ClickHouse/docs/es/getting-started/example-datasets/amplab-benchmark.md
2020-10-13 20:23:29 +03:00

4.0 KiB

machine_translated machine_translated_rev toc_priority toc_title
true 72537a2d52 17 Referencia de Big Data de AMPLab

Referencia de Big Data de AMPLab

Ver https://amplab.cs.berkeley.edu/benchmark/

Regístrese para obtener una cuenta gratuita en https://aws.amazon.com. Requiere una tarjeta de crédito, correo electrónico y número de teléfono. Obtenga una nueva clave de acceso en https://console.aws.amazon.com/iam/home?nc2=h_m_sc#security_credential

Ejecute lo siguiente en la consola:

$ sudo apt-get install s3cmd
$ mkdir tiny; cd tiny;
$ s3cmd sync s3://big-data-benchmark/pavlo/text-deflate/tiny/ .
$ cd ..
$ mkdir 1node; cd 1node;
$ s3cmd sync s3://big-data-benchmark/pavlo/text-deflate/1node/ .
$ cd ..
$ mkdir 5nodes; cd 5nodes;
$ s3cmd sync s3://big-data-benchmark/pavlo/text-deflate/5nodes/ .
$ cd ..

Ejecute las siguientes consultas de ClickHouse:

CREATE TABLE rankings_tiny
(
    pageURL String,
    pageRank UInt32,
    avgDuration UInt32
) ENGINE = Log;

CREATE TABLE uservisits_tiny
(
    sourceIP String,
    destinationURL String,
    visitDate Date,
    adRevenue Float32,
    UserAgent String,
    cCode FixedString(3),
    lCode FixedString(6),
    searchWord String,
    duration UInt32
) ENGINE = MergeTree(visitDate, visitDate, 8192);

CREATE TABLE rankings_1node
(
    pageURL String,
    pageRank UInt32,
    avgDuration UInt32
) ENGINE = Log;

CREATE TABLE uservisits_1node
(
    sourceIP String,
    destinationURL String,
    visitDate Date,
    adRevenue Float32,
    UserAgent String,
    cCode FixedString(3),
    lCode FixedString(6),
    searchWord String,
    duration UInt32
) ENGINE = MergeTree(visitDate, visitDate, 8192);

CREATE TABLE rankings_5nodes_on_single
(
    pageURL String,
    pageRank UInt32,
    avgDuration UInt32
) ENGINE = Log;

CREATE TABLE uservisits_5nodes_on_single
(
    sourceIP String,
    destinationURL String,
    visitDate Date,
    adRevenue Float32,
    UserAgent String,
    cCode FixedString(3),
    lCode FixedString(6),
    searchWord String,
    duration UInt32
) ENGINE = MergeTree(visitDate, visitDate, 8192);

Volver a la consola:

$ for i in tiny/rankings/*.deflate; do echo $i; zlib-flate -uncompress < $i | clickhouse-client --host=example-perftest01j --query="INSERT INTO rankings_tiny FORMAT CSV"; done
$ for i in tiny/uservisits/*.deflate; do echo $i; zlib-flate -uncompress < $i | clickhouse-client --host=example-perftest01j --query="INSERT INTO uservisits_tiny FORMAT CSV"; done
$ for i in 1node/rankings/*.deflate; do echo $i; zlib-flate -uncompress < $i | clickhouse-client --host=example-perftest01j --query="INSERT INTO rankings_1node FORMAT CSV"; done
$ for i in 1node/uservisits/*.deflate; do echo $i; zlib-flate -uncompress < $i | clickhouse-client --host=example-perftest01j --query="INSERT INTO uservisits_1node FORMAT CSV"; done
$ for i in 5nodes/rankings/*.deflate; do echo $i; zlib-flate -uncompress < $i | clickhouse-client --host=example-perftest01j --query="INSERT INTO rankings_5nodes_on_single FORMAT CSV"; done
$ for i in 5nodes/uservisits/*.deflate; do echo $i; zlib-flate -uncompress < $i | clickhouse-client --host=example-perftest01j --query="INSERT INTO uservisits_5nodes_on_single FORMAT CSV"; done

Consultas para obtener muestras de datos:

SELECT pageURL, pageRank FROM rankings_1node WHERE pageRank > 1000

SELECT substring(sourceIP, 1, 8), sum(adRevenue) FROM uservisits_1node GROUP BY substring(sourceIP, 1, 8)

SELECT
    sourceIP,
    sum(adRevenue) AS totalRevenue,
    avg(pageRank) AS pageRank
FROM rankings_1node ALL INNER JOIN
(
    SELECT
        sourceIP,
        destinationURL AS pageURL,
        adRevenue
    FROM uservisits_1node
    WHERE (visitDate > '1980-01-01') AND (visitDate < '1980-04-01')
) USING pageURL
GROUP BY sourceIP
ORDER BY totalRevenue DESC
LIMIT 1

Artículo Original