Since the iSCSI protocol adds an extra hop and offers an added layer of complexity, it should be expected to perform slightly worse as compared to a direct-path solution like krbd. The RBD iSCSI interface is really a workaround for environments that cannot directly access the Ceph cluster via krbd / librbd. On Mon, May 28, 2018 at 8:29 AM, Frank (lists) <lists@xxxxxxxxxxx> wrote: > Hi, > > I an test cluster (3 nodes, 24 osd's) I'm testing the ceph iscsi gateway > (with http://docs.ceph.com/docs/master/rbd/iscsi-targets/). For a client I > used a seperate server, everything runs Centos 7.5. The iscsi gateway are > located on 2 of the existing nodes in the cluster. > > How does iscsi perform compared to krbd? I've already did some benchmarking, > but it didn't performed any near what krbd is doing. krbd easily saturates > the public netwerk, iscsi about 75%. Tmcu-runner is running during a > benchmark at a load of 50 to 75% on the (owner)target > > > Regards, > > Frank de Bot > _______________________________________________ > ceph-users mailing list > ceph-users@xxxxxxxxxxxxxx > http://lists.ceph.com/listinfo.cgi/ceph-users-ceph.com -- Jason _______________________________________________ ceph-users mailing list ceph-users@xxxxxxxxxxxxxx http://lists.ceph.com/listinfo.cgi/ceph-users-ceph.com
 |