From 78a6976bbf4e58ecede82eb45e08b7b10d5efa97 Mon Sep 17 00:00:00 2001 From: Yang Cen Date: Fri, 25 Sep 2026 00:53:41 +0800 Subject: [PATCH] feat(sql): use Lance beta 14 native pair tiles --- Cargo.lock | 88 +++++++++---------- Cargo.toml | 28 +++--- .../table/datafusion/udtf/duplicate_pairs.rs | 33 +++++-- rust/lancedb/tests/duplicate_pairs.rs | 2 +- 4 files changed, 83 insertions(+), 68 deletions(-) diff --git a/Cargo.lock b/Cargo.lock index 5ddc09a24..67b4b55cb 100644 --- a/Cargo.lock +++ b/Cargo.lock @@ -3588,8 +3588,8 @@ checksum = "42703706b716c37f96a77aea830392ad231f44c9e9a67872fa5548707e11b11c" [[package]] name = "fsst" -version = "13.0.0-beta.12" -source = "git+https://github.com/lance-format/lance.git?tag=v13.0.0-beta.12#5d2946fa452c61cb018144f3200892b6dd4a8b4f" +version = "13.0.0-beta.14" +source = "git+https://github.com/lance-format/lance.git?tag=v13.0.0-beta.14#b80ac1d9f3c24b47bd8e297d03053ea35d216a9f" dependencies = [ "arrow-array", "rand 0.9.5", @@ -5143,8 +5143,8 @@ checksum = "e037a2e1d8d5fdbd49b16a4ea09d5d6401c1f29eca5ff29d03d3824dba16256a" [[package]] name = "lance" -version = "13.0.0-beta.12" -source = "git+https://github.com/lance-format/lance.git?tag=v13.0.0-beta.12#5d2946fa452c61cb018144f3200892b6dd4a8b4f" +version = "13.0.0-beta.14" +source = "git+https://github.com/lance-format/lance.git?tag=v13.0.0-beta.14#b80ac1d9f3c24b47bd8e297d03053ea35d216a9f" dependencies = [ "arc-swap", "arrow", @@ -5216,8 +5216,8 @@ dependencies = [ [[package]] name = "lance-arrow" -version = "13.0.0-beta.12" -source = "git+https://github.com/lance-format/lance.git?tag=v13.0.0-beta.12#5d2946fa452c61cb018144f3200892b6dd4a8b4f" +version = "13.0.0-beta.14" +source = "git+https://github.com/lance-format/lance.git?tag=v13.0.0-beta.14#b80ac1d9f3c24b47bd8e297d03053ea35d216a9f" dependencies = [ "arrow-array", "arrow-buffer", @@ -5239,7 +5239,7 @@ dependencies = [ [[package]] name = "lance-arrow-scalar" version = "58.0.0" -source = "git+https://github.com/lance-format/lance.git?tag=v13.0.0-beta.12#5d2946fa452c61cb018144f3200892b6dd4a8b4f" +source = "git+https://github.com/lance-format/lance.git?tag=v13.0.0-beta.14#b80ac1d9f3c24b47bd8e297d03053ea35d216a9f" dependencies = [ "arrow-array", "arrow-buffer", @@ -5253,7 +5253,7 @@ dependencies = [ [[package]] name = "lance-arrow-stats" version = "58.0.0" -source = "git+https://github.com/lance-format/lance.git?tag=v13.0.0-beta.12#5d2946fa452c61cb018144f3200892b6dd4a8b4f" +source = "git+https://github.com/lance-format/lance.git?tag=v13.0.0-beta.14#b80ac1d9f3c24b47bd8e297d03053ea35d216a9f" dependencies = [ "arrow-array", "arrow-schema", @@ -5262,8 +5262,8 @@ dependencies = [ [[package]] name = "lance-bitpacking" -version = "13.0.0-beta.12" -source = "git+https://github.com/lance-format/lance.git?tag=v13.0.0-beta.12#5d2946fa452c61cb018144f3200892b6dd4a8b4f" +version = "13.0.0-beta.14" +source = "git+https://github.com/lance-format/lance.git?tag=v13.0.0-beta.14#b80ac1d9f3c24b47bd8e297d03053ea35d216a9f" dependencies = [ "arrayref", "crunchy", @@ -5273,8 +5273,8 @@ dependencies = [ [[package]] name = "lance-core" -version = "13.0.0-beta.12" -source = "git+https://github.com/lance-format/lance.git?tag=v13.0.0-beta.12#5d2946fa452c61cb018144f3200892b6dd4a8b4f" +version = "13.0.0-beta.14" +source = "git+https://github.com/lance-format/lance.git?tag=v13.0.0-beta.14#b80ac1d9f3c24b47bd8e297d03053ea35d216a9f" dependencies = [ "arrow-array", "arrow-buffer", @@ -5311,8 +5311,8 @@ dependencies = [ [[package]] name = "lance-datafusion" -version = "13.0.0-beta.12" -source = "git+https://github.com/lance-format/lance.git?tag=v13.0.0-beta.12#5d2946fa452c61cb018144f3200892b6dd4a8b4f" +version = "13.0.0-beta.14" +source = "git+https://github.com/lance-format/lance.git?tag=v13.0.0-beta.14#b80ac1d9f3c24b47bd8e297d03053ea35d216a9f" dependencies = [ "arrow", "arrow-array", @@ -5343,8 +5343,8 @@ dependencies = [ [[package]] name = "lance-datagen" -version = "13.0.0-beta.12" -source = "git+https://github.com/lance-format/lance.git?tag=v13.0.0-beta.12#5d2946fa452c61cb018144f3200892b6dd4a8b4f" +version = "13.0.0-beta.14" +source = "git+https://github.com/lance-format/lance.git?tag=v13.0.0-beta.14#b80ac1d9f3c24b47bd8e297d03053ea35d216a9f" dependencies = [ "arrow", "arrow-array", @@ -5361,8 +5361,8 @@ dependencies = [ [[package]] name = "lance-derive" -version = "13.0.0-beta.12" -source = "git+https://github.com/lance-format/lance.git?tag=v13.0.0-beta.12#5d2946fa452c61cb018144f3200892b6dd4a8b4f" +version = "13.0.0-beta.14" +source = "git+https://github.com/lance-format/lance.git?tag=v13.0.0-beta.14#b80ac1d9f3c24b47bd8e297d03053ea35d216a9f" dependencies = [ "proc-macro2", "quote", @@ -5371,8 +5371,8 @@ dependencies = [ [[package]] name = "lance-encoding" -version = "13.0.0-beta.12" -source = "git+https://github.com/lance-format/lance.git?tag=v13.0.0-beta.12#5d2946fa452c61cb018144f3200892b6dd4a8b4f" +version = "13.0.0-beta.14" +source = "git+https://github.com/lance-format/lance.git?tag=v13.0.0-beta.14#b80ac1d9f3c24b47bd8e297d03053ea35d216a9f" dependencies = [ "arrow-arith", "arrow-array", @@ -5405,8 +5405,8 @@ dependencies = [ [[package]] name = "lance-file" -version = "13.0.0-beta.12" -source = "git+https://github.com/lance-format/lance.git?tag=v13.0.0-beta.12#5d2946fa452c61cb018144f3200892b6dd4a8b4f" +version = "13.0.0-beta.14" +source = "git+https://github.com/lance-format/lance.git?tag=v13.0.0-beta.14#b80ac1d9f3c24b47bd8e297d03053ea35d216a9f" dependencies = [ "arrow-arith", "arrow-array", @@ -5438,8 +5438,8 @@ dependencies = [ [[package]] name = "lance-geo" -version = "13.0.0-beta.12" -source = "git+https://github.com/lance-format/lance.git?tag=v13.0.0-beta.12#5d2946fa452c61cb018144f3200892b6dd4a8b4f" +version = "13.0.0-beta.14" +source = "git+https://github.com/lance-format/lance.git?tag=v13.0.0-beta.14#b80ac1d9f3c24b47bd8e297d03053ea35d216a9f" dependencies = [ "datafusion", "geo-traits", @@ -5453,8 +5453,8 @@ dependencies = [ [[package]] name = "lance-index" -version = "13.0.0-beta.12" -source = "git+https://github.com/lance-format/lance.git?tag=v13.0.0-beta.12#5d2946fa452c61cb018144f3200892b6dd4a8b4f" +version = "13.0.0-beta.14" +source = "git+https://github.com/lance-format/lance.git?tag=v13.0.0-beta.14#b80ac1d9f3c24b47bd8e297d03053ea35d216a9f" dependencies = [ "arc-swap", "arrow", @@ -5524,8 +5524,8 @@ dependencies = [ [[package]] name = "lance-index-core" -version = "13.0.0-beta.12" -source = "git+https://github.com/lance-format/lance.git?tag=v13.0.0-beta.12#5d2946fa452c61cb018144f3200892b6dd4a8b4f" +version = "13.0.0-beta.14" +source = "git+https://github.com/lance-format/lance.git?tag=v13.0.0-beta.14#b80ac1d9f3c24b47bd8e297d03053ea35d216a9f" dependencies = [ "arrow-array", "arrow-schema", @@ -5547,8 +5547,8 @@ dependencies = [ [[package]] name = "lance-io" -version = "13.0.0-beta.12" -source = "git+https://github.com/lance-format/lance.git?tag=v13.0.0-beta.12#5d2946fa452c61cb018144f3200892b6dd4a8b4f" +version = "13.0.0-beta.14" +source = "git+https://github.com/lance-format/lance.git?tag=v13.0.0-beta.14#b80ac1d9f3c24b47bd8e297d03053ea35d216a9f" dependencies = [ "arrow", "arrow-array", @@ -5590,8 +5590,8 @@ dependencies = [ [[package]] name = "lance-linalg" -version = "13.0.0-beta.12" -source = "git+https://github.com/lance-format/lance.git?tag=v13.0.0-beta.12#5d2946fa452c61cb018144f3200892b6dd4a8b4f" +version = "13.0.0-beta.14" +source = "git+https://github.com/lance-format/lance.git?tag=v13.0.0-beta.14#b80ac1d9f3c24b47bd8e297d03053ea35d216a9f" dependencies = [ "arrow-array", "arrow-schema", @@ -5605,8 +5605,8 @@ dependencies = [ [[package]] name = "lance-namespace" -version = "13.0.0-beta.12" -source = "git+https://github.com/lance-format/lance.git?tag=v13.0.0-beta.12#5d2946fa452c61cb018144f3200892b6dd4a8b4f" +version = "13.0.0-beta.14" +source = "git+https://github.com/lance-format/lance.git?tag=v13.0.0-beta.14#b80ac1d9f3c24b47bd8e297d03053ea35d216a9f" dependencies = [ "arrow", "async-trait", @@ -5620,8 +5620,8 @@ dependencies = [ [[package]] name = "lance-namespace-impls" -version = "13.0.0-beta.12" -source = "git+https://github.com/lance-format/lance.git?tag=v13.0.0-beta.12#5d2946fa452c61cb018144f3200892b6dd4a8b4f" +version = "13.0.0-beta.14" +source = "git+https://github.com/lance-format/lance.git?tag=v13.0.0-beta.14#b80ac1d9f3c24b47bd8e297d03053ea35d216a9f" dependencies = [ "arrow", "arrow-ipc", @@ -5674,8 +5674,8 @@ dependencies = [ [[package]] name = "lance-select" -version = "13.0.0-beta.12" -source = "git+https://github.com/lance-format/lance.git?tag=v13.0.0-beta.12#5d2946fa452c61cb018144f3200892b6dd4a8b4f" +version = "13.0.0-beta.14" +source = "git+https://github.com/lance-format/lance.git?tag=v13.0.0-beta.14#b80ac1d9f3c24b47bd8e297d03053ea35d216a9f" dependencies = [ "arrow-array", "arrow-buffer", @@ -5689,8 +5689,8 @@ dependencies = [ [[package]] name = "lance-table" -version = "13.0.0-beta.12" -source = "git+https://github.com/lance-format/lance.git?tag=v13.0.0-beta.12#5d2946fa452c61cb018144f3200892b6dd4a8b4f" +version = "13.0.0-beta.14" +source = "git+https://github.com/lance-format/lance.git?tag=v13.0.0-beta.14#b80ac1d9f3c24b47bd8e297d03053ea35d216a9f" dependencies = [ "arrow", "arrow-array", @@ -5730,8 +5730,8 @@ dependencies = [ [[package]] name = "lance-testing" -version = "13.0.0-beta.12" -source = "git+https://github.com/lance-format/lance.git?tag=v13.0.0-beta.12#5d2946fa452c61cb018144f3200892b6dd4a8b4f" +version = "13.0.0-beta.14" +source = "git+https://github.com/lance-format/lance.git?tag=v13.0.0-beta.14#b80ac1d9f3c24b47bd8e297d03053ea35d216a9f" dependencies = [ "arrow-array", "arrow-schema", @@ -5744,8 +5744,8 @@ dependencies = [ [[package]] name = "lance-tokenizer" -version = "13.0.0-beta.12" -source = "git+https://github.com/lance-format/lance.git?tag=v13.0.0-beta.12#5d2946fa452c61cb018144f3200892b6dd4a8b4f" +version = "13.0.0-beta.14" +source = "git+https://github.com/lance-format/lance.git?tag=v13.0.0-beta.14#b80ac1d9f3c24b47bd8e297d03053ea35d216a9f" dependencies = [ "frostem", "icu_segmenter", diff --git a/Cargo.toml b/Cargo.toml index c64305048..15770bebc 100644 --- a/Cargo.toml +++ b/Cargo.toml @@ -13,20 +13,20 @@ categories = ["database-implementations"] rust-version = "1.91.0" [workspace.dependencies] -lance = { "version" = "=13.0.0-beta.12", default-features = false, "tag" = "v13.0.0-beta.12", "git" = "https://github.com/lance-format/lance.git" } -lance-core = { "version" = "=13.0.0-beta.12", "tag" = "v13.0.0-beta.12", "git" = "https://github.com/lance-format/lance.git" } -lance-datagen = { "version" = "=13.0.0-beta.12", "tag" = "v13.0.0-beta.12", "git" = "https://github.com/lance-format/lance.git" } -lance-file = { "version" = "=13.0.0-beta.12", "tag" = "v13.0.0-beta.12", "git" = "https://github.com/lance-format/lance.git" } -lance-io = { "version" = "=13.0.0-beta.12", default-features = false, "tag" = "v13.0.0-beta.12", "git" = "https://github.com/lance-format/lance.git" } -lance-index = { "version" = "=13.0.0-beta.12", "tag" = "v13.0.0-beta.12", "git" = "https://github.com/lance-format/lance.git" } -lance-linalg = { "version" = "=13.0.0-beta.12", "tag" = "v13.0.0-beta.12", "git" = "https://github.com/lance-format/lance.git" } -lance-namespace = { "version" = "=13.0.0-beta.12", "tag" = "v13.0.0-beta.12", "git" = "https://github.com/lance-format/lance.git" } -lance-namespace-impls = { "version" = "=13.0.0-beta.12", default-features = false, "tag" = "v13.0.0-beta.12", "git" = "https://github.com/lance-format/lance.git" } -lance-table = { "version" = "=13.0.0-beta.12", "tag" = "v13.0.0-beta.12", "git" = "https://github.com/lance-format/lance.git" } -lance-testing = { "version" = "=13.0.0-beta.12", "tag" = "v13.0.0-beta.12", "git" = "https://github.com/lance-format/lance.git" } -lance-datafusion = { "version" = "=13.0.0-beta.12", "tag" = "v13.0.0-beta.12", "git" = "https://github.com/lance-format/lance.git" } -lance-encoding = { "version" = "=13.0.0-beta.12", "tag" = "v13.0.0-beta.12", "git" = "https://github.com/lance-format/lance.git" } -lance-arrow = { "version" = "=13.0.0-beta.12", "tag" = "v13.0.0-beta.12", "git" = "https://github.com/lance-format/lance.git" } +lance = { "version" = "=13.0.0-beta.14", default-features = false, "tag" = "v13.0.0-beta.14", "git" = "https://github.com/lance-format/lance.git" } +lance-core = { "version" = "=13.0.0-beta.14", "tag" = "v13.0.0-beta.14", "git" = "https://github.com/lance-format/lance.git" } +lance-datagen = { "version" = "=13.0.0-beta.14", "tag" = "v13.0.0-beta.14", "git" = "https://github.com/lance-format/lance.git" } +lance-file = { "version" = "=13.0.0-beta.14", "tag" = "v13.0.0-beta.14", "git" = "https://github.com/lance-format/lance.git" } +lance-io = { "version" = "=13.0.0-beta.14", default-features = false, "tag" = "v13.0.0-beta.14", "git" = "https://github.com/lance-format/lance.git" } +lance-index = { "version" = "=13.0.0-beta.14", "tag" = "v13.0.0-beta.14", "git" = "https://github.com/lance-format/lance.git" } +lance-linalg = { "version" = "=13.0.0-beta.14", "tag" = "v13.0.0-beta.14", "git" = "https://github.com/lance-format/lance.git" } +lance-namespace = { "version" = "=13.0.0-beta.14", "tag" = "v13.0.0-beta.14", "git" = "https://github.com/lance-format/lance.git" } +lance-namespace-impls = { "version" = "=13.0.0-beta.14", default-features = false, "tag" = "v13.0.0-beta.14", "git" = "https://github.com/lance-format/lance.git" } +lance-table = { "version" = "=13.0.0-beta.14", "tag" = "v13.0.0-beta.14", "git" = "https://github.com/lance-format/lance.git" } +lance-testing = { "version" = "=13.0.0-beta.14", "tag" = "v13.0.0-beta.14", "git" = "https://github.com/lance-format/lance.git" } +lance-datafusion = { "version" = "=13.0.0-beta.14", "tag" = "v13.0.0-beta.14", "git" = "https://github.com/lance-format/lance.git" } +lance-encoding = { "version" = "=13.0.0-beta.14", "tag" = "v13.0.0-beta.14", "git" = "https://github.com/lance-format/lance.git" } +lance-arrow = { "version" = "=13.0.0-beta.14", "tag" = "v13.0.0-beta.14", "git" = "https://github.com/lance-format/lance.git" } lancedb = { path = "rust/lancedb", default-features = false } ahash = "0.8" # Note that this one does not include pyarrow diff --git a/rust/lancedb/src/table/datafusion/udtf/duplicate_pairs.rs b/rust/lancedb/src/table/datafusion/udtf/duplicate_pairs.rs index 6fd0f6216..eeb21112f 100644 --- a/rust/lancedb/src/table/datafusion/udtf/duplicate_pairs.rs +++ b/rust/lancedb/src/table/datafusion/udtf/duplicate_pairs.rs @@ -35,12 +35,17 @@ use crate::table::NativeTableExt; // Admission estimates for Lance 13's bounded pairwise kernel. Keep these with // the minimum dependency when the kernel's buffering contract changes. /// Version of the native task descriptor and its execution semantics. -pub const DUPLICATE_PAIRS_OPERATOR_VERSION: u32 = 1; +pub const DUPLICATE_PAIRS_OPERATOR_VERSION: u32 = 2; const CODE_STAGING_BYTES: usize = 16 * 1024 * 1024; const INDEX_READ_ROWS: usize = 8192; -const VECTOR_BATCH_ROWS: usize = 1024; +const VECTOR_BATCH_ROWS: usize = 8192; +const VECTOR_BATCH_BYTES: usize = 16 * 1024 * 1024; +const MIN_VECTOR_BATCH_ROWS: usize = 32; +const ANCHOR_BLOCK_ROWS: usize = 32; +const SCORING_CONCURRENCY: usize = 4; const MAX_COORDINATE_BYTES: usize = 8; +const STAGED_ROW_OVERHEAD_BYTES: usize = 64; const PAIR_ROW_BYTES: usize = 20; /// Configuration belongs to one immutable source snapshot. Threshold uses @@ -431,9 +436,9 @@ impl ExecutionPlan for DuplicatePairsExec { let output_rows = MetricBuilder::new(&self.metrics).counter("output_rows", partition); let completed = MetricBuilder::new(&self.metrics).counter("completed_partitions", partition); - // Admission estimate for the released Lance kernel: compact-code staging, - // one 8192-row read and two decoded 1024-row batches. This reservation - // limits concurrent kernels; Lance still owns its bounded buffers/spill. + // Beta.14 stages native codes and scores bounded tiles concurrently. + // Keep the host staging budget explicit rather than inheriting Lance's + // larger default or multiplying CPU-pool concurrency across PE tasks. let dimension = match dataset .schema() .field(&config.column) @@ -442,9 +447,16 @@ impl ExecutionPlan for DuplicatePairsExec { Some(DataType::FixedSizeList(_, dimension)) if dimension > 0 => dimension as usize, _ => return plan_err!("duplicate pairs requires a fixed-size vector column"), }; - let budget = CODE_STAGING_BYTES - + (INDEX_READ_ROWS + 2 * VECTOR_BATCH_ROWS) * dimension * MAX_COORDINATE_BYTES - + VECTOR_BATCH_ROWS * PAIR_ROW_BYTES; + let batch_bytes = VECTOR_BATCH_BYTES.max( + MIN_VECTOR_BATCH_ROWS * (dimension * MAX_COORDINATE_BYTES + STAGED_ROW_OVERHEAD_BYTES), + ); + // Allow staging/preparation overlap, at least three live spill batches, + // source input, and in-flight output plus the batch being encoded. + // Quantizer models and caches remain outside this admission estimate. + let budget = 2 * CODE_STAGING_BYTES + + 3 * batch_bytes + + INDEX_READ_ROWS * (dimension * MAX_COORDINATE_BYTES + STAGED_ROW_OVERHEAD_BYTES) + + (SCORING_CONCURRENCY + 1) * ANCHOR_BLOCK_ROWS * VECTOR_BATCH_ROWS * PAIR_ROW_BYTES; let reservation = datafusion_execution::memory_pool::MemoryConsumer::new("DuplicatePairsExec") .register(context.memory_pool()); @@ -461,12 +473,15 @@ impl ExecutionPlan for DuplicatePairsExec { let output_rows = output_rows.clone(); let completed = completed.clone(); async move { - let reader = lance::index::vector::dedup::find_duplicate_pairs_in_partition( + let reader = lance::index::vector::dedup::find_duplicate_pairs_in_partition_with_options( dataset, &config.column, task.segment_id, task.partition_id, config.distance_threshold, + lance::index::vector::dedup::DuplicatePairsOptions::default() + .with_memory_limit(CODE_STAGING_BYTES) + .with_max_concurrency(SCORING_CONCURRENCY), ) .await?; let measured = stream::try_unfold( diff --git a/rust/lancedb/tests/duplicate_pairs.rs b/rust/lancedb/tests/duplicate_pairs.rs index ea3530717..4f3ed50f6 100644 --- a/rust/lancedb/tests/duplicate_pairs.rs +++ b/rust/lancedb/tests/duplicate_pairs.rs @@ -162,7 +162,7 @@ async fn sql_pairs_match_native_snapshot_and_partition_tasks() -> anyhow::Result // execution must consume scoped readers sequentially. let runtime = Arc::new( datafusion_execution::runtime_env::RuntimeEnvBuilder::new() - .with_memory_limit(32 * 1024 * 1024, 1.0) + .with_memory_limit(128 * 1024 * 1024, 1.0) .build()?, ); let ctx =