Fuzzy0101

Does this happen only during boot? Can you post the full log when you modify something in the plugin's GUI and apply the changes? What type of network card/chip is in your system?

All of the features of the GUI is available in the script used by the GUI. "Power profile" setting on GUI uses these two functions: /usr/local/emhttp/plugins/autotweak/scripts/autotweak set_scaling_governor /usr/local/emhttp/plugins/autotweak/scripts/autotweak set_cpu_performance_preference If you execute them they give you a little help about the possible parameters. You can set powersave "Power profile" like this: /usr/local/emhttp/plugins/autotweak/scripts/autotweak set_scaling_governor "powersave" /usr/local/emhttp/plugins/autotweak/scripts/autotweak set_cpu_performance_preference "balance_power" And you can set performance "Power profile" like this: /usr/local/emhttp/plugins/autotweak/scripts/autotweak set_scaling_governor "performance" /usr/local/emhttp/plugins/autotweak/scripts/autotweak set_cpu_performance_preference "performance" And you can set balanced "Power profile" like this: /usr/local/emhttp/plugins/autotweak/scripts/autotweak set_scaling_governor "powersave" /usr/local/emhttp/plugins/autotweak/scripts/autotweak set_cpu_performance_preference "balance_performance" These log their output into /var/log/syslog. Just be aware that these functions do not modify permanently these parameters (not saved in the config). So if you open the GUI you will see that last set "Power profile". And if you modify any parameter the GUI will reapply that "Power profile".

Yes, it would conflict. The plugin configures same power management parameters as powertop does and many other stuff. The only deliberate difference is that this plugin avoids enabling autosuspend for USB devices. You can verify this after restarting your system before running powertop --auto-tune command. Just start powertop and check the Tunables tab on the gui.

I would say no. They try to configure some of the same stuff.

I fixed it in 1.3.13. It was just a harmless bug. I forgot to comment out the debug logging.

I fixed it in 1.3.13. It was just a harmless bug. I forgot to comment out the debug logging.

Yes. Probably buggy firmware. It turns out you can disable L1.1 and L1.2 per device. If the pci address of the NVME is 01:00.0, you can disable L1.2 like this: echo 0 > /sys/bus/pci/devices/0000\:01\:00.0/link/l1_2_aspm There are other switches in that directory to turn off other pm features: l1_1_pcipm l1_2_aspm l1_2_pcipm l1_aspm

I uploaded the new version 1.3.11 Adds NVME SSD power management policy feature. Improves GUI field descriptions and consistency.

Yes but also makes it probably very warm. I don't know how much you played with it to make it work, but may be you can try to disable only APST PS states deeper than PS3. You can see the exlat parameters of PS3 and PS4 at the end of nvme id-ctrl /dev/nvme0 If you set nvme_core.default_ps_max_latency_us between the two value you can disable only PS4 You can check the current PS state with: nvme get-feature -f 2 -H /dev/nvme0

You can try the kernel I compiled; it works with Unraid and is based on version 6.6.23. I also tried to include AMD support. https://github.com/fuzzy01/unraid_enhanced_kernel/releases/tag/6.6.23-u6.12.10

I uploaded the new version 1.3.9 New optimization features. Add support SATA PM and Link PM control. Add support for disabling NMI watchdog. Many minor updates.

In the next release I changed it to schedutil in balanced profile on cpus that don't have pstate driver. Otherwise it uses powersave. I don't have a system with AMD CPU to test it. But I have a 6.6.22 kernel compiled myself... ASPM is tuned through a global kernel parameter not per device. Did you try to update the firmware of your NVMe? I updated my WD NVMe with nvme-cli.

For detailed information about any setting within the plugin, you can always use the question mark icon to reveal the documentation. Additionally the plugin provides detailed logging of its operations within the system log.

I'd like to provide some clarity on the two features currently not visible in the GUI: - Modern NICs support hardware queues, which can improve network traffic processing by distributing it across multiple CPUs. The plugin is designed to optimize this by assigning different hardware queues (and their corresponding interrupts) to various CPUs. Additionally, for systems with hybrid CPUs, the plugin aims to allocate these to E-cores. The plugin also enables the Transmit Packet Steering (XPS) feature in the kernel to further enhance network performance. - The other feature sets some TCP buffer size parameters based on the maximum physical interface speed detected in the system. For detailed information about any setting within the plugin, you can always use the question mark icon to reveal the documentation. Additionally the plugin provides detailed logging of its operations within the system log.

Just created a support thread ...

Yes.

Unraid plugin that enables you to adjust your Unraid system's power profile to enhance performance or improve energy efficiency. Additionally, it fine-tunes the TCP stack settings and network interface card (NIC) interrupt affinities to optimize network performance. Please note: This plugin is not compatible with other plugins that alter the same settings.

Do you have a list what was set by "powertop ---auto-tune"?

Try this echo "powersupersave" > /sys/module/pcie_aspm/parameters/policy

See my post https://forums.unraid.net/topic/141349-plugin-realtek-r8125-r8168-and-r81526-drivers/?do=findComment&comment=1379870

There are many unexplained stories about Realtek cards and ASPM ... so I made a little investigation: The kernel in-tree r8169 driver is a generic driver for all Realtek network cards, despite its name. It contains lots of workaround for different Realtek chipset. It also has a very strict condition for using ASPM (this condition was removed for a few weeks last year then reverted back...). It enables ASPM only for RTL8125A and RTL8125B chipset and only if a bit in a register is set in the chip by the system vendor, which signals to the driver that vendor successfully tested ASPM 1.2 on this configuration. (Probably not many motherboard vendor bothers to do this ...). If this condition not met it tries to disable ASPM, if it is denied by BIOS then it uses ASPM whatever the chipset is ... This behaviour cannot be overridden. That basically means low chance for having ASPM with the in-tree driver. I also checked the r8125 driver (from Realtek) used by this plugin. It contains CONFIG_ASPM = n in the Makefile but this just sets the default value of ASPM, it is not a real compile time option. After installing this plugin you can easily enable ASMP if you create a file r8125.conf in /boot/config/modprobe.d with the following line: options r8125 aspm=1 It enables ASPM the correct way. With this my server reaches C10 package state... @jinlife please try to enable firmware load support with ENABLE_USE_FIRMWARE_FILE = y. The firmware files are already in /lib/firmware/rtl_nic/ as the in-tree driver uses them. Probably most of these cards are shipped with outdated firmware, so enabling this option would help. Correction: The r8125 source code contains the firmware file in binary form. No need to enable ENABLE_USE_FIRMWARE_FILE. The speed issues can be caused by EEE (Energy Efficient Ethernet) which is enabled by default by this driver. You can check the status with ethtool --show-eee eth0 Or disable it with an extra line in r8125.conf options r8125 eee=0