FWIW, I believe the particular/similar bug I was thinking of was fixed by:
commit 590fb51f1c (vfs: call d_op->d_prune() before unhashing dentry)
--Lincoln
On May 9, 2014, at 12:37 PM, Gregory Farnum wrote:
> I'm less current on the kernel client, so maybe there are some
> since-fixed bugs I'm forgetting, but:
>
> On Fri, May 9, 2014 at 8:55 AM, Aronesty, Erik
> <earone...@expressionanalysis.com> wrote:
>> I can always remount and see them.
>>
>> But I wanted to preserve the "broken" state and see if I could figure out
>> why it was happening. (strace isn't particularly revealing.)
>>
>> Some other things I noted was that
>>
>> - if I reboot the metadata server nobody seems to "fail over" to the hot
>> spare (everything locks up until it's back online). I'm guessing you have
>> to manually make the spare primary, and then switch back?
>
> That shouldn't happen. What's the output of "ceph -s"?
>
>> - if I reboot the mon that someone is mounted to, his mount locks up (even
>> if I list 4 monitors in the fstab), but other clients still work.
>
> Can you elaborate? We discovered an issue in our userspace network
> code that might have an analogous problem in the kernel, but it
> generally was only a problem if a NIC disappeared (ie, powered off)
> without coming back on.
> -Greg
> Software Engineer #42 @ http://inktank.com | http://ceph.com
_______________________________________________
ceph-users mailing list
ceph-users@lists.ceph.com
http://lists.ceph.com/listinfo.cgi/ceph-users-ceph.com
