I haven't used the striper, but it appears to make you specify sizes, stripe units, and stripe counts. I would expect you need to make sure that the size is an integer multiple of the stripe unit. And it probably defaults to a 4MB object if you don't specify one?
On Fri, Sep 29, 2017 at 2:09 AM Alexander Kushnirenko <kushnire...@gmail.com> wrote: > Hi, > > I'm trying to use CEPH-12.2.0 as storage for with Bareos-16.2.4 backup > with libradosstriper1 support. > > Libradosstriber was suggested on this list to solve the problem, that > current CEPH-12 discourages users from using object with very big size > (>128MB). Bareos treat Rados Object as Volume and in CEPH-10 it created > objects with very big size (10G and more). CEPH-10 allowed such behaviour, > put recovery indeed take very long time. So stripping objects seems to be > the right thing to do. > > Bareos supports libradosstriper and the code seems to work. But for some > reason it run only with stripe_unit=4194304, which seems to be typical > value for RadosGW for example. I tried several other values for > stripe_unit, but the code exit with error. > > Is there a particular reason why only 4M size works? Can one use some CLI > to test different stripe sizes? > > Basic flow of creating object in Bareos is the following: > rados_ioctx_create(m_cluster, m_rados_poolname, &m_ctx); > rados_striper_create(m_ctx, &m_striper); > rados_striper_set_object_layout_stripe_unit(m_striper, m_stripe_unit); > rados_striper_set_object_layout_stripe_count(m_striper, m_stripe_count); > ..... > status = rados_striper_write(m_striper, m_virtual_filename, buffer, count, > offset); > > Alexander > > _______________________________________________ > 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
