Skip to content

feat(query): Inverted index support search Variant inner fields #18861

New issue

Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.

Sign up for GitHub

By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.

Already on GitHub? Sign in to your account

Merged
merged 2 commits into from
Oct 20, 2025
Merged

feat(query): Inverted index support search Variant inner fields #18861

Show file tree
Hide file tree
Changes from all commits
Commits
Show all changes
2 commits
Select commit Hold shift + click to select a range
7960533
feat(query): Inverted index support search Variant inner fields
b41sh Oct 17, 2025
a353c60
fix
b41sh Oct 19, 2025
File filter

Filter by extension

Filter by extension
Conversations
Failed to load comments.
Loading
Jump to
Jump to file
Failed to load files.
Loading
Diff view
Diff view
457 changes: 291 additions & 166 deletions Cargo.lock
View file
Open in desktop

Large diffs are not rendered by default.

12 changes: 6 additions & 6 deletions Cargo.toml
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -506,10 +506,10 @@ strum = "0.24.1"
sub-cache = "0.2.1"
sys-info = "0.9"
sysinfo = "0.34.2"
tantivy = "0.22.0"
tantivy-common = "0.7.0"
tantivy = "0.25.0"
tantivy-common = "0.10.0"
tantivy-fst = "0.5"
tantivy-jieba = "0.11.0"
tantivy-jieba = "0.17.0"
temp-env = "0.3.0"
tempfile = "3.4.0"
terminal_size = "0.4.2"
Expand Down Expand Up @@ -665,8 +665,8 @@ recursive = { git = "https://github.com/datafuse-extras/recursive.git", rev = "1
sled = { git = "https://github.com/datafuse-extras/sled", tag = "v0.34.7-datafuse.1" }
state-machine-api = { git = "https://github.com/databendlabs/state-machine-api.git", tag = "v0.3.4" }
sub-cache = { git = "https://github.com/databendlabs/sub-cache", tag = "v0.2.1" }
tantivy = { git = "https://github.com/datafuse-extras/tantivy", rev = "7502370" }
tantivy-common = { git = "https://github.com/datafuse-extras/tantivy", rev = "7502370", package = "tantivy-common" }
tantivy-jieba = { git = "https://github.com/datafuse-extras/tantivy-jieba", rev = "0e300e9" }
tantivy = { git = "https://github.com/datafuse-extras/tantivy", rev = "9065a4d" }
tantivy-common = { git = "https://github.com/datafuse-extras/tantivy", rev = "9065a4d", package = "tantivy-common" }
tantivy-jieba = { git = "https://github.com/datafuse-extras/tantivy-jieba", rev = "ac27464" }
watcher = { git = "https://github.com/databendlabs/watcher", tag = "v0.4.2" }
xorfilter-rs = { git = "https://github.com/datafuse-extras/xorfilter", tag = "databend-alpha.4" }
6 changes: 6 additions & 0 deletions src/common/metrics/src/metrics/storage.rs
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -174,6 +174,8 @@ static BLOCK_INVERTED_INDEX_GENERATE_MILLISECONDS: LazyLock<Histogram> = LazyLoc
static BLOCK_INVERTED_INDEX_READ_MILLISECONDS: LazyLock<Histogram> = LazyLock::new(|| {
register_histogram_in_milliseconds("fuse_block_inverted_index_read_milliseconds")
});
static BLOCK_INVERTED_INDEX_READ_BYTES: LazyLock<Counter> =
LazyLock::new(|| register_counter("fuse_block_inverted_index_read_bytes"));
static BLOCK_INVERTED_INDEX_SEARCH_MILLISECONDS: LazyLock<Histogram> = LazyLock::new(|| {
register_histogram_in_milliseconds("fuse_block_inverted_index_search_milliseconds")
});
Expand Down Expand Up @@ -602,6 +604,10 @@ pub fn metrics_inc_block_inverted_index_read_milliseconds(c: u64) {
BLOCK_INVERTED_INDEX_READ_MILLISECONDS.observe(c as f64);
}

pub fn metrics_inc_block_inverted_index_read_bytes(c: u64) {
BLOCK_INVERTED_INDEX_READ_BYTES.inc_by(c);
}

pub fn metrics_inc_block_inverted_index_search_milliseconds(c: u64) {
BLOCK_INVERTED_INDEX_SEARCH_MILLISECONDS.observe(c as f64);
}
Expand Down
4 changes: 2 additions & 2 deletions src/query/config/src/config.rs
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -3318,15 +3318,15 @@ pub struct CacheConfig {
#[clap(
long = "cache-inverted-index-meta-count",
value_name = "VALUE",
default_value = "3000"
default_value = "30000"
)]
pub inverted_index_meta_count: u64,

/// Max bytes of cached inverted index filters used. Set it to 0 to disable it.
#[clap(
long = "cache-inverted-index-filter-size",
value_name = "VALUE",
default_value = "2147483648"
default_value = "64424509440"
)]
pub inverted_index_filter_size: u64,

Expand Down
4 changes: 2 additions & 2 deletions src/query/config/src/inner.rs
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -756,8 +756,8 @@ impl Default for CacheConfig {
table_bloom_index_filter_size: 2147483648,
disk_cache_table_bloom_index_data_size: 0,
disk_cache_table_bloom_index_meta_size: 0,
inverted_index_meta_count: 3000,
inverted_index_filter_size: 2147483648,
inverted_index_meta_count: 30000,
inverted_index_filter_size: 64424509440,
inverted_index_filter_memory_ratio: 0,
vector_index_meta_count: 30000,
vector_index_filter_size: 64424509440,
Expand Down
2 changes: 1 addition & 1 deletion src/query/ee/tests/it/inverted_index/index_refresh.rs
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -160,7 +160,7 @@ async fn test_fuse_do_refresh_inverted_index() -> Result<()> {
let queries = vec![
("rust".to_string(), vec![0, 1]),
("java".to_string(), vec![2]),
("data".to_string(), vec![1, 4, 5]),
("data".to_string(), vec![4, 1, 5]),
];

for (query_text, ids) in queries.into_iter() {
Expand Down
34 changes: 18 additions & 16 deletions src/query/service/tests/it/storages/testdata/caches_table.txt
View file
Open in desktop
Original file line number Diff line number Diff line change
@@ -1,21 +1,23 @@
---------- TABLE INFO ------------
DB.Table: 'system'.'caches', Table: caches-table_id:1, ver:0, Engine: SystemCache
-------- TABLE CONTENTS ----------
+-------------+----------------------------------------------+----------+----------+------------+----------+----------+----------+----------+
| Column 0 | Column 1 | Column 2 | Column 3 | Column 4 | Column 5 | Column 6 | Column 7 | Column 8 |
+-------------+----------------------------------------------+----------+----------+------------+----------+----------+----------+----------+
| 'test-node' | 'memory_cache_bloom_index_file_meta_data' | 0 | 0 | 3000 | 'count' | 0 | 0 | 0 |
| 'test-node' | 'memory_cache_bloom_index_filter' | 0 | 0 | 2147483648 | 'bytes' | 0 | 0 | 0 |
| 'test-node' | 'memory_cache_column_oriented_segment_info' | 0 | 0 | 1073741824 | 'bytes' | 0 | 0 | 0 |
| 'test-node' | 'memory_cache_compact_segment_info' | 0 | 0 | 1073741824 | 'bytes' | 0 | 0 | 0 |
| 'test-node' | 'memory_cache_iceberg_table' | 0 | 0 | 1024 | 'count' | 0 | 0 | 0 |
| 'test-node' | 'memory_cache_inverted_index_file' | 0 | 0 | 2147483648 | 'bytes' | 0 | 0 | 0 |
| 'test-node' | 'memory_cache_inverted_index_file_meta_data' | 0 | 0 | 3000 | 'count' | 0 | 0 | 0 |
| 'test-node' | 'memory_cache_parquet_meta_data' | 0 | 0 | 3000 | 'count' | 0 | 0 | 0 |
| 'test-node' | 'memory_cache_prune_partitions' | 0 | 0 | 256 | 'count' | 0 | 0 | 0 |
| 'test-node' | 'memory_cache_segment_statistics' | 0 | 0 | 1073741824 | 'bytes' | 0 | 0 | 0 |
| 'test-node' | 'memory_cache_table_snapshot' | 0 | 0 | 256 | 'count' | 0 | 0 | 0 |
| 'test-node' | 'memory_cache_table_statistics' | 0 | 0 | 256 | 'count' | 0 | 0 | 0 |
+-------------+----------------------------------------------+----------+----------+------------+----------+----------+----------+----------+
+-------------+----------------------------------------------+----------+----------+-------------+----------+----------+----------+----------+
| Column 0 | Column 1 | Column 2 | Column 3 | Column 4 | Column 5 | Column 6 | Column 7 | Column 8 |
+-------------+----------------------------------------------+----------+----------+-------------+----------+----------+----------+----------+
| 'test-node' | 'memory_cache_bloom_index_file_meta_data' | 0 | 0 | 3000 | 'count' | 0 | 0 | 0 |
| 'test-node' | 'memory_cache_bloom_index_filter' | 0 | 0 | 2147483648 | 'bytes' | 0 | 0 | 0 |
| 'test-node' | 'memory_cache_column_oriented_segment_info' | 0 | 0 | 1073741824 | 'bytes' | 0 | 0 | 0 |
| 'test-node' | 'memory_cache_compact_segment_info' | 0 | 0 | 1073741824 | 'bytes' | 0 | 0 | 0 |
| 'test-node' | 'memory_cache_iceberg_table' | 0 | 0 | 1024 | 'count' | 0 | 0 | 0 |
| 'test-node' | 'memory_cache_inverted_index_file' | 0 | 0 | 64424509440 | 'bytes' | 0 | 0 | 0 |
| 'test-node' | 'memory_cache_inverted_index_file_meta_data' | 0 | 0 | 30000 | 'count' | 0 | 0 | 0 |
| 'test-node' | 'memory_cache_parquet_meta_data' | 0 | 0 | 3000 | 'count' | 0 | 0 | 0 |
| 'test-node' | 'memory_cache_prune_partitions' | 0 | 0 | 256 | 'count' | 0 | 0 | 0 |
| 'test-node' | 'memory_cache_segment_statistics' | 0 | 0 | 1073741824 | 'bytes' | 0 | 0 | 0 |
| 'test-node' | 'memory_cache_table_snapshot' | 0 | 0 | 256 | 'count' | 0 | 0 | 0 |
| 'test-node' | 'memory_cache_table_statistics' | 0 | 0 | 256 | 'count' | 0 | 0 | 0 |
| 'test-node' | 'memory_cache_vector_index_file' | 0 | 0 | 64424509440 | 'bytes' | 0 | 0 | 0 |
| 'test-node' | 'memory_cache_vector_index_file_meta_data' | 0 | 0 | 30000 | 'count' | 0 | 0 | 0 |
+-------------+----------------------------------------------+----------+----------+-------------+----------+----------+----------+----------+


4 changes: 2 additions & 2 deletions src/query/service/tests/it/storages/testdata/configs_table_basic.txt
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -17,8 +17,8 @@ DB.Table: 'system'.'configs', Table: configs-table_id:1, ver:0, Engine: SystemCo
| 'cache' | 'enable_table_meta_cache' | 'true' | '' |
| 'cache' | 'iceberg_table_meta_count' | '1024' | '' |
| 'cache' | 'inverted_index_filter_memory_ratio' | '0' | '' |
| 'cache' | 'inverted_index_filter_size' | '2147483648' | '' |
| 'cache' | 'inverted_index_meta_count' | '3000' | '' |
| 'cache' | 'inverted_index_filter_size' | '64424509440' | '' |
| 'cache' | 'inverted_index_meta_count' | '30000' | '' |
| 'cache' | 'meta_service_ownership_cache' | 'false' | '' |
| 'cache' | 'segment_block_metas_count' | '0' | '' |
| 'cache' | 'segment_statistics_bytes' | '1073741824' | '' |
Expand Down
1 change: 1 addition & 0 deletions src/query/storages/common/index/Cargo.toml
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -22,6 +22,7 @@ bitvec = { workspace = true }
bytemuck = { workspace = true }
bytes = { workspace = true }
cbordata = { workspace = true }
crc32fast = { workspace = true }
fastrace = { workspace = true }
feistel-permutation-rs = { workspace = true }
goldenfile = { workspace = true }
Expand Down
Loading