In Hammer, ceph does not keep track of which objects exist and which ones don't. The delete is trying to delete every possible object in the rbd. In Jewel, the object_map keeps track of which objects exist and the delete of that rbd would be drastically faster. If you were 1PB of data to the rbd, it would still take a couple days to delete the rbd. The faster way to delete a large empty rbd in Hammer would be to find the rbd prefix, run rados ls grepping for the prefix, and then use the rados command to delete the objects that exist for that rbd.
On Sun, Jul 16, 2017, 1:45 AM Alvaro Soto <alsot...@gmail.com> wrote: > Hi, > does anyone have experienced or know why the delete process takes longer > that a creation of a RBD volume. > > My test was this: > > - Create a 1PB volume -> less than a minute > - Delete the volume created -> like 2 days > > The result was unexpected by me and till now, don't know the reason, the > process of deletion was initiated exactly at the end of the creation, so > the volume was never used. > > About the environment: > > - Ubuntu trusty 64bits > - 5 Servers cluster > - 24 Intel SSD per server * 800GB each disk > - Intel NVMe PCIe for journal > - CEPH Hammer. > - Replica 3 > > Hope that someone can tell me why this deletion takes so long. > Best. > > -- > > ATTE. Alvaro Soto Escobar > > ---------------------------------------------------------- > Great people talk about ideas, > average people talk about things, > small people talk ... about other people. > _______________________________________________ > ceph-users mailing list > ceph-users@lists.ceph.com > http://lists.ceph.com/listinfo.cgi/ceph-users-ceph.com >
_______________________________________________ ceph-users mailing list ceph-users@lists.ceph.com http://lists.ceph.com/listinfo.cgi/ceph-users-ceph.com
