Metrics Developer Guide

1
use dynamo_runtime::DistributedRuntime;
2
3
let runtime = DistributedRuntime::new()?;
4
let endpoint = runtime.namespace("my_namespace").component("my_component").endpoint("my_endpoint");
5
6
// Simple metrics
7
let requests_total = endpoint.metrics().create_counter(
8
    "requests_total",
9
    "Total requests",
10
    &[]
11
)?;
12
13
let active_connections = endpoint.metrics().create_gauge(
14
    "active_connections",
15
    "Active connections",
16
    &[]
17
)?;
18
19
let latency = endpoint.metrics().create_histogram(
20
    "latency_seconds",
21
    "Request latency",
22
    &[],
23
    Some(vec![0.001, 0.01, 0.1, 1.0, 10.0])
24
)?;

1
// Counters
2
requests_total.inc();
3
4
// Gauges
5
active_connections.set(42.0);
6
active_connections.inc();
7
active_connections.dec();
8
9
// Histograms
10
latency.observe(0.023);  // 23ms

1
// Create vector metrics with label names
2
let requests_by_model = endpoint.metrics().create_countervec(
3
    "requests_by_model",
4
    "Requests by model",
5
    &["model_type", "model_size"],
6
    &[]
7
)?;
8
9
let memory_by_gpu = endpoint.metrics().create_gaugevec(
10
    "gpu_memory_bytes",
11
    "GPU memory by device",
12
    &["gpu_id", "memory_type"],
13
    &[]
14
)?;
15
16
// Use with specific label values
17
requests_by_model.with_label_values(&["llama", "7b"]).inc();
18
memory_by_gpu.with_label_values(&["0", "allocated"]).set(8192.0);

1
let latency = endpoint.metrics().create_histogram(
2
    "latency_seconds",
3
    "Request latency",
4
    &[],
5
    Some(vec![0.001, 0.01, 0.1, 1.0, 10.0])
6
)?;

1
let counter = endpoint.metrics().create_counter(
2
    "requests_total",
3
    "Total requests",
4
    &[("region", "us-west"), ("env", "prod")]
5
)?;