Hi, I try to create buckets through rgw in following order: - *bucket1* with *user1* with *access_key1* and *secret_key1* - *bucket1* with *user2* with *access_key2* and *secret_key2* when I try to create a second bucket1 with user2 I get *Error response code BucketAlreadyExists.* Why? Should not buckets relate only to users? Is this by design and is there any particular reason that it follows this concept? Regards, Rok
Hi, On 08/06/2021 11:37, Rok Jaklič wrote:
I try to create buckets through rgw in following order: - *bucket1* with *user1* with *access_key1* and *secret_key1* - *bucket1* with *user2* with *access_key2* and *secret_key2*
when I try to create a second bucket1 with user2 I get *Error response code BucketAlreadyExists.*
Why? Should not buckets relate only to users? Is this by design and is there any particular reason that it follows this concept?
By default, there is one bucket namespace (which makes sense if you're going with the common bucket name as hostname pattern); you can do multi-tenancy if you want, however: https://docs.ceph.com/en/latest/radosgw/multitenancy/ Regards, Matthew -- The Wellcome Sanger Institute is operated by Genome Research Limited, a charity registered in England with number 1021457 and a company registered in England with number 2742969, whose registered office is 215 Euston Road, London, NW1 2BE.
Den tis 8 juni 2021 kl 12:38 skrev Rok Jaklič <rjaklic@gmail.com>:
Hi, I try to create buckets through rgw in following order: - *bucket1* with *user1* with *access_key1* and *secret_key1* - *bucket1* with *user2* with *access_key2* and *secret_key2*
when I try to create a second bucket1 with user2 I get *Error response code BucketAlreadyExists.*
Why? Should not buckets relate only to users? Is this by design and is there any particular reason that it follows this concept?
If you want to use http(s)://bucketname.domain.name/ to access buckets it certainly helps if they are uniquely named, no? Apart from that, there is a mode for RGW with tenant/bucketname where overlapping/duplicate bucket names are possible, but of course you will not get simple DNS-names for published content in that case. -- May the most significant bit of your life be positive.
Which mode is that and where can I set it? This one described in https://docs.ceph.com/en/latest/radosgw/multitenancy/ ? On Tue, Jun 8, 2021 at 2:24 PM Janne Johansson <icepic.dz@gmail.com> wrote:
Den tis 8 juni 2021 kl 12:38 skrev Rok Jaklič <rjaklic@gmail.com>:
Hi, I try to create buckets through rgw in following order: - *bucket1* with *user1* with *access_key1* and *secret_key1* - *bucket1* with *user2* with *access_key2* and *secret_key2*
when I try to create a second bucket1 with user2 I get *Error response code BucketAlreadyExists.*
Why? Should not buckets relate only to users? Is this by design and is there any particular reason that it follows this concept?
If you want to use http(s)://bucketname.domain.name/ to access buckets it certainly helps if they are uniquely named, no?
Apart from that, there is a mode for RGW with tenant/bucketname where overlapping/duplicate bucket names are possible, but of course you will not get simple DNS-names for published content in that case.
-- May the most significant bit of your life be positive.
Den tis 8 juni 2021 kl 14:31 skrev Rok Jaklič <rjaklic@gmail.com>:
Which mode is that and where can I set it? This one described in https://docs.ceph.com/en/latest/radosgw/multitenancy/ ?
Yes, the description says it all there, doesn't it?
Apart from that, there is a mode for RGW with tenant/bucketname where overlapping/duplicate bucket names are possible, but of course you will not get simple DNS-names for published content in that case.
-- May the most significant bit of your life be positive.
participants (3)
-
Janne Johansson
-
Matthew Vernon
-
Rok Jaklič