On 28.09.2018 21:49, Gilberto Nunes wrote:
Hi there
I have a 6 server Ceph Cluster maded with proxmox 5.2
Suddenly, after power failure, I have only 3 servers UP, but even with 3
server, Ceph Cluster doesn't work.
pveceph status give me a timeout
pveceph status got timeout
Any advice?
out of
And to make day outstanding, I get a fiber optic ruptured
---
Gilberto Nunes Ferreira
(47) 3025-5907
(47) 99676-7530 - Whatsapp / Telegram
Skype: gilberto.nunes36
Em sex, 28 de set de 2018 às 17:24, Gilberto Nunes <
gilberto.nune...@gmail.com> escreveu:
> I thing I figure out what
I thing I figure out what happens...
For my lucky one of the servers, pve-ceph05 that remains, has the OSD crush
marked to 0.
My environment consist a mix of different disks sizes
---
Gilberto Nunes Ferreira
(47) 3025-5907
(47) 99676-7530 - Whatsapp / Telegram
Skype: gilberto.nunes36
also, 3 out of 6 servers is not quorum. you need a majority of the total.
On Fri, 28 Sep 2018, 21:22 Mark Adams, wrote:
> the exact same 3 servers have been down and everything has worked? do you
> run ceph mons on every server?
>
> On Fri, 28 Sep 2018, 21:19 Gilberto Nunes,
> wrote:
>
>>
Everything is working couple of hours ago!
Due a power failure, 3 hosts are down, but I suppose with 3 host the
cluster garantee the quorum and allow ceph continues to work.
This already happen before and ceph works perfectly with 3 servers
---
Gilberto Nunes Ferreira
(47) 3025-5907
(47)
So the times are massively different. Fix that.
And corosync needs multicast , and that’s tested using omping, not ping.
Go back through the initial set up documentation and read what is required for
the basic network configuration.
If corosync and ceph are both not working, start
I get this error
ceph-mon
2018-09-28 17:10:49.189979 7f8588d66100 -1 monitor data directory at
'/var/lib/ceph/mon/ceph-admin' does not exist: have
you run 'mkfs'?
---
Gilberto Nunes Ferreira
(47) 3025-5907
(47) 99676-7530 - Whatsapp / Telegram
Skype: gilberto.nunes36
Em sex, 28 de set
Oh and cluster is up and running too!
---
Gilberto Nunes Ferreira
(47) 3025-5907
(47) 99676-7530 - Whatsapp / Telegram
Skype: gilberto.nunes36
Em sex, 28 de set de 2018 às 17:07, Gilberto Nunes <
gilberto.nune...@gmail.com> escreveu:
> pve-ceph01:~# ssh pve-ceph01 date
> Fri Sep 28
pve-ceph01:~# ssh pve-ceph01 date
Fri Sep 28 17:06:34 -03 2018
pve-ceph01:~# ssh pve-ceph02 date
Fri Sep 28 17:06:37 -03 2018
pve-ceph01:~# ssh pve-ceph05 date
Fri Sep 28 17:06:39 -03 2018
pve-ceph01:~# ping -c 1 pve-ceph01
PING pve-ceph01.cepam.com.br (10.10.10.100) 56(84) bytes of data.
64
Network issues?
Time issues?
> On Sep 28, 2018, at 11:50, Gilberto Nunes wrote:
>
> Hi there
> I have a 6 server Ceph Cluster maded with proxmox 5.2
> Suddenly, after power failure, I have only 3 servers UP, but even with 3
> server, Ceph Cluster doesn't work.
> pveceph status give me a
10 matches
Mail list logo