Getting Physical - Seagate Kinetic Drive Hardware
swiftstack.comRAID over IP via broadcast? From a security standpoint, it would seem there are many hurdles to jump. Not too long ago, I talked to Dickinson about what you guys do. I never considered the amount of harddrives necessary to facilitate Swiftstack's goals. Of course the software challenges are interesting, but the amount of hardware and maintaining risk/DR/costs/etc. Oh man. Hats off to you guys.
It's not RAID over IP. Each drive itself is a network endpoint.
On the practical side, this means that the drive is "connected" to one or more servers (and can be re-homed on the fly). The storage system itself is responsible for coordinating the communication across the cluster of Kinetic drives. In our case, the coordinating storage system is OpenStack Swift.
On the humorous side, this means that technobabble like "Can you ping the boot record?" or "What does a traceroute to the directory show?" actually sorta make sense now.
RAID over IP was a joke. I remember reading this story about someone flooding routers to turn them into a broadcasts to view the flow of packets over the network. I imagined the same thing, then said, hey with HDDs and broadcast, you could simulate RAID. I made a long stretch on that one.
That's probably not too far off. If you wanted to do mirror a write, you could imagine broadcasting that same packet to a set of devices. The devices would have to figure out whether or not they needed to store the packet. Otherwise, you'd be sending N packets to the same switch for N-way mirroring. In a typical hardware RAID, the sector write is sent to the RAID controller once.
It's probably not too long of a stretch.
Writing with multicast and using tcp only for the control plane? Interesting concept.
lol @ technobabble
Same connector as SAS, but a different pinout?
Does this not scream "bad idea" to anyone else?
This is a good thing for a couple of reasons. First it allows equipment manufacturers to build chassis with the same drive trays that are already in production. Second, it that from a drive assembly standpoint, the same build and testing equipment can be used. This should speed development and manufacturing quality.
Is the concern more from an ergonomic perspective, that someone in a data center may plug in a drive into the wrong system?
If the testing equipment is expecting a SAS port, then wouldn't the dual ethernet ports pose a problem? Or, is it that they are using SAS power pins to do the ethernet transfer leaving the other pins untouched? (I don't know my SAS pin-outs very well).
The main concern would be that, yes, someone could plug the drive into the wrong system.
I'd imagine that would be a pretty big concern. This is a regression for serviceability. Connectors should be keyed specific to the function for a variety of reasons. I'm sure seagate has their reasons, but this seems like a bad idea to me.
That was my first thought. Wonder what the failure mode is if you mismatch things?
Well given that the device will start asking for a DHCP address when it is powered on, it will probably not do anything.
Actually I was thinking more about what happens electrically.
Maybe they can/will be making the jack on the drive a unique standard color?
Still a bad idea. At the very least they should make sure that nothing is fried on either side if you plug one of these drives into a SAS controller, or a SAS drive into a backplane that expects to see dual Ethernet on those pins.
Even though (for example) USB3 is blue connectors, it's interoperable if you plug USB2 gear in.
Good question. That sounds like a reasonable idea for quickly identify when looking for a replacement in the spares closet.
unless you're colorblind, in which case you're SOL.
I have a good feeling that there will be some text as well. :) FWIW we imagine that field replacements will be less common and simply run with 'dead drives' will be more common.
Incidentally, because the drive is moving to a key/value model vs. sectors it means that the useful life of the device will be much better. This is because the device can manage bad sectors itself vs having that be the responsibility of the filesystem. So the drive would just report lower % capacity.