> > On 27.09.2018, at 15:04, John Spray <jspray@xxxxxxxxxx> wrote: > > On Thu, Sep 27, 2018 at 11:34 AM Sergey Malinin <hell@xxxxxxxxxxx> wrote: >> >> Can such behaviour be related to data pool cache tiering? > > Yes -- if there's a cache tier in use then deletions in the base pool > can be delayed and then happen later when the cache entries get > expired. > > You may find that for a full scan of objects in the system, having a > cache pool actually slows things down quite a lot, due to the overhead > of promoting things in and out of the cache as we scan. 'forward' cache mode is still reported dangerous. Is it safe enough to switch to forward mode while doing recovery? > > John > >> >> >>> On 27.09.2018, at 13:14, Sergey Malinin <hell@xxxxxxxxxxx> wrote: >>> >>> I'm trying alternate metadata pool approach. I double checked that MDS servers are down and both original and recovery fs are set not joinable. >>> >>> >>>> On 27.09.2018, at 13:10, John Spray <jspray@xxxxxxxxxx> wrote: >>>> >>>> On Thu, Sep 27, 2018 at 11:03 AM Sergey Malinin <hell@xxxxxxxxxxx> wrote: >>>>> >>>>> Hello, >>>>> Does anybody have experience with using cephfs-data-scan tool? >>>>> Questions I have are how long would it take to scan extents on filesystem with 120M relatively small files? While running extents scan I noticed that number of objects in data pool is decreasing over the time. Is that normal? >>>> >>>> The scan_extents operation does not do any deletions, so that is >>>> surprising. Is it possible that you've accidentially left an MDS >>>> running? >>>> >>>> John >>>> >>>> John >>>> >>>>> Thanks. >>>>> _______________________________________________ >>>>> 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