Hi Harry,
When dynamic resharding was introduced for luminous, this limit on the
number of bucket index shards was increased from 7877 to 65521. However,
you're likely to have problems with bucket listing performance before
you get to 7877 shards, because every listing request has to read from
every shard of the bucket in order to produce sorted results.
If you can avoid listings entirely, indexless buckets are recommended.
Otherwise, you can use our 'allow-unordered' extension to the s3 GET
Bucket api [1] which is able to list one shard at a time for better
scaling with shard count. Note that there was a bug [2] affecting this
extension that was resolved for v12.2.13, v13.2.6, and v14.2.2.
[1] http://docs.ceph.com/docs/luminous/radosgw/s3/bucketops/#get-bucket
[2] http://tracker.ceph.com/issues/39393
On 6/17/19 11:00 AM, Harald Staub wrote:
There are customers asking for 500 million objects in a single object
storage bucket (i.e. 5000 shards), but also more. But we found some
places that say that there is a limit in the number of shards per
bucket, e.g.
https://access.redhat.com/documentation/en-us/red_hat_ceph_storage/2/html/object_gateway_guide_for_ubuntu/administration_cli
It says that the maximum number of shards is 7877. But I could not
find this magic number (or any other limit) on http://docs.ceph.com.
Maybe this hard limit no longer applies to Nautilus? Maybe there is a
recommended soft limit?
Background about the application: Veeam (veeam.com) is a backup
solution for VMWare that can embed a cloud storage tier with object
storage (only with a single bucket). Just thinking loud: Maybe this
could work with an indexless bucket. Not sure how manageable this
would be, e.g. to monitor how much space is used. Maybe separate pools
would be needed.
Harry
_______________________________________________
ceph-users mailing list
ceph-users@xxxxxxxxxxxxxx
http://lists.ceph.com/listinfo.cgi/ceph-users-ceph.com
_______________________________________________
ceph-users mailing list
ceph-users@xxxxxxxxxxxxxx
http://lists.ceph.com/listinfo.cgi/ceph-users-ceph.com
