Hi Lars, Is there a specific bench result you're concerned about? I would think that small write perf could be kept reasonable thanks to bluestore's deferred writes. FWIW, our bench results (all flash cluster) didn't show a massive performance difference between 3 replica and 4+2 EC. I agree about not needing to read the parity during a write though. Hopefully that's just a typo? (Or maybe there's a fast way to update EC chunks without communicating across OSDs ?) -- dan -- Dan On Mon, Jul 8, 2019 at 10:47 AM Lars Marowsky-Bree <lmb@xxxxxxx> wrote: > > Morning all, > > since Luminous/Mimic, Ceph supports allow_ec_overwrites. However, this has a > performance impact that looks even worse than what I'd expect from a > Read-Modify-Write cycle. > > https://ceph.com/community/new-luminous-erasure-coding-rbd-cephfs/ also > mentions that the small writes would read the previous value from all > k+m OSDs; shouldn't the k stripes be sufficient (assuming we're not > currently degraded)? > > Is there any suggestion on how to make this go faster, or suggestions on > which solution one could implement going forward? > > > Regards, > Lars > > -- > SUSE Linux GmbH, GF: Felix Imendörffer, Mary Higgins, Sri Rasiah, HRB 21284 (AG Nürnberg) > "Architects should open possibilities and not determine everything." (Ueli Zbinden) > > _______________________________________________ > 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
 |