[Date Prev][Date Next]   [Thread Prev][Thread Next]   [Thread Index] [Date Index] [Author Index]

[Linux-cluster] gfs over raid/lvm or any other option?



Hello experts,

If on one machine i have 8 block devices (/deb/sda, /dev/sdb, ... /dev/sdg, 
dev/sdh) imported via iscsi from 8 different computers (computerX) can i 
group volumes two by two using raid1 and after that to join resulted /dev/md0 
up to md3 in one logical volume and run GFS on top?

If this thing is not possible, how can i join together all 8 sd[a-h] in order 
to have fault-tolerance shared storage (failure of a single drive sd[a-h] or 
server (computerX) should not bring down the GFS)? I read about gnbd but is 
working only on 2 nodes. Any idea about how to construct a shared storage 
volume using all 8 devices?

Lustre can be a solution to my problem? I have one doubt regarding lustre: i 
saw that they are using EXT3 on top, which I know that is a LOCAL FILE SYSTEM 
not suitable for SHARED STORAGE (different computers accesing the same volume 
and write at the same time on it).

So, using their patched kernels, ext3 become suitable for SHARED STORAGE?

Regards,
Alx


[Date Prev][Date Next]   [Thread Prev][Thread Next]   [Thread Index] [Date Index] [Author Index]