Do-It-Yourself Fibre Channel Array
skarphedin writes "There's an interesting story here on a do-it-yourself fibre channel array. These guys make one for under $250 and it can perform up there with 15k SCSI in some cases." You know you want one.
Try eBay. We got a QLogic 2100 (Copper) for $40. Drives can be found for $99 for a tenpack of 18.2GB Seagate 10k drives.
Uhh, yes we DID get a host adapter for $40. =)
QLogic 2100 copper, purchased on eBay for $32, shipping was about $8.
Check it out yourself, there's some on there right now for less than $30.
Apple's solution however doesn't involve blocks of wood next to high speed and therefore hot devices...
It's also comparing Apples to oranges.. the Apple XServe RAID has an FC interface to the host controller, ie the XServe, but only uses ATA HDDs internally. Apple's is expensive, yes, but for 2.4TB, it's a pretty damn good price.
Optical fiber is not required for shorter distances, however, because Fibre Channel also works using coaxial cable and ordinary telephone twisted pair. Fibre Channel offers point-to-point, switched, and loop interfaces.
Too bad whoever wrote that was completely full of it. Fibre Channel does not exist over coax or twisted pair.
Coax really isn't used much for data cabling any more.
Twisted Pair? Who knows. I expect the error rates are too high for the extremely tight specs required by Fibre Channel.
SirWired
insightful, but you didn't really touch upon the more common reason for an array to be mounted on two or more systems.
fail over cluster.
far more common, and the file locking/sgi cxfs stuff doesn't even come into the picture.
Where I used to work, we had a few Sun servers with FC disk arrays.
Here's the Sun engineer's explanation of why FC is so interesting for servers:
1) The FC protocol has a 100MByte/s dedicated bandwidth to data. The communication between disks etc. will not interfer with this bandwidth.
2) Modern SCSI has two modes: one for data (burst mode) and one communication mode. The communication mode is a lot slower (first scsi standard) in order to remain compatible with older disks. This means that scsi is a lot more advantageous to users reading large files than small files.
This is where FC becomes interesting: If you have a striped disk array, you will read many small segments from different disks instead of large segments from single disks. In this special case, FC is faster than SCSI, even though it is "slower" by looking at the burst rates in the specs.
You might want to look for Netapp FC(xx) disk shelves. They're normal hot-swap fibre channel JBODs. They're also very expensive, but if you get lucky you might see one sans drives and get it for much cheaper.
Thanks,
Matt
me@mzi.to
In a nutshell:
- the disk setup is not rendundant
- there is no documented disaster recovery plan
Would you be so candid to tell me what kind of enterprise are you working for?
Sigged!