NCM

Add me to the list of people with this issue. Unraid 7.x (also present in 6.x), 265K (also present on 9700K, Xeon W-2135, but not a dual socket E5-2630L V4, although the latter could potentially be considered "before the issue" chronologically).I'm running 2 Frigate containers as primary server purpose, although issue persists with a single Frigate instance. About once every 30-45 days CPU usage will max out and make the Unraid interface unreachable but leave Frigate accessible (on prior hardware server would entirely hard lock). If I restart Frigate through the Frigate interface I can quickly hop on to Unraid and see the load average in HTOP up to 80... The tricky part is that the issue resolves temporarily if I restart either Frigate container, certainly no clear indication of what the root cause is. I managed to snag this from HTOP at some intermittent point that I could still reach the server. [Main] [I/O] PID USER PRI NI VIRT RES SHR S CPU%▽MEM% TIME+ Command 17890 root 20 0 8121M 190M 0 R 44.6 0.6 0:00.70 /usr/bin/dockerd -p /var/run/dockerd.pid --log-opt max-size=50m --log-opt max-file=1 --log-level=fatal --storage-driver=btrfs 1525810 root 20 0 8121M 190M 0 S 41.3 0.6 2h10:41 /usr/bin/dockerd -p /var/run/dockerd.pid --log-opt max-size=50m --log-opt max-file=1 --log-level=fatal --storage-driver=btrfs 17863 root 20 0 8121M 190M 0 R 40.6 0.6 0:00.70 /usr/bin/dockerd -p /var/run/dockerd.pid --log-opt max-size=50m --log-opt max-file=1 --log-level=fatal --storage-driver=btrfs 18931 root 20 0 8121M 190M 0 S 40.0 0.6 34:43.03 /usr/bin/dockerd -p /var/run/dockerd.pid --log-opt max-size=50m --log-opt max-file=1 --log-level=fatal --storage-driver=btrfs 3339829 root 20 0 8121M 190M 0 S 39.3 0.6 53:03.99 /usr/bin/dockerd -p /var/run/dockerd.pid --log-opt max-size=50m --log-opt max-file=1 --log-level=fatal --storage-driver=btrfs 236458 root 20 0 8121M 190M 0 S 37.4 0.6 0:22.28 /usr/bin/dockerd -p /var/run/dockerd.pid --log-opt max-size=50m --log-opt max-file=1 --log-level=fatal --storage-driver=btrfs 2841797 root 20 0 8121M 190M 0 R 37.4 0.6 1:49.11 /usr/bin/dockerd -p /var/run/dockerd.pid --log-opt max-size=50m --log-opt max-file=1 --log-level=fatal --storage-driver=btrfs 17889 root 20 0 8121M 190M 0 R 36.7 0.6 0:00.63 /usr/bin/dockerd -p /var/run/dockerd.pid --log-opt max-size=50m --log-opt max-file=1 --log-level=fatal --storage-driver=btrfs 937490 root 20 0 8121M 190M 0 R 36.7 0.6 0:02.29 /usr/bin/dockerd -p /var/run/dockerd.pid --log-opt max-size=50m --log-opt max-file=1 --log-level=fatal --storage-driver=btrfs 1303784 root 20 0 8121M 190M 0 R 36.0 0.6 0:40.90 /usr/bin/dockerd -p /var/run/dockerd.pid --log-opt max-size=50m --log-opt max-file=1 --log-level=fatal --storage-driver=btrfs 1007996 root 20 0 8121M 190M 0 R 35.4 0.6 0:19.77 /usr/bin/dockerd -p /var/run/dockerd.pid --log-opt max-size=50m --log-opt max-file=1 --log-level=fatal --storage-driver=btrfs 810052 root 20 0 8121M 190M 0 R 33.4 0.6 0:29.51 /usr/bin/dockerd -p /var/run/dockerd.pid --log-opt max-size=50m --log-opt max-file=1 --log-level=fatal --storage-driver=btrfs 3339841 root 20 0 8121M 190M 0 R 33.4 0.6 19:28.91 /usr/bin/dockerd -p /var/run/dockerd.pid --log-opt max-size=50m --log-opt max-file=1 --log-level=fatal --storage-driver=btrfs 3438731 root 20 0 8121M 190M 0 S 33.4 0.6 0:01.98 /usr/bin/dockerd -p /var/run/dockerd.pid --log-opt max-size=50m --log-opt max-file=1 --log-level=fatal --storage-driver=btrfs 1301962 root 20 0 8121M 190M 0 R 32.8 0.6 0:21.12 /usr/bin/dockerd -p /var/run/dockerd.pid --log-opt max-size=50m --log-opt max-file=1 --log-level=fatal --storage-driver=btrfs 1091186 root 20 0 8121M 190M 0 S 31.5 0.6 0:04.41 /usr/bin/dockerd -p /var/run/dockerd.pid --log-opt max-size=50m --log-opt max-file=1 --log-level=fatal --storage-driver=btrfs 3438732 root 20 0 8121M 190M 0 R 31.5 0.6 0:01.98 /usr/bin/dockerd -p /var/run/dockerd.pid --log-opt max-size=50m --log-opt max-file=1 --log-level=fatal --storage-driver=btrfs 1304886 root 20 0 8121M 190M 0 R 30.8 0.6 0:25.29 /usr/bin/dockerd -p /var/run/dockerd.pid --log-opt max-size=50m --log-opt max-file=1 --log-level=fatal --storage-driver=btrfs 629642 root 20 0 8121M 190M 0 S 30.1 0.6 0:19.65 /usr/bin/dockerd -p /var/run/dockerd.pid --log-opt max-size=50m --log-opt max-file=1 --log-level=fatal --storage-driver=btrfs 1093325 root 20 0 8121M 190M 0 S 29.5 0.6 0:04.62 /usr/bin/dockerd -p /var/run/dockerd.pid --log-opt max-size=50m --log-opt max-file=1 --log-level=fatal --storage-driver=btrfs 3748482 root 20 0 8121M 190M 0 S 29.5 0.6 0:09.48 /usr/bin/dockerd -p /var/run/dockerd.pid --log-opt max-size=50m --log-opt max-file=1 --log-level=fatal --storage-driver=btrfs 1526366 root 20 0 8121M 190M 0 S 28.8 0.6 0:01.46 /usr/bin/dockerd -p /var/run/dockerd.pid --log-opt max-size=50m --log-opt max-file=1 --log-level=fatal --storage-driver=btrfs 236803 root 20 0 8121M 190M 0 R 27.5 0.6 0:31.44 /usr/bin/dockerd -p /var/run/dockerd.pid --log-opt max-size=50m --log-opt max-file=1 --log-level=fatal --storage-driver=btrfs 1093315 root 20 0 8121M 190M 0 R 27.5 0.6 0:25.44 /usr/bin/dockerd -p /var/run/dockerd.pid --log-opt max-size=50m --log-opt max-file=1 --log-level=fatal --storage-driver=btrfs 1304121 root 20 0 8121M 190M 0 S 26.2 0.6 0:43.02 /usr/bin/dockerd -p /var/run/dockerd.pid --log-opt max-size=50m --log-opt max-file=1 --log-level=fatal --storage-driver=btrfs 17862 root 20 0 8121M 190M 0 S 25.6 0.6 0:00.52 /usr/bin/dockerd -p /var/run/dockerd.pid --log-opt max-size=50m --log-opt max-file=1 --log-level=fatal --storage-driver=btrfs 17755 root 20 0 8121M 190M 0 S 24.2 0.6 0:00.45 /usr/bin/dockerd -p /var/run/dockerd.pid --log-opt max-size=50m --log-opt max-file=1 --log-level=fatal --storage-driver=btrfs 432192 root 20 0 8121M 190M 0 R 19.0 0.6 0:31.71 /usr/bin/dockerd -p /var/run/dockerd.pid --log-opt max-size=50m --log-opt max-file=1 --log-level=fatal --storage-driver=btrfs 16135 root 20 0 8121M 190M 0 R 14.4 0.6 0:00.30 /usr/bin/dockerd -p /var/run/dockerd.pid --log-opt max-size=50m --log-opt max-file=1 --log-level=fatal --storage-driver=btrfs 2380 root 20 0 83544 8052 4924 S 11.1 0.0 2h18:55 /usr/sbin/winbindd -D 119608 root 20 0 1242M 30536 0 S 8.5 0.1 1h33:27 containerd --config /var/run/docker/containerd/containerd.toml --log-level fatal 17464 root 20 0 1496M 25624 0 S 6.6 0.1 0:02.16 libvirtd -d -l -f /etc/libvirt/libvirtd.conf -p /var/run/libvirt/libvirtd.pid 13320 root 20 0 21.3G 182M 57884 S 4.6 0.6 4h09:54 node /usr/local/unraid-api/dist/main.js 17298 root 20 0 1496M 25624 4676 S 3.3 0.1 0:39.41 libvirtd -d -l -f /etc/libvirt/libvirtd.conf -p /var/run/libvirt/libvirtd.pid 19113 root 20 0 7336M 2178M 9728 S 3.3 6.9 2d02h48m /usr/bin/qemu-system-x86_64 -name guest=HomeAssistant,debug-threads=on -S -object {"qom-type":"secret","id":"masterKey0","format":"raw","file":"/var/lib/libvirt/qemu/domain-1-HomeAssistant/master-key.aes"} -blockdev {"driver":"file","filename":"/usr/share/qemu/ovmf-x64/OVMF_CODE-pure-efi.fd","node-name":"libvirt-pflash0-storage","auto-read-only":true,"discard":"unmap"} -blockdev {"node-name":"libvirt-pflash0 2382 root 20 0 83392 8972 5120 S 2.6 0.0 24:08.12 /usr/sbin/winbindd -D 3444529 root 20 0 13500 5552 4112 S 2.6 0.0 3:14.21 /usr/bin/ttyd -d0 -W -t rendererType canvas -t closeOnDisconnect true -t disableLeaveAlert true -t theme {'background':'black'} -t fontSize 15 -t fontFamily monospace -s9 -om1 -i /var/run/syslog.sock /usr/local/emhttp/webGui/scripts/run_cmd tail -f -n 90 /var/log/syslog 2359 root 20 0 88356 9496 6312 S 2.0 0.0 4:51.07 /usr/sbin/smbd -D 1173742 root 20 0 12280 9760 3200 R 2.0 0.0 0:28.25 htop 3357549 root 20 0 13500 5856 4416 S 2.0 0.0 11:30.54 /usr/bin/ttyd -d0 -W -t rendererType canvas -t closeOnDisconnect true -t disableLeaveAlert true -t theme {'background':'black'} -t fontSize 15 -t fontFamily monospace -s9 -om1 -i /var/tmp/Frigate-Test.log.sock /usr/local/emhttp/webGui/scripts/run_cmd docker logs -f -n 90 Frigate-Test 3633332 root 20 0 6196 4768 2924 S 2.0 0.0 28:06.30 /bin/bash /usr/local/emhttp/plugins/ca.mover.tuning/age_mover start 19217 root 20 0 7336M 2178M 0 R 1.3 6.9 8h11:23 /usr/bin/qemu-system-x86_64 -name guest=HomeAssistant,debug-threads=on -S -object {"qom-type":"secret","id":"masterKey0","format":"raw","file":"/var/lib/libvirt/qemu/domain-1-HomeAssistant/master-key.aes"} -blockdev {"driver":"file","filename":"/usr/share/qemu/ovmf-x64/OVMF_CODE-pure-efi.fd","node-name":"libvirt-pflash0-storage","auto-read-only":true,"discard":"unmap"} -blockdev {"node-name":"libvirt-pflash0

ca.mover.tuning-debug-20250603-1933.zip Hopefully that's helpful.

At least in my limited testing Rsync seemed ~50% faster than native move.

I'm using Frigate on unraid with constant recording. Due to how frigate reassembles clips this entails moving several hundred thousand 10 second segments that are ~2MB each. I removed parity from the pool to avoid the parity write penalty and I'm getting about 18-20MB/s write speed on Ultrastar HC530 disks using move. Rsync does a bit better at 25MB/s. Mover tuning settings are pretty standard, moved based on age with normal priority. This basically means it takes about 3 days to put 1TB on cache and about 12-16 hours to move it to disk lol. Obviously writing to cache just to move it is a bit silly but I like the low latency on M.2 and ability to spin down. Any suggestions on speeding this up further before I descend into normalcy and write directly to pool?

I got down to about 20-22W (still with I340 and RTL8125 disabled), not much gain and could be partially related to being completely stripped down vs probably still having Unraid web interface up etc. If I jumper my power supply it's a baseline 4.5W so potentially 10W or more of my 25W power from the wall could be power supply losses. I have a smaller and newer power supply in route that should be an improvement but realistically even though it is 80+ Gold 250W the 10% load efficiency is 76%. I suspect my normal load will be ~40-50W even if I get C10, which is 90% efficient on this PWS so overall this is satisfactory.

Unraid 7.1.1 Intel UItra 265K TUF GAMING B860M-PLUS WIFI (RTL8125) Pretty sure I've exhausted all combinations of relevant BIOS settings (native ASPM, C10, turbo off, etc) as well as disabling hardware features up to disabling the RTL8125 and swapping in an Intel I340-T2. This is a test install of Unraid so it has next to nothing going on or plugged in otherwise. powertop seems to be having issues representing states higher than C3, but tuneables are good. I did notice this is showing pkg(OS) while @12323r is getting pkg(HW) from 2.15 so not sure if I'm missing another aspect of Arrow Lake compatibility or some other factor. PowerTOP 2.15 Overview Idle stats Frequency stats Device stats Tunables WakeUp Pkg(OS) | CPU(OS) 0 Powered On 0.0% | POLL 0.0% 0.0 ms C1_ACPI 3.3% | C1_ACPI 0.8% 0.2 ms C2_ACPI 13.4% | C2_ACPI 23.1% 0.9 ms C3_ACPI 72.7% | C3_ACPI 71.0% 1.8 ms RC6pp 0.0% | In corefreq it does acknowledge that the core are going into higher C states (oddly P cores reaching higher states than E cores). --- Freq(MHz) Ratio - Turbo -- C0 ---- C1 -- C2:C3 - C4:C6 --- C7 -- Min TMP Max 000 3.31 ( 0.03) 0.09% 0.44% 0.25% 0.00% 1.23% 97.94% 32 / 32/ 36 001 3.50 ( 0.04) 0.09% 0.25% 0.10% 0.00% 1.68% 97.89% 32 / 34/ 36 ... 006 2.05 ( 0.02) 0.05% 0.12% 0.00% 0.00% 0.00% 99.84% 32 / 32/ 36 007 2.38 ( 0.02) 0.06% 0.17% 0.02% 0.00% 0.00% 99.77% 34 / 34/ 36 008 8.88 ( 0.09) 0.23% 1.11% 12.43% 0.00% 86.27% 0.00% 32 / 32/ 34 009 12.79 ( 0.13) 0.33% 1.60% 3.33% 0.00% 94.74% 0.00% 32 / 32/ 34 ... lspci looks good with all devices having ASPM L1 enabled. root@Tower:~# lspci -vv | awk '/ASPM/{print $0}' RS= | grep --color -P '(^[a-z0-9:.]+|ASPM )' 00:06.0 PCI bridge: Intel Corporation Device ae4d (rev 10) (prog-if 00 [Normal decode]) LnkCap: Port #13, Speed 32GT/s, Width x16, ASPM L1, Exit Latency L1 <64us LnkCtl: ASPM L1 Enabled; RCB 64 bytes, LnkDisable- CommClk- 80:1b.0 PCI bridge: Intel Corporation Device 7f44 (rev 10) (prog-if 00 [Normal decode]) LnkCap: Port #21, Speed 16GT/s, Width x4, ASPM L1, Exit Latency L1 <64us LnkCtl: ASPM L1 Enabled; RCB 64 bytes, LnkDisable- CommClk+ 80:1c.0 PCI bridge: Intel Corporation Device 7f38 (rev 10) (prog-if 00 [Normal decode]) LnkCap: Port #1, Speed 16GT/s, Width x4, ASPM L1, Exit Latency L1 <64us LnkCtl: ASPM L1 Enabled; RCB 64 bytes, LnkDisable- CommClk- 80:1c.4 PCI bridge: Intel Corporation Device 7f3c (rev 10) (prog-if 00 [Normal decode]) LnkCap: Port #5, Speed 16GT/s, Width x4, ASPM L1, Exit Latency L1 <64us LnkCtl: ASPM L1 Enabled; RCB 64 bytes, LnkDisable- CommClk+ 80:1d.0 PCI bridge: Intel Corporation Device 7f36 (rev 10) (prog-if 00 [Normal decode]) LnkCap: Port #15, Speed 16GT/s, Width x1, ASPM L1, Exit Latency L1 <64us LnkCtl: ASPM L1 Enabled; RCB 64 bytes, LnkDisable+ CommClk+ 80:1d.7 PCI bridge: Intel Corporation Device 7f37 (rev 10) (prog-if 00 [Normal decode]) LnkCap: Port #16, Speed 16GT/s, Width x1, ASPM L1, Exit Latency L1 <64us LnkCtl: ASPM L1 Enabled; RCB 64 bytes, LnkDisable+ CommClk+ 81:00.0 Non-Volatile memory controller: Micron/Crucial Technology P5 Plus NVMe PCIe SSD (prog-if 02 [NVM Express]) LnkCap: Port #0, Speed 16GT/s, Width x4, ASPM L1, Exit Latency L1 <8us LnkCtl: ASPM L1 Enabled; RCB 64 bytes, LnkDisable- CommClk+ 83:00.0 Ethernet controller: Intel Corporation 82580 Gigabit Network Connection (rev 01) LnkCap: Port #0, Speed 5GT/s, Width x4, ASPM L0s L1, Exit Latency L0s <4us, L1 <8us LnkCtl: ASPM L1 Enabled; RCB 64 bytes, LnkDisable- CommClk+ 83:00.1 Ethernet controller: Intel Corporation 82580 Gigabit Network Connection (rev 01) LnkCap: Port #0, Speed 5GT/s, Width x4, ASPM L0s L1, Exit Latency L0s <4us, L1 <8us LnkCtl: ASPM L1 Enabled; RCB 64 bytes, LnkDisable- CommClk+ Basically sitting at about 25W with a power supply that is probably only 70% efficient at that load. Not terrible but I didn't really gain much over Bios default and feel like something is still hung up at lower package states. Going to try ubuntu to see what I get, any suggestions in the interim?

Is it possible to use the same PCI TPU between 2 Frigate containers or am I going to need to get a second TPU? Trying to run a second container with the beta release (eventually I'd like to run a Frigate container for a second premises) but the logs make it look like the TPU isn't detected although it's set up identically as the stable container.