Re: [ceph-users] EC pool errors with some k/m combinations

Hi Michael, I'm trying to reproduce the problem from sources (today's instead of yesterday's but there is no difference that could explain the behaviour you have): cd src rm -fr /tmp/dev /tmp/out ; mkdir -p /tmp/dev ; CEPH_DIR=/tmp LC_ALL=C MON=1 OSD=6 bash -x ./vstart.sh -d -n -X -l mon osd

Re: [ceph-users] Ceph KVM Ganeti

Hello, On Sat, 29 Mar 2014 11:05:53 +0100 Andreas Rammhold wrote: > Hi Jon, > It might be that your qemu-kvm version/build doesn't support > lib{rados,rbd}. Which Ganeti version are you using? > That's exactly what I'm suspecting. He's using 2.10, the hotdisk is a dead giveaway. And he's trying

[ceph-users] RDO - CEPH

I was trying to play around with RDO and CEPH at http://openstack.redhat.com/Using_Ceph_for_Cinder_with_RDO_Havana but after I install QEMU for CEPH and when I run qemu-img create –f raw rbd:data/foo 1G The command just hangs without creating any raw device. Am I missing something here ? Than

Re: [ceph-users] RDO - CEPH

On 30/03/2014 14:23, Vilobh Meshram wrote: > I was trying to play around with RDO and CEPH at > http://openstack.redhat.com/Using_Ceph_for_Cinder_with_RDO_Havana but after I > install QEMU for CEPH and when I run > > qemu-img create –f raw rbd:data/foo 1G > > The command just hangs without c

[ceph-users] Mon hangs when started after Emperor upgrade

Hi guys, I upgraded a working cluster from Dumpling to Emperor which went OK. All mons, osds and mds running 0.72.2 on Fedora 18 now. I then installed the ceph-extras repo and let it update curl, libcurl and leveldb. Next I tried restarting a mon - but it won't start up again. It just just

Re: [ceph-users] Mon hangs when started after Emperor upgrade

Hi again, Next I tried restarting a mon - but it won't start up again. It just just hangs: I have captured a backtrace of the hang using gdb: (gdb) bt #0 0x773e6e4d in __lll_lock_wait () from /lib64/libpthread.so.0 #1 0x773e2cc1 in _L_lock_885 () from /lib64/libpthread.so.0

Re: [ceph-users] RDO - CEPH

Hi Loic, Thanks for your reply. Not really I have setup 3 nodes as storage nodes ³ceph osd tree² output also confirms that. I was more concerned about the authentication aspect meaning the request not able to reach the MON node and hence not getting forwarded to the storage nodes ? Thanks, Vilob

Re: [ceph-users] EC pool errors with some k/m combinations

Hi Loic, On Sun, 30 Mar 2014, Loic Dachary wrote: Hi Michael, I'm trying to reproduce the problem from sources (today's instead of yesterday's but there is no difference that could explain the behaviour you have): cd src rm -fr /tmp/dev /tmp/out ; mkdir -p /tmp/dev ; CEPH_DIR=/tmp LC_ALL=C

[ceph-users] openstack + ceph

hi all, I am trying to get ceph work with openstack havana. I am following the instructions here. https://ceph.com/docs/master/rbd/rbd-openstack/ However, I found i probably need more details on openstack. The instruction mentioned cinder-volume nodes. How about cinder-api cinder-scheduler? Do

Re: [ceph-users] OSDs vanishing from Ceph cluster?

Thanks for the prompt response and for the good advice. Since this is a test Ceph cluster with no data of any value, I have already rebuilt it from scratch so I can resume testing. Will keep the group posted if the issue resurfaces, or if I learn anything new that seems worth sharing. Thanks again.