Jetson Thor reboots under AI workloads and when connecting 2.5" HDD

Hi everyone,

I’m facing serious stability issues with my brand new Jetson Thor and I’m trying to understand whether this is a hardware, power, or software problem.

The system reboots instantly (no alerts, no warnings, no logs) under specific conditions and sometimes even randomly.

  • When I run models on Ollama:

    • large models (e.g. gpt-oss:120b) reboot the board almost immediately

    • smaller models (e.g. qwen3:4b) allow 1–2 responses, then the system reboots

  • When I generate images with ComfyUI (e.g. Flux or similar models), the system reboots as soon as generation starts

  • Every time I connect a 2.5" magnetic HDD via USB, the system reboots immediately; after reboot, the drive is accessible and works normally

  • The board can also reboot randomly even when I’m not doing anything heavy

I also ran some tests that did NOT cause reboots:

  • CPU stress (stress-ng) → stable

  • Light CUDA test (small torch tensor on GPU) → stable

Crashes seem to be triggered by sustained GPU + memory load or by USB power draw (e.g. HDD spin-up), but they can also occur randomly, although less frequently.

Could this indicate power delivery instability (even with the original PSU)? Or could it still be software-related? Does the fact that the board reboots instantly clearly point to a hardware/power issue?

Any help to understand or isolate the problem, and suggestions on how to fix it, would be greatly appreciated.

Thanks!

Hi,

I’m seeing a similar class of problems, although my case seems more specific.

Setup details that may be relevant:

  • Ollama v0.20.2 in Docker

  • Docker with NVIDIA runtime

  • JetPack 7 / L4T R38.2.1

  • otherwise basically original setup, not manually updated or modified at the JetPack/CUDA/driver level

I have already done quite a lot with Thor + Ollama over the last weeks/months, including different Ollama versions and many different local models. Until very recently, the system was basically stable.

The important difference in my case:

  • Text generation still works perfectly and very stable.

  • Even very large text contexts work. I can run around 260k context without problems.

  • I tested Flux quickly again in ComfyUI, and image generation works perfectly on my system.

  • My problem appears specifically with vision models / image analysis on the GPU.

  • qwen2.5vl:3b through Ollama GPU offload can hard reboot the system.

  • The same vision model works CPU-only, so the image, model, and Ollama API path seem to be okay.

  • This does not look like a normal container OOM. Docker shows OOMKilled=false.

What makes this especially strange is that this started only recently. Before that, even huge context windows with many images were possible. Of course, at some point things became very slow, but the system itself was stable.

So in my case, Ollama text workloads are stable, ComfyUI/Flux image generation is stable, but Ollama vision workloads on CUDA are not.

Your case sounds broader because you also see reboots with ComfyUI and even USB HDD spin-up. That may point more strongly toward power delivery or board-level instability. But I would not rule out JetPack 7 / Thor software/runtime instability either, especially because I see very similar hard-reboot behavior under GPU vision workloads without USB power draw involved.

Can you share:

  • Which Ollama version are you using?

  • Are you running Ollama natively or inside Docker?

  • Did you manually update anything, or is your JetPack/CUDA/driver stack still basically stock?

  • Which power mode are you using? (sudo nvpmodel -q)

  • Do you see any NVRM, Xid, or GPU errors in journalctl -k -b -1 after a reboot?

  • Does docker inspect show OOMKilled=false after the crash?

  • Do text-only models also crash for you, or mainly vision / image generation / high GPU-memory workloads?

I’m trying to isolate whether this is a hardware/power issue or a deeper Thor + JetPack 7 + CUDA + Docker/Ollama stability issue.

Is the drive you attach externally powered? If not you might want try that.

How often do you manually reboot Thor. I reboot mine twice a day, and if running heavy loads will run this in between them:

sudo sync &&  echo 3 |sudo tee /proc/sys/vm/drop_caches

With vllm you can

--gpu-memory-utilization $value        (e.g. 0.25)

You may need to do something similar in your applications.

Hi, @bigassonr

Just want to double-check that you use the default power supply?
More, have you try usb pendrive before?

Thanks.

Hi, @westhauser-aerospace

Do you want to file a new topic for your use case separately?
Thanks.

Das kam nicht von dir, sondern aus seiner Frage:

“Is the drive you attach externally powered? If not you might want try that.”

I am not actually running the workload from an externally attached drive in the critical setup. So external-drive power is probably not the main factor here.

Regarding manual reboots: I do not normally reboot Thor twice a day. In my old stable setup, that was not necessary. The system was used very heavily and was still stable.

Regarding “drop_caches”: I do use it, but not on a fixed schedule. I use it depending on the situation. If memory is full but I know the models are no longer active, I clear caches manually. That can be once a day, or it can be many times per day during heavy testing.

The strange part in my case is that I don’t think this is normal memory pressure or that Thor generally can’t handle these workloads. Before the first hard crash, my setup was extremely stable. I used it daily for visual AI tests in quality assurance at my main employer: analyzing large amounts of images, generating many images with Flux Schnell, testing 3D workflows, and running heavy workloads without issues.

Flux Schnell using 40–50 GB unified memory was normal for my setup. I generated hundreds of images like that on Thor before, so the memory usage itself does not seem to be the real problem.

The issue seems to start after one hard crash / reboot event from a still unknown cause. After that, the system appears to remain permanently unstable: Ollama Vision starts crashing again, ComfyUI/Flux becomes dangerous to run, and the same kinds of workloads that were stable before suddenly trigger reboots.

After reinstalling JetPack 7.0 cleanly, the system seems to behave like the old stable setup again. I tested Ollama Vision with many full-size images across different models and so far there were no crashes.

So my current suspicion is that one specific container / CUDA / PyTorch / offloading path triggered a hard GPU/system failure, and after that the system state became unreliable. It may be related to aggressive pinned memory, async offloading, CUDA kernels, container runtime state, or something similar — but it is very hard to isolate because the actual crash does not leave useful logs.

For my use case, rebooting twice a day or carefully limiting every workload is not really an acceptable solution. The system has to be production-ready. I eventually want this stack to support robotics/vision workloads, so it cannot behave like a fragile desktop experiment. A robot brain that randomly reboots under load is not useful.

My next step is to test a cleaner CUDA 13 / PyTorch 25.11 ComfyUI container built for Spark/GB10-class systems, because Spark and Thor are at least closer in architecture. If that fails as well, I may move to JetPack 7.1 and test the whole core stack again immediately: ComfyUI, Flux Schnell, WAN, and Ollama Vision.

I mean, the board is brand new, so it hasn’t been powered on for long. Also, since it keeps rebooting on its own, it ends up restarting multiple times a day.

I also tried with a USB pendrive, and it seems that every time I connect or disconnect any USB device (even something simple like a mouse or keyboard), the system can randomly reboot.

I am running JetPack 7.1 (L4T R38.4.0).

  • ComfyUI is running from the original repository (cloned, no major modifications)

  • Ollama is running inside Docker

  • Power mode is set to 1

Text models behave as described earlier:

  • Heavy models → the system reboots almost immediately

  • Lighter models → I can get 1–2 responses, then the system reboots

Hi,

We want to reproduce this issue internally.
Could you share the steps to reproduce?

If we have an LLM serving, suppose the issue can be reproduced with the USB connection, is that right?

If there is not LLM related work running, do you also see this reboot issue on Thor?
Thanks.

I just installed the BSP following the quick start guide, then Jetpack using apt. While, I run ollama docker following this guide.
Nothing more was done to reproduce this error.

I tried to log any error using journalctl and I don’t think anything suspicious gets logged, this is the log for one of the crashes:

May 08 16:45:28 thor kernel: camrtc-coe tegra-capture-coe2: netdev event 1 dev mgbe2_0
May 08 16:45:28 thor kernel: camrtc-coe tegra-capture-coe2: netdev event 4 dev mgbe2_0
May 08 16:45:28 thor kernel: camrtc-coe tegra-capture-coe3: netdev event 14 dev mgbe3_0
May 08 16:45:28 thor kernel: camrtc-coe tegra-capture-coe3: netdev event 1 dev mgbe3_0
May 08 16:45:28 thor kernel: camrtc-coe tegra-capture-coe3: netdev event 4 dev mgbe3_0
May 08 16:45:28 thor kernel: [RF]halrf_ic_cfg_init aid = 0x6758 !!
May 08 16:45:28 thor kernel: [RF]hal_i->chip_id = 3 !!
May 08 16:45:28 thor kernel: [RF]rf->ic_type = 0x8 !!
May 08 16:45:28 thor kernel: [WARNING][BB][halbb_cck_rpl_ofst_ref_init] There is no cck_rpl_ofst_ref !
May 08 16:45:28 thor kernel: [BB][halbb_la_bb_set_smp_rate] smp_rate_tmp=7, la_smp_rate_log=160 M
May 08 16:45:28 thor kernel: [BB]addr=[0x30000 ~ 0x70000], buf_size=(256 K), smp_num_max=(32768)
May 08 16:45:28 thor kernel: camrtc-coe tegra-capture-coe0: netdev event 4 dev mgbe0_0
May 08 16:45:28 thor kernel: camrtc-coe tegra-capture-coe1: netdev event 4 dev mgbe1_0
May 08 16:45:28 thor kernel: camrtc-coe tegra-capture-coe2: netdev event 4 dev mgbe2_0
May 08 16:45:28 thor kernel: camrtc-coe tegra-capture-coe3: netdev event 4 dev mgbe3_0
May 08 16:45:28 thor kernel: loop9: detected capacity change from 0 to 8
May 08 16:45:28 thor kernel: Consider using thermal netlink events interface
May 08 16:45:28 thor kernel: nv_platform 8808c00000.display: Adding to iommu group 57
May 08 16:45:28 thor kernel: nv_platform 8808c00000.display: Cannot reserve IOVA region of 0 size
May 08 16:45:28 thor kernel: nv_platform 8808c00000.display: Cannot reserve IOVA region of 0 size
May 08 16:45:28 thor kernel: platform 8808c00000.display:nvdisplay-niso: Adding to iommu group 58
May 08 16:45:28 thor kernel: NVRM: devm_reset_control_get failed, err: -2
May 08 16:45:28 thor kernel: NVRM: devm_reset_control_get failed, err: -2
May 08 16:45:28 thor kernel: NVRM: mipi_cal devm_reset_control_get failed, err: -2
May 08 16:45:28 thor kernel: NVRM: loading NVIDIA UNIX Open Kernel Module for aarch64 TempVersion Release Build (bugfix_main) (buildbrain@288300e6-664a-4818-9b68-cc3e41612901-juaq-jkjpg) Tue Dec 30 15:54>
May 08 16:45:28 thor kernel: nvidia-modeset: Loading NVIDIA UNIX Open Kernel Mode Setting Driver for aarch64 TempVersion Release Build (bugfix_main) (buildbrain@288300e6-664a-4818-9b68-cc3e41612901-juaq-j>
May 08 16:45:28 thor kernel: [drm] [nvidia-drm] [GPU ID 0x00000100] Loading driver
May 08 16:45:28 thor kernel: tegra-bpmp-bwmgr bwmgr: set EMC floor frequency to 665600KHz
May 08 16:45:28 thor kernel: tegra-bpmp-bwmgr bwmgr: cap EMC frequency to 4266000000Hz
May 08 16:45:29 thor kernel: [drm] Initialized nvidia-drm 0.0.0 20160202 for 0000:01:00.0 on minor 1
May 08 16:45:29 thor kernel: nvidia 0000:01:00.0: [drm] No compatible format found
May 08 16:45:29 thor kernel: nvidia 0000:01:00.0: [drm] Cannot find any crtc or sizes
May 08 16:45:29 thor kernel: [drm] [nvidia-drm] [GPU ID 0x00020000] Loading driver
May 08 16:45:29 thor kernel: nvidia-modeset: WARNING: HW supports 8 heads. Limiting to 4 heads
May 08 16:45:29 thor kernel: nvidia-modeset: WARNING: GPU:0: The head configuration (0xff) is inconsistent with the number of heads (4)
May 08 16:45:29 thor kernel: NVRM: rpcRmApiControl_dce: NVRM_RPC_DCE: Failed RM ctrl call cmd:0x731341 result 0xffff: Failure: Generic Error [NV_ERR_GENERIC]
May 08 16:45:29 thor kernel: [drm] Initialized nvidia-drm 0.0.0 20160202 for 8808c00000.display on minor 2
May 08 16:45:29 thor kernel: [drm] [nvidia-drm] [GPU ID 0x00020000] Invalid framebuffer console info
May 08 16:45:29 thor kernel: nv_platform 8808c00000.display: [drm] Cannot find any crtc or sizes
May 08 16:45:31 thor kernel: rfkill: input handler disabled
May 08 16:45:32 thor kernel: Bluetooth: RFCOMM TTY layer initialized
May 08 16:45:32 thor kernel: Bluetooth: RFCOMM socket layer initialized
May 08 16:45:32 thor kernel: Bluetooth: RFCOMM ver 1.11
May 08 16:45:38 thor kernel: _cmd_abort_notify(570)vv abort=1
May 08 16:45:38 thor kernel: [BB]halbb_wifi_event_notify: connect start: rssi=0xFF, set to RSSI_MAX
May 08 16:45:38 thor kernel: [BB]halbb_wifi_event_notify: connect start: PDth=110
May 08 16:45:38 thor kernel: 1A24=0x009d1de3, 1A34=0x02451d82, 1A64=0x009e0214, 1A08=0x1b0a000d
May 08 16:45:38 thor kernel: RF0=0x20001:0x20001, RF18=0x01c06:0x01c00
May 08 16:45:38 thor kernel: 1A24=0x009d1de3, 1A34=0x02451d82, 1A64=0x009e0214, 1A08=0x1b0b000d
May 08 16:45:38 thor kernel: RF0=0x20001:0x20001, RF18=0x01c06:0x01c00
May 08 16:45:28 thor kernel: Consider using thermal netlink events interface
May 08 16:45:28 thor kernel: nv_platform 8808c00000.display: Adding to iommu group 57
May 08 16:45:28 thor kernel: nv_platform 8808c00000.display: Cannot reserve IOVA region of 0 size
May 08 16:45:28 thor kernel: nv_platform 8808c00000.display: Cannot reserve IOVA region of 0 size
May 08 16:45:28 thor kernel: platform 8808c00000.display:nvdisplay-niso: Adding to iommu group 58
May 08 16:45:28 thor kernel: NVRM: devm_reset_control_get failed, err: -2
May 08 16:45:28 thor kernel: NVRM: devm_reset_control_get failed, err: -2
May 08 16:45:28 thor kernel: NVRM: mipi_cal devm_reset_control_get failed, err: -2
May 08 16:45:28 thor kernel: NVRM: loading NVIDIA UNIX Open Kernel Module for aarch64 TempVersion Release Build (bugfix_main) (buildbrain@288300e6-664a-4818-9b68-cc3e41612901-juaq-jkjpg) Tue Dec 30 15:54>
May 08 16:45:28 thor kernel: nvidia-modeset: Loading NVIDIA UNIX Open Kernel Mode Setting Driver for aarch64 TempVersion Release Build (bugfix_main) (buildbrain@288300e6-664a-4818-9b68-cc3e41612901-juaq-j>
May 08 16:45:28 thor kernel: [drm] [nvidia-drm] [GPU ID 0x00000100] Loading driver
May 08 16:45:28 thor kernel: tegra-bpmp-bwmgr bwmgr: set EMC floor frequency to 665600KHz
May 08 16:45:28 thor kernel: tegra-bpmp-bwmgr bwmgr: cap EMC frequency to 4266000000Hz
May 08 16:45:29 thor kernel: [drm] Initialized nvidia-drm 0.0.0 20160202 for 0000:01:00.0 on minor 1
May 08 16:45:29 thor kernel: nvidia 0000:01:00.0: [drm] No compatible format found
May 08 16:45:29 thor kernel: nvidia 0000:01:00.0: [drm] Cannot find any crtc or sizes
May 08 16:45:29 thor kernel: [drm] [nvidia-drm] [GPU ID 0x00020000] Loading driver
May 08 16:45:29 thor kernel: nvidia-modeset: WARNING: HW supports 8 heads. Limiting to 4 heads
May 08 16:45:29 thor kernel: nvidia-modeset: WARNING: GPU:0: The head configuration (0xff) is inconsistent with the number of heads (4)
May 08 16:45:29 thor kernel: NVRM: rpcRmApiControl_dce: NVRM_RPC_DCE: Failed RM ctrl call cmd:0x731341 result 0xffff: Failure: Generic Error [NV_ERR_GENERIC]
May 08 16:45:29 thor kernel: [drm] Initialized nvidia-drm 0.0.0 20160202 for 8808c00000.display on minor 2
May 08 16:45:29 thor kernel: [drm] [nvidia-drm] [GPU ID 0x00020000] Invalid framebuffer console info
May 08 16:45:29 thor kernel: nv_platform 8808c00000.display: [drm] Cannot find any crtc or sizes
May 08 16:45:31 thor kernel: rfkill: input handler disabled
May 08 16:45:32 thor kernel: Bluetooth: RFCOMM TTY layer initialized
May 08 16:45:32 thor kernel: Bluetooth: RFCOMM socket layer initialized
May 08 16:45:32 thor kernel: Bluetooth: RFCOMM ver 1.11
May 08 16:45:38 thor kernel: _cmd_abort_notify(570)vv abort=1
May 08 16:45:38 thor kernel: [BB]halbb_wifi_event_notify: connect start: rssi=0xFF, set to RSSI_MAX
May 08 16:45:38 thor kernel: [BB]halbb_wifi_event_notify: connect start: PDth=110
May 08 16:45:38 thor kernel: 1A24=0x009d1de3, 1A34=0x02451d82, 1A64=0x009e0214, 1A08=0x1b0a000d
May 08 16:45:38 thor kernel: RF0=0x20001:0x20001, RF18=0x01c06:0x01c00
May 08 16:45:38 thor kernel: 1A24=0x009d1de3, 1A34=0x02451d82, 1A64=0x009e0214, 1A08=0x1b0b000d
May 08 16:45:38 thor kernel: RF0=0x20001:0x20001, RF18=0x01c06:0x01c00
May 08 16:45:38 thor kernel: 1A24=0x009d1de6, 1A34=0x02471d85, 1A64=0x009e0214, 1A08=0x1b10000d
May 08 16:45:38 thor kernel: RF0=0x331e1:0x332c1, RF18=0x01c06:0x01c00
May 08 16:45:48 thor kernel: [ 36-5G] [ 40-5G] [ 44-5G] [ 48-5G] [149-5G] [153-5G] [157-5G] [161-5G]
May 08 16:45:48 thor kernel: [165-5G] [ 52-5G] [ 56-5G] [ 60-5G] [ 64-5G] [100-5G] [104-5G] [108-5G]
May 08 16:45:48 thor kernel: [112-5G] [116-5G] [120-5G] [124-5G] [128-5G] [132-5G] [136-5G] [140-5G]
May 08 16:45:48 thor kernel: [ 1-2G] [ 2-2G] [ 3-2G] [ 4-2G] [ 5-2G] [ 6-2G] [ 7-2G] [ 8-2G]
May 08 16:45:48 thor kernel: [ 9-2G] [ 10-2G] [ 11-2G] [ 12-2G] [ 13-2G] [ 5-6G] [ 21-6G] [ 37-6G]
May 08 16:45:48 thor kernel: [ 53-6G] [ 69-6G] [ 85-6G]
May 08 16:46:02 thor kernel: [ 36-5G] [ 40-5G] [ 44-5G] [ 48-5G] [149-5G] [153-5G] [157-5G] [161-5G]
May 08 16:46:02 thor kernel: [165-5G] [ 52-5G] [ 56-5G] [ 60-5G] [ 64-5G] [100-5G] [104-5G] [108-5G]
May 08 16:46:02 thor kernel: [112-5G] [116-5G] [120-5G] [124-5G] [128-5G] [132-5G] [136-5G] [140-5G]
May 08 16:46:02 thor kernel: [ 1-2G] [ 2-2G] [ 3-2G] [ 4-2G] [ 5-2G] [ 6-2G] [ 7-2G] [ 8-2G]
May 08 16:46:02 thor kernel: [ 9-2G] [ 10-2G] [ 11-2G] [ 12-2G] [ 13-2G] [ 5-6G] [ 21-6G] [ 37-6G]
May 08 16:46:02 thor kernel: [ 53-6G] [ 69-6G] [ 85-6G]
May 08 16:46:11 thor kernel: [ 36-5G] [ 40-5G] [ 44-5G] [ 48-5G] [149-5G] [153-5G] [157-5G] [161-5G]
May 08 16:46:11 thor kernel: [165-5G] [ 52-5G] [ 56-5G] [ 60-5G] [ 64-5G] [100-5G] [104-5G] [108-5G]
May 08 16:46:11 thor kernel: [112-5G] [116-5G] [120-5G] [124-5G] [128-5G] [132-5G] [136-5G] [140-5G]
May 08 16:46:11 thor kernel: [ 1-2G] [ 2-2G] [ 3-2G] [ 4-2G] [ 5-2G] [ 6-2G] [ 7-2G] [ 8-2G]
May 08 16:46:11 thor kernel: [ 9-2G] [ 10-2G] [ 11-2G] [ 12-2G] [ 13-2G] [ 5-6G] [ 21-6G] [ 37-6G]
May 08 16:46:11 thor kernel: [ 53-6G] [ 69-6G] [ 85-6G]
May 08 16:46:21 thor kernel: [ 36-5G] [ 40-5G] [ 44-5G] [ 48-5G] [149-5G] [153-5G] [157-5G] [161-5G]
May 08 16:46:21 thor kernel: [165-5G] [ 52-5G] [ 56-5G] [ 60-5G] [ 64-5G] [100-5G] [104-5G] [108-5G]
May 08 16:46:21 thor kernel: [112-5G] [116-5G] [120-5G] [124-5G] [128-5G] [132-5G] [136-5G] [140-5G]
May 08 16:46:21 thor kernel: [ 1-2G] [ 2-2G] [ 3-2G] [ 4-2G] [ 5-2G] [ 6-2G] [ 7-2G] [ 8-2G]
May 08 16:46:21 thor kernel: [ 9-2G] [ 10-2G] [ 11-2G] [ 12-2G] [ 13-2G] [ 5-6G] [ 21-6G] [ 37-6G]
May 08 16:46:21 thor kernel: [ 53-6G] [ 69-6G] [ 85-6G]
May 08 16:46:31 thor kernel: [ 36-5G] [ 40-5G] [ 44-5G] [ 48-5G] [149-5G] [153-5G] [157-5G] [161-5G]
May 08 16:46:31 thor kernel: [165-5G] [ 52-5G] [ 56-5G] [ 60-5G] [ 64-5G] [100-5G] [104-5G] [108-5G]
May 08 16:46:31 thor kernel: [112-5G] [116-5G] [120-5G] [124-5G] [128-5G] [132-5G] [136-5G] [140-5G]
May 08 16:46:31 thor kernel: [ 1-2G] [ 2-2G] [ 3-2G] [ 4-2G] [ 5-2G] [ 6-2G] [ 7-2G] [ 8-2G]
May 08 16:46:31 thor kernel: [ 9-2G] [ 10-2G] [ 11-2G] [ 12-2G] [ 13-2G] [ 5-6G] [ 21-6G] [ 37-6G]
May 08 16:46:31 thor kernel: [ 53-6G] [ 69-6G] [ 85-6G]
May 08 16:46:41 thor kernel: [ 36-5G] [ 40-5G] [ 44-5G] [ 48-5G] [149-5G] [153-5G] [157-5G] [161-5G]
May 08 16:46:41 thor kernel: [165-5G] [ 52-5G] [ 56-5G] [ 60-5G] [ 64-5G] [100-5G] [104-5G] [108-5G]
May 08 16:46:41 thor kernel: [112-5G] [116-5G] [120-5G] [124-5G] [128-5G] [132-5G] [136-5G] [140-5G]
May 08 16:46:41 thor kernel: [ 1-2G] [ 2-2G] [ 3-2G] [ 4-2G] [ 5-2G] [ 6-2G] [ 7-2G] [ 8-2G]
May 08 16:46:41 thor kernel: [ 9-2G] [ 10-2G] [ 11-2G] [ 12-2G] [ 13-2G] [ 5-6G] [ 21-6G] [ 37-6G]
May 08 16:46:41 thor kernel: [ 53-6G] [ 69-6G] [ 85-6G]
May 08 16:46:45 thor kernel: _cmd_abort_notify(570)vv abort=1
May 08 16:46:46 thor kernel: [ 36-5G] [ 40-5G] [ 44-5G] [ 48-5G] [149-5G] [153-5G] [157-5G] [161-5G]
May 08 16:46:46 thor kernel: [165-5G] [ 52-5G] [ 56-5G] [ 60-5G] [ 64-5G] [100-5G] [104-5G] [108-5G]
May 08 16:46:46 thor kernel: [112-5G] [116-5G] [120-5G] [124-5G] [128-5G] [132-5G] [136-5G] [140-5G]
May 08 16:46:46 thor kernel: [ 1-2G] [ 2-2G] [ 3-2G] [ 4-2G] [ 5-2G] [ 6-2G] [ 7-2G] [ 8-2G]
May 08 16:46:46 thor kernel: [ 9-2G] [ 10-2G] [ 11-2G] [ 12-2G] [ 13-2G] [ 5-6G] [ 21-6G] [ 37-6G]
May 08 16:46:46 thor kernel: [ 53-6G] [ 69-6G] [ 85-6G]
May 08 16:46:56 thor kernel: [ 36-5G] [ 40-5G] [ 44-5G] [ 48-5G] [149-5G] [153-5G] [157-5G] [161-5G]
May 08 16:46:56 thor kernel: [165-5G] [ 52-5G] [ 56-5G] [ 60-5G] [ 64-5G] [100-5G] [104-5G] [108-5G]
May 08 16:46:56 thor kernel: [112-5G] [116-5G] [120-5G] [124-5G] [128-5G] [132-5G] [136-5G] [140-5G]
May 08 16:46:56 thor kernel: [ 1-2G] [ 2-2G] [ 3-2G] [ 4-2G] [ 5-2G] [ 6-2G] [ 7-2G] [ 8-2G]
May 08 16:46:56 thor kernel: [ 9-2G] [ 10-2G] [ 11-2G] [ 12-2G] [ 13-2G] [ 5-6G] [ 21-6G] [ 37-6G]
May 08 16:46:56 thor kernel: [ 53-6G] [ 69-6G] [ 85-6G]
May 08 16:47:05 thor kernel: [ 36-5G] [ 40-5G] [ 44-5G] [ 48-5G] [149-5G] [153-5G] [157-5G] [161-5G]
May 08 16:47:05 thor kernel: [165-5G] [ 52-5G] [ 56-5G] [ 60-5G] [ 64-5G] [100-5G] [104-5G] [108-5G]
May 08 16:47:05 thor kernel: [112-5G] [116-5G] [120-5G] [124-5G] [128-5G] [132-5G] [136-5G] [140-5G]
May 08 16:47:05 thor kernel: [ 1-2G] [ 2-2G] [ 3-2G] [ 4-2G] [ 5-2G] [ 6-2G] [ 7-2G] [ 8-2G]
May 08 16:47:05 thor kernel: [ 9-2G] [ 10-2G] [ 11-2G] [ 12-2G] [ 13-2G] [ 5-6G] [ 21-6G] [ 37-6G]
May 08 16:47:05 thor kernel: [ 53-6G] [ 69-6G] [ 85-6G]
May 08 16:47:16 thor kernel: [ 36-5G] [ 40-5G] [ 44-5G] [ 48-5G] [149-5G] [153-5G] [157-5G] [161-5G]
May 08 16:47:16 thor kernel: [165-5G] [ 52-5G] [ 56-5G] [ 60-5G] [ 64-5G] [100-5G] [104-5G] [108-5G]
May 08 16:47:16 thor kernel: [112-5G] [116-5G] [120-5G] [124-5G] [128-5G] [132-5G] [136-5G] [140-5G]
May 08 16:47:16 thor kernel: [ 1-2G] [ 2-2G] [ 3-2G] [ 4-2G] [ 5-2G] [ 6-2G] [ 7-2G] [ 8-2G]
May 08 16:47:16 thor kernel: [ 9-2G] [ 10-2G] [ 11-2G] [ 12-2G] [ 13-2G] [ 5-6G] [ 21-6G] [ 37-6G]
May 08 16:47:16 thor kernel: [ 53-6G] [ 69-6G] [ 85-6G]
May 08 16:47:26 thor kernel: [ 36-5G] [ 40-5G] [ 44-5G] [ 48-5G] [149-5G] [153-5G] [157-5G] [161-5G]
May 08 16:47:26 thor kernel: [165-5G] [ 52-5G] [ 56-5G] [ 60-5G] [ 64-5G] [100-5G] [104-5G] [108-5G]
May 08 16:47:26 thor kernel: [112-5G] [116-5G] [120-5G] [124-5G] [128-5G] [132-5G] [136-5G] [140-5G]
May 08 16:47:26 thor kernel: [ 1-2G] [ 2-2G] [ 3-2G] [ 4-2G] [ 5-2G] [ 6-2G] [ 7-2G] [ 8-2G]
May 08 16:47:26 thor kernel: [ 9-2G] [ 10-2G] [ 11-2G] [ 12-2G] [ 13-2G] [ 5-6G] [ 21-6G] [ 37-6G]
May 08 16:47:26 thor kernel: [ 53-6G] [ 69-6G] [ 85-6G]
May 08 16:47:36 thor kernel: [ 36-5G] [ 40-5G] [ 44-5G] [ 48-5G] [149-5G] [153-5G] [157-5G] [161-5G]
May 08 16:47:36 thor kernel: [165-5G] [ 52-5G] [ 56-5G] [ 60-5G] [ 64-5G] [100-5G] [104-5G] [108-5G]
May 08 16:47:36 thor kernel: [112-5G] [116-5G] [120-5G] [124-5G] [128-5G] [132-5G] [136-5G] [140-5G]
May 08 16:47:36 thor kernel: [ 1-2G] [ 2-2G] [ 3-2G] [ 4-2G] [ 5-2G] [ 6-2G] [ 7-2G] [ 8-2G]
May 08 16:47:36 thor kernel: [ 9-2G] [ 10-2G] [ 11-2G] [ 12-2G] [ 13-2G] [ 5-6G] [ 21-6G] [ 37-6G]
May 08 16:47:36 thor kernel: [ 53-6G] [ 69-6G] [ 85-6G]
May 08 16:47:48 thor kernel: [ 36-5G] [ 40-5G] [ 44-5G] [ 48-5G] [149-5G] [153-5G] [157-5G] [161-5G]
May 08 16:47:48 thor kernel: [165-5G] [ 52-5G] [ 56-5G] [ 60-5G] [ 64-5G] [100-5G] [104-5G] [108-5G]
May 08 16:47:48 thor kernel: [112-5G] [116-5G] [120-5G] [124-5G] [128-5G] [132-5G] [136-5G] [140-5G]
May 08 16:47:48 thor kernel: [ 1-2G] [ 2-2G] [ 3-2G] [ 4-2G] [ 5-2G] [ 6-2G] [ 7-2G] [ 8-2G]
May 08 16:47:48 thor kernel: [ 9-2G] [ 10-2G] [ 11-2G] [ 12-2G] [ 13-2G] [ 5-6G] [ 21-6G] [ 37-6G]
May 08 16:47:48 thor kernel: [ 53-6G] [ 69-6G] [ 85-6G]
May 08 16:47:58 thor kernel: [ 36-5G] [ 40-5G] [ 44-5G] [ 48-5G] [149-5G] [153-5G] [157-5G] [161-5G]
May 08 16:47:58 thor kernel: [165-5G] [ 52-5G] [ 56-5G] [ 60-5G] [ 64-5G] [100-5G] [104-5G] [108-5G]
May 08 16:47:58 thor kernel: [112-5G] [116-5G] [120-5G] [124-5G] [128-5G] [132-5G] [136-5G] [140-5G]
May 08 16:47:58 thor kernel: [ 1-2G] [ 2-2G] [ 3-2G] [ 4-2G] [ 5-2G] [ 6-2G] [ 7-2G] [ 8-2G]
May 08 16:47:58 thor kernel: [ 9-2G] [ 10-2G] [ 11-2G] [ 12-2G] [ 13-2G] [ 5-6G] [ 21-6G] [ 37-6G]
May 08 16:47:58 thor kernel: [ 53-6G] [ 69-6G] [ 85-6G]
May 08 16:48:08 thor kernel: [ 36-5G] [ 40-5G] [ 44-5G] [ 48-5G] [149-5G] [153-5G] [157-5G] [161-5G]
May 08 16:48:08 thor kernel: [165-5G] [ 52-5G] [ 56-5G] [ 60-5G] [ 64-5G] [100-5G] [104-5G] [108-5G]
May 08 16:48:08 thor kernel: [112-5G] [116-5G] [120-5G] [124-5G] [128-5G] [132-5G] [136-5G] [140-5G]
May 08 16:48:08 thor kernel: [ 1-2G] [ 2-2G] [ 3-2G] [ 4-2G] [ 5-2G] [ 6-2G] [ 7-2G] [ 8-2G]
May 08 16:48:08 thor kernel: [ 9-2G] [ 10-2G] [ 11-2G] [ 12-2G] [ 13-2G] [ 5-6G] [ 21-6G] [ 37-6G]
May 08 16:48:08 thor kernel: [ 53-6G] [ 69-6G] [ 85-6G]
May 08 16:48:19 thor kernel: [ 36-5G] [ 40-5G] [ 44-5G] [ 48-5G] [149-5G] [153-5G] [157-5G] [161-5G]
May 08 16:48:19 thor kernel: [165-5G] [ 52-5G] [ 56-5G] [ 60-5G] [ 64-5G] [100-5G] [104-5G] [108-5G]
May 08 16:48:19 thor kernel: [112-5G] [116-5G] [120-5G] [124-5G] [128-5G] [132-5G] [136-5G] [140-5G]
May 08 16:48:19 thor kernel: [ 1-2G] [ 2-2G] [ 3-2G] [ 4-2G] [ 5-2G] [ 6-2G] [ 7-2G] [ 8-2G]
May 08 16:48:19 thor kernel: [ 9-2G] [ 10-2G] [ 11-2G] [ 12-2G] [ 13-2G] [ 5-6G] [ 21-6G] [ 37-6G]
May 08 16:48:19 thor kernel: [ 53-6G] [ 69-6G] [ 85-6G]
May 08 16:48:29 thor kernel: [ 36-5G] [ 40-5G] [ 44-5G] [ 48-5G] [149-5G] [153-5G] [157-5G] [161-5G]
May 08 16:48:29 thor kernel: [165-5G] [ 52-5G] [ 56-5G] [ 60-5G] [ 64-5G] [100-5G] [104-5G] [108-5G]
May 08 16:48:29 thor kernel: [112-5G] [116-5G] [120-5G] [124-5G] [128-5G] [132-5G] [136-5G] [140-5G]
May 08 16:48:29 thor kernel: [ 1-2G] [ 2-2G] [ 3-2G] [ 4-2G] [ 5-2G] [ 6-2G] [ 7-2G] [ 8-2G]
May 08 16:48:29 thor kernel: [ 9-2G] [ 10-2G] [ 11-2G] [ 12-2G] [ 13-2G] [ 5-6G] [ 21-6G] [ 37-6G]
May 08 16:48:29 thor kernel: [ 53-6G] [ 69-6G] [ 85-6G]
May 08 16:48:40 thor kernel: [ 36-5G] [ 40-5G] [ 44-5G] [ 48-5G] [149-5G] [153-5G] [157-5G] [161-5G]
May 08 16:48:40 thor kernel: [165-5G] [ 52-5G] [ 56-5G] [ 60-5G] [ 64-5G] [100-5G] [104-5G] [108-5G]
May 08 16:48:40 thor kernel: [112-5G] [116-5G] [120-5G] [124-5G] [128-5G] [132-5G] [136-5G] [140-5G]
May 08 16:48:40 thor kernel: [ 1-2G] [ 2-2G] [ 3-2G] [ 4-2G] [ 5-2G] [ 6-2G] [ 7-2G] [ 8-2G]
May 08 16:48:40 thor kernel: [ 9-2G] [ 10-2G] [ 11-2G] [ 12-2G] [ 13-2G] [ 5-6G] [ 21-6G] [ 37-6G]
May 08 16:48:40 thor kernel: [ 53-6G] [ 69-6G] [ 85-6G]
May 08 16:48:49 thor kernel: [ 36-5G] [ 40-5G] [ 44-5G] [ 48-5G] [149-5G] [153-5G] [157-5G] [161-5G]
May 08 16:48:49 thor kernel: [165-5G] [ 52-5G] [ 56-5G] [ 60-5G] [ 64-5G] [100-5G] [104-5G] [108-5G]
May 08 16:48:49 thor kernel: [112-5G] [116-5G] [120-5G] [124-5G] [128-5G] [132-5G] [136-5G] [140-5G]
May 08 16:48:49 thor kernel: [ 1-2G] [ 2-2G] [ 3-2G] [ 4-2G] [ 5-2G] [ 6-2G] [ 7-2G] [ 8-2G]
May 08 16:48:49 thor kernel: [ 9-2G] [ 10-2G] [ 11-2G] [ 12-2G] [ 13-2G] [ 5-6G] [ 21-6G] [ 37-6G]
May 08 16:48:49 thor kernel: [ 53-6G] [ 69-6G] [ 85-6G]
May 08 16:48:59 thor kernel: [ 36-5G] [ 40-5G] [ 44-5G] [ 48-5G] [149-5G] [153-5G] [157-5G] [161-5G]
May 08 16:48:59 thor kernel: [165-5G] [ 52-5G] [ 56-5G] [ 60-5G] [ 64-5G] [100-5G] [104-5G] [108-5G]
May 08 16:48:59 thor kernel: [112-5G] [116-5G] [120-5G] [124-5G] [128-5G] [132-5G] [136-5G] [140-5G]
May 08 16:48:59 thor kernel: [ 1-2G] [ 2-2G] [ 3-2G] [ 4-2G] [ 5-2G] [ 6-2G] [ 7-2G] [ 8-2G]
May 08 16:48:59 thor kernel: [ 9-2G] [ 10-2G] [ 11-2G] [ 12-2G] [ 13-2G] [ 5-6G] [ 21-6G] [ 37-6G]
May 08 16:48:59 thor kernel: [ 53-6G] [ 69-6G] [ 85-6G]
May 08 16:49:09 thor kernel: [ 36-5G] [ 40-5G] [ 44-5G] [ 48-5G] [149-5G] [153-5G] [157-5G] [161-5G]
May 08 16:49:09 thor kernel: [165-5G] [ 52-5G] [ 56-5G] [ 60-5G] [ 64-5G] [100-5G] [104-5G] [108-5G]
May 08 16:49:09 thor kernel: [112-5G] [116-5G] [120-5G] [124-5G] [128-5G] [132-5G] [136-5G] [140-5G]
May 08 16:49:09 thor kernel: [ 1-2G] [ 2-2G] [ 3-2G] [ 4-2G] [ 5-2G] [ 6-2G] [ 7-2G] [ 8-2G]
May 08 16:49:09 thor kernel: [ 9-2G] [ 10-2G] [ 11-2G] [ 12-2G] [ 13-2G] [ 5-6G] [ 21-6G] [ 37-6G]
May 08 16:49:09 thor kernel: [ 53-6G] [ 69-6G] [ 85-6G]
May 08 16:49:17 thor kernel: [ 36-5G] [ 40-5G] [ 44-5G] [ 48-5G] [149-5G] [153-5G] [157-5G] [161-5G]
May 08 16:49:17 thor kernel: [165-5G] [ 52-5G] [ 56-5G] [ 60-5G] [ 64-5G] [100-5G] [104-5G] [108-5G]
May 08 16:49:17 thor kernel: [112-5G] [116-5G] [120-5G] [124-5G] [128-5G] [132-5G] [136-5G] [140-5G]
May 08 16:49:17 thor kernel: [ 1-2G] [ 2-2G] [ 3-2G] [ 4-2G] [ 5-2G] [ 6-2G] [ 7-2G] [ 8-2G]
May 08 16:49:17 thor kernel: [ 9-2G] [ 10-2G] [ 11-2G] [ 12-2G] [ 13-2G] [ 5-6G] [ 21-6G] [ 37-6G]
May 08 16:49:17 thor kernel: [ 53-6G] [ 69-6G] [ 85-6G]
May 08 16:49:27 thor kernel: [ 36-5G] [ 40-5G] [ 44-5G] [ 48-5G] [149-5G] [153-5G] [157-5G] [161-5G]
May 08 16:49:27 thor kernel: [165-5G] [ 52-5G] [ 56-5G] [ 60-5G] [ 64-5G] [100-5G] [104-5G] [108-5G]
May 08 16:49:27 thor kernel: [112-5G] [116-5G] [120-5G] [124-5G] [128-5G] [132-5G] [136-5G] [140-5G]
May 08 16:49:27 thor kernel: [ 1-2G] [ 2-2G] [ 3-2G] [ 4-2G] [ 5-2G] [ 6-2G] [ 7-2G] [ 8-2G]
May 08 16:49:27 thor kernel: [ 9-2G] [ 10-2G] [ 11-2G] [ 12-2G] [ 13-2G] [ 5-6G] [ 21-6G] [ 37-6G]
May 08 16:49:27 thor kernel: [ 53-6G] [ 69-6G] [ 85-6G]
May 08 16:49:38 thor kernel: [ 36-5G] [ 40-5G] [ 44-5G] [ 48-5G] [149-5G] [153-5G] [157-5G] [161-5G]
May 08 16:49:38 thor kernel: [165-5G] [ 52-5G] [ 56-5G] [ 60-5G] [ 64-5G] [100-5G] [104-5G] [108-5G]
May 08 16:49:38 thor kernel: [112-5G] [116-5G] [120-5G] [124-5G] [128-5G] [132-5G] [136-5G] [140-5G]
May 08 16:49:38 thor kernel: [ 1-2G] [ 2-2G] [ 3-2G] [ 4-2G] [ 5-2G] [ 6-2G] [ 7-2G] [ 8-2G]
May 08 16:49:38 thor kernel: [ 9-2G] [ 10-2G] [ 11-2G] [ 12-2G] [ 13-2G] [ 5-6G] [ 21-6G] [ 37-6G]
May 08 16:49:38 thor kernel: [ 53-6G] [ 69-6G] [ 85-6G]
May 08 16:49:50 thor kernel: [ 36-5G] [ 40-5G] [ 44-5G] [ 48-5G] [149-5G] [153-5G] [157-5G] [161-5G]
May 08 16:49:50 thor kernel: [165-5G] [ 52-5G] [ 56-5G] [ 60-5G] [ 64-5G] [100-5G] [104-5G] [108-5G]
May 08 16:49:50 thor kernel: [112-5G] [116-5G] [120-5G] [124-5G] [128-5G] [132-5G] [136-5G] [140-5G]
May 08 16:49:50 thor kernel: [ 1-2G] [ 2-2G] [ 3-2G] [ 4-2G] [ 5-2G] [ 6-2G] [ 7-2G] [ 8-2G]
May 08 16:49:50 thor kernel: [ 9-2G] [ 10-2G] [ 11-2G] [ 12-2G] [ 13-2G] [ 5-6G] [ 21-6G] [ 37-6G]
May 08 16:49:50 thor kernel: [ 53-6G] [ 69-6G] [ 85-6G]
May 08 16:49:52 thor kernel: _cmd_abort_notify(570)vv abort=1
May 08 16:49:54 thor kernel: [ 36-5G] [ 40-5G] [ 44-5G] [ 48-5G] [149-5G] [153-5G] [157-5G] [161-5G]
May 08 16:49:54 thor kernel: [165-5G] [ 52-5G] [ 56-5G] [ 60-5G] [ 64-5G] [100-5G] [104-5G] [108-5G]
May 08 16:49:54 thor kernel: [112-5G] [116-5G] [120-5G] [124-5G] [128-5G] [132-5G] [136-5G] [140-5G]
May 08 16:49:54 thor kernel: [ 1-2G] [ 2-2G] [ 3-2G] [ 4-2G] [ 5-2G] [ 6-2G] [ 7-2G] [ 8-2G]
May 08 16:49:54 thor kernel: [ 9-2G] [ 10-2G] [ 11-2G] [ 12-2G] [ 13-2G] [ 5-6G] [ 21-6G] [ 37-6G]
May 08 16:49:54 thor kernel: [ 53-6G] [ 69-6G] [ 85-6G]
May 08 16:49:57 thor kernel: _cmd_abort_notify(570)vv abort=1
May 08 16:50:00 thor kernel: [ 36-5G] [ 40-5G] [ 44-5G] [ 48-5G] [149-5G] [153-5G] [157-5G] [161-5G]
May 08 16:50:00 thor kernel: [165-5G] [ 52-5G] [ 56-5G] [ 60-5G] [ 64-5G] [100-5G] [104-5G] [108-5G]
May 08 16:50:00 thor kernel: [112-5G] [116-5G] [120-5G] [124-5G] [128-5G] [132-5G] [136-5G] [140-5G]
May 08 16:50:00 thor kernel: [ 1-2G] [ 2-2G] [ 3-2G] [ 4-2G] [ 5-2G] [ 6-2G] [ 7-2G] [ 8-2G]
May 08 16:50:00 thor kernel: [ 9-2G] [ 10-2G] [ 11-2G] [ 12-2G] [ 13-2G] [ 5-6G] [ 21-6G] [ 37-6G]
May 08 16:50:00 thor kernel: [ 53-6G] [ 69-6G] [ 85-6G]
May 08 16:50:10 thor kernel: [ 36-5G] [ 40-5G] [ 44-5G] [ 48-5G] [149-5G] [153-5G] [157-5G] [161-5G]
May 08 16:50:10 thor kernel: [165-5G] [ 52-5G] [ 56-5G] [ 60-5G] [ 64-5G] [100-5G] [104-5G] [108-5G]
May 08 16:50:10 thor kernel: [112-5G] [116-5G] [120-5G] [124-5G] [128-5G] [132-5G] [136-5G] [140-5G]
May 08 16:50:10 thor kernel: [ 1-2G] [ 2-2G] [ 3-2G] [ 4-2G] [ 5-2G] [ 6-2G] [ 7-2G] [ 8-2G]
May 08 16:50:10 thor kernel: [ 9-2G] [ 10-2G] [ 11-2G] [ 12-2G] [ 13-2G] [ 5-6G] [ 21-6G] [ 37-6G]
May 08 16:50:10 thor kernel: [ 53-6G] [ 69-6G] [ 85-6G]
May 08 16:50:20 thor kernel: [ 36-5G] [ 40-5G] [ 44-5G] [ 48-5G] [149-5G] [153-5G] [157-5G] [161-5G]
May 08 16:50:20 thor kernel: [165-5G] [ 52-5G] [ 56-5G] [ 60-5G] [ 64-5G] [100-5G] [104-5G] [108-5G]
May 08 16:50:20 thor kernel: [112-5G] [116-5G] [120-5G] [124-5G] [128-5G] [132-5G] [136-5G] [140-5G]
May 08 16:50:20 thor kernel: [ 1-2G] [ 2-2G] [ 3-2G] [ 4-2G] [ 5-2G] [ 6-2G] [ 7-2G] [ 8-2G]
May 08 16:50:20 thor kernel: [ 9-2G] [ 10-2G] [ 11-2G] [ 12-2G] [ 13-2G] [ 5-6G] [ 21-6G] [ 37-6G]
May 08 16:50:20 thor kernel: [ 53-6G] [ 69-6G] [ 85-6G]
May 08 16:50:28 thor kernel: [ 36-5G] [ 40-5G] [ 44-5G] [ 48-5G] [149-5G] [153-5G] [157-5G] [161-5G]
May 08 16:50:28 thor kernel: [165-5G] [ 52-5G] [ 56-5G] [ 60-5G] [ 64-5G] [100-5G] [104-5G] [108-5G]
May 08 16:50:28 thor kernel: [112-5G] [116-5G] [120-5G] [124-5G] [128-5G] [132-5G] [136-5G] [140-5G]
May 08 16:50:28 thor kernel: [ 1-2G] [ 2-2G] [ 3-2G] [ 4-2G] [ 5-2G] [ 6-2G] [ 7-2G] [ 8-2G]
May 08 16:50:28 thor kernel: [ 9-2G] [ 10-2G] [ 11-2G] [ 12-2G] [ 13-2G] [ 5-6G] [ 21-6G] [ 37-6G]
May 08 16:50:28 thor kernel: [ 53-6G] [ 69-6G] [ 85-6G]
May 08 16:50:47 thor kernel: _cmd_abort_notify(570)vv abort=1
May 08 16:50:51 thor kernel: [ 36-5G] [ 40-5G] [ 44-5G] [ 48-5G] [149-5G] [153-5G] [157-5G] [161-5G]
May 08 16:50:51 thor kernel: [165-5G] [ 52-5G] [ 56-5G] [ 60-5G] [ 64-5G] [100-5G] [104-5G] [108-5G]
May 08 16:50:51 thor kernel: [112-5G] [116-5G] [120-5G] [124-5G] [128-5G] [132-5G] [136-5G] [140-5G]
May 08 16:50:51 thor kernel: [ 1-2G] [ 2-2G] [ 3-2G] [ 4-2G] [ 5-2G] [ 6-2G] [ 7-2G] [ 8-2G]
May 08 16:50:51 thor kernel: [ 9-2G] [ 10-2G] [ 11-2G] [ 12-2G] [ 13-2G] [ 5-6G] [ 21-6G] [ 37-6G]
May 08 16:50:51 thor kernel: [ 53-6G] [ 69-6G] [ 85-6G]
May 08 16:52:39 thor kernel: nvidia 0000:01:00.0: Using 40-bit DMA addresses

Next time you get a forced reboot, maybe run this and then post result here? -b -1 gets the prior boot log.

journalctl -b -1 --no-pager |tee reset.txt

What purpose does your usb drive serve? If it is mounted in the file system then you could try setting it to not suspend. Replacing aaaa and bbbb with your actual lsusb values:

sudo nano /etc/udev/rules.d/99-usb-disk-no-suspend.rules

ACTION=="add|change", SUBSYSTEM=="usb", ATTR{idVendor}=="aaaa", ATTR{idProduct}=="bbbb", TEST=="power/control", ATTR{power/control}="on"

sudo udevadm control --reload-rules
sudo udevadm trigger


You could see if the hub.docker.com ollama image gets the same error?

docker run -d --runtime=nvidia --gpus=all --network host \ 
    -v ollama:/root/.ollama -p 11434:11434  \ 
    --name ollama ollama/ollama