mirror of
https://github.com/ClickHouse/ClickHouse.git
synced 2024-10-04 23:50:50 +00:00
132 lines
4.2 KiB
Markdown
132 lines
4.2 KiB
Markdown
---
|
||
machine_translated: true
|
||
machine_translated_rev: 72537a2d527c63c07aa5d2361a8829f3895cf2bd
|
||
toc_priority: 17
|
||
toc_title: "\u0645\u0639\u06CC\u0627\u0631 \u0628\u0632\u0631\u06AF \u062F\u0627\u062F\
|
||
\u0647 \u0647\u0627\u06CC \u062A\u0642\u0648\u06CC\u062A \u06A9\u0646\u0646\u062F\
|
||
\u0647"
|
||
---
|
||
|
||
# معیار بزرگ داده های تقویت کننده {#amplab-big-data-benchmark}
|
||
|
||
ببینید https://amplab.cs.berkeley.edu/benchmark/
|
||
|
||
ثبت نام برای یک حساب کاربری رایگان در https://aws.amazon.com. این نیاز به یک کارت اعتباری, پست الکترونیک, و شماره تلفن. یک کلید دسترسی جدید در https://console.aws.amazon.com/iam/home?nc2=h_m_sc#security_credential
|
||
|
||
زیر را در کنسول اجرا کنید:
|
||
|
||
``` bash
|
||
$ 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 ..
|
||
```
|
||
|
||
اجرای نمایش داده شد زیر کلیک:
|
||
|
||
``` sql
|
||
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);
|
||
```
|
||
|
||
بازگشت به کنسول:
|
||
|
||
``` bash
|
||
$ 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
|
||
```
|
||
|
||
نمایش داده شد برای اخذ نمونه داده ها:
|
||
|
||
``` sql
|
||
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
|
||
```
|
||
|
||
[مقاله اصلی](https://clickhouse.tech/docs/en/getting_started/example_datasets/amplab_benchmark/) <!--hide-->
|