Thanks for the tip

For the record, I fixed it using radosgw-admin bucket check
--bucket=<bucket-name> --check-objects --fix


On 10/09/2017 11:44, Andreas Calminder wrote:
> Hi,
> I had a similar problem on jewel, where I was unable to properly delete
> objects eventhough radosgw-admin returned rc 0 after issuing rm, somehow
> the object was deleted but the metadata wasn't removed.
> 
> I ran
> # radosgw-admin --cluster ceph object stat --bucket=weird_bucket
> --object=$OBJECT
> 
> to figure out if the object was there or not and then used the 'rados put'
> command to upload a dummy object and then remove it properly
> # rados -c /etc/ceph/ceph.conf -p ceph.rgw.buckets.data put
> be8fa19b-ad79-4cd8-ac7b-1e14fdc882f6.2384280.20_$OBJECT dummy.file
> 
> Hope it helps,
> Andreas
> 
> On 10 Sep 2017 1:20 a.m., "Jack" <c...@jack.fr.eu.org> wrote:
> 
>> Hi,
>>
>> I face a wild issue: I cannot remove an object from rgw (via s3 API)
>>
>> My steps:
>> s3cmd ls s3://bucket/object -> it exists
>> s3cmd rm s3://bucket/object -> success
>> s3cmd ls s3://bucket/object -> it still exists
>>
>> At this point, I can curl and get the object (thus, it does exists)
>>
>> Doing the same via boto leads to the same behavior
>>
>> Log sample:
>> 2017-09-10 01:18:42.502486 7fd189e7d700  1 ====== starting new request
>> req=0x7fd189e77300 =====
>> 2017-09-10 01:18:42.504028 7fd189e7d700  1 ====== req done
>> req=0x7fd189e77300 op status=-2 http_status=204 ======
>> 2017-09-10 01:18:42.504076 7fd189e7d700  1 civetweb: 0x560ebc275000:
>> 10.42.43.6 - - [10/Sep/2017:01:18:38 +0200] "DELETE /bucket/object
>> HTTP/1.1" 1 0 - Boto/2.44.0 Python/3.5.4 Linux/4.12.0-1-amd64
>>
>> What can I do ?
>> What data shall I provide to debug this issue ?
>>
>> Regards,
>> _______________________________________________
>> ceph-users mailing list
>> ceph-users@lists.ceph.com
>> http://lists.ceph.com/listinfo.cgi/ceph-users-ceph.com
>>
> 

_______________________________________________
ceph-users mailing list
ceph-users@lists.ceph.com
http://lists.ceph.com/listinfo.cgi/ceph-users-ceph.com

Reply via email to