Server dies under heavy I/O

Basil Hussain basil.hussain at kodakweddings.com
Wed Aug 27 12:20:01 CDT 2003


Hi,

Well, I downgraded my kernel to 2.4.20-18.8 and installed the latest aic7xxx
driver (6.2.36). Everything seems to work, but I got this message upon
bootup:

blk: queue c181dc14, I/O limit 4095Mb (mask 0xffffffff)
(scsi0:A:0): 160.000MB/s transfers (80.000MHz DT, offset 127, 16bit)
scsi1:A:0:0: DV failed to configure device.  Please file a bug report
against this driver.
  Vendor: FUJITSU   Model: MAM3184MC         Rev: 5A01
  Type:   Direct-Access                      ANSI SCSI revision: 03

What does this mean? I believe 'DV' stands for Domain Validation, but that's
pretty much all I know. A bit of Googling shows me that this could possibly
be to-do with the firmware on the SCSI drive in question and that there are
settings for enabling/disabling Domain Validation in the Adaptec's
SCSI-Select BIOS.

I'm not quite sure where to go from here. Any suggestions? Do I have a bad
drive that is causing me all these problems?

Regards,

Basil Hussain
---------------------------------------
Internet Developer, Kodak Weddings
E-Mail: basil.hussain at kodakweddings.com

P.S. Further relevant content from /var/log/dmesg below:

SCSI subsystem driver Revision: 1.00
PCI: Found IRQ 3 for device 02:05.0
PCI: Found IRQ 11 for device 02:05.1
scsi0 : Adaptec AIC7XXX EISA/VLB/PCI SCSI HBA DRIVER, Rev 6.2.36
        <Adaptec aic7899 Ultra160 SCSI adapter>
        aic7899: Ultra160 Wide Channel A, SCSI Id=7, 32/253 SCBs

scsi1 : Adaptec AIC7XXX EISA/VLB/PCI SCSI HBA DRIVER, Rev 6.2.36
        <Adaptec aic7899 Ultra160 SCSI adapter>
        aic7899: Ultra160 Wide Channel B, SCSI Id=7, 32/253 SCBs

blk: queue c181dc14, I/O limit 4095Mb (mask 0xffffffff)
(scsi0:A:0): 160.000MB/s transfers (80.000MHz DT, offset 127, 16bit)
scsi1:A:0:0: DV failed to configure device.  Please file a bug report
against this driver.
  Vendor: FUJITSU   Model: MAM3184MC         Rev: 5A01
  Type:   Direct-Access                      ANSI SCSI revision: 03
blk: queue c181de14, I/O limit 4095Mb (mask 0xffffffff)
  Vendor: DELL      Model: 1x3 U2W SCSI BP   Rev: 1.21
  Type:   Processor                          ANSI SCSI revision: 02
blk: queue c181d414, I/O limit 4095Mb (mask 0xffffffff)
scsi0:A:0:0: Tagged Queuing enabled.  Depth 32
(scsi1:A:0): 160.000MB/s transfers (80.000MHz DT, offset 31, 16bit)
  Vendor: JetStor   Model: III IDE           Rev: 0001
  Type:   Direct-Access                      ANSI SCSI revision: 03
blk: queue c181d214, I/O limit 4095Mb (mask 0xffffffff)
  Vendor: JetStor   Model: III IDE           Rev: 0001
  Type:   Direct-Access                      ANSI SCSI revision: 03
blk: queue c181d614, I/O limit 4095Mb (mask 0xffffffff)
  Vendor: JetStor   Model: III IDE           Rev: 0001
  Type:   Direct-Access                      ANSI SCSI revision: 03
blk: queue c181da14, I/O limit 4095Mb (mask 0xffffffff)
  Vendor: JetStor   Model: III IDE           Rev: 0001
  Type:   Direct-Access                      ANSI SCSI revision: 03
blk: queue c181d014, I/O limit 4095Mb (mask 0xffffffff)
  Vendor: JetStor   Model: III IDE           Rev: 0001
  Type:   Direct-Access                      ANSI SCSI revision: 03
blk: queue c181d814, I/O limit 4095Mb (mask 0xffffffff)
scsi1:A:0:0: Tagged Queuing enabled.  Depth 32
scsi1:A:0:1: Tagged Queuing enabled.  Depth 32
scsi1:A:0:2: Tagged Queuing enabled.  Depth 32
scsi1:A:0:3: Tagged Queuing enabled.  Depth 32
scsi1:A:0:4: Tagged Queuing enabled.  Depth 32
Attached scsi disk sda at scsi0, channel 0, id 0, lun 0
Attached scsi disk sdb at scsi1, channel 0, id 0, lun 0
Attached scsi disk sdc at scsi1, channel 0, id 0, lun 1
Attached scsi disk sdd at scsi1, channel 0, id 0, lun 2
Attached scsi disk sde at scsi1, channel 0, id 0, lun 3
Attached scsi disk sdf at scsi1, channel 0, id 0, lun 4
SCSI device sda: 35566478 512-byte hdwr sectors (18210 MB)
Partition check:
 sda: sda1 sda2 sda3 sda4 < sda5 sda6 sda7 sda8 sda9 >
SCSI device sdb: 683737088 512-byte hdwr sectors (350073 MB)
 sdb: sdb1
SCSI device sdc: 683737088 512-byte hdwr sectors (350073 MB)
 sdc: sdc1
SCSI device sdd: 683737088 512-byte hdwr sectors (350073 MB)
 sdd: sdd1
SCSI device sde: 683737088 512-byte hdwr sectors (350073 MB)
 sde: sde1
SCSI device sdf: 683737088 512-byte hdwr sectors (350073 MB)
 sdf: sdf1


> -----Original Message-----
> From: Steve_Boley at Dell.com [mailto:Steve_Boley at Dell.com]
> Sent: 27 August 2003 15:46
> To: basil.hussain at kodakweddings.com
> Subject: RE: Server dies under heavy I/O
>
>
> No it won't work, you need to email Justin and see if he
> will provide with source so you can build a module for the
> 2.4.20-20 version of the kernel or see if he has one already
> built for you.  Modules have to match the kernel or you will
> have symbol failures and it won't load.
> Steve
>
> -----Original Message-----
> From: Basil Hussain [mailto:basil.hussain at kodakweddings.com]
> Sent: Wednesday, August 27, 2003 9:37 AM
> To: Boley, Steve
> Subject: RE: Server dies under heavy I/O
>
>
> Hi,
>
> I checked the tarball inside the RPM and found that the latest module
> applicable to me is aic7xxx-2.4.20-18.8-i686. I'm running the latest RH8
> errata kernel of 2.4.20-20.8.
>
> Will this work? Does it matter if it's '-18.8' versus '-20.8'? I
> can go back
> to running the out-of-the-box 2.4.18-14 kernel if need be (I only upgraded
> to 2.4.20 in the hope of curing this problem).
>
> Thanks,
>
> Basil Hussain
> ---------------------------------------
> Internet Developer, Kodak Weddings
> E-Mail: basil.hussain at kodakweddings.com
>
>
> > -----Original Message-----
> > From: Steve_Boley at Dell.com [mailto:Steve_Boley at Dell.com]
> > Sent: 27 August 2003 14:47
> > To: basil.hussain at kodakweddings.com
> > Subject: RE: Server dies under heavy I/O
> >
> >
> > Get the tarball and look inside the package and you will then see what
> > kernels he has the modules built against.  They usually lag a
> > couple behind
> > what redhat has currently out.
> >
> > He has built the package correctly to where it installs the modules and
> > does all the initrd in the background, so yes just do rpm -ivh and if
> > it complains it is already on the system do --force with it.
> > Steve
> >
> > -----Original Message-----
> > From: Basil Hussain [mailto:basil.hussain at kodakweddings.com]
> > Sent: Wednesday, August 27, 2003 4:19 AM
> > To: Boley, Steve
> > Cc: Linux-Poweredge at exchange.dell.com
> > Subject: RE: Server dies under heavy I/O
> >
> >
> > Hi,
> >
> > By the way, is there anything I need to know or do before I go ahead and
> > install this RPM?
> >
> > I gather from its contents (various bash and awk scripts) that it
> > does stuff
> > like rebuild your initrd and fiddle with your grub setup and
> modules.conf.
> >
> > Or is it just a straightforward "rpm -ivh aic7xxx-6.2.36-rh80.i686.rpm"?
> >
> > Regards,
> >
> > Basil Hussain
> > ---------------------------------------
> > Internet Developer, Kodak Weddings
> > E-Mail: basil.hussain at kodakweddings.com
> >
> > > -----Original Message-----
> > > From: linux-poweredge-admin at dell.com
> > > [mailto:linux-poweredge-admin at dell.com]On Behalf Of Basil Hussain
> > > Sent: 27 August 2003 10:02
> > > To: Steve_Boley at dell.com
> > > Cc: Linux-Poweredge at dell.com
> > > Subject: RE: Server dies under heavy I/O
> > >
> > >
> > > Hi,
> > >
> > > Thanks for that tip. I will try updating the aic7xxx module to
> > the latest
> > > 6.2.36 (it's currently running 6.2.8). Oh, and to save anyone Googling
> > > around for half-an-hour, I imagine you would've wanted to give me
> > > a link to
> > > the following... ;-)
> > >
> > > http://people.freebsd.org/~gibbs/linux/
> > >
> > > Regards,
> > >
> > > Basil Hussain
> > > ---------------------------------------
> > > Internet Developer, Kodak Weddings
> > > E-Mail: basil.hussain at kodakweddings.com
> > >
> > >
> > > > -----Original Message-----
> > > > From: linux-poweredge-admin at dell.com
> > > > [mailto:linux-poweredge-admin at dell.com]On Behalf Of
> > Steve_Boley at dell.com
> > > > Sent: 26 August 2003 22:23
> > > > To: basil.hussain at kodakweddings.com
> > > > Cc: Linux-Poweredge at dell.com
> > > > Subject: RE: Server dies under heavy I/O
> > > >
> > > >
> > > > update the aic7xxx and see if that fixes it.  Justin Gibbs page has
> > > > some statically compiled for various recent kernels and if not
> > > available,
> > > > you could hit him up for latest 6.2.3x source.
> > > > Steve




More information about the Linux-PowerEdge mailing list