Hi Matt,
We upgraded our cluster to 13.2.8 yesterday . After restarting radosgw, gc process successfully cleaned up those objects and omap.
thanks again !
By the way, for other users , in our case the backlog had been increased to more than 3 million. the cleanup after upgrading runs really fast and thus cpu on gc nodes costs much than usual. That may caused by our setting "rgw_gc_max_concurrent_io = 40 , rgw_gc_max_trim_chunk = 1024". The client IO of cluster is less than 300MB/s at that time, so the performance hasn't been affected much. However in our other test , speeding up gc for large amount of objects can cause severe performance degradation, so it's better to consider the current client IO level before upgrading.
_______________________________________________
ceph-users mailing list -- ceph-users@xxxxxxx
To unsubscribe send an email to ceph-users-leave@xxxxxxx
