86641f72df
Merge pull request #3029 from quickwit-oss/trinity.pointard/get-ff-tokenizer-comeback
...
reintroduce get_fast_field_tokenizer_name
2026-08-04 21:04:46 +02:00
0743fe7d67
reintroduce get_fast_field_tokenizer_name
2026-08-04 18:24:15 +02:00
bc225eecdf
rename bench name
2026-08-04 13:23:19 +02:00
83ffe96189
Reuse existing term ordinals for multi-terms missing values
...
Map a configured string missing value to its dictionary ordinal when the
term is already present. This coalesces real and missing documents before
the segment-level cutoff, preserving counts and sub-aggregation results.
Keep synthetic sentinels for absent terms and non-string columns, and add
regression coverage with a segment size of one.
2026-08-04 13:23:19 +02:00
92fd5c5cde
Refactor multi-term key collection paths
...
Extract full and non-full field key construction into dedicated helpers.
Rename the surviving document buffer and avoid copying IDs on the full-field path.
2026-08-04 13:23:19 +02:00
c9bf057162
Skip unreachable multi-term missing handling
...
Omit missing accessors when any physical column is full because the logical
field cannot be absent.
2026-08-04 13:23:19 +02:00
e77c256f01
simpler missing algorithm
2026-08-04 13:23:19 +02:00
1bfdf14415
restore TODO
2026-08-04 13:23:19 +02:00
21bb20ff1a
better clustering algorithm
2026-08-04 13:23:19 +02:00
16f38f6a64
refactor
2026-08-04 13:23:19 +02:00
d3abc9a0b3
simplify
2026-08-04 13:23:19 +02:00
17de33d8f0
merge multi-terms code
2026-08-04 13:23:19 +02:00
09e869dae1
refactor benches
2026-08-04 13:23:19 +02:00
295d5e4aa8
fix merge
2026-08-04 13:23:19 +02:00
90ff347cc9
move impl
2026-08-04 13:23:19 +02:00
766454d32a
improve naming
2026-08-04 13:23:19 +02:00
3010dbb8ea
Optimize sparse multi-terms collection
...
Filter documents without values after each single-valued field so later
decoding and key construction only process viable documents. Use exact
block lengths to validate aligned results and keep unsupported missing-value
combinations on the general path.
2026-08-04 13:23:19 +02:00
864a1d4b2d
improve missing performance
2026-08-04 13:23:19 +02:00
3e4cb34bfd
add missing to benchmark
2026-08-04 13:23:19 +02:00
2d1ddca54d
fmt
2026-08-04 13:23:19 +02:00
f1efd748fa
cleanup
2026-08-04 13:23:19 +02:00
164f62c4cc
Simplify optional multi-terms document filtering
...
Track valid document positions in a reusable bitset instead of compacting
parallel document and index buffers after each optional field. Decode each
field against the original block and consult the mask before writing keys or
populating buckets.
This favors simpler collection logic over shrinking later sparse decodes.
2026-08-04 13:23:19 +02:00
035fbe4d47
Refactor multi-terms collection around typed key codecs
...
Fan out dynamic/JSON physical column combinations during aggregation tree
construction so each segment collector handles one typed accessor per
field and applies missing values exactly once.
Use a generic key codec and shared term bucket maps for both packed and
unpacked keys. Keep optional and multivalued fields eligible for packed
storage, short-circuit sparse documents, and account for spilled composite
keys.
2026-08-04 13:23:19 +02:00
95e8760050
columnar storage - add batched rank
2026-08-04 13:23:19 +02:00
3cdc15e8b6
add filtered benchmark
2026-08-04 13:23:19 +02:00
f72044faf9
more benchmarks to compare
2026-08-04 13:23:19 +02:00
2d91c31468
rename vars
2026-08-04 13:23:19 +02:00
59b6859c16
move term req data to collector
2026-08-04 13:23:19 +02:00
5c1937a1ec
rename agg benches
2026-08-04 13:23:19 +02:00
9bcd99c396
rustfmt
2026-08-04 13:23:19 +02:00
d6666d09f3
extract per-field fast-path compatiblity check
2026-08-04 13:23:19 +02:00
8af115f802
decode column once per doc max
2026-08-04 13:23:19 +02:00
2f477e9414
more codex review
2026-08-04 13:23:19 +02:00
1fcf935f5c
fix handling of bytes for cardinality agg
2026-08-04 13:23:19 +02:00
73010f4d86
codex review
2026-08-04 13:23:19 +02:00
53d7af7b50
rustfmt
2026-08-04 13:23:19 +02:00
901af02fe0
fix bool serialization
2026-08-04 13:23:19 +02:00
9a3b4f3a8a
first pass of optimising multi-terms agg
2026-08-04 13:23:19 +02:00
261c0a11d4
allow extracting values from IntermediateMultiTermsBucketResult
2026-08-04 13:23:19 +02:00
ebd37278ca
first swab at multi-terms impl
2026-08-04 13:23:19 +02:00
2b9ba006b8
test: exercise parsed exists queries against documents
2026-08-03 12:14:51 +02:00
e1bc31e27e
docs: document exists query syntax
2026-08-03 12:14:51 +02:00
276740bed4
feat: PR review suggestion
...
Signed-off-by: Darkheir <raphael.cohen@sekoia.io >
2026-08-03 12:14:51 +02:00
f981e6e1f1
feat: Add support for Exists leaf in query parser
...
Signed-off-by: Darkheir <raphael.cohen@sekoia.io >
2026-08-03 12:14:51 +02:00
3bb9a430dd
Refactoring TextFastFieldOptions ( #3020 )
...
Co-authored-by: Paul Masurel <paul.masurel@datadoghq.com >
2026-08-02 17:17:02 +02:00
667132fa7a
rename to WithLanes
2026-07-29 08:57:54 +02:00
95f2c0c5b6
Optimize low-cardinality term aggregation counters
2026-07-29 08:57:54 +02:00
bb049ee714
default REUSE_AGG_BENCH_INDEX to true
2026-07-29 08:57:54 +02:00
277e59776b
Extend Vec term storage to 20k with eager/lazy bucket ids
...
Raise MAX_NUM_TERMS_FOR_VEC to 20_000 so the dense Vec term storage
(direct-indexed, no hashing/paging) is used for low/moderate cardinality
both with and without sub-aggregations, not just the <100 low-card case.
Split the old single threshold into MAX_NUM_TERMS_FOR_LOWCARD_SUBAGG (100,
still gates the Vec + LowCard-buffer pairing) and MAX_NUM_TERMS_FOR_VEC.
VecTermBuckets is now generic over a compile-time `const LAZY: bool`:
- eager (default): assigns all ids up front in `new`, branchless term_entry
- lazy: assigns on first occurrence, keeping the sub-agg bucket range down
to the terms that actually occur (no blowup for sparse ordinal spaces)
A new BucketIdSlot::ASSIGNS_ID const plus the LAZY const fully gate the
first-seen branch out at monomorphization, so the only branchy path is the
deliberately-lazy <BucketId, true> instantiation. The with-sub-agg Vec path
picks eager below MAX_NUM_TERMS_FOR_EAGER_BUCKET_IDS (4096) and lazy above,
avoiding the ~6-11% hot-loop regression eager fixes while keeping large
sparse cases compact.
Biggest impact on terms_zipf_1000_only with -40%
```
full
terms_7 Memory: 46.5 KB Avg: 2.3566ms (+4.29%) Median: 2.3566ms (+4.29%) [2.3566ms .. 2.3566ms]
terms_all_unique Memory: 11.5 MB Avg: 4.8532ms (-5.74%) Median: 4.8532ms (-5.74%) [4.8532ms .. 4.8532ms]
terms_all_unique_order_by_key Memory: 11.5 MB Avg: 4.8448ms (-0.53%) Median: 4.8448ms (-0.53%) [4.8448ms .. 4.8448ms]
terms_150_000 Memory: 2.7 MB Avg: 5.5295ms (+0.64%) Median: 5.5295ms (+0.64%) [5.5295ms .. 5.5295ms]
terms_many_top_1000 Memory: 5.3 MB Avg: 8.4738ms (+0.58%) Median: 8.4738ms (+0.58%) [8.4738ms .. 8.4738ms]
terms_many_order_by_term Memory: 2.7 MB (-0.01%) Avg: 4.5959ms (-0.15%) Median: 4.5959ms (-0.15%) [4.5959ms .. 4.5959ms]
terms_many_with_top_hits Memory: 48.9 MB (-0.00%) Avg: 85.8206ms (-5.46%) Median: 85.8206ms (-5.46%) [85.8206ms .. 85.8206ms]
terms_all_unique_with_avg_sub_agg Memory: 54.7 MB (-0.00%) Avg: 17.8747ms (+8.16%) Median: 17.8747ms (+8.16%) [17.8747ms .. 17.8747ms]
terms_many_with_avg_sub_agg Memory: 13.5 MB (-0.00%) Avg: 14.7797ms (+2.54%) Median: 14.7797ms (+2.54%) [14.7797ms .. 14.7797ms]
terms_status_with_avg_sub_agg Memory: 92.1 KB (-0.35%) Avg: 5.1467ms (+0.72%) Median: 5.1467ms (+0.72%) [5.1467ms .. 5.1467ms]
terms_status_with_terms_zipf_1000_sub_agg Memory: 213.2 KB Avg: 3.9576ms (-2.73%) Median: 3.9576ms (-2.73%) [3.9576ms .. 3.9576ms]
terms_zipf_1000_with_terms_status_sub_agg Memory: 726.5 KB (+0.28%) Avg: 12.1432ms (+3.30%) Median: 12.1432ms (+3.30%) [12.1432ms .. 12.1432ms]
terms_status_with_histogram Memory: 139.0 KB Avg: 2.4717ms (+2.45%) Median: 2.4717ms (+2.45%) [2.4717ms .. 2.4717ms]
terms_status_with_date_histogram Memory: 145.9 KB Avg: 2.3644ms (-0.44%) Median: 2.3644ms (-0.44%) [2.3644ms .. 2.3644ms]
terms_status_with_date_histogram_hard_bounds Memory: 145.4 KB Avg: 2.5705ms (+4.70%) Median: 2.5705ms (+4.70%) [2.5705ms .. 2.5705ms]
terms_status_with_date_histogram_and_sibling_terms Memory: 143.3 KB Avg: 3.8946ms (+1.61%) Median: 3.8946ms (+1.61%) [3.8946ms .. 3.8946ms]
terms_zipf_1000_only Memory: 75.8 KB (-0.02%) Avg: 1.2684ms (-41.50%) Median: 1.2684ms (-41.50%) [1.2684ms .. 1.2684ms]
terms_zipf_1000_with_histogram Memory: 1.2 MB (+0.17%) Avg: 20.9323ms (+4.08%) Median: 20.9323ms (+4.08%) [20.9323ms .. 20.9323ms]
terms_zipf_1000_with_avg_sub_agg Memory: 486.7 KB (+2.95%) Avg: 8.5297ms (-1.66%) Median: 8.5297ms (-1.66%) [8.5297ms .. 8.5297ms]
terms_many_json_mixed_type_with_avg_sub_agg Memory: 17.9 MB Avg: 27.0210ms (+1.81%) Median: 27.0210ms (+1.81%) [27.0210ms .. 27.0210ms]
terms_status_with_cardinality_agg Memory: 93.9 KB Avg: 3.2022ms (-0.64%) Median: 3.2022ms (-0.64%) [3.2022ms .. 3.2022ms]
terms_100_buckets_with_cardinality_agg Memory: 9.8 MB (+0.31%) Avg: 49.3188ms (-1.70%) Median: 49.3188ms (-1.70%) [49.3188ms .. 49.3188ms]
terms_many_with_single_term_order_by_card Memory: 48.9 MB Avg: 77.2127ms (-5.02%) Median: 77.2127ms (-5.02%) [77.2127ms .. 77.2127ms]
terms_many_with_single_term_2_order_by_card Memory: 40.6 MB (-0.02%) Avg: 45.8004ms (-17.57%) Median: 45.8004ms (-17.57%) [45.8004ms .. 45.8004ms]
```
2026-07-27 18:00:37 +02:00
fc84c0f299
fix REUSE_AGG_BENCH_INDEX
2026-07-27 18:00:37 +02:00
trinity-1686a
Pascal Seitz
Darkheir
Paul Masurel
PSeitz