mirror of
https://github.com/ClickHouse/ClickHouse.git
synced 2024-12-15 02:41:59 +00:00
4.0 KiB
4.0 KiB
slug | sidebar_label | description |
---|---|---|
/ja/getting-started/example-datasets/amplab-benchmark | AMPLab ビッグデータベンチマーク | データウェアハウスソリューションのパフォーマンスを比較するために使用されるベンチマークデータセット。 |
AMPLab ビッグデータベンチマーク
詳細は https://amplab.cs.berkeley.edu/benchmark/ をご覧ください。
https://aws.amazon.com で無料アカウントに登録してください。クレジットカード、メールアドレス、電話番号が必要です。https://console.aws.amazon.com/iam/home?nc2=h_m_sc#security_credential から新しいアクセスキーを取得してください。
コンソールで以下を実行します:
$ 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 ..
以下の ClickHouse クエリを実行します:
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);
コンソールに戻ります:
$ 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
データサンプルを取得するためのクエリ:
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