ClickHouse/docs/fa/getting_started/example_datasets/amplab_benchmark.md

137 lines
3.9 KiB
Markdown
Raw Normal View History

<div dir="rtl" markdown="1">
# بنچمارک AMPLab Big Data
ببینید <https://amplab.cs.berkeley.edu/benchmark/>
با یک اکانت مجانی در <https://aws.amazon.com> ثبت نام کنید. شما نیاز به ایمیل، شماره تلفن و credit card دارید. یک Access key جدید از <https://console.aws.amazon.com/iam/home?nc2=h_m_sc#security_credential> دریافت کنید.
در کنسول این دستورات را وارد کنید:
</div>
```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 ..
```
<div dir="rtl" markdown="1">
این query های ClickHouse را اجرا کنید:
</div>
```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);
```
<div dir="rtl" markdown="1">
به کنسول برگردید و دستورات زیر را مجددا اجرا کنید:
</div>
```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
```
<div dir="rtl" markdown="1">
query های گرفتن data sample
</div>
```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
```