- nebula 版本:v1.2.0
- 部署方式(分布式 / 单机 / Docker / DBaaS):Docker
- 硬件信息
- 磁盘( 必须为 SSD ,不支持 HDD):SSD
- CPU、内存信息:24核48线程、378GB
ID Name Partition number Replica Factor Charset Collate
133 knowledge_2hm 15 3 utf8 utf8_bin
- 问题的具体描述
spark导入任务启动一段时间以后,会出现:
21/01/20 15:00:06 ERROR AbstractNebulaCallback: onError: java.util.concurrent.TimeoutException: Operation class com.vesoft.nebula.graph.GraphService$AsyncClient$execute_call timed out after 5005 ms.
java.util.concurrent.TimeoutException: Operation class com.vesoft.nebula.graph.GraphService$AsyncClient$execute_call timed out after 5005 ms.
at com.facebook.thrift.async.TAsyncClientManager$SelectThread.timeoutMethods(TAsyncClientManager.java:157)
at com.facebook.thrift.async.TAsyncClientManager$SelectThread.run(TAsyncClientManager.java:114)
然后整个spark任务就卡住了,好几个小时都不动。
导入的exchange配置文件如下:
{
spark: {
app: {
name: Spark Writer
}
driver: {
cores: 2
maxResultSize: 8G
}
cores {
max: 8
}
}
nebula: {
address: {
graph: ["10.38.16.87:3699", "10.38.16.87:3700", "10.38.16.87:3701"]
meta: ["10.38.16.87:45501"]
}
user: user
pswd: password
space: knowledge_2hm
connection {
timeout: 5000
retry: 3
}
execution {
retry: 3
}
error: {
max: 32
output: /tmp/errors
}
rate: {
limit: 1024
timeout: 1000
}
}
tags: [
{
name: Thing
type: {
source: hive
sink: client
}
exec: "select thing_id, thing_name, thing_namech, thing_nameen, thing_abbreviation, thing_tag, thing_alias, thing_abstract, thing_image, thing_video, thing_audio, thing_gmtcreated, thing_gmtmodified, thing_popularity, thing_prior, thing_datasource, thing_urls from oppo_kg_dw.thing_20210103 where ds = '20210103'"
fields: [thing_name, thing_namech, thing_nameen, thing_abbreviation, thing_tag, thing_alias, thing_abstract, thing_image, thing_video, thing_audio, thing_gmtcreated, thing_gmtmodified, thing_popularity, thing_prior, thing_datasource, thing_urls]
nebula.fields: [Thing_name, Thing_nameCh, Thing_nameEn, Thing_abbreviation, Thing_tag, Thing_alias, Thing_abstract, Thing_image, Thing_video, Thing_audio, Thing_gmtCreated, Thing_gmtModified, Thing_popularity, Thing_prior, Thing_dataSource, Thing_urls]
vertex: thing_id
isImplicit: true
batch: 128
partition: 8
}
]
edges: [
{
name: Thing_type
type: {
source: hive
sink: client
}
exec: "select src_id, dst_id from oppo_kg_dw.edge_20210103 where ds = '20210103' and edge_label = 'Thing_type'"
fields: []
nebula.fields: []
source: src_id
target: dst_id
isImplicit: true
batch: 256
partition: 8
}
]
}