NodeBB

Téléchargement :

# git clone https://github.com/raboof/nethogs
Cloning into 'nethogs'...
remote: Enumerating objects: 1888, done.
remote: Counting objects: 100% (276/276), done.
remote: Compressing objects: 100% (71/71), done.
remote: Total 1888 (delta 230), reused 205 (delta 205), pack-reused 1612 (from 1)
Receiving objects: 100% (1888/1888), 1.53 MiB | 6.39 MiB/s, done.
Resolving deltas: 100% (1245/1245), done.

# apt-get install libpcap-dev

# make

# make install

# ldd src/nethogs
        linux-vdso.so.1 (0x00007ffde5ee4000)
        libpcap.so.0.8 => /lib/x86_64-linux-gnu/libpcap.so.0.8 (0x00007f5feedff000)
        libncurses.so.6 => /lib/x86_64-linux-gnu/libncurses.so.6 (0x00007f5feedd7000)
        libtinfo.so.6 => /lib/x86_64-linux-gnu/libtinfo.so.6 (0x00007f5feeda5000)
        libstdc++.so.6 => /lib/x86_64-linux-gnu/libstdc++.so.6 (0x00007f5feeb79000)
        libgcc_s.so.1 => /lib/x86_64-linux-gnu/libgcc_s.so.1 (0x00007f5feeb59000)
        libc.so.6 => /lib/x86_64-linux-gnu/libc.so.6 (0x00007f5fee92e000)
        libdbus-1.so.3 => /lib/x86_64-linux-gnu/libdbus-1.so.3 (0x00007f5fee8e0000)
        libm.so.6 => /lib/x86_64-linux-gnu/libm.so.6 (0x00007f5fee7f9000)
        /lib64/ld-linux-x86-64.so.2 (0x00007f5feee7b000)
        libsystemd.so.0 => /lib/x86_64-linux-gnu/libsystemd.so.0 (0x00007f5fee732000)
        liblzma.so.5 => /lib/x86_64-linux-gnu/liblzma.so.5 (0x00007f5fee707000)
        libzstd.so.1 => /lib/x86_64-linux-gnu/libzstd.so.1 (0x00007f5fee636000)
        liblz4.so.1 => /lib/x86_64-linux-gnu/liblz4.so.1 (0x00007f5fee616000)
        libcap.so.2 => /lib/x86_64-linux-gnu/libcap.so.2 (0x00007f5fee60b000)
        libgcrypt.so.20 => /lib/x86_64-linux-gnu/libgcrypt.so.20 (0x00007f5fee4cd000)
        libgpg-error.so.0 => /lib/x86_64-linux-gnu/libgpg-error.so.0 (0x00007f5fee4a7000)

# elf-arch src/nethogs
amd64

Le problème :

docker: Error response from daemon: failed to create task for container: failed to create shim task: OCI runtime create failed: runc create failed: unable to start container process: error during container init: error setting cgroup config for procHooks process: failed to write "a *:* rwm": write /sys/fs/cgroup/devices/docker/9062e5fe97eaccd163ea072644a4593a1dc707e090298a08d959ae5dc8f510b3/devices.allow: operation not permitted: unknown.

Version :

#  lsb_release -a
No LSB modules are available.
Distributor ID: Ubuntu
Description:    Ubuntu 22.04.5 LTS
Release:        22.04
Codename:       jammy

# docker --version
Docker version 24.0.2, build cb74dfc

# docker info | grep Cgroup
 Cgroup Driver: cgroupfs
 Cgroup Version: 1

# grep cgroup /proc/filesystems
nodev   cgroup
nodev   cgroup2

# stat -fc %T /sys/fs/cgroup/
tmpfs

# dpkg -l | grep docker
ii  docker-buildx-plugin              0.10.5-1~ubuntu.18.04~bionic                     amd64        Docker Buildx cli plugin.
ii  docker-ce                         5:24.0.2-1~ubuntu.18.04~bionic                   amd64        Docker: the open-source application container engine
ii  docker-ce-cli                     5:24.0.2-1~ubuntu.18.04~bionic                   amd64        Docker CLI: the open-source application container engine
ii  docker-ce-rootless-extras         5:24.0.2-1~ubuntu.18.04~bionic                   amd64        Rootless support for Docker.
ii  docker-compose-plugin             2.18.1-1~ubuntu.18.04~bionic                     amd64        Docker Compose (V2) plugin for the Docker CLI.

Trop de cache sur apt :

# du -sh /var/cache/apt/
2.0G    /var/cache/apt/
# sudo apt clean
# sudo apt autoclean
Reading package lists... Done
Building dependency tree... Done
Reading state information... Done
# du -sh /var/cache/apt/
119M    /var/cache/apt/

❯ abuseipdb-s100-1d (53363 ips)
❯ abuseipdb-s100-3d (58143 ips)
❯ abuseipdb-s100-7d (69300 ips)
❯ abuseipdb-s100-14d (86898 ips)
❯ abuseipdb-s100-30d (125070 ips)
❯ abuseipdb-s100-60d (183928 ips)
❯ abuseipdb-s100-90d (247119 ips)
❯ abuseipdb-s100-120d (357106 ips)
❯ abuseipdb-s100-180d (654007 ips)
❯ abuseipdb-s100-365d (1173988 ips)
❯ abuseipdb-s100-all (1830085 ips)

Hardware utilisé pour le dev :

# lshw
local
    description: Desktop Computer
    product: Precision 3660 (0A9F)
    vendor: Dell Inc.
...
  *-core
       description: Motherboard
       product: 0PRR48
       vendor: Dell Inc.
...
     *-firmware
          description: BIOS
          vendor: Dell Inc.
          physical id: 1
          version: 2.12.0
          date: 01/30/2024
...
     *-cpu
          description: CPU
          product: 13th Gen Intel(R) Core(TM) i9-13900
          vendor: Intel Corp.
          physical id: 400
          bus info: cpu@0
          version: 6.183.1
...
     *-memory
....
        *-bank:0
             description: DIMM Synchronous 5600 MHz (0.2 ns)
             product: HMCG88AGBUA081N
...
        *-bank:1
             description: DIMM Synchronous 5600 MHz (0.2 ns)
             product: HMCG88AGBUA081N
....
        *-bank:2
             description: DIMM Synchronous 4800 MHz (0.2 ns)
             product: CT32G48C40U5.M16A1
             vendor: Micron Technology
....
        *-bank:3
             description: DIMM Synchronous 4800 MHz (0.2 ns)
             product: CT32G48C40U5.M16A1
             vendor: Micron Technology
....
        *-pci:0
             description: PCI bridge
             product: Alder Lake-S PCH PCI Express Root Port #25
....
           *-network:0
                description: Ethernet interface
                product: 82576 Gigabit Network Connection
                vendor: Intel Corporation
                physical id: 0
                bus info: pci@0000:01:00.0
                logical name: enp1s0f0
....
        *-network DISABLED
             description: Ethernet interface
             product: Ethernet Connection (17) I219-LM
             vendor: Intel Corporation
             physical id: 1f.6
             bus info: pci@0000:00:1f.6
             logical name: enp0s31f6
...
  *-nvme0
       description: NVMe device
       product: Samsung SSD 990 PRO 2TB
       physical id: 2
       logical name: /dev/nvme0
       version: 4B2QJXD7
....
  *-nvme1
       description: NVMe device
       product: Samsung SSD 9100 PRO 2TB
       physical id: 3
       logical name: /dev/nvme1
       version: 0B2QNXH7
....
  *-nvme2
       description: NVMe device
       product: Samsung SSD 9100 PRO 2TB
       physical id: 4
       logical name: /dev/nvme2
       version: 0B2QNXH7

En résumé :

• DELL Precision 3660 (Nvidia T1000, 4GB) :
  • 124 Go de RAM .
  • 32 x 13th Gen Intel Core i9-13900 .
  • 2 x Samsung SSD 990 PRO 2TB .
  • 1 x Samsung SSD 990 PRO 2TB .
  • 4TB 5400rpm SATA 3.5" HDD.
  • 1 x PCIe Intel 82576 Gigabit Network Connection.

Configuration à 4100 Euros chez DELL, pour moi c’est le minimum.

Je sais pas si c’est conseillé mais j’ai supprimé des fichiers dans /var/cache/uptrack/.

# du -sh /var/cache/uptrack/
2.1G    /var/cache/uptrack/
# yum clean all
44 files removed
# du -sh /var/cache/uptrack/
2.1G    /var/cache/uptrack/
# ls -l /var/cache/uptrack/Linux/x86_64/
total 0
drwxr-xr-x. 3 root root 49 Feb 14  2023 5.4.17-2102.201.3.el8uek.x86_64
drwxr-xr-x. 3 root root 49 Feb 14  2023 5.4.17-2136.316.7.el8uek.x86_64
drwxr-xr-x  3 root root 49 Nov  9  2023 5.4.17-2136.324.5.3.el8uek.x86_64
drwxr-xr-x  3 root root 48 Jun  6  2024 5.4.17-2136.331.7.el8uek.x86_64
drwxr-xr-x  3 root root 48 Nov 12  2024 5.4.17-2136.336.5.1.el8uek.x86_64
drwxr-xr-x  3 root root 49 Jan  8  2025 5.4.17-2136.337.5.1.el8uek.x86_64
# rm -rf /var/cache/uptrack/Linux/x86_64/5.4.17-2102.201.3.el8uek.x86_64/ /var/cache/uptrack/Linux/x86_64/5.4.17-2136.316.7.el8uek.x86_64/  /var/cache/uptrack/Linux/x86_64/5.4.17-2136.324.5.3.el8uek.x86_64/ /var/cache/uptrack/Linux/x86_64/5.4.17-2136.331.7.el8uek.x86_64/ /var/cache/uptrack/Linux/x86_64/5.4.17-2136.336.5.1.el8uek.x86_64/
# du -sh /var/cache/uptrack/
399M    /var/cache/uptrack/

J’ai gardé seulement les fichiers du noyau en cours ‘5.4.17-2136.337.5.1.el8uek.x86_64’ .
J’ai gagné 2 Go.

J’ai pas essayé la commande :

uptrack-remove —all

En bref:

$ sudo apt-get remove --purge '^nvidia-.*'

$ sudo apt-get remove --purge '^libnvidia-.*'

$ sudo apt-get remove --purge '^cuda-.*'

$ sudo apt-get install linux-headers-$(uname -r)

$ cat /etc/os-release | grep "PRETTY_NAME"
PRETTY_NAME="Ubuntu 24.04.3 LTS"

$ wget https://developer.download.nvidia.com/compute/cuda/repos/ubuntu2404/x86_64/cuda-keyring_1.1-1_all.deb

$ sudo dpkg -i cuda-keyring_1.1-1_all.deb

$ sudo apt-get update

$ sudo apt-get -y install cuda-toolkit-13-0

$ sudo apt-get install -y nvidia-open

$ nvidia-smi
Wed Aug 13 10:40:03 2025
+-----------------------------------------------------------------------------------------+
| NVIDIA-SMI 580.65.06              Driver Version: 580.65.06      CUDA Version: 13.0     |
+-----------------------------------------+------------------------+----------------------+
| GPU  Name                 Persistence-M | Bus-Id          Disp.A | Volatile Uncorr. ECC |
| Fan  Temp   Perf          Pwr:Usage/Cap |           Memory-Usage | GPU-Util  Compute M. |
|                                         |                        |               MIG M. |
|=========================================+========================+======================|
|   0  NVIDIA T1000                   Off |   00000000:00:10.0 Off |                  N/A |
| 54%   51C    P0            N/A  /   50W |       0MiB /   4096MiB |      0%      Default |
|                                         |                        |                  N/A |
+-----------------------------------------+------------------------+----------------------+

+-----------------------------------------------------------------------------------------+
| Processes:                                                                              |
|  GPU   GI   CI              PID   Type   Process name                        GPU Memory |
|        ID   ID                                                               Usage      |
|=========================================================================================|
|  No running processes found                                                             |
+-----------------------------------------------------------------------------------------+

Pas de problème …

A tester le bouton reset pendant 15 sec :

Pour fixer j’ai du faire :

# apt update --allow-releaseinfo-change 

A suivre.

J’ai l’erreur “Detected Hardware Unit Hang:”

# journalctl --since=2025-08-13 | grep "e1000e" | more
Journal file /var/log/journal/99b0a514478f45a993f76cd1a02892ef/system@000622d8a1539478-fcd8335a7d591443.journal~ is truncated, ignoring file.
Aug 13 12:12:58 local kernel: e1000e: Intel(R) PRO/1000 Network Driver
Aug 13 12:12:58 local kernel: e1000e: Copyright(c) 1999 - 2015 Intel Corporation.
Aug 13 12:12:58 local kernel: e1000e 0000:00:1f.6: Interrupt Throttling Rate (ints/sec) set to dynamic conservative mode
Aug 13 12:12:58 local kernel: e1000e 0000:00:1f.6 0000:00:1f.6 (uninitialized): registered PHC clock
Aug 13 12:12:58 local kernel: e1000e 0000:00:1f.6 eth0: (PCI Express:2.5GT/s:Width x1) 4c:d7:17:84:3a:65
Aug 13 12:12:58 local kernel: e1000e 0000:00:1f.6 eth0: Intel(R) PRO/1000 Network Connection
Aug 13 12:12:58 local kernel: e1000e 0000:00:1f.6 eth0: MAC: 15, PHY: 12, PBA No: FFFFFF-0FF
Aug 13 12:12:58 local kernel: e1000e 0000:02:00.0: enabling device (0000 -> 0002)
Aug 13 12:12:58 local kernel: e1000e 0000:02:00.0: Interrupt Throttling Rate (ints/sec) set to dynamic conservative mode
Aug 13 12:12:58 local kernel: e1000e 0000:02:00.0 eth1: (PCI Express:2.5GT/s:Width x1) 00:1b:21:05:05:4f
Aug 13 12:12:58 local kernel: e1000e 0000:02:00.0 eth1: Intel(R) PRO/1000 Network Connection
Aug 13 12:12:58 local kernel: e1000e 0000:02:00.0 eth1: MAC: 1, PHY: 4, PBA No: D50854-003
Aug 13 12:12:58 local kernel: e1000e 0000:02:00.0 enp2s0: renamed from eth1
Aug 13 12:12:58 local kernel: e1000e 0000:00:1f.6 enp0s31f6: renamed from eth0
Aug 13 12:13:02 local kernel: e1000e 0000:00:1f.6 enp0s31f6: entered allmulticast mode
Aug 13 12:13:02 local kernel: e1000e 0000:00:1f.6 enp0s31f6: entered promiscuous mode
Aug 13 12:13:05 local kernel: e1000e 0000:00:1f.6 enp0s31f6: NIC Link is Up 1000 Mbps Full Duplex, Flow Control: None
Aug 13 12:22:21 local kernel: e1000e: Intel(R) PRO/1000 Network Driver
Aug 13 12:22:21 local kernel: e1000e: Copyright(c) 1999 - 2015 Intel Corporation.
Aug 13 12:22:21 local kernel: e1000e 0000:00:1f.6: Interrupt Throttling Rate (ints/sec) set to dynamic conservative mode
Aug 13 12:22:21 local kernel: e1000e 0000:00:1f.6 0000:00:1f.6 (uninitialized): registered PHC clock
Aug 13 12:22:21 local kernel: e1000e 0000:00:1f.6 eth0: (PCI Express:2.5GT/s:Width x1) 4c:d7:17:84:3a:65
Aug 13 12:22:21 local kernel: e1000e 0000:00:1f.6 eth0: Intel(R) PRO/1000 Network Connection
Aug 13 12:22:21 local kernel: e1000e 0000:00:1f.6 eth0: MAC: 15, PHY: 12, PBA No: FFFFFF-0FF
Aug 13 12:22:21 local kernel: e1000e 0000:02:00.0: enabling device (0000 -> 0002)
Aug 13 12:22:21 local kernel: e1000e 0000:02:00.0: Interrupt Throttling Rate (ints/sec) set to dynamic conservative mode
Aug 13 12:22:21 local kernel: e1000e 0000:02:00.0 eth1: (PCI Express:2.5GT/s:Width x1) 00:1b:21:05:05:4f
Aug 13 12:22:21 local kernel: e1000e 0000:02:00.0 eth1: Intel(R) PRO/1000 Network Connection
Aug 13 12:22:21 local kernel: e1000e 0000:02:00.0 eth1: MAC: 1, PHY: 4, PBA No: D50854-003
Aug 13 12:22:21 local kernel: e1000e 0000:00:1f.6 enp0s31f6: renamed from eth0
Aug 13 12:22:21 local kernel: e1000e 0000:02:00.0 enp2s0: renamed from eth1
Aug 13 12:22:25 local kernel: e1000e 0000:00:1f.6 enp0s31f6: entered allmulticast mode
Aug 13 12:22:25 local kernel: e1000e 0000:00:1f.6 enp0s31f6: entered promiscuous mode
Aug 13 12:22:28 local kernel: e1000e 0000:00:1f.6 enp0s31f6: NIC Link is Up 1000 Mbps Full Duplex, Flow Control: None
Aug 14 16:05:00 local kernel: e1000e 0000:00:1f.6 enp0s31f6: Detected Hardware Unit Hang:
Aug 14 16:05:02 local kernel: e1000e 0000:00:1f.6 enp0s31f6: Detected Hardware Unit Hang:
Aug 14 16:05:04 local kernel: e1000e 0000:00:1f.6 enp0s31f6: Detected Hardware Unit Hang:
Aug 14 16:05:06 local kernel: e1000e 0000:00:1f.6 enp0s31f6: Detected Hardware Unit Hang:
Aug 14 16:05:08 local kernel: e1000e 0000:00:1f.6 enp0s31f6: Detected Hardware Unit Hang:
Aug 14 16:05:10 local kernel: e1000e 0000:00:1f.6 enp0s31f6: Detected Hardware Unit Hang:
Aug 14 16:05:12 local kernel: e1000e 0000:00:1f.6 enp0s31f6: Detected Hardware Unit Hang:
Aug 14 16:05:14 local kernel: e1000e 0000:00:1f.6 enp0s31f6: Detected Hardware Unit Hang:
Aug 14 16:05:16 local kernel: e1000e 0000:00:1f.6 enp0s31f6: Detected Hardware Unit Hang:
Aug 14 16:05:18 local kernel: e1000e 0000:00:1f.6 enp0s31f6: Detected Hardware Unit Hang:

Mon kernel :

# uname -a
Linux local 6.14.11-1-pve #1 SMP PREEMPT_DYNAMIC PMX 6.14.11-1 (2025-08-26T16:06Z) x86_64 GNU/Linux
# cat /etc/os-release | grep "PRETTY"
PRETTY_NAME="Debian GNU/Linux 13 (trixie)"

La configuration de la carte :

# ethtool -k  enp0s31f6
Features for enp0s31f6:
rx-checksumming: on
tx-checksumming: on
        tx-checksum-ipv4: off [fixed]
        tx-checksum-ip-generic: on
        tx-checksum-ipv6: off [fixed]
        tx-checksum-fcoe-crc: off [fixed]
        tx-checksum-sctp: off [fixed]
scatter-gather: on
        tx-scatter-gather: on
        tx-scatter-gather-fraglist: off [fixed]
tcp-segmentation-offload: on
        tx-tcp-segmentation: on
        tx-tcp-ecn-segmentation: off [fixed]
        tx-tcp-mangleid-segmentation: off
        tx-tcp6-segmentation: on
generic-segmentation-offload: on
generic-receive-offload: on
large-receive-offload: off [fixed]
rx-vlan-offload: on
tx-vlan-offload: on
ntuple-filters: off [fixed]
receive-hashing: on
highdma: on [fixed]
rx-vlan-filter: off [fixed]
vlan-challenged: off [fixed]
tx-gso-robust: off [fixed]
tx-fcoe-segmentation: off [fixed]
tx-gre-segmentation: off [fixed]
tx-gre-csum-segmentation: off [fixed]
tx-ipxip4-segmentation: off [fixed]
tx-ipxip6-segmentation: off [fixed]
tx-udp_tnl-segmentation: off [fixed]
tx-udp_tnl-csum-segmentation: off [fixed]
tx-gso-partial: off [fixed]
tx-tunnel-remcsum-segmentation: off [fixed]
tx-sctp-segmentation: off [fixed]
tx-esp-segmentation: off [fixed]
tx-udp-segmentation: off [fixed]
tx-gso-list: off [fixed]
tx-nocache-copy: off
loopback: off [fixed]
rx-fcs: off
rx-all: off
tx-vlan-stag-hw-insert: off [fixed]
rx-vlan-stag-hw-parse: off [fixed]
rx-vlan-stag-filter: off [fixed]
l2-fwd-offload: off [fixed]
hw-tc-offload: off [fixed]
esp-hw-offload: off [fixed]
esp-tx-csum-hw-offload: off [fixed]
rx-udp_tunnel-port-offload: off [fixed]
tls-hw-tx-offload: off [fixed]
tls-hw-rx-offload: off [fixed]
rx-gro-hw: off [fixed]
tls-hw-record: off [fixed]
rx-gro-list: off
macsec-hw-offload: off [fixed]
rx-udp-gro-forwarding: off
hsr-tag-ins-offload: off [fixed]
hsr-tag-rm-offload: off [fixed]
hsr-fwd-offload: off [fixed]
hsr-dup-offload: off [fixed]

Sur un forum j’ai vu : https://forum.proxmox.com/threads/intel-nic-e1000e-hardware-unit-hang.106001/

ethtool -K eth0 gso off gro off tso off tx off rx off rxvlan off txvlan off

Il me faudrait remplacer eth0 par enp0s31f6 …

Et sur : https://forum.proxmox.com/threads/help-eno1-detected-hardware-unit-hang.117305/ , modifier /etc/networking/interfaces .

iface eno1 inet manual
post-up /usr/sbin/ethtool -K $IFACE tso off gso off 2> /dev/null

A suivre …

Les commandes :

# journalctl --disk-usage
Journal file /var/log/journal/99b0a514478f45a993f76cd1a02892ef/system@000622d8a1539478-fcd8335a7d591443.journal~ is truncated, ignoring file.
Archived and active journals take up 3.7G in the file system.
# journalctl --verify
...
# journalctl --flush
# journalctl --disk-usage
Journal file /var/log/journal/99b0a514478f45a993f76cd1a02892ef/system@000622d8a1539478-fcd8335a7d591443.journal~ is truncated, ignoring file.
Archived and active journals take up 3.7G in the file system.
root@local:~# journalctl --vacuum-size=100M
# journalctl --disk-usage
Archived and active journals take up 77.9M in the file system.

Première ligne :

# journalctl -b | head -1
Sep 03 15:46:30 local kernel: Linux version 6.14.11-1-pve (tom@alp1) (gcc (Debian 14.2.0-19) 14.2.0, GNU ld (GNU Binutils for Debian) 2.44) #1 SMP PREEMPT_DYNAMIC PMX 6.14.11-1 (2025-08-26T16:06Z) ()

Cela m’a permis de supprimer les logs de crash de la carte réseau.