[DRBD-user] Re: MD Raid-0 over DRBD or DRBD over MD Raid-0

Rick Rothstein rickrsr2 at yahoo.com
Wed Feb 21 08:22:26 CET 2007

Note: "permalinks" may not be as permanent as we would like,
direct links of old sources may well be a few messages off.


Lars Ellenberg <Lars.Ellenberg at ...> writes:
> out of curiosity:
>   why do you need to move away from PVFS?
>   what is your experience with it?

I've had very good experience with PVFS (performance, stability, etc), 
but I'm looking to move to GFS2/EVMS/MD_Raid0/ISCSI for a 
10gb_Ethernet/TCP/ISCSI/hardware_acceleration_boost, and better 
cluster_awareness (add nodes without need for server_restart and 
client_remount, GUI cluster admin tools, etc). 

In either case, I need to find a more timely approach to data protection than 
the currently used nightly_backups, rsyncs, etc.

> 
> you currently cannot have more than two nodes active
> for the same drb device.
> 
> but if you contact us directly,
> and explain more about what you actually do,
> I'm sure we can come up with something interessting.
> 

I'll email more details to you at "lars.ellenberg at linbit.com"

Thanks - Rick Rothstein








More information about the drbd-user mailing list