የጽሁፉ ትርጉም የተዘጋጀው በተለይ ለትምህርቱ ተማሪዎች ነው።
ከሁለት አመት በፊት አሳልፌ ነበር።
ClickHouse የሶስተኛ ወገን ቤተ-መጻሕፍትን ሳይጨምር 170 የC++ ኮድ መስመሮችን ያቀፈ ሲሆን በጣም አነስተኛ ከተከፋፈሉት የመረጃ ቋቶች ኮድ ቤዝ አንዱ ነው። በንፅፅር ፣ SQLite ስርጭትን አይደግፍም እና 235 ሺህ የ C ኮድ መስመሮችን ያቀፈ ነው ። እስከዚህ ጽሑፍ ድረስ 207 መሐንዲሶች ለ ClickHouse አስተዋፅኦ አድርገዋል ፣ እና የድርጊቱ ጥንካሬ በቅርቡ እየጨመረ ነው።
በማርች 2017 ክሊክ ሃውስ መምራት ጀመረ
በዚህ ጽሑፍ ውስጥ የ 2-ኮር ፕሮሰሰር እና NVMe ማከማቻን በመጠቀም በ AWS EC36 ላይ የ ClickHouse ክላስተር አፈጻጸምን ለማየት እሞክራለሁ።
አዘምን፡ ይህን ልጥፍ በመጀመሪያ ካተምኩት ከአንድ ሳምንት በኋላ፣ በተሻሻለ ውቅረት ፈተናውን ደግሜያለሁ እና በጣም የተሻሉ ውጤቶችን አስመዝግቤያለሁ። ይህ ልጥፍ እነዚህን ለውጦች ለማንፀባረቅ ተዘምኗል።
የAWS EC2 ክላስተር በማስጀመር ላይ
ለዚህ ልጥፍ ሶስት c5d.9xlarge EC2 ምሳሌዎችን እጠቀማለሁ። እያንዳንዳቸው 36 ምናባዊ ሲፒዩዎች፣ 72 ጊባ ራም፣ 900 ጂቢ NVMe SSD ማከማቻ እና 10 Gigabit ኔትወርክን ይደግፋሉ። በ eu-west-1,962 ክልል ውስጥ በፍላጎት ሲሄዱ እያንዳንዳቸው 1 ዶላር በሰዓት ያስከፍላሉ። ኡቡንቱ አገልጋይ 16.04 LTSን እንደ ኦፕሬቲንግ ሲስተም እጠቀማለሁ።
ፋየርዎል የተዋቀረው እያንዳንዱ ማሽን ያለ ገደብ እርስ በርስ እንዲግባባ ነው፣ እና የእኔ IPv4 አድራሻ ብቻ በክላስተር ውስጥ በኤስኤስኤስ የተፈቀደ ነው።
NVMe መንዳት በተግባር ዝግጁነት ሁኔታ
ClickHouse እንዲሰራ፣ በእያንዳንዱ አገልጋይ ላይ በ NVMe ድራይቭ ላይ በ EXT4 ቅርጸት የፋይል ስርዓት እፈጥራለሁ።
$ sudo mkfs -t ext4 /dev/nvme1n1
$ sudo mkdir /ch
$ sudo mount /dev/nvme1n1 /ch
ሁሉም ነገር ከተዋቀረ በኋላ በእያንዳንዱ ስርዓት ላይ ያለውን የ 783 ጂቢ ቦታ እና የ XNUMX ጂቢ ቦታ ማየት ይችላሉ.
$ 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
└─nvme0n1p1 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
በዚህ ሙከራ የምጠቀምበት የመረጃ ስብስብ በኒውዮርክ ከተማ ከስድስት ዓመታት በላይ በወሰድኩት 1.1 ቢሊዮን የታክሲ ግልቢያዎች ያፈጠርኩት የመረጃ መጣያ ነው። ብሎግ ላይ
$ sudo apt update
$ sudo apt install awscli
$ aws configure
ፋይሎች ከነባሪው መቼቶች በበለጠ ፍጥነት እንዲወርዱ የደንበኛውን በተመሳሳይ ጊዜ የጥያቄ ገደብ ወደ 100 አዘጋጃለሁ።
$ aws configure set
default.s3.max_concurrent_requests
100
የታክሲ ግልቢያ ዳታ ስብስብን ከAWS S3 አውርጄ በመጀመሪያው አገልጋይ ላይ ባለው NVMe ድራይቭ ላይ አከማችታለሁ። ይህ የውሂብ ስብስብ ~104GB በGZIP የታመቀ CSV ቅርጸት ነው።
$ sudo mkdir -p /ch/csv
$ sudo chown -R ubuntu /ch/csv
$ aws s3 sync s3://<bucket>/csv /ch/csv
ClickHouse መጫን
ለጃቫ 8 የ OpenJDK ስርጭትን እጭነዋለሁ Apache ZooKeeper ን ለማስኬድ ስለሚያስፈልግ በሶስቱም ማሽኖች ላይ ለተሰራጨው ClickHouse መጫን ያስፈልጋል።
$ sudo apt update
$ sudo apt install
openjdk-8-jre
openjdk-8-jdk-headless
ከዚያም የአካባቢን ተለዋዋጭ አዘጋጃለሁ JAVA_HOME
.
$ sudo vi /etc/profile
export JAVA_HOME=/usr
$ source /etc/profile
ከዚያ በሦስቱም ማሽኖች ላይ ClickHouse 18.16.1፣ glances እና ZooKeeperን ለመጫን የኡቡንቱን የጥቅል አስተዳደር ስርዓት እጠቀማለሁ።
$ 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
ለ ClickHouse ማውጫ እፈጥራለሁ እና በሦስቱም አገልጋዮች ላይ አንዳንድ የውቅረት መሻሮችን አደርጋለሁ።
$ 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
እነዚህ እኔ የምጠቀምባቸው የውቅረት መሻሮች ናቸው።
<?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>
ከዚያ ZooKeeper እና ClickHouse አገልጋይን በሶስቱም ማሽኖች ላይ እሰራለሁ።
$ sudo /etc/init.d/zookeeper start
$ sudo service clickhouse-server start
ወደ ClickHouse ውሂብ በመስቀል ላይ
በመጀመሪያው አገልጋይ ላይ የጉዞ ጠረጴዛን እፈጥራለሁ (trips
), ይህም የሎግ ሞተርን በመጠቀም የታክሲ ጉዞዎችን የውሂብ ስብስብ ያከማቻል.
$ 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;
ከዚያ እያንዳንዱን የሲኤስቪ ፋይሎች ወደ የጉዞ ጠረጴዛ አውጥቼ እጭነዋለሁ (trips
). የሚከተለው በ55 ደቂቃ ከ10 ሰከንድ ውስጥ ተጠናቀቀ። ከዚህ ክዋኔ በኋላ የውሂብ ማውጫው መጠን 134 ጂቢ ነበር.
$ 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)
የማስመጣት ፍጥነት 155 ሜባ ያልታመቀ የሲኤስቪ ይዘት በሰከንድ ነበር። ይህ በGZIP የመበስበስ ችግር ምክንያት ነው ብዬ እገምታለሁ። ሁሉንም የጂዚፕ ፋይሎችን በትይዩ xargs ን መክፈት እና ከዚያ ያልተከፈተውን ዳታ መጫን ፈጣን ሊሆን ይችላል። ከዚህ በታች በCSV ማስመጣት ሂደት ወቅት የተዘገበው መግለጫ ነው።
$ 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
ከመቀጠሌ በፊት የመጀመሪያዎቹን የCSV ፋይሎች በመሰረዝ በNVMe ድራይቭ ላይ ቦታ አስለቅቄአለሁ።
$ sudo rm -fr /ch/csv
ወደ አምድ ቅጽ ቀይር
Log ClickHouse ሞተር በረድፍ-ተኮር ቅርጸት ያከማቻል። መረጃን በፍጥነት ለመጠየቅ የMergeTree ሞተርን በመጠቀም ወደ አምድ ቅርፀት እቀይረዋለሁ።
$ clickhouse-client --host=0.0.0.0
የሚከተለው በ34 ደቂቃ ከ50 ሰከንድ ውስጥ ተጠናቀቀ። ከዚህ ክዋኔ በኋላ የውሂብ ማውጫው መጠን 237 ጂቢ ነበር.
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;
በቀዶ ጥገናው ወቅት የጨረፍታ ውፅዓት ይህን ይመስላል።
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)
በመጨረሻው ፈተና፣ በርካታ ዓምዶች ተለውጠዋል እና እንደገና ተቆጥረዋል። ከእነዚህ ተግባራት መካከል አንዳንዶቹ በዚህ የውሂብ ስብስብ ላይ እንደተጠበቀው እንደማይሰሩ ተረድቻለሁ። ይህንን ችግር ለመፍታት, አግባብ ያልሆኑ ተግባራትን አስወግጄ ወደ ተጨማሪ የጥራጥሬ ዓይነቶች ሳይቀይሩ ውሂቡን ጫንኩ.
በክላስተር ላይ የውሂብ ስርጭት
ውሂቡን በሦስቱም የክላስተር ኖዶች ላይ አከፋፍላለሁ። ለመጀመር, ከታች በሶስቱም ማሽኖች ላይ ጠረጴዛ እፈጥራለሁ.
$ 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);
ከዚያም የመጀመሪያው አገልጋይ በክላስተር ውስጥ ያሉትን ሶስቱን አንጓዎች ማየት እንደሚችል አረጋግጣለሁ።
SELECT *
FROM system.clusters
WHERE cluster = 'perftest_3shards'
FORMAT Vertical;
Row 1:
──────
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:
──────
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:
──────
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:
ከዚያም በመጀመሪያው አገልጋይ ላይ በስርዓተ-ፆታ ላይ የተመሰረተ አዲስ ሰንጠረዥ እገልጻለሁ trips_mergetree_third
እና የተከፋፈለውን ሞተር ይጠቀማል.
CREATE TABLE trips_mergetree_x3
AS trips_mergetree_third
ENGINE = Distributed(perftest_3shards,
default,
trips_mergetree_third,
rand());
ከዚያም መረጃውን ከ MergeTree መሰረት ካለው ሰንጠረዥ ወደ ሶስቱም አገልጋዮች እቀዳለሁ። የሚከተለው በ34 ደቂቃ ከ44 ሰከንድ ውስጥ ተጠናቀቀ።
INSERT INTO trips_mergetree_x3
SELECT * FROM trips_mergetree;
ከላይ ከተጠቀሰው ቀዶ ጥገና በኋላ ከከፍተኛው የማከማቻ ደረጃ ምልክት ለመውጣት 15 ደቂቃ ለ ClickHouse ሰጠሁት። የመረጃ ማውጫዎቹ 264 ጂቢ፣ 34 ጂቢ እና 33 ጂቢ እንደቅደም ተከተላቸው በሶስቱ አገልጋዮች ላይ አብቅተዋል።
ClickHouse ክላስተር አፈጻጸም ግምገማ
ቀጥሎ ያየሁት እያንዳንዱን መጠይቅ በጠረጴዛ ላይ ብዙ ጊዜ ስሮጥ ካየሁት ፈጣን ሰአት ነው። trips_mergetree_x3
.
$ clickhouse-client --host=0.0.0.0
የሚከተለው በ2.449 ሰከንድ ውስጥ ተጠናቀቀ።
SELECT cab_type, count(*)
FROM trips_mergetree_x3
GROUP BY cab_type;
የሚከተለው በ0.691 ሰከንድ ውስጥ ተጠናቀቀ።
SELECT passenger_count,
avg(total_amount)
FROM trips_mergetree_x3
GROUP BY passenger_count;
የሚከተለው በ0 ሰከንድ ውስጥ ተጠናቀቀ።
SELECT passenger_count,
toYear(pickup_date) AS year,
count(*)
FROM trips_mergetree_x3
GROUP BY passenger_count,
year;
የሚከተለው በ0.983 ሰከንድ ውስጥ ተጠናቀቀ።
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;
ለማነጻጸር፣ በመጀመሪያው አገልጋይ ላይ ብቻ በሚኖረው MergeTree ላይ በተመሰረተ ጠረጴዛ ላይ ተመሳሳይ መጠይቆችን ሮጫለሁ።
የአንድ ClickHouse መስቀለኛ መንገድ የአፈጻጸም ግምገማ
ቀጥሎ ያየሁት እያንዳንዱን መጠይቅ በጠረጴዛ ላይ ብዙ ጊዜ ስሮጥ ካየሁት ፈጣን ሰአት ነው። trips_mergetree_x3
.
የሚከተለው በ0.241 ሰከንድ ውስጥ ተጠናቀቀ።
SELECT cab_type, count(*)
FROM trips_mergetree
GROUP BY cab_type;
የሚከተለው በ0.826 ሰከንድ ውስጥ ተጠናቀቀ።
SELECT passenger_count,
avg(total_amount)
FROM trips_mergetree
GROUP BY passenger_count;
የሚከተለው በ1.209 ሰከንድ ውስጥ ተጠናቀቀ።
SELECT passenger_count,
toYear(pickup_date) AS year,
count(*)
FROM trips_mergetree
GROUP BY passenger_count,
year;
የሚከተለው በ1.781 ሰከንድ ውስጥ ተጠናቀቀ።
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;
በውጤቶቹ ላይ ነጸብራቅ
በፈተናዎቼ ውስጥ ነፃ ሲፒዩ ላይ የተመሰረተ ዳታቤዝ ጂፒዩ ላይ የተመሰረተ ዳታቤዝ ብልጫ ሲያደርግ ይህ የመጀመሪያው ነው። ያ በጂፒዩ ላይ የተመሰረተ የውሂብ ጎታ ከዚያን ጊዜ ጀምሮ በሁለት ክለሳዎች ውስጥ አልፏል፣ ነገር ግን ClickHouse በአንድ መስቀለኛ መንገድ ላይ ያቀረበው አፈጻጸም በጣም አስደናቂ ነው።
በተመሳሳይ ጊዜ መጠይቅ 1 በተከፋፈለው ሞተር ላይ ሲፈጽም, የትርፍ ወጪዎች ከፍተኛ መጠን ያለው ትዕዛዝ ነው. ለዚህ ልጥፍ ባደረኩት ጥናት ውስጥ የሆነ ነገር እንዳመለጠኝ ተስፋ አደርጋለሁ ምክንያቱም ወደ ክላስተር ተጨማሪ አንጓዎችን ስጨምር የመጠይቅ ጊዜ ሲቀንስ ማየት ጥሩ ነበር። ሆኖም፣ ሌሎች መጠይቆችን በሚፈጽሙበት ጊዜ አፈፃፀሙ በ2 ጊዜ ያህል መጨመሩ በጣም ጥሩ ነው።
ClickHouse ማከማቻን ለመለየት እና እራሳቸውን ችለው እንዲመዘኑ ለማስላት ሲያድጉ ማየት ጥሩ ነው። ባለፈው ዓመት የተጨመረው የኤችዲኤፍኤስ ድጋፍ ለዚህ አንድ እርምጃ ሊሆን ይችላል። በኮምፒዩተር ረገድ፣ አንድ ነጠላ መጠይቅ ወደ ክላስተር ተጨማሪ ኖዶችን በመጨመር ማፋጠን ከተቻለ የዚህ ሶፍትዌር የወደፊት ዕጣ በጣም ብሩህ ነው።
ይህንን ጽሑፍ ለማንበብ ጊዜ ስለወሰዱ እናመሰግናለን። በሰሜን አሜሪካ እና በአውሮፓ ላሉ ደንበኞች የማማከር፣ የሕንፃ እና የተግባር ልማት አገልግሎቶችን አቀርባለሁ። የእኔ ጥቆማዎች ንግድዎን እንዴት እንደሚረዱ ለመወያየት ከፈለጉ እባክዎን በ በኩል ያነጋግሩኝ።
ምንጭ: hab.com