From 81581f9719bc56f01d5aa08952671d65fda9867a Mon Sep 17 00:00:00 2001
From: Daniel Baumann <daniel.baumann@progress-linux.org>
Date: Mon, 8 May 2023 18:27:08 +0200
Subject: Merging upstream version 1.39.0.

Signed-off-by: Daniel Baumann <daniel.baumann@progress-linux.org>
---
 collectors/python.d.plugin/nvidia_smi/README.md | 98 +++++++++++++++++++++++--
 1 file changed, 93 insertions(+), 5 deletions(-)

(limited to 'collectors/python.d.plugin/nvidia_smi/README.md')

diff --git a/collectors/python.d.plugin/nvidia_smi/README.md b/collectors/python.d.plugin/nvidia_smi/README.md
index ce5473c26..7d45289a4 100644
--- a/collectors/python.d.plugin/nvidia_smi/README.md
+++ b/collectors/python.d.plugin/nvidia_smi/README.md
@@ -4,16 +4,13 @@ custom_edit_url: "https://github.com/netdata/netdata/edit/master/collectors/pyth
 sidebar_label: "nvidia_smi-python.d.plugin"
 learn_status: "Published"
 learn_topic_type: "References"
-learn_rel_path: "References/Collectors references/Devices"
+learn_rel_path: "Integrations/Monitor/Devices"
 -->
 
-# Nvidia GPU monitoring with Netdata
+# Nvidia GPU collector
 
 Monitors performance metrics (memory usage, fan speed, pcie bandwidth utilization, temperature, etc.) using `nvidia-smi` cli tool.
 
-> **Warning**: this collector does not work when the Netdata Agent is [running in a container](https://github.com/netdata/netdata/blob/master/packaging/docker/README.md).
-
-
 ## Requirements and Notes
 
 -   You must have the `nvidia-smi` tool installed and your NVIDIA GPU(s) must support the tool. Mostly the newer high end models used for AI / ML and Crypto or Pro range, read more about [nvidia_smi](https://developer.nvidia.com/nvidia-system-management-interface).
@@ -67,3 +64,94 @@ exclude_zero_memory_users : yes
 ```
 
 
+### Troubleshooting
+
+To troubleshoot issues with the `nvidia_smi` module, run the `python.d.plugin` with the debug option enabled. The 
+output will give you the output of the data collection job or error messages on why the collector isn't working.
+
+First, navigate to your plugins directory, usually they are located under `/usr/libexec/netdata/plugins.d/`. If that's 
+not the case on your system, open `netdata.conf` and look for the setting `plugins directory`. Once you're in the 
+plugin's directory, switch to the `netdata` user.
+
+```bash
+cd /usr/libexec/netdata/plugins.d/
+sudo su -s /bin/bash netdata
+```
+
+Now you can manually run the `nvidia_smi` module in debug mode:
+
+```bash
+./python.d.plugin nvidia_smi debug trace
+```
+
+## Docker
+
+GPU monitoring in a docker container is possible with [nvidia-container-toolkit](https://docs.nvidia.com/datacenter/cloud-native/container-toolkit/install-guide.html) installed on the host system, and `gcompat` added to the `NETDATA_EXTRA_APK_PACKAGES` environment variable.
+
+Sample `docker-compose.yml`
+```yaml
+version: '3'
+services:
+  netdata:
+    image: netdata/netdata
+    container_name: netdata
+    hostname: example.com # set to fqdn of host
+    ports:
+      - 19999:19999
+    restart: unless-stopped
+    cap_add:
+      - SYS_PTRACE
+    security_opt:
+      - apparmor:unconfined
+    environment:
+      - NETDATA_EXTRA_APK_PACKAGES=gcompat
+    volumes:
+      - netdataconfig:/etc/netdata
+      - netdatalib:/var/lib/netdata
+      - netdatacache:/var/cache/netdata
+      - /etc/passwd:/host/etc/passwd:ro
+      - /etc/group:/host/etc/group:ro
+      - /proc:/host/proc:ro
+      - /sys:/host/sys:ro
+      - /etc/os-release:/host/etc/os-release:ro
+    deploy:
+      resources:
+        reservations:
+          devices:
+          - driver: nvidia
+            count: all
+            capabilities: [gpu]
+
+volumes:
+  netdataconfig:
+  netdatalib:
+  netdatacache:
+```
+
+Sample `docker run`
+```yaml
+docker run -d --name=netdata \
+  -p 19999:19999 \
+  -e NETDATA_EXTRA_APK_PACKAGES=gcompat \
+  -v netdataconfig:/etc/netdata \
+  -v netdatalib:/var/lib/netdata \
+  -v netdatacache:/var/cache/netdata \
+  -v /etc/passwd:/host/etc/passwd:ro \
+  -v /etc/group:/host/etc/group:ro \
+  -v /proc:/host/proc:ro \
+  -v /sys:/host/sys:ro \
+  -v /etc/os-release:/host/etc/os-release:ro \
+  --restart unless-stopped \
+  --cap-add SYS_PTRACE \
+  --security-opt apparmor=unconfined \
+  --gpus all \
+  netdata/netdata
+```
+
+### Docker Troubleshooting
+To troubleshoot `nvidia-smi` in a docker container, first confirm that `nvidia-smi` is working on the host system. If that is working correctly, run `docker exec -it netdata nvidia-smi` to confirm it's working within the docker container. If `nvidia-smi` is fuctioning both inside and outside of the container, confirm that `nvidia-smi: yes` is uncommented in `python.d.conf`.
+```bash
+docker exec -it netdata bash
+cd /etc/netdata
+./edit-config python.d.conf
+```
-- 
cgit v1.2.3