GPU components

• accelerator-nvidia-clock: Monitors NVIDIA GPU clock events of all GPUs, such as HW Slowdown events.
• accelerator-nvidia-clock-speed: Tracks the per-GPU clock speed.
• accelerator-nvidia-ecc: Tracks the NVIDIA per-GPU ECC errors.
• accelerator-nvidia-error: Tracks NVIDIA GPU errors real-time in the SMI queries -- likely requires host restarts.
• accelerator-nvidia-error-sxid: Tracks the NVIDIA GPU SXid errors scanning the dmesg -- see fabric manager documentation.
• accelerator-nvidia-error-xid: Tracks the NVIDIA GPU Xid errors scanning the dmesg and using the NVIDIA Management Library (NVML) -- see Xid messages.
• accelerator-nvidia-fabric-manager: Tracks the fabric manager version and its activeness.
• accelerator-nvidia-infiniband: Monitors the infiniband status of the system. Optional, enabled if the host has NVIDIA GPUs.
• accelerator-nvidia-info: Serves relatively static information about the NVIDIA accelerators (e.g., GPU product names).
• accelerator-nvidia-memory: Monitors the NVIDIA per-GPU memory usage.
• accelerator-nvidia-gpm: Monitors the NVIDIA per-GPU GPM metrics.
• accelerator-nvidia-nvlink: Monitors the NVIDIA per-GPU nvlink devices.
• accelerator-nvidia-peermem: Monitors the peermem module status. Optional, enabled if the host has NVIDIA GPUs.
• accelerator-nvidia-power: Tracks the NVIDIA per-GPU power usage.
• accelerator-nvidia-processes: Tracks the NVIDIA per-GPU processes.
• accelerator-nvidia-temperature: Tracks the NVIDIA per-GPU temperatures.
• accelerator-nvidia-utilization: Tracks the NVIDIA per-GPU utilization.

General Hardware components

• cpu: Tracks the combined usage of all CPUs (not per-CPU).
• disk: Tracks the disk usage of all the mount points specified in the configuration.
• memory: Tracks the memory usage of the host.
• network-latency: Tracks global network connectivity statistics.
• power-supply: Tracks the power supply/usage on the host.

System components

• info: Provides static information about the host (e.g., labels, IDs).
• os: Queries the host OS information (e.g., kernel version).
• systemd: Tracks the systemd state and unit files.
• dmesg: Scans and watches dmesg outputs for errors,, as specified in the configuration (e.g., regex match NVIDIA GPU errors).
• file-descriptor: Tracks the number of file descriptors used on the host.

Misc. components

• containerd-pod: Tracks the current pods from the containerd CRI.
• k8s-pod: Tracks the current pods from the kubelet read-only port.
• docker-container: Tracks the current containers from the docker runtime.
• tailscale: Tracks the tailscale state (e.g., version) if available.