There seems to be a bug in the ceph kernel client NFS implementation. Triage: using the same cluster/servers and client 1) export ceph filesystem via NFS, mount on client, copy over files and build --> stale filehandle/corruption issues 2) export ext filesystem via NFS (same server node as in #1), mount on client, copy over files and build --> no problem 3) mount ceph locally on build client, copy over files and build --> no problem >From this, it seems most likely that the problem lies in the kernel client NFS export code. Kernel 2.6.37rc8 Mounting via NFSv4 (noticed other issues with directories disappearing when previously testing with NFSv3 that I can retest after figuring this out) Other than kernel, systems are a rhel6 beta distro I wanted to check whether/what testing has been done of the export code thus far, and see whether this is a known issue. -- To unsubscribe from this list: send the line "unsubscribe ceph-devel" in the body of a message to majordomo@xxxxxxxxxxxxxxx More majordomo info at http://vger.kernel.org/majordomo-info.html
