By default the vstart.sh setup would put all data below a directory called ?dev? in the source tree. In that case you?re using a single spindle. The vstart script isn?t intended for performance testing. David Zafman Senior Developer http://www.inktank.com http://www.redhat.com On Jul 2, 2014, at 5:48 PM, Zhe Zhang <Zhe_Zhang at symantec.com> wrote: > Hi folks, > > I run ceph on a single node which contains 25 hard drives and each @7200 RPM. I write raw data into the array, it achieved 2 GB/s. I presumed the performance of ceph could go beyond 1 GB/s. but when I compile and ceph code and run development mode with vstart.sh, the average throughput is only 200 MB/s for rados bench write. > I suspected it was due to the debug mode when I configure the source code, and I disable the gdb with ./configure CFLAGS=?-O3? CXXFLAGS=?O3? (avoid ??g? flag). But it did not help at all. > I switched to the repository, and install ceph with ceph-deploy, the performance achieved 800 MB/s. Since I did not successfully set up the ceph with ceph-deploy, and there are still some pg at ?creating+incomplete? state, I guess this could impact the performance. > Anyway, could someone give me some suggestions? Why it is so slow when I run from vstart.sh? > > Best, > Zhe > _______________________________________________ > ceph-users mailing list > ceph-users at lists.ceph.com > http://lists.ceph.com/listinfo.cgi/ceph-users-ceph.com -------------- next part -------------- An HTML attachment was scrubbed... URL: <http://lists.ceph.com/pipermail/ceph-users-ceph.com/attachments/20140702/e28859b1/attachment.htm>
 |