【详述】
使用的 orcale 云的对象存储, 支持 S3 协议,
INSERT INTO FILES 导出到 S3 报错:
[2025-03-25 14:40:59] [HY000][5025] S3: Fail to create multipart upload for object bd-ml-bucket/test/fe75d7f4-0943-11f0-bb98-a25014ad5001_0_0_0.parquet: curlCode: 60, SSL peer certificate or SSH remote key was not OK
执行的 sql:
INSERT INTO
FILES(
"path" = "s3://bd-ml-bucket/test/",
"format" = "parquet",
"compression" = "lz4",
"aws.s3.access_key" = "xxx",
"aws.s3.secret_key" = "xxx",
"aws.s3.region" = "us-phoenix-1",
"aws.s3.endpoint" = "https://axwzipgcxxtm.compat.objectstorage.us-phoenix-1.oraclecloud.com",
"target_max_file_size" = "536870912"
)
SELECT * FROM dms.rtb_ml_bundle where __d = '20250324' limit 100;
表结构:
CREATE TABLE `rtb_ml_bundle` (
`__d` date NOT NULL COMMENT "",
`ifa` varchar(1048576) NULL COMMENT "",
`media_bundle_array` array<varchar(65533)> NULL COMMENT "",
`bundle_info` map<varchar(65533),varchar(65533)> NULL COMMENT "",
`make` varchar(1048576) NULL COMMENT "",
`model` varchar(1048576) NULL COMMENT "",
`os_version` varchar(1048576) NULL COMMENT "",
`lang_code` varchar(1048576) NULL COMMENT "",
`region` varchar(1048576) NULL COMMENT "",
`max_rating` decimal(7, 4) NULL COMMENT "",
`min_rating` decimal(7, 4) NULL COMMENT "",
`latest_day` int(11) NULL COMMENT "",
`country` varchar(65533) NOT NULL COMMENT ""
) ENGINE=OLAP
DUPLICATE KEY(`__d`)
COMMENT "OLAP"
PARTITION BY date_trunc('day', __d)
DISTRIBUTED BY HASH(`country`, `ifa`) BUCKETS 100
PROPERTIES (
"compression" = "LZ4",
"datacache.enable" = "false",
"enable_async_write_back" = "false",
"partition_live_number" = "2",
"replication_num" = "1",
"storage_volume" = "volume_s3"
);
【背景】执行导出操作
【业务影响】无法导出数据
【是否存算分离】是
【StarRocks版本】3.3.9
【集群规模】3fe + 16 cn
【机器信息】CPU虚拟核/内存/网卡,例如:48C/64G/万兆
【表模型】:明细表
【导入或者导出方式】 INSERT INTO FILES
【联系方式】StarRocks 3.0-存算分离用户群: 可以自然点嘛
【附件】
经过测试, 发现桶的命名中如果包含减号-
就会报错, 如果将 -
替换成下划线_
,
即: 桶名bd-ml-bucket
改为 bd_ml_bucket
, 能够正常导出
修改后的 sql:
INSERT INTO
FILES(
"path" = "s3://bd_ml_bucket/test/",
"format" = "parquet",
"compression" = "lz4",
"aws.s3.access_key" = "xxx",
"aws.s3.secret_key" = "xxx",
"aws.s3.region" = "us-phoenix-1",
"aws.s3.endpoint" = "https://axwzipgcxxtm.compat.objectstorage.us-phoenix-1.oraclecloud.com",
"target_max_file_size" = "536870912"
)
SELECT * FROM dms.rtb_ml_bundle where __d = '20250324' limit 100;
请核查一下,这个是否是个 bug