Re: Ceph very slow bucket listing performance! how to deal with it.

[Date Prev][Date Next][Thread Prev][Thread Next][Date Index][Thread Index]

 



I encountered a ceph 14.2.8 bug. and have to upgrade to 14.2.11 to solve this issue.

发自我的iPhone

> 在 2021年10月15日,17:01,Xianqiang Jing <jingxianqiang11@xxxxxxx> 写道:
> 
> Here is the bucket stats. I have manually set the adasupload bucket reshard number to 2000. with this command "radosgw-admin reshard add --bucket adasupload --num-shards 2000" 
> but seems not work.
> 
> 
> [root@mon1 ~]# radosgw-admin metadata list bucket.instance
> [
>    "druid:e0c3bcaa-084b-4919-8a31-d17b6b9e143d.54345.100",
>    "adasdownload:e0c3bcaa-084b-4919-8a31-d17b6b9e143d.170081.1",
>    "adasupload:e0c3bcaa-084b-4919-8a31-d17b6b9e143d.183240.1",
>    "adastest:e0c3bcaa-084b-4919-8a31-d17b6b9e143d.169872.2",
>    "autotech:e0c3bcaa-084b-4919-8a31-d17b6b9e143d.54345.92",
>    "product:e0c3bcaa-084b-4919-8a31-d17b6b9e143d.84929.1",
>    "autonomy:e0c3bcaa-084b-4919-8a31-d17b6b9e143d.54345.102",
>    "develop:e0c3bcaa-084b-4919-8a31-d17b6b9e143d.84929.2"
> ]
> [root@mon1 ~]# radosgw-admin metadata get bucket.instance:adasupload:e0c3bcaa-084b-4919-8a31-d17b6b9e143d.183240.1
> {
>    "key": "bucket.instance:adasupload:e0c3bcaa-084b-4919-8a31-d17b6b9e143d.183240.1",
>    "ver": {
>        "tag": "vBLl2vUlOaG844VfviRjKQm7",
>        "ver": 2
>    },
>    "mtime": "2021-10-15 06:23:38.938000Z",
>    "data": {
>        "bucket_info": {
>            "bucket": {
>                "name": "adasupload",
>                "marker": "e0c3bcaa-084b-4919-8a31-d17b6b9e143d.54345.93",
>                "bucket_id": "e0c3bcaa-084b-4919-8a31-d17b6b9e143d.183240.1",
>                "tenant": "",
>                "explicit_placement": {
>                    "data_pool": "",
>                    "data_extra_pool": "",
>                    "index_pool": ""
>                }
>            },
>            "creation_time": "2021-02-07 03:25:21.724340Z",
>            "owner": "adasupload",
>            "flags": 0,
>            "zonegroup": "87a57eeb-2beb-48c6-b1db-2849cd3a4437",
>            "placement_rule": "default-placement",
>            "has_instance_obj": "true",
>            "quota": {
>                "enabled": false,
>                "check_on_raw": false,
>                "max_size": -1,
>                "max_size_kb": 0,
>                "max_objects": -1
>            },
>            "num_shards": 2000,
>            "bi_shard_hash_type": 0,
>            "requester_pays": "false",
>            "has_website": "false",
>            "swift_versioning": "false",
>            "swift_ver_location": "",
>            "index_type": 0,
>            "mdsearch_config": [],
>            "reshard_status": 0,
>            "new_bucket_instance_id": ""
>        },
>        "attrs": [
>            {
>                "key": "user.rgw.acl",
>                "val": "AgKfAAAAAwIcAAAACgAAAGFkYXN1cGxvYWQKAAAAYWRhc3VwbG9hZAQDdwAAAAEBAAAACgAAAGFkYXN1cGxvYWQPAAAAAQAAAAoAAABhZGFzdXBsb2FkBQNAAAAAAgIEAAAAAAAAAAoAAABhZGFzdXBsb2FkAAAAAAAAAAACAgQAAAAPAAAACgAAAGFkYXN1cGxvYWQAAAAAAAAAAAAAAAAAAAAA"
>            },
>            {
>                "key": "user.rgw.iam-policy",
>                "val": "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"
>            }
>        ]
>    }
> }
> 
> 
> 
> 
> 签名由网易邮箱大师定制
> On 10/15/2021 16:55,Janne Johansson<icepic.dz@xxxxxxxxx> wrote:
> Is the bucket sharded? Did you tell the rgw's that listing unordered is allowed?
> 
> https://docs.ceph.com/en/latest/radosgw/s3/bucketops/#get-bucket
> 
> Den fre 15 okt. 2021 kl 10:52 skrev Xianqiang Jing <jingxianqiang11@xxxxxxx>:
> 
> I have a ceph cluster with 3 rgws.  I created a few buckets, then put 5800000 object in one bucket. when i use “s3cmd ls s3://adasupload/parsed/" it will take a long time to response, sometimes it will response a timeout error.
> root@mon1 ~]# s3cmd -c s3cfg-adasupload ls s3://adasupload/parsed
> WARNING: Retrying failed request: /?delimiter=%2F&prefix=parsed (timed out)
> WARNING: Waiting 3 sec...
> WARNING: Retrying failed request: /?delimiter=%2F&prefix=parsed (timed out)
> WARNING: Waiting 6 sec...
> WARNING: Retrying failed request: /?delimiter=%2F&prefix=parsed (timed out)
> WARNING: Waiting 9 sec...
> WARNING: Retrying failed request: /?delimiter=%2F&prefix=parsed (timed out)
> WARNING: Waiting 12 sec...
> 
> 
> Anyone can give me some suggestion???
> 
> 
> 
> xjing@xxxxxxxxxx
> _______________________________________________
> ceph-users mailing list -- ceph-users@xxxxxxx
> To unsubscribe send an email to ceph-users-leave@xxxxxxx
> 
> 
> 
> --
> May the most significant bit of your life be positive.
> _______________________________________________
> ceph-users mailing list -- ceph-users@xxxxxxx
> To unsubscribe send an email to ceph-users-leave@xxxxxxx
> _______________________________________________
> ceph-users mailing list -- ceph-users@xxxxxxx
> To unsubscribe send an email to ceph-users-leave@xxxxxxx

_______________________________________________
ceph-users mailing list -- ceph-users@xxxxxxx
To unsubscribe send an email to ceph-users-leave@xxxxxxx




[Index of Archives]     [Information on CEPH]     [Linux Filesystem Development]     [Ceph Development]     [Ceph Large]     [Ceph Dev]     [Linux USB Development]     [Video for Linux]     [Linux Audio Users]     [Yosemite News]     [Linux Kernel]     [Linux SCSI]     [xfs]


  Powered by Linux