Adding upstream version 1.46.3.upstream

Signed-off-by: Daniel Baumann <daniel.baumann@progress-linux.org>

4 files changed, 247 insertions, 0 deletions

diff --git a/src/collectors/python.d.plugin/nvidia_smi/README.md b/src/collectors/python.d.plugin/nvidia_smi/README.md
new file mode 100644
index 000000000..240b65af3
--- /dev/null
+++ b/src/collectors/python.d.plugin/nvidia_smi/README.md
@@ -0,0 +1,81 @@
+<!--
+title: "Nvidia GPU monitoring with Netdata"
+custom_edit_url: "https://github.com/netdata/netdata/edit/master/src/collectors/python.d.plugin/nvidia_smi/README.md"
+sidebar_label: "nvidia_smi-python.d.plugin"
+learn_status: "Published"
+learn_topic_type: "References"
+learn_rel_path: "Integrations/Monitor/Devices"
+-->
+
+# Nvidia GPU collector
+
+Monitors performance metrics (memory usage, fan speed, pcie bandwidth utilization, temperature, etc.) using `nvidia-smi` cli tool.
+
+## Requirements
+
+-   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).
+-   Enable this plugin, as it's disabled by default due to minor performance issues:
+    ```bash
+    cd /etc/netdata   # Replace this path with your Netdata config directory, if different
+    sudo ./edit-config python.d.conf
+    ```
+    Remove the '#' before nvidia_smi so it reads: `nvidia_smi: yes`.
+-   On some systems when the GPU is idle the `nvidia-smi` tool unloads and there is added latency again when it is next queried. If you are running GPUs under constant workload this isn't likely to be an issue.
+
+If using Docker, see [Netdata Docker container with NVIDIA GPUs monitoring](https://github.com/netdata/netdata/tree/master/packaging/docker#with-nvidia-gpus-monitoring).  
+
+## Charts
+
+It produces the following charts:
+
+-   PCI Express Bandwidth Utilization in `KiB/s`
+-   Fan Speed in `percentage`
+-   GPU Utilization in `percentage`
+-   Memory Bandwidth Utilization in `percentage`
+-   Encoder/Decoder Utilization in `percentage`
+-   Memory Usage in `MiB`
+-   Temperature in `celsius`
+-   Clock Frequencies in `MHz`
+-   Power Utilization in `Watts`
+-   Memory Used by Each Process in `MiB`
+-   Memory Used by Each User in `MiB`
+-   Number of User on GPU in `num`
+
+## Configuration
+
+Edit the `python.d/nvidia_smi.conf` configuration file using `edit-config` from the Netdata [config
+directory](/docs/netdata-agent/configuration/README.md), which is typically at `/etc/netdata`.
+
+```bash
+cd /etc/netdata   # Replace this path with your Netdata config directory, if different
+sudo ./edit-config python.d/nvidia_smi.conf
+```
+
+Sample:
+
+```yaml
+loop_mode    : yes
+poll_seconds : 1
+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
+```
diff --git a/src/collectors/python.d.plugin/nvidia_smi/metadata.yaml b/src/collectors/python.d.plugin/nvidia_smi/metadata.yaml
new file mode 100644
index 000000000..0b049d31b
--- /dev/null
+++ b/src/collectors/python.d.plugin/nvidia_smi/metadata.yaml
@@ -0,0 +1,166 @@
+# This collector will not appear in documentation, as the go version is preferred,
+# /src/go/collectors/go.d.plugin/modules/nvidia_smi/README.md
+#
+# meta:
+#   plugin_name: python.d.plugin
+#   module_name: nvidia_smi
+#   monitored_instance:
+#     name: python.d nvidia_smi
+#     link: ''
+#     categories: []
+#     icon_filename: ''
+#   related_resources:
+#     integrations:
+#       list: []
+#   info_provided_to_referring_integrations:
+#     description: ''
+#   keywords: []
+#   most_popular: false
+# overview:
+#   data_collection:
+#     metrics_description: ''
+#     method_description: ''
+#   supported_platforms:
+#     include: []
+#     exclude: []
+#   multi_instance: true
+#   additional_permissions:
+#     description: ''
+#   default_behavior:
+#     auto_detection:
+#       description: ''
+#     limits:
+#       description: ''
+#     performance_impact:
+#       description: ''
+# setup:
+#   prerequisites:
+#     list: []
+#   configuration:
+#     file:
+#       name: ''
+#       description: ''
+#     options:
+#       description: ''
+#       folding:
+#         title: ''
+#         enabled: true
+#       list: []
+#     examples:
+#       folding:
+#         enabled: true
+#         title: ''
+#       list: []
+# troubleshooting:
+#   problems:
+#     list: []
+# alerts: []
+# metrics:
+#   folding:
+#     title: Metrics
+#     enabled: false
+#   description: ""
+#   availability: []
+#   scopes:
+#   - name: GPU
+#     description: ""
+#     labels: []
+#     metrics:
+#     - name: nvidia_smi.pci_bandwidth
+#       description: PCI Express Bandwidth Utilization
+#       unit: "KiB/s"
+#       chart_type: area
+#       dimensions:
+#       - name: rx
+#       - name: tx
+#     - name: nvidia_smi.pci_bandwidth_percent
+#       description: PCI Express Bandwidth Percent
+#       unit: "percentage"
+#       chart_type: area
+#       dimensions:
+#       - name: rx_percent
+#       - name: tx_percent
+#     - name: nvidia_smi.fan_speed
+#       description: Fan Speed
+#       unit: "percentage"
+#       chart_type: line
+#       dimensions:
+#       - name: speed
+#     - name: nvidia_smi.gpu_utilization
+#       description: GPU Utilization
+#       unit: "percentage"
+#       chart_type: line
+#       dimensions:
+#       - name: utilization
+#     - name: nvidia_smi.mem_utilization
+#       description: Memory Bandwidth Utilization
+#       unit: "percentage"
+#       chart_type: line
+#       dimensions:
+#       - name: utilization
+#     - name: nvidia_smi.encoder_utilization
+#       description: Encoder/Decoder Utilization
+#       unit: "percentage"
+#       chart_type: line
+#       dimensions:
+#       - name: encoder
+#       - name: decoder
+#     - name: nvidia_smi.memory_allocated
+#       description: Memory Usage
+#       unit: "MiB"
+#       chart_type: stacked
+#       dimensions:
+#       - name: free
+#       - name: used
+#     - name: nvidia_smi.bar1_memory_usage
+#       description: Bar1 Memory Usage
+#       unit: "MiB"
+#       chart_type: stacked
+#       dimensions:
+#       - name: free
+#       - name: used
+#     - name: nvidia_smi.temperature
+#       description: Temperature
+#       unit: "celsius"
+#       chart_type: line
+#       dimensions:
+#       - name: temp
+#     - name: nvidia_smi.clocks
+#       description: Clock Frequencies
+#       unit: "MHz"
+#       chart_type: line
+#       dimensions:
+#       - name: graphics
+#       - name: video
+#       - name: sm
+#       - name: mem
+#     - name: nvidia_smi.power
+#       description: Power Utilization
+#       unit: "Watts"
+#       chart_type: line
+#       dimensions:
+#       - name: power
+#     - name: nvidia_smi.power_state
+#       description: Power State
+#       unit: "state"
+#       chart_type: line
+#       dimensions:
+#       - name: a dimension per {power_state}
+#     - name: nvidia_smi.processes_mem
+#       description: Memory Used by Each Process
+#       unit: "MiB"
+#       chart_type: stacked
+#       dimensions:
+#       - name: a dimension per process
+#     - name: nvidia_smi.user_mem
+#       description: Memory Used by Each User
+#       unit: "MiB"
+#       chart_type: stacked
+#       dimensions:
+#       - name: a dimension per user
+#     - name: nvidia_smi.user_num
+#       description: Number of User on GPU
+#       unit: "num"
+#       chart_type: line
+#       dimensions:
+#       - name: users
diff --git a/collectors/python.d.plugin/nvidia_smi/nvidia_smi.chart.py b/src/collectors/python.d.plugin/nvidia_smi/nvidia_smi.chart.py
index 556a61435..556a61435 100644
--- a/collectors/python.d.plugin/nvidia_smi/nvidia_smi.chart.py
+++ b/src/collectors/python.d.plugin/nvidia_smi/nvidia_smi.chart.py
diff --git a/collectors/python.d.plugin/nvidia_smi/nvidia_smi.conf b/src/collectors/python.d.plugin/nvidia_smi/nvidia_smi.conf
index 3d2a30d41..3d2a30d41 100644
--- a/collectors/python.d.plugin/nvidia_smi/nvidia_smi.conf
+++ b/src/collectors/python.d.plugin/nvidia_smi/nvidia_smi.conf