For the sake of experimentation, I'll throw in a *real* Pro-100B card
and see if it happens again (it takes 8 days for the panic to happen).
I can also measure the consistency of this "8 day" phenomena.
As an aside, there's not much SCSI activity on this system. I've had
very good results with 7200 RPM ATA-66 IDE drives, and kernel tweaks
for the wd controller (flags 0xb0ffb0ff):
wdc0: unit 0 (wd0): <WDC WD273BA>, LBA, DMA, 32-bit, multi-block-16
wd0: 26105MB (53464320 sectors), 3328 cyls, 255 heads, 63 S/T, 512 B/S
wdc0: unit 1 (wd1): <WDC WD273BA>, LBA, DMA, 32-bit, multi-block-16
wd1: 26105MB (53464320 sectors), 3328 cyls, 255 heads, 63 S/T, 512 B/S
These IDE drives, in a ccd array, are the ones that get pounded,
compared to the "da0" SCSI system drive. Soft-updates are also
enabled... (please forward to list if appropriate - I'm not a sub).
% iostat 30 10 (truncated)
ccd0 da0 wd0 cpu
KB/t tps MB/s KB/t tps MB/s KB/t tps MB/s us ni sy in id
27.61 124 3.34 7.80 108 0.82 19.31 91 1.72 19 0 15 8 57
32.06 115 3.60 7.92 72 0.56 21.26 88 1.83 18 0 13 8 60
25.95 110 2.79 7.99 63 0.49 18.46 81 1.46 15 0 11 6 68
24.84 111 2.70 7.86 55 0.42 17.29 84 1.42 13 0 10 7 71
27.77 118 3.21 7.98 67 0.52 19.18 86 1.62 17 0 13 8 62
25.78 106 2.68 8.05 61 0.48 18.07 77 1.36 13 0 11 7 70
23.61 121 2.79 8.00 71 0.55 16.45 88 1.42 15 0 12 7 66
David Greenman:
> I think it is caused by the NCR/Symbios controller. It might be a side
> effect of the NCR just using up a lot of PCI bandwidth, with the real
> bug being in the fxp driver (though I've looked and haven't found one).
> So I don't think putting in a real Pro/100 will have any effect on the
> problem. Of course I don't really know what is causing it, so just
> about anything is possible.
---
Lew Payne Publishing, Inc. Dunn & Bradstreet listed
994 San Antonio Road DUNS # 055037852
Palo Alto, CA 94303
To Unsubscribe: send mail to [EMAIL PROTECTED]
with "unsubscribe freebsd-hackers" in the body of the message
