query

type MemoryErrorManagementCapabilities struct {
	// (If supported) GPU can limit the impact of uncorrectable ECC errors to GPU applications.
	// Existing/new workloads will run unaffected, both in terms of accuracy and performance.
	// Thus, does not require a GPU reset when memory errors occur.
	//
	// Note thtat there are some rarer cases, where uncorrectable errors are still uncontained
	// thus impacting all other workloads being procssed in the GPU.
	//
	// ref. https://docs.nvidia.com/deploy/a100-gpu-mem-error-mgmt/index.html#error-containments
	ErrorContainment bool `json:"error_containment"`

	// (If supported) GPU can dynamically mark the page containing uncorrectable errors
	// as unusable, and any existing or new workloads will not be allocating this page.
	//
	// Thus, does not require a GPU reset to recover from most uncorrectable ECC errors.
	//
	// ref. https://docs.nvidia.com/deploy/a100-gpu-mem-error-mgmt/index.html#dynamic-page-offlining
	DynamicPageOfflining bool `json:"dynamic_page_offlining"`

	// (If supported) GPU can replace degrading memory cells with spare ones
	// to avoid offlining regions of memory. And the row remapping is different
	// from dynamic page offlining which is fixed at a hardware level.
	//
	// The row remapping requires a GPU reset to take effect.
	//
	// even for "NVIDIA GeForce RTX 4090", nvml returns no error
	// thus "NVML.Supported" is not a reliable way to check if row remapping is supported
	// thus we track a separate boolean value based on the GPU product name
	//
	// ref. https://docs.nvidia.com/deploy/a100-gpu-mem-error-mgmt/index.html#row-remapping
	RowRemapping bool `json:"row_remapping"`

	// Message contains the message to the user about the memory error management capabilities.
	Message string `json:"message,omitempty"`
}

type Op struct {
	// contains filtered or unexported fields
}

type OpOption func(*Op)

type Output struct {
	// Time is the time when the query is executed.
	Time time.Time `json:"time"`

	// GPU device count from the /dev directory.
	GPUDeviceCount int `json:"gpu_device_count"`

	LsmodPeermem       *peermem.LsmodPeermemModuleOutput `json:"lsmod_peermem,omitempty"`
	LsmodPeermemErrors []string                          `json:"lsmod_peermem_errors,omitempty"`

	NVML       *nvml.Output `json:"nvml,omitempty"`
	NVMLErrors []string     `json:"nvml_errors,omitempty"`

	MemoryErrorManagementCapabilities MemoryErrorManagementCapabilities `json:"memory_error_management_capabilities,omitempty"`
}