lgreen@pnet01.cts.com (Lawrence Greenwald) (01/06/91)
Yesterday, thru Central Coast Software's BBS connection, I upgraded my
version of QuarterBack tools to the latest version (1.3c, December 6,
1990). I was/am hoping that the bugs reported in previous versions had been
eradicated, so I went out and tested it.
My configuration is a B2000, revision 4.3 motherboard, 512K Agnus, A2052
memory card w/2 meg), GVP series II HardCard (w/ram installed - 2meg),
Supra 2400ZI internal modem. Software is Kickstart 34.5, Workbench 34.28
(Technically, AmigaDos 1.3.2), ConMan 1.3e, ArpShell, Dmouse 1.25.
First thing I did was back up my partitions (one can never be too safe!),
then ran the tools program against both partitions, making sure to re-boot
after each partition was completed (Oh yes, I shut down BlitzDisk II and
VirusX 4.01 as a precaution *before* I started).
Afterward, I ran the DH0: partiton thru DiskSpeed 3.1 and came up with:
DiskSpeed 3.1 - Copyright (c) 1989,90 by MKSoft Development
Device: Drive0:
Comment CPI-3100, 68000 mode, medium (w/BlitzDisk II)
Test Intensity: Med Performance Stress: None
12 Files/s Create
64 Files/s Open/Close
205 Files/s Scan
54 Files/s Delete
189 Seek/Read
Buffer Size 512 4096 32768 262144
--------- --------- --------- --------- ---------
Bytes/s Create 27380 118514 228067 308546
Bytes/s Write 28558 170977 425412 596523
Bytes/s Read 143318 280106 539388 657930
I then realized that I had run the test with BlitzDisk running, so I shut
down BD and ran the speed test again. Results:
DiskSpeed 3.1 - Copyright (c) 1989,90 by MKSoft Development
Device: Drive0:
Comment CPI-3100, 68000 mode, medium (no BlitzDisk II)
Test Intensity: Med Performance Stress: None
10 Files/s Create
21 Files/s Open/Close
104 Files/s Scan
25 Files/s Delete
189 Seek/Read
Buffer Size 512 4096 32768 262144
--------- --------- --------- --------- ---------
Bytes/s Create 28049 142708 244922 308546
Bytes/s Write 29188 180825 522247 617093
Bytes/s Read 61003 275601 520223 625237
Now from previous testing, I had the drive running in the 350K to 400K
range, so I would say that reorganization did a pretty damn good job of
increasing disk throughput, even though some of the read counts may have
been skewed because of my running of BlitzDisk.
Larry Greenwald
UUCP: {hplabs!hp-sdd sdcsvax nosc}!crash!pnet01!lgreen
ARPA: crash!pnet01!lgreen@nosc.mil
INET: lgreen@pnet01.cts.com
SNAIL:4545 Collwood Blvd, #52 San Diego, CA 92115
"I'm looking over a three-leaf clover that I overlooked be-three!" -Bugs Bunny