aboutsummaryrefslogtreecommitdiffstats
path: root/searchlib/src
Commit message (Collapse)AuthorAgeFilesLines
* Prettify printing of BenchmarkResult.Geir Storli2024-02-191-12/+19
|
* Analyze complex leaf and term search over attributes with fast-search.Geir Storli2024-02-161-116/+202
|
* Refactor and use auto instead of template argument.Geir Storli2024-02-151-23/+25
|
* Merge pull request #30276 from ↵Geir Storli2024-02-151-56/+264
|\ | | | | | | | | vespa-engine/geirst/analyze-search-in-attributes-without-fast-search Analyze term search in attributes without fast-search.
| * Analyze term search in attributes without fast-search.Geir Storli2024-02-141-56/+264
| | | | | | | | | | This results in a breakdown of average "ms per cost" for the different attribute types, with suggestions on how the blueprint costs can be tuned to match the benchmark results.
* | Add search::predicate::SimpleIndexSaver.Tor Egge2024-02-1414-115/+163
|/ | | | Remove extra logging when saving predicate attribute.
* Merge pull request #30266 from ↵v8.305.17Geir Storli2024-02-1410-112/+261
|\ | | | | | | | | vespa-engine/toregge/add-data-buffer-buffer-writer Add search::DataBufferWriter.
| * Add class comment for search::predicate::DocumentFeaturesStoreSaver.Tor Egge2024-02-141-0/+4
| |
| * Add search::DataBufferWriter.Tor Egge2024-02-1410-112/+257
| | | | | | | | | | Add search::predicate::DocumentFeatureStoreSaver. Use search::BufferWriter API when saving document feature store.
* | Merge pull request #30263 from ↵Geir Storli2024-02-1413-24/+141
|\ \ | |/ |/| | | | | vespa-engine/havardpe/baseline-flow-stats-for-complex-leafs baseline flow stats for complex leafs
| * baseline flow stats for complex leafsHåvard Pettersen2024-02-1313-24/+141
| |
* | Merge pull request #30260 from ↵Tor Egge2024-02-134-104/+244
|\ \ | |/ |/| | | | | vespa-engine/toregge/use-array-store-in-search-predicate-document-features-store Use array store in search::predicate::DocumentFeaturesStore.
| * Remove unused typedefs and includes.Tor Egge2024-02-132-6/+0
| |
| * Use array store in search::predicate::DocumentFeaturesStore.Tor Egge2024-02-134-98/+244
| |
* | Merge pull request #30255 from vespa-engine/geirst/extend-iterator-benchmarkGeir Storli2024-02-131-46/+79
|\ \ | |/ |/| Extend search iterator benchmark program
| * Use search iterator class name directly.Geir Storli2024-02-131-13/+2
| |
| * Add name of the search iterator in a benchmark result.Geir Storli2024-02-131-6/+19
| |
| * Support AND operator and reduce the time for populating attributes.Geir Storli2024-02-131-41/+72
| |
* | Merge pull request #30243 from vespa-engine/havardpe/better-or-flow-statsGeir Storli2024-02-135-121/+166
|\ \ | |/ |/| account for heap cost in strict OR
| * account for heap cost in strict ORHåvard Pettersen2024-02-125-121/+166
| | | | | | | | | | | | | | | | - make it easier to do flow analysis directly on FlowStats - use FlowStats in tests (less custom test code) - added flow_tuning.h for special sauce - strict flow must now have in-flow of 1.0 - split low-level flow tests into full/partial
* | Remove dead code from search::predicate::DocumentFeaturesStore.Tor Egge2024-02-123-31/+1
| |
* | Add extra logging when saving predicate attribute.Tor Egge2024-02-127-10/+65
| |
* | Merge pull request #30234 from vespa-engine/balder/some-code-cleanupGeir Storli2024-02-123-20/+20
|\ \ | |/ |/| - DocId is an overloaded type already. Just use string as directly fo…
| * - DocId is an overloaded type already. Just use string as directly for ↵Henning Baldersheim2024-02-103-20/+20
| | | | | | | | | | | | readability. - Add noexcept and and using.
* | Add noexcept, remove virtual and use = defaultHenning Baldersheim2024-02-122-13/+7
| |
* | - Drop the optimization from long to int and just use long throughout.Henning Baldersheim2024-02-101-1/+1
|/ | | | - That enables that numeric hashes are also handled efficiently, without resorting to strings.
* Merge pull request #30231 from ↵Henning Baldersheim2024-02-091-2/+2
|\ | | | | | | | | vespa-engine/toregge/copy-interleaved-features-in-term-field-match-data Copy interleaved features in search::fef::TermFieldMatchData.
| * Copy interleaved features in search::fef::TermFieldMatchData.Tor Egge2024-02-091-2/+2
| |
* | Merge pull request #30229 from ↵Henning Baldersheim2024-02-0916-114/+554
|\ \ | | | | | | | | | | | | vespa-engine/toregge/handle-equiv-query-node-as-a-leaf-in-streaming-query-tree Handle search::streaming::EquivQueryNode as a leaf in the query tree.
| * | Use constexpr variables to make code somewhat readable.Tor Egge2024-02-091-30/+58
| | |
| * | Reduce code duplication.Tor Egge2024-02-095-154/+107
| | |
| * | Handle search::streaming::EquivQueryNode as a leaf in the query tree.Tor Egge2024-02-0914-31/+490
| |/
* | Merge pull request #30232 from vespa-engine/havardpe/more-insightHåvard Pettersen2024-02-093-10/+58
|\ \ | | | | | | benchmark effect of being strict in a non-strict context
| * | benchmark effect of being strict in a non-strict contextHåvard Pettersen2024-02-093-10/+58
| | |
* | | Use smaller buffer for reading file headers. And GC some unused code.Henning Baldersheim2024-02-0910-41/+29
| |/ |/|
* | Require non-empty fieldsHenning Baldersheim2024-02-081-20/+22
| |
* | - Complete dumping of 1 index field before progressing to the next.Henning Baldersheim2024-02-0813-316/+267
|/ | | | | - This prevents allocating memory buffers, and file descriptors for all fields concurrently. - It will reduce memory footprint during flush if there are many fields.
* Add low-level benchmark program for search iterators.Geir Storli2024-02-084-10/+413
| | | | | Currently, it can benchmark the following query operators over an attribute vector: Single term, In, WeightedSet, DotProduct, Or.
* Merge pull request #30211 from vespa-engine/havardpe/more-benchmarkingv8.301.19Geir Storli2024-02-072-31/+133
|\ | | | | benchmark non-strict iterators
| * benchmark non-strict iteratorsHåvard Pettersen2024-02-072-31/+133
| | | | | | | | | | measure ns per seek also calculate experimental flow stats and calculate ms per cost
* | Track number of active nodes in hnsw graph.Tor Egge2024-02-076-6/+61
|/
* Merge pull request #30202 from ↵v8.300.15Henning Baldersheim2024-02-061-5/+5
|\ | | | | | | | | vespa-engine/toregge/stop-getting-phrase-index-from-subterm-in-streaming-mode Stop getting phrase index from subterm in streaming mode.
| * Stop getting phrase index from subterm in streaming mode.Tor Egge2024-02-061-5/+5
| |
* | Merge pull request #30199 from vespa-engine/havardpe/explicit-flow-defaultsGeir Storli2024-02-0631-10/+152
|\ \ | |/ |/| make default flow stats more explicit
| * make default flow stats more explicitHåvard Pettersen2024-02-0631-10/+152
| | | | | | | | | | | | for both simple and complex leafs account for number of inner children in complex leafs account for seek nesting for complex leafs with children
* | Empty index => 'default' indexHenning Baldersheim2024-02-063-2/+5
| |
* | Handle search::streaming::PhraseQueryNode as a leaf in the query tree.Tor Egge2024-02-0610-107/+20
| |
* | Merge pull request #30185 from ↵Henning Baldersheim2024-02-0610-158/+182
|\ \ | |/ |/| | | | | vespa-engine/balder/symmetric-query-processing-docsum-time Balder/symmetric query processing docsum time
| * Add a short class description.Henning Baldersheim2024-02-061-0/+4
| |
| * Wire QueryNormalization in to JuniperQueryAdapter and use it there.Henning Baldersheim2024-02-057-131/+121
| |