mirror of
https://github.com/seaweedfs/seaweedfs.git
synced 2026-11-10 22:08:48 +01:00
* vector: expose request metrics and registration-aware health endpoints * vector: report immutable read cache and storage fetch metrics * docs: describe vector engine health, metrics, and maintenance * vector: count canceled requests when their handler is dropped * vector: account for uncached large immutable storage reads * vector: reliably release the stalled credential reader in tests * vector: observe large reads as their streamed body is consumed * vector: bound heartbeats on established master registration streams * test: exercise hardened vector maintenance on Go and Rust volumes * vector: register engines in their configured filer group * vector: make retried index creation preserve compatible datasets * vector: allow registration to advertise a separate address * test: release stalled credential readers without blocking FIFO cleanup * test: allow hardened vector coverage in a named filer group * vector: discover engines in the same filer group as their gateway * vector: fall back when the advertised address is empty * admin: expose vector readiness, maintenance, and management tools (#12520) * s3vectors: share vector discovery with trusted management clients * admin: show vector engine readiness and recent maintenance activity * admin: suggest S3 Vectors IAM actions from the supported operations * admin: manage vector indexes, policies, tags, encryption, and query data * admin: validate SSE-S3 support before creating encrypted vector buckets * admin: discover vector engines in their registration group * admin: probe vector engines concurrently with independent time budgets * admin: verify encryption capability on the remote S3 gateway * admin: defer discovery until after the HTTP server can start * admin: distinguish unknown vector health services from failed engines * admin: count workers that can execute vector index maintenance * admin: allow read-only users to query vectors and inspect tags * vector: scope gateway and admin discovery to the configured filer group * admin: refresh policy state after mutations and serialize policy controls * vector: drain active RPCs before closing replaced discovery connections * vector: respect request cancellation while waiting for discovery * vector: prefer another registered engine after a transport failure * admin: check all masters before reporting no registered vector engines * iam: honor attached vector policies without broadening legacy grants * vector: allow short-lived discovery clients to close their connections * vector: refresh cached master addresses for each discovery lookup * iam: enforce vector bucket tag conditions in attached policies * iam: authorize vector bucket creation with the requested tags * test: exercise vector IAM grants and tag denies on Go and Rust volumes * admin: reject authenticated vector mutations without an admin role * test: run vector IAM assertions before the shared engine is stopped * vector: add native mini startup, shell tools, and a runnable Compose example (#12522) * s3vectors: share vector discovery with trusted management clients * admin: show vector engine readiness and recent maintenance activity * admin: suggest S3 Vectors IAM actions from the supported operations * admin: manage vector indexes, policies, tags, encryption, and query data * admin: validate SSE-S3 support before creating encrypted vector buckets * admin: discover vector engines in their registration group * admin: probe vector engines concurrently with independent time budgets * admin: verify encryption capability on the remote S3 gateway * admin: defer discovery until after the HTTP server can start * admin: distinguish unknown vector health services from failed engines * admin: count workers that can execute vector index maintenance * admin: allow read-only users to query vectors and inspect tags * vector: scope gateway and admin discovery to the configured filer group * admin: refresh policy state after mutations and serialize policy controls * vector: drain active RPCs before closing replaced discovery connections * vector: respect request cancellation while waiting for discovery * vector: prefer another registered engine after a transport failure * admin: check all masters before reporting no registered vector engines * iam: honor attached vector policies without broadening legacy grants * vector: allow short-lived discovery clients to close their connections * vector: refresh cached master addresses for each discovery lookup * iam: enforce vector bucket tag conditions in attached policies * iam: authorize vector bucket creation with the requested tags * test: exercise vector IAM grants and tag denies on Go and Rust volumes * admin: reject authenticated vector mutations without an admin role * test: run vector IAM assertions before the shared engine is stopped * mini: optionally start and supervise the vector engine * mini: bootstrap vector buckets with existing Lance catalog helpers * shell: manage vector buckets, indexes, and vector data * docs: provide a runnable vector and maintenance worker Compose stack * shell: scope vector discovery to the session and close its connections * mini: honor the bind address for vector and metrics listeners * mini: reserve vector ports before assigning gRPC and compatibility listeners * mini: wait for vector storage setup and master registration * mini: create requested vector buckets without requiring the Lance HTTP listener * shell: refresh master addresses during vector discovery * mini: resolve sibling vector executables with platform extensions * vector: preserve uncertain creates and fix mini listener allocation (#12525) * vector: retain catalog records when index creation has an unknown outcome * mini: keep chosen listener ports reserved throughout allocation * mini: resolve hostname binds before starting vector listeners * vector: fix integration test imports and recover interrupted index creation (#12533) * shell: register vector operations from the command package * s3vectors: resume interrupted index initialization safely * mini: exclude disabled WebDAV from listener allocation * s3vectors: retain uncertain creates across refused retries * s3vectors: claim pending indexes before retrying initialization * s3vectors: compare resolved distance metrics during recovery * s3vectors: preserve metadata keys when retrying initialization * s3vectors: verify ownership before initializing new catalog records
112 lines
3.6 KiB
Rust
112 lines
3.6 KiB
Rust
use std::sync::Arc;
|
|
|
|
use bytes::Bytes;
|
|
use lance::io::WrappingObjectStore;
|
|
use object_store::{ObjectStoreExt, memory::InMemory, path::Path};
|
|
use weed_vector_server::{metrics::Metrics, read_cache::ReadCache};
|
|
|
|
#[tokio::test]
|
|
async fn immutable_reads_report_hits_misses_bytes_and_weight() {
|
|
let metrics = Metrics::new().unwrap();
|
|
let cache = ReadCache::new(1024).with_metrics(metrics.clone());
|
|
let store = cache.wrap("memory", Arc::new(InMemory::new()));
|
|
let path = Path::from("data/example.lance");
|
|
store
|
|
.put(&path, Bytes::from_static(b"abc").into())
|
|
.await
|
|
.unwrap();
|
|
for _ in 0..2 {
|
|
assert_eq!(
|
|
store.get(&path).await.unwrap().bytes().await.unwrap(),
|
|
"abc"
|
|
);
|
|
}
|
|
assert_eq!(metrics.cache_requests.with_label_values(&["miss"]).get(), 1);
|
|
assert_eq!(metrics.cache_requests.with_label_values(&["hit"]).get(), 1);
|
|
assert_eq!(metrics.storage_bytes.get(), 3);
|
|
assert_eq!(metrics.storage_read_seconds.get_sample_count(), 1);
|
|
let (entries, weight) = cache.size();
|
|
assert_eq!(entries, 1);
|
|
assert!(weight >= 3);
|
|
let metrics_endpoint = tokio::net::TcpListener::bind("127.0.0.1:0").await.unwrap();
|
|
let endpoint = format!("http://{}/metrics", metrics_endpoint.local_addr().unwrap());
|
|
let task = tokio::spawn(weed_vector_server::metrics::serve_listener(
|
|
metrics,
|
|
metrics_endpoint,
|
|
Some(cache),
|
|
));
|
|
let body = reqwest::get(endpoint).await.unwrap().text().await.unwrap();
|
|
assert!(body.contains("SeaweedFS_vector_cache_entries 1"));
|
|
assert!(body.contains("SeaweedFS_vector_cache_bytes "));
|
|
task.abort();
|
|
}
|
|
|
|
#[tokio::test]
|
|
async fn cancelled_requests_are_counted_once() {
|
|
let metrics = Metrics::new().unwrap();
|
|
let guard = metrics.start("QueryVectors");
|
|
let task = tokio::spawn(async move {
|
|
let _guard = guard;
|
|
std::future::pending::<()>().await;
|
|
});
|
|
task.abort();
|
|
let _ = task.await;
|
|
assert_eq!(
|
|
metrics.in_flight.with_label_values(&["QueryVectors"]).get(),
|
|
0
|
|
);
|
|
assert_eq!(
|
|
metrics
|
|
.requests
|
|
.with_label_values(&["QueryVectors", "Cancelled"])
|
|
.get(),
|
|
1
|
|
);
|
|
assert_eq!(
|
|
metrics
|
|
.request_seconds
|
|
.with_label_values(&["QueryVectors"])
|
|
.get_sample_count(),
|
|
1
|
|
);
|
|
{
|
|
let mut guard = metrics.start("QueryVectors");
|
|
guard.complete(None);
|
|
}
|
|
assert_eq!(
|
|
metrics
|
|
.requests
|
|
.with_label_values(&["QueryVectors", "OK"])
|
|
.get(),
|
|
1
|
|
);
|
|
assert_eq!(
|
|
metrics
|
|
.requests
|
|
.with_label_values(&["QueryVectors", "Cancelled"])
|
|
.get(),
|
|
1
|
|
);
|
|
}
|
|
|
|
#[tokio::test]
|
|
async fn large_immutable_reads_report_bytes_without_caching() {
|
|
let metrics = Metrics::new().unwrap();
|
|
let cache = ReadCache::new(16 * 1024 * 1024).with_metrics(metrics.clone());
|
|
let store = cache.wrap("memory", Arc::new(InMemory::new()));
|
|
let path = Path::from("data/large.lance");
|
|
let size = 5 * 1024 * 1024;
|
|
store
|
|
.put(&path, Bytes::from(vec![0; size]).into())
|
|
.await
|
|
.unwrap();
|
|
let result = store.get(&path).await.unwrap();
|
|
assert_eq!(metrics.storage_bytes.get(), 0);
|
|
assert_eq!(metrics.storage_read_seconds.get_sample_count(), 0);
|
|
assert_eq!(result.bytes().await.unwrap().len(), size);
|
|
assert_eq!(metrics.storage_bytes.get(), size as u64);
|
|
assert_eq!(metrics.cache_requests.with_label_values(&["miss"]).get(), 1);
|
|
assert_eq!(metrics.storage_read_seconds.get_sample_count(), 1);
|
|
assert_eq!(cache.size(), (0, 0));
|
|
}
|