe diskdzinÄ«, izdzÄÅ”ot sÄkotnÄjos CSV failus.
$ sudo rm -fr /ch/csv
KonvertÄt uz kolonnas formu
Log ClickHouse dzinÄjs saglabÄs datus rindÄ orientÄtÄ formÄtÄ. Lai ÄtrÄk meklÄtu datus, es tos pÄrveidoju kolonnu formÄtÄ, izmantojot programmu MergeTree.
$ clickhouse-client --host=0.0.0.0
TÄlÄkais tika pabeigts 34 minÅ«tÄs un 50 sekundÄs. PÄc Ŕīs operÄcijas datu direktorija lielums bija 237 GB.
CREATE TABLE trips_mergetree
ENGINE = MergeTree(pickup_date, pickup_datetime, 8192)
AS SELECT
trip_id,
CAST(vendor_id AS Enum8('1' = 1,
'2' = 2,
'CMT' = 3,
'VTS' = 4,
'DDS' = 5,
'B02512' = 10,
'B02598' = 11,
'B02617' = 12,
'B02682' = 13,
'B02764' = 14)) AS vendor_id,
toDate(pickup_datetime) AS pickup_date,
ifNull(pickup_datetime, toDateTime(0)) AS pickup_datetime,
toDate(dropoff_datetime) AS dropoff_date,
ifNull(dropoff_datetime, toDateTime(0)) AS dropoff_datetime,
assumeNotNull(store_and_fwd_flag) AS store_and_fwd_flag,
assumeNotNull(rate_code_id) AS rate_code_id,
assumeNotNull(pickup_longitude) AS pickup_longitude,
assumeNotNull(pickup_latitude) AS pickup_latitude,
assumeNotNull(dropoff_longitude) AS dropoff_longitude,
assumeNotNull(dropoff_latitude) AS dropoff_latitude,
assumeNotNull(passenger_count) AS passenger_count,
assumeNotNull(trip_distance) AS trip_distance,
assumeNotNull(fare_amount) AS fare_amount,
assumeNotNull(extra) AS extra,
assumeNotNull(mta_tax) AS mta_tax,
assumeNotNull(tip_amount) AS tip_amount,
assumeNotNull(tolls_amount) AS tolls_amount,
assumeNotNull(ehail_fee) AS ehail_fee,
assumeNotNull(improvement_surcharge) AS improvement_surcharge,
assumeNotNull(total_amount) AS total_amount,
assumeNotNull(payment_type) AS payment_type_,
assumeNotNull(trip_type) AS trip_type,
pickup AS pickup,
pickup AS dropoff,
CAST(assumeNotNull(cab_type)
AS Enum8('yellow' = 1, 'green' = 2))
AS cab_type,
precipitation AS precipitation,
snow_depth AS snow_depth,
snowfall AS snowfall,
max_temperature AS max_temperature,
min_temperature AS min_temperature,
average_wind_speed AS average_wind_speed,
pickup_nyct2010_gid AS pickup_nyct2010_gid,
pickup_ctlabel AS pickup_ctlabel,
pickup_borocode AS pickup_borocode,
pickup_boroname AS pickup_boroname,
pickup_ct2010 AS pickup_ct2010,
pickup_boroct2010 AS pickup_boroct2010,
pickup_cdeligibil AS pickup_cdeligibil,
pickup_ntacode AS pickup_ntacode,
pickup_ntaname AS pickup_ntaname,
pickup_puma AS pickup_puma,
dropoff_nyct2010_gid AS dropoff_nyct2010_gid,
dropoff_ctlabel AS dropoff_ctlabel,
dropoff_borocode AS dropoff_borocode,
dropoff_boroname AS dropoff_boroname,
dropoff_ct2010 AS dropoff_ct2010,
dropoff_boroct2010 AS dropoff_boroct2010,
dropoff_cdeligibil AS dropoff_cdeligibil,
dropoff_ntacode AS dropoff_ntacode,
dropoff_ntaname AS dropoff_ntaname,
dropoff_puma AS dropoff_puma
FROM trips;
Å Ädi izskatÄ«jÄs skatiena izvade darbÄ«bas laikÄ:
ip-172-30-2-200 (Ubuntu 16.04 64bit / Linux 4.4.0-1072-aws) Uptime: 1:06:09
CPU 10.3% nice: 0.0% LOAD 36-core MEM 16.1% active: 13.3G SWAP 0.0%
user: 7.9% irq: 0.0% 1 min: 1.87 total: 68.7G inactive: 52.8G total: 0
system: 1.6% iowait: 0.8% 5 min: 1.76 used: 11.1G buffers: 71.8M used: 0
idle: 89.7% steal: 0.0% 15 min: 1.95 free: 57.6G cached: 57.2G free: 0
NETWORK Rx/s Tx/s TASKS 367 (523 thr), 1 run, 366 slp, 0 oth sorted automatically by cpu_percent, flat view
ens5 1Kb 8Kb
lo 2Kb 2Kb CPU% MEM% VIRT RES PID USER NI S TIME+ IOR/s IOW/s Command
241.9 12.8 20.7G 8.78G 8091 clickhous 0 S 30:36.73 34M 125M /usr/bin/clickhouse-server --config=/etc/clickhouse-server/config.xml
DISK I/O R/s W/s 2.6 0.0 90.4M 28.3M 9948 root 0 R 1:18.53 0 0 /usr/bin/python3 /usr/bin/glances
loop0 0 0 1.3 0.0 0 0 203 root 0 S 0:09.82 0 0 kswapd0
loop1 0 0 0.3 0.1 315M 61.3M 15701 ubuntu 0 S 0:00.40 0 0 clickhouse-client --host=0.0.0.0
nvme0n1 0 3K 0.3 0.0 0 0 7 root 0 S 0:00.83 0 0 rcu_sched
nvme0n1p1 0 3K 0.0 0.0 0 0 142 root 0 S 0:00.22 0 0 migration/27
nvme1n1 25.8M 330M 0.0 0.0 59.7M 1.79M 2764 ubuntu 0 S 0:00.00 0 0 (sd-pam)
PÄdÄjÄ testÄ vairÄkas kolonnas tika pÄrveidotas un pÄrrÄÄ·inÄtas. Es atklÄju, ka dažas no Ŕīm funkcijÄm Å”ajÄ datu kopÄ vairs nedarbojas, kÄ paredzÄts. Lai atrisinÄtu Å”o problÄmu, es noÅÄmu nepiemÄrotÄs funkcijas un ielÄdÄju datus, nepÄrveidojot uz sÄ«kÄkiem veidiem.
Datu sadale pa klasteru
Es sadalÄ«Å”u datus pa visiem trim klastera mezgliem. Lai sÄktu, zemÄk es izveidoÅ”u tabulu par visÄm trim maŔīnÄm.
$ clickhouse-client --host=0.0.0.0
CREATE TABLE trips_mergetree_third (
trip_id UInt32,
vendor_id String,
pickup_date Date,
pickup_datetime DateTime,
dropoff_date Date,
dropoff_datetime Nullable(DateTime),
store_and_fwd_flag Nullable(FixedString(1)),
rate_code_id Nullable(UInt8),
pickup_longitude Nullable(Float64),
pickup_latitude Nullable(Float64),
dropoff_longitude Nullable(Float64),
dropoff_latitude Nullable(Float64),
passenger_count Nullable(UInt8),
trip_distance Nullable(Float64),
fare_amount Nullable(Float32),
extra Nullable(Float32),
mta_tax Nullable(Float32),
tip_amount Nullable(Float32),
tolls_amount Nullable(Float32),
ehail_fee Nullable(Float32),
improvement_surcharge Nullable(Float32),
total_amount Nullable(Float32),
payment_type Nullable(String),
trip_type Nullable(UInt8),
pickup Nullable(String),
dropoff Nullable(String),
cab_type Nullable(String),
precipitation Nullable(Int8),
snow_depth Nullable(Int8),
snowfall Nullable(Int8),
max_temperature Nullable(Int8),
min_temperature Nullable(Int8),
average_wind_speed Nullable(Int8),
pickup_nyct2010_gid Nullable(Int8),
pickup_ctlabel Nullable(String),
pickup_borocode Nullable(Int8),
pickup_boroname Nullable(String),
pickup_ct2010 Nullable(String),
pickup_boroct2010 Nullable(String),
pickup_cdeligibil Nullable(FixedString(1)),
pickup_ntacode Nullable(String),
pickup_ntaname Nullable(String),
pickup_puma Nullable(String),
dropoff_nyct2010_gid Nullable(UInt8),
dropoff_ctlabel Nullable(String),
dropoff_borocode Nullable(UInt8),
dropoff_boroname Nullable(String),
dropoff_ct2010 Nullable(String),
dropoff_boroct2010 Nullable(String),
dropoff_cdeligibil Nullable(String),
dropoff_ntacode Nullable(String),
dropoff_ntaname Nullable(String),
dropoff_puma Nullable(String)
) ENGINE = MergeTree(pickup_date, pickup_datetime, 8192);
Tad es pÄrliecinÄÅ”os, ka pirmais serveris var redzÄt visus trÄ«s klastera mezglus.
SELECT *
FROM system.clusters
WHERE cluster = 'perftest_3shards'
FORMAT Vertical;
Row 1:
āāāāāā
cluster: perftest_3shards
shard_num: 1
shard_weight: 1
replica_num: 1
host_name: 172.30.2.192
host_address: 172.30.2.192
port: 9000
is_local: 1
user: default
default_database:
Row 2:
āāāāāā
cluster: perftest_3shards
shard_num: 2
shard_weight: 1
replica_num: 1
host_name: 172.30.2.162
host_address: 172.30.2.162
port: 9000
is_local: 0
user: default
default_database:
Row 3:
āāāāāā
cluster: perftest_3shards
shard_num: 3
shard_weight: 1
replica_num: 1
host_name: 172.30.2.36
host_address: 172.30.2.36
port: 9000
is_local: 0
user: default
default_database:
PÄc tam es definÄÅ”u jaunu tabulu pirmajÄ serverÄ«, kuras pamatÄ ir shÄma trips_mergetree_third
un izmanto Distributed dzinÄju.
CREATE TABLE trips_mergetree_x3
AS trips_mergetree_third
ENGINE = Distributed(perftest_3shards,
default,
trips_mergetree_third,
rand());
PÄc tam es kopÄÅ”u datus no MergeTree balstÄ«tÄs tabulas uz visiem trim serveriem. TÄlÄkais tika pabeigts 34 minÅ«tÄs un 44 sekundÄs.
INSERT INTO trips_mergetree_x3
SELECT * FROM trips_mergetree;
PÄc iepriekÅ” minÄtÄs darbÄ«bas es devu ClickHouse 15 minÅ«tes, lai pÄrvietotos no maksimÄlÄ krÄtuves lÄ«meÅa atzÄ«mes. Datu direktoriju apjoms katrÄ no trim serveriem bija attiecÄ«gi 264 GB, 34 GB un 33 GB.
ClickHouse klastera veiktspÄjas novÄrtÄjums
NÄkamais bija ÄtrÄkais laiks, kad katrs vaicÄjums tabulÄ tika izpildÄ«ts vairÄkas reizes trips_mergetree_x3
.
$ clickhouse-client --host=0.0.0.0
TÄlÄkais tika pabeigts 2.449 sekundÄs.
SELECT cab_type, count(*)
FROM trips_mergetree_x3
GROUP BY cab_type;
TÄlÄkais tika pabeigts 0.691 sekundÄs.
SELECT passenger_count,
avg(total_amount)
FROM trips_mergetree_x3
GROUP BY passenger_count;
TÄlÄkais tika pabeigts 0 sekundÄs.
SELECT passenger_count,
toYear(pickup_date) AS year,
count(*)
FROM trips_mergetree_x3
GROUP BY passenger_count,
year;
TÄlÄkais tika pabeigts 0.983 sekundÄs.
SELECT passenger_count,
toYear(pickup_date) AS year,
round(trip_distance) AS distance,
count(*)
FROM trips_mergetree_x3
GROUP BY passenger_count,
year,
distance
ORDER BY year,
count(*) DESC;
SalÄ«dzinÄjumam es izpildÄ«ju tos paÅ”us vaicÄjumus uz MergeTree balstÄ«tÄ tabulÄ, kas atrodas tikai pirmajÄ serverÄ«.
Viena ClickHouse mezgla veiktspÄjas novÄrtÄjums
NÄkamais bija ÄtrÄkais laiks, kad katrs vaicÄjums tabulÄ tika izpildÄ«ts vairÄkas reizes trips_mergetree_x3
.
TÄlÄkais tika pabeigts 0.241 sekundÄs.
SELECT cab_type, count(*)
FROM trips_mergetree
GROUP BY cab_type;
TÄlÄkais tika pabeigts 0.826 sekundÄs.
SELECT passenger_count,
avg(total_amount)
FROM trips_mergetree
GROUP BY passenger_count;
TÄlÄkais tika pabeigts 1.209 sekundÄs.
SELECT passenger_count,
toYear(pickup_date) AS year,
count(*)
FROM trips_mergetree
GROUP BY passenger_count,
year;
TÄlÄkais tika pabeigts 1.781 sekundÄs.
SELECT passenger_count,
toYear(pickup_date) AS year,
round(trip_distance) AS distance,
count(*)
FROM trips_mergetree
GROUP BY passenger_count,
year,
distance
ORDER BY year,
count(*) DESC;
PÄrdomas par rezultÄtiem
Å Ä« ir pirmÄ reize, kad bezmaksas uz CPU balstÄ«ta datu bÄze manos testos spÄja pÄrspÄt uz GPU balstÄ«tu datu bÄzi. KopÅ” tÄ laika Ŕī uz GPU balstÄ«tÄ datu bÄze ir piedzÄ«vojusi divas pÄrskatÄ«Å”anas, taÄu veiktspÄja, ko ClickHouse nodroÅ”inÄja vienÄ mezglÄ, tomÄr ir ļoti iespaidÄ«ga.
TajÄ paÅ”Ä laikÄ, izpildot 1. vaicÄjumu sadalÄ«tÄ dzinÄjÄ, pieskaitÄmÄs izmaksas ir par lielumu augstÄkas. Es ceru, ka esmu kaut ko palaidis garÄm savÄ izpÄtÄ par Å”o ziÅu, jo bÅ«tu jauki redzÄt, ka vaicÄjumu laiki samazinÄs, pievienojot klasterim vairÄk mezglu. TomÄr lieliski, ka, izpildot citus vaicÄjumus, veiktspÄja palielinÄjÄs apmÄram 2 reizes.
BÅ«tu jauki redzÄt ClickHouse attÄ«stÄ«bu, lai varÄtu nodalÄ«t krÄtuvi un aprÄÄ·inus, lai tÄs varÄtu mÄrogot neatkarÄ«gi. HDFS atbalsts, kas tika pievienots pagÄjuÅ”ajÄ gadÄ, varÄtu bÅ«t solis uz to. RunÄjot par skaitļoÅ”anu, ja vienu vaicÄjumu var paÄtrinÄt, pievienojot klasterim vairÄk mezglu, tad Ŕīs programmatÅ«ras nÄkotne ir ļoti gaiÅ”a.
Paldies, ka veltÄ«jÄt laiku Ŕīs ziÅas izlasÄ«Å”anai. PiedÄvÄju konsultÄciju, arhitektÅ«ras un prakses attÄ«stÄ«bas pakalpojumus klientiem ZiemeļamerikÄ un EiropÄ. Ja vÄlaties apspriest, kÄ mani ieteikumi var palÄ«dzÄt jÅ«su uzÅÄmumam, lÅ«dzu, sazinieties ar mani pa
Avots: www.habr.com