milo@ndmath.UUCP (Greg Corson) (05/03/90)
Has anyone seen any benchmarks of hard disks yet that include performance figures for the Mac IIfx? I'm getting ready to buy one and I'm wondering if I can get a faster transfer rate on my SCSI disk by getting a CDC Wren-runner drive instead of the usual apple Quantum. I've heard the standard Apple Quantum drive is no faster on an FX than it is on a CI...does anyone know this to be true? If it is true, it would seem the drive is the bottleneck and having a faster unit like a Wren-Runner would give you better disk transfer rates. If anyone has done any benchmarking of FX drives (particularly compairing their performance against a CI or Mac IIx) I'd like to hear about it. Greg Corson 19141 Summers Drive South Bend, IN 46637 (219) 277-5306 {uunet, rutgers}!iuvax!ndmath!milo milo@ndmath GEnie: GCORSON
ephraim@leander.think.com (Ephraim Vishniac) (05/04/90)
In article <1800@ndmath.UUCP> milo@ndmath.UUCP (Greg Corson) writes: >Has anyone seen any benchmarks of hard disks yet that include performance >figures for the Mac IIfx? I'm getting ready to buy one and I'm wondering >if I can get a faster transfer rate on my SCSI disk by getting a CDC Wren-runner >drive instead of the usual apple Quantum. >I've heard the standard Apple Quantum drive is no faster on an FX than it >is on a CI...does anyone know this to be true? I just ran a simple test using SCSI Evaluator 1.02 on a IIfx. My internal disk is an Apple (Quantum) 80MB disk; the external disk is a CDC Wren III. Both disks are formatted with 1:1 interleaving. I ran SCSI Evaluator's default tests, for reads only. For small transfers (10K, 15K), the Apple 80MB disk was literally off the chart. I suspect this means that the controller caches more than 15K, but less than 20K. For 20K transfers and larger, the Apple disk did about 6000kbps. For comparison, I ran the same test on my external disk, a CDC Wren III. Note that this is an old disk (1987?), presumably slower than the Wren Runner. I don't believe it does any local caching. Transfers rates increased fairly smoothly with transfer size, starting at about 6000kbps and increasing to nearly 8000kbps for the largest transfers. So, the Apple disk scored better on small transfers, probably due to caching, and the CDC disk scored better on large transfers. In practice, which is "better" depends on the cache hit rate, the typical transfer size, and the seek rate of the drives. I didn't test seek times for two reasons: (1) the test is lengthy and (2) my results on a Wren III have absolutely no bearing on the performance of the Wren Runner. Ephraim Vishniac ephraim@think.com ThinkingCorp@applelink.apple.com Thinking Machines Corporation / 245 First Street / Cambridge, MA 02142 One of the flaws in the anarchic bopper society was the ease with which such crazed rumors could spread.
ephraim@leander.think.com (Ephraim Vishniac) (05/04/90)
In article <36069@think.Think.COM> ephraim@think.com (Ephraim Vishniac) writes: >I just ran a simple test using SCSI Evaluator 1.02 on a IIfx. My >internal disk is an Apple (Quantum) 80MB disk; the external disk is a >CDC Wren III. Both disks are formatted with 1:1 interleaving. I ran >SCSI Evaluator's default tests, for reads only. For small transfers >(10K, 15K), the Apple 80MB disk was literally off the chart. I >suspect this means that the controller caches more than 15K, but less >than 20K. For 20K transfers and larger, the Apple disk did about >6000kbps. After I wrote this yesterday, my memory suddenly engaged. The Quantum disks use a multi-way read-ahead cache. That is, if you read a group of sectors ending with X, the disk controller uses its idle time to read sectors starting at X+1 into the cache. If that's what you read next, you win. If not, you haven't lost anything because the disk was just sitting there anyway. The number and length of read-ahead groups is configurable. If you suspect, for example, that you'll typically switch back and forth between reading three different areas of the disk, you can divide the 64K cache three ways. From the SCSI Evaluator results, I guess Apple has divided it four ways, with 16K of look-ahead for the four most recently read sectors. There are actually two benefits to this kind of caching. Obviously, the transfer of cached data is very quick because there's no rotational latency. Also, the number of seeks is reduced. This is extremely important in reducing working time for disk-bound operations. It's also very difficult to judge the importance of it from simple benchmarks. There's nothing like running your own application to judge the disks. Ephraim Vishniac ephraim@think.com ThinkingCorp@applelink.apple.com Thinking Machines Corporation / 245 First Street / Cambridge, MA 02142 One of the flaws in the anarchic bopper society was the ease with which such crazed rumors could spread.