Struct Invocation System Stats | NVIDIA NeMo Fabric

Generated from cargo doc --no-deps -p nemo-fabric-core.

pub struct InvocationSystemStats {
    pub collected_groups: Vec<SystemStatsMetricGroup>,
    pub elapsed_seconds: f64,
    pub before: ResourceObservation,
    pub after: ResourceObservation,
    pub cpu_time_seconds_estimate: Option<f64>,
    pub cgroup: Option<CgroupStats>,
    pub sampled: Option<SampleSummary>,
}

System measurements around one invocation, collected inside the executing runner. Process-tree observations cover its adapter host and descendants, excluding the orchestrator and remote model/service processes. The separate cgroup observations may include other workloads in the same cgroup.

Endpoints are instantaneous readings, not peaks or time averages. CPU time is cumulative since runtime startup; its difference is only an estimate because process reaping and reparenting can change which work is visible.

Fields

`collected_groups: Vec<SystemStatsMetricGroup>`

Requested groups, including selected groups unavailable on this platform.

`elapsed_seconds: f64`

Monotonic elapsed seconds for the adapter exchange. Excludes runtime startup, endpoint collection, artifact preparation, and teardown. Optional sampling runs concurrently; its effect is not subtracted.

`before: ResourceObservation`

Observation immediately before the adapter exchange.

`after: ResourceObservation`

Observation immediately after the adapter exchange, before another invocation can acquire this runtime’s host lock.

`cpu_time_seconds_estimate: Option<f64>`

Nonnegative CPU counter difference, in seconds. Absent if an endpoint is missing, the runtime identity differs, or its CPU counter decreased. It can undercount work whose processes leave the tree between reads.

`cgroup: Option<CgroupStats>`

Before/after readings for the adapter host’s cgroup. This scope may contain other workloads and overlaps the process tree; never add them.

`sampled: Option<SampleSummary>`

Bounded sample reductions and collection quality when sampling is enabled.

Trait Implementations

`impl Clone for InvocationSystemStats`

impl Clone for InvocationSystemStats

`clone`

fn clone(&self) -> InvocationSystemStats

`clone_from`

fn clone_from(&mut self, source: &Self)

`impl Debug for InvocationSystemStats`

impl Debug for InvocationSystemStats

`fmt`

fn fmt(&self, f: &mut Formatter<'_>) -> Result

`impl<'de> Deserialize<'de> for InvocationSystemStats`

impl<'de> Deserialize<'de> for InvocationSystemStats

`deserialize`

fn deserialize<__D>(__deserializer: __D) -> Result<Self, __D::Error>where
    __D: Deserializer<'de>,

`impl JsonSchema for InvocationSystemStats`

impl JsonSchema for InvocationSystemStats

`schema_name`

fn schema_name() -> Cow<'static, str>

`schema_id`

fn schema_id() -> Cow<'static, str>

`json_schema`

fn json_schema(generator: &mut SchemaGenerator) -> Schema

`inline_schema`

fn inline_schema() -> bool

`impl PartialEq for InvocationSystemStats`

impl PartialEq for InvocationSystemStats

`eq`

fn eq(&self, other: &InvocationSystemStats) -> bool

`ne`

fn ne(&self, other: &Rhs) -> bool

`impl Serialize for InvocationSystemStats`

impl Serialize for InvocationSystemStats

`serialize`

fn serialize<__S>(&self, __serializer: __S) -> Result<__S::Ok, __S::Error>where
    __S: Serializer,

`impl StructuralPartialEq for InvocationSystemStats`

impl StructuralPartialEq for InvocationSystemStats