1.1 billion lub tsheb tavxij mus ncig: 108-core ClickHouse pawg

Cov lus txhais ntawm tsab xov xwm tau npaj tshwj xeeb rau cov tub ntxhais kawm ntawm chav kawm Data Engineer.

1.1 billion lub tsheb tavxij mus ncig: 108-core ClickHouse pawg

Nyem Tsev yog ib qhov chaw qhib columnar database. Nws yog ib qho chaw zoo uas ntau pua tus kws tshuaj ntsuam tuaj yeem nug cov ntaub ntawv ntxaws ntxaws, txawm tias kaum tawm txhiab tus ntaub ntawv tshiab tau nkag rau ib hnub. Cov nqi tsim kho vaj tse los txhawb cov txheej txheem zoo li no tuaj yeem siab txog $ 100 toj xyoo, thiab muaj peev xwm ib nrab nyob ntawm kev siv. Ntawm ib qho taw tes, ClickHouse installation los ntawm Yandex Metrics muaj 10 trillion cov ntaub ntawv. Ntxiv nrog rau Yandex, ClickHouse kuj pom muaj kev vam meej nrog Bloomberg thiab Cloudflare.

Ob xyoos dhau los kuv siv kev sib piv databases siv ib lub tshuab, thiab nws tau los ua ceev tshaj plaws free database software kuv twb puas tau pom. Txij thaum ntawd los, cov neeg tsim khoom tau txuas ntxiv ntxiv nta, suav nrog kev txhawb nqa rau Kafka, HDFS thiab ZStandard compression. Xyoo tas los lawv ntxiv kev txhawb nqa rau cascading compression txoj kev, thiab delta-los ntawm-delta coding ua tau. Thaum compressing lub sij hawm series cov ntaub ntawv, ntsuas qhov tseem ceeb yuav compressed zoo siv delta encoding, tab sis rau cov txee nws yuav zoo dua los siv delta-by-delta encoding. Zoo compression tau dhau los ua tus yuam sij rau ClickHouse qhov kev ua tau zoo.

ClickHouse muaj 170 txhiab kab ntawm C ++ code, tsis suav nrog cov tsev qiv ntawv thib peb, thiab yog ib qho ntawm cov ntaub ntawv me tshaj plaws faib cov ntaub ntawv codebases. Hauv kev sib piv, SQLite tsis txhawb kev faib tawm thiab muaj 235 txhiab kab ntawm C code. Raws li kev sau ntawv no, 207 engineers tau pab txhawb rau ClickHouse, thiab kev siv zog ntawm kev cog lus tau nce tsis ntev los no.

Thaum Lub Peb Hlis 2017, ClickHouse pib ua hloov log raws li txoj hauv kev yooj yim kom taug qab kev txhim kho. Lawv kuj tau tsoo cov ntaub ntawv monolithic rau hauv Markdown-raws li cov ntaub ntawv hierarchy. Cov teeb meem thiab cov yam ntxwv tau taug qab ntawm GitHub, thiab feem ntau cov software tau nkag mus tau ntau dua hauv ob peb xyoos dhau los.

Hauv kab lus no, kuv yuav los saib qhov kev ua tau zoo ntawm ClickHouse pawg ntawm AWS EC2 siv 36-core processors thiab NVMe cia.

Hloov tshiab: Ib lub lim tiam tom qab pib tshaj tawm cov ntawv tshaj tawm no, kuv rov ua qhov kev sim nrog kev txhim kho thiab ua tiav cov txiaj ntsig zoo dua. Cov ntawv tshaj tawm no tau hloov kho kom pom cov kev hloov pauv no.

Launching AWS EC2 Cluster

Kuv yuav siv peb c5d.9xlarge EC2 piv txwv rau cov ntawv no. Txhua ntawm lawv muaj 36 virtual CPUs, 72 GB ntawm RAM, 900 GB ntawm NVMe SSD cia thiab txhawb nqa 10 Gigabit network. Lawv raug nqi $ 1,962 / teev txhua tus hauv cheeb tsam eu-west-1 thaum khiav ntawm kev thov. Kuv yuav siv Ubuntu Server 16.04 LTS ua lub operating system.

Lub firewall tau teeb tsa kom txhua lub tshuab tuaj yeem sib txuas lus nrog txhua tus yam tsis muaj kev txwv, thiab tsuas yog kuv qhov chaw nyob IPv4 tau teev npe dawb los ntawm SSH hauv pawg.

NVMe tsav hauv lub xeev npaj ua haujlwm

Rau ClickHouse ua haujlwm, Kuv yuav tsim cov ntaub ntawv hauv EXT4 hom ntawm NVMe tsav ntawm txhua tus servers.

$ sudo mkfs -t ext4 /dev/nvme1n1
$ sudo mkdir /ch
$ sudo mount /dev/nvme1n1 /ch

Thaum txhua yam teeb tsa, koj tuaj yeem pom qhov taw tes mount thiab 783 GB ntawm qhov chaw muaj nyob ntawm txhua qhov system.

$ 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

Cov ntaub ntawv kuv yuav siv hauv qhov kev sim no yog cov ntaub ntawv pov tseg uas kuv tau tsim los ntawm 1.1 billion lub tsheb tavxij caij tsheb hauv New York City tshaj rau xyoo. Hauv blog Ib Billion Taxi Trips hauv Redshift paub meej tias kuv sau cov ntaub ntawv no li cas. Lawv tau khaws cia rau hauv AWS S3, yog li kuv yuav teeb tsa AWS CLI nrog kuv nkag mus thiab cov yuam sij zais cia.

$ sudo apt update
$ sudo apt install awscli
$ aws configure

Kuv mam li teeb tsa tus neeg siv qhov kev thov ib ntus rau 100 kom cov ntaub ntawv rub tawm sai dua li qhov chaw pib.

$ aws configure set 
    default.s3.max_concurrent_requests 
    100

Kuv mam li rub tawm cov ntaub ntawv caij tsheb tavxij los ntawm AWS S3 thiab khaws cia rau ntawm NVMe tsav ntawm thawj server. Cov ntaub ntawv no yog ~ 104GB hauv GZIP-compressed CSV hom.

$ sudo mkdir -p /ch/csv
$ sudo chown -R ubuntu /ch/csv
$ aws s3 sync s3://<bucket>/csv /ch/csv

NyemHouse installation

Kuv yuav nruab OpenJDK faib rau Java 8 raws li nws yuav tsum tau khiav Apache ZooKeeper, uas yuav tsum tau rau ib tug faib installation ntawm ClickHouse ntawm tag nrho peb lub tshuab.

$ sudo apt update
$ sudo apt install 
    openjdk-8-jre 
    openjdk-8-jdk-headless

Tom qab ntawd kuv teeb tsa ib puag ncig hloov pauv JAVA_HOME.

$ sudo vi /etc/profile
 
export JAVA_HOME=/usr
 
$ source /etc/profile

Tom qab ntawd kuv yuav siv Ubuntu lub pob tswj qhov system los nruab ClickHouse 18.16.1, saib thiab ZooKeeper ntawm tag nrho peb lub tshuab.

$ 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

Kuv mam li tsim ib daim ntawv teev npe rau ClickHouse thiab tseem ua qee qhov kev teeb tsa overrides ntawm tag nrho peb lub servers.

$ 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

Cov no yog cov configuration overrides uas kuv yuav siv.

<?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>

Tom qab ntawd kuv yuav khiav ZooKeeper thiab ClickHouse server ntawm tag nrho peb lub tshuab.

$ sudo /etc/init.d/zookeeper start
$ sudo service clickhouse-server start

Uploading cov ntaub ntawv rau ClickHouse

Nyob rau thawj server kuv yuav tsim ib lub rooj mus txawv tebchaws (trips), uas yuav khaws cov ntaub ntawv ntawm cov tsheb tavxij mus ncig uas siv lub cav cav.

$ 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;

Tom qab ntawd kuv rho tawm thiab thauj txhua CSV cov ntaub ntawv rau hauv lub rooj mus ncig (trips). Cov hauv qab no tau ua tiav hauv 55 feeb thiab 10 vib nas this. Tom qab ua haujlwm no, qhov loj ntawm cov ntaub ntawv teev npe yog 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)

Tus ceev ntshuam yog 155 MB ntawm uncompressed CSV cov ntsiab lus ib ob. Kuv xav tias qhov no yog vim muaj kev tsis sib haum xeeb hauv GZIP decompression. Tej zaum nws yuav tau sai dua rau unzip tag nrho cov ntaub ntawv gzip nyob rau hauv parallel siv xargs thiab ces thauj cov ntaub ntawv unzipped. Hauv qab no yog cov lus piav qhia ntawm qhov tau tshaj tawm thaum lub sijhawm CSV ntshuam txheej txheem.

$ 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

Kuv mam li tso qhov chaw ntawm NVMe tsav los ntawm kev rho tawm cov ntaub ntawv CSV thawj zaug ua ntej txuas ntxiv.

$ sudo rm -fr /ch/csv

Hloov mus rau kab ntawv

Lub cav ClickHouse yuav khaws cov ntaub ntawv nyob rau hauv ib kab-taw qhia kom paub hom ntawv. Txhawm rau nug cov ntaub ntawv sai dua, kuv hloov nws mus rau kab ntawv hom siv lub tshuab MergeTree.

$ clickhouse-client --host=0.0.0.0

Cov hauv qab no tau ua tiav hauv 34 feeb thiab 50 vib nas this. Tom qab ua haujlwm no, qhov loj ntawm cov ntaub ntawv teev npe yog 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;

Qhov no yog dab tsi glance tso zis zoo li thaum lub sijhawm ua haujlwm:

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)

Hauv kev xeem dhau los, ob peb kab tau hloov dua siab tshiab thiab rov suav dua. Kuv pom tias qee qhov haujlwm no tsis ua haujlwm raws li qhov xav tau ntawm cov ntaub ntawv no. Txhawm rau daws qhov teeb meem no, kuv tshem tawm cov haujlwm tsis tsim nyog thiab thauj cov ntaub ntawv tsis hloov mus rau ntau hom granular.

Kev faib tawm cov ntaub ntawv thoob plaws hauv pawg

Kuv yuav faib cov ntaub ntawv hla tag nrho peb pawg nodes. Txhawm rau pib, hauv qab no kuv yuav tsim ib lub rooj ntawm tag nrho peb lub tshuab.

$ 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);

Tom qab ntawd kuv yuav xyuas kom meej tias thawj tus neeg rau zaub mov tuaj yeem pom tag nrho peb cov nodes hauv pawg.

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:

Tom qab ntawd kuv yuav txhais ib lub rooj tshiab ntawm thawj tus neeg rau zaub mov uas yog raws li schema trips_mergetree_third thiab siv Distributed engine.

CREATE TABLE trips_mergetree_x3
    AS trips_mergetree_third
    ENGINE = Distributed(perftest_3shards,
                         default,
                         trips_mergetree_third,
                         rand());

Kuv mam li luam cov ntaub ntawv los ntawm MergeTree raws li lub rooj rau tag nrho peb lub servers. Cov hauv qab no tau ua tiav hauv 34 feeb thiab 44 vib nas this.

INSERT INTO trips_mergetree_x3
    SELECT * FROM trips_mergetree;

Tom qab ua haujlwm saum toj no, kuv muab ClickHouse 15 feeb kom txav deb ntawm qhov siab tshaj plaws cia qib cim. Cov ntaub ntawv teev npe tau dhau los ua 264 GB, 34 GB thiab 33 GB feem ntawm txhua tus ntawm peb lub servers.

ClickHouse pawg kev ntsuas kev ua tau zoo

Qhov kuv pom tom ntej no yog lub sijhawm ceev tshaj plaws uas kuv tau pom khiav txhua qhov lus nug ntawm lub rooj ntau zaus trips_mergetree_x3.

$ clickhouse-client --host=0.0.0.0

Cov nram qab no ua tiav hauv 2.449 vib nas this.

SELECT cab_type, count(*)
FROM trips_mergetree_x3
GROUP BY cab_type;

Cov nram qab no ua tiav hauv 0.691 vib nas this.

SELECT passenger_count,
       avg(total_amount)
FROM trips_mergetree_x3
GROUP BY passenger_count;

Cov nram qab no ua tiav hauv 0 vib nas this.

SELECT passenger_count,
       toYear(pickup_date) AS year,
       count(*)
FROM trips_mergetree_x3
GROUP BY passenger_count,
         year;

Cov nram qab no ua tiav hauv 0.983 vib nas this.

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;

Rau kev sib piv, kuv tau khiav tib cov lus nug ntawm MergeTree-raws li lub rooj uas nyob rau ntawm thawj server.

Kev ntsuas kev ua tau zoo ntawm ib qho ClickHouse node

Qhov kuv pom tom ntej no yog lub sijhawm ceev tshaj plaws uas kuv tau pom khiav txhua qhov lus nug ntawm lub rooj ntau zaus trips_mergetree_x3.

Cov nram qab no ua tiav hauv 0.241 vib nas this.

SELECT cab_type, count(*)
FROM trips_mergetree
GROUP BY cab_type;

Cov nram qab no ua tiav hauv 0.826 vib nas this.

SELECT passenger_count,
       avg(total_amount)
FROM trips_mergetree
GROUP BY passenger_count;

Cov nram qab no ua tiav hauv 1.209 vib nas this.

SELECT passenger_count,
       toYear(pickup_date) AS year,
       count(*)
FROM trips_mergetree
GROUP BY passenger_count,
         year;

Cov nram qab no ua tiav hauv 1.781 vib nas this.

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;

Reflections ntawm qhov tshwm sim

Nov yog thawj zaug uas cov ntaub ntawv pub dawb CPU-raws li muaj peev xwm ua tau zoo dua GPU-raws li database hauv kuv qhov kev sim. GPU-raws li database tau dhau los ntawm ob qhov kev hloov kho txij thaum ntawd los, tab sis qhov kev ua tau zoo uas ClickHouse tau xa tawm ntawm ib qho ntawm qhov tseem ceeb heev.

Nyob rau tib lub sijhawm, thaum ua tiav Cov Lus Nug 1 ntawm lub tshuab xa tawm, cov nqi nyiaj siv ua haujlwm yog qhov kev txiav txim siab dua. Kuv vam tias kuv plam qee yam hauv kuv qhov kev tshawb fawb rau cov ntawv tshaj tawm no vim tias nws yuav zoo rau pom cov lus nug hauv qab thaum kuv ntxiv cov nodes rau pawg. Txawm li cas los xij, nws yog qhov zoo uas thaum ua tiav lwm cov lus nug, kev ua haujlwm tau nce li ntawm 2 zaug.

Nws yuav yog qhov zoo kom pom ClickHouse hloov zuj zus mus rau qhov muaj peev xwm cais qhov chaw cia thiab suav kom lawv tuaj yeem ntsuas nws tus kheej. Kev txhawb nqa HDFS, uas tau ntxiv rau xyoo tas los, tuaj yeem yog kauj ruam ntawm qhov no. Hais txog kev suav, yog tias ib qho lus nug tuaj yeem nrawm los ntawm kev ntxiv cov nodes rau pawg, tom qab ntawd lub neej yav tom ntej ntawm cov software no yog qhov kaj heev.

Ua tsaug rau koj siv sijhawm los nyeem cov ntawv no. Kuv muab kev sab laj, architecture, thiab xyaum kev txhim kho kev pabcuam rau cov neeg siv khoom hauv North America thiab Europe. Yog tias koj xav tham txog seb kuv cov lus qhia yuav pab tau koj li cas, thov hu rau kuv ntawm LinkedIn.

Tau qhov twg los: www.hab.com

Ntxiv ib saib