mirror of
https://github.com/lancedb/lancedb.git
synced 2026-10-12 23:02:28 +00:00
feat: let a table's maintained index set be changed in place
Changing the set meant unsetting the spec and setting it again, which drops the MemWAL and everything in its fresh tier. `set_lsm_write_spec` now accepts a repeat that differs only there and updates the set on the live index; the sharding still cannot move, because the generations already written were homed under it. The default set also stops being a snapshot. It is stored as the intent to maintain everything, which lance re-reads as the table changes, so an index created later is maintained without another call. An index of a kind the MemWAL cannot mirror is skipped under that intent rather than refusing the table, since nobody asked for it by name; a named one is still refused. The LSM read path asks the spec whether an index is maintained rather than searching the stored list, which an unnamed set leaves empty -- reading the list alone would refuse full-text and vector search on every table using the default.
This commit is contained in:
+62
-39
@@ -330,7 +330,8 @@ 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.
|
||||
/// A fresh spec maintains every index on the table, including ones created
|
||||
/// after it is installed.
|
||||
///
|
||||
/// Install a spec with [`Table::set_lsm_write_spec`] and remove it with
|
||||
/// [`Table::unset_lsm_write_spec`]. The actual `merge_insert` dispatch
|
||||
@@ -348,9 +349,8 @@ pub enum LsmWriteSpec {
|
||||
num_buckets: u32,
|
||||
/// 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.
|
||||
/// `None` means every index the table has, including ones created
|
||||
/// later. `Some([])` maintains nothing.
|
||||
maintained_indexes: Option<Vec<String>>,
|
||||
/// Default `ShardWriter` configuration recorded in the MemWAL index.
|
||||
writer_config_defaults: HashMap<String, String>,
|
||||
@@ -363,9 +363,8 @@ pub enum LsmWriteSpec {
|
||||
column: String,
|
||||
/// 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.
|
||||
/// `None` means every index the table has, including ones created
|
||||
/// later. `Some([])` maintains nothing.
|
||||
maintained_indexes: Option<Vec<String>>,
|
||||
/// Default `ShardWriter` configuration recorded in the MemWAL index.
|
||||
writer_config_defaults: HashMap<String, String>,
|
||||
@@ -374,9 +373,8 @@ pub enum LsmWriteSpec {
|
||||
Unsharded {
|
||||
/// 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.
|
||||
/// `None` means every index the table has, including ones created
|
||||
/// later. `Some([])` maintains nothing.
|
||||
maintained_indexes: Option<Vec<String>>,
|
||||
/// Default `ShardWriter` configuration recorded in the MemWAL index.
|
||||
writer_config_defaults: HashMap<String, String>,
|
||||
@@ -422,14 +420,15 @@ impl LsmWriteSpec {
|
||||
|
||||
/// 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.
|
||||
/// `None` (the default) is every index on the table, re-read as the table
|
||||
/// changes, so an index created later is maintained too; one of a kind the
|
||||
/// MemWAL cannot mirror is skipped rather than failing the table. 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:
|
||||
/// // Every index the table has, now and later:
|
||||
/// LsmWriteSpec::unsharded().with_maintained_indexes(None);
|
||||
/// // Exactly these:
|
||||
/// LsmWriteSpec::unsharded().with_maintained_indexes(vec!["id_idx".to_string()]);
|
||||
@@ -1985,6 +1984,10 @@ impl Table {
|
||||
/// - [`LsmWriteSpec::identity`] — shard by the raw value of a scalar column.
|
||||
/// - [`LsmWriteSpec::unsharded`] — route every write to a single shard.
|
||||
///
|
||||
/// Calling this again on a table that already has a spec is how the
|
||||
/// maintained index set is changed; the sharding cannot move, because the
|
||||
/// generations already written were homed under it.
|
||||
///
|
||||
/// # Example
|
||||
///
|
||||
/// ```
|
||||
@@ -5648,29 +5651,22 @@ 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".
|
||||
// A spec left at its default round-trips as the default: what is stored
|
||||
// is the intent to maintain everything, not the set it resolves to now.
|
||||
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.with_maintained_indexes(vec![idx_name.clone()]))
|
||||
);
|
||||
assert_eq!(table.get_lsm_write_spec().await.unwrap(), Some(spec));
|
||||
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.with_maintained_indexes(vec![idx_name]))
|
||||
);
|
||||
assert_eq!(table.get_lsm_write_spec().await.unwrap(), Some(spec));
|
||||
}
|
||||
|
||||
/// 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.
|
||||
/// The maintained set defaults to every index on the table. A named index
|
||||
/// the memtable cannot build fails the install, because the caller asked
|
||||
/// for it; an unnamed one is skipped, because it arrived by existing.
|
||||
#[tokio::test]
|
||||
async fn test_set_lsm_write_spec_infers_maintained_indexes() {
|
||||
let tmp_dir = tempdir().unwrap();
|
||||
@@ -5723,19 +5719,25 @@ mod tests {
|
||||
);
|
||||
assert_eq!(table.get_lsm_write_spec().await.unwrap(), None);
|
||||
|
||||
// The default covers every index, so the bitmap fails it too.
|
||||
let err = table
|
||||
// The default names nothing, so the bitmap is skipped rather than
|
||||
// refusing the table: it is maintained by existing, not by being asked
|
||||
// for. The intent is what is stored, not the set it resolves to today.
|
||||
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:?}"
|
||||
.unwrap();
|
||||
assert_eq!(
|
||||
table
|
||||
.get_lsm_write_spec()
|
||||
.await
|
||||
.unwrap()
|
||||
.unwrap()
|
||||
.maintained_indexes(),
|
||||
None,
|
||||
"an unnamed set is stored as the intent to maintain everything"
|
||||
);
|
||||
assert_eq!(table.get_lsm_write_spec().await.unwrap(), None);
|
||||
|
||||
// Naming the maintainable subset installs.
|
||||
// Naming the maintainable subset narrows it, with no unset in between.
|
||||
table
|
||||
.set_lsm_write_spec(
|
||||
LsmWriteSpec::unsharded().with_maintained_indexes(vec!["id_btree".to_string()]),
|
||||
@@ -5753,7 +5755,6 @@ mod tests {
|
||||
);
|
||||
|
||||
// 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
|
||||
@@ -5767,6 +5768,28 @@ mod tests {
|
||||
.maintained_indexes(),
|
||||
Some([].as_slice())
|
||||
);
|
||||
|
||||
// The sharding cannot move, so the repeat that changes it is refused
|
||||
// and the installed spec is left alone.
|
||||
let err = table
|
||||
.set_lsm_write_spec(LsmWriteSpec::bucket("id", 4))
|
||||
.await
|
||||
.unwrap_err();
|
||||
assert!(
|
||||
matches!(err, Error::InvalidInput { ref message }
|
||||
if message.contains("only its maintained index set can be changed")),
|
||||
"expected the sharding change to be refused, got {err:?}"
|
||||
);
|
||||
assert_eq!(
|
||||
table
|
||||
.get_lsm_write_spec()
|
||||
.await
|
||||
.unwrap()
|
||||
.unwrap()
|
||||
.maintained_indexes(),
|
||||
Some([].as_slice()),
|
||||
"a refused call changes nothing"
|
||||
);
|
||||
}
|
||||
|
||||
#[tokio::test]
|
||||
|
||||
@@ -160,6 +160,10 @@ impl NativeTable {
|
||||
builder = builder.name(name);
|
||||
}
|
||||
builder.await?;
|
||||
self.dataset
|
||||
.shard_writer()
|
||||
.refresh_maintained_indexes(&dataset)
|
||||
.await;
|
||||
self.dataset.update(dataset);
|
||||
Ok(())
|
||||
}
|
||||
|
||||
@@ -1251,6 +1251,30 @@ mod lsm_tests {
|
||||
);
|
||||
}
|
||||
|
||||
/// A table with `id`/`text` and a primary key, ready for an LSM write spec.
|
||||
async fn lsm_text_table(dir: &tempfile::TempDir) -> crate::Table {
|
||||
let conn = connect(dir.path().to_str().unwrap())
|
||||
.execute()
|
||||
.await
|
||||
.unwrap();
|
||||
let table = conn
|
||||
.create_table("t", id_text_reader(vec![(1, "alpha")]))
|
||||
.execute()
|
||||
.await
|
||||
.unwrap();
|
||||
table.set_unenforced_primary_key(["id"]).await.unwrap();
|
||||
table
|
||||
}
|
||||
|
||||
/// Upsert `rows` through the LSM write path.
|
||||
async fn upsert_text(table: &crate::Table, rows: Vec<(i64, &str)>) {
|
||||
let mut builder = table.merge_insert(&[]);
|
||||
builder
|
||||
.when_matched_update_all(None)
|
||||
.when_not_matched_insert_all();
|
||||
builder.execute(id_text_reader(rows)).await.unwrap();
|
||||
}
|
||||
|
||||
/// A reader of `[id: Int64, text: Utf8]` rows.
|
||||
fn id_text_reader(rows: Vec<(i64, &str)>) -> Box<dyn RecordBatchReader + Send> {
|
||||
let schema = Arc::new(Schema::new(vec![
|
||||
@@ -1270,6 +1294,148 @@ mod lsm_tests {
|
||||
Box::new(RecordBatchIterator::new(vec![Ok(batch)], schema))
|
||||
}
|
||||
|
||||
/// Under the default set, an index created while a writer is open reaches
|
||||
/// that writer.
|
||||
///
|
||||
/// The default maintains every index the table has, so creating one changes
|
||||
/// what the table maintains without anyone touching the spec. A writer left
|
||||
/// on its old configs would keep building MemTables the new index does not
|
||||
/// cover.
|
||||
#[tokio::test]
|
||||
async fn lsm_default_set_picks_up_an_index_created_while_writing() {
|
||||
use crate::index::Index;
|
||||
use lance_index::scalar::FullTextSearchQuery;
|
||||
|
||||
let dir = tempdir().unwrap();
|
||||
let table = lsm_text_table(&dir).await;
|
||||
// The default set, on a table with no FTS index yet.
|
||||
table
|
||||
.set_lsm_write_spec(LsmWriteSpec::unsharded())
|
||||
.await
|
||||
.unwrap();
|
||||
|
||||
// Opens the writer, whose MemTable carries no FTS index.
|
||||
upsert_text(&table, vec![(99, "zebra")]).await;
|
||||
|
||||
// Created with the writer still open and never reopened.
|
||||
table
|
||||
.create_index(&["text"], Index::FTS(Default::default()))
|
||||
.execute()
|
||||
.await
|
||||
.unwrap();
|
||||
|
||||
upsert_text(&table, vec![(100, "zebra stripes")]).await;
|
||||
|
||||
let query = FullTextSearchQuery::new("stripes".to_string())
|
||||
.with_column("text".to_string())
|
||||
.unwrap();
|
||||
let batches = table
|
||||
.query()
|
||||
.full_text_search(query)
|
||||
.execute()
|
||||
.await
|
||||
.expect("the created index reached the open writer")
|
||||
.try_collect::<Vec<_>>()
|
||||
.await
|
||||
.unwrap();
|
||||
let found: usize = batches.iter().map(|b| b.num_rows()).sum();
|
||||
assert_eq!(found, 1, "the row written after create_index must be found");
|
||||
}
|
||||
|
||||
/// Changing the set on a live table reaches the writer already open on it.
|
||||
///
|
||||
/// Without that, the commit would land and the writer would keep building
|
||||
/// MemTables from the old set, so a query needing the newly maintained
|
||||
/// index would stay refused until something reopened the writer.
|
||||
#[tokio::test]
|
||||
async fn lsm_set_change_reaches_an_already_open_writer() {
|
||||
use crate::index::Index;
|
||||
use lance_index::scalar::FullTextSearchQuery;
|
||||
|
||||
let dir = tempdir().unwrap();
|
||||
let table = lsm_text_table(&dir).await;
|
||||
table
|
||||
.create_index(&["text"], Index::FTS(Default::default()))
|
||||
.execute()
|
||||
.await
|
||||
.unwrap();
|
||||
let fts_index = table.list_indices().await.unwrap()[0].name.clone();
|
||||
|
||||
// Installed maintaining nothing, then written to: the writer opens with
|
||||
// no FTS index.
|
||||
table
|
||||
.set_lsm_write_spec(LsmWriteSpec::unsharded().with_maintained_indexes(Vec::new()))
|
||||
.await
|
||||
.unwrap();
|
||||
upsert_text(&table, vec![(99, "zebra")]).await;
|
||||
|
||||
// Change the set in place on the live table.
|
||||
table
|
||||
.set_lsm_write_spec(LsmWriteSpec::unsharded().with_maintained_indexes(vec![fts_index]))
|
||||
.await
|
||||
.unwrap();
|
||||
|
||||
// A row written after the change is answered by the index the writer
|
||||
// picked up.
|
||||
upsert_text(&table, vec![(100, "zebra stripes")]).await;
|
||||
|
||||
let query = FullTextSearchQuery::new("stripes".to_string())
|
||||
.with_column("text".to_string())
|
||||
.unwrap();
|
||||
let batches = table
|
||||
.query()
|
||||
.full_text_search(query)
|
||||
.execute()
|
||||
.await
|
||||
.expect("the set change reached the open writer")
|
||||
.try_collect::<Vec<_>>()
|
||||
.await
|
||||
.unwrap();
|
||||
let found: usize = batches.iter().map(|b| b.num_rows()).sum();
|
||||
assert_eq!(found, 1, "the row written after the change must be found");
|
||||
}
|
||||
|
||||
/// A writer opened before the index existed keeps a MemTable without it, so
|
||||
/// an indexed read is refused rather than served without those rows.
|
||||
///
|
||||
/// The default set maintains every index the table has, which the spec
|
||||
/// records as intent. That intent alone would let the read through while
|
||||
/// the live MemTable still cannot answer it.
|
||||
#[tokio::test]
|
||||
async fn lsm_read_refuses_when_a_resident_memtable_predates_the_index() {
|
||||
use crate::index::Index;
|
||||
use lance_index::scalar::FullTextSearchQuery;
|
||||
|
||||
let dir = tempdir().unwrap();
|
||||
let table = lsm_text_table(&dir).await;
|
||||
// No index yet, and the default set: maintain whatever the table has.
|
||||
table
|
||||
.set_lsm_write_spec(LsmWriteSpec::unsharded())
|
||||
.await
|
||||
.unwrap();
|
||||
|
||||
// Opens the writer, whose MemTable therefore carries no FTS index.
|
||||
upsert_text(&table, vec![(99, "zebra")]).await;
|
||||
|
||||
// Built afterwards: the spec now resolves to it, the MemTable does not.
|
||||
table
|
||||
.create_index(&["text"], Index::FTS(Default::default()))
|
||||
.execute()
|
||||
.await
|
||||
.unwrap();
|
||||
|
||||
let query = FullTextSearchQuery::new("zebra".to_string())
|
||||
.with_column("text".to_string())
|
||||
.unwrap();
|
||||
let Err(error) = table.query().full_text_search(query).execute().await else {
|
||||
panic!("an indexed read the resident MemTable cannot answer must be refused");
|
||||
};
|
||||
assert!(
|
||||
error.to_string().contains("resident MemTable"),
|
||||
"unexpected error: {error}"
|
||||
);
|
||||
}
|
||||
|
||||
#[tokio::test]
|
||||
async fn lsm_read_full_text_search() {
|
||||
use crate::index::Index;
|
||||
|
||||
@@ -73,27 +73,62 @@ const SHARD_NAMESPACE: Uuid = Uuid::from_u128(0x4c53_4d57_5249_5445_5f53_4841_52
|
||||
pub(crate) async fn set_lsm_write_spec(table: &NativeTable, spec: LsmWriteSpec) -> Result<()> {
|
||||
table.dataset.ensure_mutable()?;
|
||||
|
||||
// A named set is checked against the table here, where the caller can still
|
||||
// be told which names exist. An unnamed set is not resolved at all: it is an
|
||||
// intent lance re-reads whenever it builds a MemTable, so an index created
|
||||
// later is maintained without another call.
|
||||
let maintained_indexes = match spec.maintained_indexes() {
|
||||
Some(requested) => {
|
||||
let indices = table.list_indices().await?;
|
||||
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),
|
||||
),
|
||||
});
|
||||
}
|
||||
}
|
||||
// Before the builder borrows the dataset clone.
|
||||
let dataset = table.dataset.get().await?;
|
||||
validate_maintained_indexes(&dataset, requested).await?;
|
||||
Some(requested.to_vec())
|
||||
}
|
||||
None => None,
|
||||
};
|
||||
|
||||
// A table that already has a spec accepts one kind of repeat: the same
|
||||
// sharding with a different maintained set. The rest of a spec describes
|
||||
// how the generations already written were homed, so it cannot move.
|
||||
{
|
||||
let dataset = table.dataset.get().await?;
|
||||
if dataset.mem_wal_index_details().await?.is_some() {
|
||||
return Err(Error::InvalidInput {
|
||||
message: "set_lsm_write_spec: an LSM write spec is already set on this table; mutation is not supported".into(),
|
||||
});
|
||||
if let Some(details) = dataset.mem_wal_index_details().await? {
|
||||
let installed = lsm_write_spec_from_details(&details, dataset.schema())?;
|
||||
if !same_except_maintained_indexes(&installed, &spec) {
|
||||
return Err(Error::InvalidInput {
|
||||
message: "set_lsm_write_spec: an LSM write spec is already set on this \
|
||||
table; only its maintained index set can be changed"
|
||||
.into(),
|
||||
});
|
||||
}
|
||||
drop(dataset);
|
||||
table.checkout_latest().await?;
|
||||
let mut dataset = (*table.dataset.get().await?).clone();
|
||||
dataset
|
||||
.update_mem_wal_maintained_indexes(maintained_indexes)
|
||||
.await?;
|
||||
table
|
||||
.dataset
|
||||
.shard_writer()
|
||||
.refresh_maintained_indexes(&dataset)
|
||||
.await;
|
||||
table.dataset.update(dataset);
|
||||
return Ok(());
|
||||
}
|
||||
}
|
||||
|
||||
// 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?
|
||||
};
|
||||
|
||||
table.checkout_latest().await?;
|
||||
let mut dataset = (*table.dataset.get().await?).clone();
|
||||
let schema = arrow_schema::Schema::from(dataset.schema());
|
||||
@@ -138,7 +173,9 @@ pub(crate) async fn set_lsm_write_spec(table: &NativeTable, spec: LsmWriteSpec)
|
||||
writer_config_defaults
|
||||
}
|
||||
};
|
||||
builder = builder.maintained_indexes(maintained_indexes);
|
||||
if let Some(maintained_indexes) = maintained_indexes {
|
||||
builder = builder.maintained_indexes(maintained_indexes);
|
||||
}
|
||||
for (key, value) in writer_config_defaults {
|
||||
builder = builder.add_writer_config_default(key, value);
|
||||
}
|
||||
@@ -147,48 +184,6 @@ 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<Vec<String>> {
|
||||
let Some(requested) = requested else {
|
||||
let all: Vec<String> = 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() {
|
||||
@@ -298,10 +293,17 @@ fn lsm_write_spec_from_details(
|
||||
};
|
||||
|
||||
Ok(base
|
||||
.with_maintained_indexes(details.maintained_indexes.clone())
|
||||
.with_maintained_indexes(
|
||||
(!details.maintain_all_indexes).then(|| details.maintained_indexes.clone()),
|
||||
)
|
||||
.with_writer_config_defaults(details.writer_config_defaults.clone()))
|
||||
}
|
||||
|
||||
/// Whether two specs agree on everything an installed spec cannot change.
|
||||
fn same_except_maintained_indexes(a: &LsmWriteSpec, b: &LsmWriteSpec) -> bool {
|
||||
a.clone().with_maintained_indexes(None) == b.clone().with_maintained_indexes(None)
|
||||
}
|
||||
|
||||
/// Resolve the single routing column name from a sharding field's source id.
|
||||
///
|
||||
/// `set_lsm_write_spec` records the shard column by its Lance field id, so the
|
||||
@@ -460,6 +462,37 @@ impl ShardWriterCache {
|
||||
Ok(entry)
|
||||
}
|
||||
|
||||
/// Install `dataset`'s maintained index set on the cached writer, if one is
|
||||
/// open, so a change reaches a table that is already being written to.
|
||||
///
|
||||
/// Reported rather than propagated: both callers have already committed the
|
||||
/// change durably, and the writer this process happens to hold may be
|
||||
/// fenced or poisoned -- which is not a reason to fail creating an index.
|
||||
/// Any writer opened afterwards reads the committed set.
|
||||
///
|
||||
/// Holds the entry's read lock across the refresh, so a concurrent close
|
||||
/// waits rather than retiring the writer mid-seal. Writes take the same
|
||||
/// lock first, so the order matches theirs.
|
||||
pub(crate) async fn refresh_maintained_indexes(&self, dataset: &Dataset) {
|
||||
let entry = {
|
||||
let guard = self.slot.read().await;
|
||||
guard.as_ref().map(|(_, entry)| entry.clone())
|
||||
};
|
||||
let Some(entry) = entry else {
|
||||
return;
|
||||
};
|
||||
let guard = entry.inner.read().await;
|
||||
let Some(writer) = guard.as_ref() else {
|
||||
return;
|
||||
};
|
||||
if let Err(error) = dataset.refresh_mem_wal_index_configs(writer).await {
|
||||
log::warn!(
|
||||
"the maintained index set changed but the open shard writer could \
|
||||
not be refreshed, so it keeps the set it opened with: {error}"
|
||||
);
|
||||
}
|
||||
}
|
||||
|
||||
/// Snapshot the cached writer's shard for the LSM read path: its shard id,
|
||||
/// authoritative in-memory manifest, and active + frozen memtable refs.
|
||||
/// Returns `None` when no writer is currently cached (e.g. nothing has been
|
||||
|
||||
@@ -33,7 +33,7 @@ use datafusion_physical_plan::expressions::Column;
|
||||
use datafusion_physical_plan::projection::ProjectionExec;
|
||||
use datafusion_physical_plan::{ExecutionPlan, PhysicalExpr};
|
||||
use lance::Dataset;
|
||||
use lance::dataset::mem_wal::scanner::InMemoryMemTables;
|
||||
use lance::dataset::mem_wal::scanner::{InMemoryMemTableRef, InMemoryMemTables};
|
||||
use lance::dataset::mem_wal::{
|
||||
DatasetMemWalExt, LsmScanner, ShardManifestStore, ShardSnapshot, ShardWriterConfig,
|
||||
};
|
||||
@@ -471,17 +471,14 @@ async fn fts_plan(
|
||||
// Without a maintained in-memory FTS index for this column, the active memtable
|
||||
// arm produces an empty plan (`active_source_can_execute_fts` returns false), so
|
||||
// the search silently omits un-compacted documents. Reject rather than mislead.
|
||||
if !index_maintained(
|
||||
dataset,
|
||||
column,
|
||||
&details.maintained_indexes,
|
||||
"InvertedIndexDetails",
|
||||
)
|
||||
.await?
|
||||
if !index_maintained(dataset, column, details, "InvertedIndexDetails").await?
|
||||
|| !resident_memtables_carry(&in_memory, |memtable| {
|
||||
memtable.index_store.get_fts_by_column(column).is_some()
|
||||
})
|
||||
{
|
||||
return Err(Error::NotSupported {
|
||||
message: format!(
|
||||
"the MemWAL LSM scanner full-text search requires the FTS index on '{column}' to be maintained by the write spec (LsmWriteSpec::with_maintained_indexes); otherwise un-compacted documents are omitted. set use_lsm(false) to read the base table only"
|
||||
"the MemWAL LSM scanner full-text search requires the FTS index on '{column}' to be maintained by the write spec (LsmWriteSpec::with_maintained_indexes) and carried by every resident MemTable; otherwise un-compacted documents are omitted. set use_lsm(false) to read the base table only"
|
||||
),
|
||||
});
|
||||
}
|
||||
@@ -493,6 +490,27 @@ async fn fts_plan(
|
||||
Ok(scanner.create_plan().await?)
|
||||
}
|
||||
|
||||
/// Whether the spec maintains the index named `name`.
|
||||
///
|
||||
/// An unnamed set names nothing and covers everything, so the stored list alone
|
||||
/// cannot answer this.
|
||||
fn spec_maintains(details: &MemWalIndexDetails, name: &str) -> bool {
|
||||
details.maintain_all_indexes || details.maintained_indexes.iter().any(|n| n == name)
|
||||
}
|
||||
|
||||
/// Whether every resident MemTable carries the index an arm needs.
|
||||
///
|
||||
/// The spec is intent; a MemTable built before the index joined the set
|
||||
/// contributes nothing to an indexed read, so its rows would go missing.
|
||||
fn resident_memtables_carry(
|
||||
in_memory: &HashMap<Uuid, InMemoryMemTables>,
|
||||
carries: impl Fn(&InMemoryMemTableRef) -> bool,
|
||||
) -> bool {
|
||||
in_memory
|
||||
.values()
|
||||
.all(|tables| carries(&tables.active) && tables.frozen.iter().all(&carries))
|
||||
}
|
||||
|
||||
/// Whether an index of `type_url_suffix` covering `column` is in the MemWAL spec's
|
||||
/// maintained set. Only a maintained index has its catch-up tracked (so exclusion is
|
||||
/// gated correctly) and its in-memory arm kept current; an unmaintained base index
|
||||
@@ -502,7 +520,7 @@ async fn fts_plan(
|
||||
async fn index_maintained(
|
||||
dataset: &Dataset,
|
||||
column: &str,
|
||||
maintained: &[String],
|
||||
details: &MemWalIndexDetails,
|
||||
type_url_suffix: &str,
|
||||
) -> Result<bool> {
|
||||
use lance::index::DatasetIndexExt;
|
||||
@@ -512,7 +530,7 @@ async fn index_maintained(
|
||||
let indices = dataset.load_indices().await?;
|
||||
Ok(indices.iter().any(|idx| {
|
||||
idx.fields.contains(&field.id)
|
||||
&& maintained.iter().any(|m| m == &idx.name)
|
||||
&& spec_maintains(details, &idx.name)
|
||||
&& idx
|
||||
.index_details
|
||||
.as_ref()
|
||||
@@ -583,9 +601,7 @@ async fn arm_maintained_index_names(
|
||||
})
|
||||
.map(|idx| idx.name.clone())
|
||||
.collect();
|
||||
if let Some(name) =
|
||||
resolve_single_index(segment_names, &details.maintained_indexes, arm, &column)?
|
||||
{
|
||||
if let Some(name) = resolve_single_index(segment_names, details, arm, &column)? {
|
||||
names.push(name);
|
||||
}
|
||||
}
|
||||
@@ -604,7 +620,7 @@ async fn arm_maintained_index_names(
|
||||
/// compaction watermark).
|
||||
fn resolve_single_index(
|
||||
mut names: Vec<String>,
|
||||
maintained: &[String],
|
||||
details: &MemWalIndexDetails,
|
||||
arm: &str,
|
||||
column: &str,
|
||||
) -> Result<Option<String>> {
|
||||
@@ -620,7 +636,7 @@ fn resolve_single_index(
|
||||
Ok(names
|
||||
.into_iter()
|
||||
.next()
|
||||
.filter(|name| maintained.contains(name)))
|
||||
.filter(|name| spec_maintains(details, name)))
|
||||
}
|
||||
|
||||
/// Drop the primary-key columns Lance appends internally for dedup when the user's
|
||||
@@ -692,17 +708,14 @@ async fn vector_plan(
|
||||
// maintained, its catch-up is untracked and exclusion falls back to the
|
||||
// compaction watermark — dropping compacted SSTables the (lagging) base index has
|
||||
// not re-indexed. Reject rather than silently omit rows, mirroring the FTS arm.
|
||||
if !index_maintained(
|
||||
dataset,
|
||||
&column,
|
||||
&details.maintained_indexes,
|
||||
"VectorIndexDetails",
|
||||
)
|
||||
.await?
|
||||
if !index_maintained(dataset, &column, details, "VectorIndexDetails").await?
|
||||
|| !resident_memtables_carry(&in_memory, |memtable| {
|
||||
memtable.index_store.get_hnsw_by_column(&column).is_some()
|
||||
})
|
||||
{
|
||||
return Err(Error::NotSupported {
|
||||
message: format!(
|
||||
"the MemWAL LSM scanner requires the vector index on '{column}' to be maintained by the write spec (LsmWriteSpec::with_maintained_indexes); otherwise compacted rows not yet re-indexed are omitted. set use_lsm(false) to read the base table only"
|
||||
"the MemWAL LSM scanner requires the vector index on '{column}' to be maintained by the write spec (LsmWriteSpec::with_maintained_indexes) and carried by every resident MemTable; otherwise compacted rows not yet re-indexed are omitted. set use_lsm(false) to read the base table only"
|
||||
),
|
||||
});
|
||||
}
|
||||
@@ -888,7 +901,10 @@ mod tests {
|
||||
|
||||
#[test]
|
||||
fn resolve_single_index_dedupes_segments() {
|
||||
let maintained = vec!["fts_idx".to_string()];
|
||||
let maintained = MemWalIndexDetails {
|
||||
maintained_indexes: vec!["fts_idx".to_string()],
|
||||
..Default::default()
|
||||
};
|
||||
// Two physical segments of ONE logical index must not count as "multiple".
|
||||
assert_eq!(
|
||||
resolve_single_index(
|
||||
@@ -917,4 +933,33 @@ mod tests {
|
||||
None
|
||||
);
|
||||
}
|
||||
|
||||
/// A spec that maintains every index names none of them, so the stored list
|
||||
/// is empty while every index on the table is in fact maintained. Reading
|
||||
/// the list alone would refuse the read path on the default spec.
|
||||
#[test]
|
||||
fn an_unnamed_set_maintains_every_index() {
|
||||
let all = MemWalIndexDetails {
|
||||
maintained_indexes: Vec::new(),
|
||||
maintain_all_indexes: true,
|
||||
..Default::default()
|
||||
};
|
||||
assert!(spec_maintains(&all, "fts_idx"));
|
||||
assert_eq!(
|
||||
resolve_single_index(vec!["fts_idx".to_string()], &all, "full-text", "text").unwrap(),
|
||||
Some("fts_idx".to_string()),
|
||||
);
|
||||
|
||||
// The same empty list without the flag maintains nothing.
|
||||
let none = MemWalIndexDetails {
|
||||
maintained_indexes: Vec::new(),
|
||||
maintain_all_indexes: false,
|
||||
..Default::default()
|
||||
};
|
||||
assert!(!spec_maintains(&none, "fts_idx"));
|
||||
assert_eq!(
|
||||
resolve_single_index(vec!["fts_idx".to_string()], &none, "full-text", "text").unwrap(),
|
||||
None,
|
||||
);
|
||||
}
|
||||
}
|
||||
|
||||
Reference in New Issue
Block a user