Occasional message: Locking max tag count at 128 - why?

Basil Hussain basil.hussain at kodakweddings.com
Mon Aug 11 06:23:00 CDT 2003

Hi all,

Every now and again, I see this message in my logs:

Aug  8 04:02:58 trillian kernel: (scsi0:A:0:0): Locking max tag count at 128

As far as I can gather from /proc/scsi/scsi (output below), the SCSI device
it refers to is the sole internal SCSI drive in the system.

Host: scsi0 Channel: 00 Id: 00 Lun: 00
  Vendor: FUJITSU  Model: MAM3184MC        Rev: 5A01
  Type:   Direct-Access                    ANSI SCSI revision: 03

Scouting around the kernel source, the error message seems to come from
aic7xxx_linux.c, line 2150. There's a comment close by that says:

 * If we repeatedly see a queue full
 * at the same queue depth, this
 * device has a fixed number of tag
 * slots.  Lock in this tag depth
 * so we stop seeing queue fulls from
 * this device.

I don't quite get the explanation above, and nothing seems to be wrong, but
I am curious as to why it is occurring, and whether it should occur. Anyone
got any ideas?

Oh, and by the way, this is on a PE1550.


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

More information about the Linux-PowerEdge mailing list