/proc/rd/ relevant information:
***** DAC960 RAID Driver Version 2.2.4 of 23 August 1999 *****
Copyright 1998-1999 by Leonard N. Zubkoff <[EMAIL PROTECTED]>
Configuring Mylex DAC960PG PCI RAID Controller
Firmware Version: 4.06-0-08, Channels: 1, Memory Size: 4MB
PCI Bus: 0, Device: 10, Function: 1, I/O Address: Unassigned
PCI Address: 0xE3000000 mapped at 0xE0000000, IRQ Channel: 10
Controller Queue Depth: 64, Maximum Blocks per Command: 128
Driver Queue Depth: 63, Maximum Scatter/Gather Segments: 33
Stripe Size: 64KB, Segment Size: 8KB, BIOS Geometry: 255/63
Physical Devices:
0:1 Vendor: QUANTUM Model: ATLAS IV 9 WLS Revision: 0808
Serial Number: 369920036610
Disk Status: Online, 17940480 blocks
0:2 Vendor: QUANTUM Model: ATLAS IV 9 WLS Revision: 0909
Serial Number: 369928636270
Disk Status: Online, 17940480 blocks
Logical Drives:
/dev/rd/c0d0: RAID-1, Online, 17940480 blocks, Write Back
No Rebuild or Consistency Check in Progress
Rebooted with 48M, runlevel 1 and used card's default settings (god help
me if I'm to remember) - results were [close to abysmal]:
Bonnie (meaningless to some, but the more numbers the merrier)
-------Sequential Output-------- ---Sequential Input-- --Random--
-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
200 3972 15.8 4035 3.1 2469 4.0 9629 26.9 11728 6.2 125.8 1.2
o size specified, using 200 MB
Size is MB, BlkSz is Bytes, Read and Write are MB/sec, Seeks are
Seeks/sec
Dir Size BlkSz Thr# Read (CPU%) Write (CPU%) Seeks (CPU%)
----- ------ ------- ---- ------------- -------------- --------------
. 200 4096 1 10.9170 4.42% 3.56428 2.67% 155.410 0.46%
. 200 4096 2 6.22406 2.39% 3.52560 2.71% 160.548 0.56%
. 200 4096 4 5.23795 2.17% 3.50997 2.75% 168.489 0.58%
. 200 4096 8 5.03577 2.26% 3.48347 2.76% 182.122 0.64%
. 200 4096 16 4.81379 2.21% 3.45413 2.77% 194.571 0.62%
. 200 4096 32 4.68638 2.21% 3.44538 2.79% 204.298 0.68%
. 200 4096 64 4.61414 2.25% 3.46862 2.82% 218.871 0.73%
Looks pretty bad, huh? You might want to argue that a) The drives are
crummy cheapos and b) CPU load is held down - but I sure was disappointed
on the money we spent.
Cheers,
--
_/\ Christian Reis is sometimes [EMAIL PROTECTED]
\/~ suicide architect | free software advocate | mountain biker
