IDE Co-Processors?
morbid asks: "EIDE is generally considered to be inferior to SCSI because it requires more involvement from the processor slowing the system down, but would it not be possible to build an EIDE/ATA (?) controller with its own processor, freeing up the CPU and increasing system performamce while allowing the use of inexpensive drives?"
Bus Master IDE FAQ
--
http://gammatron.weblogger.com
its called scsi why reinvent the wheel?
Why not something faster than scsi, but for 2 devices per channel? Already, the only thing faster than ATA 100 is Ultra160, but there's the one disk at a time thing. Once this is fixed, SCSI will really need to be trashed!
"Ancillary does not mean you get to rule the world." --U.S. Circuit Judge Harry Edwards, speaking to the FCC's lawyer
Right now the next step in consumer high-speed drives appears to be Firewire/iLink/1394 (depending on the vendor.) USB 2.0 has just appreared in silicon but it's already slower then Firewire/iLink/1394 and not as flexible. Intel is also working on PCI/X as a next generation replacement for the now venerable PCI bus. They appear to be going to a serial-bus design with smart interconnects.
One well regarded scenario for the future of PC's has them turning into black boxes containing little more then a CPU and graphics card. Everything else would be handled through high-speed serial connections.
I don't read ACs: If a post isn't worth so much as a nom de plume to its author then I wont bother either.
ah but you forget - SCSI 4 and 5 are on the way - up to something like 480mb/s.
--onyx--
Ultra2/80 performs remarkably better than ATA/100, and supports a load more devices, too... Ultra 320 (packetized SCSI - like FC) is not too far off, with 640 being just a little pipe-dream at the moment (the silicon tech required for the SCSI drivers... well, that many lines with that much speed with that much driving capability all on one chip is a tall order).
Once ATA gets fixed (trashed) we won't need to bother with it anymore... damn legacy 8^)
--
"It's tough to be bilingual when you get hit in the head."
and at like 4x the cost per megabyte over IDE
--Justin
Western Digital18.0GB EIDE 7200 RPM OEM,1 YEAR WARRANTY $109
Doesn't look like 4-to-1 to me. I'll pay the extra $130 for SCSI, personally.
- A.P.
--
"One World, one Web, one Program" - Microsoft promotional ad
"Remember when the U.S. had a drug problem, and then we declared a War On Drugs, and now you can't buy drugs anymore?"
Besides the advantages that have already been mentioned, Ultra160 supports much longer cables (12 meters) than any variety of IDE. Assuming you had enough IDE controller chips, how are you going to connect 8 hard drives to a PC with 18" cables?
Mea navis aericumbens anguillis abundat
Thought recent incarnation of the IDE bus may adddress these problems, lower cpu overhead is not the only reason that SCSI driver are better, the support for tagged command queueing and the ability of a SCSI drive to accept a command over the bus and then get off the bus till it has the data (thus allowing commands and data to flow over the bus to and from other devices while the first is till working) also made the SCSI system better than (at least early) IDE systems, especially for server systems running unix where there are lots of concurent transactions.
I've got 6 short and 8 full height drives, 2 dual ppro systems, powers supplies fans & so on, in less space than a single full size tower case.
though I'm a big SCSI fan, I got to admit the single 8' SCSI cable is much more of a bitch to deal with than the IDE cables.
You get what you pay for.
- A.P.
--
"One World, one Web, one Program" - Microsoft promotional ad
"Remember when the U.S. had a drug problem, and then we declared a War On Drugs, and now you can't buy drugs anymore?"
If IDE requires so much assistance from the main CPU to get its deed done, then would it not be possible to SCSIfy an IDE drive with some tantric controller card / embedded adapter encasing that would do this "dirty work" and emulate SCSI with its lovely 1% cpu usage ? Even dedicated ATA/66 and ATA/100 cards like the Promise Raid Controller swallow a good slice of the CPU time.
For most hard drives it's not too bad, but the real problem comes when you have a high-speed cdrom. Think Kenwood 72x. That thing sucks away nearly 20% CPU no matter how fast the PC. Another brand name 40x drive also bogs down my other box by a good 12-15%. On the other hand, my SCSI 24x could (theoretically) run on a 286/12 without a hiccup (of course the system bus would freak out).
Are there spec incompatibilities between SCSI and IDE that would prevent this kind of gadget from existing ? It would allow high-end workstation users to add cheap unreliable storage for their pr0n on those fancy-shmancy SGI boxes.
-Billco, Fnarg.com
It has already been done, at least as a RAID solution. I was searching for fast, huge storage solutions 3 years ago and found a company that was making SCSI RAID drives based on IDE. I can't remember the company that I talked to back then, but here's one link I could find with a brief search.
I think if you take it to RAID-0 you can array all those IDE drives to look like one HUGE SCSI drive.
Did you look at the IDE RAID controllers? They use normal IDE drives, so the controller must be fairly intelligent. And I believe you can select whether writes are reported as complete when the controller gets the request or when the data has been physically written to the disks.
Forget Promise, SIIG and others. 3Ware's Escalade series of products are just what you are looking for. Keys to performance with Escalade:
If you want to minimize cost and performance, 3Ware's Escalade is what you want. Their new 6000-series offers 2-8 channels of RAID-0/1/1+0 with Ultra66 support for $139/279/479 (2/4/8 channel).
3Ware is also working on a 64-bit PCI board with RAID-5 support (as well as Ultra100). Be looking out for it (I know I will).
-- Bryan "TheBS" Smith
-- Bryan "TheBS" Smith
Independent Author, Consultant and Trainer
This debate has gone on for a long time... SCSI has many more benefits than just speed over IDE. Processor overhead is a big issue of course, and i can see a tremendous difference in an IDE and SCSI system because of this. Another HUGE issuse is bus width. One reason SCSI outpreforms IDE is the fact that all the wide SCSI flavors are working on a 16bit wide bus. (hence the 68 pin cable) ATA/33/66/100 is all a burst mode thing. Sure you can get the high speed, but it's really a joke because you only get that high speed for a very short time. Wide SCSI can sustain much higher speeds for much longer times. How often do you see IDE servers? There's a reason for that, you can't have your disk access bog down when more than a couple of users hitting it.
My personal favorite part of SCSI is the ability of devices to work independently. On an IDE controler the bus is dominated by the slowest device on the chain. On a SCSI system, you can have SCSI-1, SCSI-2, SCSI-3 all running at their own speeds happy together.
Over all, as IDE gets faster, so will SCSI. They are two technologies and one is really not going to bury the other. IDE will have it's market with budget minded customers and SCSI will be there for the preformance applications and power users. Both these technologies will eventually reach their peak and fade out, but for now it's what we have.
Silly slashdot, sigs are for kids!