[HCoop-Discuss] hardware advice

[Adam Chlipala]

Adam Megacz wrote:
> Adam Chlipala <adamc at hcoop.net> writes:
>   
>
>> You don't think it's worth replicating enough data that the back-up 
>> machine can take over for the main machine immediately, albeit probably 
>> starting from an old snapshot?
>>     
>
> I do.  Unfortunately AFS doesn't really have support for this ("high
> availability" of non-readonly volumes).
>
> You can kinda hack it if you use "network block device" in RAID-1 mode
> as the underlying storage for /vicepa, but the performance
> implications are unclear.
>   

What about taking frequent snapshots?  Is that too expensive for us to 
be able to do it every hour or so to a machine in the same data center?  
If it works, it seems like this would let us resume without losing more 
than an hour of data.