Re: [Machinekit] Decent latency results on a cheap old computer

[schoone...@btinternet.com]

Hi Yes there is plenty of old hardware out there that works well and at a fraction of the cost of even a BBB, let alone the cape etc. I am still using a single core P4 in my workshop that returns a rock sold 9K max jitter on base thread, using a home brew rtai kernel. Those are good figures for xenomai though, they are usually considerably worse. You may find that running the test with a base thread improves the servo thread figure considerably, by keeping the rt code on one cache. Would be interesting to compare to the figure for just the servo thread. This can be so marked, that on another machine which has a much newer dual core processor, I run a 'dummy' base thread to keep one processor busy, which considerably improves the servo max jitter ( from 100K down to 25K) Very similar to the machine in this discussion https://github.com/machinekit/machinekit/issues/792#issuecomment-233187822 regards On 06/01/17 14:20, Fernando Correa Neto wrote: Hey there Just wanted to share some findings after combining all sorts of "good practices" for getting a decent MachineKit setup. The machine is dated and uses a CPU than can be bought for less than a dollar I think. The TL;DR is: Servo thread at 15052 Base thread at 12569 Details: OS: Debian Jessie with a Xenomai kernel upgraded from a LinuxCNC Wheezy system Hardware: Dell Optiplex 745 Bios: Almost everything turned off except USB, parallel port, ethernet and CPU thermal protection Hardware details: cnc@TC3020:~$ lspci 00:00.0 Host bridge: Intel Corporation 82Q963/Q965 Memory Controller Hub (rev 02) 00:02.0 VGA compatible controller: Intel Corporation 82Q963/Q965 Integrated Graphics Controller (rev 02) 00:02.1 Display controller: Intel Corporation 82Q963/Q965 Integrated Graphics Controller (rev 02) 00:1a.0 USB controller: Intel Corporation 82801H (ICH8 Family) USB UHCI Controller #4 (rev 02) 00:1a.1 USB controller: Intel Corporation 82801H (ICH8 Family) USB UHCI Controller #5 (rev 02) 00:1a.7 USB controller: Intel Corporation 82801H (ICH8 Family) USB2 EHCI Controller #2 (rev 02) 00:1c.0 PCI bridge: Intel Corporation 82801H (ICH8 Family) PCI Express Port 1 (rev 02) 00:1c.4 PCI bridge: Intel Corporation 82801H (ICH8 Family) PCI Express Port 5 (rev 02) 00:1d.0 USB controller: Intel Corporation 82801H (ICH8 Family) USB UHCI Controller #1 (rev 02) 00:1d.1 USB controller: Intel Corporation 82801H (ICH8 Family) USB UHCI Controller #2 (rev 02) 00:1d.2 USB controller: Intel Corporation 82801H (ICH8 Family) USB UHCI Controller #3 (rev 02) 00:1d.7 USB controller: Intel Corporation 82801H (ICH8 Family) USB2 EHCI Controller #1 (rev 02) 00:1e.0 PCI bridge: Intel Corporation 82801 PCI Bridge (rev f2) 00:1f.0 ISA bridge: Intel Corporation 82801HB/HR (ICH8/R) LPC Interface Controller (rev 02 < /span>) 00:1f.2 IDE interface: Intel Corporation 82801H (ICH8 Family) 4 port SATA Controller [IDE mode] (rev 02) 00:1f.3 SMBus: Intel Corporation 82801H (ICH8 Family) SMBus Controller (rev 02) 00:1f.5 IDE interface: Intel Corporation 82801HR/HO/HH (ICH8R/DO/DH) 2 port SATA Controller [IDE mode] (rev 02) 02:00.0 Ethernet controller: Broadcom Corporation NetXtreme BCM5754 Gigabit Ethernet PCI Express (rev 02) cnc@TC3020:~$ 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: 15 Model name: Intel(R) Pentium(R) Dual CPU E2200 @ 2.20GHz Stepping: 13 CPU MHz: 2192.790 BogoMIPS: 4385.58 L1d cache: 32K L1i cache: 32K L2 cache: 1024K Grub details: cnc@TC3020:~$ dmesg | grep command [ 0.000000] Kernel command line: BOOT_IMAGE=/boot/vmlinuz-3.8-1-xenomai.x86-686-pae root = UUID=63401999-b871-430d-9566-de89b087ffef ro initrd=/install/initrd.gz quiet rootdelay=5 xeno_hal.smi=1 lapic=notscdeadline hpet=disable i915.i915_enable_rc6=0 i915.powersave=0 intel_idle.max_cstate=1 pro c essor.max_cstate=1 isolcpus=1 idle=poll acpi_irq_nobalance noirqbalance cnc@TC3020:~$ cat /proc/interrupts CPU0 CPU1 0: 72 0 IO-APIC-edge timer 1: 3 0 IO-APIC-edge i8042 7: 0 0 IO-APIC-edge parport0 8: 0 0 IO-APIC-edge rtc0 9: 0 0 IO-APIC-fasteoi acpi 12: 4 0 IO-APIC-edge i8042 16: 100272 0 IO-APIC-fasteoi uhci_hcd:usb3, i915, eth0 17: 56226 0 IO-APIC-fasteoi uhci_hcd:usb4, uhci_hcd:usb6 18: 0 0 IO-APIC-fasteoi uhci_hcd:usb7 20: 28260 0 IO-APIC-fasteoi ata_piix, ata_piix, i801_smbus 22: 3 0 IO-APIC-fasteoi ehci_hcd:usb1 23: 0 0 IO-APIC-fasteoi ehci_hcd:usb2, uhci_hcd:usb5 NMI: 2861 2861 Non-maskable interrupts LOC: 1377714 350753 Local timer interrupts SPU: 0 0 Spurious interrupts PMI: 2861 2861 Performance monitoring interrupts IWI: 0 0 IRQ work interrupts RTR: 0 0 APIC ICR read retries RES: 2 2 Rescheduling interrupts CAL: 0 347 Function call interrupts TLB: 0 1 TLB shootdowns TRM: 0 0 Thermal event interrupts THR: 0 0 Threshold APIC interrupts MCE: 0 0 Machine check exceptions MCP: 9 9 Machine check polls ERR: 0 MIS: 0 For the "stress test" itself, I ran 5 glxgears and played repeatedly a video stream and the latency was not affected at all after 30 minutes. Here's the evidence: http://i.imgur.com/OnYcAXn.png That system is driving a 3.2x2.1m CNC router through the parallel port with the gantry component (adapted from the Probotix BBB one) for auto-squaring, debouncers for the limit switches, sindle control using PDM (worked best for us). Steppers are set to 1/16 and I can get rapids as high as 7.2m/min though the machine will fall apart since the ballscrews will start jumping up and down so we're keeping it at 4m/min which is great. Later today we're going to upgrade the CPU for a Core 2 Duo quad and we may have different figures. We'll see. Anyways, I'm pretty happy with this. Ask me anything about OS or hardware and I'll be happy to share. -Fernando -- website: http://www.machinekit.io blog: http://blog.machinekit.io github: https://github.com/machinekit --- You received this message because you are subscribed to the Google Groups "Machinekit" group. To unsubscribe from this group and stop receiving emails from it, send an email to machinekit+unsubscr...@googlegroups.com. Visit this group at https://groups.google.com/group/machinekit. For more options, visit https://groups.google.com/d/optout. -- website: http://www.machinekit.io blog: http://blog.machinekit.io github: https://github.com/machinekit --- You received this message because you are subscribed to the Google Groups "Machinekit" group. To unsubscribe from this group and stop receiving emails from it, send an email to machinekit+unsubscr...@googlegroups.com. Visit this group at https://groups.google.com/group/machinekit. For more options, visit https://groups.google.com/d/optout.