Occasional message: Locking max tag count at 128 - why?
basil.hussain at kodakweddings.com
Mon Aug 11 06:23:00 CDT 2003
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.
Internet Developer, Kodak Weddings
E-Mail: basil.hussain at kodakweddings.com
More information about the Linux-PowerEdge