Subject: Re: Re: PWS IDE Questions
To: None <Riccardo.Veraldi@fi.infn.it,>
From: Matthew Lukaszewicz <proliant@bellsouth.net>
List: port-alpha
Date: 03/25/2003 11:24:44
Hello All,
      I am currently using a WD 100GB with 8MB cache on my PWS 433a running FreeBSD 5.0 release. I have experienced no known issues and it happily chugs along running my home network file and print sharing and serving web and ftp.

Matthew

> 
> From: Riccardo.Veraldi@fi.infn.it
> Date: 2003/03/25 Tue AM 08:43:25 EST
> To: Ray Phillips <r.phillips@jkmrc.uq.edu.au>
> CC: port-alpha@netbsd.org
> Subject: Re: PWS IDE Questions
> 
> 
> I could use a 120GB IBM on my DPW 500a succesfully
> 
> Rick
> 
> 
> On Tue, 25 Mar 2003, Ray Phillips wrote:
> 
> > Dear port-alpha:
> >
> > What's the biggest IDE disk which can be used successfully with the
> > IDE controller on the PWS's main logic board?  I suppose it might
> > vary with the vintage of the machine (and SRM version?) -- mine has a
> > 500 MHz CPU, the Pyxis DMA bug and SRM V7.2-1.  The largest I've
> > tried is a 40 GB Seagate ST340016A which wasn't a problem.
> >
> > That is, creating the biggest partition possible and newfs'ing it was
> > fine, but copying my /usr partition--on sd1, containing about 8
> > GB--to it took 68 minutes.  That's a rate of only about 2 MB per
> > second which seems rather slow.  I tried the same thing again the
> > next day and gave up waiting for it to finish after  258 minutes had
> > passed, by which time only about 62 MB had been copied.
> >
> > I also tried connecting the ST340016A to a PCI IDE controller based
> > on a CMD chip and copying /usr to it.  That took about 40% longer.
> >
> > Even copying /usr to another SCSI disk (a Seagate ST318417N) took 109 minutes.
> >
> > Any thoughts on why it's so slow?  I thought a SCSI to SCSI copy
> > would achieve at least 5 MB/s and that a modern IDE disk wouldn't be
> > too far behind.  Maybe I shouldn't expect that when so many small
> > files are involved?  I've appended part of dmesg's output to this
> > email.
> >
> >
> > Ray
> >
> >
> >
> > NetBSD 1.6Q (GENERIC) #0: Sun Mar 23 09:34:37 EST 2003
> >
> > root@pws500.jkmrc.uq.edu.au:/usr/obj/sys/arch/alpha/compile.alpha/GENERC
> > Digital Personal WorkStation 500au, 500MHz, s/n
> > 8192 byte page size, 1 processor.
> > total memory = 256 MB
> > (1896 KB reserved for PROM, 254 MB used by NetBSD)
> > avail memory = 229 MB
> > using 1639 buffers containing 13112 KB of memory
> > .
> > pciide0 at pci0 dev 4 function 0: CMD Technology PCI0646 (rev. 0x01)
> > pciide0: bus-master DMA support present
> > pciide0: primary channel wired to compatibility mode
> > .
> > pci1 at ppb0 bus 1
> > pci1: i/o space, memory space enabled
> > pciide1 at pci1 dev 8 function 0: CMD Technology PCI0649 (rev. 0x01)
> > pciide1: bus-master DMA support present
> > pciide1: primary channel configured to native-PCI mode
> > pciide1: using dec 550 irq 12 for native-PCI interrupt
> > wd0 at pciide1 channel 0 drive 0: <ST340016A>
> > wd0: drive supports 16-sector PIO transfers, LBA addressing
> > wd0: 38166 MB, 16383 cyl, 16 head, 63 sec, 512 bytes/sect x 78165360 sectors
> > wd0: 32-bit data port
> > wd0: drive supports PIO mode 4, DMA mode 2, Ultra-DMA mode 5 (Ultra/100)
> > wd0(pciide1:0:0): using PIO mode 4, Ultra-DMA mode 2 (Ultra/33)
> > (using DMA data)
> > .
> > siop0 at pci1 dev 10 function 0: Symbios Logic 53c875 (ultra-wide scsi)
> > .
> > sd1 at scsibus0 target 1 lun 0: <SEAGATE, ST318436LW, 0005> disk fixed
> > sd1: 17522 MB, 14384 cyl, 6 head, 415 sec, 512 bytes/sect x 35885168 sectors
> > sd1: sync (100.0ns offset 8), 16-bit (20.000MB/s) transfers, tagged queueing
> >
> 
>