Before I throw this computer in the garbage....
Before I just move on and put together a new controller computer based on hardware that is known to work, I'm wondering if anyone else has gotten such atrocious performance and are there any low hanging fruit I might have overlooked?
Hardware: Dell Optiplex 755, I5 4 core 2.4Ghz, 2GB ram, 500GB HDD (80GB for linux, dual boot with windows vista) Asus HD 5450 Silent graphics card (added to see in onboard graphics was causing the problem.)
Screenshots attached.
Thanks!
Please Log in or Create an account to join the conversation.
AFAIK a Dell Optiplex 755 is a Core Duo (socket 775) machine
Please Log in or Create an account to join the conversation.
Edit: BIOS confirms it's a Intel Core2 Quad CPU Q6600 @ 2.40GHz, so I guess it's not an I5.
sun@debian:/proc$ lscpu
Architecture: i686
CPU op-mode(s): 32-bit, 64-bit
Byte Order: Little Endian
CPU(s): 4
On-line CPU(s) list: 0-3
Thread(s) per core: 1
Core(s) per socket: 4
Socket(s): 1
Vendor ID: GenuineIntel
CPU family: 6
Model: 15
Stepping: 11
CPU MHz: 2393.999
BogoMIPS: 4787.99
Virtualization: VT-x
L1d cache: 32K
L1i cache: 32K
L2 cache: 4096K
sun@debian:/proc$ dmesg
[ 0.000000] Initializing cgroup subsys cpuset
[ 0.000000] Initializing cgroup subsys cpu
[ 0.000000] Linux version 3.4-9-rtai-686-pae (Debian 3.4.55-4linuxcnc) () (gcc version 4.6.3 (Debian 4.6.3-14) ) #1 SMP PREEMPT Debian 3.4.55-4linuxcnc
[ 0.000000] BIOS-provided physical RAM map:
[ 0.000000] BIOS-e820: 0000000000000000 - 000000000009ec00 (usable)
[ 0.000000] BIOS-e820: 00000000000f0000 - 0000000000100000 (reserved)
[ 0.000000] BIOS-e820: 0000000000100000 - 000000007ddff800 (usable)
[ 0.000000] BIOS-e820: 000000007ddff800 - 000000007de53c00 (ACPI NVS)
[ 0.000000] BIOS-e820: 000000007de53c00 - 000000007de55c00 (ACPI data)
[ 0.000000] BIOS-e820: 000000007de55c00 - 000000007e000000 (reserved)
[ 0.000000] BIOS-e820: 00000000e0000000 - 00000000fed00400 (reserved)
[ 0.000000] BIOS-e820: 00000000fed20000 - 00000000feda0000 (reserved)
[ 0.000000] BIOS-e820: 00000000fee00000 - 00000000fef00000 (reserved)
[ 0.000000] BIOS-e820: 00000000ffb00000 - 0000000100000000 (reserved)
[ 0.000000] Notice: NX (Execute Disable) protection missing in CPU!
[ 0.000000] SMBIOS 2.5 present.
[ 0.000000] DMI: Dell Inc. OptiPlex 755 /0PU052, BIOS A04 11/05/2007
...rest omitted.
Please Log in or Create an account to join the conversation.
- kornphlake79
- Offline
- Senior Member
- Posts: 55
- Thank you received: 10
linuxCNC:~$ lscpu
Architecture: i686
CPU op-mode(s): 32-bit, 64-bit
Byte Order: Little Endian
CPU(s): 2
On-line CPU(s) list: 0,1
Thread(s) per core: 1
Core(s) per socket: 2
Socket(s): 1
Vendor ID: GenuineIntel
CPU family: 6
Model: 23
Stepping: 6
CPU MHz: 2526.822
BogoMIPS: 5053.64
L1d cache: 32K
L1i cache: 32K
L2 cache: 3072K
Unless a few mhz makes that much difference vs a couple cores. It sounds like you've done your due diligence to fix the problem, I'd say there's something wrong with the hardware and it might not be worth saving the computer at this point. Have you tried booting from the live cd and running the latency test?
Please Log in or Create an account to join the conversation.
are there any low hanging fruit I might have overlooked?
I was wondering about SMI, but your plot seems to show a constant high latency, rather than the regular spike caused by SMI.
Please Log in or Create an account to join the conversation.
At this point I'm back to mach3 until I can assemble a linuxcnc friendly controller and take the time to configure it (my spindle is step based )
But thanks for the suggestions!
Please Log in or Create an account to join the conversation.
I have not tried the SMI mod, mostly because as you note the latency is constant rather than periodic, and the mod seems to involve compiling kernals and such
The smi module is supplied pre-compiled with LinuxCNC nowadays, you just need to edit rtapi.conf (as described on the Wiki).
I doubt it will help, but you might as well give it a go.
Please Log in or Create an account to join the conversation.
Please Log in or Create an account to join the conversation.
- Todd Zuercher
- Offline
- Platinum Member
- Posts: 5007
- Thank you received: 1441
Please Log in or Create an account to join the conversation.
OK Thanks! I'll try that. I guess my eyes glazed over when I hit the part about compiling the kernal (presumably for an earlier version) and I stopped there.
The smi fix is not something you can just try.
Read this and if your chipset matches you can apply it
www.linuxcnc.org/index.php/english/forum...me-latency-solutions
Please Log in or Create an account to join the conversation.