> > I am currently having problems with my new Dual Celeron testsystem,
> > when trying to use UDMA66.
...
> If you are using the newest code, then the problem might be that
> your disks doesn't work proberly with UDMA66. I've seen several
> newer disks that has problems here, and frankly Maxtor is not
> known for their quality in this respect.
...
> Trying another disk is also an option, I know that the IBM's
> work just fine, and that some of the Quantums and WDC's are broken.
FWIW, I can confirm that IBM disks work just fine. I have a system with
BP6, 2 x Celeron 366 (no overclocking), IBM DTTA-351010 on UDMA33, IBM
DPTA-372730 on UDMA66. The system works great, no timeouts (even when
doing the "dd if=junk of=/dev/null bs=1024k" test suggested).
I do have one issue with the new disk driver on this system: Running
rawio produces inconsistent results for the sequential write case.
This does not happen with the old wd driver and the same disk used in
UDMA33 mode (PIIX4 controller).
Here are some results from -current of today, DPTA-372730/UDMA66. You
can clearly see the effect on the sequential write case, while the
other cases are very nice and consistent.
Steinar Haug, Nethelp consulting, [EMAIL PROTECTED]
----------------------------------------------------------------------
# rawio -a -v 1 /dev/rad1
RR anon 1726.7 107 0.1 0.7 0.7 16384
SR anon 48016.6 2931 0.2 17.8 18.0 16384
RW anon 1526.4 95 0.0 0.7 0.7 16384
SW anon 7777.5 475 0.1 2.9 3.0 16384
# rawio -a -v 1 /dev/rad1
Test ID K/sec /sec %User %Sys %Total
RR anon 1702.7 106 0.0 0.7 0.7 16384
SR anon 48088.4 2935 0.6 17.4 17.9 16384
RW anon 1518.3 95 0.1 0.7 0.7 16384
SW anon 14244.6 869 0.2 5.1 5.3 16384
# rawio -a -v 1 /dev/rad1
Test ID K/sec /sec %User %Sys %Total
RR anon 1724.2 107 0.0 0.7 0.7 16384
SR anon 48051.5 2933 0.6 17.5 18.1 16384
RW anon 1511.8 94 0.0 0.7 0.7 16384
SW anon 7421.0 453 0.1 2.8 2.9 16384
# rawio -a -v 1 /dev/rad1
Test ID K/sec /sec %User %Sys %Total
RR anon 1714.9 106 0.0 0.7 0.7 16384
SR anon 48060.2 2933 0.6 17.4 18.1 16384
RW anon 1533.3 95 0.0 0.7 0.7 16384
SW anon 7781.0 475 0.3 2.7 3.0 16384
# rawio -a -v 1 /dev/rad1
Test ID K/sec /sec %User %Sys %Total
RR anon 1721.2 106 0.0 0.7 0.7 16384
SR anon 48066.2 2934 0.9 17.0 17.9 16384
RW anon 1524.0 95 0.0 0.7 0.7 16384
SW anon 14083.9 860 0.3 5.0 5.4 16384
# rawio -a -v 1 /dev/rad1
Test ID K/sec /sec %User %Sys %Total
RR anon 1711.9 106 0.0 0.7 0.7 16384
SR anon 48043.6 2932 0.8 17.2 18.0 16384
RW anon 1504.7 95 0.0 0.7 0.7 16384
SW anon 7790.9 476 0.2 2.8 3.0 16384
# rawio -a -v 1 /dev/rad1
Test ID K/sec /sec %User %Sys %Total
RR anon 1708.0 106 0.0 0.7 0.7 16384
SR anon 48057.5 2933 0.9 17.1 18.0 16384
RW anon 1528.4 95 0.0 0.7 0.7 16384
SW anon 14284.0 872 0.3 5.2 5.5 16384
# rawio -a -v 1 /dev/rad1
Test ID K/sec /sec %User %Sys %Total
RR anon 1706.9 106 0.0 0.7 0.7 16384
SR anon 48015.8 2931 1.0 17.0 18.0 16384
RW anon 1515.0 95 0.0 0.7 0.7 16384
SW anon 7742.7 473 0.1 2.9 2.9 16384
# rawio -a -v 1 /dev/rad1
Test ID K/sec /sec %User %Sys %Total
RR anon 1704.9 106 0.0 0.7 0.7 16384
SR anon 48074.9 2934 0.7 17.3 18.0 16384
RW anon 1517.0 94 0.0 0.7 0.7 16384
SW anon 7475.3 456 0.2 2.8 2.9 16384
# rawio -a -v 1 /dev/rad1
Test ID K/sec /sec %User %Sys %Total
RR anon 1721.8 106 0.0 0.7 0.7 16384
SR anon 48051.0 2933 1.2 16.8 18.0 16384
RW anon 1525.4 95 0.0 0.7 0.7 16384
SW anon 14061.4 858 0.2 5.1 5.3 16384
# rawio -a -v 1 /dev/rad1
Test ID K/sec /sec %User %Sys %Total
RR anon 1712.8 106 0.0 0.7 0.7 16384
SR anon 48070.0 2934 0.9 17.2 18.1 16384
RW anon 1528.9 95 0.0 0.7 0.7 16384
SW anon 7788.8 475 0.1 2.9 3.0 16384
To Unsubscribe: send mail to [EMAIL PROTECTED]
with "unsubscribe freebsd-current" in the body of the message
