Hacker News new | ask | show | jobs
by mrbill 4616 days ago
Same connector as SAS, but a different pinout?

Does this not scream "bad idea" to anyone else?

3 comments

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.