number of masters and quorum

[Dick Davies <di...@hellooperator.net>]

I might be wrong but doesn't the new quorum setting mean
it only makes sense to run an odd number of masters
(a la zookeepers)?

i.e. 4 masters is no more resilient than 3 (in fact less so, since
you increase your chance of a node failure as number of nodes
increases).

Re: number of masters and quorum

[Benjamin Mahler <be...@gmail.com>]

Just to clarify:

You can run a single master (--quorum=1) if you are looking to experiment
and don't care about high availability.

You can run 3 masters (--quorum=2) if you want to remain operating with 1
machine being down (planned or unplanned). You can also operate in the face
of the complete loss of 1 of the disks/machines.

You can run 5 masters (--quorum=3) if you want to remain operating with 2
machines being down (planned or unplanned). You can also operate in the
face of the complete loss of 2 of the disks/machines.

And so on. I would recommend 3 or 5 depending on your requirements. Jie
and/or myself will look to get some documentation up for this soon!


On Tue, Jul 1, 2014 at 3:29 PM, Jie Yu <yu...@gmail.com> wrote:

> Dick, you are right.
>
> - Jie
>
>
> On Tue, Jul 1, 2014 at 3:20 PM, Dick Davies <di...@hellooperator.net>
> wrote:
>
>> I might be wrong but doesn't the new quorum setting mean
>> it only makes sense to run an odd number of masters
>> (a la zookeepers)?
>>
>> i.e. 4 masters is no more resilient than 3 (in fact less so, since
>> you increase your chance of a node failure as number of nodes
>> increases).
>>
>
>

Re: number of masters and quorum

[Jie Yu <yu...@gmail.com>]

Dick, you are right.

- Jie


On Tue, Jul 1, 2014 at 3:20 PM, Dick Davies <di...@hellooperator.net> wrote:

> I might be wrong but doesn't the new quorum setting mean
> it only makes sense to run an odd number of masters
> (a la zookeepers)?
>
> i.e. 4 masters is no more resilient than 3 (in fact less so, since
> you increase your chance of a node failure as number of nodes
> increases).
>