We have a small (3 node) Ceph cluster that occasionally has issues. It loses files and directories, truncates them or fills the contents with NULL bytes. So far we haven't been able to build a repro case but it seems to happen when bulk loading data into the cluster, a process that is run each evening by a cron job. We've gone about a month without any issues but had it happen again yesterday during a larger bulk load. The data is backed up outside of ceph and can be reloaded but finding the corrupt files takes quite a while. Has anyone heard of similar issues before? Should I try upgrading to 0.48.2 or a newer kernel? ceph version 0.48.1argonaut (commit:a7ad701b9bd479f20429f19e6fea7373ca6bba7c) Linux _ 3.4.4-gentoo #2 SMP Sun Jul 1 18:28:16 UTC 2012 x86_64 Intel(R) Xeon(R) CPU E31240 @ 3.30GHz GenuineIntel GNU/Linux I'm using the kernel provided cephfs, mounted with these options: 10.0.2.2:6789:/ on /ceph type ceph (rw,noatime,nodiratime) thanks, -n -- 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
