本月初，SeaTunnel同步计算引擎STE 2.3.0 beta2（commit id 7393c47）在社区的共同努力之下正式发布。与此同时，社区对大家期待的性能指标进行了测试。
为了让大家对测试结果有一个更直观的概念，我们采用了对比测试的方法。熟悉数据集成领域的人应该了解，DataX是目前数据开源同步引擎里，性能较好的同步工具之一，这次SeaTunnel做对比的对象，正是这款目前在数据集成领域使用较多的开源同步引擎。
为了保证对比测试的准确性，我们选取了相同的测试场景：在相同的资源情况下，测试DataX和SeaTunnel将数据批量从MySQL同步到HDFS，以Text格式保存，所需要花费的时间，并进行对比。
1
测试环境
MySQL
阿里云RDS MySQL 8Core 32G
HDFS
CPU：Intel(R) Xeon(R) Platinum 8369B CPU @ 2.70GHz
Memory：32G
节点数：3
NameNode -Xmx4G
DataNode -Xmx16G
2
测试数据
列数：31
行数：32226320 （3000万条）
大小：数据写入HDFS（text格式）大小为18G
create table test.type_source_table
(
id int auto_increment
primary key,
f_binary binary(64) null,
f_blob blob null,
f_long_varbinary mediumblob null,
f_longblob longblob null,
f_tinyblob tinyblob null,
f_varbinary varbinary(100) null,
f_smallint smallint null,
f_smallint_unsigned smallint unsigned null,
f_mediumint mediumint null,
f_mediumint_unsigned mediumint unsigned null,
f_int int null,
f_int_unsigned int unsigned null,
f_integer int null,
f_integer_unsigned int unsigned null,
f_bigint bigint null,
f_bigint_unsigned bigint unsigned null,
f_numeric decimal null,
f_decimal decimal null,
f_float float null,
f_double double null,
f_double_precision double null,
f_longtext longtext null,
f_mediumtext mediumtext null,
f_text text null,
f_tinytext tinytext null,
f_varchar varchar(100) null,
f_date date null,
f_datetime datetime null,
f_time time null,
f_timestamp timestamp null
);
3
DataX任务配置
{
"job": {
"content": [
{
"reader": {
"name": "mysqlreader",
"parameter": {
"column": [
"id",
"f_binary",
"f_blob",
"f_long_varbinary",
"f_longblob",
"f_tinyblob",
"f_varbinary",
"f_smallint",
"f_smallint_unsigned",
"f_mediumint",
"f_mediumint_unsigned",
"f_int",
"f_int_unsigned",
"f_integer",
"f_integer_unsigned",
"f_bigint",
"f_bigint_unsigned",
"f_numeric",
"f_decimal",
"f_float",
"f_double",
"f_double_precision",
"f_longtext",
"f_mediumtext",
"f_text",
"f_tinytext",
"f_varchar",
"f_date",
"f_datetime",
"f_time",
"f_timestamp"
],
"connection": [
{
"jdbcUrl": [
"jdbc:mysql://seatunnel.rds.aliyuncs.com:3306/test"
],
"table": [
"type_source_table"
]
}
],
"password": "password",
"username": "root",
"splitPk": "id"
}
},
"writer": {
"name": "hdfswriter",
"parameter": {
"column": [
{
"name": "id",
"type": "INT"
},
{
"name": "f_binary",
"type": "STRING"
},
{
"name": "f_blob",
"type": "STRING"
},
{
"name": "f_long_varbinary",
"type": "STRING"
},
{
"name": "f_longblob",
"type": "STRING"
},
{
"name": "f_tinyblob",
"type": "STRING"
},
{
"name": "f_varbinary",
"type": "STRING"
},
{
"name": "f_smallint",
"type": "SMALLINT"
},
{
"name": "f_smallint_unsigned",
"type": "SMALLINT"
},
{
"name": "f_mediumint",
"type": "SMALLINT"
},
{
"name": "f_mediumint_unsigned",
"type": "SMALLINT"
},
{
"name": "f_int",
"type": "INT"
},
{
"name": "f_int_unsigned",
"type": "INT"
},
{
"name": "f_integer",
"type": "INT"
},
{
"name": "f_integer_unsigned",
"type": "INT"
},
{
"name": "f_bigint",
"type": "BIGINT"
},
{
"name": "f_bigint_unsigned",
"type": "BIGINT"
},
{
"name": "f_numeric",
"type": "DOUBLE"
},
{
"name": "f_decimal",
"type": "DOUBLE"
},
{
"name": "f_float",
"type": "FLOAT"
},
{
"name": "f_double",
"type": "DOUBLE"
},
{
"name": "f_double_precision",
"type": "DOUBLE"
},
{
"name": "f_longtext",
"type": "STRING"
},
{
"name": "f_mediumtext",
"type": "STRING"
},
{
"name": "f_text",
"type": "STRING"
},
{
"name": "f_tinytext",
"type": "STRING"
},
{
"name": "f_varchar",
"type": "STRING"
},
{
"name": "f_date",
"type": "DATE"
},
{
"name": "f_datetime",
"type": "TIMESTAMP"
},
{
"name": "f_time",
"type": "DATE"
},
{
"name": "f_timestamp",
"type": "TIMESTAMP"
}
],
"defaultFS": "hdfs://hadoop1:9000",
"fieldDelimiter": ",",
"fileName": "result",
"fileType": "text",
"path": "/test/result",
"writeMode": "append"
}
}
}
],
"setting": {
"speed": {
"channel": 8
}
}
}
}
4
SeaTunnel Engine任务配置
env {
# You can set engine configuration here
job.mode = "BATCH"
checkpoint.interval = 300000
#execution.checkpoint.data-uri = "hdfs://localhost:9000/checkpoint"
}
source {
# This is a example source plugin **only for test and demonstrate the feature source plugin**
jdbc{
url = "jdbc:mysql://seatunnel.mysql.rds.aliyuncs.com:3306/test"
driver = "com.mysql.cj.jdbc.Driver"
user = "root"
password = "password"
query = "select * from type_source_table"
partition_column = "id"
parallelism = 8
}
}
transform {
}
sink {
HdfsFile {
fs.defaultFS="hdfs://hadoop1:9000"
path="/test/result/"
field_delimiter="\t"
row_delimiter="\n"
file_name_expression="${transactionId}_${now}"
file_format="text"
filename_time_format="yyyy.MM.dd"
is_enable_transaction=true
}
}
5
结论
Apache SeaTunnel
往期推荐
点击“阅读原文”参与活动！
文章转载自SeaTunnel，如果涉嫌侵权，请发送邮件至：contact@modb.pro进行举报，并提供相关证据，一经查实，墨天轮将立刻删除相关内容。
