AMPLab 大数据基准测试

一个用于比较数据仓库解决方案性能的基准数据集。

请参见 https://amplab.cs.berkeley.edu/benchmark/

在 https://aws.amazon.com 注册一个免费账户。注册时需要提供信用卡、电子邮件地址和电话号码。请在 https://console.aws.amazon.com/iam/home?nc2=h_m_sc#security_credential 获取新的访问密钥

在终端中运行以下内容：

$ 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 ..

运行以下 ClickHouse 查询：

CREATE TABLE rankings_tiny
(
    pageURL String,
    pageRank UInt32,
    avgDuration UInt32
) ENGINE = MergeTree
ORDER BY ();

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 = MergeTree
ORDER BY ();

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 = MergeTree
ORDER BY ();

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);

返回控制台：

$ 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

获取数据样本的查询：

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