SJS wrote: > begin quoting Bob La Quey as of Sun, Dec 16, 2007 at 05:30:15AM -0800: > [snip] >> Yes but ... >> >> It seems from what I read that ZFS accomplishes all of what >> hardware RAID does but without the hardware. So where lies >> the hardware RAID advantage? >> >> I still do _not_ get it. > > The advantage of hardware RAID is, as I understand it, performance. > > A hardware RAID controller can write to each disk in parallel, computing > the necessary checksums, etc., while a JBOD with a single controller > will need to write to each disk separately (if the data is to span > multiple disks). > > Consider mirroring with software RAID (or JBOD): > > CPU DISK A DISK B > | | | > |------------->| | Hey, disk A, write <data> to <location> > |<-------------| | Okay. > |--------------+------------->| Hey, disk B, write <data> to <location> > |<-------------+--------------| Okay > | | | > | | | > > > And with hardware RAID: > > CPU RAID DISK A DISK B > | | | | > |------------>|------------->+------------>| Hey, RAID, write <data>... > |<------------|<-------------+-------------| Okay > | | | | > > That's not saying that hardware RAID controllers all *do* that; I > would not be at all suprised to find out that some don't. But they > *can* (and arguably *should*). >
Nice art! My understanding is that software raids do parallel access effectively the same as hardware controllers. But hw offloads the parity and error checking/handling onto the cpu in the controller, thus gaining performance.. and.. - a. protection from damaging meddling (direct disk access) from other sw on the host & (usually) - b. prevention of debugging, monitoring or exploratory recovery operations. Regards, ..jim -- [email protected] http://www.kernel-panic.org/cgi-bin/mailman/listinfo/kplug-list
