Files
Will Jones 285add40dd feat: expose Lance metrics via OpenTelemetry in Python and Node (#3609)
Bridges Lance's internal `metrics`-crate instrumentation (object store
request counts, bytes, latency, errors, and throttles) into
OpenTelemetry, in both the Python and Node bindings, with a shared
adapter in the Rust core. This is the LanceDB counterpart to
lance-format/lance#7537.

## Rust core (`rust/lancedb`)
Two new, **off-by-default** features:
- `metrics` — re-exports the [`metrics`](https://docs.rs/metrics) crate
as `lancedb::metrics` and turns on Lance's object-store instrumentation.
Install any `metrics`-compatible recorder to collect them.
- `metrics-otel` — adds `lancedb::metrics_otel`, a pull-based adapter
that installs a process-global recorder aggregating into lock-free
cumulative storage and exposes a snapshot/catalog API
(`register_metrics_recorder`, `metrics_catalog`, `snapshot_metrics`,
`MetricPoint`/`MetricValue`/`MetricKind`/`MetricDescription`). Both
bindings build on this.

## Python
`lancedb.otel.instrument_lancedb_metrics()` registers each metric as an
OpenTelemetry observable instrument on the given (or global)
`MeterProvider`. Available via the `otel` extra (`pip install
lancedb[otel]`), which pulls in only `opentelemetry-api` — the
application supplies and configures the SDK.

## Node
`instrumentLanceDbMetrics()` provides the equivalent wiring against
`@opentelemetry/api`. This is the only public entry point; the
underlying recorder/catalog/snapshot functions stay internal.

Because OpenTelemetry has no asynchronous histogram instrument,
histograms are exported Prometheus-style as `<name>_bucket` (with an
`le` attribute), `<name>_count`, and `<name>_sum`. Only `_sum` carries
the histogram's unit; `_bucket` and `_count` observe cumulative counts
and are unitless. The adapter is enabled by default in the Python and
Node builds, and off by default in the Rust crate.

## Notes
- Requires Lance ≥ `v9.0.0-beta.19`, which ships the object-store
metrics APIs (upstream lance-format/lance#7537, now merged). `main` is
already on beta.19, so this is a single feature commit with no
dependency bump.
- Tests: 8 Rust unit tests, 3 Python tests, 2 Node tests, all covering
the end-to-end object-store-metrics → OpenTelemetry path.

🤖 Generated with [Claude Code](https://claude.com/claude-code)

Co-authored-by: Claude Opus 4.8 (1M context) <noreply@anthropic.com>
2026-07-09 15:36:03 -07:00

115 lines
4.5 KiB
TypeScript

// SPDX-License-Identifier: Apache-2.0
// SPDX-FileCopyrightText: Copyright The LanceDB Authors
import {
MeterProvider,
type MetricData,
MetricReader,
} from "@opentelemetry/sdk-metrics";
import * as tmp from "tmp";
import { connect, instrumentLanceDbMetrics } from "../lancedb";
// snapshotLancedbMetrics is internal plumbing (not part of the public API), so
// it is imported from the native module rather than the package entry point.
import { snapshotLancedbMetrics } from "../lancedb/native";
// The metrics recorder is process-global and installed once, so the whole
// bridge is exercised in a single test to avoid cross-test global-state coupling.
// A minimal pull-based reader whose `collect()` we drive directly, invoking the
// observable-instrument callbacks. `@opentelemetry/sdk-metrics` ships no
// in-memory reader, so we subclass the abstract base.
class TestMetricReader extends MetricReader {
protected async onForceFlush(): Promise<void> {
// no-op: collection is driven directly via collect()
}
protected async onShutdown(): Promise<void> {
// no-op: nothing to release
}
}
async function metricsByName(
reader: TestMetricReader,
): Promise<Map<string, MetricData>> {
const collected = await reader.collect();
const result = new Map<string, MetricData>();
for (const scope of collected.resourceMetrics.scopeMetrics) {
for (const metric of scope.metrics) {
result.set(metric.descriptor.name, metric);
}
}
return result;
}
describe("OpenTelemetry metrics bridge", () => {
let tmpDir: tmp.DirResult;
beforeEach(() => {
tmpDir = tmp.dirSync({ unsafeCleanup: true });
});
afterEach(() => tmpDir.removeCallback());
it("snapshot is safe to call regardless of install state", () => {
expect(Array.isArray(snapshotLancedbMetrics())).toBe(true);
});
it("exports object store metrics via observable instruments", async () => {
const reader = new TestMetricReader();
const provider = new MeterProvider({ readers: [reader] });
expect(instrumentLanceDbMetrics(provider)).toBe(true);
// Generate object store activity on the local filesystem (scheme "file").
const db = await connect(tmpDir.name);
const data = Array.from({ length: 256 }, (_, i) => ({ id: i }));
const table = await db.createTable("t", data);
expect(await table.countRows()).toBe(256);
const metrics = await metricsByName(reader);
const requests = metrics.get("lance_object_store_requests_total");
expect(requests).toBeDefined();
// biome-ignore lint/suspicious/noExplicitAny: SDK point shape
const requestPoints = (requests!.dataPoints as any[]) ?? [];
expect(requestPoints.length).toBeGreaterThan(0);
for (const p of requestPoints) {
// Labelled by `operation` and `base` (the store scheme by default).
expect(p.attributes).toHaveProperty("base");
expect(p.attributes).toHaveProperty("operation");
}
const totalRequests = requestPoints.reduce((acc, p) => acc + p.value, 0);
expect(totalRequests).toBeGreaterThan(0);
// Histograms are decomposed into bucket / count / sum observable counters.
const bucket = metrics.get(
"lance_object_store_request_duration_seconds_bucket",
);
expect(bucket).toBeDefined();
// biome-ignore lint/suspicious/noExplicitAny: SDK point shape
const bucketPoints = (bucket!.dataPoints as any[]) ?? [];
expect(bucketPoints.length).toBeGreaterThan(0);
expect(bucketPoints.every((p) => "le" in p.attributes)).toBe(true);
// The implicit +Inf bucket must be present.
expect(bucketPoints.some((p) => p.attributes.le === "+Inf")).toBe(true);
const count = metrics.get(
"lance_object_store_request_duration_seconds_count",
);
expect(count).toBeDefined();
// biome-ignore lint/suspicious/noExplicitAny: SDK point shape
const countPoints = (count!.dataPoints as any[]) ?? [];
expect(countPoints.reduce((acc, p) => acc + p.value, 0)).toBeGreaterThan(0);
const sum = metrics.get("lance_object_store_request_duration_seconds_sum");
expect(sum).toBeDefined();
// biome-ignore lint/suspicious/noExplicitAny: SDK point shape
const sumPoints = (sum!.dataPoints as any[]) ?? [];
expect(sumPoints.reduce((acc, p) => acc + p.value, 0)).toBeGreaterThan(0);
// Unit handling: only `_sum` keeps the histogram's unit (seconds); `_bucket`
// and `_count` observe cumulative counts and are unitless.
expect(sum!.descriptor.unit).toBe("s");
expect(bucket!.descriptor.unit).toBe("");
expect(count!.descriptor.unit).toBe("");
await provider.shutdown();
});
});