Path: utzoo!utgpu!news-server.csri.toronto.edu!cs.utexas.edu!wuarchive!zaphod.mps.ohio-state.edu!uakari.primate.wisc.edu!aplcen!aplcomm!uunet!cbmvax!cbmehq!babylon!rbabel
From: rbabel@babylon.UUCP (Ralph Babel)
Newsgroups: comp.sys.amiga.tech
Subject: Re: DiskPerf for GVP Series II scsi + RAM
Summary: Luke 23:34
Message-ID: <04933.AA04933@babylon.UUCP>
Date: 18 Nov 90 13:34:26 GMT
References: <1990Nov18.191622.13242@lavaca.uh.edu>
Reply-To: cbmvax.commodore.com!cbmehq!babylon!rbabel (Ralph Babel)
Lines: 53

In article <1990Nov18.191622.13242@lavaca.uh.edu>
jet@karazm.math.uh.edu (J. Eric Townsend) writes:

> System: Amiga 2000, rev 4.3, FatAgnus, 1Mb motherboard
> Card: GVP Series II SCSI+ram, 4Mb 80ns RAM
> Drive: 40Mb Quantum

Benchmarks, once again ... sigh ...

Somehow, Eric's results do not match the figures I get:

- B2000 PAL, MC68000, 1 MB Chip, 0 Fast,
- GVP Series-II SCSI (no RAM) w/ 40 meg Quantum,
- Kickstart 1.3, 1.3 FastFileSystem, 512-byte blocks,
- no Startup-Sequence, 640x256x2 Workbench screen,
- empty partition, no AddBuffers (Envec = 32),
- DiskPerf from Fish Disk 187.

Please note:

- accelerator boards,
- different memory configurations,
- new 2.0 FS (also available on disk!),
- larger block sizes (only with 2.0 FS),
- different drives (e.g. Quantum 52S),
- different Benchmarks

will give you other results (usually higher). BTW: With a
Quantum 40, it's more likely that you measure the drive's
speed, not the controller's.

File create/delete:    create 16 files/sec, delete 38 files/sec
Directory scan:     106 entries/sec
Seek/read test:     101 seek/reads per second
r/w speed:          buf 512 bytes, rd 51442 byte/sec, wr 29358 byte/sec
r/w speed:          buf 4096 bytes, rd 177724 byte/sec, wr 156115 byte/sec
r/w speed:          buf 8192 bytes, rd 244803 byte/sec, wr 185588 byte/sec
r/w speed:          buf 32768 bytes, rd 455902 byte/sec, wr 262144 byte/sec
r/w speed:          buf 131072 bytes, rd 587986 byte/sec, wr 349525 byte/sec
r/w speed:          buf 524288 bytes, rd 635500 byte/sec, wr 388361 byte/sec

Now, what do all those figures mean? Actually, nothing at all,
since they won't make Eric's system any faster, but that's a
general problem with benchmarks. Somehow, this reminds me of
an article I found in comp.sys.amiga.tech just recently:

> I ran Dhrystones 2.1 on a 3000/25 with 68030 specific
> options (and 881 for the printf's %f) using non-register
> args and the optimizer. I got 5263 dhrystones. Does this
> sound right? I thought people here were claiming 7000?
> Anything I should be doing differently?

Ralph