Hi,
I have a production cluster and it is experiencing lot of DELETES since
many months. However, with the default gc configs - I did not see the
cluster space utilization going down. Moreover, the gc list has more than 4
million objects. I tried increasing the gc configs on 4 rados gateways and
Hi,
We have a large production cluster with Writeback Cache Tier. Recently, we
observed that some of the OSDs were near full and got full from the Cache
Tier and the cluster is in error state. The target_max_bytes was not set
correctly and hence I think the flush and eviction never happened.
I
Thanks. This is helpful.
On Wed 15 Apr, 2020, 9:39 PM Pritha Srivastava, wrote:
> 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 Seh
ll, 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
&g
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
Hi,
I am trying to find out whether Ceph has a method to detect silent
corruption such as bit rot. I came across this text in a book - "Mastering
Ceph : Infrastructure Storage Solution with the latest Ceph release" by
Nick Fisk -
Luminous release of Ceph employs ZFS-like ability to checksum data