IDE to SCSI Converters?
ericdano asks: "Addonics has announced a pair of SCSI solutions, which convert common ATAPI devices and IDE hard drives to high-speed SCSI devices on all Windows, Macintosh, and Linux-based computers: the IDE-SCSI converter ($100) for hard drives and the ATAPI-SCSI converter ($110) for ATAPI-based CDRW, DVD-R/RW, DVD-ROM or CD-ROMs. The company has also announced a high-performance single-channel Ultra160 SCSI PCI host controller ($170) with 160MB/sec. data throughput. How safe are these products?"
Nevertheless, when it comes to hard drives, the basic performance of the drive itself will be a limiting factor. I doubt your IDE drive will suddenly get a boost in performance, though it would be neat to see some Bonnie++ results to confirm this.
As for the SCSI controller, does anyone have any experience with these? Its a fair bit cheaper than the equivalent Adaptec model. After putting SCSI in my Linux workstation at work, I'm hooked on it: what's not to like about cutting compile times by 50%? Maybe I could get SCSI at home if this controller is the real deal.
Why do they mention the OS at all? If it doesn't work on all OSes which support SCSI out of the box they must have done something horrible wrong which violates SCSI standards.
http://www.memorylabs.net/scsiidconfor.html
their cards work fine for both atapi and ide in one card, they even have cards for 50 and 68 pin, plus lvd
at memorylabs for 74$ us
macena 61.90$ us
works like a charm, and is great for when you don't want to pay the outrageous prices they charge for scsi 40x burners for your older sun system, at least that's why my roommate wanted one
The page doesn't mention anything about tagged command queueing. SCSI drives can receive multiple commands from the controller simultaneously and return the results in whatever order they think is the fastest at that moment. ATA cannot do this, and this is a reason why SCSI usually 'seems' to be faster than ATA. Then there's the issue of latency; the converter would necessarily take some time to convert the commands between SCSI and ATA. Even with ATA/133, I suspect that an ATA drive connected to a SCSI bus using this converter will be much slower than a native SCSI drive. And, at USD$99, it cancels out any savings that you might get from buying an ATA drive over a SCSI one. It'd be better, though, if the converter allowed the user to connect two ATA drives simultaneously, instead of having to use one converter per drive.
In Soviet Russia, Jesus asks: "What Would You Do?"
goes back as far as the ibm 14gxp series, which has to be 6-7 years ago.
look at the sources for the ata controllers in your os
This is what I am waiting for hot-swapable, plug and play Serial ATA.
This has been in the workls for a long time, but there are some actual products coming to market this year.
Tom's has a good story. Serial ATA
The features in brief:
150 MByte/s maximum transfer rate (300/600 MByte/s envisioned for the future)
Hot-plugging capability
Two power saving modes: partial and slumber
Overlapping (commands)
Tagged command queueing
Seven-wire data cable. Connectors measure just 8 mm wide.
what? what I thought we were in the trust tree in the nest, were we not?
well it is possible to spin down/up a IDE drive, I think that holding a couple of lines down on the IDE connector will probebly do this. So the convertor will spin up the drive when it is called to do so, just like a native SCSI drive
I posted a note on a different topic yesterday about RAID options.
I highly recommend going to www.3ware.com or grab a used card on eBay. The cards use IDE drives but the volumes are perceived by the BIOS and operating system as SCSI devices.
They have fantastic customer support, and write their own Linux drivers (which are constantly committed with stable kernel releases). BSD drivers are also available. I've never used them under Windows.
The cards use a patented network-oriented algorithm for reading and writing to the IDE drives. Their benchmarks are impressive and well-publicized.
Can't say enough nice things about them.