Subject: Re: aac(4) vs. Dell PERC 3/Di _and_ HP NetRAID-4M in same host
To: NetBSD Help List <netbsd-help@netbsd.org>
From: Greg A. Woods <woods@planix.com>
List: netbsd-help
Date: 03/16/2007 22:47:18
--pgp-sign-Multipart_Fri_Mar_16_22:47:15_2007-1
Content-Type: text/plain; charset=US-ASCII
Content-Transfer-Encoding: quoted-printable

At Thu, 01 Mar 2007 21:12:02 -0500,
Me-planix.com wrote:
>=20
> I've got a Dell PowerEdge 2650 here with that I've added an HP
> NetRAID-4M card to for additional external storage.

OK, so I threw one of the pair of NetRAID-4M cards I have into an AMD-64
box after finally clearing enough junk off the top of it to get it
opened up (having rack-mount boxes that are not on rails and not in a
cabinet is not ideal, so say the least), and then did a fresh
FreeBSD-6.2 install onto it.

Since I only had room and power in the box for a pair of drives, I threw
in a pair of older Seagate Cheeta 9GB drives and created a simple RAID-0
container from them.

All's well.  FreeBSD can read from the raw device for the container at
nearly 80MB/s, and from a file on a filesystem at over 60MB/s, and can
write to it nearly as fast.  The controller definitely works A-OK.

So, just for laughs I created a RAID-0 container from some of the drives
on the array connected to the Dell PE2650 and it's NetRAID-4m card.  The
container appeared as "OK" right after the create of course and all
seemed well from the BIOS level.

aac1 at pci4 dev 6 function 0: HP NetRAID-4M
aac1: interrupting at ioapic1 pin 0 (irq 7)
aac1: StrongARM SA110 at 233MHz, 144MB mem (128MB cache), required battery =
present
aac1: Kernel 2.4-1 [Build 4607], Monitor 2.4-1 [Build 4607], S/N 8A1A4F
aac1: Controller supports: 17f<SNAPSHOT,CLUSTERS,WCACHE,DATA64,HOSTTIME,RAI=
D50,WINDOW4GB,SOFTERR>
ld1 at aac1 unit 0: RAID 0 (Stripe)
ld1: 69418 MB, 8849 cyl, 255 head, 63 sec, 512 bytes/sect x 142169088 secto=
rs

=46rom NetBSD things are still bizzare, but I can read something other
than zeros off the container sometimes.  However the first few megabytes
are still always all zeros and even though a newfs runs without
complaint the resulting filesystem cannot be mounted and I still read
all zeros from the start of the device.

I'm guessing FreeBSD on the Dell won't improve the situtation any more
with a RAID-0 container than it did with RAID-5, and that the problem is
actually somehow related with the HP card working inside the Dell
server, but I'll give it a try sometime tomorrow anyway.

Hints and suggestions would be very welcome!

--=20
						Greg A. Woods
						Planix, Inc.

<woods@planix.com>     +1 416 489-5852 x122     http://www.planix.com/

--pgp-sign-Multipart_Fri_Mar_16_22:47:15_2007-1
Content-Type: application/pgp-signature
Content-Transfer-Encoding: 7bit

-----BEGIN PGP SIGNATURE-----
Version: PGPfreeware 5.0i for non-commercial use
MessageID: w+2nUq3su40ai0NcWkY+ZS8PT04SVn9J

iQA/AwUBRftWtmZ9cbd4v/R/EQIpZwCdHS98uVju9nHfypbw++Orw8sYTIsAn3sx
fC3Mn3UhQwTowZunlZcFntv1
=oCbs
-----END PGP SIGNATURE-----

--pgp-sign-Multipart_Fri_Mar_16_22:47:15_2007-1--