Terjemahan artikel disiapake khusus kanggo siswa kursus kasebut .
minangka basis data kolom open source. Iki minangka lingkungan sing apik ing ngendi atusan analis bisa nggoleki data rinci kanthi cepet, sanajan puluhan milyar rekaman anyar dilebokake saben dina. Biaya infrastruktur kanggo ndhukung sistem kasebut bisa nganti $ 100 saben taun, lan bisa uga setengah gumantung saka panggunaan. Ing sawijining wektu, instalasi ClickHouse saka Yandex Metrics ngemot 10 triliun cathetan. Saliyane Yandex, ClickHouse uga sukses karo Bloomberg lan Cloudflare.
Rong taun kepungkur aku ngginakaken database nggunakake siji mesin, lan dadi free lunak database aku wis tau ndeleng. Wiwit iku, pangembang ora mandheg nambahake fitur, kalebu dhukungan kanggo kompresi Kafka, HDFS lan ZStandard. Paling taun padha ditambahaké support kanggo cara komprèsi cascading, lan coding dadi bisa. Nalika ngompres data seri wektu, nilai gauge bisa dikompres kanthi apik nggunakake enkoding delta, nanging kanggo counter luwih apik nggunakake enkoding delta-by-delta. Kompresi sing apik wis dadi kunci kanggo kinerja ClickHouse.
ClickHouse kasusun saka 170 ewu baris kode C ++, ora kalebu perpustakaan pihak katelu, lan minangka salah sawijining basis kode basis data sing disebarake paling cilik. Ing comparison, SQLite ora ndhukung distribusi lan kasusun saka 235 ewu baris kode C. Ing tulisan iki, 207 engineers wis nyumbang kanggo ClickHouse, lan intensitas commits wis nambah bubar.
Ing Maret 2017, ClickHouse wiwit tumindak minangka cara sing gampang kanggo nglacak pembangunan. Dheweke uga nyuwil file dokumentasi monolitik dadi hirarki file adhedhasar Markdown. Masalah lan fitur dilacak liwat GitHub, lan umume piranti lunak dadi luwih gampang diakses ing sawetara taun kepungkur.
Ing artikel iki, Aku bakal njupuk dipikir ing kinerja kluster ClickHouse ing AWS EC2 nggunakake prosesor 36-inti lan panyimpenan NVMe.
UPDATE: Seminggu sawise nerbitake kiriman iki, aku nyoba maneh tes kanthi konfigurasi sing luwih apik lan entuk asil sing luwih apik. Kiriman iki wis dianyari kanggo nggambarake owah-owahan kasebut.
Ngluncurake Kluster AWS EC2
Aku bakal nggunakake telung c5d.9xlarge EC2 kedadean kanggo kirim iki. Saben wong ngemot 36 CPU virtual, 72 GB RAM, 900 GB panyimpenan NVMe SSD lan ndhukung jaringan 10 Gigabit. Padha regane $1,962/jam saben ing wilayah eu-kulon-1 nalika mlaku ing dikarepake. Aku bakal nggunakake Ubuntu Server 16.04 LTS minangka sistem operasi.
Firewall wis diatur supaya saben mesin bisa komunikasi karo saben liyane tanpa watesan, lan mung alamat IPv4 sandi whitelisted dening SSH ing kluster.
Drive NVMe ing status kesiapan operasional
Kanggo ClickHouse bisa digunakake, aku bakal nggawe sistem file ing format EXT4 ing drive NVMe ing saben server.
$ sudo mkfs -t ext4 /dev/nvme1n1
$ sudo mkdir /ch
$ sudo mount /dev/nvme1n1 /chSawise kabeh wis diatur, sampeyan bisa ndeleng titik gunung lan 783 GB papan kasedhiya ing saben sistem.
$ lsblkNAME 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
ββnvme0n1p1 259:2 0 8G 0 part /
nvme1n1 259:0 0 838.2G 0 disk /ch$ df -hFilesystem 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% /chDataset sing bakal digunakake ing tes iki yaiku mbucal data sing digawe saka 1.1 milyar taksi sing dijupuk ing New York City sajrone nem taun. Ing blog rincian carane aku diklumpukake set data iki. Padha disimpen ing AWS S3, supaya aku bakal ngatur AWS CLI karo akses lan kunci rahasia.
$ sudo apt update
$ sudo apt install awscli
$ aws configureAku bakal nyetel watesan panjalukan bebarengan klien kanggo 100 supaya file download luwih cepet saka setelan gawan.
$ aws configure set
default.s3.max_concurrent_requests
100Aku bakal ngundhuh dataset nitih taksi saka AWS S3 lan nyimpen ing drive NVMe ing server pisanan. Set data iki ~ 104GB ing format CSV sing dikompres GZIP.
$ sudo mkdir -p /ch/csv
$ sudo chown -R ubuntu /ch/csv
$ aws s3 sync s3://<bucket>/csv /ch/csvInstalasi ClickHouse
Aku bakal nginstal distribusi OpenJDK kanggo Java 8 amarga dibutuhake kanggo mbukak Apache ZooKeeper, sing dibutuhake kanggo instalasi ClickHouse sing disebarake ing kabeh telung mesin.
$ sudo apt update
$ sudo apt install
openjdk-8-jre
openjdk-8-jdk-headless
Banjur aku nyetel variabel lingkungan JAVA_HOME.
$ sudo vi /etc/profile
export JAVA_HOME=/usr
$ source /etc/profileAku banjur bakal nggunakake sistem manajemen paket Ubuntu kanggo nginstal ClickHouse 18.16.1, glances lan ZooKeeper ing kabeh telung mesin.
$ 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
zookeeperdAku bakal nggawe direktori kanggo ClickHouse lan uga nindakake sawetara konfigurasi overrides ing kabeh telung server.
$ 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.confIki minangka overrides konfigurasi sing bakal digunakake.
<?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>Aku banjur bakal mbukak ZooKeeper lan server ClickHouse ing kabeh telung mesin.
$ sudo /etc/init.d/zookeeper start
$ sudo service clickhouse-server startNgunggah data menyang ClickHouse
Ing server pisanan aku bakal nggawe tabel trip (trips), sing bakal nyimpen dataset lelungan taksi nggunakake mesin Log.
$ 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;
Aku banjur extract lan mbukak saben file CSV menyang tabel trip (trips). Ing ngisor iki rampung ing 55 menit lan 10 detik. Sawise operasi iki, ukuran direktori data ana 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)Kacepetan impor yaiku 155 MB konten CSV sing ora dikompres per detik. Aku curiga iki amarga bottleneck ing dekompresi GZIP. Bisa uga luwih cepet unzip kabeh file gzip ing podo karo nggunakake xargs banjur mbukak data unzip. Ing ngisor iki ana katrangan babagan apa sing dilaporake sajrone proses ngimpor CSV.
$ sudo glancesip-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/23:1HAku bakal mbebasake spasi ing drive NVMe kanthi mbusak file CSV asli sadurunge nerusake.
$ sudo rm -fr /ch/csvNgonversi menyang Formulir Column
Mesin Log ClickHouse bakal nyimpen data ing format berorientasi baris. Kanggo pitakon data luwih cepet, aku ngowahi menyang format kolom nggunakake mesin MergeTree.
$ clickhouse-client --host=0.0.0.0Ing ngisor iki rampung ing 34 menit lan 50 detik. Sawise operasi iki, ukuran direktori data 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;Iki minangka output tampilan sajrone operasi:
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)Ing tes pungkasan, sawetara kolom diowahi lan diitung maneh. Aku nemokake sawetara fungsi kasebut ora bisa digunakake maneh kaya sing dikarepake ing dataset iki. Kanggo ngatasi masalah iki, aku mbusak fungsi sing ora cocog lan mbukak data tanpa ngowahi menyang jinis sing luwih granular.
Distribusi data ing kluster
Aku bakal mbagekke data ing kabeh telung kelenjar kluster. Kanggo miwiti, ing ngisor iki aku bakal nggawe tabel ing kabeh telung mesin.
$ clickhouse-client --host=0.0.0.0CREATE 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);Banjur aku bakal nggawe manawa server pisanan bisa ndeleng kabeh telung kelenjar ing kluster.
SELECT *
FROM system.clusters
WHERE cluster = 'perftest_3shards'
FORMAT Vertical;Row 1:
ββββββ
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:
ββββββ
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:
ββββββ
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:
Banjur aku bakal nemtokake tabel anyar ing server pisanan sing adhedhasar skema trips_mergetree_third lan nggunakake mesin Distribusi.
CREATE TABLE trips_mergetree_x3
AS trips_mergetree_third
ENGINE = Distributed(perftest_3shards,
default,
trips_mergetree_third,
rand());Aku banjur bakal nyalin data saka MergeTree adhedhasar tabel kanggo kabeh telung server. Ing ngisor iki rampung ing 34 menit lan 44 detik.
INSERT INTO trips_mergetree_x3
SELECT * FROM trips_mergetree;Sawise operasi ing ndhuwur, aku menehi ClickHouse 15 menit kanggo pindhah saka tandha tingkat panyimpenan maksimum. Direktori data rampung dadi 264 GB, 34 GB lan 33 GB ing saben telung server kasebut.
Evaluasi kinerja kluster ClickHouse
Sing dakdeleng sabanjure yaiku wektu paling cepet aku ndeleng saben pitakon ing meja kaping pirang-pirang trips_mergetree_x3.
$ clickhouse-client --host=0.0.0.0Ing ngisor iki rampung ing 2.449 detik.
SELECT cab_type, count(*)
FROM trips_mergetree_x3
GROUP BY cab_type;Ing ngisor iki rampung ing 0.691 detik.
SELECT passenger_count,
avg(total_amount)
FROM trips_mergetree_x3
GROUP BY passenger_count;Ing ngisor iki rampung ing 0 detik.
SELECT passenger_count,
toYear(pickup_date) AS year,
count(*)
FROM trips_mergetree_x3
GROUP BY passenger_count,
year;Ing ngisor iki rampung ing 0.983 detik.
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;Kanggo mbandhingake, aku mbukak pitakon sing padha ing tabel basis MergeTree sing mung ana ing server pisanan.
Evaluasi kinerja siji simpul ClickHouse
Sing dakdeleng sabanjure yaiku wektu paling cepet aku ndeleng saben pitakon ing meja kaping pirang-pirang trips_mergetree_x3.
Ing ngisor iki rampung ing 0.241 detik.
SELECT cab_type, count(*)
FROM trips_mergetree
GROUP BY cab_type;Ing ngisor iki rampung ing 0.826 detik.
SELECT passenger_count,
avg(total_amount)
FROM trips_mergetree
GROUP BY passenger_count;Ing ngisor iki rampung ing 1.209 detik.
SELECT passenger_count,
toYear(pickup_date) AS year,
count(*)
FROM trips_mergetree
GROUP BY passenger_count,
year;Ing ngisor iki rampung ing 1.781 detik.
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;Renungan ing asil
Iki pisanan sing free basis CPU basis data bisa outperform basis GPU ing tes sandi. Database basis GPU kasebut wis ngalami rong revisi wiwit saiki, nanging kinerja sing dikirim ClickHouse ing simpul siji pancen apik banget.
Ing wektu sing padha, nalika nglakokake Query 1 ing mesin sing disebarake, biaya overhead minangka urutan gedhene sing luwih dhuwur. Mugi aku ora kejawab soko ing riset kanggo kirim iki amarga iku bakal becik kanggo ndeleng kaping query mudhun nalika aku nambah kelenjar liyane menyang kluster. Nanging, apik banget yen nalika nindakake pitakon liyane, kinerja mundhak udakara 2 kali.
Luwih becik ndeleng ClickHouse berkembang dadi bisa misahake panyimpenan lan ngitung supaya bisa ukuran kanthi mandiri. Dhukungan HDFS, sing ditambahake taun kepungkur, bisa dadi langkah menyang iki. Ing babagan komputasi, yen query siji bisa dicepetake kanthi nambahake simpul liyane menyang kluster, mula masa depan piranti lunak iki cerah banget.
Matur nuwun kanggo njupuk wektu kanggo maca kirim iki. Aku nawakake konsultasi, arsitektur, lan layanan pangembangan praktik kanggo klien ing Amerika Utara lan Eropa. Yen sampeyan pengin ngrembug babagan carane saran bisa mbantu bisnis sampeyan, hubungi kula liwat .
Source: www.habr.com