mirror of
https://github.com/lancedb/lancedb.git
synced 2026-08-17 11:38:19 +00:00
Will Jones
285add40dd
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>
53 lines
1.5 KiB
TOML
53 lines
1.5 KiB
TOML
[package]
|
|
name = "lancedb-python"
|
|
version = "0.34.0-beta.6"
|
|
publish = false
|
|
edition.workspace = true
|
|
description = "Python bindings for LanceDB"
|
|
license.workspace = true
|
|
repository.workspace = true
|
|
keywords.workspace = true
|
|
categories.workspace = true
|
|
rust-version = "1.91.0"
|
|
|
|
[lib]
|
|
name = "_lancedb"
|
|
crate-type = ["cdylib"]
|
|
|
|
[dependencies]
|
|
arrow = { version = "58.0.0", features = ["pyarrow"] }
|
|
async-trait = "0.1"
|
|
bytes = "1"
|
|
lancedb = { path = "../rust/lancedb", default-features = false }
|
|
datafusion-common.workspace = true
|
|
lance-core.workspace = true
|
|
lance-namespace.workspace = true
|
|
lance-namespace-impls.workspace = true
|
|
lance-io.workspace = true
|
|
env_logger.workspace = true
|
|
log.workspace = true
|
|
pyo3 = { version = "0.28", features = ["extension-module", "abi3-py39", "chrono"] }
|
|
chrono = { version = "0.4", default-features = false, features = ["clock"] }
|
|
pyo3-async-runtimes = { version = "0.28", features = [
|
|
"attributes",
|
|
"tokio-runtime",
|
|
] }
|
|
pin-project = "1.1.5"
|
|
futures.workspace = true
|
|
serde = "1"
|
|
serde_json = "1"
|
|
snafu.workspace = true
|
|
tokio = { version = "1.40", features = ["sync", "rt-multi-thread"] }
|
|
libc = "0.2"
|
|
|
|
[build-dependencies]
|
|
pyo3-build-config = { version = "0.28", features = [
|
|
"extension-module",
|
|
"abi3-py39",
|
|
] }
|
|
|
|
[features]
|
|
default = ["remote", "lancedb/aws", "lancedb/gcs", "lancedb/azure", "lancedb/dynamodb", "lancedb/oss", "lancedb/huggingface", "lancedb/cos", "lancedb/goosefs", "lancedb/metrics-otel"]
|
|
fp16kernels = ["lancedb/fp16kernels"]
|
|
remote = ["lancedb/remote"]
|