Date: Thu, 12 Dec 1996 09:05:27 +0100 (MET) From: Christoph Kukulies <kuku@gilberto.physik.rwth-aachen.de> To: freebsd-hackers@freefall.FreeBSD.org Subject: ccd - some measurements Message-ID: <199612120805.JAA25514@gilberto.physik.rwth-aachen.de>
next in thread | raw e-mail | index | archive | help
Yesterday I finally got my ccd drive working. I have slow but cheap
SCSI disks and I thought I'd invest in future and put in two
ncr/pci controllers, with one drive attached to each (for the first).
Then I ran a batch job
#!/bin/sh
for i in 8 10 12 14 16 18 20 22 24 26 28 30 32 40 48 56 64 72 80 96
do
umount /a 2>&1 >/dev/null
ccdconfig -U
ccdconfig ccd0c $i none /dev/sd0e /dev/sd1e
newfs /dev/rccd0c 2>&1 >/dev/null
mount /dev/ccd0c /a
cd /a
bonnie 2>&1 >/root/$i.result
cd /
umount /a
done
which tested the ccd performance with different interleave factors using
bonnie. The results are below.
I didn't yet get higher than an interleave of 96. I didn't expect that
the results did still grow beyonf and interleave of 32 anyway. So
I tend to think that benchmarking the ccd with bonnie that way might
be questionable.
Also strange the high CPU percentage which I would expect with a PCI
busmaster DMA driven controller/transfer.
Quantum Atlas 2GB, PPRO-200/256, 32MB
Bonnie result:
-Per Char- --Block--- -Rewrite-- -Per Char- --Block--- --Seeks---
Machine MB K/sec %CPU K/sec %CPU K/sec %CPU K/sec %CPU K/sec %CPU /sec %CPU
PPRO 100 5006 43.3 4959 11.3 2290 6.3 5022 43.7 4890 7.0 87.1 1.9
CCD Amd K5/PR-133, two ncr/pci controllers, 2 Quantum Tempest 3.2 GB (slow)
I/L
8 100 2103 39.5 2118 10.9 828 7.0 2555 39.6 2324 13.6 58.9 4.3
12 100 2151 36.7 2160 10.4 968 8.0 3305 50.4 3067 17.0 59.1 4.3
10 100 2209 39.4 2231 11.4 934 7.9 2940 45.1 2682 15.2 61.3 4.6
18 100 2304 38.1 2290 10.8 1118 9.3 4182 64.4 3899 21.8 60.9 4.2
14 100 2415 41.2 2436 12.3 1020 8.7 3568 54.5 3293 18.1 60.5 4.3
20 100 2494 41.6 2525 12.0 1158 9.9 4523 68.6 4227 24.2 62.8 4.3
22 100 2559 42.0 2580 11.7 1153 9.6 4583 69.9 4527 24.8 64.3 4.4
16 100 2749 47.1 2790 13.2 1148 9.7 4150 62.8 3892 21.5 68.0 3.9
24 100 2760 45.8 2787 12.8 1197 10.4 4921 74.6 4900 26.9 66.0 4.2
26 100 2783 45.8 2814 13.3 1257 10.7 4962 74.9 4734 26.2 63.0 4.1
40 100 2853 45.0 2851 12.5 1416 11.5 5465 82.2 5256 28.9 67.3 4.2
28 100 2920 48.1 2941 13.7 1283 10.9 5224 79.2 4946 27.5 64.5 4.2
48 100 2934 46.5 2959 12.9 1657 13.5 5555 83.9 5340 29.8 67.8 4.0
30 100 3094 50.8 3133 14.2 1333 10.9 5370 81.2 5138 27.5 64.3 4.2
56 100 3210 51.7 3258 14.6 1737 14.2 5772 87.2 5643 31.2 68.4 4.2
32 100 3271 53.3 3322 14.8 1469 12.2 5241 78.7 5067 27.5 68.7 4.0
72 100 3552 56.6 3641 16.0 1963 15.9 5829 86.3 5651 29.8 67.7 4.1
80 100 3643 57.7 3679 16.1 2102 16.7 6113 90.5 5884 31.5 69.2 4.0
64 100 3657 57.8 3669 15.9 2153 17.7 6417 95.2 6430 34.5 69.2 4.1
96 100 4312 69.6 4404 19.7 2414 19.5 6359 93.6 6486 34.4 67.8 4.1
--Chris Christoph P. U. Kukulies kuku@gil.physik.rwth-aachen.de
Want to link to this message? Use this URL: <https://mail-archive.FreeBSD.org/cgi/mid.cgi?199612120805.JAA25514>