Memory on SD16K

[Prashant Zanwar_4]

Error
CAB/CELL DIMM Error Address Error Type Page Count
------------- ----------------- ---------- --------- -----
0/0 0B 0x000000064a568d00 Single-Bit 0x064a568 67
0/0 0D 0x00000004b1d79500 Single-Bit 0x04b1d79 9
0/1 0B 0x000000058a177d40 Single-Bit 0x058a177 4
0/1 0B 0x00000003b3368240 Single-Bit 0x03b3368 9


I am able to track these memory errors on my
9000/800/S16K-A
...How do I interprit...I already have system memory utilisation shouts...

and also please suggest if I have space to add more memory..

CPU Memory Use
OK/ (GB) Core On
Hardware Actual Deconf/ OK/ Cell Next Par
Location Usage Max Deconf Connected To Capable Boot Num
========== ============ ======= ========= =================== ======= ==== ===
cab0,cell0 active core 4/0/4 16.0/ 0.0 cab0,bay0,chassis0 yes yes 0
cab0,cell1 active base 4/0/4 16.0/ 0.0 cab0,bay0,chassis1 yes yes 0
cab0,cell2 active base 4/0/4 12.0/ 0.0 - no yes 0
cab0,cell3 active base 4/0/4 12.0/ 0.0 - no yes 0


Thanks and regards
Prashant

[Prashant Zanwar_4]

Hey guys pls reply as I need to act fast on the issue..
Thx
Prashant

[Dave Hutton]

Do you have cstm on your server? You can check to see your dimm configuration with that.
Log creation time: Thu Jan 20 16:00:26 2005

Hardware path: 2/5


Basic Memory Description

Module Type: MEMORY
Total Configured Memory : 32768 MB
Page Size: 4096 Bytes

Memory interleaving is supported on this machine and is ON.

Memory Board Inventory

CAB/CELL: 0/0

DIMM A DIMM B
Slot Size (MB) Size (MB)
---- --------- ---------
0 1024 1024
1 1024 1024
2 1024 1024
3 1024 1024
4 1024 1024
5 1024 1024
6 1024 1024
7 1024 1024

Cell Total (MB): 16384
-------------------------------------------------

CAB/CELL: 0/2

DIMM A DIMM B
Slot Size (MB) Size (MB)
---- --------- ---------
0 1024 1024
1 1024 1024
2 1024 1024
3 1024 1024
4 1024 1024
5 1024 1024
6 1024 1024
7 1024 1024

Cell Total (MB): 16384
-------------------------------------------------

System Total (MB): 32768

Memory Error Log Summary

Error
CAB/CELL DIMM Error Address Error Type Page Count
------------- ----------------- ---------- --------- -----
0/0 1a 0x0000000508ed6100 Single-Bit 0x0508ed6 1


It will also indicate which dimms are giving errors. Like I guess our server has one right now.

[Dave Hutton]

I meant to add if you have cstm you just launch it.
#cstm
cstm> map
cstm> sel dev (whatever the device number is of your memory)
cstm> info
cstm> infolog

[Prashant Zanwar_4]

yes above one are captured from CSTM output and also CSTM shows free slots in cell 3 & 4..How much can be total memory in SD16K, We have 54G I believe right now..
Thx
Prashant

[Jeff Schussele]

Hmmmm...an rp8400 reports as an SD16K-A whereas an SD16 will report as an SD16000.
Are you sure of just which system you're dealing with here?
Either way you have memory errors on
Cab 0 Cell 0 DIMMS 11 & 13
Cab 0 Cell 1 DIMM 11
and they need to be reported, but nevertheless the pages have been de-allocated.
You should check the PDT (Page Deallocation Table) from the BCH prompy at your earliest opportunity - you'll need a reboot of course. Because sometimes HP won't replace the DIMM until there are a significant amount of de-allocations on A specific DIMM.

Rgds,
Jeff