error

Documentation

Overview

Package error implements NVIDIA GPU driver error detector.

Index

• Constants
• Variables
• func New(ctx context.Context, cfg Config) components.Component
• type Config
  • func ParseConfig(b any, db *sql.DB) (*Config, error)
  • func (cfg Config) Validate() error
• type Output
  • func ParseOutputJSON(data []byte) (*Output, error)
  • func ParseStateError(m map[string]string) (*Output, error)
  • func ParseStatesToOutput(states ...components.State) (*Output, error)
  • func ToOutput(i *nvidia_query.Output) *Output
  • func (o *Output) Evaluate() (string, bool, error)
  • func (o *Output) JSON() ([]byte, error)
  • func (o *Output) States() ([]components.State, error)

Constants

const (
	Name        = "accelerator-nvidia-error"
	Description = "Tracks NVIDIA GPU errors real-time in the SMI queries -- likely requires host restarts."
)

const (
	StateNameError = "error"

	StateKeyErrorData           = "data"
	StateKeyErrorEncoding       = "encoding"
	StateValueErrorEncodingJSON = "json"
)

Variables

var Tags = []string{"nvidia", "gpu", "error"}

Functions

func New

func New(ctx context.Context, cfg Config) components.Component

Types

type Config

type Config struct {
	Query query_config.Config `json:"query"`
}

func ParseConfig

func ParseConfig(b any, db *sql.DB) (*Config, error)

func (Config) Validate

func (cfg Config) Validate() error

type Output

type Output struct {
	Errors []string `json:"errors"`
}

func ParseOutputJSON

func ParseOutputJSON(data []byte) (*Output, error)

func ParseStateError

func ParseStateError(m map[string]string) (*Output, error)

func ParseStatesToOutput

func ParseStatesToOutput(states ...components.State) (*Output, error)

func ToOutput

func ToOutput(i *nvidia_query.Output) *Output

func (*Output) Evaluate

func (o *Output) Evaluate() (string, bool, error)

Returns the output evaluation reason and its healthy-ness.

func (*Output) JSON

func (o *Output) JSON() ([]byte, error)

func (*Output) States

func (o *Output) States() ([]components.State, error)