[Raion]

I always suggest .22 -- .30 is unfortunately not the latest and greatest and has some issues with it that earlier versions don't.

[weblacky]

Yeah, I caught that. I didn’t mean to imply to use 6.5.17, only be higher. I wasn’t clear enough, bad assumption.

[jwhat]

Hi Megaimg,

the likely cause of the "TLB Refill Exception" is that you are using an IRIX version that does not support your HW (Fuel).

I have seen this when:
- 1. Running later series machine with older IRIX version
- 2. Having L1 SW version that is older than O350 board version

If this continues after you try more recent IRIX version, then you might need to go into POD/CAC mode and do a log clear and reset.

Cheers from Oz,

jwhat/John

[megaimg]

So enable Debug, let me know if you see anything....

IP35 PROM SGI Version 6.210 built 02:33:51 PM Aug 26, 2004
built for bedrock rev. 1.1 or greater
running in IP34 mode
Running in DDR mode
Local master CPU A revision: f24
PROM length: 0x1686a8, BSS length: 0xa7a0, flash count: 6
Configured bedrock clock: 200.0 MHz
Status of local IO: 0x1 0x3fc0fff6403
Bedrock Rev: 2, Module: 1 (001c01) from Sys Ctlr
On PROM entry: ERR_EPC=0xc00000001fc6b5e8 (0xc00000001fc6b5e8)
Configuring memory
Local memory configured: 1024 MB (standard)
*** Warning: System controller debug switches are non-zero (0x10d)
*** Diag level set to None (2)
*** Info level set to verbose
*** Boot stop requested at Global (2)
before reading NICHub NIC: 0x54591bbe
SR1 set to 0x0000080690349000
SR0 set to 0x0000000054591bbe
Testing/Initializing memory ............... DONE
Copying PROM code to memory ............... Copy PROM (0x9000000018000000) to RAM (0x9600000001a00000), len 0x1686a8
Done
DONE
Skipping secondary cache diags
CPU A switching stack into UALIAS and invalidating D-cache
CPU A switching into node 0 cached RAM
CPU A running cached
Initializing kldir.
Done initializing kldir.
Initializing klconfig.
init_klcfg: nasid 0 start 9600000000030000 size 10000
Done initializing klconfig.
Discovering local IO ...................... Check_master: link 10 is master
Check_master: link 10 is master
DONE
CPU A initialized subnode
Discovering NUMAlink connectivity .........
Local hub NUMAlink is down.
*** Local network link down
DONE
Found 1 objects (1 hubs, 0 routers) in 30360 usec
Waiting for peers to complete discovery.... Discovery results:
ENTRY 0: HUB(54591bbe)
NASID=-1 Mod=1 Flg=0x1500000 PROM=6.210 Route=N/A
MODULE=001c01 PARTITION=0 SPACE=RESET
Port 1 connection: Not connected
Port status: NF
DONE
No other nodes present; becoming global master
Global master is entry 0, NIC 0x54591bbe, /hw/rack/001/bay/01
Global master is /hw/rack/001/bay/01
Global barrier (line 4315)Global barrier passed.
Global barrier (line 4348)Global barrier passed.
Master System Topology Graph (pre-nasid_assign):
ENTRY 0: HUB(54591bbe)
NASID=-1 Mod=1 Flg=0x1500000 PROM=6.210 Route=N/A
MODULE=001c01 PARTITION=0 SPACE=RESET
Port 1 connection: Not connected
Port status: NF
Calculating NASIDs
num_routers is 0
Master System Topology Graph:
ENTRY 0: HUB(54591bbe)
NASID=0 Mod=1 Flg=0x1500000 PROM=6.210 Route=N/A
MODULE=001c01 PARTITION=0 SPACE=RESET
Port 1 connection: Not connected
Port status: NF
Distributing routing tables
Distributing NASIDs
*** NASID assigned to 0
CPU A switching to UALIAS
CPU A running in UALIAS
Changing node ID to 0
Global barrier (line 4823)Global barrier passed.
CPU A Flushing and invalidating caches
Global barrier (line 4928)Global barrier passed.
CPU A switching to node 0 cached RAM
CPU A running cached
Nasids in partition: +0
Regions in partition: +0
Intializing any CPUless nodes.............. Global barrier (line 7714)Global barrier passed.
Global barrier (line 7715)Global barrier passed.
DONE
Global barrier (line 5089)Global barrier passed.
hubii_link_good: A-brick attached to module 001c01.
Checking partitioning information ......... DONE
No other nodes present; becoming partition master
*** After partitioning ***
ENTRY 0: HUB(54591bbe)
NASID=0 Mod=1 Flg=0x1500000 PROM=6.210 Route=N/A
MODULE=001c01 PARTITION=0 SPACE=RESET
Port 1 connection: Not connected
Port status: FE
Erecting partition fences ................ DONE
Update config for routers connected to hubs
Update config for hubs and hubless routers
CPU A flushing cache
check_router_cfg: nasid 0 is_voyager 0 check_cfg = 0
Global barrier (line 5300)Global barrier passed.
Nasids in partition: +0
Regions in partition: +0

A 000: *** Entering POD mode on node 0
A 000: POD IOC3 Cac>

[jwhat]

Hi Megaimg,

1. Are you using more recent IRIX version ?
2. What is the L1 version ?
3. What is the system board version (part no) ?
4. What is the processor version / model ?

Assuming all these are ok for the version L1 / IRIX you are using then then you could try to do log clear via POD/CAC:
- in POD/CAC ..
- Clear the logs: "clearalllogs"
- Reinitalise logs: "initalllogs"
- flush the buffers - "flush"
- Now back to L1 and reset debug to 0: "debug 0"
- Returning to console (POD/CAC), do a reset: "reset".

If you have a L1 / HW incompatibility issue the only way to address this is wind the HW version back, up the L1 to new version then go back to newer HW...
With Fuel I think the only way this could happen is your PIMM module not valid for L1 version, this would be very hard to deal with as to go back to slower CPU without first updating PROM (via booted machine) is currently no possible...

Lets hope it is simple IRIX compatabability issue.

See here for my notes on this stuff, which is mostly O350 with a smattering of Fuel...

Cheers from Oz,

jwhat/John

[megaimg]

Hi Megaimg,

1. Are you using more recent IRIX version ?
2. What is the L1 version ?
3. What is the system board version (part no) ?
4. What is the processor version / model ?

Assuming all these are ok for the version L1 / IRIX you are using then then you could try to do log clear via POD/CAC:
- in POD/CAC ..
- Clear the logs: "clearalllogs"
- Reinitalise logs: "initalllogs"
- flush the buffers - "flush"
- Now back to L1 and reset debug to 0: "debug 0"
- Returning to console (POD/CAC), do a reset: "reset".

If you have a L1 / HW incompatibility issue the only way to address this is wind the HW version back, up the L1 to new version then go back to newer HW...
With Fuel I think the only way this could happen is your PIMM module not valid for L1 version, this would be very hard to deal with as to go back to slower CPU without first updating PROM (via booted machine) is currently no possible...

Lets hope it is simple IRIX compatabability issue.

See here for my notes on this stuff, which is mostly O350 with a smattering of Fuel...

Cheers from Oz,

jwhat/John

L1 1.26.5 (Image B), Built 12/15/2003 12:57:41    [Fuel/PE 1MB image]
IP35 PROM SGI Version 6.210  built 02:33:51 PM Aug 26, 2004
Irix that I try 6.5, 6.5.17, 6.5.30
Motherboard Part# 030-1707-004 Rev c
CPU Part# 030-1730-002 Rev E
After doing your command and can switch on the L1 Module to console perfectly so that fix something, before I had one serial to the com1 and other in the motherboard.

Thanks...

[jwhat]

Hi Megaimg,

so did the reset fix the TBL Exception issue ?

On HW using info from SGI Depot:

System Board is: Mid Life Fuel
CPU is pretty regular: 600 MHz

So nothing special there...

BTW, I also had a lot of issues with Fuel and Serial comms, which I also documented in notes (Part I),

The Fuel Serial should be what is printed on Label on case, which corresponds to the MAC address on ef0 Ethernet port, unless yours system board was swapped at some point and the ID chip was not...

Note: Fuels should not have serial set via L1, as they take on the id via the EEPROM chip.

Cheers from Oz,

jwhat/John.

[megaimg]

Hi Megaimg,

so did the reset fix the TBL Exception issue ?

On HW using info from SGI Depot:

System Board is: Mid Life Fuel
CPU is pretty regular: 600 MHz

So nothing special there...

BTW, I also had a lot of issues with Fuel and Serial comms, which I also documented in notes (Part I),

The Fuel Serial should be what is printed on Label on case, which corresponds to the MAC address on ef0 Ethernet port, unless yours system board was swapped at some point and the ID chip was not...

Note: Fuels should not have serial set via L1, as they take on the id via the EEPROM chip.

Cheers from Oz,

jwhat/John.

Thanks sir, I will verify , try to access your notes, I cant...can you verify the link...

[jwhat]

Hi Megaimg,

yes link is correct, but to quote Raion, my link is "as slow as dog sh#t" ;-)

did you do (via POD/CAC) ? :
- Clear the logs: "clearalllogs"
- Reinitalise logs: "initalllogs"
- flush the buffers - "flush"
- Now back to L1 and reset debug to 0: "debug 0"
- Returning to console (POD/CAC), do a reset: "reset".

If you can boot machine into Command mode, then I would run the "update" from there ...

Also your L1 version is pretty old, so if you can get boot going I would update L1 (via "flashsc"), read the L1 & L2 docs, as there are two sets of L1 SW and you will need to set the right default to pickup the newer version and do an L1 reboot)

After that if you still get TBL Exception, and you are already using IRIX 6.5.30 then I am out of suggestions for now...

Cheers from Oz,

jwhat/John

[megaimg]

Hi Megaimg,

yes link is correct, but to quote Raion, my link is "as slow as dog sh#t" ;-)

did you do (via POD/CAC) ? :
- Clear the logs: "clearalllogs"
- Reinitalise logs: "initalllogs"
- flush the buffers - "flush"
- Now back to L1 and reset debug to 0: "debug 0"
- Returning to console (POD/CAC), do a reset: "reset".

If you can boot machine into Command mode, then I would run the "update" from there ...

Also your L1 version is pretty old, so if you can get boot going I would update L1 (via "flashsc"), read the L1 & L2 docs, as there are two sets of L1 SW and you will need to set the right default to pickup the newer version and do an L1 reboot)

After that if you still get TBL Exception, and  you are already using IRIX 6.5.30 then I am out of suggestions for now...

Cheers from Oz,

jwhat/John

Thanks sir again, I am a little new on SGI, so sorry about my ignorance, but where I can find the new firmware for the L1/L2....On the Irix CD?