From 79ba076429d60dbdc245278ea3959d97bd5b5aa3 Mon Sep 17 00:00:00 2001 From: Dan Rammer Date: Fri, 7 Aug 2026 13:44:49 -0500 Subject: [PATCH 01/14] feat(table): checkpoint_lsm, flush_lsm, compact_lsm, get_lsm_stats (#3736) MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit Converge a table's LSM write path into its base table, and inspect it. `checkpoint_lsm` is `flush` then `compact`, repeated until the fresh tier is empty — and the loop runs **client-side**. Putting it on the server would mean a background task, which means a single-flight intent, an intent that leaks on panic, a bounded-iteration policy, an "is it done" observable, and a story for every way a client can vanish mid-operation. None of that exists in this shape: each request does a bounded unit of work and reports what is left, so completion is *carried in the responses* rather than inferred from a shared counter that cannot distinguish "converged" from "hasn't started yet". Best-effort by construction. Nothing is frozen, so `converged` means L0 was empty as of the last pass. It is idempotent, abandonable at any point with zero consequence, and safe to run on a cadence — an already-converged table costs one round trip and zero compaction passes, because `flush` reports `generations_remaining` and the loop is never entered. ## The failure taxonomy is the load-bearing part Five distinct conditions used to arrive at a client as one 503. `Error::LsmRoute` carries a classification read from the response body's namespace error code **at the point of receipt** — before any generic helper folds the body into a string and keeps only the status. | condition | wire | client action | |---|---|---| | contention (latch held / pool saturated) | 429, code 21 | retry with backoff | | owning node draining | 503, code 19 `InvalidTableState` | **stop** | | fenced / no slot / transport | 503, code 17 | retry with backoff | | registry entry vanished | 404 | re-issue from `flush` (capped) | | table being dropped / not WAL-backed | 409 / 400 | stop | Draining is terminal because the drain gate is a one-way latch — retrying spins until the deadline to report a failure that was knowable on the first response. Transport retry is disabled on these routes for the same reason: it treats every 503 alike and would burn its budget before the classifier ever saw the body. `get_lsm_stats` returns `Option`, matching `get_lsm_write_spec` — `None` only when the table has no LSM write path, since a struct of zeros would read as measurements. Python bindings mirror all four, preserving per-bucket detail rather than flattening to a table-level summary. ## Testing Six new unit tests against the mocked endpoint, plus the taxonomy round-trip: - flush into an empty L0 issues **zero** compact calls (asserts the call count — `generations_consumed: 0` is also true of a loop that ran a pointless pass) - the loop drives compact until the server reports zero remaining - **contention is not draining**: a 429 retries and converges; asserts the retry count - a draining node stops after **exactly one** request, no retries - stats round-trips fully populated; `include_generation_rows` off by default - every `(status, code)` pair classifies correctly, including unparseable 503 bodies falling back to *retryable* rather than terminal `cargo test -p lancedb --features remote --lib`: 723 passed. ## Notes for review - Depends on the sibling lance change returning `SealedGeneration` from `force_seal_active` only at the *server* level — no lance API is used here. - The branch is based on `codex/update-lance-10-0-0-beta-5`, so it carries one extra commit (`chore: update lance dependency to v10.0.0-beta.5`) that is not part of this change. 🤖 Generated with [Claude Code](https://claude.com/claude-code) --------- Co-authored-by: lancedb automation Co-authored-by: Claude Opus 5 (1M context) --- python/python/lancedb/_lancedb.pyi | 4 + python/python/lancedb/table.py | 83 ++++ python/src/table.rs | 108 +++++- rust/lancedb/Cargo.toml | 2 +- rust/lancedb/src/remote/table.rs | 541 +++++++++++++++++++++++++++ rust/lancedb/src/table.rs | 107 ++++++ rust/lancedb/src/table/checkpoint.rs | 315 ++++++++++++++++ rust/lancedb/src/table/lsm_stats.rs | 162 ++++++++ 8 files changed, 1320 insertions(+), 2 deletions(-) create mode 100644 rust/lancedb/src/table/checkpoint.rs create mode 100644 rust/lancedb/src/table/lsm_stats.rs diff --git a/python/python/lancedb/_lancedb.pyi b/python/python/lancedb/_lancedb.pyi index 47e727f99..fad2744d3 100644 --- a/python/python/lancedb/_lancedb.pyi +++ b/python/python/lancedb/_lancedb.pyi @@ -355,6 +355,10 @@ class Table: async def set_lsm_write_spec(self, spec: LsmWriteSpec) -> None: ... async def unset_lsm_write_spec(self) -> None: ... async def get_lsm_write_spec(self) -> Optional[LsmWriteSpec]: ... + async def checkpoint_lsm(self) -> None: ... + async def flush_lsm(self) -> None: ... + async def compact_lsm(self) -> None: ... + async def get_lsm_stats(self, include_generation_rows: bool) -> Optional[dict]: ... async def close_lsm_writers(self) -> None: ... @property def tags(self) -> Tags: ... diff --git a/python/python/lancedb/table.py b/python/python/lancedb/table.py index 59e2650eb..0828f04dc 100644 --- a/python/python/lancedb/table.py +++ b/python/python/lancedb/table.py @@ -3976,6 +3976,28 @@ class LanceTable(Table): [`AsyncTable.get_lsm_write_spec`][lancedb.AsyncTable.get_lsm_write_spec].""" return LOOP.run(self._table.get_lsm_write_spec()) + def checkpoint_lsm(self) -> None: + """Synchronous version of + [`AsyncTable.checkpoint_lsm`][lancedb.AsyncTable.checkpoint_lsm].""" + return LOOP.run(self._table.checkpoint_lsm()) + + def flush_lsm(self) -> None: + """Synchronous version of + [`AsyncTable.flush_lsm`][lancedb.AsyncTable.flush_lsm].""" + return LOOP.run(self._table.flush_lsm()) + + def compact_lsm(self) -> None: + """Synchronous version of + [`AsyncTable.compact_lsm`][lancedb.AsyncTable.compact_lsm].""" + return LOOP.run(self._table.compact_lsm()) + + def get_lsm_stats(self, *, include_generation_rows: bool = False) -> Optional[dict]: + """Synchronous version of + [`AsyncTable.get_lsm_stats`][lancedb.AsyncTable.get_lsm_stats].""" + return LOOP.run( + self._table.get_lsm_stats(include_generation_rows=include_generation_rows) + ) + def close_lsm_writers(self) -> None: """Close cached MemWAL shard writers. See [`AsyncTable.close_lsm_writers`][lancedb.AsyncTable.close_lsm_writers].""" @@ -4686,6 +4708,67 @@ class AsyncTable: """ return await self._inner.get_lsm_write_spec() + async def checkpoint_lsm(self) -> None: + """Converge this table's LSM write path into its base table. + + One flush, sealing every memtable into L0, then compaction triggers + until every generation that existed at that moment has reached base. + The loop runs client-side, reading progress from ``get_lsm_stats``. + + Best-effort: generations created *while* it runs are deliberately not + waited on, which is what lets it terminate on a table taking writes. + Idempotent and safe on a cadence. + + There is no deadline, and the caller owns that. It returns when the + target generations are gone, raises on a terminal server fault, and + otherwise waits however long the server takes. A slow table and a + stuck one are the same picture from the client: the compactor pool is + shared across every table on the node, so a checkpoint queued behind + unrelated work looks exactly like one that is merging. Wrap this in + ``asyncio.wait_for`` for a wall-clock bound; abandoning it partway + costs nothing. + """ + return await self._inner.checkpoint_lsm() + + async def flush_lsm(self) -> None: + """Seal every bucket's active memtable into L0. + + Does not touch the base table — moving L0 into base is + `compact_lsm`. On a node that has not claimed this table, this claims + it and replays its WAL log first. + """ + return await self._inner.flush_lsm() + + async def compact_lsm(self) -> None: + """Trigger a background L0 to base compaction pass per bucket. + + Returns once the passes are dispatched, not once they finish: watch + ``get_lsm_stats`` for progress, or use ``checkpoint_lsm`` to loop + until the current L0 has reached base. + """ + return await self._inner.compact_lsm() + + async def get_lsm_stats( + self, *, include_generation_rows: bool = False + ) -> Optional[dict]: + """Read live per-bucket LSM state. + + Answers "how far behind is my fresh tier", "which bucket is hot", and + "why is my fresh-tier vector search brute-force". Mutates no table + state, though on a node that has not claimed this table it claims it, + exactly as a read would. + + Returns ``None`` only when the LSM write path is not enabled. + + Parameters + ---------- + include_generation_rows + Report a row count per L0 generation. Off by default: each count + opens an uncached Lance dataset, and ``checkpoint_lsm`` polls this + needing only generation numbers. + """ + return await self._inner.get_lsm_stats(include_generation_rows) + async def close_lsm_writers(self) -> None: """Drain and close any cached MemWAL shard writers for this table. diff --git a/python/src/table.rs b/python/src/table.rs index 5b5d6596a..119388708 100644 --- a/python/src/table.rs +++ b/python/src/table.rs @@ -28,11 +28,72 @@ use pyo3::{ Bound, FromPyObject, Py, PyAny, PyRef, PyResult, Python, exceptions::{PyRuntimeError, PyValueError}, pyclass, pyfunction, pymethods, - types::{IntoPyDict, PyAnyMethods, PyBytes, PyDict, PyDictMethods}, + types::{IntoPyDict, PyAnyMethods, PyBytes, PyDict, PyDictMethods, PyList, PyListMethods}, }; mod scannable; +/// Convert `LsmStats` to a Python dict, preserving the per-bucket list. +/// +/// Deliberately not flattened to a table-level summary: a table is N +/// buckets on one node, and the per-bucket detail is the reason the +/// endpoint exists — flattening hides the single hot bucket someone opened +/// it to find. +fn lsm_stats_to_py(py: Python<'_>, stats: &lancedb::table::LsmStats) -> PyResult> { + let out = PyDict::new(py); + let buckets = PyList::empty(py); + for b in &stats.buckets { + let e = PyDict::new(py); + e.set_item("shard_id", &b.shard_id)?; + e.set_item("status", &b.status)?; + e.set_item("writer_epoch", b.writer_epoch)?; + e.set_item("manifest_version", b.manifest_version)?; + e.set_item("current_generation", b.current_generation)?; + e.set_item( + "replay_after_wal_entry_position", + b.replay_after_wal_entry_position, + )?; + e.set_item( + "wal_entry_position_last_seen", + b.wal_entry_position_last_seen, + )?; + + let generations = PyList::empty(py); + for g in &b.generations { + let ge = PyDict::new(py); + ge.set_item("generation", g.generation)?; + ge.set_item("bytes", g.bytes)?; + ge.set_item("rows", g.rows)?; + generations.append(ge)?; + } + e.set_item("generations", generations)?; + e.set_item("compacting", b.compacting)?; + + e.set_item( + "memtables", + b.memtables + .as_ref() + .map(|ms| { + let l = PyList::empty(py); + for m in ms { + let d = PyDict::new(py); + d.set_item("generation", m.generation)?; + d.set_item("rows", m.rows)?; + d.set_item("bytes", m.bytes)?; + d.set_item("batches", m.batches)?; + d.set_item("indexes", m.indexes.clone())?; + l.append(d)?; + } + PyResult::Ok(l.unbind()) + }) + .transpose()?, + )?; + buckets.append(e)?; + } + out.set_item("buckets", buckets)?; + Ok(out.unbind()) +} + #[derive(FromPyObject)] enum PredicateArg { Expr(PyExpr), @@ -1339,6 +1400,51 @@ impl Table { }) } + /// Converge the table's LSM write path into its base table. + /// + /// Best-effort: with writes flowing, new rows may land after the last + /// pass. Errors if the table stops making progress. + pub fn checkpoint_lsm(self_: PyRef<'_, Self>) -> PyResult> { + let inner = self_.inner_ref()?.clone(); + future_into_py(self_.py(), async move { + inner.checkpoint_lsm().await.infer_error() + }) + } + + /// Seal every bucket's active memtable into L0. + pub fn flush_lsm(self_: PyRef<'_, Self>) -> PyResult> { + let inner = self_.inner_ref()?.clone(); + future_into_py( + self_.py(), + async move { inner.flush_lsm().await.infer_error() }, + ) + } + + /// Trigger a background L0 → base pass per bucket. Returns once the + /// passes are dispatched, not once they finish — watch `get_lsm_stats`. + pub fn compact_lsm(self_: PyRef<'_, Self>) -> PyResult> { + let inner = self_.inner_ref()?.clone(); + future_into_py(self_.py(), async move { + inner.compact_lsm().await.infer_error() + }) + } + + /// Live LSM state, or `None` when the LSM write path is not enabled. + #[pyo3(signature = (include_generation_rows=false))] + pub fn get_lsm_stats( + self_: PyRef<'_, Self>, + include_generation_rows: bool, + ) -> PyResult> { + let inner = self_.inner_ref()?.clone(); + future_into_py(self_.py(), async move { + let stats = inner + .get_lsm_stats(include_generation_rows) + .await + .infer_error()?; + Python::attach(|py| stats.map(|s| lsm_stats_to_py(py, &s)).transpose()) + }) + } + pub fn close_lsm_writers(self_: PyRef<'_, Self>) -> PyResult> { let inner = self_.inner_ref()?.clone(); future_into_py(self_.py(), async move { diff --git a/rust/lancedb/Cargo.toml b/rust/lancedb/Cargo.toml index 96ea9ec95..c2137d0b5 100644 --- a/rust/lancedb/Cargo.toml +++ b/rust/lancedb/Cargo.toml @@ -100,7 +100,7 @@ anyhow = "1" lance-testing = { workspace = true } tempfile = "3.5.0" random_word = { version = "0.4.3", features = ["en"] } -tokio = { version = "1.23", features = ["io-util", "macros", "net", "rt-multi-thread", "sync"] } +tokio = { version = "1.23", features = ["io-util", "macros", "net", "rt-multi-thread", "sync", "test-util"] } uuid = { version = "1.7.0", features = ["v4"] } walkdir = "2" aws-sdk-dynamodb = { version = "1.55.0" } diff --git a/rust/lancedb/src/remote/table.rs b/rust/lancedb/src/remote/table.rs index 388bed0f7..f3e872cbe 100644 --- a/rust/lancedb/src/remote/table.rs +++ b/rust/lancedb/src/remote/table.rs @@ -23,11 +23,13 @@ use crate::table::AddResult; use crate::table::BranchDiff; use crate::table::DeleteResult; use crate::table::DropColumnsResult; +use crate::table::LsmStats; use crate::table::LsmWriteSpec; use crate::table::MergeBranchResult; use crate::table::MergeResult; use crate::table::Tags; use crate::table::UpdateResult; +use crate::table::lsm_stats::GetLsmStatsResponse; use crate::table::merge::MergeFilter; use crate::table::query::create_multi_vector_plan; use crate::table::write_progress::FinishOnDrop; @@ -991,6 +993,18 @@ impl RemoteTable { } } + /// Send an LSM operator request with the transport retry layer **off**. + /// + /// Retry policy on these routes belongs to the checkpoint loop, which + /// reads the status and can tell contention from a lost claim. Leaving the + /// transport layer on would re-ask on its own schedule first, and surface + /// an `Error::Retry` whose status the loop would then have to unwrap. + async fn send_lsm_route(&self, request: RequestBuilder) -> Result<(String, reqwest::Response)> { + let (request_id, response) = self.send(request, false).await?; + let response = self.check_table_response(&request_id, response).await?; + Ok((request_id, response)) + } + /// Build a POST request and attach the read-freshness headers /// (`x-lancedb-min-version`, `x-lancedb-min-timestamp`). fn post_read(&self, uri: &str) -> RequestBuilder { @@ -2468,6 +2482,40 @@ impl BaseTable for RemoteTable { }) } + async fn flush_lsm(&self) -> Result<()> { + let request = self + .client + .post(&format!("/v1/table/{}/flush_lsm/", self.identifier)); + self.send_lsm_route(request).await?; + Ok(()) + } + + async fn compact_lsm(&self) -> Result<()> { + let request = self + .client + .post(&format!("/v1/table/{}/compact_lsm/", self.identifier)); + self.send_lsm_route(request).await?; + Ok(()) + } + + async fn get_lsm_stats(&self, include_generation_rows: bool) -> Result> { + // Read-semantics POST, like `get_lsm_write_spec`. + let request = self + .post_read(&format!("/v1/table/{}/get_lsm_stats/", self.identifier)) + .json(&serde_json::json!({ + "include_generation_rows": include_generation_rows, + })); + let (request_id, response) = self.send_lsm_route(request).await?; + let body = response.text().await.err_to_http(request_id.clone())?; + let parsed: GetLsmStatsResponse = serde_json::from_str(&body).map_err(|e| Error::Http { + source: format!("Failed to parse get_lsm_stats response: {e}").into(), + request_id, + status_code: None, + })?; + // `null` — and only — when the table has no LSM write path. + Ok(parsed.lsm_stats) + } + async fn set_lsm_write_spec(&self, spec: LsmWriteSpec) -> Result<()> { self.check_mutable().await?; @@ -6682,6 +6730,499 @@ mod tests { assert!(table.get_lsm_write_spec().await.unwrap().is_none()); } + /// Build a `get_lsm_stats` body for one bucket holding `generations`. + fn stats_body(generations: &[u64], compacting: bool) -> String { + serde_json::json!({ + "lsm_stats": { + "buckets": [{ + "shard_id": "b0", + "status": "Active", + "writer_epoch": 1, + "manifest_version": 1, + "current_generation": generations.iter().max().copied().unwrap_or(0) + 1, + "replay_after_wal_entry_position": 0, + "wal_entry_position_last_seen": 0, + "generations": generations.iter() + .map(|g| serde_json::json!({ "generation": g, "bytes": 1 })) + .collect::>(), + "compacting": compacting, + "memtables": [], + }], + } + }) + .to_string() + } + + /// `flush_lsm` / `compact_lsm` answer 202 with no body at all. + fn accepted() -> http::Response { + http::Response::builder() + .status(202) + .body(String::new()) + .unwrap() + } + + fn ok_json(body: String) -> http::Response { + http::Response::builder().status(200).body(body).unwrap() + } + + /// A flush landing in an empty L0 finishes on the opening stats read + /// alone. Asserting zero compacts is the point: "it returned Ok" is also + /// true of a loop that ran a pointless pass. + #[tokio::test(start_paused = true)] + async fn test_checkpoint_short_circuits_on_empty_l0() { + let compacts = Arc::new(std::sync::atomic::AtomicUsize::new(0)); + let seen = compacts.clone(); + let table = Table::new_with_handler("my_table", move |request| { + let path = request.url().path().to_string(); + if path.contains("compact_lsm") { + seen.fetch_add(1, std::sync::atomic::Ordering::SeqCst); + panic!("an already-converged table must issue no compact calls"); + } + if path.contains("flush_lsm") { + return accepted(); + } + assert_eq!(path, "/v1/table/my_table/get_lsm_stats/"); + ok_json(stats_body(&[], false)) + }); + + table.checkpoint_lsm().await.unwrap(); + assert_eq!(compacts.load(std::sync::atomic::Ordering::SeqCst), 0); + } + + /// The loop triggers compaction until every generation that existed at + /// the start is gone, one bounded prefix per pass. + #[tokio::test(start_paused = true)] + async fn test_checkpoint_triggers_until_targets_are_drained() { + let compacts = Arc::new(std::sync::atomic::AtomicUsize::new(0)); + let seen = compacts.clone(); + let table = Table::new_with_handler("my_table", move |request| { + let path = request.url().path().to_string(); + if path.contains("flush_lsm") { + return accepted(); + } + if path.contains("compact_lsm") { + seen.fetch_add(1, std::sync::atomic::Ordering::SeqCst); + return accepted(); + } + // Each pass drains the oldest generation. + let drained = seen.load(std::sync::atomic::Ordering::SeqCst); + let left: Vec = [1u64, 2, 3].into_iter().skip(drained).collect(); + ok_json(stats_body(&left, false)) + }); + + table.checkpoint_lsm().await.unwrap(); + assert_eq!( + compacts.load(std::sync::atomic::Ordering::SeqCst), + 3, + "one trigger per generation prefix, then stop" + ); + } + + /// Generations created *during* the checkpoint are not waited on, which + /// is what lets the loop terminate on a table taking writes where "L0 is + /// empty" never becomes true. + #[tokio::test(start_paused = true)] + async fn test_checkpoint_ignores_generations_created_while_it_runs() { + let compacts = Arc::new(std::sync::atomic::AtomicUsize::new(0)); + let seen = compacts.clone(); + let table = Table::new_with_handler("my_table", move |request| { + let path = request.url().path().to_string(); + if path.contains("flush_lsm") { + return accepted(); + } + if path.contains("compact_lsm") { + seen.fetch_add(1, std::sync::atomic::Ordering::SeqCst); + return accepted(); + } + // Target is 5. One pass drains it; a writer keeps adding above. + let n = seen.load(std::sync::atomic::Ordering::SeqCst); + let body = if n == 0 { + stats_body(&[5], false) + } else { + stats_body(&[6, 7], false) + }; + ok_json(body) + }); + + table.checkpoint_lsm().await.unwrap(); + assert_eq!( + compacts.load(std::sync::atomic::Ordering::SeqCst), + 1, + "the loop must not chase generations written after it started" + ); + } + + /// Contention is a 429 and must be retried. The server keeps it off 503 + /// precisely so the client can act on the status alone — reading it as + /// terminal stops the checkpoint early on a healthy node. + #[tokio::test(start_paused = true)] + async fn test_checkpoint_retries_contention() { + let compacts = Arc::new(std::sync::atomic::AtomicUsize::new(0)); + let seen = compacts.clone(); + let table = Table::new_with_handler("my_table", move |request| { + let path = request.url().path().to_string(); + if path.contains("flush_lsm") { + return accepted(); + } + if path.contains("compact_lsm") { + // First two triggers: every bucket already latched. + if seen.fetch_add(1, std::sync::atomic::Ordering::SeqCst) < 2 { + return http::Response::builder() + .status(429) + .body(r#"{"code":21,"error":"Too many concurrent writes"}"#.to_string()) + .unwrap(); + } + return accepted(); + } + let accepted_triggers = seen + .load(std::sync::atomic::Ordering::SeqCst) + .saturating_sub(2); + let left: Vec = if accepted_triggers == 0 { + vec![1] + } else { + vec![] + }; + ok_json(stats_body(&left, false)) + }); + + table + .checkpoint_lsm() + .await + .expect("contention must not abort the checkpoint"); + assert_eq!( + compacts.load(std::sync::atomic::Ordering::SeqCst), + 3, + "assert the retry count, not just the outcome" + ); + } + + /// A transient fault on the poll must not abort the checkpoint. This route + /// meets the most contention — it runs every `POLL_INTERVAL` for the + /// checkpoint's whole life, with the transport retry layer disabled — yet + /// was the one call reached with a bare `?`. + #[tokio::test(start_paused = true)] + async fn test_checkpoint_retries_a_contended_stats_poll() { + let polls = Arc::new(std::sync::atomic::AtomicUsize::new(0)); + let seen = polls.clone(); + let table = Table::new_with_handler("my_table", move |request| { + let path = request.url().path().to_string(); + if path.contains("flush_lsm") || path.contains("compact_lsm") { + return accepted(); + } + // The opening read lands; the next two polls are latched out. + let n = seen.fetch_add(1, std::sync::atomic::Ordering::SeqCst); + if (1..3).contains(&n) { + return http::Response::builder() + .status(429) + .body(r#"{"code":21,"error":"Too many concurrent writes"}"#.to_string()) + .unwrap(); + } + ok_json(stats_body(if n < 4 { &[1] } else { &[] }, false)) + }); + + table + .checkpoint_lsm() + .await + .expect("a contended poll must be retried, not surfaced"); + assert_eq!( + polls.load(std::sync::atomic::Ordering::SeqCst), + 5, + "the two rejected polls must be re-issued, not skipped" + ); + } + + /// Contention and a lost claim draw on separate budgets: five straight + /// 429s on `flush`, more than `MAX_REISSUES`, must still converge. On one + /// shared counter this spent the re-issue cap and then reported a lost + /// claim nothing had ever reported. + #[tokio::test(start_paused = true)] + async fn test_contention_does_not_exhaust_the_reissue_budget() { + let flushes = Arc::new(std::sync::atomic::AtomicUsize::new(0)); + let seen = flushes.clone(); + let table = Table::new_with_handler("my_table", move |request| { + let path = request.url().path().to_string(); + if path.contains("flush_lsm") { + if seen.fetch_add(1, std::sync::atomic::Ordering::SeqCst) < 5 { + return http::Response::builder() + .status(429) + .body(r#"{"code":21,"error":"Too many concurrent writes"}"#.to_string()) + .unwrap(); + } + return accepted(); + } + if path.contains("compact_lsm") { + return accepted(); + } + ok_json(stats_body(&[], false)) + }); + + table + .checkpoint_lsm() + .await + .expect("contention must not be reported as a lost claim"); + assert_eq!( + flushes.load(std::sync::atomic::Ordering::SeqCst), + 6, + "five retries against one seal, then it lands" + ); + } + + /// An exhausted retry budget surfaces the fault that consumed it, not a + /// message the loop invented: "429, nine times" points an operator at a + /// saturated pool, a generic runtime error points them nowhere. + #[tokio::test(start_paused = true)] + async fn test_exhausted_retries_surface_the_underlying_fault() { + let calls = Arc::new(std::sync::atomic::AtomicUsize::new(0)); + let seen = calls.clone(); + let table = Table::new_with_handler("my_table", move |_request| { + seen.fetch_add(1, std::sync::atomic::Ordering::SeqCst); + http::Response::builder() + .status(429) + .body(r#"{"code":21,"error":"Too many concurrent writes"}"#.to_string()) + .unwrap() + }); + + let err = table.checkpoint_lsm().await.unwrap_err(); + assert!( + matches!(&err, Error::Http { status_code: Some(s), .. } if s.as_u16() == 429), + "the fault that spent the budget must be the one reported: {err:?}" + ); + assert_eq!( + calls.load(std::sync::atomic::Ordering::SeqCst), + 9, + "one call plus MAX_RETRIES — the re-issue budget is not spent on top" + ); + } + + /// A draining node is terminal, but the client does not know that from the + /// status: draining and a proxy blip are both 503, and telling them apart + /// takes parsing the body for a namespace code. So it spends the retry + /// budget and then reports what the server said — the drain gate never + /// releases, so the answer does not change, and the operator still reads + /// "WAL node draining" in the error. + #[tokio::test(start_paused = true)] + async fn test_draining_surfaces_after_the_retry_budget() { + let calls = Arc::new(std::sync::atomic::AtomicUsize::new(0)); + let seen = calls.clone(); + let table = Table::new_with_handler("my_table", move |_request| { + seen.fetch_add(1, std::sync::atomic::Ordering::SeqCst); + http::Response::builder() + .status(503) + .body(r#"{"code":19,"error":"WAL node draining"}"#.to_string()) + .unwrap() + }); + + let err = table.checkpoint_lsm().await.unwrap_err(); + let message = err.to_string(); + assert!( + matches!(&err, Error::Http { status_code: Some(s), .. } if s.as_u16() == 503), + "the 503 must surface as itself: {err:?}" + ); + assert!( + message.contains("WAL node draining"), + "the server's own diagnosis must survive to the caller: {message}" + ); + assert_eq!( + calls.load(std::sync::atomic::Ordering::SeqCst), + 9, + "one call plus MAX_RETRIES, then it reports rather than spinning" + ); + } + + /// A long stall with nothing compacting must keep waiting, not fail. The + /// client cannot judge this: a checkpoint queued behind unrelated tables + /// on the pod-wide compactor pool reports exactly these numbers — flat + /// generations, an idle latch — as one whose merges are failing. The + /// deadline is the caller's. + #[tokio::test(start_paused = true)] + async fn test_checkpoint_waits_out_a_long_stall_rather_than_failing() { + let polls = Arc::new(std::sync::atomic::AtomicUsize::new(0)); + let seen = polls.clone(); + let table = Table::new_with_handler("my_table", move |request| { + let path = request.url().path().to_string(); + if path.contains("flush_lsm") || path.contains("compact_lsm") { + return accepted(); + } + // Flat for far longer than any bound this loop ever had, with + // `compacting: false` throughout — then it drains. + let n = seen.fetch_add(1, std::sync::atomic::Ordering::SeqCst); + ok_json(stats_body(if n < 40 { &[1, 2] } else { &[] }, false)) + }); + + table + .checkpoint_lsm() + .await + .expect("a stall is the server being slow, not the client's call to make"); + assert!( + polls.load(std::sync::atomic::Ordering::SeqCst) > 40, + "the loop must have kept polling well past the old ten-poll bound" + ); + } + + /// A pass already owns the latch on every outstanding bucket, so the loop + /// waits rather than piling on triggers it would only refuse. This is the + /// sole thing `compacting` is read for. + #[tokio::test(start_paused = true)] + async fn test_checkpoint_waits_while_a_pass_is_running() { + let polls = Arc::new(std::sync::atomic::AtomicUsize::new(0)); + let compacts = Arc::new(std::sync::atomic::AtomicUsize::new(0)); + let seen_polls = polls.clone(); + let seen_compacts = compacts.clone(); + let table = Table::new_with_handler("my_table", move |request| { + let path = request.url().path().to_string(); + if path.contains("flush_lsm") { + return accepted(); + } + if path.contains("compact_lsm") { + seen_compacts.fetch_add(1, std::sync::atomic::Ordering::SeqCst); + return accepted(); + } + // Latched for many polls, then done. + let n = seen_polls.fetch_add(1, std::sync::atomic::Ordering::SeqCst); + ok_json(if n > 15 { + stats_body(&[], false) + } else { + stats_body(&[1], true) + }) + }); + + table + .checkpoint_lsm() + .await + .expect("a running pass is progress, not a stall"); + assert_eq!( + compacts.load(std::sync::atomic::Ordering::SeqCst), + 0, + "never trigger against a bucket already compacting" + ); + } + + /// WAL off ⇒ `None`; WAL on ⇒ a fully populated `Some` with no field + /// defaulting to a zero it did not measure. `include_generation_rows` + /// rides in the body and is off unless asked for. + #[tokio::test] + async fn test_get_lsm_stats_round_trip() { + let table = Table::new_with_handler("my_table", |request| { + assert_eq!(request.url().path(), "/v1/table/my_table/get_lsm_stats/"); + let body = request.body().unwrap().as_bytes().unwrap(); + let body: serde_json::Value = serde_json::from_slice(body).unwrap(); + assert_eq!( + body["include_generation_rows"], true, + "the flag must reach the server, not be silently dropped" + ); + let response = serde_json::json!({ + "lsm_stats": { + "buckets": [{ + "shard_id": "b0", + "status": "Active", + "writer_epoch": 3, + "manifest_version": 11, + "current_generation": 9, + "replay_after_wal_entry_position": 100, + "wal_entry_position_last_seen": 140, + "generations": [{ "generation": 8, "bytes": 4096, "rows": 30 }], + "compacting": false, + "memtables": [ + { "generation": 9, "rows": 12, "bytes": 900, "batches": 2, + "indexes": ["vec_idx"] } + ], + }], + } + }); + http::Response::builder() + .status(200) + .body(response.to_string()) + .unwrap() + }); + + let stats = table + .get_lsm_stats(true) + .await + .unwrap() + .expect("a WAL-backed table reports Some"); + let bucket = &stats.buckets[0]; + assert_eq!(bucket.replay_after_wal_entry_position, 100); + assert_eq!(bucket.wal_entry_position_last_seen, 140); + assert!(!bucket.compacting); + assert_eq!(bucket.generations[0].generation, 8); + assert_eq!(bucket.generations[0].rows, Some(30)); + // The line that answers "why is my fresh-tier vector search + // brute-force" — an absent index name is the whole explanation. + let memtables = bucket.memtables.as_ref().unwrap(); + assert_eq!(memtables[0].indexes, vec!["vec_idx".to_string()]); + } + + /// A 404 arrives as `TableNotFound`, not as a lost claim the loop + /// re-issues from flush until its cap. The two are distinguished by + /// status: 404 is "no such table", 421 is "this node holds no claim". + /// They shared 404 once, and the loop chased a name that never existed. + #[tokio::test(start_paused = true)] + async fn test_missing_table_is_not_read_as_a_lost_claim() { + let calls = Arc::new(std::sync::atomic::AtomicUsize::new(0)); + let seen = calls.clone(); + let table = Table::new_with_handler("my_table", move |_request| { + seen.fetch_add(1, std::sync::atomic::Ordering::SeqCst); + http::Response::builder() + .status(404) + .body(r#"{"code":4,"error":"Not found: Table not found: my_table"}"#.to_string()) + .unwrap() + }); + + let err = table.checkpoint_lsm().await.unwrap_err(); + assert!( + matches!(err, Error::TableNotFound { .. }), + "a missing table must say so: {err:?}" + ); + assert_eq!( + calls.load(std::sync::atomic::Ordering::SeqCst), + 1, + "no point re-claiming a table that does not exist" + ); + } + + /// A lost claim — 421, not 404 — does re-issue from flush, the call that + /// re-claims and replays. + #[tokio::test(start_paused = true)] + async fn test_registry_miss_reissues_from_flush() { + let calls = Arc::new(std::sync::atomic::AtomicUsize::new(0)); + let seen = calls.clone(); + let table = Table::new_with_handler("my_table", move |request| { + let path = request.url().path().to_string(); + let n = seen.fetch_add(1, std::sync::atomic::Ordering::SeqCst); + if path.contains("flush_lsm") { + // First flush lands; the claim is then lost, and the + // re-issued flush succeeds. + return accepted(); + } + if path.contains("compact_lsm") { + if n < 4 { + return http::Response::builder() + .status(421) + .body(r#"{"code":19,"error":"table not claimed"}"#.to_string()) + .unwrap(); + } + return accepted(); + } + ok_json(stats_body(if n < 6 { &[1] } else { &[] }, false)) + }); + + table + .checkpoint_lsm() + .await + .expect("a lost claim must be recovered by re-flushing, not surfaced"); + } + + #[tokio::test] + async fn test_get_lsm_stats_absent_when_wal_off() { + let table = Table::new_with_handler("my_table", |_request| { + http::Response::builder() + .status(200) + .body(serde_json::json!({ "lsm_stats": null }).to_string()) + .unwrap() + }); + assert!(table.get_lsm_stats(false).await.unwrap().is_none()); + } + #[tokio::test] async fn test_wait_for_index() { let table = _make_table_with_indices(0); diff --git a/rust/lancedb/src/table.rs b/rust/lancedb/src/table.rs index 0d8a8e8b9..74ab17921 100644 --- a/rust/lancedb/src/table.rs +++ b/rust/lancedb/src/table.rs @@ -68,10 +68,12 @@ use self::merge::MergeInsertBuilder; pub mod add_columns; mod add_data; pub mod branch_merge; +pub mod checkpoint; mod create_index; pub mod datafusion; pub(crate) mod dataset; pub mod delete; +pub mod lsm_stats; pub mod merge; pub mod optimize; mod primary_key; @@ -95,6 +97,7 @@ pub use lance::dataset::refs::{BranchContents, Ref, TagContents, Tags as LanceTa pub use lance::dataset::scanner::DatasetRecordBatchStream; use lance::dataset::statistics::DatasetStatisticsExt; pub use lance_index::optimize::OptimizeOptions; +pub use lsm_stats::{BucketStats, GenerationStats, LsmStats, MemtableStats}; pub use optimize::{CompactionOptions, OptimizeAction, OptimizeStats}; pub use schema_evolution::{ AddColumnsResult, AlterColumnsResult, DropColumnsResult, FieldMetadataUpdate, @@ -685,6 +688,31 @@ pub trait BaseTable: std::fmt::Display + std::fmt::Debug + Send + Sync { message: "get_lsm_write_spec is not supported on this table type".into(), }) } + /// Seal every bucket's active memtable into L0. + /// + /// The default implementation returns `NotSupported`. + async fn flush_lsm(&self) -> Result<()> { + Err(Error::NotSupported { + message: "flush_lsm is not supported on this table type".into(), + }) + } + /// Trigger a background L0 → base compaction pass per bucket. + /// + /// The default implementation returns `NotSupported`. + async fn compact_lsm(&self) -> Result<()> { + Err(Error::NotSupported { + message: "compact_lsm is not supported on this table type".into(), + }) + } + /// Read live LSM state, or `None` when the LSM write path is not + /// enabled for this table. + /// + /// The default implementation returns `NotSupported`. + async fn get_lsm_stats(&self, _include_generation_rows: bool) -> Result> { + Err(Error::NotSupported { + message: "get_lsm_stats is not supported on this table type".into(), + }) + } /// Drain and close any cached MemWAL shard writers for this table. /// /// The default implementation is a no-op; table types that maintain @@ -1726,6 +1754,85 @@ impl Table { self.inner.get_lsm_write_spec().await } + /// Converge this table's LSM write path into its base table. + /// + /// One `flush` to seal every memtable into L0, then compaction triggers + /// until every generation that existed at that moment has reached base. + /// The loop runs client-side, reading progress from `get_lsm_stats`, so + /// there is no held socket and nothing to reconcile if you drop this + /// future partway through. + /// + /// **Best-effort.** Generations created *after* the opening flush are + /// deliberately not waited on — that is what lets this terminate on a + /// table taking writes. Idempotent and safe on a cadence: an + /// already-converged table costs two round trips and triggers nothing. + /// + /// **No deadline, and the caller owns that.** It returns when the target + /// generations are gone, propagates a terminal server fault, and + /// otherwise waits however long the server takes. A slow table and a + /// stuck one are the same picture from here: the compactor pool is shared + /// across every table on the node, so a checkpoint queued behind + /// unrelated work is indistinguishable from one that is merging. Wrap + /// this in `tokio::time::timeout` for a wall-clock bound; abandoning it + /// partway costs nothing. + /// + /// # Example + /// + /// ```no_run + /// # use lancedb::Table; + /// # async fn example(table: &Table) -> Result<(), Box> { + /// let before = table.get_lsm_stats(false).await?; + /// table.checkpoint_lsm().await?; + /// let after = table.get_lsm_stats(false).await?; + /// # Ok(()) + /// # } + /// ``` + pub async fn checkpoint_lsm(&self) -> Result<()> { + checkpoint::checkpoint_lsm(self).await + } + + /// Seal every bucket's active memtable into L0 without touching the + /// base table. + /// + /// Independently useful: flushing makes memtable rows readable from L0 at + /// a lower per-query cost. On a node that has not claimed this table it + /// claims it and replays the WAL log first — reporting "nothing to flush" + /// without replaying would lie about durable data. + pub async fn flush_lsm(&self) -> Result<()> { + self.inner.flush_lsm().await + } + + /// Run one bounded L0 → base compaction pass per bucket, reporting what + /// it merged and what is left. + /// + /// One pass, not convergence: that bounds each request's cost and gives a + /// caller driving its own cadence a progress signal per round trip. + pub async fn compact_lsm(&self) -> Result<()> { + self.inner.compact_lsm().await + } + + /// Read live per-bucket LSM state. + /// + /// Answers "how far behind is my fresh tier", "which bucket is hot", and + /// "why is my fresh-tier vector search brute-force". Mutates no table + /// state, though on a node that has not claimed this table it claims it, + /// exactly as a read would. + /// + /// `include_generation_rows` reports a row count per L0 generation. Off by + /// default: each count opens an uncached Lance dataset, and + /// `checkpoint_lsm` polls this needing only generation numbers. + /// + /// `Ok(None)` only when the LSM write path is not enabled, matching + /// [`Table::get_lsm_write_spec`]. Stats is fresh-tier only, so with the + /// WAL off there is no manifest to report and a struct of zeros would + /// read as measurements. + /// + /// Do not build a checkpoint's termination on this: the completion + /// predicate lives in the `flush` and `compact` responses. + pub async fn get_lsm_stats(&self, include_generation_rows: bool) -> Result> { + self.inner.get_lsm_stats(include_generation_rows).await + } + /// Drain and close any cached MemWAL shard writers held for this table. /// /// When an [`LsmWriteSpec`] is installed, `merge_insert` opens MemWAL shard diff --git a/rust/lancedb/src/table/checkpoint.rs b/rust/lancedb/src/table/checkpoint.rs new file mode 100644 index 000000000..bb76604ed --- /dev/null +++ b/rust/lancedb/src/table/checkpoint.rs @@ -0,0 +1,315 @@ +// SPDX-License-Identifier: Apache-2.0 +// SPDX-FileCopyrightText: Copyright The LanceDB Authors + +//! Converging a table's LSM write path into its base table. +//! +//! `checkpoint_lsm` seals once, then triggers compaction and watches +//! generation numbers until the L0 that existed at the start is gone. +//! +//! The loop runs in the client, not the server: `compact_lsm` dispatches a +//! pass and returns, so nothing holds a socket and a client can vanish +//! mid-operation with nothing to reconcile. Completion is read from +//! generation numbers in the shard manifest — durable state, unlike a count +//! in a compact response, which a concurrent write invalidates. +//! +//! The target set is fixed at the start, so generations created *during* the +//! checkpoint are ignored. That is what lets it terminate under write load, +//! and what makes it best-effort: it converges the fresh tier as of some +//! instant. Idempotent, abandonable at any point, safe on a cadence. +//! +//! No liveness bound — the caller owns the deadline. The compactor pool is +//! shared pod-wide, so a checkpoint queued behind unrelated tables looks +//! exactly like one that is merging. + +use std::collections::HashMap; +use std::future::Future; +use std::time::Duration; + +use crate::{Error, Result, Table}; + +/// The HTTP status a failed request carried, if it carried one. +/// +/// `None` for anything with no retry story: a `TableNotFound` that +/// `check_table_response` already translated, or a connection failure that +/// never reached the server. Both are terminal. +fn status_of(e: &Error) -> Option { + #[cfg(feature = "remote")] + { + match e { + Error::Http { + status_code: Some(status), + .. + } => Some(status.as_u16()), + _ => None, + } + } + #[cfg(not(feature = "remote"))] + { + let _ = e; + None + } +} + +/// 429 (latch held, pool saturated, or the pod replaying its WAL) and 503 (a +/// draining node, or a proxy between here and it). +/// +/// The status is the whole signal: the server deliberately keeps contention +/// off 503, so a latch collision is a 429. A draining node *is* terminal, but +/// it is also a 503 that stays a 503, so retrying spends one budget and then +/// reports the server's own message — cheaper than parsing the body for the +/// namespace code it would take to tell the two apart. +fn is_retryable(e: &Error) -> bool { + matches!(status_of(e), Some(429 | 503)) +} + +/// 421: the owning node holds no claim. Only `flush` re-claims and replays, +/// so this cannot be retried in place — the caller has to start over. +fn is_lost_claim(e: &Error) -> bool { + status_of(e) == Some(421) +} + +/// Interval between `get_lsm_stats` polls. One interval is roughly one +/// compaction pass, the granularity at which the answer can change. +/// +/// Fixed rather than configurable, matching `wait_for_index`. It costs +/// nothing on an already-converged table and at most one interval of tail +/// latency after the final pass lands. +const POLL_INTERVAL: Duration = Duration::from_secs(5); + +/// Cap on re-issues from `flush` after a 421, so a crash-looping node cannot +/// turn flush → compact → 421 → flush into a spin. +/// +/// Deliberately not shared with [`MAX_RETRIES`]: a claim that keeps +/// evaporating is a broken node, while contention is routine and wants a real +/// budget. One shared counter let a merely contended table exhaust this cap +/// and then blame a claim it never lost. +const MAX_REISSUES: usize = 3; + +/// Retryable faults tolerated on a *single* request, reset on every success — +/// scattered contention across a long checkpoint must not accumulate toward a +/// cap. Roughly 16s of retrying against the backoff below. +const MAX_RETRIES: usize = 8; + +/// Backoff between retries, doubling up to [`RETRY_BACKOFF_MAX`]. Latch +/// contention clears in about the time one pass takes, so start small; a +/// saturated pool wants the ceiling. +const RETRY_BACKOFF_BASE: Duration = Duration::from_millis(100); +const RETRY_BACKOFF_MAX: Duration = Duration::from_secs(5); + +/// Sleep before re-issuing a retryable request. +async fn backoff(attempt: usize) { + let delay = RETRY_BACKOFF_BASE + .saturating_mul(1u32 << attempt.min(8) as u32) + .min(RETRY_BACKOFF_MAX); + tokio::time::sleep(delay).await; +} + +/// Whether the drain loop finished or needs the table re-claimed first. +#[derive(Debug, Clone, Copy, PartialEq, Eq)] +enum CheckpointOutcome { + Done, + ReissueFromFlush, +} + +/// What one LSM request produced: its value, or word that the owning node +/// holds no claim and only `flush` can get it back. +enum Attempt { + Ok(T), + ReissueFromFlush, +} + +/// Issue one LSM request, retrying in place while the fault is retryable. +/// +/// The two recoverable faults have separate budgets: contention clears on its +/// own and retries here against [`MAX_RETRIES`], while a 421 needs `flush` to +/// re-claim, which only the caller can drive. +/// +/// An exhausted budget propagates the last error *as itself* rather than a +/// synthesized one — "429 after nine tries" beats "checkpoint failed", and a +/// draining node arrives carrying the server's own message. +async fn issue(mut call: F) -> Result> +where + F: FnMut() -> Fut, + Fut: Future>, +{ + let mut retries = 0; + loop { + let e = match call().await { + Ok(value) => return Ok(Attempt::Ok(value)), + Err(e) => e, + }; + if is_lost_claim(&e) { + return Ok(Attempt::ReissueFromFlush); + } + if !is_retryable(&e) || retries >= MAX_RETRIES { + return Err(e); + } + backoff(retries).await; + retries += 1; + } +} + +/// Drive [`Table::checkpoint_lsm`]: seal once, fix the target watermark +/// from the resulting L0, then trigger and poll until it drains. +pub(crate) async fn checkpoint_lsm(table: &Table) -> Result<()> { + for reissue in 0..=MAX_REISSUES { + // The seal turns everything written before this call into a + // generation, so the watermark has to be read after it. Idempotent: + // sealing an empty memtable is a no-op, so a re-issue does not churn + // empty generations. + match issue(|| table.flush_lsm()).await? { + Attempt::Ok(()) => {} + Attempt::ReissueFromFlush => { + backoff(reissue).await; + continue; + } + } + + let stats = match issue(|| table.get_lsm_stats(false)).await? { + Attempt::Ok(stats) => stats, + Attempt::ReissueFromFlush => { + backoff(reissue).await; + continue; + } + }; + let Some(stats) = stats else { + // Not WAL-backed; `flush_lsm` would have errored first but for a race. + return Ok(()); + }; + let targets: HashMap = stats + .buckets + .iter() + .filter_map(|b| Some((b.shard_id.clone(), b.newest_generation()?))) + .collect(); + if targets.is_empty() { + return Ok(()); + } + + match drain_to_targets(table, &targets).await? { + CheckpointOutcome::Done => return Ok(()), + CheckpointOutcome::ReissueFromFlush => { + backoff(reissue).await; + continue; + } + } + } + Err(Error::Runtime { + message: "checkpoint_lsm: the owning node kept losing its claim; \ + re-issued from flush the maximum number of times" + .into(), + }) +} + +/// Trigger and poll until no bucket holds a generation at or below its +/// target. +/// +/// No liveness bound, deliberately. The pod-wide compactor pool (a semaphore +/// of 2 by default, shared across every table on the node) is taken *inside* +/// the pass, after the bucket latch, so a checkpoint queued behind unrelated +/// tables is indistinguishable from one that is merging. An idle-poll counter +/// here could only ever have fired on a table that would have finished. +async fn drain_to_targets( + table: &Table, + targets: &HashMap, +) -> Result { + loop { + let stats = match issue(|| table.get_lsm_stats(false)).await? { + Attempt::Ok(stats) => stats, + Attempt::ReissueFromFlush => return Ok(CheckpointOutcome::ReissueFromFlush), + }; + let Some(stats) = stats else { + return Ok(CheckpointOutcome::Done); + }; + // `compacting` is the bucket's compaction latch, held from dispatch + // until the pass ends — including while it waits on the pod-wide + // permit. So it answers one question only: do not pile on. Buckets + // with nothing outstanding are skipped, not counted as idle. + let mut outstanding = 0; + let mut all_compacting = true; + for b in &stats.buckets { + let Some(target) = targets.get(&b.shard_id) else { + continue; + }; + let n = b.outstanding_generations(*target); + if n > 0 { + outstanding += n; + all_compacting &= b.compacting; + } + } + if outstanding == 0 { + return Ok(CheckpointOutcome::Done); + } + + if !all_compacting { + match table.compact_lsm().await { + Ok(()) => {} + Err(e) if is_lost_claim(&e) => return Ok(CheckpointOutcome::ReissueFromFlush), + Err(e) if !is_retryable(&e) => return Err(e), + // A 429 here means the server could latch no bucket at all, + // which the poll above already handles. Not retried in place: + // the latch it would contend for is the one doing the work, so + // fall through and re-read — `POLL_INTERVAL` is the backoff. + Err(_) => {} + } + } + tokio::time::sleep(POLL_INTERVAL).await; + } +} + +#[cfg(all(test, feature = "remote"))] +mod tests { + use super::*; + + fn http(status: u16) -> Error { + Error::Http { + source: "server said no".into(), + request_id: "rid".into(), + status_code: reqwest::StatusCode::from_u16(status).ok(), + } + } + + /// Every status the loop acts on. The two predicates are checked together + /// because their overlap is what would be wrong: a status must never be + /// both, and 421 in particular must not read as retryable — retrying it in + /// place re-issues the call that just said the node holds no claim. + #[test] + fn taxonomy_round_trips() { + for status in [429, 503] { + assert!(is_retryable(&http(status)), "{status} must retry"); + assert!( + !is_lost_claim(&http(status)), + "{status} is not a lost claim" + ); + } + assert!(is_lost_claim(&http(421)), "a lost claim must re-claim"); + assert!( + !is_retryable(&http(421)), + "retrying a lost claim in place only asks the same node again" + ); + for status in [400, 404, 409, 500] { + assert!(!is_retryable(&http(status)), "{status} is terminal"); + assert!(!is_lost_claim(&http(status)), "{status} is terminal"); + } + } + + /// An error carrying no status has no retry story and must be terminal — + /// a connection that never reached the server, or a `TableNotFound` that + /// `check_table_response` translated before the loop saw it. + #[test] + fn errors_without_a_status_are_terminal() { + let no_status = Error::Http { + source: "connection reset".into(), + request_id: "rid".into(), + status_code: None, + }; + assert!(!is_retryable(&no_status)); + assert!(!is_lost_claim(&no_status)); + + let translated = Error::TableNotFound { + name: "t".into(), + source: "gone".into(), + }; + assert!(!is_retryable(&translated)); + assert!(!is_lost_claim(&translated)); + } +} diff --git a/rust/lancedb/src/table/lsm_stats.rs b/rust/lancedb/src/table/lsm_stats.rs new file mode 100644 index 000000000..953aea90f --- /dev/null +++ b/rust/lancedb/src/table/lsm_stats.rs @@ -0,0 +1,162 @@ +// SPDX-License-Identifier: Apache-2.0 +// SPDX-FileCopyrightText: Copyright The LanceDB Authors + +//! Live per-bucket LSM state — the shape [`crate::Table::get_lsm_stats`] +//! returns and [`super::checkpoint`] polls. +//! +//! Nothing here is derived: sums and differences (total L0 bytes, WAL lag) +//! are the caller's to compute. There is no "WAL is off" shape — that case is +//! `None`, because a struct of zeros would read as measurements. + +use serde::Deserialize; + +/// One flushed L0 generation. +#[derive(Debug, Clone, Deserialize)] +pub struct GenerationStats { + pub generation: u64, + pub bytes: u64, + /// Present only when `include_generation_rows` was requested. Off by + /// default because each count opens an uncached Lance dataset, and the + /// checkpoint loop polls this route needing only generation numbers. + #[serde(default)] + pub rows: Option, +} + +/// One in-memory memtable. +#[derive(Debug, Clone, Deserialize)] +pub struct MemtableStats { + pub generation: u64, + pub rows: u64, + pub bytes: u64, + pub batches: u64, + /// Names of the indexes this memtable carries. An absent name is the whole + /// answer to "why is my fresh-tier search on that column brute-force". + pub indexes: Vec, +} + +/// Live state of one bucket. A table is N buckets on one node; flattening to +/// a single number hides the one hot bucket that is usually why someone +/// opened this endpoint. +#[derive(Debug, Clone, Deserialize)] +pub struct BucketStats { + pub shard_id: String, + /// `Active` | `Sealed` (drop-table 2PC in flight). + pub status: String, + pub writer_epoch: u64, + pub manifest_version: u64, + pub current_generation: u64, + pub replay_after_wal_entry_position: u64, + pub wal_entry_position_last_seen: u64, + pub generations: Vec, + /// Whether a pass owns this bucket's compaction latch right now. Says *a* + /// driver is running, not *whose*, and the latch is held from dispatch — + /// including while the pass queues for a pod-wide compactor permit. Read + /// it as "do not pile on", never as "mine is progressing". + pub compacting: bool, + /// Oldest first, active last. Absent for a `Sealed` bucket, whose + /// in-memory state is torn down. + #[serde(default)] + pub memtables: Option>, +} + +impl BucketStats { + /// The newest flushed generation, or `None` when L0 is empty. + pub(crate) fn newest_generation(&self) -> Option { + self.generations.iter().map(|g| g.generation).max() + } + + /// How many generations at or below `target` are still in L0. + /// + /// A count, not a boolean: one pass drains a bounded prefix rather than + /// the whole target set, so a boolean would read as "no progress" for + /// every pass but the last. Compaction drains oldest-first, so this + /// decreases monotonically. + pub(crate) fn outstanding_generations(&self, target: u64) -> usize { + self.generations + .iter() + .filter(|g| g.generation <= target) + .count() + } +} + +/// Live LSM state, one entry per bucket. +#[derive(Debug, Clone, Deserialize)] +pub struct LsmStats { + pub buckets: Vec, +} + +/// Server-side JSON envelope for `get_lsm_stats`. `lsm_stats` is null when +/// the table has no LSM write path. +#[derive(Debug, Deserialize)] +pub(crate) struct GetLsmStatsResponse { + #[serde(default)] + pub lsm_stats: Option, +} + +#[cfg(test)] +mod tests { + use super::*; + + fn bucket(shard: &str, generations: &[u64], compacting: bool) -> BucketStats { + BucketStats { + shard_id: shard.into(), + status: "Active".into(), + writer_epoch: 1, + manifest_version: 1, + current_generation: generations.iter().max().copied().unwrap_or(0) + 1, + replay_after_wal_entry_position: 0, + wal_entry_position_last_seen: 0, + generations: generations + .iter() + .map(|g| GenerationStats { + generation: *g, + bytes: 1, + rows: None, + }) + .collect(), + compacting, + memtables: None, + } + } + + /// The target watermark is the newest generation at the start, and a + /// generation created after it must not hold the loop open — that is why + /// the predicate terminates under write load. + #[test] + fn newer_generations_do_not_extend_the_target() { + let start = bucket("b0", &[7, 8], false); + let target = start.newest_generation().expect("L0 is non-empty"); + assert_eq!(target, 8); + + // Compaction drained 7 and 8; 9 and 10 arrived while it ran. + let later = bucket("b0", &[9, 10], false); + assert_eq!( + later.outstanding_generations(target), + 0, + "generations above the target are somebody else's problem" + ); + + // Still holding 8 means still outstanding. + assert_eq!( + bucket("b0", &[8, 9], false).outstanding_generations(target), + 1 + ); + } + + /// The metric counts generations, not buckets: a pass drains a bounded + /// prefix, so one bucket going 3 → 2 → 1 → 0 is three steps. + #[test] + fn progress_is_measured_in_generations() { + let target = 3; + let counts: Vec = [&[1u64, 2, 3][..], &[2, 3][..], &[3][..], &[][..]] + .iter() + .map(|gens| bucket("b0", gens, false).outstanding_generations(target)) + .collect(); + assert_eq!(counts, vec![3, 2, 1, 0]); + } + + #[test] + fn empty_l0_has_no_target() { + assert!(bucket("b0", &[], false).newest_generation().is_none()); + } +} From be290447d9fa156f17d3c1eea028bb532645f2f0 Mon Sep 17 00:00:00 2001 From: LanceDB Robot Date: Fri, 7 Aug 2026 11:54:32 -0700 Subject: [PATCH 02/14] chore: update lance dependency to v11.0.0-beta.3 (#3896) Updates the Rust workspace Lance dependencies and Java lance-core dependency to v11.0.0-beta.3. No compatibility fixes were required; all-features clippy and Rust formatting pass. Triggering tag: https://github.com/lance-format/lance/releases/tag/v11.0.0-beta.3 --- Cargo.lock | 86 ++++++++++++++++++++++++++-------------------------- Cargo.toml | 28 ++++++++--------- java/pom.xml | 2 +- 3 files changed, 58 insertions(+), 58 deletions(-) diff --git a/Cargo.lock b/Cargo.lock index 93e16c06d..f6186672c 100644 --- a/Cargo.lock +++ b/Cargo.lock @@ -3455,8 +3455,8 @@ checksum = "42703706b716c37f96a77aea830392ad231f44c9e9a67872fa5548707e11b11c" [[package]] name = "fsst" -version = "11.0.0-beta.2" -source = "git+https://github.com/lance-format/lance.git?tag=v11.0.0-beta.2#35da5d920159b49d1b53032652f7615ab699c160" +version = "11.0.0-beta.3" +source = "git+https://github.com/lance-format/lance.git?tag=v11.0.0-beta.3#f7d475539cefbd140cc46a828f3d843e68cd10f1" dependencies = [ "arrow-array", "rand 0.9.5", @@ -4815,8 +4815,8 @@ checksum = "e037a2e1d8d5fdbd49b16a4ea09d5d6401c1f29eca5ff29d03d3824dba16256a" [[package]] name = "lance" -version = "11.0.0-beta.2" -source = "git+https://github.com/lance-format/lance.git?tag=v11.0.0-beta.2#35da5d920159b49d1b53032652f7615ab699c160" +version = "11.0.0-beta.3" +source = "git+https://github.com/lance-format/lance.git?tag=v11.0.0-beta.3#f7d475539cefbd140cc46a828f3d843e68cd10f1" dependencies = [ "arc-swap", "arrow", @@ -4890,8 +4890,8 @@ dependencies = [ [[package]] name = "lance-arrow" -version = "11.0.0-beta.2" -source = "git+https://github.com/lance-format/lance.git?tag=v11.0.0-beta.2#35da5d920159b49d1b53032652f7615ab699c160" +version = "11.0.0-beta.3" +source = "git+https://github.com/lance-format/lance.git?tag=v11.0.0-beta.3#f7d475539cefbd140cc46a828f3d843e68cd10f1" dependencies = [ "arrow-array", "arrow-buffer", @@ -4913,7 +4913,7 @@ dependencies = [ [[package]] name = "lance-arrow-scalar" version = "58.0.0" -source = "git+https://github.com/lance-format/lance.git?tag=v11.0.0-beta.2#35da5d920159b49d1b53032652f7615ab699c160" +source = "git+https://github.com/lance-format/lance.git?tag=v11.0.0-beta.3#f7d475539cefbd140cc46a828f3d843e68cd10f1" dependencies = [ "arrow-array", "arrow-buffer", @@ -4927,7 +4927,7 @@ dependencies = [ [[package]] name = "lance-arrow-stats" version = "58.0.0" -source = "git+https://github.com/lance-format/lance.git?tag=v11.0.0-beta.2#35da5d920159b49d1b53032652f7615ab699c160" +source = "git+https://github.com/lance-format/lance.git?tag=v11.0.0-beta.3#f7d475539cefbd140cc46a828f3d843e68cd10f1" dependencies = [ "arrow-array", "arrow-schema", @@ -4936,8 +4936,8 @@ dependencies = [ [[package]] name = "lance-bitpacking" -version = "11.0.0-beta.2" -source = "git+https://github.com/lance-format/lance.git?tag=v11.0.0-beta.2#35da5d920159b49d1b53032652f7615ab699c160" +version = "11.0.0-beta.3" +source = "git+https://github.com/lance-format/lance.git?tag=v11.0.0-beta.3#f7d475539cefbd140cc46a828f3d843e68cd10f1" dependencies = [ "arrayref", "crunchy", @@ -4947,8 +4947,8 @@ dependencies = [ [[package]] name = "lance-core" -version = "11.0.0-beta.2" -source = "git+https://github.com/lance-format/lance.git?tag=v11.0.0-beta.2#35da5d920159b49d1b53032652f7615ab699c160" +version = "11.0.0-beta.3" +source = "git+https://github.com/lance-format/lance.git?tag=v11.0.0-beta.3#f7d475539cefbd140cc46a828f3d843e68cd10f1" dependencies = [ "arrow-array", "arrow-buffer", @@ -4988,8 +4988,8 @@ dependencies = [ [[package]] name = "lance-datafusion" -version = "11.0.0-beta.2" -source = "git+https://github.com/lance-format/lance.git?tag=v11.0.0-beta.2#35da5d920159b49d1b53032652f7615ab699c160" +version = "11.0.0-beta.3" +source = "git+https://github.com/lance-format/lance.git?tag=v11.0.0-beta.3#f7d475539cefbd140cc46a828f3d843e68cd10f1" dependencies = [ "arrow", "arrow-array", @@ -5019,8 +5019,8 @@ dependencies = [ [[package]] name = "lance-datagen" -version = "11.0.0-beta.2" -source = "git+https://github.com/lance-format/lance.git?tag=v11.0.0-beta.2#35da5d920159b49d1b53032652f7615ab699c160" +version = "11.0.0-beta.3" +source = "git+https://github.com/lance-format/lance.git?tag=v11.0.0-beta.3#f7d475539cefbd140cc46a828f3d843e68cd10f1" dependencies = [ "arrow", "arrow-array", @@ -5037,8 +5037,8 @@ dependencies = [ [[package]] name = "lance-derive" -version = "11.0.0-beta.2" -source = "git+https://github.com/lance-format/lance.git?tag=v11.0.0-beta.2#35da5d920159b49d1b53032652f7615ab699c160" +version = "11.0.0-beta.3" +source = "git+https://github.com/lance-format/lance.git?tag=v11.0.0-beta.3#f7d475539cefbd140cc46a828f3d843e68cd10f1" dependencies = [ "proc-macro2", "quote", @@ -5047,8 +5047,8 @@ dependencies = [ [[package]] name = "lance-encoding" -version = "11.0.0-beta.2" -source = "git+https://github.com/lance-format/lance.git?tag=v11.0.0-beta.2#35da5d920159b49d1b53032652f7615ab699c160" +version = "11.0.0-beta.3" +source = "git+https://github.com/lance-format/lance.git?tag=v11.0.0-beta.3#f7d475539cefbd140cc46a828f3d843e68cd10f1" dependencies = [ "arrow-arith", "arrow-array", @@ -5082,8 +5082,8 @@ dependencies = [ [[package]] name = "lance-file" -version = "11.0.0-beta.2" -source = "git+https://github.com/lance-format/lance.git?tag=v11.0.0-beta.2#35da5d920159b49d1b53032652f7615ab699c160" +version = "11.0.0-beta.3" +source = "git+https://github.com/lance-format/lance.git?tag=v11.0.0-beta.3#f7d475539cefbd140cc46a828f3d843e68cd10f1" dependencies = [ "arrow-arith", "arrow-array", @@ -5114,8 +5114,8 @@ dependencies = [ [[package]] name = "lance-index" -version = "11.0.0-beta.2" -source = "git+https://github.com/lance-format/lance.git?tag=v11.0.0-beta.2#35da5d920159b49d1b53032652f7615ab699c160" +version = "11.0.0-beta.3" +source = "git+https://github.com/lance-format/lance.git?tag=v11.0.0-beta.3#f7d475539cefbd140cc46a828f3d843e68cd10f1" dependencies = [ "arc-swap", "arrow", @@ -5182,8 +5182,8 @@ dependencies = [ [[package]] name = "lance-index-core" -version = "11.0.0-beta.2" -source = "git+https://github.com/lance-format/lance.git?tag=v11.0.0-beta.2#35da5d920159b49d1b53032652f7615ab699c160" +version = "11.0.0-beta.3" +source = "git+https://github.com/lance-format/lance.git?tag=v11.0.0-beta.3#f7d475539cefbd140cc46a828f3d843e68cd10f1" dependencies = [ "arrow-array", "arrow-schema", @@ -5205,8 +5205,8 @@ dependencies = [ [[package]] name = "lance-io" -version = "11.0.0-beta.2" -source = "git+https://github.com/lance-format/lance.git?tag=v11.0.0-beta.2#35da5d920159b49d1b53032652f7615ab699c160" +version = "11.0.0-beta.3" +source = "git+https://github.com/lance-format/lance.git?tag=v11.0.0-beta.3#f7d475539cefbd140cc46a828f3d843e68cd10f1" dependencies = [ "arrow", "arrow-array", @@ -5242,8 +5242,8 @@ dependencies = [ [[package]] name = "lance-linalg" -version = "11.0.0-beta.2" -source = "git+https://github.com/lance-format/lance.git?tag=v11.0.0-beta.2#35da5d920159b49d1b53032652f7615ab699c160" +version = "11.0.0-beta.3" +source = "git+https://github.com/lance-format/lance.git?tag=v11.0.0-beta.3#f7d475539cefbd140cc46a828f3d843e68cd10f1" dependencies = [ "arrow-array", "arrow-buffer", @@ -5259,8 +5259,8 @@ dependencies = [ [[package]] name = "lance-namespace" -version = "11.0.0-beta.2" -source = "git+https://github.com/lance-format/lance.git?tag=v11.0.0-beta.2#35da5d920159b49d1b53032652f7615ab699c160" +version = "11.0.0-beta.3" +source = "git+https://github.com/lance-format/lance.git?tag=v11.0.0-beta.3#f7d475539cefbd140cc46a828f3d843e68cd10f1" dependencies = [ "arrow", "async-trait", @@ -5272,8 +5272,8 @@ dependencies = [ [[package]] name = "lance-namespace-impls" -version = "11.0.0-beta.2" -source = "git+https://github.com/lance-format/lance.git?tag=v11.0.0-beta.2#35da5d920159b49d1b53032652f7615ab699c160" +version = "11.0.0-beta.3" +source = "git+https://github.com/lance-format/lance.git?tag=v11.0.0-beta.3#f7d475539cefbd140cc46a828f3d843e68cd10f1" dependencies = [ "arrow", "arrow-ipc", @@ -5303,7 +5303,6 @@ dependencies = [ "serde", "serde_json", "sha2 0.10.9", - "time", "tokio", "tower", "tower-http 0.5.2", @@ -5327,8 +5326,8 @@ dependencies = [ [[package]] name = "lance-select" -version = "11.0.0-beta.2" -source = "git+https://github.com/lance-format/lance.git?tag=v11.0.0-beta.2#35da5d920159b49d1b53032652f7615ab699c160" +version = "11.0.0-beta.3" +source = "git+https://github.com/lance-format/lance.git?tag=v11.0.0-beta.3#f7d475539cefbd140cc46a828f3d843e68cd10f1" dependencies = [ "arrow-array", "arrow-buffer", @@ -5343,8 +5342,8 @@ dependencies = [ [[package]] name = "lance-table" -version = "11.0.0-beta.2" -source = "git+https://github.com/lance-format/lance.git?tag=v11.0.0-beta.2#35da5d920159b49d1b53032652f7615ab699c160" +version = "11.0.0-beta.3" +source = "git+https://github.com/lance-format/lance.git?tag=v11.0.0-beta.3#f7d475539cefbd140cc46a828f3d843e68cd10f1" dependencies = [ "arrow", "arrow-array", @@ -5354,6 +5353,7 @@ dependencies = [ "async-trait", "aws-credential-types", "aws-sdk-dynamodb", + "blake3", "byteorder", "bytes", "chrono", @@ -5383,8 +5383,8 @@ dependencies = [ [[package]] name = "lance-testing" -version = "11.0.0-beta.2" -source = "git+https://github.com/lance-format/lance.git?tag=v11.0.0-beta.2#35da5d920159b49d1b53032652f7615ab699c160" +version = "11.0.0-beta.3" +source = "git+https://github.com/lance-format/lance.git?tag=v11.0.0-beta.3#f7d475539cefbd140cc46a828f3d843e68cd10f1" dependencies = [ "arrow-array", "arrow-schema", @@ -5397,8 +5397,8 @@ dependencies = [ [[package]] name = "lance-tokenizer" -version = "11.0.0-beta.2" -source = "git+https://github.com/lance-format/lance.git?tag=v11.0.0-beta.2#35da5d920159b49d1b53032652f7615ab699c160" +version = "11.0.0-beta.3" +source = "git+https://github.com/lance-format/lance.git?tag=v11.0.0-beta.3#f7d475539cefbd140cc46a828f3d843e68cd10f1" dependencies = [ "frostem", "icu_segmenter", diff --git a/Cargo.toml b/Cargo.toml index 78474cd16..936660d78 100644 --- a/Cargo.toml +++ b/Cargo.toml @@ -13,20 +13,20 @@ categories = ["database-implementations"] rust-version = "1.91.0" [workspace.dependencies] -lance = { "version" = "=11.0.0-beta.2", default-features = false, "tag" = "v11.0.0-beta.2", "git" = "https://github.com/lance-format/lance.git" } -lance-core = { "version" = "=11.0.0-beta.2", "tag" = "v11.0.0-beta.2", "git" = "https://github.com/lance-format/lance.git" } -lance-datagen = { "version" = "=11.0.0-beta.2", "tag" = "v11.0.0-beta.2", "git" = "https://github.com/lance-format/lance.git" } -lance-file = { "version" = "=11.0.0-beta.2", "tag" = "v11.0.0-beta.2", "git" = "https://github.com/lance-format/lance.git" } -lance-io = { "version" = "=11.0.0-beta.2", default-features = false, "tag" = "v11.0.0-beta.2", "git" = "https://github.com/lance-format/lance.git" } -lance-index = { "version" = "=11.0.0-beta.2", "tag" = "v11.0.0-beta.2", "git" = "https://github.com/lance-format/lance.git" } -lance-linalg = { "version" = "=11.0.0-beta.2", "tag" = "v11.0.0-beta.2", "git" = "https://github.com/lance-format/lance.git" } -lance-namespace = { "version" = "=11.0.0-beta.2", "tag" = "v11.0.0-beta.2", "git" = "https://github.com/lance-format/lance.git" } -lance-namespace-impls = { "version" = "=11.0.0-beta.2", default-features = false, "tag" = "v11.0.0-beta.2", "git" = "https://github.com/lance-format/lance.git" } -lance-table = { "version" = "=11.0.0-beta.2", "tag" = "v11.0.0-beta.2", "git" = "https://github.com/lance-format/lance.git" } -lance-testing = { "version" = "=11.0.0-beta.2", "tag" = "v11.0.0-beta.2", "git" = "https://github.com/lance-format/lance.git" } -lance-datafusion = { "version" = "=11.0.0-beta.2", "tag" = "v11.0.0-beta.2", "git" = "https://github.com/lance-format/lance.git" } -lance-encoding = { "version" = "=11.0.0-beta.2", "tag" = "v11.0.0-beta.2", "git" = "https://github.com/lance-format/lance.git" } -lance-arrow = { "version" = "=11.0.0-beta.2", "tag" = "v11.0.0-beta.2", "git" = "https://github.com/lance-format/lance.git" } +lance = { "version" = "=11.0.0-beta.3", default-features = false, "tag" = "v11.0.0-beta.3", "git" = "https://github.com/lance-format/lance.git" } +lance-core = { "version" = "=11.0.0-beta.3", "tag" = "v11.0.0-beta.3", "git" = "https://github.com/lance-format/lance.git" } +lance-datagen = { "version" = "=11.0.0-beta.3", "tag" = "v11.0.0-beta.3", "git" = "https://github.com/lance-format/lance.git" } +lance-file = { "version" = "=11.0.0-beta.3", "tag" = "v11.0.0-beta.3", "git" = "https://github.com/lance-format/lance.git" } +lance-io = { "version" = "=11.0.0-beta.3", default-features = false, "tag" = "v11.0.0-beta.3", "git" = "https://github.com/lance-format/lance.git" } +lance-index = { "version" = "=11.0.0-beta.3", "tag" = "v11.0.0-beta.3", "git" = "https://github.com/lance-format/lance.git" } +lance-linalg = { "version" = "=11.0.0-beta.3", "tag" = "v11.0.0-beta.3", "git" = "https://github.com/lance-format/lance.git" } +lance-namespace = { "version" = "=11.0.0-beta.3", "tag" = "v11.0.0-beta.3", "git" = "https://github.com/lance-format/lance.git" } +lance-namespace-impls = { "version" = "=11.0.0-beta.3", default-features = false, "tag" = "v11.0.0-beta.3", "git" = "https://github.com/lance-format/lance.git" } +lance-table = { "version" = "=11.0.0-beta.3", "tag" = "v11.0.0-beta.3", "git" = "https://github.com/lance-format/lance.git" } +lance-testing = { "version" = "=11.0.0-beta.3", "tag" = "v11.0.0-beta.3", "git" = "https://github.com/lance-format/lance.git" } +lance-datafusion = { "version" = "=11.0.0-beta.3", "tag" = "v11.0.0-beta.3", "git" = "https://github.com/lance-format/lance.git" } +lance-encoding = { "version" = "=11.0.0-beta.3", "tag" = "v11.0.0-beta.3", "git" = "https://github.com/lance-format/lance.git" } +lance-arrow = { "version" = "=11.0.0-beta.3", "tag" = "v11.0.0-beta.3", "git" = "https://github.com/lance-format/lance.git" } ahash = "0.8" # Note that this one does not include pyarrow arrow = { version = "58.0.0", optional = false } diff --git a/java/pom.xml b/java/pom.xml index e8f030b27..e1c39c3e2 100644 --- a/java/pom.xml +++ b/java/pom.xml @@ -28,7 +28,7 @@ UTF-8 15.0.0 - 11.0.0-beta.2 + 11.0.0-beta.3 false 2.30.0 1.7 From 706a9c327fb324e7961620cf1e159fe8c15f7fab Mon Sep 17 00:00:00 2001 From: Dan Rammer Date: Fri, 7 Aug 2026 14:50:22 -0500 Subject: [PATCH 03/14] feat: infer maintained indexes when an LsmWriteSpec omits them (#3748) MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit ## What `LsmWriteSpec::maintained_indexes` becomes `Option>`: | value | meaning | |---|---| | `None` (new default) | every index the MemWAL supports, resolved when the spec is installed | | `Some([])` | maintain nothing — a scan/filter-only WAL table | | `Some([..])` | exactly these, taken verbatim | `with_maintained_indexes` keeps its signature; `with_no_maintained_indexes()` is new. Surfaced through the remote path (null on the wire), Python, and Node. ## Why Callers had to state the maintained set by hand every time, which is both tedious and easy to get wrong — the common case is "maintain what I already built." Resolution filters on `IndexConfig::is_memwal_maintainable`, delegating to lance's `is_maintainable_index_type`. This is load-bearing rather than cosmetic: lance does **not** skip an index type its memtable cannot build, it errors when the shard writer opens, so sweeping up a bitmap index would fail every memtable claim and leave the table unwritable. The inferred set excludes those, and an explicit list naming one is now rejected at spec time instead of at claim time. ## Behavior change A freshly constructed spec used to maintain **nothing**; it now maintains **everything supported**. This flipped because napi collapses `undefined` and `null` to `None`, so TypeScript cannot express "absent means nothing, null means all" — any other choice makes the bindings disagree with the wire. The error direction also favors it: an unwanted maintained index costs memory, while a silently unmaintained one degrades FTS to an unscored scan. Three existing tests encoded the old default and are updated rather than worked around. ## Caveat The resolved set is a snapshot, not a subscription. An index created after the spec is installed is not maintained until the spec is unset and set again. `get_lsm_write_spec` therefore always reports a concrete list — `None` never round-trips. ## Dependency Needs a lance release carrying `is_maintainable_index_type` (lance-format/lance#8095) before this builds against the pinned tag. Draft until then. ## Testing 38 Rust LSM tests and 10 Python tests pass against a local lance build, including new coverage that a bitmap index is excluded from inference and rejected when named, and that `[]` stays distinguishable from null on the wire. 🤖 Generated with [Claude Code](https://claude.com/claude-code) --------- Co-authored-by: Claude Opus 5 (1M context) --- docs/src/js/classes/Table.md | 12 +- docs/src/js/interfaces/LsmWriteSpec.md | 4 +- nodejs/lancedb/table.ts | 18 +- nodejs/src/table.rs | 12 +- python/python/lancedb/_lancedb.pyi | 11 +- python/python/lancedb/table.py | 13 +- python/python/tests/test_lsm_write_spec.py | 15 +- python/python/tests/test_merge_insert_lsm.py | 4 +- python/src/table.rs | 46 +++-- rust/lancedb/src/remote/table.rs | 30 ++- rust/lancedb/src/table.rs | 202 +++++++++++++++---- rust/lancedb/src/table/merge.rs | 4 +- rust/lancedb/src/table/merge/lsm.rs | 82 +++++++- 13 files changed, 360 insertions(+), 93 deletions(-) diff --git a/docs/src/js/classes/Table.md b/docs/src/js/classes/Table.md index 11fca32d0..3fa3b08db 100644 --- a/docs/src/js/classes/Table.md +++ b/docs/src/js/classes/Table.md @@ -431,9 +431,10 @@ Read the [LsmWriteSpec](../interfaces/LsmWriteSpec.md) currently installed on th Resolves to `undefined` when the MemWAL LSM write path is not enabled (no spec has been set, or it was removed with [Table#unsetLsmWriteSpec](Table.md#unsetlsmwritespec)). -The returned spec — including its `maintainedIndexes` and -`writerConfigDefaults` — mirrors what was passed to -[Table#setLsmWriteSpec](Table.md#setlsmwritespec). +The returned spec mirrors what was passed to +[Table#setLsmWriteSpec](Table.md#setlsmwritespec), except that `maintainedIndexes` always +reports the concrete list resolved when the spec was set — `undefined` +never round-trips. #### Returns @@ -806,6 +807,11 @@ All variants require the table to have an unenforced primary key ([Table#setUnenforcedPrimaryKey](Table.md#setunenforcedprimarykey)); bucket sharding additionally requires it to be the single column being bucketed. +Omitting `maintainedIndexes` maintains every index on the table, resolved +here, failing if one cannot be maintained — name them to install anyway. +Naming them pins an exact set, and a still-building index is rejected +rather than quietly omitted. + #### Parameters * **spec**: [`LsmWriteSpec`](../interfaces/LsmWriteSpec.md) diff --git a/docs/src/js/interfaces/LsmWriteSpec.md b/docs/src/js/interfaces/LsmWriteSpec.md index 8a588df6a..f2ae91186 100644 --- a/docs/src/js/interfaces/LsmWriteSpec.md +++ b/docs/src/js/interfaces/LsmWriteSpec.md @@ -34,7 +34,9 @@ Bucket and identity variants: the sharding column. optional maintainedIndexes: string[]; ``` -Names of indexes the MemWAL should keep up to date during writes. +Indexes the MemWAL keeps up to date. Omit to maintain every supported +index, resolved on install — a snapshot, so indexes created later are not +maintained. Pass `[]` for none. *** diff --git a/nodejs/lancedb/table.ts b/nodejs/lancedb/table.ts index 3359a2643..04705475b 100644 --- a/nodejs/lancedb/table.ts +++ b/nodejs/lancedb/table.ts @@ -197,7 +197,11 @@ export interface LsmWriteSpec { column?: string; /** Bucket variant: the number of buckets, in `[1, 1024]`. */ numBuckets?: number; - /** Names of indexes the MemWAL should keep up to date during writes. */ + /** + * Indexes the MemWAL keeps up to date. Omit to maintain every supported + * index, resolved on install — a snapshot, so indexes created later are not + * maintained. Pass `[]` for none. + */ maintainedIndexes?: string[]; /** Default `ShardWriter` configuration recorded in the MemWAL index. */ writerConfigDefaults?: Record; @@ -595,6 +599,11 @@ export abstract class Table { * All variants require the table to have an unenforced primary key * ({@link Table#setUnenforcedPrimaryKey}); bucket sharding additionally * requires it to be the single column being bucketed. + * + * Omitting `maintainedIndexes` maintains every index on the table, resolved + * here, failing if one cannot be maintained — name them to install anyway. + * Naming them pins an exact set, and a still-building index is rejected + * rather than quietly omitted. * @param {LsmWriteSpec} spec The sharding spec to install. * @returns {Promise} * @example @@ -622,9 +631,10 @@ export abstract class Table { * * Resolves to `undefined` when the MemWAL LSM write path is not enabled (no * spec has been set, or it was removed with {@link Table#unsetLsmWriteSpec}). - * The returned spec — including its `maintainedIndexes` and - * `writerConfigDefaults` — mirrors what was passed to - * {@link Table#setLsmWriteSpec}. + * The returned spec mirrors what was passed to + * {@link Table#setLsmWriteSpec}, except that `maintainedIndexes` always + * reports the concrete list resolved when the spec was set — `undefined` + * never round-trips. * @returns {Promise} */ abstract getLsmWriteSpec(): Promise; diff --git a/nodejs/src/table.rs b/nodejs/src/table.rs index 2ac2fecb2..d26a44845 100644 --- a/nodejs/src/table.rs +++ b/nodejs/src/table.rs @@ -772,7 +772,8 @@ pub struct LsmWriteSpec { pub column: Option, /// Bucket variant: the number of buckets, in `[1, 1024]`. pub num_buckets: Option, - /// Names of indexes the MemWAL should keep up to date during writes. + /// Indexes the MemWAL keeps up to date. Omitted resolves every + /// maintainable index on install; an empty array means none. pub maintained_indexes: Option>, /// Default `ShardWriter` configuration recorded in the MemWAL index. pub writer_config_defaults: Option>, @@ -782,7 +783,6 @@ impl TryFrom for lancedb::table::LsmWriteSpec { type Error = napi::Error; fn try_from(value: LsmWriteSpec) -> napi::Result { - let maintained = value.maintained_indexes.unwrap_or_default(); let writer_config_defaults = value.writer_config_defaults.unwrap_or_default(); let spec = match value.spec_type.as_str() { "bucket" => { @@ -809,7 +809,7 @@ impl TryFrom for lancedb::table::LsmWriteSpec { } }; Ok(spec - .with_maintained_indexes(maintained) + .with_maintained_indexes(value.maintained_indexes) .with_writer_config_defaults(writer_config_defaults)) } } @@ -827,7 +827,7 @@ impl From for LsmWriteSpec { spec_type: "bucket".to_string(), column: Some(column), num_buckets: Some(num_buckets), - maintained_indexes: Some(maintained_indexes), + maintained_indexes, writer_config_defaults: Some(writer_config_defaults), }, Native::Identity { @@ -838,7 +838,7 @@ impl From for LsmWriteSpec { spec_type: "identity".to_string(), column: Some(column), num_buckets: None, - maintained_indexes: Some(maintained_indexes), + maintained_indexes, writer_config_defaults: Some(writer_config_defaults), }, Native::Unsharded { @@ -848,7 +848,7 @@ impl From for LsmWriteSpec { spec_type: "unsharded".to_string(), column: None, num_buckets: None, - maintained_indexes: Some(maintained_indexes), + maintained_indexes, writer_config_defaults: Some(writer_config_defaults), }, } diff --git a/python/python/lancedb/_lancedb.pyi b/python/python/lancedb/_lancedb.pyi index fad2744d3..f87fd3d13 100644 --- a/python/python/lancedb/_lancedb.pyi +++ b/python/python/lancedb/_lancedb.pyi @@ -653,9 +653,10 @@ class LsmWriteSpec: def identity(column: str) -> "LsmWriteSpec": ... @staticmethod def unsharded() -> "LsmWriteSpec": ... - def with_maintained_indexes(self, indexes: List[str]) -> "LsmWriteSpec": - """Return a copy of this spec asking the MemWAL to keep the named - indexes up to date as rows are appended.""" + def with_maintained_indexes(self, indexes: Optional[List[str]]) -> "LsmWriteSpec": + """Set which indexes the MemWAL keeps up to date. None resolves every + index on the table at install, failing if one cannot be maintained; + a list is verbatim, empty means none.""" ... def with_writer_config_defaults(self, defaults: Dict[str, str]) -> "LsmWriteSpec": """Return a copy of this spec recording the given default @@ -670,7 +671,9 @@ class LsmWriteSpec: @property def num_buckets(self) -> Optional[int]: ... @property - def maintained_indexes(self) -> List[str]: ... + def maintained_indexes(self) -> Optional[List[str]]: + """Indexes the MemWAL keeps up to date, or None for every supported one.""" + ... @property def writer_config_defaults(self) -> Dict[str, str]: ... diff --git a/python/python/lancedb/table.py b/python/python/lancedb/table.py index 0828f04dc..f0d7dc8c8 100644 --- a/python/python/lancedb/table.py +++ b/python/python/lancedb/table.py @@ -4676,6 +4676,13 @@ class AsyncTable: via [`set_unenforced_primary_key`]; bucket sharding additionally requires it to be the single column being bucketed. + By default the MemWAL maintains every index on the table, resolved + here — a snapshot, so an index created afterwards needs the spec unset + and set again. This fails if one cannot be maintained; name the set + with ``with_maintained_indexes`` to install anyway. That pins an exact + set (a still-building index is rejected, not omitted); ``[]`` maintains + none. + Parameters ---------- spec : LsmWriteSpec @@ -4702,9 +4709,9 @@ class AsyncTable: Returns ``None`` when the MemWAL LSM write path is not enabled (no spec has been set, or it was removed with `unset_lsm_write_spec`). - The returned spec — including its ``maintained_indexes`` and - ``writer_config_defaults`` — mirrors what was passed to - `set_lsm_write_spec`. + The returned spec mirrors what was passed to `set_lsm_write_spec`, + except that ``maintained_indexes`` always reports the concrete list + resolved when the spec was set — ``None`` never round-trips. """ return await self._inner.get_lsm_write_spec() diff --git a/python/python/tests/test_lsm_write_spec.py b/python/python/tests/test_lsm_write_spec.py index d38918f09..218793b89 100644 --- a/python/python/tests/test_lsm_write_spec.py +++ b/python/python/tests/test_lsm_write_spec.py @@ -83,7 +83,9 @@ def test_lsm_write_spec_repr(): assert s.spec_type == "bucket" assert s.column == "id" assert s.num_buckets == 4 - assert s.maintained_indexes == [] + # A fresh spec defers its maintained set to install time. + assert s.maintained_indexes is None + assert s.with_maintained_indexes([]).maintained_indexes == [] assert "bucket" in repr(s) assert "id" in repr(s) assert "4" in repr(s) @@ -169,18 +171,23 @@ def test_get_lsm_write_spec(tmp_path): table.unset_lsm_write_spec() assert table.get_lsm_write_spec() is None - # Identity round-trips (column recovered from the schema). + # Identity round-trips (column recovered from the schema). Leaving the + # maintained set to be inferred picks up the index on the table, so the + # spec reads back naming it rather than as "infer". table.set_lsm_write_spec(LsmWriteSpec.identity("id")) spec = table.get_lsm_write_spec() assert spec.spec_type == "identity" assert spec.column == "id" + assert spec.maintained_indexes == [idx_name] table.unset_lsm_write_spec() - # Unsharded round-trips (no routing column). - table.set_lsm_write_spec(LsmWriteSpec.unsharded()) + # Unsharded round-trips (no routing column). Opting out is distinct from + # the inferred default. + table.set_lsm_write_spec(LsmWriteSpec.unsharded().with_maintained_indexes([])) spec = table.get_lsm_write_spec() assert spec.spec_type == "unsharded" assert spec.column is None + assert spec.maintained_indexes == [] @pytest.mark.asyncio diff --git a/python/python/tests/test_merge_insert_lsm.py b/python/python/tests/test_merge_insert_lsm.py index 5674a05ab..e74c21589 100644 --- a/python/python/tests/test_merge_insert_lsm.py +++ b/python/python/tests/test_merge_insert_lsm.py @@ -544,7 +544,7 @@ def test_lsm_read_fts_unmaintained_index_errors(tmp_path): table.create_index("text", config=FTS()) # No maintained indexes: the active memtable FTS arm cannot serve un-compacted # docs, so the search would silently omit them — reject instead. - table.set_lsm_write_spec(LsmWriteSpec.unsharded()) + table.set_lsm_write_spec(LsmWriteSpec.unsharded().with_maintained_indexes([])) with pytest.raises(Exception, match="maintained"): table.search("fox", query_type="fts", fts_columns="text").to_arrow() @@ -631,7 +631,7 @@ def test_lsm_read_vector_unmaintained_index_errors(tmp_path): ) # Spec with NO maintained indexes: the base vector index's catch-up is untracked, # so the scanner rejects rather than risk dropping compacted-but-unindexed rows. - table.set_lsm_write_spec(LsmWriteSpec.unsharded()) + table.set_lsm_write_spec(LsmWriteSpec.unsharded().with_maintained_indexes([])) with pytest.raises(Exception, match="maintained"): table.search([1.0] * VECTOR_DIM).to_arrow() diff --git a/python/src/table.rs b/python/src/table.rs index 119388708..20a93556f 100644 --- a/python/src/table.rs +++ b/python/src/table.rs @@ -246,12 +246,22 @@ impl From for MergeResult { } } +/// Render for `__repr__`, so the default reads as Python's `None` rather than +/// Rust's `Some([..])`. +fn fmt_maintained(maintained: &Option>) -> String { + match maintained { + Some(names) => format!("{:?}", names), + None => "None".to_string(), + } +} + /// Specification selecting Lance's MemWAL LSM-style write path for /// `merge_insert`. /// /// Constructed via the `bucket(...)`, `identity(...)`, or `unsharded()` /// classmethods, then optionally chain `with_maintained_indexes(...)` and -/// `with_writer_config_defaults(...)`. +/// `with_writer_config_defaults(...)`. A fresh spec maintains every index the +/// MemWAL supports, resolved on install. #[pyclass(from_py_object)] #[derive(Clone, Debug)] pub struct LsmWriteSpec { @@ -291,11 +301,11 @@ impl LsmWriteSpec { } } - /// Replace the list of indexes the MemWAL should keep up to date as - /// rows are appended. Each name must reference an index that - /// already exists on the table at the time `set_lsm_write_spec` - /// is called. - pub fn with_maintained_indexes(&self, indexes: Vec) -> Self { + /// Set which indexes the MemWAL maintains. `None` (the default) + /// resolves every supported index on install; a list is verbatim, + /// and an empty list maintains nothing. + #[pyo3(signature = (indexes))] + pub fn with_maintained_indexes(&self, indexes: Option>) -> Self { Self { inner: self.inner.clone().with_maintained_indexes(indexes), } @@ -317,23 +327,29 @@ impl LsmWriteSpec { maintained_indexes, writer_config_defaults, } => format!( - "LsmWriteSpec.bucket(column={:?}, num_buckets={}, maintained_indexes={:?}, writer_config_defaults={:?})", - column, num_buckets, maintained_indexes, writer_config_defaults, + "LsmWriteSpec.bucket(column={:?}, num_buckets={}, maintained_indexes={}, writer_config_defaults={:?})", + column, + num_buckets, + fmt_maintained(maintained_indexes), + writer_config_defaults, ), lancedb::table::LsmWriteSpec::Identity { column, maintained_indexes, writer_config_defaults, } => format!( - "LsmWriteSpec.identity(column={:?}, maintained_indexes={:?}, writer_config_defaults={:?})", - column, maintained_indexes, writer_config_defaults, + "LsmWriteSpec.identity(column={:?}, maintained_indexes={}, writer_config_defaults={:?})", + column, + fmt_maintained(maintained_indexes), + writer_config_defaults, ), lancedb::table::LsmWriteSpec::Unsharded { maintained_indexes, writer_config_defaults, } => format!( - "LsmWriteSpec.unsharded(maintained_indexes={:?}, writer_config_defaults={:?})", - maintained_indexes, writer_config_defaults, + "LsmWriteSpec.unsharded(maintained_indexes={}, writer_config_defaults={:?})", + fmt_maintained(maintained_indexes), + writer_config_defaults, ), } } @@ -368,10 +384,10 @@ impl LsmWriteSpec { } } - /// Names of indexes the MemWAL should keep up to date during writes. + /// Indexes the MemWAL keeps up to date, or `None` for every supported one. #[getter] - pub fn maintained_indexes(&self) -> Vec { - self.inner.maintained_indexes().to_vec() + pub fn maintained_indexes(&self) -> Option> { + self.inner.maintained_indexes().map(<[String]>::to_vec) } /// Default `ShardWriter` configuration recorded by this spec. diff --git a/rust/lancedb/src/remote/table.rs b/rust/lancedb/src/remote/table.rs index f3e872cbe..0d843dd54 100644 --- a/rust/lancedb/src/remote/table.rs +++ b/rust/lancedb/src/remote/table.rs @@ -2520,9 +2520,9 @@ impl BaseTable for RemoteTable { self.check_mutable().await?; // Map the spec onto the server's request DTO. `sharding` is internally - // tagged on `mode` to mirror sophon's `Sharding` enum; `maintained_indexes` - // and `writer_config_defaults` are sent verbatim (an empty list means "no - // maintained indexes", not "default to all"). + // tagged on `mode` to mirror sophon's `Sharding` enum. A null + // `maintained_indexes` asks the server to resolve every maintainable + // index at HEAD; a list is verbatim, an empty one meaning none. let sharding = match &spec { LsmWriteSpec::Bucket { column, @@ -6599,7 +6599,7 @@ mod tests { .unwrap() }); let spec = crate::table::LsmWriteSpec::unsharded() - .with_maintained_indexes(["id_idx"]) + .with_maintained_indexes(vec!["id_idx".to_string()]) .with_writer_config_defaults([("max_memtable_rows", "1000")]); table.set_lsm_write_spec(spec).await.unwrap(); } @@ -6618,7 +6618,8 @@ mod tests { body["sharding"], serde_json::json!({ "mode": "bucket", "column": "id", "num_buckets": 16 }) ); - assert_eq!(body["maintained_indexes"], serde_json::json!([])); + // An unpinned maintained set sends null: resolve server-side. + assert_eq!(body["maintained_indexes"], serde_json::Value::Null); http::Response::builder().status(200).body("{}").unwrap() }); table @@ -6627,6 +6628,23 @@ mod tests { .unwrap(); } + /// `[]` (none) must stay distinguishable on the wire from null (all). + #[tokio::test] + async fn test_set_lsm_write_spec_no_maintained_indexes() { + let table = Table::new_with_handler("my_table", |request| { + let body = request.body().unwrap().as_bytes().unwrap(); + let body: serde_json::Value = serde_json::from_slice(body).unwrap(); + assert_eq!(body["maintained_indexes"], serde_json::json!([])); + http::Response::builder().status(200).body("{}").unwrap() + }); + table + .set_lsm_write_spec( + crate::table::LsmWriteSpec::bucket("id", 16).with_maintained_indexes(Vec::new()), + ) + .await + .unwrap(); + } + #[tokio::test] async fn test_set_lsm_write_spec_identity() { let table = Table::new_with_handler("my_table", |request| { @@ -6701,7 +6719,7 @@ mod tests { } => { assert_eq!(column, "id"); assert_eq!(num_buckets, 4); - assert_eq!(maintained_indexes, vec!["id_idx".to_string()]); + assert_eq!(maintained_indexes, Some(vec!["id_idx".to_string()])); assert_eq!( writer_config_defaults .get("durable_write") diff --git a/rust/lancedb/src/table.rs b/rust/lancedb/src/table.rs index 74ab17921..e23bb7c47 100644 --- a/rust/lancedb/src/table.rs +++ b/rust/lancedb/src/table.rs @@ -371,6 +371,8 @@ pub use self::merge::MergeResult; /// date) and [`LsmWriteSpec::with_writer_config_defaults`] (default /// `ShardWriter` configuration recorded in the MemWAL index). /// +/// A fresh spec maintains every index on the table, resolved on install. +/// /// Install a spec with [`Table::set_lsm_write_spec`] and remove it with /// [`Table::unset_lsm_write_spec`]. The actual `merge_insert` dispatch /// onto the MemWAL writer is a follow-up. @@ -385,9 +387,12 @@ pub enum LsmWriteSpec { Bucket { column: String, num_buckets: u32, - /// Names of indexes (already created on the table) that the - /// MemWAL should maintain in-memory as rows are appended. - maintained_indexes: Vec, + /// Indexes the MemWAL maintains in-memory as rows are appended. + /// + /// `None` means every index it can maintain, resolved on install — a + /// snapshot, so indexes created later need the spec unset and re-set. + /// `Some([])` maintains nothing. + maintained_indexes: Option>, /// Default `ShardWriter` configuration recorded in the MemWAL index. writer_config_defaults: HashMap, }, @@ -397,35 +402,41 @@ pub enum LsmWriteSpec { /// distinct value of `column` becomes its own shard. Identity { column: String, - /// Names of indexes (already created on the table) that the - /// MemWAL should maintain in-memory as rows are appended. - maintained_indexes: Vec, + /// Indexes the MemWAL maintains in-memory as rows are appended. + /// + /// `None` means every index it can maintain, resolved on install — a + /// snapshot, so indexes created later need the spec unset and re-set. + /// `Some([])` maintains nothing. + maintained_indexes: Option>, /// Default `ShardWriter` configuration recorded in the MemWAL index. writer_config_defaults: HashMap, }, /// No sharding — every `merge_insert` call writes to a single MemWAL shard. Unsharded { - /// Names of indexes (already created on the table) that the - /// MemWAL should maintain in-memory as rows are appended. - maintained_indexes: Vec, + /// Indexes the MemWAL maintains in-memory as rows are appended. + /// + /// `None` means every index it can maintain, resolved on install — a + /// snapshot, so indexes created later need the spec unset and re-set. + /// `Some([])` maintains nothing. + maintained_indexes: Option>, /// Default `ShardWriter` configuration recorded in the MemWAL index. writer_config_defaults: HashMap, }, } impl LsmWriteSpec { - /// Construct a hash-bucket sharding spec with no maintained indexes. + /// Construct a hash-bucket sharding spec maintaining every index on the table. pub fn bucket(column: impl Into, num_buckets: u32) -> Self { Self::Bucket { column: column.into(), num_buckets, - maintained_indexes: Vec::new(), + maintained_indexes: None, writer_config_defaults: HashMap::new(), } } /// Construct an identity-sharding spec (shard by the raw value of - /// `column`) with no maintained indexes. + /// `column`) maintaining every index on the table. /// /// `column` must be a deterministic function of the unenforced primary /// key: every row with a given primary key must always produce the same @@ -437,28 +448,37 @@ impl LsmWriteSpec { pub fn identity(column: impl Into) -> Self { Self::Identity { column: column.into(), - maintained_indexes: Vec::new(), + maintained_indexes: None, writer_config_defaults: HashMap::new(), } } - /// Construct an unsharded spec with no maintained indexes. + /// Construct an unsharded spec maintaining every index on the table. pub fn unsharded() -> Self { Self::Unsharded { - maintained_indexes: Vec::new(), + maintained_indexes: None, writer_config_defaults: HashMap::new(), } } - /// Replace the list of indexes the MemWAL should keep up to date as - /// rows are appended. Each name must reference an index that already - /// exists on the table at the time `set_lsm_write_spec` is called. - pub fn with_maintained_indexes(mut self, indexes: I) -> Self - where - I: IntoIterator, - S: Into, - { - let v: Vec = indexes.into_iter().map(Into::into).collect(); + /// Set which indexes the MemWAL maintains. + /// + /// `None` (the default) resolves to every index on the table at install, + /// failing if one cannot be maintained — name the set to install anyway. A + /// list is verbatim: each name must already exist and be maintainable, and + /// an empty list maintains nothing. + /// + /// ``` + /// # use lancedb::table::LsmWriteSpec; + /// // Every index the table has when the spec is installed: + /// LsmWriteSpec::unsharded().with_maintained_indexes(None); + /// // Exactly these: + /// LsmWriteSpec::unsharded().with_maintained_indexes(vec!["id_idx".to_string()]); + /// // None at all: + /// LsmWriteSpec::unsharded().with_maintained_indexes(Vec::new()); + /// ``` + pub fn with_maintained_indexes(mut self, indexes: impl Into>>) -> Self { + let indexes = indexes.into(); match &mut self { Self::Bucket { maintained_indexes, .. @@ -468,7 +488,7 @@ impl LsmWriteSpec { } | Self::Unsharded { maintained_indexes, .. - } => *maintained_indexes = v, + } => *maintained_indexes = indexes, } self } @@ -504,8 +524,9 @@ impl LsmWriteSpec { self } - /// Borrow the list of index names this spec asks MemWAL to maintain. - pub fn maintained_indexes(&self) -> &[String] { + /// Borrow the list of index names this spec asks MemWAL to maintain, or + /// `None` when it asks for every index on the table. + pub fn maintained_indexes(&self) -> Option<&[String]> { match self { Self::Bucket { maintained_indexes, .. @@ -515,7 +536,7 @@ impl LsmWriteSpec { } | Self::Unsharded { maintained_indexes, .. - } => maintained_indexes, + } => maintained_indexes.as_deref(), } } @@ -1713,7 +1734,7 @@ impl Table { /// # async fn example(table: &Table) -> Result<(), Box> { /// table /// .set_lsm_write_spec( - /// LsmWriteSpec::bucket("id", 16).with_maintained_indexes(["id_idx"]), + /// LsmWriteSpec::bucket("id", 16).with_maintained_indexes(vec!["id_idx".to_string()]), /// ) /// .await?; /// # Ok(()) @@ -1735,9 +1756,10 @@ impl Table { /// /// Returns `Ok(None)` when the MemWAL LSM write path is not enabled (no /// spec has been set, or it was removed with [`Table::unset_lsm_write_spec`]). - /// The returned spec — including its [`LsmWriteSpec::maintained_indexes`] and - /// [`LsmWriteSpec::writer_config_defaults`] — mirrors what was passed to - /// [`Table::set_lsm_write_spec`]. + /// The returned spec mirrors what was passed to + /// [`Table::set_lsm_write_spec`], except that + /// [`LsmWriteSpec::maintained_indexes`] always reports the concrete list + /// resolved when the spec was set — `None` never round-trips. /// /// # Example /// @@ -5065,7 +5087,7 @@ mod tests { // Bucket spec round-trips exactly, including the routing column (recovered // from its field id), maintained indexes, and writer config defaults. let spec = LsmWriteSpec::bucket("id", 4) - .with_maintained_indexes([idx_name]) + .with_maintained_indexes(vec![idx_name.clone()]) .with_writer_config_defaults([("durable_write", "false")]); table.set_lsm_write_spec(spec.clone()).await.unwrap(); assert_eq!(table.get_lsm_write_spec().await.unwrap(), Some(spec)); @@ -5075,15 +5097,125 @@ mod tests { assert_eq!(table.get_lsm_write_spec().await.unwrap(), None); // Identity sharding round-trips (column recovered from the schema). + // A spec left at its default maintains every index on the table, so it + // reads back naming the one on the table rather than as "infer". let spec = LsmWriteSpec::identity("region"); table.set_lsm_write_spec(spec.clone()).await.unwrap(); - assert_eq!(table.get_lsm_write_spec().await.unwrap(), Some(spec)); + assert_eq!( + table.get_lsm_write_spec().await.unwrap(), + Some(spec.with_maintained_indexes(vec![idx_name.clone()])) + ); table.unset_lsm_write_spec().await.unwrap(); // Unsharded round-trips (no routing column). let spec = LsmWriteSpec::unsharded(); table.set_lsm_write_spec(spec.clone()).await.unwrap(); - assert_eq!(table.get_lsm_write_spec().await.unwrap(), Some(spec)); + assert_eq!( + table.get_lsm_write_spec().await.unwrap(), + Some(spec.with_maintained_indexes(vec![idx_name])) + ); + } + + /// The maintained set defaults to every index on the table, resolved at + /// install. An index the memtable cannot build fails the install rather + /// than being dropped: maintaining it would take the table offline for + /// writes, dropping it would hide that from the caller. + #[tokio::test] + async fn test_set_lsm_write_spec_infers_maintained_indexes() { + let tmp_dir = tempdir().unwrap(); + let uri = tmp_dir.path().to_str().unwrap(); + + let schema = Arc::new(Schema::new(vec![ + Field::new("id", DataType::Int64, false), + Field::new("tag", DataType::Utf8, true), + ])); + let batch = RecordBatch::try_new( + schema.clone(), + vec![ + Arc::new(arrow_array::Int64Array::from(vec![1, 2, 3])), + Arc::new(StringArray::from(vec!["a", "b", "c"])), + ], + ) + .unwrap(); + let reader: Box = + Box::new(RecordBatchIterator::new(vec![Ok(batch)], schema.clone())); + let conn = ConnectBuilder::new(uri) + .read_consistency_interval(Duration::from_secs(0)) + .execute() + .await + .unwrap(); + let table = conn.create_table("t", reader).execute().await.unwrap(); + + table + .create_index(&["id"], Index::BTree(Default::default())) + .name("id_btree".to_string()) + .execute() + .await + .unwrap(); + table + .create_index(&["tag"], Index::Bitmap(Default::default())) + .name("tag_bitmap".to_string()) + .execute() + .await + .unwrap(); + + // Explicitly naming the bitmap index fails before anything commits. + let err = table + .set_lsm_write_spec( + LsmWriteSpec::unsharded().with_maintained_indexes(vec!["tag_bitmap".to_string()]), + ) + .await + .unwrap_err(); + assert!( + matches!(err, Error::InvalidInput { ref message } if message.contains("tag_bitmap")), + "expected the bitmap index to be rejected, got {err:?}" + ); + assert_eq!(table.get_lsm_write_spec().await.unwrap(), None); + + // The default covers every index, so the bitmap fails it too. + let err = table + .set_lsm_write_spec(LsmWriteSpec::unsharded()) + .await + .unwrap_err(); + assert!( + matches!(err, Error::InvalidInput { ref message } + if message.contains("tag_bitmap") && message.contains("maintained_indexes")), + "expected the inferred set to be rejected, got {err:?}" + ); + assert_eq!(table.get_lsm_write_spec().await.unwrap(), None); + + // Naming the maintainable subset installs. + table + .set_lsm_write_spec( + LsmWriteSpec::unsharded().with_maintained_indexes(vec!["id_btree".to_string()]), + ) + .await + .unwrap(); + assert_eq!( + table + .get_lsm_write_spec() + .await + .unwrap() + .unwrap() + .maintained_indexes(), + Some(["id_btree".to_string()].as_slice()) + ); + + // Opting out entirely is distinct from the default. + table.unset_lsm_write_spec().await.unwrap(); + table + .set_lsm_write_spec(LsmWriteSpec::unsharded().with_maintained_indexes(Vec::new())) + .await + .unwrap(); + assert_eq!( + table + .get_lsm_write_spec() + .await + .unwrap() + .unwrap() + .maintained_indexes(), + Some([].as_slice()) + ); } #[tokio::test] diff --git a/rust/lancedb/src/table/merge.rs b/rust/lancedb/src/table/merge.rs index 82a1d1473..3a5b6882d 100644 --- a/rust/lancedb/src/table/merge.rs +++ b/rust/lancedb/src/table/merge.rs @@ -1161,7 +1161,7 @@ mod lsm_tests { .unwrap(); let fts_index = table.list_indices().await.unwrap()[0].name.clone(); table - .set_lsm_write_spec(LsmWriteSpec::unsharded().with_maintained_indexes([fts_index])) + .set_lsm_write_spec(LsmWriteSpec::unsharded().with_maintained_indexes(vec![fts_index])) .await .unwrap(); @@ -1254,7 +1254,7 @@ mod lsm_tests { .unwrap(); let vec_index = table.list_indices().await.unwrap()[0].name.clone(); table - .set_lsm_write_spec(LsmWriteSpec::unsharded().with_maintained_indexes([vec_index])) + .set_lsm_write_spec(LsmWriteSpec::unsharded().with_maintained_indexes(vec![vec_index])) .await .unwrap(); diff --git a/rust/lancedb/src/table/merge/lsm.rs b/rust/lancedb/src/table/merge/lsm.rs index 0eb7c0231..87c427b3c 100644 --- a/rust/lancedb/src/table/merge/lsm.rs +++ b/rust/lancedb/src/table/merge/lsm.rs @@ -29,6 +29,7 @@ use arrow_schema::{DataType, Schema as ArrowSchema, SchemaRef}; use lance::Dataset; use lance::dataset::mem_wal::{ DatasetMemWalExt, ShardWriter, ShardWriterConfig, evaluate_sharding_spec, + validate_maintained_indexes, }; use lance::index::DatasetIndexExt; use lance_core::datatypes::Schema as LanceSchema; @@ -37,8 +38,9 @@ use tokio::sync::RwLock; use uuid::Uuid; use crate::error::{Error, Result}; +use crate::index::IndexConfig; use crate::table::merge::{MergeInsertBuilder, MergeResult}; -use crate::table::{LsmWriteSpec, NativeTable}; +use crate::table::{BaseTable, LsmWriteSpec, NativeTable}; /// Spec id of the sole sharding spec installed by [`set_lsm_write_spec`]. /// Must match Lance's `InitializeMemWalBuilder` (`SHARDING_SPEC_ID`). @@ -80,32 +82,44 @@ pub(crate) async fn set_lsm_write_spec(table: &NativeTable, spec: LsmWriteSpec) } } + // Before the builder borrows the dataset clone. `list_indices` merges an + // index's segments into one entry, so the result needs no dedup. + let maintained_indexes = { + let dataset = table.dataset.get().await?; + resolve_maintained_indexes( + &dataset, + &table.list_indices().await?, + spec.maintained_indexes(), + ) + .await? + }; + let mut dataset = (*table.dataset.get().await?).clone(); let mut builder = dataset.initialize_mem_wal(); - let (maintained_indexes, writer_config_defaults) = match spec { + let writer_config_defaults = match spec { LsmWriteSpec::Bucket { column, num_buckets, - maintained_indexes, writer_config_defaults, + .. } => { builder = builder.bucket_sharding(column, num_buckets); - (maintained_indexes, writer_config_defaults) + writer_config_defaults } LsmWriteSpec::Identity { column, - maintained_indexes, writer_config_defaults, + .. } => { builder = builder.identity_sharding(column); - (maintained_indexes, writer_config_defaults) + writer_config_defaults } LsmWriteSpec::Unsharded { - maintained_indexes, writer_config_defaults, + .. } => { builder = builder.unsharded(); - (maintained_indexes, writer_config_defaults) + writer_config_defaults } }; builder = builder.maintained_indexes(maintained_indexes); @@ -117,6 +131,58 @@ pub(crate) async fn set_lsm_write_spec(table: &NativeTable, spec: LsmWriteSpec) Ok(()) } +/// Resolve a spec's maintained-index selection against `indices`, as reported +/// by [`Table::list_indices`](crate::Table::list_indices). +/// +/// `None` means every index on the table, snapshotted now. Lance validates +/// either selection against its shard-writer rules, so a spec that installs is +/// one the MemWAL can open. +/// +/// An unmaintainable index fails an inferred set rather than being dropped from +/// it — dropping would leave the caller believing it is maintained. +async fn resolve_maintained_indexes( + dataset: &Dataset, + indices: &[IndexConfig], + requested: Option<&[String]>, +) -> Result> { + let Some(requested) = requested else { + let all: Vec = indices.iter().map(|index| index.name.clone()).collect(); + validate_maintained_indexes(dataset, &all) + .await + .map_err(|source| Error::InvalidInput { + message: format!( + "cannot maintain every index on this table: {source}. Set \ + maintained_indexes explicitly to choose from {}", + index_name_list(indices), + ), + })?; + return Ok(all); + }; + for name in requested { + if !indices.iter().any(|index| &index.name == name) { + return Err(Error::InvalidInput { + message: format!( + "maintained index '{}' does not exist on this table; it has {}", + name, + index_name_list(indices), + ), + }); + } + } + validate_maintained_indexes(dataset, requested).await?; + Ok(requested.to_vec()) +} + +/// Index names for an error message. +fn index_name_list(indices: &[IndexConfig]) -> String { + if indices.is_empty() { + return "no indexes".to_string(); + } + let mut names: Vec<&str> = indices.iter().map(|index| index.name.as_str()).collect(); + names.sort_unstable(); + format!("[{}]", names.join(", ")) +} + // ============================================================================= // unset_lsm_write_spec // ============================================================================= From 5b347afd9925dfe9017feae5725a93230b123b30 Mon Sep 17 00:00:00 2001 From: Andrew Chen Date: Sat, 8 Aug 2026 05:05:45 +0800 Subject: [PATCH 04/14] fix: avoid AttributeError in JinaEmbeddings image input for str/Path (#3670) MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit ## What `JinaEmbeddings._generate_image_input_dict()` crashes with `AttributeError: 'function' object has no attribute 'urlparse'` on any image given as a URL string, local path string, or `pathlib.Path` — i.e. every documented `jina-clip-v1` image-embedding use case except raw `bytes`. ## Why ```python from urllib.parse import urlparse ... parsed = urlparse.urlparse(image) ``` `urlparse` is imported as a function, then called as if it were the `urllib.parse` module (`urlparse.urlparse(...)`). The module-level `is_valid_url()` a few lines above does it correctly (`urlparse(text)`), which is why this reads as a typo rather than intentional. Fixed to `urlparse(str(image))` — `str()` is needed because `urlparse()` only accepts `str`/`bytes` and raises a different `AttributeError` on a raw `Path`. ## Testing Added `test_jina_generate_image_input_dict_local_path`, which fails with the original `AttributeError` before the fix and passes after, covering both a `str` path and a `pathlib.Path`. Verified locally (built the Rust extension, ran red→green, then the full `test_embeddings.py` file: 15 passed / 8 skipped, no regressions) and with `ruff check`/`ruff format`. --- Disclosure: this PR was drafted with AI assistance (Claude); I reviewed, tested, and take responsibility for the change. --------- Co-authored-by: Claude Opus 4.8 --- python/python/lancedb/embeddings/jinaai.py | 7 ++++--- python/python/tests/test_embeddings.py | 20 ++++++++++++++++++++ 2 files changed, 24 insertions(+), 3 deletions(-) diff --git a/python/python/lancedb/embeddings/jinaai.py b/python/python/lancedb/embeddings/jinaai.py index 9656f041f..f6ab601b3 100644 --- a/python/python/lancedb/embeddings/jinaai.py +++ b/python/python/lancedb/embeddings/jinaai.py @@ -87,12 +87,13 @@ class JinaEmbeddings(EmbeddingFunction): if isinstance(image, bytes): image_dict = {"image": base64.b64encode(image).decode("utf-8")} elif isinstance(image, (str, Path)): - parsed = urlparse.urlparse(image) - # TODO handle drive letter on windows. + parsed = urlparse(str(image)) PIL_Image = attempt_import_or_raise("PIL.Image", "pillow") if parsed.scheme == "file": pil_image = PIL_Image.open(parsed.path) - elif parsed.scheme == "": + elif parsed.scheme == "" or (os.name == "nt" and len(parsed.scheme) == 1): + # A Windows drive letter parses as a one-character scheme + # ("C:\\img.png" -> scheme="c"), so treat it as a local path. pil_image = PIL_Image.open(image if os.name == "nt" else parsed.path) elif parsed.scheme.startswith("http"): pil_image = PIL_Image.open(io.BytesIO(url_retrieve(image))) diff --git a/python/python/tests/test_embeddings.py b/python/python/tests/test_embeddings.py index 678270f19..9850669eb 100644 --- a/python/python/tests/test_embeddings.py +++ b/python/python/tests/test_embeddings.py @@ -631,3 +631,23 @@ def test_url_retrieve_downloads_image(): image_bytes = url_retrieve(image_url) img = Image.open(io.BytesIO(image_bytes)) assert img.size[0] > 0 and img.size[1] > 0 + + +def test_jina_generate_image_input_dict_local_path(tmp_path): + """ + JinaEmbeddings._generate_image_input_dict must accept a local image path + (str or Path), not just bytes. Previously it crashed with + `AttributeError: 'function' object has no attribute 'urlparse'` on any + str/Path input because it called `urlparse.urlparse(image)` instead of + `urlparse(image)` (urlparse was imported as a function, not a module). + """ + Image = pytest.importorskip("PIL.Image") + from lancedb.embeddings.jinaai import JinaEmbeddings + + image_path = tmp_path / "test.png" + Image.new("RGB", (4, 4), color="red").save(image_path, format="PNG") + + for image in (str(image_path), image_path): + image_dict = JinaEmbeddings._generate_image_input_dict(image) + assert "image" in image_dict + assert isinstance(image_dict["image"], str) and len(image_dict["image"]) > 0 From 7bb501839a18f5160bf858d6a10438630a7099ea Mon Sep 17 00:00:00 2001 From: Lance Release Date: Fri, 7 Aug 2026 21:15:20 +0000 Subject: [PATCH 05/14] =?UTF-8?q?Bump=20version:=200.37.1-beta.0=20?= =?UTF-8?q?=E2=86=92=200.37.1-beta.1?= MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit --- .bumpversion.toml | 2 +- Cargo.lock | 6 +++--- docs/src/java/java.md | 2 +- java/lancedb-core/pom.xml | 2 +- java/pom.xml | 2 +- nodejs/Cargo.toml | 2 +- nodejs/npm/darwin-arm64/package.json | 2 +- nodejs/npm/linux-arm64-gnu/package.json | 2 +- nodejs/npm/linux-arm64-musl/package.json | 2 +- nodejs/npm/linux-x64-gnu/package.json | 2 +- nodejs/npm/linux-x64-musl/package.json | 2 +- nodejs/npm/win32-arm64-msvc/package.json | 2 +- nodejs/npm/win32-x64-msvc/package.json | 2 +- nodejs/package-lock.json | 4 ++-- nodejs/package.json | 2 +- python/Cargo.toml | 2 +- rust/lancedb/Cargo.toml | 2 +- 17 files changed, 20 insertions(+), 20 deletions(-) diff --git a/.bumpversion.toml b/.bumpversion.toml index 601b14d3f..a015353cb 100644 --- a/.bumpversion.toml +++ b/.bumpversion.toml @@ -1,5 +1,5 @@ [tool.bumpversion] -current_version = "0.37.1-beta.0" +current_version = "0.37.1-beta.1" parse = """(?x) (?P0|[1-9]\\d*)\\. (?P0|[1-9]\\d*)\\. diff --git a/Cargo.lock b/Cargo.lock index f6186672c..04ab7b099 100644 --- a/Cargo.lock +++ b/Cargo.lock @@ -5411,7 +5411,7 @@ dependencies = [ [[package]] name = "lancedb" -version = "0.37.1-beta.0" +version = "0.37.1-beta.1" dependencies = [ "ahash", "anyhow", @@ -5499,7 +5499,7 @@ dependencies = [ [[package]] name = "lancedb-nodejs" -version = "0.37.1-beta.0" +version = "0.37.1-beta.1" dependencies = [ "arrow-array", "arrow-buffer", @@ -5524,7 +5524,7 @@ dependencies = [ [[package]] name = "lancedb-python" -version = "0.37.1-beta.0" +version = "0.37.1-beta.1" dependencies = [ "arrow", "async-trait", diff --git a/docs/src/java/java.md b/docs/src/java/java.md index 11e901ad0..091588922 100644 --- a/docs/src/java/java.md +++ b/docs/src/java/java.md @@ -14,7 +14,7 @@ Add the following dependency to your `pom.xml`: com.lancedb lancedb-core - 0.37.1-beta.0 + 0.37.1-beta.1 ``` diff --git a/java/lancedb-core/pom.xml b/java/lancedb-core/pom.xml index 3df2ac178..20f69e134 100644 --- a/java/lancedb-core/pom.xml +++ b/java/lancedb-core/pom.xml @@ -8,7 +8,7 @@ com.lancedb lancedb-parent - 0.37.1-beta.0 + 0.37.1-beta.1 ../pom.xml diff --git a/java/pom.xml b/java/pom.xml index e1c39c3e2..f85b5c906 100644 --- a/java/pom.xml +++ b/java/pom.xml @@ -6,7 +6,7 @@ com.lancedb lancedb-parent - 0.37.1-beta.0 + 0.37.1-beta.1 pom ${project.artifactId} LanceDB Java SDK Parent POM diff --git a/nodejs/Cargo.toml b/nodejs/Cargo.toml index 10e12edc8..48e5f5295 100644 --- a/nodejs/Cargo.toml +++ b/nodejs/Cargo.toml @@ -1,7 +1,7 @@ [package] name = "lancedb-nodejs" edition.workspace = true -version = "0.37.1-beta.0" +version = "0.37.1-beta.1" publish = false license.workspace = true description.workspace = true diff --git a/nodejs/npm/darwin-arm64/package.json b/nodejs/npm/darwin-arm64/package.json index 3c93ed470..d3792f9c2 100644 --- a/nodejs/npm/darwin-arm64/package.json +++ b/nodejs/npm/darwin-arm64/package.json @@ -1,6 +1,6 @@ { "name": "@lancedb/lancedb-darwin-arm64", - "version": "0.37.1-beta.0", + "version": "0.37.1-beta.1", "os": ["darwin"], "cpu": ["arm64"], "main": "lancedb.darwin-arm64.node", diff --git a/nodejs/npm/linux-arm64-gnu/package.json b/nodejs/npm/linux-arm64-gnu/package.json index 5ade5aaa3..44bc309ca 100644 --- a/nodejs/npm/linux-arm64-gnu/package.json +++ b/nodejs/npm/linux-arm64-gnu/package.json @@ -1,6 +1,6 @@ { "name": "@lancedb/lancedb-linux-arm64-gnu", - "version": "0.37.1-beta.0", + "version": "0.37.1-beta.1", "os": ["linux"], "cpu": ["arm64"], "main": "lancedb.linux-arm64-gnu.node", diff --git a/nodejs/npm/linux-arm64-musl/package.json b/nodejs/npm/linux-arm64-musl/package.json index 16bb0edd0..e78f0fe6a 100644 --- a/nodejs/npm/linux-arm64-musl/package.json +++ b/nodejs/npm/linux-arm64-musl/package.json @@ -1,6 +1,6 @@ { "name": "@lancedb/lancedb-linux-arm64-musl", - "version": "0.37.1-beta.0", + "version": "0.37.1-beta.1", "os": ["linux"], "cpu": ["arm64"], "main": "lancedb.linux-arm64-musl.node", diff --git a/nodejs/npm/linux-x64-gnu/package.json b/nodejs/npm/linux-x64-gnu/package.json index 6ee11e4bc..0e27c5f51 100644 --- a/nodejs/npm/linux-x64-gnu/package.json +++ b/nodejs/npm/linux-x64-gnu/package.json @@ -1,6 +1,6 @@ { "name": "@lancedb/lancedb-linux-x64-gnu", - "version": "0.37.1-beta.0", + "version": "0.37.1-beta.1", "os": ["linux"], "cpu": ["x64"], "main": "lancedb.linux-x64-gnu.node", diff --git a/nodejs/npm/linux-x64-musl/package.json b/nodejs/npm/linux-x64-musl/package.json index c2e15bb9f..7bd27ba18 100644 --- a/nodejs/npm/linux-x64-musl/package.json +++ b/nodejs/npm/linux-x64-musl/package.json @@ -1,6 +1,6 @@ { "name": "@lancedb/lancedb-linux-x64-musl", - "version": "0.37.1-beta.0", + "version": "0.37.1-beta.1", "os": ["linux"], "cpu": ["x64"], "main": "lancedb.linux-x64-musl.node", diff --git a/nodejs/npm/win32-arm64-msvc/package.json b/nodejs/npm/win32-arm64-msvc/package.json index d2820b1a1..5c76024b2 100644 --- a/nodejs/npm/win32-arm64-msvc/package.json +++ b/nodejs/npm/win32-arm64-msvc/package.json @@ -1,6 +1,6 @@ { "name": "@lancedb/lancedb-win32-arm64-msvc", - "version": "0.37.1-beta.0", + "version": "0.37.1-beta.1", "os": [ "win32" ], diff --git a/nodejs/npm/win32-x64-msvc/package.json b/nodejs/npm/win32-x64-msvc/package.json index 601b51380..f8cc7d8e0 100644 --- a/nodejs/npm/win32-x64-msvc/package.json +++ b/nodejs/npm/win32-x64-msvc/package.json @@ -1,6 +1,6 @@ { "name": "@lancedb/lancedb-win32-x64-msvc", - "version": "0.37.1-beta.0", + "version": "0.37.1-beta.1", "os": ["win32"], "cpu": ["x64"], "main": "lancedb.win32-x64-msvc.node", diff --git a/nodejs/package-lock.json b/nodejs/package-lock.json index bdbd3cf79..f7b6670e4 100644 --- a/nodejs/package-lock.json +++ b/nodejs/package-lock.json @@ -1,12 +1,12 @@ { "name": "@lancedb/lancedb", - "version": "0.37.1-beta.0", + "version": "0.37.1-beta.1", "lockfileVersion": 3, "requires": true, "packages": { "": { "name": "@lancedb/lancedb", - "version": "0.37.1-beta.0", + "version": "0.37.1-beta.1", "cpu": [ "x64", "arm64" diff --git a/nodejs/package.json b/nodejs/package.json index 671f3f94d..0416ce81b 100644 --- a/nodejs/package.json +++ b/nodejs/package.json @@ -11,7 +11,7 @@ "ann" ], "private": false, - "version": "0.37.1-beta.0", + "version": "0.37.1-beta.1", "main": "dist/index.js", "exports": { ".": "./dist/index.js", diff --git a/python/Cargo.toml b/python/Cargo.toml index 5a196e27c..9d36edd5c 100644 --- a/python/Cargo.toml +++ b/python/Cargo.toml @@ -1,6 +1,6 @@ [package] name = "lancedb-python" -version = "0.37.1-beta.0" +version = "0.37.1-beta.1" publish = false edition.workspace = true description = "Python bindings for LanceDB" diff --git a/rust/lancedb/Cargo.toml b/rust/lancedb/Cargo.toml index c2137d0b5..05251f59a 100644 --- a/rust/lancedb/Cargo.toml +++ b/rust/lancedb/Cargo.toml @@ -1,6 +1,6 @@ [package] name = "lancedb" -version = "0.37.1-beta.0" +version = "0.37.1-beta.1" edition.workspace = true description = "LanceDB: A serverless, low-latency vector database for AI applications" license.workspace = true From 77a93fee76f091445450513dfa32252e3bda00fa Mon Sep 17 00:00:00 2001 From: Dan Tasse <105866+dantasse@users.noreply.github.com> Date: Fri, 7 Aug 2026 17:41:41 -0400 Subject: [PATCH 06/14] fix: get table size from metadata, not files (#3790) Some issues: - file_size_bytes is optional in the manifest, so if it's not there (old writer I guess) it'll under-report the table size. - it changes results a little bit from the old way by including per-file footers and metadata (probably not a big difference at real scale) --------- Co-authored-by: Will Jones --- Cargo.lock | 1 + docs/src/js/interfaces/TableStatistics.md | 5 +- nodejs/__test__/table.test.ts | 10 +- nodejs/src/table.rs | 5 +- python/python/lancedb/table.py | 4 +- python/python/tests/test_table.py | 10 +- rust/lancedb/Cargo.toml | 1 + rust/lancedb/src/table.rs | 228 +++++++++++++++++++++- 8 files changed, 253 insertions(+), 11 deletions(-) diff --git a/Cargo.lock b/Cargo.lock index 04ab7b099..20f20a0ac 100644 --- a/Cargo.lock +++ b/Cargo.lock @@ -5480,6 +5480,7 @@ dependencies = [ "random_word", "regex", "reqwest 0.12.28", + "roaring", "rstest", "semver", "serde", diff --git a/docs/src/js/interfaces/TableStatistics.md b/docs/src/js/interfaces/TableStatistics.md index e19cba119..e2e8ef34d 100644 --- a/docs/src/js/interfaces/TableStatistics.md +++ b/docs/src/js/interfaces/TableStatistics.md @@ -44,4 +44,7 @@ The number of rows in the table totalBytes: number; ``` -The total number of bytes in the table +The total size, in bytes, of the table's data files, index files, and +overlay files + +Read from the manifest, so this excludes deletion files and manifests. diff --git a/nodejs/__test__/table.test.ts b/nodejs/__test__/table.test.ts index 15d6e0804..d263d9cab 100644 --- a/nodejs/__test__/table.test.ts +++ b/nodejs/__test__/table.test.ts @@ -277,8 +277,16 @@ describe.each([arrow15, arrow16, arrow17, arrow18])( }, numIndices: 0, numRows: 3, - totalBytes: 44, + // Full on-disk size of the two data files, footers and metadata included. + totalBytes: 684, }); + + // Index files count toward totalBytes too (only deletion files and + // manifests are excluded). + await table.createIndex("id", { config: Index.btree() }); + const statsWithIndex = await table.stats(); + expect(statsWithIndex.numIndices).toBe(1); + expect(statsWithIndex.totalBytes).toBeGreaterThan(684); }); it("should overwrite data if asked", async () => { diff --git a/nodejs/src/table.rs b/nodejs/src/table.rs index d26a44845..c4ece20e2 100644 --- a/nodejs/src/table.rs +++ b/nodejs/src/table.rs @@ -1043,7 +1043,10 @@ impl From for IndexStatistics { #[napi(object)] pub struct TableStatistics { - /// The total number of bytes in the table + /// The total size, in bytes, of the table's data files, index files, and + /// overlay files + /// + /// Read from the manifest, so this excludes deletion files and manifests. pub total_bytes: i64, /// The number of rows in the table diff --git a/python/python/lancedb/table.py b/python/python/lancedb/table.py index f0d7dc8c8..c566fc532 100644 --- a/python/python/lancedb/table.py +++ b/python/python/lancedb/table.py @@ -6341,7 +6341,9 @@ class TableStatistics: Attributes ---------- total_bytes: int - The total number of bytes in the table. + The total size, in bytes, of the table's data files, index files, and + overlay files. Read from the manifest, so this excludes deletion files + and manifests. num_rows: int The total number of rows in the table. num_indices: int diff --git a/python/python/tests/test_table.py b/python/python/tests/test_table.py index eb6eaefaa..2a069c712 100644 --- a/python/python/tests/test_table.py +++ b/python/python/tests/test_table.py @@ -3713,7 +3713,8 @@ def test_stats(mem_db: DBConnection): stats = table.stats() print(f"{stats=}") assert stats == { - "total_bytes": 60, + # Full on-disk size of the data file, footer and metadata included. + "total_bytes": 633, "num_rows": 2, "num_indices": 0, "fragment_stats": { @@ -3731,6 +3732,13 @@ def test_stats(mem_db: DBConnection): }, } + # Index files count toward total_bytes too (only deletion files and + # manifests are excluded). + table.create_index("id", config=BTree()) + stats_with_index = table.stats() + assert stats_with_index["num_indices"] == 1 + assert stats_with_index["total_bytes"] > stats["total_bytes"] + def test_create_table_empty_list_with_schema(mem_db: DBConnection): """Test creating table with empty list data and schema diff --git a/rust/lancedb/Cargo.toml b/rust/lancedb/Cargo.toml index 05251f59a..2dbd9d895 100644 --- a/rust/lancedb/Cargo.toml +++ b/rust/lancedb/Cargo.toml @@ -100,6 +100,7 @@ anyhow = "1" lance-testing = { workspace = true } tempfile = "3.5.0" random_word = { version = "0.4.3", features = ["en"] } +roaring = "0.11.4" tokio = { version = "1.23", features = ["io-util", "macros", "net", "rt-multi-thread", "sync", "test-util"] } uuid = { version = "1.7.0", features = ["v4"] } walkdir = "2" diff --git a/rust/lancedb/src/table.rs b/rust/lancedb/src/table.rs index e23bb7c47..5120c48b7 100644 --- a/rust/lancedb/src/table.rs +++ b/rust/lancedb/src/table.rs @@ -95,7 +95,6 @@ pub use delete::DeleteResult; use futures::future::join_all; pub use lance::dataset::refs::{BranchContents, Ref, TagContents, Tags as LanceTags}; pub use lance::dataset::scanner::DatasetRecordBatchStream; -use lance::dataset::statistics::DatasetStatisticsExt; pub use lance_index::optimize::OptimizeOptions; pub use lsm_stats::{BucketStats, GenerationStats, LsmStats, MemtableStats}; pub use optimize::{CompactionOptions, OptimizeAction, OptimizeStats}; @@ -3570,9 +3569,24 @@ impl BaseTable for NativeTable { let num_rows = self.count_rows(None).await?; let num_indices = self.list_indices().await?.len(); let ds = self.dataset.get().await?; - let ds_clone = (*ds).clone(); - let ds_stats = Arc::new(ds_clone).calculate_data_stats().await?; - let total_bytes = ds_stats.fields.iter().map(|f| f.bytes_on_disk).sum::() as usize; + // Sizes come from the manifest. Summing per-field `bytes_on_disk` instead + // would open every data file to read its column metadata, which costs one + // IO per fragment and reports 0 for legacy v1 storage. + // + // The manifest summary covers only the fragments' base data files, so + // overlay files (recorded on each fragment) and index files (recorded in + // the manifest's index section) are added separately. + let mut total_bytes = ds.manifest().summary().total_files_size as usize; + for frag in ds.manifest().fragments.iter() { + for overlay in &frag.overlays { + if let Some(size) = overlay.data_file.file_size_bytes.get() { + total_bytes += size.get() as usize; + } + } + } + for index in ds.load_indices().await?.iter() { + total_bytes += index.total_size_bytes().unwrap_or(0) as usize; + } let frags = ds.get_fragments(); let mut sorted_sizes = join_all( @@ -3644,7 +3658,12 @@ impl BaseTable for NativeTable { #[skip_serializing_none] #[derive(Debug, Deserialize, PartialEq)] pub struct TableStatistics { - /// The total number of bytes in the table + /// The total size, in bytes, of the table's data files, index files, and + /// overlay files + /// + /// Read from the manifest, so this excludes deletion files and manifests, + /// and it excludes any file whose size the manifest does not record + /// (tables and indices written before writers persisted file sizes). pub total_bytes: usize, /// The number of rows in the table @@ -3705,6 +3724,7 @@ mod tests { use super::*; use crate::connect; use crate::connection::ConnectBuilder; + use crate::io::object_store::io_tracking::IoTrackingStore; use crate::query::Select; use crate::query::{ExecutableQuery, QueryBase}; use crate::test_utils::connection::new_test_connection; @@ -5263,12 +5283,16 @@ mod tests { let res = table.stats().await.unwrap(); println!("{:#?}", res); + // `total_bytes` is the full on-disk size of the 11 data files (this table + // has no index or overlay files), so it is well above the 2000 bytes of + // column data these 250 int32 pairs hold: each file carries its own footer + // and metadata. assert_eq!( res, TableStatistics { num_rows: 250, num_indices: 0, - total_bytes: 2300, + total_bytes: 8925, fragment_stats: FragmentStatistics { num_fragments: 11, num_small_fragments: 11, @@ -5308,4 +5332,196 @@ mod tests { } ) } + + /// `total_bytes` counts more than the base data files: index files and + /// overlay files recorded in the manifest are included too. + #[tokio::test] + pub async fn test_stats_includes_index_and_overlay_files() { + use lance::dataset::WriteDestination; + use lance::dataset::transaction::{DataOverlayGroup, Operation}; + use lance_file::version::{ConcreteFileVersion, LanceFileVersion}; + use lance_file::writer::FileWriterOptions; + use lance_io::utils::CachedFileSize; + use lance_table::format::DataFile; + use lance_table::format::overlay::{DataOverlayFile, OverlayCoverage}; + use roaring::RoaringBitmap; + + let tmp_dir = tempdir().unwrap(); + let uri = tmp_dir.path().to_str().unwrap(); + let conn = ConnectBuilder::new(uri) + .read_consistency_interval(Duration::from_secs(0)) + .execute() + .await + .unwrap(); + + let schema = Arc::new(Schema::new(vec![ + Field::new("id", DataType::Int32, false), + Field::new("foo", DataType::Int32, true), + ])); + let batch = RecordBatch::try_new( + schema.clone(), + vec![ + Arc::new(Int32Array::from_iter_values(0..100)), + Arc::new(Int32Array::from_iter_values(0..100)), + ], + ) + .unwrap(); + let table = conn + .create_table("test_stats_extra_files", batch) + .execute() + .await + .unwrap(); + + let data_only = table.stats().await.unwrap().total_bytes; + assert!(data_only > 0); + + // A scalar index adds index files whose sizes are recorded in the + // manifest's index section. + table + .create_index(&["id"], Index::Auto) + .execute() + .await + .unwrap(); + let with_index = table.stats().await.unwrap().total_bytes; + let dataset = { + let native = table.as_native().unwrap(); + (*native.dataset.get().await.unwrap()).clone() + }; + let index_bytes: usize = dataset + .load_indices() + .await + .unwrap() + .iter() + .map(|idx| idx.total_size_bytes().unwrap_or(0) as usize) + .sum(); + assert!(index_bytes > 0); + assert_eq!(with_index, data_only + index_bytes); + + // Commit an overlay file supplying new `foo` values for the first three + // rows of fragment 0. There is no high-level API that writes overlays + // yet, so write the overlay's data file and commit the `DataOverlay` + // operation by hand. + let read_version = dataset.version().version; + let fragment_id = dataset.get_fragments()[0].id() as u64; + let foo_field_id = dataset.schema().field("foo").unwrap().id; + let overlay_schema = dataset.schema().project_by_ids(&[foo_field_id], true); + let file_version = ConcreteFileVersion::from(LanceFileVersion::Stable); + + let filename = "overlay.lance".to_string(); + let store = dataset.object_store(None).await.unwrap(); + let path = dataset.data_dir().child(filename.clone()); + let obj_writer = store.create(&path).await.unwrap(); + let mut writer = lance_file::versions::create_writer( + file_version, + obj_writer, + overlay_schema, + FileWriterOptions::default(), + ) + .unwrap(); + writer + .write_column(0, Arc::new(Int32Array::from(vec![1000, 1001, 1002])) as _) + .await + .unwrap(); + let summary = writer.finish().await.unwrap(); + let overlay_bytes = summary.size_bytes as usize; + assert!(overlay_bytes > 0); + + let mut data_file = DataFile::new_unstarted(filename, file_version); + data_file.fields = writer + .field_id_to_column_indices() + .iter() + .map(|(field_id, _)| *field_id as i32) + .collect::>() + .into(); + data_file.column_indices = writer + .field_id_to_column_indices() + .iter() + .map(|(_, column_index)| *column_index as i32) + .collect::>() + .into(); + data_file.file_size_bytes = CachedFileSize::new(summary.size_bytes); + + let overlay = DataOverlayFile { + data_file, + coverage: OverlayCoverage::dense(RoaringBitmap::from_iter(0..3)), + committed_version: 0, + }; + Dataset::commit( + WriteDestination::Dataset(Arc::new(dataset)), + Operation::DataOverlay { + groups: vec![DataOverlayGroup { + fragment_id, + overlays: vec![overlay], + }], + }, + Some(read_version), + None, + None, + Arc::new(Default::default()), + false, + ) + .await + .unwrap(); + + table.checkout_latest().await.unwrap(); + let with_overlay = table.stats().await.unwrap().total_bytes; + assert_eq!(with_overlay, with_index + overlay_bytes); + } + + /// `stats()` must stay manifest-only. Summing per-field `bytes_on_disk` + /// instead opens every data file, so cost would grow with fragment count. + #[tokio::test] + pub async fn test_stats_does_not_read_data_files() { + let tmp_dir = tempdir().unwrap(); + let uri = tmp_dir.path().to_str().unwrap(); + + let conn = ConnectBuilder::new(uri).execute().await.unwrap(); + + let schema = Arc::new(Schema::new(vec![Field::new("id", DataType::Int32, false)])); + let batch = RecordBatch::try_new( + schema.clone(), + vec![Arc::new(Int32Array::from_iter_values(0..10))], + ) + .unwrap(); + + conn.create_table("test_stats_io", batch.clone()) + .execute() + .await + .unwrap(); + let table = conn.open_table("test_stats_io").execute().await.unwrap(); + const NUM_APPENDS: usize = 20; + for _ in 0..NUM_APPENDS { + table.add(batch.clone()).execute().await.unwrap(); + } + + // Reopen through a tracking store so the counters cover `stats()` alone and + // not the writes above. + let (wrapper, io_stats) = IoTrackingStore::new_wrapper(); + let table = conn + .open_table("test_stats_io") + .lance_read_params(ReadParams { + store_options: Some(ObjectStoreParams { + object_store_wrapper: Some(wrapper), + ..Default::default() + }), + ..Default::default() + }) + .execute() + .await + .unwrap(); + io_stats.lock().unwrap().read_iops = 0; + + let stats = table.stats().await.unwrap(); + let read_iops = io_stats.lock().unwrap().read_iops; + + assert_eq!(stats.fragment_stats.num_fragments, NUM_APPENDS + 1); + assert!(stats.total_bytes > 0); + // Reading the fragments' data files would take at least one IOP each. + assert!( + read_iops < stats.fragment_stats.num_fragments as u64, + "stats() issued {} read IOPs across {} fragments", + read_iops, + stats.fragment_stats.num_fragments + ); + } } From 36054be5760f54042549279333431fd8b4aaea76 Mon Sep 17 00:00:00 2001 From: "lancedb-gatefixer[bot]" <313497061+lancedb-gatefixer[bot]@users.noreply.github.com> Date: Sun, 9 Aug 2026 03:34:39 +0800 Subject: [PATCH 07/14] fix(node): preserve nested Arrow data across versions (#3900) ## Root cause When LanceDB accepted an Arrow table created by a different installed Arrow package, its compatibility sanitizer rebuilt each Data node without converting the foreign type or preserving nested children. It also dropped the separate dictionary vector payload and did not preserve identity shared by dictionary schema types, vector wrappers, or growing dictionary chunks. ## Fix Recursively sanitize nested Arrow data types and child data. Use one table-scoped sanitization context to rebuild and memoize source type objects, dictionary vectors, and Data nodes in the local Arrow realm, preserving all identities required by Arrow IPC. Add Arrow 15 through 18 regressions for list serialization, ordinary dictionaries, dictionaries shared across fields and batches, growing dictionaries, and IPC round trips. ## Validation - pnpm test __test__/arrow.test.ts --runInBand (188 passed) - pnpm lint - pnpm build - pnpm test --runInBand (706 passed, 5 skipped) - pnpm run docs Fixes #2256 --------- Co-authored-by: Gatefixer <313497061+lancedb-gatefixer[bot]@users.noreply.github.com> --- nodejs/__test__/arrow.test.ts | 115 +++++++++++++++++++ nodejs/lancedb/sanitize.ts | 203 +++++++++++++++++++++++++++++----- 2 files changed, 289 insertions(+), 29 deletions(-) diff --git a/nodejs/__test__/arrow.test.ts b/nodejs/__test__/arrow.test.ts index c05849cb9..29030d4f8 100644 --- a/nodejs/__test__/arrow.test.ts +++ b/nodejs/__test__/arrow.test.ts @@ -6,7 +6,9 @@ import * as arrow17 from "apache-arrow-17"; import * as arrow18 from "apache-arrow-18"; import { + Vector as CurrentVector, convertToTable, + tableFromIPC as currentTableFromIPC, fromBufferToRecordBatch, fromDataToBuffer, fromRecordBatchToBuffer, @@ -19,6 +21,7 @@ import { FunctionOptions, } from "../lancedb/embedding/embedding_function"; import { EmbeddingFunctionConfig } from "../lancedb/embedding/registry"; +import { sanitizeTable } from "../lancedb/sanitize"; // biome-ignore lint/suspicious/noExplicitAny: skip function sampleRecords(): Array> { @@ -64,7 +67,11 @@ describe.each([arrow15, arrow16, arrow17, arrow18])( tableFromIPC, DataType, Dictionary, + RecordBatch: ArrowRecordBatch, + Table: ArrowTable, Uint8: ArrowUint8, + makeData: arrowMakeData, + vectorFromArray, // biome-ignore lint/suspicious/noExplicitAny: } = arrow; type Schema = ApacheArrow["Schema"]; @@ -1054,6 +1061,114 @@ describe.each([arrow15, arrow16, arrow17, arrow18])( }); describe("when using two versions of arrow", function () { + it("preserves a dictionary shared by multiple fields", async function () { + const values = ["alpha", "beta", "alpha"]; + const dictionaryVector = vectorFromArray(values); + const batch = new ArrowRecordBatch({ + first: dictionaryVector.data[0], + second: dictionaryVector.data[0], + }); + const table = new ArrowTable([batch]); + + const sanitized = sanitizeTable(table); + expect([...sanitized.getChild("first")!]).toEqual(values); + expect([...sanitized.getChild("second")!]).toEqual(values); + const firstType = sanitized.schema.fields[0].type as { + dictionary: unknown; + }; + const secondType = sanitized.schema.fields[1].type as { + dictionary: unknown; + }; + expect(secondType.dictionary).toBe(firstType.dictionary); + expect(sanitized.batches[0].data.children[1].dictionary).toBe( + sanitized.batches[0].data.children[0].dictionary, + ); + + const buf = await fromDataToBuffer(table); + const actual = currentTableFromIPC(buf); + expect([...actual.getChild("first")!]).toEqual(values); + expect([...actual.getChild("second")!]).toEqual(values); + }); + + it("preserves shared dictionary data from another Arrow version", async function () { + const values = ["alpha", "beta", "alpha"]; + const dictionaryVector = vectorFromArray(values); + const firstBatch = new ArrowRecordBatch({ + label: dictionaryVector.slice(0, 2).data[0], + }); + const secondBatch = new ArrowRecordBatch({ + label: dictionaryVector.slice(2).data[0], + }); + const table = new ArrowTable([firstBatch, secondBatch]); + + const sanitized = sanitizeTable(table); + expect([...sanitized.getChild("label")!]).toEqual(values); + + const dictionaries = sanitized.batches.map( + (batch) => batch.data.children[0].dictionary, + ); + expect(dictionaries[0]).toBeInstanceOf(CurrentVector); + expect(dictionaries[1]).toBe(dictionaries[0]); + + const buf = await fromDataToBuffer(table); + const actual = currentTableFromIPC(buf); + expect([...actual.getChild("label")!]).toEqual(values); + }); + + it("preserves shared chunks in growing dictionaries", async function () { + const type = new Dictionary(new Utf8(), new Int32(), 42, false); + const firstDictionary = vectorFromArray(["alpha", "beta"], new Utf8()); + const secondDictionary = firstDictionary.concat( + vectorFromArray(["gamma"], new Utf8()), + ); + const firstData = arrowMakeData({ + type, + data: Int32Array.from([0, 1]), + dictionary: firstDictionary, + }); + const secondData = arrowMakeData({ + type, + data: Int32Array.from([2]), + dictionary: secondDictionary, + }); + const table = new ArrowTable([ + new ArrowRecordBatch({ label: firstData }), + new ArrowRecordBatch({ label: secondData }), + ]); + + const sanitized = sanitizeTable(table); + const expected = ["alpha", "beta", "gamma"]; + expect([...sanitized.getChild("label")!]).toEqual(expected); + const firstLocalDictionary = + sanitized.batches[0].data.children[0].dictionary!; + const secondLocalDictionary = + sanitized.batches[1].data.children[0].dictionary!; + expect(secondLocalDictionary.data[0]).toBe( + firstLocalDictionary.data[0], + ); + + const buf = await fromTableToBuffer(sanitized); + const actual = currentTableFromIPC(buf); + expect([...actual.getChild("label")!]).toEqual(expected); + }); + + it("can serialize list data from another Arrow version", async function () { + const values = [["anime", "action"], [], null]; + const vector = vectorFromArray( + values, + new List(new Field("item", new Utf8(), true)), + ); + const table = new ArrowTable({ tags: vector }); + + const buf = await fromDataToBuffer(table); + const actual = currentTableFromIPC(buf); + const actualTags = actual.getChild("tags"); + + expect(actualTags?.get(0)?.toJSON()).toEqual(values[0]); + expect(actualTags?.get(1)?.toJSON()).toEqual(values[1]); + expect(actualTags?.get(2)).toBeNull(); + }); + it("can still import data", async function () { const schema = new arrow15.Schema([ new arrow15.Field("id", new arrow15.Int32()), diff --git a/nodejs/lancedb/sanitize.ts b/nodejs/lancedb/sanitize.ts index ae0bc0179..8fb2f1a0a 100644 --- a/nodejs/lancedb/sanitize.ts +++ b/nodejs/lancedb/sanitize.ts @@ -9,7 +9,7 @@ // comes from the exact same library instance. This is not always the case // and so we must sanitize the input to ensure that it is compatible. -import { BufferType, Data } from "apache-arrow"; +import { BufferType, Data, Vector } from "apache-arrow"; import type { IntBitWidth, TKeys, TimeBitWidth } from "apache-arrow/type"; import { Binary, @@ -74,6 +74,20 @@ import { Utf8, } from "./arrow"; +type SanitizationContext = { + types: WeakMap; + vectors: WeakMap; + data: WeakMap>; +}; + +function createSanitizationContext(): SanitizationContext { + return { + types: new WeakMap(), + vectors: new WeakMap(), + data: new WeakMap(), + }; +} + export function sanitizeMetadata( metadataLike?: unknown, ): Map | undefined { @@ -186,6 +200,13 @@ export function sanitizeInterval(typeLike: object) { } export function sanitizeList(typeLike: object) { + return sanitizeListWithContext(typeLike, createSanitizationContext()); +} + +function sanitizeListWithContext( + typeLike: object, + context: SanitizationContext, +) { if (!("children" in typeLike) || !Array.isArray(typeLike.children)) { throw Error( "Expected a List type to have an array-like `children` property", @@ -194,19 +215,35 @@ export function sanitizeList(typeLike: object) { if (typeLike.children.length !== 1) { throw Error("Expected a List type to have exactly one child"); } - return new List(sanitizeField(typeLike.children[0])); + return new List(sanitizeFieldWithContext(typeLike.children[0], context)); } export function sanitizeStruct(typeLike: object) { + return sanitizeStructWithContext(typeLike, createSanitizationContext()); +} + +function sanitizeStructWithContext( + typeLike: object, + context: SanitizationContext, +) { if (!("children" in typeLike) || !Array.isArray(typeLike.children)) { throw Error( "Expected a Struct type to have an array-like `children` property", ); } - return new Struct(typeLike.children.map((child) => sanitizeField(child))); + return new Struct( + typeLike.children.map((child) => sanitizeFieldWithContext(child, context)), + ); } export function sanitizeUnion(typeLike: object) { + return sanitizeUnionWithContext(typeLike, createSanitizationContext()); +} + +function sanitizeUnionWithContext( + typeLike: object, + context: SanitizationContext, +) { if ( !("typeIds" in typeLike) || !("mode" in typeLike) || @@ -226,7 +263,7 @@ export function sanitizeUnion(typeLike: object) { typeLike.mode, // biome-ignore lint/suspicious/noExplicitAny: skip typeLike.typeIds as any, - typeLike.children.map((child) => sanitizeField(child)), + typeLike.children.map((child) => sanitizeFieldWithContext(child, context)), ); } @@ -234,6 +271,19 @@ export function sanitizeTypedUnion( typeLike: object, // eslint-disable-next-line @typescript-eslint/naming-convention UnionType: typeof DenseUnion | typeof SparseUnion, +) { + return sanitizeTypedUnionWithContext( + typeLike, + UnionType, + createSanitizationContext(), + ); +} + +function sanitizeTypedUnionWithContext( + typeLike: object, + // eslint-disable-next-line @typescript-eslint/naming-convention + UnionType: typeof DenseUnion | typeof SparseUnion, + context: SanitizationContext, ) { if (!("typeIds" in typeLike)) { throw Error( @@ -248,7 +298,7 @@ export function sanitizeTypedUnion( return new UnionType( typeLike.typeIds as Int32Array | number[], - typeLike.children.map((child) => sanitizeField(child)), + typeLike.children.map((child) => sanitizeFieldWithContext(child, context)), ); } @@ -262,6 +312,16 @@ export function sanitizeFixedSizeBinary(typeLike: object) { } export function sanitizeFixedSizeList(typeLike: object) { + return sanitizeFixedSizeListWithContext( + typeLike, + createSanitizationContext(), + ); +} + +function sanitizeFixedSizeListWithContext( + typeLike: object, + context: SanitizationContext, +) { if (!("listSize" in typeLike) || typeof typeLike.listSize !== "number") { throw Error("Expected a FixedSizeList type to have a `listSize` property"); } @@ -275,11 +335,18 @@ export function sanitizeFixedSizeList(typeLike: object) { } return new FixedSizeList( typeLike.listSize, - sanitizeField(typeLike.children[0]), + sanitizeFieldWithContext(typeLike.children[0], context), ); } export function sanitizeMap(typeLike: object) { + return sanitizeMapWithContext(typeLike, createSanitizationContext()); +} + +function sanitizeMapWithContext( + typeLike: object, + context: SanitizationContext, +) { if (!("children" in typeLike) || !Array.isArray(typeLike.children)) { throw Error( "Expected a Map type to have an array-like `children` property", @@ -292,7 +359,10 @@ export function sanitizeMap(typeLike: object) { throw Error("Expected a Map type to have exactly one child"); } - return new Map_(sanitizeField(typeLike.children[0]), typeLike.keysSorted); + return new Map_( + sanitizeFieldWithContext(typeLike.children[0], context), + typeLike.keysSorted, + ); } export function sanitizeDuration(typeLike: object) { @@ -303,6 +373,13 @@ export function sanitizeDuration(typeLike: object) { } export function sanitizeDictionary(typeLike: object) { + return sanitizeDictionaryWithContext(typeLike, createSanitizationContext()); +} + +function sanitizeDictionaryWithContext( + typeLike: object, + context: SanitizationContext, +) { if (!("id" in typeLike) || typeof typeLike.id !== "number") { throw Error("Expected a Dictionary type to have an `id` property"); } @@ -316,8 +393,8 @@ export function sanitizeDictionary(typeLike: object) { throw Error("Expected a Dictionary type to have an `isOrdered` property"); } return new Dictionary( - sanitizeType(typeLike.dictionary), - sanitizeType(typeLike.indices) as TKeys, + sanitizeTypeWithContext(typeLike.dictionary, context), + sanitizeTypeWithContext(typeLike.indices, context) as TKeys, typeLike.id, typeLike.isOrdered, ); @@ -325,12 +402,23 @@ export function sanitizeDictionary(typeLike: object) { // biome-ignore lint/suspicious/noExplicitAny: skip export function sanitizeType(typeLike: unknown): DataType { + return sanitizeTypeWithContext(typeLike, createSanitizationContext()); +} + +function sanitizeTypeWithContext( + typeLike: unknown, + context: SanitizationContext, +): DataType { if (typeof typeLike === "string") { return dataTypeFromName(typeLike); } if (typeof typeLike !== "object" || typeLike === null) { throw Error("Expected a Type but object was null/undefined"); } + const cached = context.types.get(typeLike); + if (cached !== undefined) { + return cached; + } if ( !("typeId" in typeLike) || !( @@ -349,6 +437,16 @@ export function sanitizeType(typeLike: unknown): DataType { throw Error("Type's typeId property was not a function or number"); } + const type = sanitizeTypeById(typeLike, typeId, context); + context.types.set(typeLike, type); + return type; +} + +function sanitizeTypeById( + typeLike: object, + typeId: Type, + context: SanitizationContext, +): DataType { switch (typeId) { case Type.NONE: throw Error("Received a Type with a typeId of NONE"); @@ -375,21 +473,21 @@ export function sanitizeType(typeLike: unknown): DataType { case Type.Interval: return sanitizeInterval(typeLike); case Type.List: - return sanitizeList(typeLike); + return sanitizeListWithContext(typeLike, context); case Type.Struct: - return sanitizeStruct(typeLike); + return sanitizeStructWithContext(typeLike, context); case Type.Union: - return sanitizeUnion(typeLike); + return sanitizeUnionWithContext(typeLike, context); case Type.FixedSizeBinary: return sanitizeFixedSizeBinary(typeLike); case Type.FixedSizeList: - return sanitizeFixedSizeList(typeLike); + return sanitizeFixedSizeListWithContext(typeLike, context); case Type.Map: - return sanitizeMap(typeLike); + return sanitizeMapWithContext(typeLike, context); case Type.Duration: return sanitizeDuration(typeLike); case Type.Dictionary: - return sanitizeDictionary(typeLike); + return sanitizeDictionaryWithContext(typeLike, context); case Type.Int8: return new Int8(); case Type.Int16: @@ -433,9 +531,9 @@ export function sanitizeType(typeLike: unknown): DataType { case Type.TimestampSecond: return sanitizeTypedTimestamp(typeLike, TimestampSecond); case Type.DenseUnion: - return sanitizeTypedUnion(typeLike, DenseUnion); + return sanitizeTypedUnionWithContext(typeLike, DenseUnion, context); case Type.SparseUnion: - return sanitizeTypedUnion(typeLike, SparseUnion); + return sanitizeTypedUnionWithContext(typeLike, SparseUnion, context); case Type.IntervalDayTime: return new IntervalDayTime(); case Type.IntervalYearMonth: @@ -454,6 +552,13 @@ export function sanitizeType(typeLike: unknown): DataType { } export function sanitizeField(fieldLike: unknown): Field { + return sanitizeFieldWithContext(fieldLike, createSanitizationContext()); +} + +function sanitizeFieldWithContext( + fieldLike: unknown, + context: SanitizationContext, +): Field { if (fieldLike instanceof Field) { return fieldLike; } @@ -471,7 +576,7 @@ export function sanitizeField(fieldLike: unknown): Field { } let type: DataType; try { - type = sanitizeType(fieldLike.type); + type = sanitizeTypeWithContext(fieldLike.type, context); } catch (error: unknown) { throw Error( `Unable to sanitize type for field: ${fieldLike.name} due to error: ${error}`, @@ -501,6 +606,13 @@ export function sanitizeField(fieldLike: unknown): Field { * than lancedb is using. */ export function sanitizeSchema(schemaLike: SchemaLike): Schema { + return sanitizeSchemaWithContext(schemaLike, createSanitizationContext()); +} + +function sanitizeSchemaWithContext( + schemaLike: SchemaLike, + context: SanitizationContext, +): Schema { if (schemaLike instanceof Schema) { return schemaLike; } @@ -522,7 +634,7 @@ export function sanitizeSchema(schemaLike: SchemaLike): Schema { ); } const sanitizedFields = schemaLike.fields.map((field) => - sanitizeField(field), + sanitizeFieldWithContext(field, context), ); return new Schema(sanitizedFields, metadata); } @@ -544,13 +656,18 @@ export function sanitizeTable(tableLike: TableLike): Table { "The table passed in does not appear to be a table (no 'columns' property)", ); } - const schema = sanitizeSchema(tableLike.schema); - - const batches = tableLike.batches.map(sanitizeRecordBatch); + const context = createSanitizationContext(); + const schema = sanitizeSchemaWithContext(tableLike.schema, context); + const batches = tableLike.batches.map((batch) => + sanitizeRecordBatch(batch, context), + ); return new Table(schema, batches); } -function sanitizeRecordBatch(batchLike: RecordBatchLike): RecordBatch { +function sanitizeRecordBatch( + batchLike: RecordBatchLike, + context: SanitizationContext, +): RecordBatch { if (batchLike instanceof RecordBatch) { return batchLike; } @@ -567,19 +684,43 @@ function sanitizeRecordBatch(batchLike: RecordBatchLike): RecordBatch { "The record batch passed in does not appear to be a record batch (no 'data' property)", ); } - const schema = sanitizeSchema(batchLike.schema); - const data = sanitizeData(batchLike.data); + const schema = sanitizeSchemaWithContext(batchLike.schema, context); + const data = sanitizeData(batchLike.data, context) as Data; return new RecordBatch(schema, data); } + +type DictionaryVectorLike = { + data: readonly DataLike[]; +}; + +type DictionaryDataLike = DataLike & { + dictionary?: DictionaryVectorLike; +}; + function sanitizeData( dataLike: DataLike, - // biome-ignore lint/suspicious/noExplicitAny: -): import("apache-arrow").Data> { + context: SanitizationContext, +): Data { if (dataLike instanceof Data) { return dataLike; } - return new Data( - dataLike.type, + const cachedData = context.data.get(dataLike); + if (cachedData !== undefined) { + return cachedData; + } + const dictionaryLike = (dataLike as DictionaryDataLike).dictionary; + let dictionary: Vector | undefined; + if (dictionaryLike !== undefined) { + dictionary = context.vectors.get(dictionaryLike); + if (dictionary === undefined) { + dictionary = new Vector( + dictionaryLike.data.map((data) => sanitizeData(data, context)), + ); + context.vectors.set(dictionaryLike, dictionary); + } + } + const data = new Data( + sanitizeTypeWithContext(dataLike.type, context), dataLike.offset, dataLike.length, dataLike.nullCount, @@ -589,7 +730,11 @@ function sanitizeData( [BufferType.VALIDITY]: dataLike.nullBitmap, [BufferType.TYPE]: dataLike.typeIds, }, + dataLike.children.map((child) => sanitizeData(child, context)), + dictionary, ); + context.data.set(dataLike, data); + return data; } const constructorsByTypeName = { From 12405a407748fd8a445131d6747e92e9592a1dc1 Mon Sep 17 00:00:00 2001 From: ForwardXu Date: Mon, 10 Aug 2026 12:16:21 +0800 Subject: [PATCH 08/14] chore: drop explicit goosefs-sdk pin in favor of opendal 0.58.1 transitive dep (#3910) MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit ## Summary `opendal 0.58.1` (the version pulled in transitively via Lance) already ships `goosefs-sdk 0.1.9`, which includes the upstream fix for the 0.1.6 compile break. The explicit version pin that lancedb has been carrying since the GooseFS feature was introduced is therefore no longer necessary and is now redundant work to maintain. ## Changes - Remove the direct `goosefs-sdk` dependency from `rust/lancedb/Cargo.toml` (it was pinned to `=0.1.9` with a comment referencing the 0.1.6 compile break). - Remove the `dep:goosefs-sdk` entry from the `goosefs` cargo feature, since no source file in lancedb imports the crate directly. - Refresh `Cargo.lock`; `goosefs-sdk 0.1.9` now resolves transitively through `lance` → `opendal 0.58.1`. ## Verification - `cargo fmt --all` — clean - `cargo check --features remote,goosefs --tests --examples` — passes - `Cargo.lock` confirms `goosefs-sdk 0.1.9` is still resolved (now transitively), so the `goosefs` feature continues to enable the same set of Lance/IOPaths as before. ## Backwards compatibility No public API changes. The `goosefs` cargo feature still activates `lance/goosefs`, `lance-io/goosefs`, and `lance-namespace-impls/dir-goosefs`, and the same `goosefs-sdk 0.1.9` version is selected by the resolver. --- Cargo.lock | 1 - rust/lancedb/Cargo.toml | 3 --- 2 files changed, 4 deletions(-) diff --git a/Cargo.lock b/Cargo.lock index 20f20a0ac..ec6b7cbfb 100644 --- a/Cargo.lock +++ b/Cargo.lock @@ -5447,7 +5447,6 @@ dependencies = [ "datafusion-physical-plan", "datafusion-sql", "futures", - "goosefs-sdk", "half", "hf-hub", "http 1.5.0", diff --git a/rust/lancedb/Cargo.toml b/rust/lancedb/Cargo.toml index 2dbd9d895..e33b86b12 100644 --- a/rust/lancedb/Cargo.toml +++ b/rust/lancedb/Cargo.toml @@ -49,8 +49,6 @@ lance-namespace = { workspace = true } lance-namespace-impls = { workspace = true } metrics = { workspace = true, optional = true } metrics-util = { workspace = true, optional = true } -# Pin the GooseFS SDK to the version required by Lance's OpenDAL dependency. -goosefs-sdk = { version = "=0.1.9", optional = true } moka = { workspace = true } pin-project = { workspace = true } tokio = { version = "1.23", features = ["rt-multi-thread", "sync"] } @@ -136,7 +134,6 @@ azure = [ ] cos = ["lance/tencent", "lance-io/tencent"] goosefs = [ - "dep:goosefs-sdk", "lance/goosefs", "lance-io/goosefs", "lance-namespace-impls/dir-goosefs", From 5acce6782e456f5f33a436a247290c4f796264f1 Mon Sep 17 00:00:00 2001 From: Xuanwo Date: Mon, 10 Aug 2026 15:08:36 +0800 Subject: [PATCH 09/14] ci(docs): report link checker failures through issues (#3909) --- .github/workflows/docs-link-check.yml | 119 +++++++++++++++----------- 1 file changed, 70 insertions(+), 49 deletions(-) diff --git a/.github/workflows/docs-link-check.yml b/.github/workflows/docs-link-check.yml index 0e22100eb..1286819bc 100644 --- a/.github/workflows/docs-link-check.yml +++ b/.github/workflows/docs-link-check.yml @@ -36,7 +36,9 @@ jobs: permissions: contents: read outputs: + checker_outcome: ${{ steps.lychee.outcome }} exit_code: ${{ steps.lychee.outputs.exit_code }} + status: ${{ steps.validate.outputs.status }} steps: - name: Checkout uses: actions/checkout@v6 @@ -50,6 +52,7 @@ jobs: - name: Check links id: lychee + continue-on-error: true uses: lycheeverse/lychee-action@e7477775783ea5526144ba13e8db5eec57747ce8 # v2.9.0 with: # Restricted to http(s) on purpose. Much of docs/src is generated @@ -68,38 +71,50 @@ jobs: format: json output: ./lychee/out.json jobSummary: false - # The report, not a red build, is the signal for broken links. The - # validation step below still fails the run if the check itself - # breaks. + # The report issue, not a red workflow run, is the signal for link + # findings and checker failures alike. fail: false - name: Validate report + id: validate # lychee does not reserve exit code 2 for broken links: its CLI # parser also exits 2 on an invalid option, before any link was # checked or any report written. Only a parseable report whose - # counts agree with the exit code counts as a link verdict; anything - # else fails here, and the report job below is skipped entirely, so - # the tracking issue is never touched. Exit 2 covers timeouts as - # well as errors, and a timed-out host is exactly the transient - # unavailability this report exists to surface, so both count as - # findings. Requiring total > 0 also catches a glob that silently - # stopped matching any file. - if: steps.lychee.outputs.exit_code == 0 || steps.lychee.outputs.exit_code == 2 + # counts agree with a completed exit code (0 or 2) counts as a link + # verdict. Everything else becomes a checker-error report instead of + # failing the workflow. Exit 2 covers timeouts as well as errors, and a + # timed-out host is exactly the transient unavailability this report + # exists to surface, so both count as findings. Requiring total > 0 + # also catches a glob that silently stopped matching any file. + if: always() env: + CHECKER_OUTCOME: ${{ steps.lychee.outcome }} EXIT_CODE: ${{ steps.lychee.outputs.exit_code }} run: | - jq -e --argjson code "$EXIT_CODE" ' - (.total > 0) and - (if $code == 0 - then .errors == 0 and .timeouts == 0 - and (.error_map | length == 0) and (.timeout_map | length == 0) - else (.errors + .timeouts) > 0 - and ((.error_map | length) + (.timeout_map | length)) > 0 - end) - ' ./lychee/out.json + status=checker-error + if [[ "$CHECKER_OUTCOME" == success ]] && + [[ "$EXIT_CODE" == 0 || "$EXIT_CODE" == 2 ]] && + jq -e --argjson code "$EXIT_CODE" ' + (.total > 0) and + (if $code == 0 + then .errors == 0 and .timeouts == 0 + and (.error_map | length == 0) and (.timeout_map | length == 0) + else (.errors + .timeouts) > 0 + and ((.error_map | length) + (.timeout_map | length)) > 0 + end) + ' ./lychee/out.json + then + if [[ "$EXIT_CODE" == 0 ]]; then + status=healthy + else + status=findings + fi + fi + echo "status=$status" >> "$GITHUB_OUTPUT" + echo "Validated link check as $status" - name: Upload report - if: steps.lychee.outputs.exit_code == 2 + if: steps.validate.outputs.status == 'findings' uses: actions/upload-artifact@v7 with: name: link-report @@ -115,26 +130,11 @@ jobs: permissions: issues: write env: + CHECKER_OUTCOME: ${{ needs.scan.outputs.checker_outcome }} EXIT_CODE: ${{ needs.scan.outputs.exit_code }} + STATUS: ${{ needs.scan.outputs.status }} GH_TOKEN: ${{ secrets.GITHUB_TOKEN }} steps: - - name: Classify checker result - # lychee exits 0 when every link resolves and 2 when links fail, - # both already cross-checked against the report by the scan job's - # validation step. Anything else (1 runtime, 3 bad config) means the - # check never produced a link verdict, which must surface as a failed - # run rather than be published as "broken documentation links". - run: | - case "$EXIT_CODE" in - 0|2) - echo "lychee exit code $EXIT_CODE" - ;; - *) - echo "::error::lychee exited with '$EXIT_CODE': the link check did not complete. Leaving the report issue untouched." - exit 1 - ;; - esac - - name: Find existing report issue id: report # Matched on title alone, and through search rather than a listing: @@ -144,7 +144,7 @@ jobs: # Closed issues are included because a healthy run closes the report: # an open-only lookup would forget that identity and the next failing # run would open a duplicate. The oldest match stays the canonical - # report and is reopened below when links break again. + # report and is reopened below when a problem recurs. run: | match=$(gh issue list --repo "$GITHUB_REPOSITORY" --state all \ --search "in:title \"$REPORT_TITLE\" author:app/github-actions" \ @@ -154,14 +154,14 @@ jobs: echo "state=$(jq -r '.state // empty' <<<"$match")" >> "$GITHUB_OUTPUT" - name: Download report - if: env.EXIT_CODE == 2 + if: env.STATUS == 'findings' uses: actions/download-artifact@v8 with: name: link-report path: ./lychee - name: Compose report - if: env.EXIT_CODE == 2 + if: env.STATUS == 'findings' run: | run_url="$GITHUB_SERVER_URL/$GITHUB_REPOSITORY/actions/runs/$GITHUB_RUN_ID" { @@ -185,22 +185,41 @@ jobs: ' ./lychee/out.json } > ./lychee/issue.md + - name: Compose checker error report + if: env.STATUS == 'checker-error' + run: | + mkdir -p ./lychee + run_url="$GITHUB_SERVER_URL/$GITHUB_REPOSITORY/actions/runs/$GITHUB_RUN_ID" + { + echo "The documentation link check did not complete in [the latest run]($run_url)." + echo + echo "This issue is rewritten by every scheduled run and closed automatically once a trustworthy run finds that all links resolve." + echo + echo "The checker did not produce a trustworthy link verdict. Treat the previous result, if any, as stale until a later run completes." + echo + echo "* Action outcome: \`$CHECKER_OUTCOME\`" + echo "* Exit code: \`${EXIT_CODE:-not reported}\`" + echo "* Verdict validation: \`failed\`" + } > ./lychee/issue.md + - name: Reopen report issue # A healthy run closes the report, and the issue action below only # rewrites the body of whatever number it is given. Without an - # explicit reopen, the 2 -> 0 -> 2 sequence would keep rewriting a - # closed issue while links are broken. A CLOSED state implies the - # lookup found a canonical issue, so no separate emptiness check. - if: env.EXIT_CODE == 2 && steps.report.outputs.state == 'CLOSED' + # explicit reopen, a later finding or checker error would rewrite a + # closed issue. A CLOSED state implies the lookup found a canonical + # issue, so no separate emptiness check. + if: >- + env.STATUS != 'healthy' && + steps.report.outputs.state == 'CLOSED' env: ISSUE_NUMBER: ${{ steps.report.outputs.number }} run: | run_url="$GITHUB_SERVER_URL/$GITHUB_REPOSITORY/actions/runs/$GITHUB_RUN_ID" gh issue reopen "$ISSUE_NUMBER" --repo "$GITHUB_REPOSITORY" \ - --comment "Broken documentation links found again in [the latest run]($run_url)." + --comment "The documentation link checker reported a problem again in [the latest run]($run_url)." - - name: Report broken links - if: env.EXIT_CODE == 2 + - name: Report link-check problem + if: env.STATUS != 'healthy' uses: peter-evans/create-issue-from-file@fca9117c27cdc29c6c4db3b86c48e4115a786710 # v6.0.0 with: # Empty on the first failing run, which creates the issue; afterwards @@ -213,7 +232,9 @@ jobs: - name: Close report issue once links are healthy # An OPEN state implies the lookup found a canonical issue; a report # that is already closed needs nothing. - if: env.EXIT_CODE == 0 && steps.report.outputs.state == 'OPEN' + if: >- + env.STATUS == 'healthy' && + steps.report.outputs.state == 'OPEN' env: ISSUE_NUMBER: ${{ steps.report.outputs.number }} run: | From 920fc0e455476ed054dae32a4b8e558faa8eec30 Mon Sep 17 00:00:00 2001 From: Xuanwo Date: Mon, 10 Aug 2026 21:40:31 +0800 Subject: [PATCH 10/14] fix(python): set native module metadata (#3913) PyO3 defaults native extension classes to `builtins`, so mkdocstrings/Griffe could not resolve the newly documented `lancedb.Session` alias and `Deploy docs to Pages` failed on `main`. Declare the extension module for the public native types referenced by the Python API docs so Griffe resolves them through `lancedb._lancedb` and Pages can build again. Validated with the docs toolchain used by CI (`griffe==0.49.0`, `mkdocstrings==0.25.2`, and `mkdocs==1.6.1`); `PYTHONPATH=. mkdocs build` succeeds. --- python/src/index.rs | 2 +- python/src/session.rs | 2 +- python/src/table.rs | 2 +- 3 files changed, 3 insertions(+), 3 deletions(-) diff --git a/python/src/index.rs b/python/src/index.rs index 8c81dcecf..dd362373e 100644 --- a/python/src/index.rs +++ b/python/src/index.rs @@ -289,7 +289,7 @@ struct IvfHnswFlatParams { target_partition_size: Option, } -#[pyclass(get_all)] +#[pyclass(module = "lancedb._lancedb", get_all)] /// A description of an index currently configured on a column pub struct IndexConfig { /// The type of the index diff --git a/python/src/session.rs b/python/src/session.rs index 891e61e44..4d58dd269 100644 --- a/python/src/session.rs +++ b/python/src/session.rs @@ -11,7 +11,7 @@ use pyo3::{PyResult, pyclass, pymethods}; /// Sessions allow you to configure cache sizes for index and metadata caches, /// which can significantly impact memory use and performance. They can /// also be re-used across multiple connections to share the same cache state. -#[pyclass(from_py_object)] +#[pyclass(module = "lancedb._lancedb", from_py_object)] #[derive(Clone)] pub struct Session { pub(crate) inner: Arc, diff --git a/python/src/table.rs b/python/src/table.rs index 20a93556f..cae6b5d9a 100644 --- a/python/src/table.rs +++ b/python/src/table.rs @@ -579,7 +579,7 @@ impl PyBlobFile { } } -#[pyclass(get_all, from_py_object)] +#[pyclass(module = "lancedb._lancedb", get_all, from_py_object)] #[derive(Clone, Debug)] pub struct FtsToken { pub text: String, From a615306f39664900da9091484c6e06de4859205d Mon Sep 17 00:00:00 2001 From: Sravan Avvaru <81159574+Sravan1011@users.noreply.github.com> Date: Mon, 10 Aug 2026 21:52:06 +0530 Subject: [PATCH 11/14] feat(python): add on_transform_error fault tolerance to StreamingDataset (#3763) MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit Closes #3704 ## Problem Transforms can fail on bad data (e.g. nulls/NaNs from incomplete user surveys). Today any transform exception aborts iteration, and there is no way to skip invalid rows during loading. ## Solution New `on_transform_error` parameter on `StreamingDataset`: - `"raise"` (default, matches current behavior and the convention in tf.data / WebDataset / Ray Data) - `"skip"` — drop the failing rows and continue - `"warn"` — like skip, plus a logged warning per failing batch - a WebDataset-style callable `handler(exc) -> bool`, so users can skip only expected error types Key design points: - **Row-granular skipping**: when a batch fails, the transform is re-run on single-row slices so only the rows that actually fail are dropped (avoids Ray-style whole-block loss). Skips are counted in a new `rows_skipped` property. - **No crash on uneven skips**: the round-robin loop now ends the epoch at the last cycle where every split still has a row, instead of hitting `IndexError` when a split runs dry early. - **Exact resumability under skips**: checkpoints are now position-based. `state_dict` gains `positions_consumed_per_split` (exact for owned splits), and a new `merge_state_dicts` static method combines per-rank states via elementwise max for elastic resume across topology changes. Old checkpoints without the new key still load. Positions equal sample counts when nothing is skipped, so existing behavior is unchanged. - **Guardrail**: transforms returning the wrong number of rows now raise a clear `ValueError` instead of silently corrupting split accounting. ### Answers to the issue's open questions - *Can we do this?* Yes — all transforms funnel through one guarded call in the Stage 2 pipeline. - *What do other libraries do?* tf.data `ignore_errors()`, WebDataset `handler=`, Ray `max_errored_blocks`; MosaicML StreamingDataset offers nothing (skipping conflicts with its determinism model). This design follows the common conventions: raise by default, opt-in skipping, count/log drops. - *Error handling or pre-filtering?* Both: the existing `filter=` remains the recommended tool for predictable bad data (splits are built post-filter, so all guarantees hold — now documented); `on_transform_error` covers failures not expressible as a predicate. - *Impact on splits / elastic determinism?* Per-split sample sequences stay deterministic (skips are data-dependent, not topology-dependent). With unequal bad-row counts across splits the last few global steps of an epoch can differ across topologies (bounded by the skew), which is documented on the parameter. With equal counts per split, full determinism is preserved — covered by a test. ## Testing 15 new tests in `test_elastic_dataloader.py` covering: default raise, invalid values, uniform and uneven skips (including epoch-end truncation), warn logging, selective callable handlers, wrong-row-count guardrail, determinism across runs and across world sizes (1/2/3/4) with skips, exact mid-epoch resume with skips on the same topology, elastic resume via `merge_state_dicts` (ws=2 → ws=1), merge validation, and backward-compat loading of old checkpoints. Note: relying on CI for the test run — my local machine OOMs during the final link of the native extension. The change itself is pure Python. --------- Co-authored-by: Claude Fable 5 --- python/python/lancedb/streaming.py | 342 +++++++++++++-- .../python/tests/test_elastic_dataloader.py | 402 ++++++++++++++++++ 2 files changed, 717 insertions(+), 27 deletions(-) diff --git a/python/python/lancedb/streaming.py b/python/python/lancedb/streaming.py index 525ed3d63..b27e606a4 100644 --- a/python/python/lancedb/streaming.py +++ b/python/python/lancedb/streaming.py @@ -11,6 +11,11 @@ Provides StreamingDataset, a PyTorch IterableDataset that guarantees: - **Resumability**: state_dict / load_state_dict capture per-split consumption counts so training can resume from an exact mid-epoch position even when the distributed topology changes between runs. + +Transform failures on bad rows (e.g. nulls or NaNs from incomplete data) can +be tolerated with ``on_transform_error="skip"``; see the parameter +documentation on StreamingDataset for how this interacts with the guarantees +above. """ import ctypes @@ -22,7 +27,7 @@ import time from collections import deque from concurrent.futures import ThreadPoolExecutor from multiprocessing import RawArray -from typing import Any, Callable, Iterator, Optional +from typing import Any, Callable, Iterator, Optional, Union from torch.utils.data import IterableDataset, get_worker_info @@ -127,6 +132,49 @@ class StreamingDataset(IterableDataset): Maximum number of transforms to run concurrently. Must be greater than zero. When ``None`` (the default), uses ``os.cpu_count()`` or 1 when the CPU count is unavailable. + on_transform_error: + What to do when the transform raises an exception: + + - ``"raise"`` (the default): the exception propagates and iteration + aborts. + - ``"skip"``: the failing rows are dropped and iteration continues. + - ``"warn"``: like ``"skip"``, but a warning is logged for each + failing batch. + - a callable ``handler(exc) -> bool``: called with the exception; + return ``True`` to skip the failing rows or ``False`` to re-raise. + Useful to skip only expected error types (compatible with + ``webdataset.handlers`` style handlers). + + When a batch fails, the transform is re-invoked on each single-row + slice of the batch so that only the rows that actually fail are + dropped. Transforms should therefore be deterministic and accept + batches of any size (including one row). Skipped rows are counted in + ``rows_skipped``. + + Skipping weakens the elastic-determinism guarantee at the end of the + epoch: splits that lose more rows than others run dry earlier, and + each rank's iterator ends at the last cycle where every split *it + owns* still has a row. Because bad rows are not distributed evenly + across splits, this means one rank's iterator can yield noticeably + fewer or more steps than another rank's *in the same run* — there is + no cross-rank coordination that stops every rank at the same global + step. This is generally safe for asynchronous or single-rank use, + but synchronous distributed training (e.g. ranks that call + ``all_reduce`` every step) can hang or deadlock if one rank's + iterator is exhausted while others are still stepping; callers doing + synchronous multi-rank training with ``on_transform_error != "raise"`` + are responsible for their own cross-rank stopping mechanism (e.g. + broadcasting a stop signal on ``StopIteration``). The final few + global steps can also differ across topologies (bounded by the skew + in bad-row counts across splits). The sequence of samples yielded + from each split remains deterministic. Mid-epoch + checkpoints remain exact provided the transform fails + deterministically; in multi-rank training each rank must save its + own ``state_dict`` and the states must be combined with + ``merge_state_dicts`` before resuming on a different topology. + Prefer the ``filter`` parameter when bad rows can be expressed as a + SQL predicate (e.g. ``"col IS NOT NULL"``) — filtering happens before + splits are built, so every guarantee is fully preserved. worker_info_override: If set, used in place of ``torch.utils.data.get_worker_info()`` to determine the DataLoader worker assignment. Intended for unit tests @@ -152,6 +200,7 @@ class StreamingDataset(IterableDataset): filter: Optional[str] = None, transform: Optional[Callable] = None, transform_parallelism: Optional[int] = None, + on_transform_error: Union[str, Callable[[Exception], bool]] = "raise", connection_factory: Optional[Callable[[str], Any]] = None, worker_info_override=None, ): @@ -167,6 +216,13 @@ class StreamingDataset(IterableDataset): ) if transform_parallelism is not None and transform_parallelism <= 0: raise ValueError("transform_parallelism must be greater than 0") + if on_transform_error not in ("raise", "skip", "warn") and not callable( + on_transform_error + ): + raise ValueError( + "on_transform_error must be 'raise', 'skip', 'warn', or a " + f"callable, got {on_transform_error!r}" + ) self._table = table self._num_splits = num_splits @@ -182,6 +238,7 @@ class StreamingDataset(IterableDataset): self._filter = filter self._transform = transform self._transform_parallelism = transform_parallelism + self._on_transform_error = on_transform_error self._connection_factory = connection_factory self._worker_info_override = worker_info_override @@ -199,19 +256,28 @@ class StreamingDataset(IterableDataset): # in the main process. RawArray is picklable via the forkserver # reduction protocol so it survives the dataset pickle round-trip. # Layout: [unscanned_rows, raw_rows, cooked_rows, consumed_rows, - # bytes_loaded, fetch_time_us, transform_time_us] - self._worker_stats: RawArray = RawArray(ctypes.c_int64, 7) + # bytes_loaded, fetch_time_us, transform_time_us, + # rows_skipped] + self._worker_stats: RawArray = RawArray(ctypes.c_int64, 8) # Cumulative bytes of Arrow buffer data fetched across all iterations. self._bytes_loaded: int = 0 # Cumulative seconds spent in LanceDB I/O and in transform functions. self._fetch_time: float = 0.0 self._transform_time: float = 0.0 + # Cumulative rows dropped by on_transform_error across all iterations. + self._rows_skipped: int = 0 # Number of samples each split has already been consumed. At global # step boundaries all splits have consumed this many samples, so a # single scalar captures the topology-independent checkpoint state. self._resume_offset: int = 0 + # Permutation position each split has consumed through, keyed by + # global split index. Equal to _resume_offset for every split unless + # on_transform_error skipped rows, in which case skipped positions + # push the watermark of the affected splits further ahead. Splits + # this instance has never iterated have no entry. + self._resume_positions: dict[int, int] = {} # Build the permutation table once, deterministically. builder = permutation_builder(table) @@ -275,6 +341,7 @@ class StreamingDataset(IterableDataset): # Set identity transform on each Permutation so __getitems__ returns # the raw RecordBatch. Stage 2 applies the real transform. permutations: list[Permutation] = [] + initial_positions: list[int] = [] for split_idx in my_splits: perm = Permutation.from_tables( self._table, self._perm_table, split=split_idx @@ -282,14 +349,20 @@ class StreamingDataset(IterableDataset): if self._columns is not None: perm = perm.select_columns(self._columns) perm = perm.with_transform(lambda batch: batch) - if self._resume_offset > 0: - perm = perm.with_skip(self._resume_offset) + start_pos = self._resume_positions.get(split_idx, self._resume_offset) + if start_pos > 0: + perm = perm.with_skip(start_pos) + initial_positions.append(start_pos) permutations.append(perm) n = len(permutations) split_sizes = [perm.num_rows for perm in permutations] initial_offset = self._resume_offset local_consumed = [0] * n + # Permutation position each split has consumed through (absolute, + # i.e. counted from the start of the unskipped split). Runs ahead of + # initial + local_consumed when rows are skipped. + pos_consumed = list(initial_positions) batch_size = self._read_batch_size max_prefetch = self._prefetch_batches @@ -302,12 +375,14 @@ class StreamingDataset(IterableDataset): self._transform if self._transform is not None else Transforms.arrow2python ) - # Per-split pipeline state. + # Per-split pipeline state. Batches are paired with the absolute + # permutation position of their first row so that skipped rows can be + # accounted for in pos_consumed. fetch_head = [0] * n - io_pending = [deque() for _ in range(n)] # Future[RecordBatch] - raw_batches = [deque() for _ in range(n)] # RecordBatch — fetched, awaiting tx - tx_pending = [deque() for _ in range(n)] # Future[list[Any]] - cooked = [deque() for _ in range(n)] # rows ready to yield + io_pending = [deque() for _ in range(n)] # (abs_start, Future[RecordBatch]) + raw_batches = [deque() for _ in range(n)] # (abs_start, RecordBatch) + tx_pending = [deque() for _ in range(n)] # Future[list[(abs_pos, row)]] + cooked = [deque() for _ in range(n)] # (abs_pos, row) ready to yield # Limit simultaneous transforms to transform_workers across all splits. tx_semaphore = threading.Semaphore(transform_workers) @@ -330,7 +405,8 @@ class StreamingDataset(IterableDataset): fetch_head[i] += fetch perm_i = permutations[i] indices = list(range(start, start + fetch)) - io_pending[i].append(io_pool.submit(_io_call, perm_i, indices)) + abs_start = initial_positions[i] + start + io_pending[i].append((abs_start, io_pool.submit(_io_call, perm_i, indices))) def _fill_io(i: int) -> None: while len(io_pending[i]) < max_prefetch and fetch_head[i] < split_sizes[i]: @@ -338,15 +414,72 @@ class StreamingDataset(IterableDataset): def _drain_io(i: int) -> None: """Move completed I/O futures into raw_batches non-blockingly.""" - while io_pending[i] and io_pending[i][0].done(): - raw_batches[i].append(io_pending[i].popleft().result()) + while io_pending[i] and io_pending[i][0][1].done(): + abs_start, fut = io_pending[i].popleft() + raw_batches[i].append((abs_start, fut.result())) # ── Stage 2 helpers ─────────────────────────────────────────────────── - def _tx_call_guarded(batch): + on_error = self._on_transform_error + + def _should_skip(exc: Exception) -> bool: + if on_error == "raise": + return False + if callable(on_error): + return bool(on_error(exc)) + return True # "skip" or "warn" + + def _check_row_count(rows: list, num_rows: int) -> None: + if len(rows) != num_rows: + raise ValueError( + f"transform returned {len(rows)} rows for a batch of " + f"{num_rows}; transforms must return exactly one output " + "row per input row. To drop bad rows, raise inside the " + "transform and pass on_transform_error='skip'." + ) + + def _transform_isolated(abs_start, batch, batch_exc): + """Re-run the transform on single-row slices, dropping failures.""" + out = [] + skipped = 0 + first_exc = None + for j in range(batch.num_rows): + try: + rows = list(final_transform(batch.slice(j, 1))) + except Exception as exc: + if not _should_skip(exc): + raise + skipped += 1 + if first_exc is None: + first_exc = exc + continue + _check_row_count(rows, 1) + out.append((abs_start + j, rows[0])) + self._rows_skipped += skipped + if skipped and on_error == "warn": + logger.warning( + "Skipped %d of %d rows whose transform failed (first error: %r)", + skipped, + batch.num_rows, + first_exc if first_exc is not None else batch_exc, + ) + return out + + def _transform_batch(abs_start, batch): + """Apply the transform, returning [(abs_pos, row), ...].""" + try: + rows = list(final_transform(batch)) + except Exception as exc: + if not _should_skip(exc): + raise + return _transform_isolated(abs_start, batch, exc) + _check_row_count(rows, batch.num_rows) + return [(abs_start + j, row) for j, row in enumerate(rows)] + + def _tx_call_guarded(abs_start, batch): try: t0 = time.perf_counter() - result = final_transform(batch) + result = _transform_batch(abs_start, batch) self._transform_time += time.perf_counter() - t0 return result finally: @@ -355,8 +488,8 @@ class StreamingDataset(IterableDataset): def _try_submit_tx(i: int) -> None: """Submit transforms for raw_batches[i] up to available capacity.""" while raw_batches[i] and tx_semaphore.acquire(blocking=False): - batch = raw_batches[i].popleft() - tx_pending[i].append(tx_pool.submit(_tx_call_guarded, batch)) + abs_start, batch = raw_batches[i].popleft() + tx_pending[i].append(tx_pool.submit(_tx_call_guarded, abs_start, batch)) def _drain_tx(i: int) -> None: """Move completed transform futures into cooked non-blockingly.""" @@ -384,11 +517,14 @@ class StreamingDataset(IterableDataset): # Acquire a transform slot (may block briefly if all # transform_workers are busy with other splits). tx_semaphore.acquire() - batch = raw_batches[i].popleft() - tx_pending[i].append(tx_pool.submit(_tx_call_guarded, batch)) + abs_start, batch = raw_batches[i].popleft() + tx_pending[i].append( + tx_pool.submit(_tx_call_guarded, abs_start, batch) + ) elif io_pending[i]: # Block on the oldest in-flight I/O fetch. - raw_batches[i].append(io_pending[i].popleft().result()) + abs_start, fut = io_pending[i].popleft() + raw_batches[i].append((abs_start, fut.result())) _advance(i) else: break # split exhausted @@ -407,15 +543,28 @@ class StreamingDataset(IterableDataset): _fill_io(i) while True: - # Stop when any split is exhausted (all exhaust - # simultaneously: equal split sizes + round-robin). - if any(local_consumed[i] >= split_sizes[i] for i in range(n)): + # A cycle only runs if every split can still produce a + # row. Without skips all splits exhaust simultaneously + # (equal split sizes + round-robin); when + # on_transform_error drops rows a split can run dry + # early, ending the epoch at the last complete cycle. + # This check only sees splits owned by this rank/worker + # (my_splits) — there is no cross-rank coordination, so + # a different rank with fewer skipped rows keeps going; + # see the on_transform_error docstring. + exhausted = False + for i in range(n): + _ensure_cooked(i) + if not cooked[i]: + exhausted = True + break + if exhausted: break for i in range(n): - _ensure_cooked(i) - row = cooked[i].popleft() + pos, row = cooked[i].popleft() local_consumed[i] += 1 + pos_consumed[i] = pos + 1 _advance(i) # After the last split in each cycle: update the @@ -424,21 +573,39 @@ class StreamingDataset(IterableDataset): # even when __iter__ runs in a worker process. if i == n - 1: self._resume_offset = initial_offset + local_consumed[i] + for j, split_idx in enumerate(my_splits): + self._resume_positions[split_idx] = pos_consumed[j] ws = self._worker_stats ws[0] = sum( split_sizes[j] - fetch_head[j] for j in range(n) ) ws[1] = sum( - batch.num_rows for q in raw_batches for batch in q + batch.num_rows + for q in raw_batches + for _, batch in q ) ws[2] = sum(len(q) for q in cooked) ws[3] = sum(local_consumed) ws[4] = self._bytes_loaded ws[5] = int(self._fetch_time * 1_000_000) ws[6] = int(self._transform_time * 1_000_000) + ws[7] = self._rows_skipped yield row finally: + # Final stats flush: the per-cycle write above never runs + # when iteration ends mid-cycle (e.g. a split whose rows + # were all skipped before completing a single cycle), so + # counters like rows_skipped would otherwise be stale. + ws = self._worker_stats + ws[0] = sum(split_sizes[j] - fetch_head[j] for j in range(n)) + ws[1] = 0 # queue-depth properties document 0 when idle + ws[2] = 0 + ws[3] = sum(local_consumed) + ws[4] = self._bytes_loaded + ws[5] = int(self._fetch_time * 1_000_000) + ws[6] = int(self._transform_time * 1_000_000) + ws[7] = self._rows_skipped self._raw_batches_ref = None self._cooked_ref = None self._fetch_head_ref = None @@ -492,7 +659,7 @@ class StreamingDataset(IterableDataset): batches. Returns 0 when not iterating. """ if self._raw_batches_ref is not None: - return sum(batch.num_rows for q in self._raw_batches_ref for batch in q) + return sum(batch.num_rows for q in self._raw_batches_ref for _, batch in q) return int(self._worker_stats[1]) @property @@ -522,6 +689,19 @@ class StreamingDataset(IterableDataset): ) return int(self._worker_stats[0]) + @property + def rows_skipped(self) -> int: + """Number of rows dropped because their transform raised an exception. + + Only ever non-zero when ``on_transform_error`` is set to ``"skip"``, + ``"warn"``, or a callable that returned ``True``. Accumulates across + multiple iterations of the same dataset instance and is never reset + automatically. + """ + if self._raw_batches_ref is not None: + return self._rows_skipped + return int(self._worker_stats[7]) + @property def consumed_rows(self) -> int: """Number of rows already yielded to the caller across all splits. @@ -587,12 +767,27 @@ class StreamingDataset(IterableDataset): every split has been consumed the same number of times (by the round-robin design), so the per-split count is a single uniform value that is identical across all ranks and DataLoader workers. + + ``positions_consumed_per_split`` records how far into each split's + permutation iteration has advanced. It only differs from + ``samples_consumed_per_split`` when ``on_transform_error`` skipped + rows, in which case entries are exact for the splits this instance + iterated and a lower bound (the sample count) for splits owned by + other ranks or workers. Combine the state dicts from all ranks with + [merge_state_dicts][lancedb.streaming.StreamingDataset.merge_state_dicts] + to recover the exact value for every split before resuming on a + different topology. """ + positions = [ + self._resume_positions.get(split, self._resume_offset) + for split in range(self._num_splits) + ] return { "shuffle_seed": self._shuffle_seed, "num_splits": self._num_splits, "epoch": self._epoch, "samples_consumed_per_split": [self._resume_offset] * self._num_splits, + "positions_consumed_per_split": positions, } def load_state_dict(self, state: dict) -> None: @@ -618,3 +813,96 @@ class StreamingDataset(IterableDataset): self._resume_offset = consumed[0] if consumed else 0 else: self._resume_offset = int(consumed) + # Older checkpoints predate positions_consumed_per_split; without + # skipped rows positions equal sample counts, so falling back to + # _resume_offset (the .get default in __iter__) is exact. + positions = state.get("positions_consumed_per_split") + if positions is None: + self._resume_positions = {} + else: + self._resume_positions = { + split: int(pos) for split, pos in enumerate(positions) + } + + @staticmethod + def merge_state_dicts(states: list[dict]) -> dict: + """Merge state dicts saved by different ranks into one exact state. + + Only needed when ``on_transform_error`` skips rows in multi-rank + training: each rank then knows the exact permutation position only for + its own splits, and records a lower bound for the rest. Because + exactly one rank owns each split, the elementwise maximum across all + ranks' ``positions_consumed_per_split`` recovers the exact position of + every split. Without skipped rows every rank's state is already + identical and merging is a no-op. + + Raises ``ValueError`` if the states are empty or were not produced by + the same run (mismatched seed, split count, epoch, or sample counts). + + The merge is always all-to-all and topology-agnostic: collect the + ``state_dict()`` from every rank of the *previous* run into one list, + merge that whole list, and hand the identical merged result to every + rank of the *next* run — regardless of whether the rank count grew, + shrank, or stayed the same. There is no pairwise or subset merging + step, because each split's exact position is only known to whichever + rank owned that split, and the elementwise maximum needs every rank's + contribution to be correct. + + For example, checkpointing 8 ranks and resuming on 4 (the same + pattern applies when growing, e.g. 4 ranks resuming on 8):: + + states = [ds.state_dict() for ds in previous_run_datasets] # 8 + merged = StreamingDataset.merge_state_dicts(states) + for ds in resumed_datasets: # now only 4 ranks + ds.load_state_dict(merged) # same dict on every rank + + The rank count on either side never affects the merge itself, since + ``merge_state_dicts`` only cares about the list of states it is + given. Each split's position is recovered by elementwise maximum; + here rank 0 owned split 0 (and skipped two rows there) while rank 1 + owned split 1 (and skipped one row): + + >>> rank0 = { + ... "shuffle_seed": 0, "num_splits": 2, "epoch": 0, + ... "samples_consumed_per_split": [3, 3], + ... "positions_consumed_per_split": [5, 3], + ... } + >>> rank1 = { + ... "shuffle_seed": 0, "num_splits": 2, "epoch": 0, + ... "samples_consumed_per_split": [3, 3], + ... "positions_consumed_per_split": [3, 4], + ... } + >>> merged = StreamingDataset.merge_state_dicts([rank0, rank1]) + >>> merged["positions_consumed_per_split"] + [5, 4] + """ + if not states: + raise ValueError("merge_state_dicts requires at least one state dict") + first = states[0] + for state in states[1:]: + for key in ("shuffle_seed", "num_splits", "epoch"): + if state[key] != first[key]: + raise ValueError( + f"{key} mismatch across state dicts: " + f"{state[key]} != {first[key]}" + ) + if ( + state["samples_consumed_per_split"] + != first["samples_consumed_per_split"] + ): + raise ValueError( + "samples_consumed_per_split mismatch across state dicts; " + "state_dict() must be called at the same global step " + "boundary on every rank" + ) + merged = dict(first) + all_positions = [ + state.get( + "positions_consumed_per_split", state["samples_consumed_per_split"] + ) + for state in states + ] + merged["positions_consumed_per_split"] = [ + max(per_split) for per_split in zip(*all_positions) + ] + return merged diff --git a/python/python/tests/test_elastic_dataloader.py b/python/python/tests/test_elastic_dataloader.py index 22918082b..734f835c6 100644 --- a/python/python/tests/test_elastic_dataloader.py +++ b/python/python/tests/test_elastic_dataloader.py @@ -1456,6 +1456,408 @@ def test_shuffle_clump_size_yields_all_rows(lance_table): ) +# --------------------------------------------------------------------------- +# on_transform_error tests +# --------------------------------------------------------------------------- + + +class BadRowError(ValueError): + """Raised by the failing transforms below when a batch contains a bad id.""" + + +def _failing_transform(bad_ids: set): + """A transform that raises BadRowError whenever the batch has a bad id. + + Raises on the full batch and on any single-row slice containing a bad id, + so per-row isolation drops exactly the bad rows. + """ + + def transform(batch: pa.RecordBatch) -> list: + ids = batch.column("id").to_pylist() + bad = sorted(set(ids) & bad_ids) + if bad: + raise BadRowError(f"bad ids in batch: {bad}") + return [{"id": i} for i in ids] + + return transform + + +def _sequential_split_members(table) -> list[list[int]]: + """Return each split's ids in yield order for shuffle=False. + + With a single rank and no workers the round-robin yields one row per split + per cycle, so item k of a clean run belongs to split k % NUM_SPLITS. + """ + ds = StreamingDataset(table, num_splits=NUM_SPLITS, shuffle=False) + members: list[list[int]] = [[] for _ in range(NUM_SPLITS)] + for k, row in enumerate(ds): + members[k % NUM_SPLITS].append(row["id"]) + return members + + +def test_on_transform_error_default_raises(lance_table): + """By default a transform exception propagates and aborts iteration.""" + ds = StreamingDataset( + lance_table, + num_splits=NUM_SPLITS, + shuffle_seed=SHUFFLE_SEED, + transform=_failing_transform({7}), + ) + with pytest.raises(BadRowError): + list(ds) + + +def test_on_transform_error_invalid_value(lance_table): + with pytest.raises(ValueError, match="on_transform_error"): + StreamingDataset(lance_table, num_splits=NUM_SPLITS, on_transform_error="bogus") + + +def test_on_transform_error_skip_drops_bad_rows(lance_table): + """With one bad row per split, 'skip' yields every good row exactly once + and counts the dropped rows in rows_skipped.""" + members = _sequential_split_members(lance_table) + bad_ids = {members[i][4] for i in range(NUM_SPLITS)} + + ds = StreamingDataset( + lance_table, + num_splits=NUM_SPLITS, + shuffle=False, + transform=_failing_transform(bad_ids), + on_transform_error="skip", + ) + assert ds.rows_skipped == 0 + + ids = [row["id"] for row in ds] + + assert sorted(ids) == sorted(set(range(NUM_ROWS)) - bad_ids) + assert ds.rows_skipped == NUM_SPLITS + + +def test_on_transform_error_skip_uneven_ends_at_last_complete_cycle(lance_table): + """When one split loses more rows than the others, the epoch ends at the + last cycle where every split still has a row — no crash, no bad rows, and + every step remains one sample per split.""" + members = _sequential_split_members(lance_table) + bad_ids = set(members[0][:3]) # all 3 bad rows in split 0 + + ds = StreamingDataset( + lance_table, + num_splits=NUM_SPLITS, + shuffle=False, + transform=_failing_transform(bad_ids), + on_transform_error="skip", + ) + items = [row["id"] for row in ds] + + rows_per_split = NUM_ROWS // NUM_SPLITS + expected_cycles = rows_per_split - len(bad_ids) + assert len(items) == expected_cycles * NUM_SPLITS + assert len(set(items)) == len(items), "duplicate samples yielded" + assert not set(items) & bad_ids, "a bad row was yielded" + # Split 0 contributed exactly its surviving rows, in order, one per cycle. + survivors = [i for i in members[0] if i not in bad_ids] + assert items[0::NUM_SPLITS] == survivors[:expected_cycles] + + +def test_on_transform_error_warn_logs(lance_table, caplog): + """'warn' skips like 'skip' but logs a warning for the failing batch.""" + members = _sequential_split_members(lance_table) + bad_ids = {members[i][3] for i in range(NUM_SPLITS)} + + ds = StreamingDataset( + lance_table, + num_splits=NUM_SPLITS, + shuffle=False, + transform=_failing_transform(bad_ids), + on_transform_error="warn", + ) + with caplog.at_level(logging.WARNING, logger="lancedb.streaming"): + items = list(ds) + + assert len(items) == NUM_ROWS - NUM_SPLITS + assert ds.rows_skipped == NUM_SPLITS + assert "Skipped" in caplog.text + assert "BadRowError" in caplog.text + + +def test_on_transform_error_callable_selective(lance_table): + """A callable handler can skip expected errors and re-raise the rest.""" + members = _sequential_split_members(lance_table) + bad_ids = {members[i][0] for i in range(NUM_SPLITS)} + + handled: list[Exception] = [] + + def handler(exc: Exception) -> bool: + handled.append(exc) + return isinstance(exc, BadRowError) + + ds = StreamingDataset( + lance_table, + num_splits=NUM_SPLITS, + shuffle=False, + transform=_failing_transform(bad_ids), + on_transform_error=handler, + ) + items = list(ds) + assert len(items) == NUM_ROWS - NUM_SPLITS + assert handled and all(isinstance(exc, BadRowError) for exc in handled) + + def broken_transform(batch: pa.RecordBatch) -> list: + raise TypeError("boom") + + ds2 = StreamingDataset( + lance_table, + num_splits=NUM_SPLITS, + shuffle=False, + transform=broken_transform, + on_transform_error=handler, + ) + with pytest.raises(TypeError, match="boom"): + list(ds2) + + +def test_transform_wrong_row_count_raises(lance_table): + """A transform that returns the wrong number of rows is an error even with + on_transform_error='skip' — silent shrinkage would corrupt accounting.""" + + def drops_rows(batch: pa.RecordBatch) -> list: + return batch.column("id").to_pylist()[:-1] + + ds = StreamingDataset( + lance_table, + num_splits=NUM_SPLITS, + shuffle_seed=SHUFFLE_SEED, + transform=drops_rows, + on_transform_error="skip", + ) + with pytest.raises(ValueError, match="one output row per input row"): + list(ds) + + +def test_skip_deterministic_across_runs(lance_table): + """With a fixed seed, skipping produces the identical sample sequence on + every run — skips are data-dependent, not run-dependent.""" + bad_ids = {5, 17, 46} + + def run() -> tuple[list[int], int]: + ds = StreamingDataset( + lance_table, + num_splits=NUM_SPLITS, + shuffle_seed=SHUFFLE_SEED, + transform=_failing_transform(bad_ids), + on_transform_error="skip", + ) + return [row["id"] for row in ds], ds.rows_skipped + + ids_a, skipped_a = run() + ids_b, skipped_b = run() + assert ids_a == ids_b + assert skipped_a == skipped_b + assert not set(ids_a) & bad_ids + + +def test_skip_elastic_det_across_world_sizes(lance_table): + """With equal bad-row counts per split, skipping preserves the full + elastic-determinism guarantee: identical global batches at every step for + every compatible world_size.""" + members = _sequential_split_members(lance_table) + bad_ids = {members[i][6] for i in range(NUM_SPLITS)} + + def collect(world_size: int) -> list[frozenset[int]]: + micro = GLOBAL_BATCH_SIZE // world_size + iters = [ + iter( + StreamingDataset( + lance_table, + num_splits=NUM_SPLITS, + shuffle=False, + rank=rank, + world_size=world_size, + transform=_failing_transform(bad_ids), + on_transform_error="skip", + ) + ) + for rank in range(world_size) + ] + _STOP = object() + batches: list[frozenset[int]] = [] + while True: + step_samples: set[int] = set() + exhausted = 0 + for it in iters: + for _ in range(micro): + val = next(it, _STOP) + if val is _STOP: + exhausted += 1 + break + step_samples.add(val["id"]) + if exhausted == len(iters): + break + assert exhausted == 0, ( + "Rank iterators exhausted at different steps despite equal " + "bad-row counts per split" + ) + batches.append(frozenset(step_samples)) + return batches + + reference = collect(1) + assert len(reference) == NUM_ROWS // NUM_SPLITS - 1 + for ws in (2, 3, 4): + assert collect(ws) == reference, f"world_size={ws} diverged" + + +def test_resumability_with_skips_same_topology(lance_table): + """Checkpointing mid-epoch with skipped rows resumes exactly: no sample + repeated, no sample lost, skipped rows stay skipped.""" + members = _sequential_split_members(lance_table) + # Uneven skips: positions diverge across splits (2 bad in split 0, 1 in + # split 5), which only a position-based checkpoint can resume exactly. + bad_ids = {members[0][2], members[0][3], members[5][7]} + kwargs = dict( + num_splits=NUM_SPLITS, + shuffle=False, + transform=_failing_transform(bad_ids), + on_transform_error="skip", + ) + + reference = [row["id"] for row in StreamingDataset(lance_table, **kwargs)] + rows_per_split = NUM_ROWS // NUM_SPLITS + assert len(reference) == (rows_per_split - 2) * NUM_SPLITS + + steps = 3 + ds = StreamingDataset(lance_table, **kwargs) + it = iter(ds) + consumed = [next(it)["id"] for _ in range(steps * NUM_SPLITS)] + checkpoint = ds.state_dict() + it.close() + + # Split 0 skipped positions 2 and 3 within its first 3 yields; split 5's + # bad row is beyond the checkpoint. Everything else is at 3 = the sample + # count. + positions = checkpoint["positions_consumed_per_split"] + assert positions[0] == 5 + assert positions[1:] == [3] * (NUM_SPLITS - 1) + assert checkpoint["samples_consumed_per_split"] == [3] * NUM_SPLITS + + ds2 = StreamingDataset(lance_table, **kwargs) + ds2.load_state_dict(checkpoint) + resumed = [row["id"] for row in ds2] + + assert consumed == reference[: steps * NUM_SPLITS] + assert resumed == reference[steps * NUM_SPLITS :] + + +def test_resumability_with_skips_elastic_merge(lance_table): + """Elastic resume with skips: each rank's checkpoint knows exact positions + only for its own splits; merge_state_dicts recovers the global state, and + a run on a different world_size continues exactly.""" + members = _sequential_split_members(lance_table) + # Bad rows early in split 0 (rank 0) and split 6 (rank 1 of a ws=2 run) so + # both ranks' position vectors diverge before the checkpoint. + bad_ids = {members[0][0], members[0][2], members[6][1]} + kwargs = dict( + num_splits=NUM_SPLITS, + shuffle=False, + transform=_failing_transform(bad_ids), + on_transform_error="skip", + ) + + reference = [row["id"] for row in StreamingDataset(lance_table, **kwargs)] + + steps = 3 + world_size = 2 + micro = GLOBAL_BATCH_SIZE // world_size + datasets = [ + StreamingDataset(lance_table, rank=rank, world_size=world_size, **kwargs) + for rank in range(world_size) + ] + iters = [iter(ds) for ds in datasets] + seen: list[frozenset[int]] = [] + for _ in range(steps): + step_samples = set() + for it in iters: + for _ in range(micro): + step_samples.add(next(it)["id"]) + seen.append(frozenset(step_samples)) + states = [ds.state_dict() for ds in datasets] + for it in iters: + it.close() + + merged = StreamingDataset.merge_state_dicts(states) + expected_positions = [3] * NUM_SPLITS + expected_positions[0] = 5 # skipped positions 0 and 2 + expected_positions[6] = 4 # skipped position 1 + assert merged["positions_consumed_per_split"] == expected_positions + + # The first 3 global batches match the world_size=1 reference. + ref_batches = [ + frozenset(reference[s * NUM_SPLITS : (s + 1) * NUM_SPLITS]) + for s in range(len(reference) // NUM_SPLITS) + ] + assert seen == ref_batches[:steps] + + # Resume on world_size=1 from the merged state. + ds_resume = StreamingDataset(lance_table, **kwargs) + ds_resume.load_state_dict(merged) + resumed = [row["id"] for row in ds_resume] + assert resumed == reference[steps * NUM_SPLITS :] + + +def test_rows_skipped_flushed_when_split_entirely_bad(lance_table): + """A split whose rows all fail never completes a cycle, so the epoch ends + immediately — but rows_skipped must still report the drops after the + iterator exits (the shared-memory counter is flushed on exhaustion).""" + members = _sequential_split_members(lance_table) + bad_ids = set(members[0]) # every row of split 0 is bad + + ds = StreamingDataset( + lance_table, + num_splits=NUM_SPLITS, + shuffle=False, + transform=_failing_transform(bad_ids), + on_transform_error="skip", + ) + assert list(ds) == [] + assert ds.rows_skipped == len(bad_ids) + + +def test_merge_state_dicts_validates_consistency(lance_table): + ds = StreamingDataset(lance_table, num_splits=NUM_SPLITS, shuffle_seed=SHUFFLE_SEED) + state = ds.state_dict() + other = dict(state, shuffle_seed=SHUFFLE_SEED + 1) + with pytest.raises(ValueError, match="shuffle_seed mismatch"): + StreamingDataset.merge_state_dicts([state, other]) + with pytest.raises(ValueError, match="at least one"): + StreamingDataset.merge_state_dicts([]) + + +def test_load_state_dict_without_positions_key(lance_table): + """Checkpoints from before positions_consumed_per_split existed still + resume exactly (positions equal sample counts when nothing is skipped).""" + reference = [ + row["id"] + for row in StreamingDataset( + lance_table, num_splits=NUM_SPLITS, shuffle_seed=SHUFFLE_SEED + ) + ] + + steps = 4 + ds = StreamingDataset(lance_table, num_splits=NUM_SPLITS, shuffle_seed=SHUFFLE_SEED) + it = iter(ds) + for _ in range(steps * NUM_SPLITS): + next(it) + checkpoint = ds.state_dict() + it.close() + del checkpoint["positions_consumed_per_split"] + + ds2 = StreamingDataset( + lance_table, num_splits=NUM_SPLITS, shuffle_seed=SHUFFLE_SEED + ) + ds2.load_state_dict(checkpoint) + resumed = [row["id"] for row in ds2] + assert resumed == reference[steps * NUM_SPLITS :] + + def test_num_splits_defaults_to_world_size(lance_table): """Omitting num_splits gives world_size splits (one per rank).""" ds = StreamingDataset( From 6fb976cf894f5b83cd24c6d7930fc6ace47e0c52 Mon Sep 17 00:00:00 2001 From: LanceDB Robot Date: Tue, 11 Aug 2026 23:43:44 -0700 Subject: [PATCH 12/14] chore: update lance dependency to v11.0.0-beta.6 (#3922) Updates the Rust workspace Lance dependencies and Java lance-core dependency to v11.0.0-beta.6. Includes compatibility updates for the new concrete Lance file-version API. Trigger: https://github.com/lance-format/lance/releases/tag/v11.0.0-beta.6 --------- Co-authored-by: XYZhan --- Cargo.lock | 84 ++++++++++----------- Cargo.toml | 28 +++---- deny.toml | 7 ++ java/pom.xml | 2 +- rust/lancedb/src/blob.rs | 11 ++- rust/lancedb/src/connection/create_table.rs | 5 +- rust/lancedb/src/table.rs | 4 +- rust/lancedb/tests/blob_integration.rs | 31 ++++---- 8 files changed, 93 insertions(+), 79 deletions(-) diff --git a/Cargo.lock b/Cargo.lock index ec6b7cbfb..c5545ea8a 100644 --- a/Cargo.lock +++ b/Cargo.lock @@ -3455,8 +3455,8 @@ checksum = "42703706b716c37f96a77aea830392ad231f44c9e9a67872fa5548707e11b11c" [[package]] name = "fsst" -version = "11.0.0-beta.3" -source = "git+https://github.com/lance-format/lance.git?tag=v11.0.0-beta.3#f7d475539cefbd140cc46a828f3d843e68cd10f1" +version = "11.0.0-beta.6" +source = "git+https://github.com/lance-format/lance.git?tag=v11.0.0-beta.6#5ab688688c411111d94d279bacd037d7c319dc10" dependencies = [ "arrow-array", "rand 0.9.5", @@ -4815,8 +4815,8 @@ checksum = "e037a2e1d8d5fdbd49b16a4ea09d5d6401c1f29eca5ff29d03d3824dba16256a" [[package]] name = "lance" -version = "11.0.0-beta.3" -source = "git+https://github.com/lance-format/lance.git?tag=v11.0.0-beta.3#f7d475539cefbd140cc46a828f3d843e68cd10f1" +version = "11.0.0-beta.6" +source = "git+https://github.com/lance-format/lance.git?tag=v11.0.0-beta.6#5ab688688c411111d94d279bacd037d7c319dc10" dependencies = [ "arc-swap", "arrow", @@ -4890,8 +4890,8 @@ dependencies = [ [[package]] name = "lance-arrow" -version = "11.0.0-beta.3" -source = "git+https://github.com/lance-format/lance.git?tag=v11.0.0-beta.3#f7d475539cefbd140cc46a828f3d843e68cd10f1" +version = "11.0.0-beta.6" +source = "git+https://github.com/lance-format/lance.git?tag=v11.0.0-beta.6#5ab688688c411111d94d279bacd037d7c319dc10" dependencies = [ "arrow-array", "arrow-buffer", @@ -4913,7 +4913,7 @@ dependencies = [ [[package]] name = "lance-arrow-scalar" version = "58.0.0" -source = "git+https://github.com/lance-format/lance.git?tag=v11.0.0-beta.3#f7d475539cefbd140cc46a828f3d843e68cd10f1" +source = "git+https://github.com/lance-format/lance.git?tag=v11.0.0-beta.6#5ab688688c411111d94d279bacd037d7c319dc10" dependencies = [ "arrow-array", "arrow-buffer", @@ -4927,7 +4927,7 @@ dependencies = [ [[package]] name = "lance-arrow-stats" version = "58.0.0" -source = "git+https://github.com/lance-format/lance.git?tag=v11.0.0-beta.3#f7d475539cefbd140cc46a828f3d843e68cd10f1" +source = "git+https://github.com/lance-format/lance.git?tag=v11.0.0-beta.6#5ab688688c411111d94d279bacd037d7c319dc10" dependencies = [ "arrow-array", "arrow-schema", @@ -4936,8 +4936,8 @@ dependencies = [ [[package]] name = "lance-bitpacking" -version = "11.0.0-beta.3" -source = "git+https://github.com/lance-format/lance.git?tag=v11.0.0-beta.3#f7d475539cefbd140cc46a828f3d843e68cd10f1" +version = "11.0.0-beta.6" +source = "git+https://github.com/lance-format/lance.git?tag=v11.0.0-beta.6#5ab688688c411111d94d279bacd037d7c319dc10" dependencies = [ "arrayref", "crunchy", @@ -4947,8 +4947,8 @@ dependencies = [ [[package]] name = "lance-core" -version = "11.0.0-beta.3" -source = "git+https://github.com/lance-format/lance.git?tag=v11.0.0-beta.3#f7d475539cefbd140cc46a828f3d843e68cd10f1" +version = "11.0.0-beta.6" +source = "git+https://github.com/lance-format/lance.git?tag=v11.0.0-beta.6#5ab688688c411111d94d279bacd037d7c319dc10" dependencies = [ "arrow-array", "arrow-buffer", @@ -4988,8 +4988,8 @@ dependencies = [ [[package]] name = "lance-datafusion" -version = "11.0.0-beta.3" -source = "git+https://github.com/lance-format/lance.git?tag=v11.0.0-beta.3#f7d475539cefbd140cc46a828f3d843e68cd10f1" +version = "11.0.0-beta.6" +source = "git+https://github.com/lance-format/lance.git?tag=v11.0.0-beta.6#5ab688688c411111d94d279bacd037d7c319dc10" dependencies = [ "arrow", "arrow-array", @@ -5019,8 +5019,8 @@ dependencies = [ [[package]] name = "lance-datagen" -version = "11.0.0-beta.3" -source = "git+https://github.com/lance-format/lance.git?tag=v11.0.0-beta.3#f7d475539cefbd140cc46a828f3d843e68cd10f1" +version = "11.0.0-beta.6" +source = "git+https://github.com/lance-format/lance.git?tag=v11.0.0-beta.6#5ab688688c411111d94d279bacd037d7c319dc10" dependencies = [ "arrow", "arrow-array", @@ -5037,8 +5037,8 @@ dependencies = [ [[package]] name = "lance-derive" -version = "11.0.0-beta.3" -source = "git+https://github.com/lance-format/lance.git?tag=v11.0.0-beta.3#f7d475539cefbd140cc46a828f3d843e68cd10f1" +version = "11.0.0-beta.6" +source = "git+https://github.com/lance-format/lance.git?tag=v11.0.0-beta.6#5ab688688c411111d94d279bacd037d7c319dc10" dependencies = [ "proc-macro2", "quote", @@ -5047,8 +5047,8 @@ dependencies = [ [[package]] name = "lance-encoding" -version = "11.0.0-beta.3" -source = "git+https://github.com/lance-format/lance.git?tag=v11.0.0-beta.3#f7d475539cefbd140cc46a828f3d843e68cd10f1" +version = "11.0.0-beta.6" +source = "git+https://github.com/lance-format/lance.git?tag=v11.0.0-beta.6#5ab688688c411111d94d279bacd037d7c319dc10" dependencies = [ "arrow-arith", "arrow-array", @@ -5082,8 +5082,8 @@ dependencies = [ [[package]] name = "lance-file" -version = "11.0.0-beta.3" -source = "git+https://github.com/lance-format/lance.git?tag=v11.0.0-beta.3#f7d475539cefbd140cc46a828f3d843e68cd10f1" +version = "11.0.0-beta.6" +source = "git+https://github.com/lance-format/lance.git?tag=v11.0.0-beta.6#5ab688688c411111d94d279bacd037d7c319dc10" dependencies = [ "arrow-arith", "arrow-array", @@ -5114,8 +5114,8 @@ dependencies = [ [[package]] name = "lance-index" -version = "11.0.0-beta.3" -source = "git+https://github.com/lance-format/lance.git?tag=v11.0.0-beta.3#f7d475539cefbd140cc46a828f3d843e68cd10f1" +version = "11.0.0-beta.6" +source = "git+https://github.com/lance-format/lance.git?tag=v11.0.0-beta.6#5ab688688c411111d94d279bacd037d7c319dc10" dependencies = [ "arc-swap", "arrow", @@ -5182,8 +5182,8 @@ dependencies = [ [[package]] name = "lance-index-core" -version = "11.0.0-beta.3" -source = "git+https://github.com/lance-format/lance.git?tag=v11.0.0-beta.3#f7d475539cefbd140cc46a828f3d843e68cd10f1" +version = "11.0.0-beta.6" +source = "git+https://github.com/lance-format/lance.git?tag=v11.0.0-beta.6#5ab688688c411111d94d279bacd037d7c319dc10" dependencies = [ "arrow-array", "arrow-schema", @@ -5205,8 +5205,8 @@ dependencies = [ [[package]] name = "lance-io" -version = "11.0.0-beta.3" -source = "git+https://github.com/lance-format/lance.git?tag=v11.0.0-beta.3#f7d475539cefbd140cc46a828f3d843e68cd10f1" +version = "11.0.0-beta.6" +source = "git+https://github.com/lance-format/lance.git?tag=v11.0.0-beta.6#5ab688688c411111d94d279bacd037d7c319dc10" dependencies = [ "arrow", "arrow-array", @@ -5242,8 +5242,8 @@ dependencies = [ [[package]] name = "lance-linalg" -version = "11.0.0-beta.3" -source = "git+https://github.com/lance-format/lance.git?tag=v11.0.0-beta.3#f7d475539cefbd140cc46a828f3d843e68cd10f1" +version = "11.0.0-beta.6" +source = "git+https://github.com/lance-format/lance.git?tag=v11.0.0-beta.6#5ab688688c411111d94d279bacd037d7c319dc10" dependencies = [ "arrow-array", "arrow-buffer", @@ -5259,8 +5259,8 @@ dependencies = [ [[package]] name = "lance-namespace" -version = "11.0.0-beta.3" -source = "git+https://github.com/lance-format/lance.git?tag=v11.0.0-beta.3#f7d475539cefbd140cc46a828f3d843e68cd10f1" +version = "11.0.0-beta.6" +source = "git+https://github.com/lance-format/lance.git?tag=v11.0.0-beta.6#5ab688688c411111d94d279bacd037d7c319dc10" dependencies = [ "arrow", "async-trait", @@ -5272,8 +5272,8 @@ dependencies = [ [[package]] name = "lance-namespace-impls" -version = "11.0.0-beta.3" -source = "git+https://github.com/lance-format/lance.git?tag=v11.0.0-beta.3#f7d475539cefbd140cc46a828f3d843e68cd10f1" +version = "11.0.0-beta.6" +source = "git+https://github.com/lance-format/lance.git?tag=v11.0.0-beta.6#5ab688688c411111d94d279bacd037d7c319dc10" dependencies = [ "arrow", "arrow-ipc", @@ -5326,8 +5326,8 @@ dependencies = [ [[package]] name = "lance-select" -version = "11.0.0-beta.3" -source = "git+https://github.com/lance-format/lance.git?tag=v11.0.0-beta.3#f7d475539cefbd140cc46a828f3d843e68cd10f1" +version = "11.0.0-beta.6" +source = "git+https://github.com/lance-format/lance.git?tag=v11.0.0-beta.6#5ab688688c411111d94d279bacd037d7c319dc10" dependencies = [ "arrow-array", "arrow-buffer", @@ -5342,8 +5342,8 @@ dependencies = [ [[package]] name = "lance-table" -version = "11.0.0-beta.3" -source = "git+https://github.com/lance-format/lance.git?tag=v11.0.0-beta.3#f7d475539cefbd140cc46a828f3d843e68cd10f1" +version = "11.0.0-beta.6" +source = "git+https://github.com/lance-format/lance.git?tag=v11.0.0-beta.6#5ab688688c411111d94d279bacd037d7c319dc10" dependencies = [ "arrow", "arrow-array", @@ -5383,8 +5383,8 @@ dependencies = [ [[package]] name = "lance-testing" -version = "11.0.0-beta.3" -source = "git+https://github.com/lance-format/lance.git?tag=v11.0.0-beta.3#f7d475539cefbd140cc46a828f3d843e68cd10f1" +version = "11.0.0-beta.6" +source = "git+https://github.com/lance-format/lance.git?tag=v11.0.0-beta.6#5ab688688c411111d94d279bacd037d7c319dc10" dependencies = [ "arrow-array", "arrow-schema", @@ -5397,8 +5397,8 @@ dependencies = [ [[package]] name = "lance-tokenizer" -version = "11.0.0-beta.3" -source = "git+https://github.com/lance-format/lance.git?tag=v11.0.0-beta.3#f7d475539cefbd140cc46a828f3d843e68cd10f1" +version = "11.0.0-beta.6" +source = "git+https://github.com/lance-format/lance.git?tag=v11.0.0-beta.6#5ab688688c411111d94d279bacd037d7c319dc10" dependencies = [ "frostem", "icu_segmenter", diff --git a/Cargo.toml b/Cargo.toml index 936660d78..b1eae918e 100644 --- a/Cargo.toml +++ b/Cargo.toml @@ -13,20 +13,20 @@ categories = ["database-implementations"] rust-version = "1.91.0" [workspace.dependencies] -lance = { "version" = "=11.0.0-beta.3", default-features = false, "tag" = "v11.0.0-beta.3", "git" = "https://github.com/lance-format/lance.git" } -lance-core = { "version" = "=11.0.0-beta.3", "tag" = "v11.0.0-beta.3", "git" = "https://github.com/lance-format/lance.git" } -lance-datagen = { "version" = "=11.0.0-beta.3", "tag" = "v11.0.0-beta.3", "git" = "https://github.com/lance-format/lance.git" } -lance-file = { "version" = "=11.0.0-beta.3", "tag" = "v11.0.0-beta.3", "git" = "https://github.com/lance-format/lance.git" } -lance-io = { "version" = "=11.0.0-beta.3", default-features = false, "tag" = "v11.0.0-beta.3", "git" = "https://github.com/lance-format/lance.git" } -lance-index = { "version" = "=11.0.0-beta.3", "tag" = "v11.0.0-beta.3", "git" = "https://github.com/lance-format/lance.git" } -lance-linalg = { "version" = "=11.0.0-beta.3", "tag" = "v11.0.0-beta.3", "git" = "https://github.com/lance-format/lance.git" } -lance-namespace = { "version" = "=11.0.0-beta.3", "tag" = "v11.0.0-beta.3", "git" = "https://github.com/lance-format/lance.git" } -lance-namespace-impls = { "version" = "=11.0.0-beta.3", default-features = false, "tag" = "v11.0.0-beta.3", "git" = "https://github.com/lance-format/lance.git" } -lance-table = { "version" = "=11.0.0-beta.3", "tag" = "v11.0.0-beta.3", "git" = "https://github.com/lance-format/lance.git" } -lance-testing = { "version" = "=11.0.0-beta.3", "tag" = "v11.0.0-beta.3", "git" = "https://github.com/lance-format/lance.git" } -lance-datafusion = { "version" = "=11.0.0-beta.3", "tag" = "v11.0.0-beta.3", "git" = "https://github.com/lance-format/lance.git" } -lance-encoding = { "version" = "=11.0.0-beta.3", "tag" = "v11.0.0-beta.3", "git" = "https://github.com/lance-format/lance.git" } -lance-arrow = { "version" = "=11.0.0-beta.3", "tag" = "v11.0.0-beta.3", "git" = "https://github.com/lance-format/lance.git" } +lance = { "version" = "=11.0.0-beta.6", default-features = false, "tag" = "v11.0.0-beta.6", "git" = "https://github.com/lance-format/lance.git" } +lance-core = { "version" = "=11.0.0-beta.6", "tag" = "v11.0.0-beta.6", "git" = "https://github.com/lance-format/lance.git" } +lance-datagen = { "version" = "=11.0.0-beta.6", "tag" = "v11.0.0-beta.6", "git" = "https://github.com/lance-format/lance.git" } +lance-file = { "version" = "=11.0.0-beta.6", "tag" = "v11.0.0-beta.6", "git" = "https://github.com/lance-format/lance.git" } +lance-io = { "version" = "=11.0.0-beta.6", default-features = false, "tag" = "v11.0.0-beta.6", "git" = "https://github.com/lance-format/lance.git" } +lance-index = { "version" = "=11.0.0-beta.6", "tag" = "v11.0.0-beta.6", "git" = "https://github.com/lance-format/lance.git" } +lance-linalg = { "version" = "=11.0.0-beta.6", "tag" = "v11.0.0-beta.6", "git" = "https://github.com/lance-format/lance.git" } +lance-namespace = { "version" = "=11.0.0-beta.6", "tag" = "v11.0.0-beta.6", "git" = "https://github.com/lance-format/lance.git" } +lance-namespace-impls = { "version" = "=11.0.0-beta.6", default-features = false, "tag" = "v11.0.0-beta.6", "git" = "https://github.com/lance-format/lance.git" } +lance-table = { "version" = "=11.0.0-beta.6", "tag" = "v11.0.0-beta.6", "git" = "https://github.com/lance-format/lance.git" } +lance-testing = { "version" = "=11.0.0-beta.6", "tag" = "v11.0.0-beta.6", "git" = "https://github.com/lance-format/lance.git" } +lance-datafusion = { "version" = "=11.0.0-beta.6", "tag" = "v11.0.0-beta.6", "git" = "https://github.com/lance-format/lance.git" } +lance-encoding = { "version" = "=11.0.0-beta.6", "tag" = "v11.0.0-beta.6", "git" = "https://github.com/lance-format/lance.git" } +lance-arrow = { "version" = "=11.0.0-beta.6", "tag" = "v11.0.0-beta.6", "git" = "https://github.com/lance-format/lance.git" } ahash = "0.8" # Note that this one does not include pyarrow arrow = { version = "58.0.0", optional = false } diff --git a/deny.toml b/deny.toml index 034b48c25..d94c9d536 100644 --- a/deny.toml +++ b/deny.toml @@ -101,6 +101,13 @@ ignore = [ # https://rustsec.org/advisories/RUSTSEC-2026-0195 { id = "RUSTSEC-2026-0194", reason = "transitive via inferno/lance/opendal; XML from trusted cloud endpoints, not attacker-controlled" }, { id = "RUSTSEC-2026-0195", reason = "transitive via inferno/lance/opendal; XML from trusted cloud endpoints, not attacker-controlled" }, + # smartstring: unmaintained — the repository was archived by its author on + # 2026-05-03. Not a vulnerability. Reached only transitively through polars + # (polars-core/-io/-ops/-time/-utils); nothing in LanceDB depends on it directly. + # The advisory states no safe upgrade is available: upstream recommends + # compact_str/smol_str, so clearing this requires polars to migrate. + # https://rustsec.org/advisories/RUSTSEC-2026-0249 + { id = "RUSTSEC-2026-0249", reason = "smartstring unmaintained via polars; no fixed upstream release" }, ] # --------------------------------------------------------------------------- diff --git a/java/pom.xml b/java/pom.xml index f85b5c906..3fec2726a 100644 --- a/java/pom.xml +++ b/java/pom.xml @@ -28,7 +28,7 @@ UTF-8 15.0.0 - 11.0.0-beta.3 + 11.0.0-beta.6 false 2.30.0 1.7 diff --git a/rust/lancedb/src/blob.rs b/rust/lancedb/src/blob.rs index e1c18dd84..d59123ec3 100644 --- a/rust/lancedb/src/blob.rs +++ b/rust/lancedb/src/blob.rs @@ -17,7 +17,7 @@ use arrow_array::builder::LargeBinaryBuilder; use arrow_schema::{DataType, Field, Schema}; use lance::dataset::{BlobRangeRequest as LanceBlobRangeRequest, Dataset, WriteParams}; use lance_arrow::FieldExt; -use lance_file::version::LanceFileVersion; +use lance_file::version::{ConcreteFileVersion, LanceFileVersion}; use lance_io::object_store::ObjectStore; use object_store::path::Path; @@ -333,7 +333,10 @@ pub(crate) fn ensure_blob_storage_version(schema: &Schema, params: &mut WritePar .data_storage_version .unwrap_or(LanceFileVersion::Stable) .resolve(); - if resolved < LanceFileVersion::V2_2 { + if matches!( + resolved, + ConcreteFileVersion::V1 | ConcreteFileVersion::V2_0 | ConcreteFileVersion::V2_1 + ) { params.data_storage_version = Some(LanceFileVersion::V2_2); } } @@ -499,7 +502,7 @@ mod tests { ensure_blob_storage_version(&blob_schema(), &mut params); assert_eq!( params.data_storage_version.unwrap().resolve(), - LanceFileVersion::V2_2 + ConcreteFileVersion::V2_2 ); } @@ -512,7 +515,7 @@ mod tests { ensure_blob_storage_version(&blob_schema(), &mut params); assert_eq!( params.data_storage_version.unwrap().resolve(), - LanceFileVersion::V2_2 + ConcreteFileVersion::V2_2 ); } diff --git a/rust/lancedb/src/connection/create_table.rs b/rust/lancedb/src/connection/create_table.rs index b10141beb..39cc82ec0 100644 --- a/rust/lancedb/src/connection/create_table.rs +++ b/rust/lancedb/src/connection/create_table.rs @@ -438,10 +438,9 @@ mod tests { .await .unwrap() .data_storage_format - .lance_file_version() - .unwrap(); + .lance_file_format(); // Compare resolved versions since Stable/Next are aliases that resolve at storage time - assert_eq!(storage_format.resolve(), data_storage_version.resolve()); + assert_eq!(storage_format, data_storage_version.resolve()); } #[tokio::test] diff --git a/rust/lancedb/src/table.rs b/rust/lancedb/src/table.rs index 5120c48b7..d03ac823f 100644 --- a/rust/lancedb/src/table.rs +++ b/rust/lancedb/src/table.rs @@ -5339,7 +5339,7 @@ mod tests { pub async fn test_stats_includes_index_and_overlay_files() { use lance::dataset::WriteDestination; use lance::dataset::transaction::{DataOverlayGroup, Operation}; - use lance_file::version::{ConcreteFileVersion, LanceFileVersion}; + use lance_file::version::stable_file_version; use lance_file::writer::FileWriterOptions; use lance_io::utils::CachedFileSize; use lance_table::format::DataFile; @@ -5405,7 +5405,7 @@ mod tests { let fragment_id = dataset.get_fragments()[0].id() as u64; let foo_field_id = dataset.schema().field("foo").unwrap().id; let overlay_schema = dataset.schema().project_by_ids(&[foo_field_id], true); - let file_version = ConcreteFileVersion::from(LanceFileVersion::Stable); + let file_version = stable_file_version(); let filename = "overlay.lance".to_string(); let store = dataset.object_store(None).await.unwrap(); diff --git a/rust/lancedb/tests/blob_integration.rs b/rust/lancedb/tests/blob_integration.rs index 77d49abd9..b92f961f4 100644 --- a/rust/lancedb/tests/blob_integration.rs +++ b/rust/lancedb/tests/blob_integration.rs @@ -10,7 +10,7 @@ use arrow_array::{ use arrow_schema::{DataType, Field, Fields, Schema}; use futures::TryStreamExt; use lance::Dataset; -use lance_file::version::LanceFileVersion; +use lance_file::version::{ConcreteFileVersion, LanceFileVersion}; use lancedb::{ Connection, Error, Result, Table, blob::{BlobRangeRequest, blob}, @@ -61,7 +61,7 @@ async fn create_inline_blob_table( Ok(table) } -async fn storage_format_version(table: &Table) -> LanceFileVersion { +async fn storage_format_version(table: &Table) -> ConcreteFileVersion { table .as_native() .unwrap() @@ -69,9 +69,14 @@ async fn storage_format_version(table: &Table) -> LanceFileVersion { .await .unwrap() .data_storage_format - .lance_file_version() - .unwrap() - .resolve() + .lance_file_format() +} + +fn supports_blob_v2(version: ConcreteFileVersion) -> bool { + matches!( + version, + ConcreteFileVersion::V2_2 | ConcreteFileVersion::V2_3 + ) } async fn uses_stable_row_ids(table: &Table) -> bool { @@ -112,7 +117,7 @@ async fn declaring_blob_column_bumps_format_and_enables_stable_row_ids() -> Resu .execute() .await?; - assert!(storage_format_version(&table).await >= LanceFileVersion::V2_2); + assert!(supports_blob_v2(storage_format_version(&table).await)); assert!(uses_stable_row_ids(&table).await); Ok(()) } @@ -127,7 +132,7 @@ async fn explicit_stable_row_id_setting_wins_over_blob_default() -> Result<()> { .execute() .await?; - assert!(storage_format_version(&table).await >= LanceFileVersion::V2_2); + assert!(supports_blob_v2(storage_format_version(&table).await)); assert!(!uses_stable_row_ids(&table).await); Ok(()) } @@ -139,7 +144,7 @@ async fn non_blob_table_keeps_default_format_and_row_id_setting() -> Result<()> let schema = Arc::new(Schema::new(vec![Field::new("id", DataType::Int64, false)])); let table = db.create_empty_table("t", schema).execute().await?; - assert!(storage_format_version(&table).await < LanceFileVersion::V2_2); + assert!(!supports_blob_v2(storage_format_version(&table).await)); assert!(!uses_stable_row_ids(&table).await); Ok(()) } @@ -171,7 +176,7 @@ async fn creating_with_blob_data_bumps_format() -> Result<()> { .unwrap(); let table = db.create_table("t", batch).execute().await?; - assert!(storage_format_version(&table).await >= LanceFileVersion::V2_2); + assert!(supports_blob_v2(storage_format_version(&table).await)); assert!(uses_stable_row_ids(&table).await); assert_eq!(table.count_rows(None).await?, 1); Ok(()) @@ -281,7 +286,7 @@ async fn connection_level_stable_row_id_setting_wins_over_blob_default() -> Resu .execute() .await?; - assert!(storage_format_version(&table).await >= LanceFileVersion::V2_2); + assert!(supports_blob_v2(storage_format_version(&table).await)); assert!(!uses_stable_row_ids(&table).await); Ok(()) } @@ -297,7 +302,7 @@ async fn namespace_create_applies_blob_defaults() -> Result<()> { .execute() .await?; - assert!(storage_format_version(&table).await >= LanceFileVersion::V2_2); + assert!(supports_blob_v2(storage_format_version(&table).await)); assert!(uses_stable_row_ids(&table).await); Ok(()) } @@ -474,7 +479,7 @@ async fn fetch_blobs_round_trips_nested_blob_column() -> Result<()> { let batch = RecordBatch::try_new(schema, vec![Arc::new(info_array) as ArrayRef]).unwrap(); let table = db.create_table("t", batch).execute().await?; - assert!(storage_format_version(&table).await >= LanceFileVersion::V2_2); + assert!(supports_blob_v2(storage_format_version(&table).await)); assert!(uses_stable_row_ids(&table).await); let ids = collect_row_ids(&table).await?; @@ -1305,7 +1310,7 @@ async fn optimize_preserves_blob_v2_null_and_empty_distinction() -> Result<()> { .await?; table.add(null_empty_input_batch()).execute().await?; assert!( - storage_format_version(&table).await >= LanceFileVersion::V2_2, + supports_blob_v2(storage_format_version(&table).await), "blob v2 columns require storage >= 2.2" ); From 031c3585a827c7fbe4467ef33d4be0fab63ec5f5 Mon Sep 17 00:00:00 2001 From: LanceDB Robot Date: Thu, 13 Aug 2026 05:37:19 -0700 Subject: [PATCH 13/14] chore: update lance dependency to v11.0.0-beta.7 (#3925) Updates the Rust workspace Lance dependencies and Java lance-core dependency to v11.0.0-beta.7. No compatibility fixes were required; full-workspace Clippy passes with warnings denied. Lance tag: https://github.com/lance-format/lance/releases/tag/v11.0.0-beta.7 --------- Co-authored-by: Yang Cen <159225399+BubbleCal@users.noreply.github.com> --- .github/workflows/pypi-publish.yml | 10 ++++ Cargo.lock | 84 +++++++++++++++--------------- Cargo.toml | 28 +++++----- java/pom.xml | 2 +- 4 files changed, 67 insertions(+), 57 deletions(-) diff --git a/.github/workflows/pypi-publish.yml b/.github/workflows/pypi-publish.yml index 74b7d05e6..4f5a927dc 100644 --- a/.github/workflows/pypi-publish.yml +++ b/.github/workflows/pypi-publish.yml @@ -69,6 +69,16 @@ jobs: uses: actions/setup-python@v6 with: python-version: "3.10" + - name: Add swap for Arm fat LTO + if: matrix.config.platform == 'aarch64' + shell: bash + run: | + swap_file="$RUNNER_TEMP/lancedb-swap" + sudo fallocate --length 16G "$swap_file" + sudo chmod 600 "$swap_file" + sudo mkswap "$swap_file" + sudo swapon "$swap_file" + free -h - uses: ./.github/workflows/build_linux_wheel with: python-minor-version: 10 diff --git a/Cargo.lock b/Cargo.lock index c5545ea8a..04332a496 100644 --- a/Cargo.lock +++ b/Cargo.lock @@ -3455,8 +3455,8 @@ checksum = "42703706b716c37f96a77aea830392ad231f44c9e9a67872fa5548707e11b11c" [[package]] name = "fsst" -version = "11.0.0-beta.6" -source = "git+https://github.com/lance-format/lance.git?tag=v11.0.0-beta.6#5ab688688c411111d94d279bacd037d7c319dc10" +version = "11.0.0-beta.7" +source = "git+https://github.com/lance-format/lance.git?tag=v11.0.0-beta.7#e581c49338bc83baf1ea50c5e235bd702f3fbeea" dependencies = [ "arrow-array", "rand 0.9.5", @@ -4815,8 +4815,8 @@ checksum = "e037a2e1d8d5fdbd49b16a4ea09d5d6401c1f29eca5ff29d03d3824dba16256a" [[package]] name = "lance" -version = "11.0.0-beta.6" -source = "git+https://github.com/lance-format/lance.git?tag=v11.0.0-beta.6#5ab688688c411111d94d279bacd037d7c319dc10" +version = "11.0.0-beta.7" +source = "git+https://github.com/lance-format/lance.git?tag=v11.0.0-beta.7#e581c49338bc83baf1ea50c5e235bd702f3fbeea" dependencies = [ "arc-swap", "arrow", @@ -4890,8 +4890,8 @@ dependencies = [ [[package]] name = "lance-arrow" -version = "11.0.0-beta.6" -source = "git+https://github.com/lance-format/lance.git?tag=v11.0.0-beta.6#5ab688688c411111d94d279bacd037d7c319dc10" +version = "11.0.0-beta.7" +source = "git+https://github.com/lance-format/lance.git?tag=v11.0.0-beta.7#e581c49338bc83baf1ea50c5e235bd702f3fbeea" dependencies = [ "arrow-array", "arrow-buffer", @@ -4913,7 +4913,7 @@ dependencies = [ [[package]] name = "lance-arrow-scalar" version = "58.0.0" -source = "git+https://github.com/lance-format/lance.git?tag=v11.0.0-beta.6#5ab688688c411111d94d279bacd037d7c319dc10" +source = "git+https://github.com/lance-format/lance.git?tag=v11.0.0-beta.7#e581c49338bc83baf1ea50c5e235bd702f3fbeea" dependencies = [ "arrow-array", "arrow-buffer", @@ -4927,7 +4927,7 @@ dependencies = [ [[package]] name = "lance-arrow-stats" version = "58.0.0" -source = "git+https://github.com/lance-format/lance.git?tag=v11.0.0-beta.6#5ab688688c411111d94d279bacd037d7c319dc10" +source = "git+https://github.com/lance-format/lance.git?tag=v11.0.0-beta.7#e581c49338bc83baf1ea50c5e235bd702f3fbeea" dependencies = [ "arrow-array", "arrow-schema", @@ -4936,8 +4936,8 @@ dependencies = [ [[package]] name = "lance-bitpacking" -version = "11.0.0-beta.6" -source = "git+https://github.com/lance-format/lance.git?tag=v11.0.0-beta.6#5ab688688c411111d94d279bacd037d7c319dc10" +version = "11.0.0-beta.7" +source = "git+https://github.com/lance-format/lance.git?tag=v11.0.0-beta.7#e581c49338bc83baf1ea50c5e235bd702f3fbeea" dependencies = [ "arrayref", "crunchy", @@ -4947,8 +4947,8 @@ dependencies = [ [[package]] name = "lance-core" -version = "11.0.0-beta.6" -source = "git+https://github.com/lance-format/lance.git?tag=v11.0.0-beta.6#5ab688688c411111d94d279bacd037d7c319dc10" +version = "11.0.0-beta.7" +source = "git+https://github.com/lance-format/lance.git?tag=v11.0.0-beta.7#e581c49338bc83baf1ea50c5e235bd702f3fbeea" dependencies = [ "arrow-array", "arrow-buffer", @@ -4988,8 +4988,8 @@ dependencies = [ [[package]] name = "lance-datafusion" -version = "11.0.0-beta.6" -source = "git+https://github.com/lance-format/lance.git?tag=v11.0.0-beta.6#5ab688688c411111d94d279bacd037d7c319dc10" +version = "11.0.0-beta.7" +source = "git+https://github.com/lance-format/lance.git?tag=v11.0.0-beta.7#e581c49338bc83baf1ea50c5e235bd702f3fbeea" dependencies = [ "arrow", "arrow-array", @@ -5019,8 +5019,8 @@ dependencies = [ [[package]] name = "lance-datagen" -version = "11.0.0-beta.6" -source = "git+https://github.com/lance-format/lance.git?tag=v11.0.0-beta.6#5ab688688c411111d94d279bacd037d7c319dc10" +version = "11.0.0-beta.7" +source = "git+https://github.com/lance-format/lance.git?tag=v11.0.0-beta.7#e581c49338bc83baf1ea50c5e235bd702f3fbeea" dependencies = [ "arrow", "arrow-array", @@ -5037,8 +5037,8 @@ dependencies = [ [[package]] name = "lance-derive" -version = "11.0.0-beta.6" -source = "git+https://github.com/lance-format/lance.git?tag=v11.0.0-beta.6#5ab688688c411111d94d279bacd037d7c319dc10" +version = "11.0.0-beta.7" +source = "git+https://github.com/lance-format/lance.git?tag=v11.0.0-beta.7#e581c49338bc83baf1ea50c5e235bd702f3fbeea" dependencies = [ "proc-macro2", "quote", @@ -5047,8 +5047,8 @@ dependencies = [ [[package]] name = "lance-encoding" -version = "11.0.0-beta.6" -source = "git+https://github.com/lance-format/lance.git?tag=v11.0.0-beta.6#5ab688688c411111d94d279bacd037d7c319dc10" +version = "11.0.0-beta.7" +source = "git+https://github.com/lance-format/lance.git?tag=v11.0.0-beta.7#e581c49338bc83baf1ea50c5e235bd702f3fbeea" dependencies = [ "arrow-arith", "arrow-array", @@ -5082,8 +5082,8 @@ dependencies = [ [[package]] name = "lance-file" -version = "11.0.0-beta.6" -source = "git+https://github.com/lance-format/lance.git?tag=v11.0.0-beta.6#5ab688688c411111d94d279bacd037d7c319dc10" +version = "11.0.0-beta.7" +source = "git+https://github.com/lance-format/lance.git?tag=v11.0.0-beta.7#e581c49338bc83baf1ea50c5e235bd702f3fbeea" dependencies = [ "arrow-arith", "arrow-array", @@ -5114,8 +5114,8 @@ dependencies = [ [[package]] name = "lance-index" -version = "11.0.0-beta.6" -source = "git+https://github.com/lance-format/lance.git?tag=v11.0.0-beta.6#5ab688688c411111d94d279bacd037d7c319dc10" +version = "11.0.0-beta.7" +source = "git+https://github.com/lance-format/lance.git?tag=v11.0.0-beta.7#e581c49338bc83baf1ea50c5e235bd702f3fbeea" dependencies = [ "arc-swap", "arrow", @@ -5182,8 +5182,8 @@ dependencies = [ [[package]] name = "lance-index-core" -version = "11.0.0-beta.6" -source = "git+https://github.com/lance-format/lance.git?tag=v11.0.0-beta.6#5ab688688c411111d94d279bacd037d7c319dc10" +version = "11.0.0-beta.7" +source = "git+https://github.com/lance-format/lance.git?tag=v11.0.0-beta.7#e581c49338bc83baf1ea50c5e235bd702f3fbeea" dependencies = [ "arrow-array", "arrow-schema", @@ -5205,8 +5205,8 @@ dependencies = [ [[package]] name = "lance-io" -version = "11.0.0-beta.6" -source = "git+https://github.com/lance-format/lance.git?tag=v11.0.0-beta.6#5ab688688c411111d94d279bacd037d7c319dc10" +version = "11.0.0-beta.7" +source = "git+https://github.com/lance-format/lance.git?tag=v11.0.0-beta.7#e581c49338bc83baf1ea50c5e235bd702f3fbeea" dependencies = [ "arrow", "arrow-array", @@ -5242,8 +5242,8 @@ dependencies = [ [[package]] name = "lance-linalg" -version = "11.0.0-beta.6" -source = "git+https://github.com/lance-format/lance.git?tag=v11.0.0-beta.6#5ab688688c411111d94d279bacd037d7c319dc10" +version = "11.0.0-beta.7" +source = "git+https://github.com/lance-format/lance.git?tag=v11.0.0-beta.7#e581c49338bc83baf1ea50c5e235bd702f3fbeea" dependencies = [ "arrow-array", "arrow-buffer", @@ -5259,8 +5259,8 @@ dependencies = [ [[package]] name = "lance-namespace" -version = "11.0.0-beta.6" -source = "git+https://github.com/lance-format/lance.git?tag=v11.0.0-beta.6#5ab688688c411111d94d279bacd037d7c319dc10" +version = "11.0.0-beta.7" +source = "git+https://github.com/lance-format/lance.git?tag=v11.0.0-beta.7#e581c49338bc83baf1ea50c5e235bd702f3fbeea" dependencies = [ "arrow", "async-trait", @@ -5272,8 +5272,8 @@ dependencies = [ [[package]] name = "lance-namespace-impls" -version = "11.0.0-beta.6" -source = "git+https://github.com/lance-format/lance.git?tag=v11.0.0-beta.6#5ab688688c411111d94d279bacd037d7c319dc10" +version = "11.0.0-beta.7" +source = "git+https://github.com/lance-format/lance.git?tag=v11.0.0-beta.7#e581c49338bc83baf1ea50c5e235bd702f3fbeea" dependencies = [ "arrow", "arrow-ipc", @@ -5326,8 +5326,8 @@ dependencies = [ [[package]] name = "lance-select" -version = "11.0.0-beta.6" -source = "git+https://github.com/lance-format/lance.git?tag=v11.0.0-beta.6#5ab688688c411111d94d279bacd037d7c319dc10" +version = "11.0.0-beta.7" +source = "git+https://github.com/lance-format/lance.git?tag=v11.0.0-beta.7#e581c49338bc83baf1ea50c5e235bd702f3fbeea" dependencies = [ "arrow-array", "arrow-buffer", @@ -5342,8 +5342,8 @@ dependencies = [ [[package]] name = "lance-table" -version = "11.0.0-beta.6" -source = "git+https://github.com/lance-format/lance.git?tag=v11.0.0-beta.6#5ab688688c411111d94d279bacd037d7c319dc10" +version = "11.0.0-beta.7" +source = "git+https://github.com/lance-format/lance.git?tag=v11.0.0-beta.7#e581c49338bc83baf1ea50c5e235bd702f3fbeea" dependencies = [ "arrow", "arrow-array", @@ -5383,8 +5383,8 @@ dependencies = [ [[package]] name = "lance-testing" -version = "11.0.0-beta.6" -source = "git+https://github.com/lance-format/lance.git?tag=v11.0.0-beta.6#5ab688688c411111d94d279bacd037d7c319dc10" +version = "11.0.0-beta.7" +source = "git+https://github.com/lance-format/lance.git?tag=v11.0.0-beta.7#e581c49338bc83baf1ea50c5e235bd702f3fbeea" dependencies = [ "arrow-array", "arrow-schema", @@ -5397,8 +5397,8 @@ dependencies = [ [[package]] name = "lance-tokenizer" -version = "11.0.0-beta.6" -source = "git+https://github.com/lance-format/lance.git?tag=v11.0.0-beta.6#5ab688688c411111d94d279bacd037d7c319dc10" +version = "11.0.0-beta.7" +source = "git+https://github.com/lance-format/lance.git?tag=v11.0.0-beta.7#e581c49338bc83baf1ea50c5e235bd702f3fbeea" dependencies = [ "frostem", "icu_segmenter", diff --git a/Cargo.toml b/Cargo.toml index b1eae918e..33bf7e09b 100644 --- a/Cargo.toml +++ b/Cargo.toml @@ -13,20 +13,20 @@ categories = ["database-implementations"] rust-version = "1.91.0" [workspace.dependencies] -lance = { "version" = "=11.0.0-beta.6", default-features = false, "tag" = "v11.0.0-beta.6", "git" = "https://github.com/lance-format/lance.git" } -lance-core = { "version" = "=11.0.0-beta.6", "tag" = "v11.0.0-beta.6", "git" = "https://github.com/lance-format/lance.git" } -lance-datagen = { "version" = "=11.0.0-beta.6", "tag" = "v11.0.0-beta.6", "git" = "https://github.com/lance-format/lance.git" } -lance-file = { "version" = "=11.0.0-beta.6", "tag" = "v11.0.0-beta.6", "git" = "https://github.com/lance-format/lance.git" } -lance-io = { "version" = "=11.0.0-beta.6", default-features = false, "tag" = "v11.0.0-beta.6", "git" = "https://github.com/lance-format/lance.git" } -lance-index = { "version" = "=11.0.0-beta.6", "tag" = "v11.0.0-beta.6", "git" = "https://github.com/lance-format/lance.git" } -lance-linalg = { "version" = "=11.0.0-beta.6", "tag" = "v11.0.0-beta.6", "git" = "https://github.com/lance-format/lance.git" } -lance-namespace = { "version" = "=11.0.0-beta.6", "tag" = "v11.0.0-beta.6", "git" = "https://github.com/lance-format/lance.git" } -lance-namespace-impls = { "version" = "=11.0.0-beta.6", default-features = false, "tag" = "v11.0.0-beta.6", "git" = "https://github.com/lance-format/lance.git" } -lance-table = { "version" = "=11.0.0-beta.6", "tag" = "v11.0.0-beta.6", "git" = "https://github.com/lance-format/lance.git" } -lance-testing = { "version" = "=11.0.0-beta.6", "tag" = "v11.0.0-beta.6", "git" = "https://github.com/lance-format/lance.git" } -lance-datafusion = { "version" = "=11.0.0-beta.6", "tag" = "v11.0.0-beta.6", "git" = "https://github.com/lance-format/lance.git" } -lance-encoding = { "version" = "=11.0.0-beta.6", "tag" = "v11.0.0-beta.6", "git" = "https://github.com/lance-format/lance.git" } -lance-arrow = { "version" = "=11.0.0-beta.6", "tag" = "v11.0.0-beta.6", "git" = "https://github.com/lance-format/lance.git" } +lance = { "version" = "=11.0.0-beta.7", default-features = false, "tag" = "v11.0.0-beta.7", "git" = "https://github.com/lance-format/lance.git" } +lance-core = { "version" = "=11.0.0-beta.7", "tag" = "v11.0.0-beta.7", "git" = "https://github.com/lance-format/lance.git" } +lance-datagen = { "version" = "=11.0.0-beta.7", "tag" = "v11.0.0-beta.7", "git" = "https://github.com/lance-format/lance.git" } +lance-file = { "version" = "=11.0.0-beta.7", "tag" = "v11.0.0-beta.7", "git" = "https://github.com/lance-format/lance.git" } +lance-io = { "version" = "=11.0.0-beta.7", default-features = false, "tag" = "v11.0.0-beta.7", "git" = "https://github.com/lance-format/lance.git" } +lance-index = { "version" = "=11.0.0-beta.7", "tag" = "v11.0.0-beta.7", "git" = "https://github.com/lance-format/lance.git" } +lance-linalg = { "version" = "=11.0.0-beta.7", "tag" = "v11.0.0-beta.7", "git" = "https://github.com/lance-format/lance.git" } +lance-namespace = { "version" = "=11.0.0-beta.7", "tag" = "v11.0.0-beta.7", "git" = "https://github.com/lance-format/lance.git" } +lance-namespace-impls = { "version" = "=11.0.0-beta.7", default-features = false, "tag" = "v11.0.0-beta.7", "git" = "https://github.com/lance-format/lance.git" } +lance-table = { "version" = "=11.0.0-beta.7", "tag" = "v11.0.0-beta.7", "git" = "https://github.com/lance-format/lance.git" } +lance-testing = { "version" = "=11.0.0-beta.7", "tag" = "v11.0.0-beta.7", "git" = "https://github.com/lance-format/lance.git" } +lance-datafusion = { "version" = "=11.0.0-beta.7", "tag" = "v11.0.0-beta.7", "git" = "https://github.com/lance-format/lance.git" } +lance-encoding = { "version" = "=11.0.0-beta.7", "tag" = "v11.0.0-beta.7", "git" = "https://github.com/lance-format/lance.git" } +lance-arrow = { "version" = "=11.0.0-beta.7", "tag" = "v11.0.0-beta.7", "git" = "https://github.com/lance-format/lance.git" } ahash = "0.8" # Note that this one does not include pyarrow arrow = { version = "58.0.0", optional = false } diff --git a/java/pom.xml b/java/pom.xml index 3fec2726a..4fdf77e81 100644 --- a/java/pom.xml +++ b/java/pom.xml @@ -28,7 +28,7 @@ UTF-8 15.0.0 - 11.0.0-beta.6 + 11.0.0-beta.7 false 2.30.0 1.7 From 1d75638deaf2d79e8ab17e036fb63e423b1909ed Mon Sep 17 00:00:00 2001 From: Yang Cen Date: Thu, 13 Aug 2026 21:22:42 +0800 Subject: [PATCH 14/14] fix: make table existence manifest-authoritative (#3919) ## What is the bug? #3731 tries to distinguish a missing table from a corrupt table after Lance returns `DatasetNotFound`. It does that by listing the database parent and treating a physical `.lance` entry as evidence that the table exists. That premise is not sound for a listing database. Table creation writes data before atomically committing the first manifest, so the same physical prefix can represent a live concurrent create, abandoned uncommitted data, or an old empty directory. It is not evidence of a committed table. The parent listing also makes every missing-table open, including the create-on-miss path, perform work proportional to the number of sibling tables. Cloud `list_with_delimiter` exhausts all pages before returning. ## How does this PR fix the problem? This PR makes the committed Lance manifest the sole table-existence authority for listing-database opens: - `DatasetNotFound` maps directly to `TableNotFound`; no parent or target storage probe runs. - Other Lance load errors continue to propagate unchanged. - A physical directory, object prefix, or uncommitted data file alone does not block `Create`. - Concurrent `Create` requests are arbitrated by the conditional version-1 manifest commit: one succeeds and the loser receives `TableAlreadyExists`. - `table_names` is documented as physical discovery, not an atomic table-existence check. Its snapshot can contain an entry that is still being created, has only uncommitted storage, or is concurrently dropped. This removes the need for a new Lance object-store capability. LanceDB remains on the official Lance `v11.0.0-beta.6` dependency from `main`; the merge commit for lance-format/lance#7722 is an ancestor of that tag, so the ambiguous-GCS-500 corruption-prevention fix is retained. ## Performance evidence Lower is better. The benchmark uses real `.lance` directories with marker objects on the local filesystem; fixture creation and teardown are outside the timed region. Baseline is `origin/main` at `6fb976cf`, candidate is `e1240751`. Both were built from the same lockfile on the same macOS arm64 machine with the repository's `release` profile (fat LTO), then executed in alternating baseline/candidate order for three pairs. Each run used 10 warmups and 100 distinct missing-table opens per scale. The table reports the median of the three run-level percentiles. | Scenario / metric | Baseline | This PR | Benefit | | --- | ---: | ---: | ---: | | 1,000 real sibling directories, p50 | 11.905 ms | 21.042 us | 566x speedup | | 10,000 real sibling directories, p50 | 143.630 ms | 18.375 us | 7,817x speedup | | 100,000 real sibling directories, p50 | 1.991 s | 19.917 us | 99,984x speedup | | 100,000 real sibling directories, p95 | 2.346 s | 25.792 us | 90,965x speedup | These results validate removal of the sibling-cardinality dependency in this local-filesystem workload; they are not an extrapolation to production GCS latency. A structural object-store regression test separately asserts that opening one missing table performs zero parent-scoped `list`, `list_with_offset`, or `list_with_delimiter` calls. Run with: ```bash BENCH_SIBLINGS=1000,10000,100000 BENCH_WARMUPS=10 BENCH_TRIALS=100 \ cargo run --locked --release --quiet -p lancedb --example bench_open_missing_table ``` ## Correctness and compatibility boundaries - An empty `.lance` directory or orphan data without a committed manifest now opens as `TableNotFound` and may be replaced by a successful `Create`. - Two synchronized creators sharing one object store deterministically produce one success and one conditional-manifest conflict mapped to `TableAlreadyExists`. - A readable manifest remains authoritative; non-`DatasetNotFound` corruption, external-manifest, authorization, and object-store errors are not folded into `TableNotFound`. - `TableCorrupted` remains in the public error enum for compatibility, but this listing-database fallback no longer synthesizes it from an ambiguous physical footprint. - Reliably distinguishing `Missing`, `Creating`, and `Corrupt` would require explicit authoritative lifecycle/catalog metadata (for example a leased creation record). It cannot be inferred from a directory or prefix, and is outside this incident fix. ## Validation - `cargo fmt --all -- --check` - `cargo check --quiet --locked -p lancedb --features remote --tests --examples` - `cargo clippy --quiet --locked -p lancedb --features remote --tests --examples -- -D warnings` - `cargo test --quiet --locked -p lancedb --features remote --tests` - library: 843 passed, 1 ignored - integration groups: 39 passed, 6 passed, 5 passed - focused coverage for empty directories, orphan data, physical listing snapshots, zero parent listings, and concurrent manifest arbitration --- rust/lancedb/Cargo.toml | 3 + .../examples/bench_open_missing_table.rs | 150 +++++++++ rust/lancedb/src/connection.rs | 12 +- rust/lancedb/src/database/listing.rs | 117 ++++++- rust/lancedb/src/table.rs | 299 ++++++++++++------ 5 files changed, 473 insertions(+), 108 deletions(-) create mode 100644 rust/lancedb/examples/bench_open_missing_table.rs diff --git a/rust/lancedb/Cargo.toml b/rust/lancedb/Cargo.toml index e33b86b12..23dc86e15 100644 --- a/rust/lancedb/Cargo.toml +++ b/rust/lancedb/Cargo.toml @@ -188,6 +188,9 @@ required-features = ["bedrock"] [[example]] name = "bench_streaming_dataloader" +[[example]] +name = "bench_open_missing_table" + [[example]] name = "simple" diff --git a/rust/lancedb/examples/bench_open_missing_table.rs b/rust/lancedb/examples/bench_open_missing_table.rs new file mode 100644 index 000000000..8e6b16e11 --- /dev/null +++ b/rust/lancedb/examples/bench_open_missing_table.rs @@ -0,0 +1,150 @@ +// SPDX-License-Identifier: Apache-2.0 +// SPDX-FileCopyrightText: Copyright The LanceDB Authors + +// Release benchmark for opening a missing table as sibling-table cardinality grows. +// +// The fixture uses real `.lance` directories and marker files. Fixture creation is +// outside the timed section. Defaults intentionally cover 1k, 10k, and 100k siblings +// with 10 warmups and 100 distinct missing-table opens per scale: +// +// ```text +// cargo run --release -p lancedb --example bench_open_missing_table +// ``` +// +// `BENCH_SIBLINGS`, `BENCH_WARMUPS`, and `BENCH_TRIALS` override those defaults. +// Reduced settings are useful only as a smoke test. Performance comparisons require +// the same machine, filesystem, fixture sizes, settings, lockfile, and alternating +// baseline/candidate execution order. + +use std::time::{Duration, Instant}; + +use anyhow::{Context, Result, bail}; +use lancedb::connection::Connection; +use lancedb::{Error, connect}; +use object_store::ObjectStoreExt as _; +use object_store::path::Path; + +const MAX_SIBLINGS: usize = 1_000_000; +const MAX_WARMUPS: usize = 10_000; +const MAX_TRIALS: usize = 100_000; + +fn env_usize(key: &str, default: usize, max: usize) -> Result { + let value = match std::env::var(key) { + Ok(value) => value + .parse() + .with_context(|| format!("invalid {key} value: {value}"))?, + Err(std::env::VarError::NotPresent) => default, + Err(error) => return Err(error).with_context(|| format!("reading {key}")), + }; + if value == 0 || value > max { + bail!("{key} must be between 1 and {max}"); + } + Ok(value) +} + +fn sibling_counts() -> Result> { + let raw = std::env::var("BENCH_SIBLINGS").unwrap_or_else(|_| "1000,10000,100000".into()); + let mut counts = raw + .split(',') + .map(|value| { + value + .trim() + .parse::() + .with_context(|| format!("invalid BENCH_SIBLINGS value: {value}")) + }) + .collect::>>()?; + counts.sort_unstable(); + counts.dedup(); + if counts.is_empty() || counts[0] == 0 || counts[counts.len() - 1] > MAX_SIBLINGS { + bail!("BENCH_SIBLINGS values must be between 1 and {MAX_SIBLINGS}"); + } + Ok(counts) +} + +async fn add_siblings( + store: &object_store::local::LocalFileSystem, + start: usize, + end: usize, +) -> Result<()> { + for index in start..end { + let marker = Path::from(format!("sibling_{index:06}.lance/_marker")); + store + .put(&marker, bytes::Bytes::new().into()) + .await + .with_context(|| format!("creating benchmark marker {marker}"))?; + } + Ok(()) +} + +async fn time_missing_open(db: &Connection, name: &str) -> Result { + let started = Instant::now(); + let result = db.open_table(name).execute().await; + let elapsed = started.elapsed(); + match result { + Err(Error::TableNotFound { .. }) => Ok(elapsed), + Err(error) => bail!("expected TableNotFound for {name}, got {error:?}"), + Ok(_) => bail!("benchmark missing-table name unexpectedly exists: {name}"), + } +} + +fn percentile(sorted: &[Duration], percentile: usize) -> Duration { + let rank = (sorted.len() * percentile).div_ceil(100).saturating_sub(1); + sorted[rank] +} + +#[tokio::main] +async fn main() -> Result<()> { + let counts = sibling_counts()?; + let warmups = env_usize("BENCH_WARMUPS", 10, MAX_WARMUPS)?; + let trials = env_usize("BENCH_TRIALS", 100, MAX_TRIALS)?; + + let fixture = tempfile::tempdir().context("creating benchmark fixture")?; + let database_path = fixture.path(); + let fixture_store = object_store::local::LocalFileSystem::new_with_prefix(database_path) + .context("creating benchmark object store")?; + let db = connect(database_path.to_str().context("non-UTF-8 fixture path")?) + .execute() + .await?; + + println!( + "config: siblings={counts:?} warmups={warmups} trials={trials} profile={} os={} arch={}", + if cfg!(debug_assertions) { + "debug" + } else { + "release" + }, + std::env::consts::OS, + std::env::consts::ARCH, + ); + println!("lower is better; fixture setup and teardown are excluded"); + println!("| siblings | samples | p50 | p95 | max |"); + println!("| ---: | ---: | ---: | ---: | ---: |"); + + let mut created = 0; + for sibling_count in counts { + add_siblings(&fixture_store, created, sibling_count).await?; + created = sibling_count; + + for index in 0..warmups { + let name = format!("__missing_warmup_{sibling_count}_{index}"); + let _ = time_missing_open(&db, &name).await?; + } + + let mut samples = Vec::with_capacity(trials); + for index in 0..trials { + let name = format!("__missing_trial_{sibling_count}_{index}"); + samples.push(time_missing_open(&db, &name).await?); + } + samples.sort_unstable(); + + println!( + "| {sibling_count} | {} | {:?} | {:?} | {:?} |", + samples.len(), + percentile(&samples, 50), + percentile(&samples, 95), + samples[samples.len() - 1], + ); + } + + Ok(()) +} diff --git a/rust/lancedb/src/connection.rs b/rust/lancedb/src/connection.rs index dd53a2d2e..1f2708d4e 100644 --- a/rust/lancedb/src/connection.rs +++ b/rust/lancedb/src/connection.rs @@ -409,6 +409,11 @@ impl Connection { /// /// The names will be returned in lexicographical order (ascending) /// + /// Listing databases discover physical `*.lance` entries without opening every + /// dataset. The result is a point-in-time discovery snapshot: an entry may still be + /// under creation, may contain only uncommitted storage, or may be concurrently + /// dropped before it is opened. + /// /// The parameters `page_token` and `limit` can be used to paginate the results pub fn table_names(&self) -> TableNamesBuilder { TableNamesBuilder::new(self.internal.clone()) @@ -456,10 +461,9 @@ impl Connection { /// /// # Returns /// Created [`TableRef`], or [`Error::TableNotFound`] if the table does not exist. - /// If the table's storage is present but holds no readable dataset (for example a - /// `.lance` directory left behind by an interrupted drop and re-create, which - /// [`Self::table_names`] still lists) this returns [`Error::TableCorrupted`] - /// instead. + /// On listing databases, a committed Lance manifest is authoritative for table + /// existence. Uncommitted files or a physical `.lance` directory alone do not + /// make a table openable. pub fn open_table(&self, name: impl Into) -> OpenTableBuilder { OpenTableBuilder::new( self.internal.clone(), diff --git a/rust/lancedb/src/database/listing.rs b/rust/lancedb/src/database/listing.rs index 0ab3614e7..f284320c6 100644 --- a/rust/lancedb/src/database/listing.rs +++ b/rust/lancedb/src/database/listing.rs @@ -1291,16 +1291,21 @@ impl Database for ListingDatabase { mod tests { use super::*; use crate::Table; + use crate::arrow::{SendableRecordBatchStream, SimpleRecordBatchStream}; use crate::connection::ConnectRequest; use crate::data::scannable::Scannable; use crate::database::{CreateTableMode, CreateTableRequest}; use crate::query::QueryRequest; use crate::table::{AnyQuery, WriteOptions}; use arrow_array::{Int32Array, RecordBatch, StringArray}; - use arrow_schema::{DataType, Field, Schema}; - use futures::TryStreamExt; + use arrow_schema::{DataType, Field, Schema, SchemaRef}; + use futures::{TryStreamExt, stream::once}; use std::path::PathBuf; + use std::sync::Arc; + use std::time::Duration; use tempfile::tempdir; + use tokio::sync::Barrier; + use tokio::time::timeout; async fn setup_database() -> (tempfile::TempDir, ListingDatabase) { let tempdir = tempdir().unwrap(); @@ -1324,6 +1329,114 @@ mod tests { (tempdir, db) } + struct BarrierScannable { + batch: RecordBatch, + barrier: Arc, + } + + impl Scannable for BarrierScannable { + fn schema(&self) -> SchemaRef { + self.batch.schema() + } + + fn scan_as_stream(&mut self) -> SendableRecordBatchStream { + let batch = self.batch.clone(); + let schema = batch.schema(); + let barrier = self.barrier.clone(); + Box::pin(SimpleRecordBatchStream { + schema, + stream: once(async move { + barrier.wait().await; + Ok(batch) + }), + }) + } + } + + fn create_request(name: &str, data: Box) -> CreateTableRequest { + CreateTableRequest { + name: name.to_string(), + namespace_path: vec![], + data, + mode: CreateTableMode::Create, + write_options: Default::default(), + location: None, + namespace_client: None, + } + } + + #[tokio::test] + async fn test_create_ignores_uncommitted_storage_without_manifest() { + let (tmp_dir, db) = setup_database().await; + let data_dir = tmp_dir.path().join("test.lance/data"); + std::fs::create_dir_all(&data_dir).unwrap(); + std::fs::write(data_dir.join("orphan.lance"), b"uncommitted").unwrap(); + + let schema = Arc::new(Schema::new(vec![Field::new("id", DataType::Int32, false)])); + let batch = + RecordBatch::try_new(schema, vec![Arc::new(Int32Array::from(vec![1]))]).unwrap(); + + let table = db + .create_table(create_request("test", Box::new(batch))) + .await + .unwrap(); + assert_eq!(table.count_rows(None).await.unwrap(), 1); + } + + #[tokio::test] + async fn test_concurrent_create_is_arbitrated_by_manifest_commit() { + let uri = format!("memory:///concurrent-create-{}", uuid::Uuid::new_v4()); + let db = crate::connect(&uri).execute().await.unwrap(); + let store: Arc = + Arc::new(object_store::memory::InMemory::new()); + let table_url = url::Url::parse("memory:///database/test.lance").unwrap(); + let schema = Arc::new(Schema::new(vec![Field::new("id", DataType::Int32, false)])); + let batch = + RecordBatch::try_new(schema, vec![Arc::new(Int32Array::from(vec![1]))]).unwrap(); + let barrier = Arc::new(Barrier::new(2)); + + #[allow(deprecated)] + let request = |batch, barrier| { + let mut request = create_request("test", Box::new(BarrierScannable { batch, barrier })); + request.write_options = WriteOptions { + lance_write_params: Some(lance::dataset::WriteParams { + store_params: Some(ObjectStoreParams { + object_store: Some((store.clone(), table_url.clone())), + ..Default::default() + }), + commit_handler: Some(Arc::new( + lance_table::io::commit::ConditionalPutCommitHandler, + )), + ..Default::default() + }), + }; + request + }; + + let left = db + .database() + .create_table(request(batch.clone(), barrier.clone())); + let right = db.database().create_table(request(batch, barrier)); + let (left, right) = timeout(Duration::from_secs(30), async { tokio::join!(left, right) }) + .await + .expect("concurrent creates deadlocked"); + + let results = [left, right]; + assert_eq!( + results.iter().filter(|result| result.is_ok()).count(), + 1, + "expected one successful create, got {results:?}" + ); + assert_eq!( + results + .iter() + .filter(|result| matches!(result, Err(Error::TableAlreadyExists { .. }))) + .count(), + 1, + "expected one manifest conflict, got {results:?}" + ); + } + #[tokio::test] async fn test_listing_database_root_ops_do_not_create_manifest() { let tempdir = tempdir().unwrap(); diff --git a/rust/lancedb/src/table.rs b/rust/lancedb/src/table.rs index d03ac823f..32b6bcebc 100644 --- a/rust/lancedb/src/table.rs +++ b/rust/lancedb/src/table.rs @@ -50,7 +50,6 @@ use crate::DistanceType; use crate::blob::BlobRangeRequest; use crate::data::scannable::{PeekedScannable, Scannable, estimate_write_partitions}; use crate::database::Database; -use crate::database::listing::LANCE_FILE_EXTENSION; use crate::database::read_freshness::TableFreshness; use crate::embeddings::{EmbeddingDefinition, EmbeddingRegistry, MemoryRegistry}; use crate::error::{Error, Result}; @@ -152,55 +151,6 @@ pub(crate) fn map_namespace_lance_error(err: lance::Error, table_name: &str) -> } } -/// Map a `lance::Error::DatasetNotFound` for the table at `uri` into a `lancedb::Error`. -/// -/// Lance reports "there is nothing at this location" and "there is a table directory -/// here but nothing loadable inside it" with the same error. Only the first is a -/// `TableNotFound`: a `.lance` directory left behind by an interrupted drop and -/// re-create is still reported by `Connection::table_names`, so callers need to be able -/// to tell "never existed" from "exists but is broken". -/// -/// See . -async fn map_dataset_not_found( - uri: &str, - name: &str, - params: ReadParams, - err: lance::Error, -) -> Error { - let name = name.to_string(); - let source = Box::new(err); - if table_dir_exists(uri, params).await.unwrap_or(false) { - Error::TableCorrupted { name, source } - } else { - Error::TableNotFound { name, source } - } -} - -/// Whether a table directory is present at `uri`, even though no dataset could be -/// loaded from it. -/// -/// This looks for a `.lance` entry in the parent directory, which is exactly what -/// `ListingDatabase::table_names` lists, so the two APIs agree on whether a table is -/// present. Probing `uri` itself would not work: object stores have no empty -/// directories to probe, and on a local filesystem the interesting case is precisely an -/// empty directory. -async fn table_dir_exists(uri: &str, params: ReadParams) -> Result { - let (object_store, path, _) = DatasetBuilder::from_uri(uri) - .with_read_params(params) - .build_object_store() - .await?; - // Only `*.lance` entries are ever reported as tables, so nothing else can produce - // the list-then-open mismatch this guards against. - if path.extension() != Some(LANCE_FILE_EXTENSION) { - return Ok(false); - } - let (Some(parent), Some(dir_name)) = (path.parent(), path.filename()) else { - return Ok(false); - }; - let entries = object_store.read_dir(parent).await?; - Ok(entries.iter().any(|entry| entry.as_str() == dir_name)) -} - /// Defines the type of column #[derive(Debug, Clone, Serialize, Deserialize)] pub enum ColumnKind { @@ -2420,8 +2370,6 @@ impl NativeTable { None => false, }; - // Kept so that a `DatasetNotFound` can be re-checked against storage below. - let recovery_params = params.clone(); let mut builder = DatasetBuilder::from_uri(uri).with_read_params(params); // Set up commit handler when managed_versioning is enabled @@ -2440,7 +2388,12 @@ impl NativeTable { let dataset = match builder.load().await { Ok(dataset) => dataset, Err(e @ lance::Error::DatasetNotFound { .. }) => { - return Err(map_dataset_not_found(uri, name, recovery_params, e).await); + // The manifest load is the existence check. A physical prefix may be + // from a concurrent or abandoned create, so it cannot refine this error. + return Err(Error::TableNotFound { + name: name.to_string(), + source: Box::new(e), + }); } Err(e) => return Err(e.into()), }; @@ -3708,7 +3661,7 @@ pub struct FragmentSummaryStats { #[allow(deprecated)] mod tests { use std::sync::Arc; - use std::sync::atomic::{AtomicBool, Ordering}; + use std::sync::atomic::{AtomicBool, AtomicUsize, Ordering}; use std::time::Duration; use arrow_array::{ @@ -3790,73 +3743,50 @@ mod tests { ); } - /// Write a table and then break it, leaving the `.lance` directory in place. - /// - /// `remove_all` reproduces an interrupted drop + re-create (the directory is left - /// empty); otherwise only the manifests are removed, leaving the data files behind. - async fn write_then_corrupt_table(dir: &std::path::Path, remove_all: bool) -> String { - let dataset_path = dir.join("test.lance"); - let uri = dataset_path.to_str().unwrap().to_string(); - - let batch = make_test_batches(); - let reader = RecordBatchIterator::new(vec![Ok(batch.clone())], batch.schema()); - Dataset::write(reader, &uri, None).await.unwrap(); - - if remove_all { - for entry in std::fs::read_dir(&dataset_path).unwrap() { - let entry = entry.unwrap(); - if entry.file_type().unwrap().is_dir() { - std::fs::remove_dir_all(entry.path()).unwrap(); - } else { - std::fs::remove_file(entry.path()).unwrap(); - } - } - assert_eq!(std::fs::read_dir(&dataset_path).unwrap().count(), 0); - } else { - let versions = dataset_path.join("_versions"); - assert!(versions.is_dir(), "expected manifests under {versions:?}"); - std::fs::remove_dir_all(&versions).unwrap(); - assert!(std::fs::read_dir(&dataset_path).unwrap().count() > 0); - } - - uri - } - #[tokio::test] - async fn test_open_corrupt_empty_dir() { + async fn test_open_not_found_when_empty_directory_exists() { let tmp_dir = tempdir().unwrap(); - let uri = write_then_corrupt_table(tmp_dir.path(), true).await; + let dataset_path = tmp_dir.path().join("test.lance"); + std::fs::create_dir(&dataset_path).unwrap(); - let err = NativeTable::open(&uri).await.unwrap_err(); + let err = NativeTable::open(dataset_path.to_str().unwrap()) + .await + .unwrap_err(); assert!( - matches!(&err, Error::TableCorrupted { name, .. } if name == "test"), + matches!(&err, Error::TableNotFound { name, .. } if name == "test"), "got {err:?}" ); } #[tokio::test] - async fn test_open_corrupt_missing_manifest() { + async fn test_open_not_found_when_only_uncommitted_storage_exists() { let tmp_dir = tempdir().unwrap(); - let uri = write_then_corrupt_table(tmp_dir.path(), false).await; + let dataset_path = tmp_dir.path().join("test.lance"); + let data_dir = dataset_path.join("data"); + std::fs::create_dir_all(&data_dir).unwrap(); + std::fs::write(data_dir.join("orphan.lance"), b"uncommitted").unwrap(); - let err = NativeTable::open(&uri).await.unwrap_err(); + let err = NativeTable::open(dataset_path.to_str().unwrap()) + .await + .unwrap_err(); assert!( - matches!(&err, Error::TableCorrupted { name, .. } if name == "test"), + matches!(&err, Error::TableNotFound { name, .. } if name == "test"), "got {err:?}" ); } - /// A table listed by `table_names()` must not be reported as missing by - /// `open_table()`. See . + /// Listing databases discover physical `*.lance` entries. That snapshot is not an + /// authoritative table-existence check: only a committed manifest makes a table + /// openable, and the entry could also be concurrently created or dropped. #[tokio::test] - async fn test_open_table_corrupt_is_still_listed() { + async fn test_table_names_may_include_uncommitted_storage() { let tmp_dir = tempdir().unwrap(); let db = connect(tmp_dir.path().to_str().unwrap()) .execute() .await .unwrap(); - write_then_corrupt_table(tmp_dir.path(), true).await; + std::fs::create_dir(tmp_dir.path().join("test.lance")).unwrap(); assert_eq!( db.table_names().execute().await.unwrap(), @@ -3864,12 +3794,177 @@ mod tests { ); let err = db.open_table("test").execute().await.unwrap_err(); assert!( - matches!(&err, Error::TableCorrupted { name, .. } if name == "test"), + matches!(&err, Error::TableNotFound { name, .. } if name == "test"), + "physical storage without a committed manifest is not a table: {err:?}" + ); + } + + #[derive(Debug)] + struct ParentListGuardStore { + inner: Arc, + parent: object_store::path::Path, + parent_list_calls: Arc, + } + + impl std::fmt::Display for ParentListGuardStore { + fn fmt(&self, f: &mut std::fmt::Formatter<'_>) -> std::fmt::Result { + f.write_str("ParentListGuardStore") + } + } + + #[async_trait::async_trait] + #[deny(clippy::missing_trait_methods)] + impl object_store::ObjectStore for ParentListGuardStore { + async fn put_opts( + &self, + location: &object_store::path::Path, + payload: object_store::PutPayload, + opts: object_store::PutOptions, + ) -> object_store::Result { + self.inner.put_opts(location, payload, opts).await + } + + async fn put_multipart_opts( + &self, + location: &object_store::path::Path, + opts: object_store::PutMultipartOptions, + ) -> object_store::Result> { + self.inner.put_multipart_opts(location, opts).await + } + + async fn get_opts( + &self, + location: &object_store::path::Path, + options: object_store::GetOptions, + ) -> object_store::Result { + self.inner.get_opts(location, options).await + } + + async fn get_ranges( + &self, + location: &object_store::path::Path, + ranges: &[std::ops::Range], + ) -> object_store::Result> { + self.inner.get_ranges(location, ranges).await + } + + fn delete_stream( + &self, + locations: futures::stream::BoxStream< + 'static, + object_store::Result, + >, + ) -> futures::stream::BoxStream<'static, object_store::Result> + { + self.inner.delete_stream(locations) + } + + fn list( + &self, + prefix: Option<&object_store::path::Path>, + ) -> futures::stream::BoxStream<'static, object_store::Result> + { + if prefix == Some(&self.parent) { + self.parent_list_calls.fetch_add(1, Ordering::Relaxed); + } + self.inner.list(prefix) + } + + fn list_with_offset( + &self, + prefix: Option<&object_store::path::Path>, + offset: &object_store::path::Path, + ) -> futures::stream::BoxStream<'static, object_store::Result> + { + if prefix == Some(&self.parent) { + self.parent_list_calls.fetch_add(1, Ordering::Relaxed); + } + self.inner.list_with_offset(prefix, offset) + } + + async fn list_with_delimiter( + &self, + prefix: Option<&object_store::path::Path>, + ) -> object_store::Result { + if prefix == Some(&self.parent) { + self.parent_list_calls.fetch_add(1, Ordering::Relaxed); + } + self.inner.list_with_delimiter(prefix).await + } + + async fn copy_opts( + &self, + from: &object_store::path::Path, + to: &object_store::path::Path, + options: object_store::CopyOptions, + ) -> object_store::Result<()> { + self.inner.copy_opts(from, to, options).await + } + + async fn rename_opts( + &self, + from: &object_store::path::Path, + to: &object_store::path::Path, + options: object_store::RenameOptions, + ) -> object_store::Result<()> { + self.inner.rename_opts(from, to, options).await + } + } + + #[derive(Debug)] + struct ParentListGuardWrapper { + parent_list_calls: Arc, + } + + impl WrappingObjectStore for ParentListGuardWrapper { + fn wrap( + &self, + _store_prefix: &str, + inner: Arc, + ) -> Arc { + Arc::new(ParentListGuardStore { + inner, + parent: object_store::path::Path::from("database"), + parent_list_calls: self.parent_list_calls.clone(), + }) + } + } + + #[tokio::test] + async fn test_open_missing_never_lists_database_parent() { + let parent_list_calls = Arc::new(AtomicUsize::new(0)); + let params = ReadParams { + store_options: Some(ObjectStoreParams { + object_store_wrapper: Some(Arc::new(ParentListGuardWrapper { + parent_list_calls: parent_list_calls.clone(), + })), + ..Default::default() + }), + ..Default::default() + }; + + let err = NativeTable::open_with_params( + "memory:///database/missing.lance", + "missing", + Vec::new(), + None, + Some(params), + None, + None, + HashSet::new(), + None, + ) + .await + .unwrap_err(); + + assert!( + matches!(&err, Error::TableNotFound { name, .. } if name == "missing"), "got {err:?}" ); - assert!( - err.to_string().contains("exists but could not be loaded"), - "got {err}" + assert_eq!( + parent_list_calls.load(Ordering::Relaxed), + 0, + "opening one missing table must not enumerate sibling tables" ); }