Eric, If you export the rbd device directly via your iSCSI target driver, it should work. I verified this with the SCST target, but the LIO target should work as well. As Wido said, you don't want to mount the same rbd device on multiple clients without a shared filesystem (and in that case, you might as well use cephfs), but exporting rbd over iSCSI works. On Tue, Dec 6, 2011 at 1:38 AM, <Eric_YH_Chen@xxxxxxxxxxx> wrote: > Hi, Wido: > > This is a preliminary experiment before implement iSCSI High Available multipath. > http://ceph.newdream.net/wiki/ISCSI > > Therefore, we use Ceph as rbd device instead of file system. > > > -----Original Message----- > From: Wido den Hollander [mailto:wido@xxxxxxxxx] > Sent: Tuesday, December 06, 2011 5:33 PM > To: Eric YH Chen/WHQ/Wistron; ceph-devel@xxxxxxxxxxxxxxx > Cc: Chris YT Huang/WHQ/Wistron > Subject: Re: How to sync data on different server but with the same image > > Hi, > > ----- Original message ----- >> Dear All: >> >> I map the same rbd image to the rbd device on two different servers. >> >> For example: >> 1. create rbd image named foo >> 2. map foo to /dev/rbd0 on server A, mount /dev/rbd0 to /mnt >> 3. map foo to /dev/rbd0 on server B, mount /dev/rbd0 to /mnt >> >> If I put add a file to /mnt via server A, I hope I can see the same >> file on server B. >> However, I can't see it until I umount /mnt on server A and re-mount >> /mnt on server B. > > You'd have to use an cluster filesystem like GFS or OCFS2 to let this work. > > But why not use Ceph as a filesystem instead of RBD? That seems to do what you want. > > Wido > >> >> Do you have any comment about this scenario? How could I force the >> data synchronization? >> >> Actually, I want to implement the iSCSI High Available multipath on >> http://ceph.newdream.net/wiki/ISCSI. >> Therefore, I tried this small experiment first, but fail. Would you >> please give me some suggestion before I start to implement it? Thanks! >> -- To unsubscribe from this list: send the line "unsubscribe ceph-devel" in the body of a message to majordomo@xxxxxxxxxxxxxxx More majordomo info at http://vger.kernel.org/majordomo-info.html
