Advice on Cluster Hardware.
Nirmal.Bissonauth at durham.ac.uk
Wed Feb 6 02:24:55 PST 2002
I have 6 Tyan Thunder K7 motherboards (Dual 1.2 GHz Athlon MP) in my
cluster. I am using Redhat7.2, kernel 2.4.9-13smp. The problem I get is
with the E-IDE driver. It does not correctly initialise the AMD7411 IDE
controller and thus it can't go any faster than UDMA33 with the IDE hard
drives. You may have the same problem with the Tyan Tiger MP.
Here are the kernel messages during boot up. I can use the override
parameters idebus=66, but I can't confirm that it actually makes it go any
faster. The hard drive is capable of UDMA 100 by the way.
Uniform Multi-Platform E-IDE driver Revision: 6.31
ide: Assuming 33MHz PCI bus speed for PIO modes; override with idebus=xx
AMD7411: IDE controller on PCI bus 00 dev 39
AMD7411: chipset revision 1
AMD7411: not 100% native mode: will probe irqs later
AMD7411: disabling single-word DMA support (revision < C4)
ide0: BM-DMA at 0xf000-0xf007, BIOS settings: hda:DMA, hdb:pio
ide1: BM-DMA at 0xf008-0xf00f, BIOS settings: hdc:pio, hdd:pio
hda: IC35L040AVER07-0, ATA DISK drive
ide0 at 0x1f0-0x1f7,0x3f6 on irq 14
hda: 80418240 sectors (41174 MB) w/1916KiB Cache, CHS=79780/16/63,
On Tue, 5 Feb 2002, Alberto Ramos wrote:
> Here in a university of Madrid, we are designing a Beowulf for paralel
> computing in QCD. We will begin with a small cluster to see the performance
> and later try with other comunications, like mirynet.
> The Hardware will be 4 nodes each consisting of:
> - 2xAMD MP 1800+ CPU
> - 1x512MB RAM DDR
> - 1xTyan tiger MP
> - 2x3-COM 905B NIC
> - 20GB HD
> The master node has 1GB of RAM DDR, and one aditional HD to use as /home.
> The conection will be trought a HP Procurve Switch 408 with 8 ports to use
> Chanel Bonding.
> Now the questions:
> - Any known problems with the hardware?
> - Are the NIC and the Switch good choices?
> - Will the Intel FORTRAN 90 Compiler work with this hardware.
> Thank you very much for your time.
> Beowulf mailing list, Beowulf at beowulf.org
> To change your subscription (digest mode or unsubscribe) visit http://www.beowulf.org/mailman/listinfo/beowulf
More information about the Beowulf