mtrr: no more MTRRs available & (scsi0:A:0:0): Locking max tag count at 64

[Steven Lee_11]

I see this error message in my dmesg and wonder if it is a major problem ?

mtrr: no more MTRRs available
mtrr: no more MTRRs available
(scsi0:A:0:0): Locking max tag count at 64
--

$ cat /proc/mtrr
reg00: base=0x10000000 ( 256MB), size= 128MB: write-back, count=1
reg01: base=0x00000000 ( 0MB), size= 256MB: write-back, count=1
reg02: base=0x400040000 (16384MB), size= 64KB: uncachable, count=1
reg03: base=0x400060000 (16384MB), size= 64KB: uncachable, count=1
reg04: base=0x400080000 (16384MB), size= 64KB: uncachable, count=1
reg05: base=0x4000a0000 (16384MB), size= 64KB: uncachable, count=1
reg06: base=0x4000c0000 (16384MB), size= 64KB: uncachable, count=1
reg07: base=0x4000e0000 (16384MB), size= 64KB: uncachable, count=1

My ML310 server is on Red Hat Linux 9.0, any feedback will be much appreciated.

From the net i found out that (scsi0:A:0:0): Locking max tag count at 64 message appears when you are having problem with your hdd , but i cant seem to find much information on how to proceed to diagnose it.


mtrr: no more MTRRs available , im not sure on this error but it shows up in the dmesg very frequently.

so i hope to find out more information on this and ways to resolve this problem

[Robert Binkhorst]

Hi Steven,

I found a document on it here:
http://www.ussg.iu.edu/hypermail/linux/kernel/0301.3/1033.html


Due to this 16MB hole, your BIOS has to set up a write-back range
covering 2048-16 (2032MB). Due to limitations on the way MTRRs work,
you can't do this all in 1, so you have to split it up over several.
The result is that you use up 5 MTRRs covering 1 range + 1 for the
unmapped 16MB. Leaving just two for..

> reg06: base=0x100000000 (4096MB), size=4096MB: write-back, count=1
> reg07: base=0x200000000 (8192MB), size=8192MB: write-back, count=1

So you really are out of MTRRs (There are only 8 on this CPU).
Does your BIOS have any option to disable this hole in low memory ?
I've seen similar things on laptops that use shared memory between
CPU & Graphics card, but I was unaware of anything like this on
desktop/server motherboards.

If this has onboard VGA, and theres a way to disable it, perhaps that
will work. (Even if it means plugging in a PCI/AGP video card)


HTH,

Robert

[Jeroen Peereboom]

I have the same problem on a DL360, 4 CPU.
In my case it has to do with X.
If I change the default runlevel to 3 (no X),
and reboot, there is no message.
If I next type 'startx', the message appears in /var/log/messages.

I also find these lines in the messages file:

mtrr: your CPUs had inconsistent fixed MTRR settings
mtrr: probably your BIOS does not setup all CPUs

I have no clue (yet).

JP.