| [Date Prev][Date Next][Thread Prev][Thread Next][Date Index][Thread Index] |
On Wednesday 05 November 2003 03:54 pm, Arcot Arumugam wrote: > > > > Maybe heartbeat combined with DRBD could utilize your Computer's A & B > > and eliminate the SPOF. > > > > i.e. DRBD is conceptually Raid 1 between 2 computers. (Note that DRBD > > does NOT support Raid 1+0 functionallity, only Raid 1). > > > > You end up with this hierarchy: > > > > ogfs on C & D > > EVMS 2 on C & D > > iscsi initiator on C & D > > iscsi target on A & B > > drbd (Mode C) on A & B > > physical drives on A & B > > > > What I have no idea about is what happens when Computer A or B dies. > > > > The key would be making sure the iSCSI subsystem itself is not doing any > > caching. I suspect that is default behavior, but I'm not sure. > > > > Maybe my understanding of iSCSI is wrong. I assumed that iSCSI would make a > hard drive on another host on the network appear as a LOCAL SCSI harddrive > of a machine. If that is the case, would not software raid 1 from EVMS would > take care of failure in A or B at one time? It should theoretically assume > that scsi harddrive B has failed (when computer B dies) and continue > operations??? Sounds like a good plan, except EVMS only supports raid-0 and linear, so no kind of high availability. --Brian Jackson > > yes, I will read about DRBD and find out more. > > If you can let me know which of my assumption is wrong, it would be greatly > appreciated. > > Thanks > > Arcot ------------------------------------------------------- This SF.net email is sponsored by: SF.net Giveback Program. Does SourceForge.net help you be more productive? Does it help you create better code? SHARE THE LOVE, and help us help YOU! Click Here: http://sourceforge.net/donate/ _______________________________________________ Opengfs-users mailing list Opengfs-users@lists.sourceforge.net https://lists.sourceforge.net/lists/listinfo/opengfs-users