On Wed, 29 Jan 2003, David Gilbert wrote: > it doesn't work that way. the result of NBD is a /dev/nbd0 not a > filesystem. Block 0 of /dev/nbd0 is block 0 of /dev/hda1 (say). nbd > runs as a server on the node with the disk and as a client on the node > using the disk. Yes, you still stripe on the client side... but you > stripe across directly mapped block devices (no NFS involved).
So involving NFS isn't really going to make that much of a difference. Likely the NBD will have lower overhead but probably not much. What you really want is SCSI over IP. Anything else is just a hack and not to be trusted. I think that NFS is less of a hack than NBD though. Of course if Linux still suffers from poor NFS performance that might explain why they came up with NBD in the first place. -- | Matthew N. Dodd | '78 Datsun 280Z | '75 Volvo 164E | FreeBSD/NetBSD | | [EMAIL PROTECTED] | 2 x '84 Volvo 245DL | ix86,sparc,pmax | | http://www.jurai.net/~winter | For Great Justice! | ISO8802.5 4ever | To Unsubscribe: send mail to [EMAIL PROTECTED] with "unsubscribe freebsd-hackers" in the body of the message
