* Unify parking_lot/arc_lock feature
* Move lib/common/{io,memory}/* -> lib/common/common/*
- Mmap-related items are grouped into `common::mmap` sub-module:
- `memory/src/chunked_utils.rs` -> `common/src/mmap/chunked.rs`
- `memory/src/madvise.rs` -> `common/src/mmap/advice.rs`
- `memory/src/mmap_ops.rs` -> `common/src/mmap/ops.rs`
- `memory/src/mmap_type_readonly.rs` -> `common/src/mmap/mmap_readonly.rs`
- `memory/src/mmap_type.rs` -> `common/src/mmap/mmap_rw.rs`
- Filesystem-related items are grouped into `common::fs` sub-module:
- `common/src/fs.rs` -> `common/src/fs/sync.rs`
- `io/src/file_operations.rs` -> `common/src/fs/ops.rs`
- `io/src/move_files.rs` -> `common/src/fs/move.rs`
- `io/src/safe_delete.rs` -> `common/src/fs/safe_delete.rs`
- `memory/src/checkfs.rs` -> `common/src/fs/check.rs`
- `memory/src/fadvise.rs` -> `common/src/fs/fadvise.rs`
- Rest is moved straight into `common`:
- `io/src/storage_version.rs` -> `common/src/storage_version.rs`
The old `io` and `memory` are now hollow crates that re-export items
from `common`. These hollow crates will be removed in next commits.
* Replace uses of `io` and `memory` with new paths in `common`
Since `io` and `memory` are just re-exports of `common`, these
replacements are no-op.
* Remove `io` and `memory` crates
* Split `SegmentEntry`
Add `ImmutableSegmentEntry` for operations that can be applied to
immutable segments, and make the `SegmentEntry` as it subtrait.
* Rename to `NonAppendableSegmentEntry`
It differs semantically from `ImmutableSegmentEntry` by allowing point
deletion. Move point deletion to the trait too.
* Fix docstring
* use NonAppendableSegmentEntry where possible
---------
Co-authored-by: Andrey Vasnetsov <andrey@vasnetsov.com>
* download tar
* compute sha256 for stream download
* wip: propagate unpacking into down to the logic, todo: validation
* unpacked snapshot validation
* Minor tweaks
* Fix typo
* validation during unpack
* cancellation token
* update docstring
* remove redundant dep
* Rearrange unpack functions
- Rename `safe_unpack.rs` into `tar_unpack.rs` so it would be listed
near `tar_ext.rs` in IDEs.
- Replace calls like `ar = open_snapshot_archive(…); safe_unpack(ar, …);`
with a single call to `tar_unpack_file(…)`.
- Put calls to `Archive::new(); Archive::set_overwrite(false);` inside
`tar_unpack_reader` (was `safe_unpack`). So, now it is the only place
that does `set_overwrite`.
* Let clippy complain if tar::Archive::unpack used
* Mock snapshot download URL
Instead of downloading from storage.googleapis.com every time the test
runs, put small snapshot file to the repo.
The snapshot file is created using this command:
curl -s \
https://storage.googleapis.com/qdrant-benchmark-snapshots/test-shard.snapshot \
| tar \
--delete segments/4ea958d8-0b64-4312-9a53-0cd857e93535.tar \
--delete segments/65ac6276-8cca-4f5c-b767-9722190cee8b.tar \
> lib/storage/src/content_manager/snapshots/test-shard.snapshot
File contents:
$ tar tf lib/storage/src/content_manager/snapshots/test-shard.snapshot
wal/
wal/closed-255
newest_clocks.json
replica_state.json
shard_config.json
$ du -sh lib/storage/src/content_manager/snapshots/test-shard.snapshot
12K lib/storage/src/content_manager/snapshots/test-shard.snapshot
$ sha256sum < lib/storage/src/content_manager/snapshots/test-shard.snapshot
5d94eac5c1ede3994a28bc406120046c37370d5d45b489a0d2252531b4e3e1f2 -
---------
Co-authored-by: timvisee <tim@visee.me>
Co-authored-by: xzfc <xzfcpw@gmail.com>
* WIP: introduce new vector store type
* handling of InRamMmap
* fmt
* feature-flag
* fmt
* Use if else
Co-authored-by: Roman Titov <ffuugoo@users.noreply.github.com>
* Update lib/common/common/src/flags.rs
Co-authored-by: Tim Visée <tim+github@visee.me>
* also choose madvise for single-file in-ram-mmap
* simplify generics
* gpu fix
* fix bug
---------
Co-authored-by: Tim Visée <tim+github@visee.me>
Co-authored-by: Roman Titov <ffuugoo@users.noreply.github.com>
* feat: Add enable_hnsw option for payload field indexes
Add optional enable_hnsw parameter to all payload index types to control
whether additional HNSW graph links are built for each indexed field.
- Add enable_hnsw field to all 8 payload index param types
- Update gRPC proto definitions and conversions
- Update OpenAPI schema
- Modify HNSW graph builder to respect enable_hnsw flag
- Add enable_hnsw() helper methods to PayloadSchemaParams and PayloadFieldSchema
- Update all tests to include new field (default: None)
When enable_hnsw is true and payload_M > 0, additional HNSW links will
be built for the payload field. Default value is true for backward compatibility.
* Fix Some format problems
* fix: address comment problem
---------
Co-authored-by: EC2 Default User <ec2-user@ip-10-78-171-148.ec2.internal>
* Replace `Option<Segment>` with `enum LoadSegmentOutcome`
* Replace some Path/PathBuf with str/String
* Rename field Segment::{current_path -> segment_path}
* safe_delete
* Add progress_tracker.rs
* Pass progress tracker around
* Populate progress tracker with actual data
* Expose progress on `/collections/{name}/optimizations` endpoint
* add stopflag check into query_points of payload index
* propagate stopflag more
* fmt
* bench: compare better against no atomic
* use stoppable iter with IteratorExt
* clippy
* Add cancelled error helper
---------
Co-authored-by: Luis Cossío <luis.cossio@outlook.com>
Co-authored-by: timvisee <tim@visee.me>
* flush all segments in one thread sequentially
* bonus: move flush-related functions into dedicated file
* Minor comment tweaks
* await for flush on segment holder level
* fmt
* Minor improvement, preallocate vector for payload index flushers
* Remove invalid comment
---------
Co-authored-by: timvisee <tim@visee.me>
* WIP: make proxy segment non-appendable
* make deleted points and index changes private to Proxy Segment
* consistently remove empty unused segment from holder on unproxifying and the end of optimization
* remove/fix obsolete test
* Fix comment, some general adjustments
* Also don't remove non-original segments
* Use ahash for map of proxy index changes
* Inline format arguments
* Simplify has point branching
* Assert that proxy flushes to latest wrapped segment version
* make vector deletetion a CoW operation
* relax debug assertions
* Update lib/shard/src/proxy_segment/mod.rs
* fix test_partial_snapshot_empty
---------
Co-authored-by: timvisee <tim@visee.me>
Co-authored-by: Tim Visée <tim+github@visee.me>
* Create and load for an appendable quantization
remove feature flag
more todo
review remarks
review remarks
* fix after rebase
* Rename is_appendable to supports_appendable
---------
Co-authored-by: timvisee <tim@visee.me>
* Enable Gridstore payload index storage, rename storage types
* Respect payload_index_skip_mutable_rocksdb feature flag
* Minor cleanup
* Fix map payload index Gridstore semantics, only create files if desired
The semantics of backing storages in payload indices are inconsistent.
This aligns the Gridstore backing storage to our RocksDB backing
storage, matching the create/open/load behavior. Now, it will only
create Gridstore files on disk if we request it to do so.
This commit only implements it on the map index. In following comments
the same will be implemented in all other payload indices too.
* Apply same Gridstore semantics to other payload index types
* Rename create parameter to create_if_missing
* Fix bench compilation errors
* bq encodings
* are you happy clippy
* are you happy clippy
* are you happy clippy
* are you happy clippy
* gpu tests
* update models
* are you happy fmt
* move additional bits to the end
* fix tests
* Welford's Algorithm
* review remarks
* are you happy clippy
* remove debug println in test
* coderabit nitpicks
* remove unnecessary clone and partialeq
* Use f64 for Welford's Algorithm
* try fix ci
* revert cargo-nextest
* add debug assertions
* Use sparse vector storage fixture without RocksDB
* Fix some tests
* Replace RocksDB sparse storage with Gristore in mutable text index tests
* Use in-memory vector storage in multivector HNSW test
* Flag many more RocksDB specifics in tests
* Use database placeholder type without RocksDB flag
* Flag more tests
* Flag even more tests
* Fix imports, fix typo, and repair base test build
* Initialize dummy database if RocksDB flag is disabled
* Assert correct storage types
* Don't use old vector storage type when RocksDB is disabled
* Expos default for vector storage type only in tests
* Only expose simple segment constructor in tests
* Don't derive Default
* Fix inverted appendable flag
* Add function to open all multi dense vector storage types
* Move list files function into common crate
* Add function to find appendable multi dense storage files without opening it
* Actively migrate away from RocksDB based multi dense vector storage
* Add test for simple multi dense vector storage migration
* Also migrate vector deletes for multi dense storage
* take max_point_offset into consideration
* add null index even if index selector is for rocksdb
* fmt
* better cardinality estimation, check deleted inside filtered iter
* fix count indexed points, add primary conditions to estimator
* use len for count_indexed_points, adjust test
* remove deleted check from filtered iter
* cleaner removal
* Pass FeatureFlags into VectorIndexBuildArgs
* Incremental HNSW index building: append-only case
* Use debug_assert
* first_few_ids
* Check deleted_point_count
* Drop unused method
* Add in rest and grpc
* add to QueryEnum
* implement Query trait
* connect to scorer creation
* upd tests
* additional changes
* fmt
* gen openapi and grpc docs
* coderabbit fix
* add changes in async scorer
* test sum_scores in more places, refactor to remove repetition
* Cardinality estimation measurements
* Apply hw measurements to latest changes from dev
* Clippy
* Also measure cardinality estimation for geo index
* Make measured units 'bytes'
* Use PointOffsetType instead of u32 for size calculation
* fix memory cost for check_values_any in mmap index
* fix double counting for value reading in mmap, remove hw_counter from mmap hashmap
* fmt
* fix hw measurement for text index
* Remove non necessary lifetime annotations
---------
Co-authored-by: generall <andrey@vasnetsov.com>
* create initial strucutres
* clippy
* start field-query refactoring
* start field-query refactoring (2/N)
* start field-query refactoring (3/N): duplicate is_empty/null condiftions as field condition
* start field-query refactoring (4/N): re-instate is_empty fallback in case new index is not built yet
* filter for is_empty/is_null
* implement add/remove point
* upd schema
* open and create of null-index
* create null-index
* fix test
* Update lib/segment/src/index/query_optimization/condition_converter.rs
Co-authored-by: Tim Visée <tim+github@visee.me>
* unit test for null-index
* more unit tests
* add openapi tests
* fmt
* fix for integartion tests
* rabbit review fix
* make [null] non-empty
---------
Co-authored-by: Tim Visée <tim+github@visee.me>
* Bump Rust edition to 2024
* gen is a reserved keyword now
* Remove ref mut on references
* Mark extern C as unsafe
* Wrap unsafe function bodies in unsafe block
* Geo hash implements Copy, don't reference but pass by value instead
* Replace secluded self import with parent
* Update execute_cluster_read_operation with new match semantics
* Fix lifetime issue
* Replace map_or with is_none_or
* set_var is unsafe now
* Reformat
* rename cpu_budget -> resource_budget
* clippy
* add io budget to resources
* fmt
* move budget structures into a separate file
* add extend permit function
* dont extend existing permit
* switch from IO to CPU permit
* do not release resource before aquiring an extension
* fmt
* Review remarks
* Improve resource permit number assertion
* Make resource permit replace_with only acquire extra needed permits
* Remove obsolete drop implementation
* allocate IO budget same as CPU
* review fixes
---------
Co-authored-by: timvisee <tim@visee.me>
xzfc