Hello experts,

A while back I've seen proposals on Linux kernel mailing lists to create
RAID firmwares based on mdadm, and apparently some hardware
vendors took to that. An added benefit for users was that RAID disks
could be migrated between software and hardware RAID running same
code, allowing for easier repairs, migrations and up/down-grades.

I remembered that idea and wondered: is it (at least theoretically)
possible and efficient to separate some ZFS storage code and turn
it into a RAID-adapter firmware code with all the good features?
Currently ZFS opposes itself to existing RAID hardware, but basically
turns a computer into one.

Perhaps some code (a stripped-down OS, ZFS, CLI and maybe GUI)
could executed on a dedicated piece of hardware (probably a board
with limited RAM - thus most of caching should be done elsewhere -
in the user's OS and main system RAM), so that any end-user OS
(not only ones directly suppporting ZFS) would benefit from ZFS
resiliency, snapshots, caching, etc. with the simplicity of using a
RAID adapter's exported volumes.

Now, it is just a thought. But I wonder if it's possible... Or useful? :)
Or if anyone has already done that?

//Jim Klimov

zfs-discuss mailing list

Reply via email to