Yes, those head objects are deleted inline and only the tail objects are
added to gc to be deleted once they expire.
Thanks,
Pritha
On Wed, Apr 15, 2020 at 4:25 PM Priya Sehgal <priya.sehgal(a)gmail.com> wrote:
Hi Pritha,
I tried running radosgw-admin gc list --include-all and it shows the
shadow objects.
One question - the above list only has list of shadow and multi-part
objects. So, objects that are less than 4MB - will they be not queued -
since they are part of the HEAD and the HEAD gets deleted when we issue
s3cmd del command?
Thanks,
Priya
On Wed, Apr 15, 2020 at 3:33 PM Pritha Srivastava <prsrivas(a)redhat.com>
wrote:
Hi Priya,
Did you try to list the objects using radosgw-admin gc list immediately
after deleting them?
Try using the command: radosgw-admin gc list --include-all, this lists
all the expired and non expired entries.
radosgw-admin gc list, only lists entries that have expired. Objects that
have been gc'ed expire after a duration that is determined by
rgw_gc_obj_min_wait the default value of which is 2 hrs.
Thanks,
Pritha
On Wed, Apr 15, 2020 at 3:25 PM Priya Sehgal <priya.sehgal(a)gmail.com>
wrote:
> Hi,
> I read at many places that when an object is deleted from ceph it is
> queued
> for deletion with the garbage collector (GC). However, when I delete
> objects of various sizes (both less than 4MB and large sized greater than
> 4MB i.e. MPU) I always find gc list as empty.
> I tried disabling GC also to make sure that it does not run and delete
> it,
> yet I did not find any object when I run the command. Here's the output:
> *radosgw-admin gc list*
>
> [
> {
> "tag": "2~KsaJkJwSGeuVzeKpkHAe_5vJ3JqZmKc",
> "time": "2020-04-10 18:25:23.0.769037s",
> "objs": []
> }
> ]
>
> NOTE: I tried to delete an object as on 14th April and 15th April.
>
> I issued "s3cmd del" command.
> Ceph Version I am using in Luminous.
>
> Please let me know how object deletes work.
>
> --
> Regards,
> Priya
> _______________________________________________
> ceph-users mailing list -- ceph-users(a)ceph.io
> To unsubscribe send an email to ceph-users-leave(a)ceph.io
>
>
--
Regards,
Priya