* feat: global quota API
Memory and disk are node-wide resources, so configuring their thresholds
per collection through strict mode makes little sense. Move them behind a
single cluster-wide `QuotaManager`.
The quota config is seeded from `storage.quotas` in the settings (and so
from env vars), overridden by `quota.json` in the storage directory, and
updated cluster-wide through a new `SetQuotaConfig` consensus operation
which rewrites that file on every peer. Raft snapshots carry it too, so a
peer that joins by snapshot picks it up.
Quotas are enforced wherever the strict mode memory and disk checks used
to run, but no longer gated behind `strict_mode.enabled`: a value set in
an enabled strict mode config still wins per resource, the quota is the
default. Rejections name both the condition that tripped and the config
that governs it.
`GET /quotas` reports the config plus current utilization to global read
users; `PUT /quotas` replaces it for global manage users.
Co-Authored-By: Claude Opus 5 (1M context) <noreply@anthropic.com>
* fix: cover the quota endpoints in the API consistency checks
`test_all_rest_endpoints_are_covered` and the OpenAPI endpoint count both
break on any new REST endpoint. Add `GET`/`PUT /quotas` to `ACTION_ACCESS`
with their JWT access tests, and bump the expected API count. The quota
endpoints stay out of `REST_ENDPOINT_WHITELIST`: that list is for
data-plane endpoints reported per-endpoint in metrics.
Also add a Raft snapshot CBOR compatibility test — snapshots are exchanged
between peers of different versions during a rolling upgrade, so
`quota_config` must be absent-tolerant in both directions.
Review feedback: persist through `SaveOnDisk`, which already implements the
write-before-swap protocol this was doing by hand; validate the config at
both persistence boundaries, since a hand-edited quota file or a config
arriving through consensus does not pass the REST handler's validation, and
a `0%` limit would reject every update forever.
Co-Authored-By: Claude Opus 5 (1M context) <noreply@anthropic.com>
* test: assert seeding a quota from invalid settings persists nothing
Follow-up to review feedback claiming `SaveOnDisk::load_or_init` writes the
init value before it is validated. It does not — only `SaveOnDisk::new`
persists — but the property matters: were seeding to persist first, invalid
settings would leave a `quota.json` that fails validation on every
subsequent start, and the node could only be recovered by deleting it by
hand. Pin it down with a test.
Co-Authored-By: Claude Opus 5 (1M context) <noreply@anthropic.com>
* refactor: make QuotaManager the single reader of memory and disk
The quota checks measured memory and disk themselves, while the optimizer
and the WAL disk watcher each called `fs4::available_space` behind their
own ad-hoc caches. Fold all of it into QuotaManager: it owns the readings,
the freshness policy, and the limits they are compared against.
Moves the module to `lib/shard`, since the optimizer sits below `storage`
and has to reach it; `storage::quota` re-exports it, so consensus, the
`/quotas` API and StorageConfig are unchanged. The manager is installed as
a process singleton by TableOfContent, ahead of loading any collection.
- Callers hand in QuotaLimits overrides instead of a StrictModeConfig, and
an override can now only tighten. A collection-level admin could raise
`max_disk_usage_percent` past a cluster-wide limit that needed global
manage rights to set; ties resolve to the quota so the rejection names
the knob that actually has to change.
- Measurements are cached for 5s, but a reading at or above its limit is
never reused: a rejected client retries, and freeing the resource has to
take effect on the next request rather than a TTL later.
- `fits_on_disk` sizes an optimization against physical free space only,
never the configured limits. Optimizations are what free a full disk, so
the quota must not be what stops one.
- `percent_of` widens to u128 instead of saturating the multiply, which
under-reported utilization (failing open) above ~184 PB.
- StorageConfig::quotas is optional; absent means no quota is enforced.
Co-Authored-By: Claude Opus 5 (1M context) <noreply@anthropic.com>
* feat: don't recover dead replicas onto a node at a resource limit
Recovering a dead replica pulls a whole copy of its shard onto this node.
If it is already at its memory or disk quota that transfer cannot finish,
and starting it only pushes the node further past the limit. Skip it and
reconsider on a later sync, once the resource frees up.
Adds QuotaManager::check_capacity for work that lands bytes here without
being an update. Unlike fits_on_disk the configured limits do apply:
taking on a replica is not what frees a full node, so there is no deadlock
to avoid by letting it through.
The check is hoisted out of the per-shard loop because a node over its
limit re-measures on every call, so checking per dead shard would cost a
statvfs each. It is free when no quota is configured.
Also trims the comments across the quota module, which had grown well past
what the code needs.
Co-Authored-By: Claude Opus 5 (1M context) <noreply@anthropic.com>
* test: drop trivial and duplicated quota tests
Six tests removed, ~140 lines, with no loss of coverage:
- a_rejection_names_the_knob_that_has_to_change asserted that a format!
contains its own literals; the message is covered end-to-end by the
override test and by test_global_quota.py.
- a_node_over_its_quota_has_no_capacity_to_take_on_a_replica was 30 lines
for check_capacity, a one-line delegation to check_update the test above
it already calls.
- a_rejecting_measurement_is_never_served_from_the_cache duplicated the
meter test, which proves the same rule with an injected reader instead
of inferring it from the real filesystem.
- free_space_is_reported_without_enforcing_anything covered a one-line
accessor, and its point is what the fits_on_disk test is for.
- The two resolve tests and the three meter tests each collapse into one.
DiskFit::Unknown keeps its coverage as two lines inside the fits_on_disk
test rather than its own fixture. The snapshot compat pair becomes one
test: the second only asserted cluster_metadata.is_empty(), which says
nothing about quotas — the real check was the deserialize, now an expect
that states it.
Co-Authored-By: Claude Opus 5 (1M context) <noreply@anthropic.com>
* fix: re-measure free space as the disk fills, and drop a Windows-only assert
Two CI failures, both from this branch.
e2e test_low_disk: the DiskUsageWatcher I replaced escalated to checking
on every call once free space fell below 512 MB. Folding it into the quota
manager lost that — available_bytes passed no limit, so a reading was
reused for the full 5s however little space was left. On a disk filling as
fast as that test fills it, 5s blind is enough to actually run out and the
WAL write dies instead of returning "No space left on device".
available_bytes now takes a watch_below level and never reuses a reading
under it, which is what the old ladder was expressing. The watcher passes
max(min_free, 512 MB), so the escalation point is back; above it the 5s
cache still costs fewer syscalls than the old 128-call ladder. fits_on_disk
gets the same rule by passing required_bytes, so a merge that does not fit
re-checks rather than sitting on a stale sample.
Windows: fits_on_disk on a missing path was asserted to be Unknown, but
GetDiskFreeSpaceEx resolves up to the containing drive and succeeds — as
common::disk_usage's own test documents. Dropped; the branch is a two-line
else and is not portably reachable.
Also renames an_optimization_is_sized_against_the_disk_not_the_quota, which
needed explaining to be understood.
Co-Authored-By: Claude Opus 5 (1M context) <noreply@anthropic.com>
* feat: report the quota config in telemetry
Reads it from the quota manager rather than the settings, so it is the
config the node is actually enforcing: a peer that missed a consensus
update reports what it is applying, not what the cluster agreed on.
Gated on global access, the same access `GET /quotas` requires, and left
out of `PeerTelemetry` — a quota is per-node state, so each peer reports
its own.
Co-Authored-By: Claude Opus 5 (1M context) <noreply@anthropic.com>
* fix: regenerate OpenAPI, and cover the quota in the telemetry key sets
Two CI failures from the previous commit.
Referencing QuotaConfig from TelemetryData moves its definition earlier
in `components/schemas`, because TelemetryData is generated ahead of
QuotaStatus. Regenerated rather than hand-patched, so the schema is a
pure move.
test_telemetry_detail asserts the exact set of top-level telemetry keys.
The quota is reported at every level, including 0 — it is three scalars,
it is the default the endpoint serves, and it is what explains an update
being rejected — so both key sets gain it.
Co-Authored-By: Claude Opus 5 (1M context) <noreply@anthropic.com>
* feat: remove `max_disk_usage_percent` from strict mode
Disk is a node-wide resource, so a per-collection percentage of it never
meant anything a caller could act on: the limit describes how full the
*node* is, and which collection the write happens to target has nothing
to do with it. The global quota is where it belongs.
It shipped in 1.18.2 without documentation, so this drops it outright
rather than deprecating. Removal is soft in every direction: StrictModeConfig
has no `deny_unknown_fields`, so a client still sending it gets it ignored
rather than a 400, and the same struct deserializes the persisted collection
config, so collections created on 1.18.2+ keep loading. Proto field 22 is
reserved so the number is never reused.
The e2e test becomes a quota test — the fixture and the timing are the
interesting parts and they carry over unchanged; only how the threshold is
configured differs.
`max_resident_memory_percent` was documented and stays for now.
Co-Authored-By: Claude Opus 5 (1M context) <noreply@anthropic.com>
* refactor: enforce the strict mode memory limit outside the quota
`max_resident_memory_percent` was folded into the quota as an override,
which meant the quota check had to know about strict mode, and retiring
the setting would mean unpicking `EffectiveLimit` and `LimitSource` from
the resolution logic.
It is now a check of its own in `verification/mod.rs`, next to the strict
mode checks it belongs with, borrowing only the measurement from the quota
manager — which stays the node's single reader of process memory, so both
checks still share one reading. Deleting the setting later is deleting one
function and its one caller.
`QuotaManager::check_update` takes no arguments and consults the quota
alone. A collection can still only tighten the limit for itself, because
its own check runs in addition rather than in place of the quota's, and
each rejection now names the config that has to change without having to
carry a `LimitSource` to say so.
Co-Authored-By: Claude Opus 5 (1M context) <noreply@anthropic.com>
* refactor: enforce the quota on the update path, not in strict mode
The quota check sat inside `check_strict_mode_toc_batch` only because that
was the one place holding the collection's strict mode config. It doesn't
need one any more, and the placement had a real cost: coverage depended on
each handler remembering to ask for a strict mode check, and four of the
internal update RPCs do — `sync_internal`, which moves the most bytes onto
a node, does not.
It now runs in `Collection::update_from_client` and `update_from_peer`,
which every update passes through. `update_from_client` checks ahead of the
shard split, so an operation is accepted or refused whole rather than
landing on some shards and being refused by others.
Classification moves with it, from ~10 `consumes_memory` impls on request
DTOs to one exhaustive `CollectionUpdateOperations::consumes_quota`. The
internal enum has variants — raw upserts, conditional upserts, the syncs —
that have no client-facing request type, so per-DTO impls structurally
could not classify them.
Shard-transfer syncs stay excluded, as they are today: a transfer is sized
up once before it starts, and refusing its batches partway abandons work
that is nearly done only for it to restart from the beginning.
Index and named-vector creation reach shards through consensus, past this
check — a peer must not refuse what the cluster agreed to — so they keep
their pre-consensus check, now against the quota manager directly.
Co-Authored-By: Claude Opus 5 (1M context) <noreply@anthropic.com>
* feat: deprecate `max_resident_memory_percent` in strict mode
Same reason the disk threshold went: memory is node-wide, so a
per-collection percentage of it caps how full the *node* is, which has
nothing to do with which collection is being written to. The node-wide
quota caps it once for everything.
Unlike the disk threshold this one shipped documented, in 1.18.0, so it
keeps working — as a limit a collection can tighten for itself, never lift
— and gets the usual markers: `#[deprecated]` on both Rust structs,
`[deprecated = true]` on proto field 21, and `deprecated: true` in the
OpenAPI schema, which schemars derives from the attribute.
The note names 1.21 as the removal. Recording a version matters here: the
audit in docs/plans/overdue-deprecations.md found that this repo has never
written a removal deadline down, and members of the 1.15.0 deprecation
batch are still in tree.
Co-Authored-By: Claude Opus 5 (1M context) <noreply@anthropic.com>
* fix: reconcile the quota readers with #9891#9891 landed effective (cgroup) figures in telemetry while this branch was
making QuotaManager the single reader of memory and disk. Two collisions,
neither of which git sees.
`segment::utils::mem::total_memory_bytes` is now a shared accessor with a
5s TTL, so a cgroup resize is picked up. The quota module had its own
`OnceLock` copy that froze the value at startup — exactly what #9891 set
out to fix — so it delegates to the shared one instead.
Telemetry's new `disk_size` called `common::disk_usage::disk_usage`
directly. That reader lost its TTL cache on this branch when the caching
moved into the quota manager's meter, so it would have taken an uncached
`statvfs` on every telemetry request, and it put a second disk reader back
in the tree. It goes through `QuotaManager::disk_capacity_bytes` now,
sharing the reading the quota check already takes. Verified it still
reports the storage filesystem, matching `df`.
Co-Authored-By: Claude Opus 5 (1M context) <noreply@anthropic.com>
* refactor: split the quota manager by what each half does
`manager.rs` had grown to 450 lines holding three separate jobs: owning
the config and its file, taking the readings, and comparing one against
the other.
- `manager/store.rs` — the `Store` enum, `QUOTA_CONFIG_FILE`, and config
validation, which is now the store's own business rather than something
every caller has to remember to do first.
- `manager/measure.rs` — every reading, and `DiskFit`. The "nothing else
calls `statvfs` or reads process RSS" claim is now checkable by looking
at one file.
- `manager/enforce.rs` — `check_update` / `check_capacity` and the
threshold comparison.
- `manager/mod.rs` — the struct, its construction, and the config
accessors: what a reader needs to see first.
Tests move with their subject. No behaviour change: `set_config` used to
validate before delegating to the store, and now the store validates on
write, which is the same order of operations from the outside.
Co-Authored-By: Claude Opus 5 (1M context) <noreply@anthropic.com>
* fix: count copy-on-write deletes toward the quota
Dropping a vector or a payload key does not free anything on its own:
copy-on-write rewrites the point to produce the version without that
field, so storage grows first and is only reclaimed once the optimizer
gets to it. Gating those as if they were reclaiming space let a full node
keep taking writes that make it fuller.
Deleting whole points stays exempt. That is the one operation that has to
work on a node at its limit, or there is no way back under it.
Co-Authored-By: Claude Opus 5 (1M context) <noreply@anthropic.com>
* docs: say that the quota's reported usage is per node
`GET /quotas` returns one cluster-wide config and one set of utilization
figures, which reads as though both describe the cluster. They do not:
memory and disk are node-local, so `usage` is whatever the peer that
served the request is seeing, and a peer under its limit says nothing
about the others.
Also corrects `resident_memory_percent`, which claimed to be a share of
total system memory. It is a share of the memory available to the
process, which under a cgroup is the limit rather than the host's RAM.
Co-Authored-By: Claude Opus 5 (1M context) <noreply@anthropic.com>
* feat: treat a node over its quota as a failed replica, not a bad request
A quota rejection described the request as invalid (400) and was classified
non-transient, which is how the replica set recognises errors that every
replica would produce alike. A quota is the opposite: the input is fine and
the answer depends on which machine you ask. On the default `wait=false`
path that combination silently dropped the write — `update.rs` only
deactivates transient failures when nothing completed — leaving the replica
Active and permanently missing data its co-replicas had.
It is now `InsufficientStorage`, transient, HTTP 507 / gRPC
`ResourceExhausted`. So a node that is out of room is handled like one that
is offline:
- last active replica, or every replica over quota: nothing could take the
write, and the client is told the cluster is out of room.
- more than one replica: the full node is deactivated through the same path
a dead peer takes, and the update stands if enough replicas accepted it.
`check_capacity` already keeps recovery off that node until it has room.
The check also moves off `update_from_client`, which applied the
coordinator's own limit to the whole operation even when it held no replica
of the shards being written. Each replica set now gates its own local write
and records the refusal as a failure of this peer, so a node only ever
answers for itself.
`ResourceExhausted` is shared with rate limiting, and the reverse conversion
mapped it straight to `RateLimitExceeded` — a forwarded rejection came back
as 429. Statuses now carry a marker so the two stay distinguishable across
the wire.
Co-Authored-By: Claude Opus 5 (1M context) <noreply@anthropic.com>
* feat: report quota pressure per node, and across the cluster
A quota is node-local, so finding out which node has hit one meant asking
each of them in turn — and nothing at all showed up in monitoring.
`/metrics` gains a `quota_exceeded` gauge for the local node. It is emitted
only while the quota is enabled: with it off the value would be a constant
0 that says nothing about the node, and an alert built on it would go quiet
rather than fire if someone disabled the quota. Telemetry's `quota` field
carries the same verdict alongside the config, since that is where the
metric is derived from.
`GET /quotas` now answers for the whole cluster. A new `GetQuotaUsage` RPC
on the internal `QdrantInternal` service returns what one peer is using,
and the handler fans it out to every known peer in parallel. Peers that do
not answer are left out rather than failing the request — the nodes that
are out of room are exactly the ones most likely to time out, and a partial
answer still names them. Outside distributed mode the field is absent
rather than a map of one.
Co-Authored-By: Claude Opus 5 (1M context) <noreply@anthropic.com>
* feat: report the quota metric per resource
`quota_exceeded` was one flag for the whole node, which does not say what
to go and fix — disk is freed by deleting or optimizing, memory by
unloading. It now carries a `resource` label:
quota_exceeded{resource="memory"} 0
quota_exceeded{resource="disk"} 1
A resource with no limit gets no series at all, for the same reason the
metric is absent while the quota is disabled: a series that can never reach
1 reads as healthy and would quietly carry an alert that cannot fire.
`QuotaManager::exceeded` returns the per-resource verdict, with `None` for
a resource this node does not cap. Telemetry reports the same breakdown,
since the metric is derived from it. The peer usage RPC keeps a single
flag — it sits next to both percentages, so it only has to answer "is this
peer refusing writes".
Co-Authored-By: Claude Opus 5 (1M context) <noreply@anthropic.com>
* fix: drop a no-op error conversion the linter caught
`check_global_access` already returns a `StorageError`, so mapping it
through `StorageError::from` converted the type to itself and tripped
`clippy::useless_conversion`.
Co-Authored-By: Claude Opus 5 (1M context) <noreply@anthropic.com>
* feat: hold a tripped quota until usage clears a release margin
A resource resting on its limit crosses it in both directions on the noise
between two readings, and each crossing is expensive: the node refuses a
write, its replica is deactivated, usage dips, recovery starts sending a
whole shard copy back, and the arriving data pushes it over again. The loop
sustains itself, and every lap costs a shard transfer.
A limit now trips at its configured value but only clears once usage has
fallen 5 percentage points below it, so the crossing has to be real. The
margin is floored at 1%, since a limit smaller than the margin would
otherwise be impossible to fall back under and would strand the node.
The verdict is carried on the manager rather than recomputed, which makes
it the thing reporting shows: expect `exceeded` to be set while the
utilization next to it is already back under the limit. Rejections say so
too, rather than claiming a limit that is no longer exceeded:
Disk usage is at 87% of total capacity. It reached the configured limit
of 90% and has to fall below 85% before this node takes writes again.
Changing the config clears the verdicts. New limits are a deliberate act,
and should not be held back by the margin of a limit that no longer exists.
Both resources are now evaluated on every check instead of stopping at the
first failure, so a verdict is never left behind reporting a reading that
has since been superseded.
Co-Authored-By: Claude Opus 5 (1M context) <noreply@anthropic.com>
* feat: make the quota release margin configurable
5 points is a guess about how noisy a deployment's usage is, which is not
something one number can be right about: a node whose disk moves in
gigabyte steps needs a wider margin than one that creeps, and an operator
who wants the old flip-on-every-reading behaviour should be able to ask
for it.
`release_margin_percent` joins the rest of the quota config, so it seeds
from `QDRANT__STORAGE__QUOTAS__RELEASE_MARGIN_PERCENT`, replicates through
consensus, and changes with `PUT /quotas`. Defaults to 5 and is filled in
when a request omits it, so it always answers with the margin actually in
force rather than leaving the caller to assume one. `0` releases as soon as
usage is back under the limit.
`QuotaConfig` grows a hand-written `Default` for it, since deriving one
would have quietly defaulted the margin to 0 and disabled the hysteresis
for anyone constructing a config in code.
Co-Authored-By: Claude Opus 5 (1M context) <noreply@anthropic.com>
* refactor: leave the release margin unset by default, and hold verdicts in atomics
`release_margin_percent` is `null` unless someone sets it, rather than
materialising 5 into every config. A quota written today then does not pin a
number a later release may want to revise, and `{"enabled": false}` still
round-trips as itself. `QuotaConfig::limits` resolves it, next to `enabled`,
so enforcement never sees the unset case.
The verdicts move from a `Mutex<QuotaExceeded>` to one `AtomicBool` per
resource. They are judged independently and nothing reads them as a pair, so
the lock only added contention to the path every update takes; a verdict
that races a concurrent check is re-decided by the next one from a fresh
reading.
That also drops the tri-state. Only "was this over its limit" has to survive
between checks — whether a resource is enforced at all follows from the
config and the reading, so it is derived when reporting rather than stored.
Co-Authored-By: Claude Opus 5 (1M context) <noreply@anthropic.com>
* docs: drop a comment arguing with a design that was never here
Co-Authored-By: Claude Opus 5 (1M context) <noreply@anthropic.com>
---------
Co-authored-by: Claude Opus 5 (1M context) <noreply@anthropic.com>
* Remove deprecated search/recommend/discover endpoints from OpenAPI
Remove deprecated REST API endpoint definitions from the OpenAPI
generator. These endpoints were deprecated in v1.13.3 (`f4ced2567`,
#5907, 2025-01-30) in favor of the universal `/points/query` endpoint:
- POST /points/search
- POST /points/search/batch
- POST /points/search/groups
- POST /points/recommend
- POST /points/recommend/batch
- POST /points/recommend/groups
- POST /points/discover
- POST /points/discover/batch
Also removes the corresponding request types from the schema generator
and updates the expected API count in the consistency check.
Co-authored-by: Cursor <cursoragent@cursor.com>
* Migrate OpenAPI integration tests to /points/query
The deprecated /points/search, /points/recommend and /points/discover
endpoints (along with their /batch and /groups variants) were removed
from the OpenAPI spec, which caused validation failures in the Python
integration test harness.
This commit migrates the affected tests to the universal /points/query
endpoint:
- Delete tests dedicated to the deprecated endpoints:
test_recommend.py, test_discover.py, test_multicollection_reco.py,
test_recommendation_multivector.py
- Refactor remaining tests to call /points/query (and /query/batch,
/query/groups), translating request bodies (vector -> query / using,
positive/negative -> query.recommend, target/context -> query.discover)
and unwrapping the new result.points response shape.
- Drop equivalence assertions against the now-removed legacy endpoints.
Co-authored-by: Cursor <cursoragent@cursor.com>
* Relax non-empty assertions in migrated recommend/discover tests
The previous migration added `len(...) > 0` assertions to tests that
previously only checked equivalence between the deprecated and new
API. These assertions are too strict because the parametrized
`query_filter` cases legitimately produce empty result sets.
Drop the `> 0` assertion and rely on `request_with_validation` to
verify the response is well-formed and HTTP OK.
Co-authored-by: Cursor <cursoragent@cursor.com>
* Migrate remaining OpenAPI tests off deprecated search endpoints
Tests added to dev after the original migration was written still call
/points/search and /points/recommend/groups through
`request_with_validation`, which resolves the endpoint against the
OpenAPI spec and therefore breaks once the endpoint is not in the spec:
- test_turbo4_storage.py, test_sparse_idf_corpus.py, test_validation.py:
translate /points/search to /points/query (vector{name,vector} ->
query + using, result -> result.points).
- test_group.py: drop the /points/recommend/groups half of the
lookup_from validation test in favour of the query equivalent.
test_sparse_idf_corpus.py's test_query_api_supports_idf_corpus goes
away: with the helper on /points/query every test in the file now
exercises what it asserted.
Also record why test_recommend_group cannot assert on its groups: it
uses every point in the collection as a recommend example, so all of
them are excluded and the result is legitimately empty.
Co-Authored-By: Claude Opus 5 <noreply@anthropic.com>
* Regenerate openapi.json without the deprecated search endpoints
Drops the 8 deprecated paths and the request schemas that only they
referenced: Search/Recommend/Discover request (+Batch, +Groups) types
and their exclusive dependencies (NamedVector, NamedSparseVector,
NamedVectorStruct, UsingVector, RecommendExample, ContextExamplePair).
Regenerated output is a strict subset of the previous spec, and every
remaining $ref still resolves.
Co-Authored-By: Claude Opus 5 <noreply@anthropic.com>
* Deprecate the search/recommend/discover RPCs in gRPC
The REST counterparts have carried `deprecated: true` since v1.13.3 and
are now gone from the OpenAPI spec, while the gRPC RPCs never got any
deprecation annotation at all. Mark all 8 with `option deprecated = true`
so generated clients warn, and point each doc comment at its `Query`
replacement.
tonic puts `#[deprecated]` on the generated client methods only; the
server trait gets the doc comment alone, so our own `impl` is unaffected.
The RPCs keep serving traffic — this is annotation only.
Co-Authored-By: Claude Opus 5 <noreply@anthropic.com>
* Restore the deleted recommend/discover suites on /points/query
The earlier migration deleted these four files outright, but the
query-side tests it left behind are all shallow smoke tests
(`len(result) > 0`, `"points" in result[0]`). The deleted ones carried
invariants with no query-API equivalent anywhere, so deleting them was a
real loss of coverage rather than de-duplication:
- test_recommend.py: default strategy equals average_vector; batch
results identical to sequential singles across six request shapes;
best_score with only negatives yields all-negative scores; best_score
with a single positive orders identically to a nearest query; raw
vectors as examples equal ids as examples.
- test_discover.py: context-only scores are all <= 0; target-only orders
identically to a nearest query but scores differently; with a fixed
context the integer part of the score is stable while the decimal part
moves, and vice versa with a fixed target; batch equals singles;
lookup_from by id equals by vector.
- test_multicollection_reco.py: cross-collection lookup_from, plus
wrong-vector-size, unknown-collection and unknown-vector rejections.
- test_recommendation_multivector.py: the same recommend invariants over
a max_sim multivector collection, which the query suite never covered.
Only test_recommend_missing_lookup_from_collection_with_raw_vector is
dropped as genuinely redundant — test_query.py's
test_query_missing_lookup_from_collection covers query, query/batch and
prefetch.
Two request-shape differences the translation had to absorb:
- Giving no examples at all is 422 (a RecommendInput validation rule),
where the legacy API reported 400 from the query itself. A malformed
example, such as an empty vector, is still 400.
- DiscoverInput requires the `context` key and accepts only an explicit
null to mean "no context", so target-only discover must spell it out.
The legacy API let it be omitted.
Co-Authored-By: Claude Opus 5 <noreply@anthropic.com>
---------
Co-authored-by: Cursor <cursoragent@cursor.com>
Co-authored-by: Claude Opus 5 <noreply@anthropic.com>
* feat: slice filtering condition for sliced scroll and deterministic sampling
Add a `slice` filter condition selecting points where
`stable_hash(point_id) % total == index`. The hash is SipHash-2-4 with a
zero key over canonical id bytes (8 LE bytes for numeric ids, 16 RFC 4122
bytes for UUIDs) — a frozen public contract, independent of the internal
resharding ring hash, reproducible by clients to predict membership.
For a fixed `total`, slices are disjoint and cover all points, enabling
parallel scroll streams (ES sliced-scroll style) and reproducible sampling
that composes with any other filter condition.
- REST: `{"slice": {"total": N, "index": R}}`; gRPC: `SliceCondition` in
the condition oneof (tag 8)
- Evaluated per point via id_tracker external-id lookup; no payload index
needed; cardinality estimated as `points / total` with no primary clause
- `total >= 1` enforced by NonZeroU32 at parse time, `index < total` by
validation in both REST and gRPC paths
- Hash contract locked by test vectors independently reproduced with a
reference SipHash-2-4 implementation
Co-Authored-By: Claude Fable 5 <noreply@anthropic.com>
* tests: minimal OpenAPI test for slice filter condition
Scrolls all slices of a fixed total over numeric + UUID ids asserting
disjointness and full coverage, checks must_not inversion, and pins the
two rejection paths (422 for index >= total, 400 for total = 0). Requests
and responses are validated against the regenerated OpenAPI spec by the
test harness.
Note: the spec cannot itself reject total = 0 client-side — the Condition
anyOf falls through to the permissive Filter schema, as with any invalid
condition — so rejection is asserted via the server response.
Co-Authored-By: Claude Fable 5 <noreply@anthropic.com>
---------
Co-authored-by: Claude Fable 5 <noreply@anthropic.com>
* Add per-query IDF corpus for sparse vector search
Let the caller choose, per query, which population sparse IDF statistics
are computed over. `params.idf` is either `"global"` (default, unchanged
behavior) or `{"corpus": <filter>}`, where the corpus filter is
independent of - and usually broader than - the retrieval filter.
Decoupling the two keeps the score scale stable when the retrieval
filter tightens: term importance is measured against a population the
user names, not against whatever subset the filter happens to select.
Design decisions:
- Corpus grammar is restricted to a conjunction (`must`) of `match`
conditions on payload fields; loosening later is backward compatible.
- Strict mode validates the corpus filter like a read filter
(unindexed fields rejected).
- `idf` on a vector without the IDF modifier is a validation error,
never silently ignored.
- An empty corpus yields degenerate but corpus-scoped scores (smoothed
IDF over N=0), never a fallback to global statistics - in multi-tenant
collections a fallback would leak term statistics across tenants.
Implementation:
- QueryContext IDF stats are keyed by corpus, so one batch can mix
requests with different corpora.
- Statistics come from the sparse index: df(term) is counted over the
query terms' posting lists only, never by scanning stored vectors.
Small corpora (under ~1/32 of the segment, by cardinality estimate)
are kept as a sorted id list galloping through posting lists via
skip_to; large ones as a dense membership mask filled streaming from
the filtered-points iterator. A misestimated small corpus degrades
into the mask.
- Exposed uniformly: REST (`params.idf`), gRPC (`IdfParams` message),
edge python bindings; OpenAPI schema regenerated.
Co-Authored-By: Claude Opus 4.8 (1M context) <noreply@anthropic.com>
* Apply rustfmt
Co-Authored-By: Claude Opus 4.8 (1M context) <noreply@anthropic.com>
* Fix clippy manual_is_multiple_of in sparse IDF corpus test.
Co-authored-by: Cursor <cursoragent@cursor.com>
* Allow any filter as IDF corpus
Drop the must+match grammar restriction on the corpus filter. A
restriction enforced only as a validation step over the full Filter
type buys nothing; if a narrower corpus syntax is ever wanted, it
should be a dedicated API-level type instead.
Co-Authored-By: Claude Opus 4.8 (1M context) <noreply@anthropic.com>
* Fix build: add memory field to SparseIndexConfig in idf corpus test
Co-authored-by: Cursor <cursoragent@cursor.com>
---------
Co-authored-by: Claude Opus 4.8 (1M context) <noreply@anthropic.com>
Co-authored-by: root <111755117+qdrant-cloud-bot@users.noreply.github.com>
Co-authored-by: Cursor <cursoragent@cursor.com>
* Add optional last-modified timestamp to ListedFile and CachedFs FileInfo
Filled where the listing backend exposes one: local filesystems
(entry metadata) and object stores (ObjectMeta::last_modified). The
uio-grpc backend reports None since the RPC does not carry mtimes.
Co-Authored-By: Claude Fable 5 <noreply@anthropic.com>
* Carry last-modified over the StorageRead ListFiles RPC
Extend ListFilesEntry with an optional google.protobuf.Timestamp, fill
it on the server from the listing metadata, and convert it back to
SystemTime in the uio-grpc client.
Co-Authored-By: Claude Fable 5 <noreply@anthropic.com>
* Update lib/common/io_bridge_object_store/src/source.rs
Co-authored-by: coderabbitai[bot] <136622811+coderabbitai[bot]@users.noreply.github.com>
* Fix missing SystemTime import in io_bridge_object_store
The CodeRabbit-suggested last_modified mapping used SystemTime::from
without importing std::time::SystemTime, breaking compile and CI.
Co-authored-by: Cursor <cursoragent@cursor.com>
* Retrigger CI after flaky integration-tests-consensus timeout
The compile fix is in; the prior run failed on an unrelated 30s timeout
in test_collection_recovery, not on PR changes.
Co-authored-by: Cursor <cursoragent@cursor.com>
---------
Co-authored-by: Claude Fable 5 <noreply@anthropic.com>
Co-authored-by: coderabbitai[bot] <136622811+coderabbitai[bot]@users.noreply.github.com>
Co-authored-by: root <111755117+qdrant-cloud-bot@users.noreply.github.com>
Co-authored-by: Cursor <cursoragent@cursor.com>
* Add unified `memory: cold|cached|pinned` placement parameter for collection components
Introduce a single `memory` parameter that controls how each collection
component's data is held in RAM, replacing the inconsistent zoo of
`on_disk` / `always_ram` / `on_disk_payload` flags:
- `cold`: not pre-loaded from disk, cached with usage
- `cached`: pre-populated into page cache on load, evictable under pressure
- `pinned`: materialized on heap, never evicted by cache pressure
The parameter is available on dense vectors, HNSW config, all quantization
configs, the sparse index, all payload field index types, and payload
storage (as a new `payload: { memory }` sub-object on collection params).
When set, it overrides the deprecated legacy flag; when unset, behavior is
unchanged. Legacy flags are marked deprecated (Rust + proto) but keep
working; conflicts are resolved in favor of `memory` with a warning.
New capabilities enabled by the tri-state model:
- HNSW graph links can be pinned (first production caller of the existing
`GraphLinksResidency::Pinned`)
- sparse mmap index, quantized vectors and on-disk payload field indexes
gain a `cached` tier (mmap + populate on open)
`pinned` is rejected by API validation for components without a heap
variant (dense vector storage, payload storage). Low-memory mode degrades
placements at load time via `Memory::clamp_to_low_memory`, matching the
existing `prefer_disk`/`skip_populate` behavior. Effective-placement
comparison in the config-mismatch optimizer avoids spurious rebuilds when
the same placement is expressed through the new parameter.
Co-Authored-By: Claude Fable 5 <noreply@anthropic.com>
Co-authored-by: Cursor <cursoragent@cursor.com>
* Fix gpu-gated tests for the new `memory` field
CI clippy runs with --all-features, which compiles the gpu-gated tests
that were missed locally: add the `memory` field to config literals and
allow deprecated placement params, same as in the rest of the tests.
Co-Authored-By: Claude Fable 5 <noreply@anthropic.com>
* Add OpenAPI tests for memory placement, keep sparse config downgrade-clean
- OpenAPI tests: create/update collections with `memory` on every component,
assert the parameters are echoed in collection info, assert legacy-only
collections expose no new fields, and assert `pinned` is rejected (422)
for dense vector storage and payload storage on both create and update.
- Persist only the explicitly requested `memory` parameter in
`sparse_index_config.json` instead of the legacy-resolved placement, so
configurations using only the deprecated `on_disk` flag keep byte-identical
files that older Qdrant versions load without unknown fields.
Co-Authored-By: Claude Fable 5 <noreply@anthropic.com>
* Validate collection meta ops at construction, not only in the API layer
The `memory: pinned` rejection for dense vectors and payload storage
lived in `Validate` impls on the internal request types, which only ran
through the REST actix extractor. gRPC validates just the proto message,
so a gRPC client could persist `pinned` where it is not supported and
have it silently treated as `cached`.
Run the derived validation in `CreateCollectionOperation::new` and
`UpdateCollectionOperation::new` instead: the constructors are the
common chokepoint for all API paths, before the operation is proposed
to consensus. This covers every validator on these types, not just the
`memory` checks, and keeps consensus-apply unaffected so mixed-version
clusters never reject already-committed operations.
`UpdateCollectionOperation::new` becomes fallible; `remove_replica` now
uses `new_empty` since it carries no user config. Regression tests drive
the gRPC conversion path and assert `InvalidArgument` for `pinned` on
create and update, with `cold`/`cached` accepted as a control.
Co-Authored-By: Claude Fable 5 <noreply@anthropic.com>
---------
Co-authored-by: Claude Fable 5 <noreply@anthropic.com>
Co-authored-by: Cursor <cursoragent@cursor.com>
* Add prefix matching option to keyword index
Introduce an opt-in `prefix` option for the keyword payload index and a
new `match: { "prefix": ... }` filter condition, enabling efficient
byte-wise prefix filtering over keyword values (e.g. URL prefixes,
web-ui value autocompletion via facet + prefix filter).
Index side: a new `prefix_index.bin` file stores a sorted, front-coded
key dictionary with a resident block index (cumulative counts per
block); it is an ordered view over the keys of `values_to_points.bin`
and stores no postings. Presence of the file signals prefix support at
load time, so legacy segments load unchanged and enabling the option
goes through the standard incompatible-schema rebuild. The mutable
variant keeps an in-RAM ordered key set (not persisted), the immutable
variant builds a sorted key vector at load, and the on-disk variant
reads the dictionary lazily (block index resident, 1-2 block reads per
prefix lookup; reader is generic over UniversalRead).
Query side: prefix conditions are served from the dictionary when
available (filter + cardinality estimation from per-block aggregates),
from the forward index as per-point checks, and degrade to the payload
full-scan fallback otherwise - same execution model as other match
conditions. Strict mode (`unindexed_filtering_*`) rejects prefix
queries on fields without a prefix-enabled keyword index via a new
KeywordPrefix capability.
HNSW payload blocks: prefix-enabled indexes additionally emit prefix
blocks for heavy branching trie nodes (single-child chains collapsed to
their longest common prefix, one block per distinct point set, emitted
largest-first) so filtered search with prefix conditions gets navigable
subgraphs without rebuilding the same subset repeatedly.
API: `prefix` flag on KeywordIndexParams (REST bool, gRPC empty
message for extensibility), `prefix` variant in the Match oneof, edge
python bindings, regenerated OpenAPI spec.
Co-Authored-By: Claude Fable 5 <noreply@anthropic.com>
* Split prefix index into a dedicated module, fix clippy in tests
Reorganize the flat prefix_index.rs / prefix_read.rs into a
map_index/prefix_index/ module: format.rs (on-disk layout primitives),
writer.rs, reader.rs (PrefixIndex), map_read.rs (StrMapIndexPrefixRead
with per-variant impls) and tests.rs, with a file-format diagram and a
read-path walkthrough in the module docs. No logic changes.
Also fix clippy --all-targets complaints in test code: replace a
wildcard Match arm with an exhaustive list and a field-reassign-with-
default with a struct literal.
Co-Authored-By: Claude Fable 5 <noreply@anthropic.com>
* Add OpenAPI test for prefix match and snapshot file-tracking test
- tests/openapi/test_prefix_match.py: index-less fallback, prefix index
creation with schema echo, scroll/count parity against ground truth,
facet + prefix filter (the autocompletion flow), strict-mode rejection
without the prefix capability.
- test_prefix_index_file_tracking: `prefix_index.bin` is listed in
`files()` / `immutable_files()` exactly when built with the option.
Co-Authored-By: Claude Fable 5 <noreply@anthropic.com>
* Replace hand-rolled varint parsing with bytemuck Pod records
Per review: the prefix index format now uses fixed-size little-endian
Pod records (BlockEntry 24 B, KeyEntry 12 B, Header 40 B) written with
bytemuck::bytes_of and read back by copy via pod_read_unaligned — no
manual varint encode/decode, no alignment requirement, one shared
read_record helper. Costs ~9 bytes per key on disk versus LEB128; the
raw key bytes dominate dictionary size, so the simplification wins.
Co-Authored-By: Claude Fable 5 <noreply@anthropic.com>
* Fetch the whole candidate block range with a single storage read
Candidate key blocks of a prefix lookup are contiguous in the file, so
enumerate them from one ranged read instead of one read per block; the
over-read versus the exact key range is bounded by the two boundary
blocks. Block decoding is split into a storage-free helper reused by
the per-block path of stats estimation.
Co-Authored-By: Claude Fable 5 <noreply@anthropic.com>
* Align prefix payload blocks with the geo index granularity principle
Geo's large_hashes emits only the smallest geohash regions above the
threshold — a disjoint antichain, never a parent nested with its
children. Prefix payload blocks now follow the same rule: a heavy
collapsed trie node is emitted only if nothing heavy is nested inside
it, counting both deeper qualifying prefixes and single heavy values
(which already get their own exact-match blocks). Emitted blocks are
therefore mutually disjoint and disjoint from exact-value blocks; no
near-collection-sized ancestor subgraphs, no reliance on the HNSW
connectivity check to skip nested duplicates.
Implemented as a `covered` flag propagated through the existing
LCP-interval scan, still one O(total key bytes) pass.
Co-Authored-By: Claude Fable 5 <noreply@anthropic.com>
* Document block wire format and unaligned-read rationale in decode_block
Co-Authored-By: Claude Fable 5 <noreply@anthropic.com>
---------
Co-authored-by: Claude Fable 5 <noreply@anthropic.com>
* [AI + manual] Include file size in `UniversalReadFileOps::list_files`
* Use dedicated `ListedFile` struct instead of `(PathBuf, u64)` pair
Co-Authored-By: Claude Opus 4.8 (1M context) <noreply@anthropic.com>
---------
Co-authored-by: generall <andrey@vasnetsov.com>
Co-authored-by: Claude Opus 4.8 (1M context) <noreply@anthropic.com>
* remove unused iter_offsets
* Replace MultivectorOffsetsStorage::iter_offsets with callback-based for_each_offset
First step of removing the iterator-returning read API (whose deep,
composable generic types blow up mangled symbol size). Convert the
offsets read from an iterator to a callback the caller pushes into:
- trait method iter_offsets -> for_each_offset(ids, FnMut(usize, MultivectorOffset))
returning common::universal_io::Result<()>
- Mmap impl now uses the callback read_batch (drops one read_iter use)
- Ram / Chunked impls push into the callback; Chunked still goes through
iter_vectors for now (converted in a later step)
- the single caller (for_each_in_multi_batch) passes a closure
Co-Authored-By: Claude Opus 4.8 (1M context) <noreply@anthropic.com>
* Implement read_batch directly on ReadPipeline, not via read_iter
read_batch now drives the pipeline itself (refill-then-wait loop, like
read_multi_iter) and invokes the callback per result, instead of
consuming the iterator returned by read_iter. A step toward removing the
iterator-returning read API.
Co-Authored-By: Claude Opus 4.8 (1M context) <noreply@anthropic.com>
* Remove the ReadMulti RPC from the StorageRead gRPC service
ReadMulti was the only real consumer of UniversalRead::read_multi (which
itself relies on read_multi_iter). Removing the RPC end-to-end clears the
path to dropping that read API. StorageReadService keeps all its other
RPCs (ListFiles, FileExists, FileLength, ReadBytes, ReadBytesStream,
ReadWhole, ReadBatch).
- proto: drop `rpc ReadMulti` + ReadMulti{Entry,Request,Response}
- regenerated lib/api + uio-client generated code; drop ReadMulti
validation rules in lib/api/build.rs
- tonic: delete the read_multi handler + its 2 tests
- uio-client: delete Client::read_multi, the mock-server impl, and 2 tests
Co-Authored-By: Claude Opus 4.8 (1M context) <noreply@anthropic.com>
* Remove UniversalRead::read_multi
Its only real consumer was the StorageRead ReadMulti gRPC handler (removed
in the previous commit); the two wrapper forwarders had no callers. Drop
the trait method and both forwarders (typed/read_only), and remove the
io_uring test that only existed to compare read_multi vs read_multi_iter
(read_multi_iter stays covered by the other tests). Another step toward
removing the iterator-returning read API.
Co-Authored-By: Claude Opus 4.8 (1M context) <noreply@anthropic.com>
* Drive ReadPipeline directly in gridstore read_from_pages
Replace the read_multi_iter call in Pages::read_from_pages with a direct
pipeline loop (refill-then-drain), scheduling each multi-page read on its
own page file. Behavior unchanged; another step toward removing the
iterator-returning read_multi_iter.
Co-Authored-By: Claude Opus 4.8 (1M context) <noreply@anthropic.com>
* Drive ReadPipeline directly in gridstore read_batch_from_pages
Replace the second read_multi_iter call (in Pages::read_batch_from_pages)
with a direct pipeline loop, scheduling each (ReadMeta, page, range) on its
own page file and propagating errors via GridstoreError. Single/multi-page
buffering and out-of-order reassembly are unchanged. No more read_multi_iter
in gridstore.
Measured overhead on warm mmap (both paths are zero-copy borrows): ~0.3 ns
per read of fixed control cost, flat across read sizes — well under 0.1% of
a real payload read.
Co-Authored-By: Claude Opus 4.8 (1M context) <noreply@anthropic.com>
* Drive ReadPipeline directly in on-disk postings with_posting_views
Replace read_iter in OnDiskPostings::with_posting_views with a direct
pipeline loop. wait_bytemuck yields a file-borrowed Cow, so postings are
still stored zero-copy in raw_postings (a read_batch swap would have forced
an owned copy of every posting list per query on the mmap backend).
Co-Authored-By: Claude Opus 4.8 (1M context) <noreply@anthropic.com>
* Read on-disk posting headers via read_batch, drop the HeadersBatch iterator
headers_iter now reads headers with the callback read_batch API: each header
is parsed (copied) out of the read bytes, so nothing borrows the file past the
read — no pipeline needed. Since the read is now eager, HeadersBatch holds the
collected Vec<HeaderResult> directly instead of a Box<dyn Iterator>, dropping
the boxing, the dynamic dispatch, and the struct's lifetime parameter.
with_posting_views takes the Vec and still pipelines the posting reads.
Removes the last read_iter use in this file.
Co-Authored-By: Claude Opus 4.8 (1M context) <noreply@anthropic.com>
* Use read_batch in simple_disk_cache populate_from
populate_from reads one byte per block only to fault blocks into the local
cache, discarding the bytes — a no-op-callback read_batch fits exactly. Drives
the same DiskCachePipeline as before; one less read_iter caller.
Co-Authored-By: Claude Opus 4.8 (1M context) <noreply@anthropic.com>
* Implement read_iter directly on ReadPipeline, not via read_multi_iter
read_iter now drives the pipeline itself (refill-then-wait loop, mirroring
read_bytes_iter) instead of mapping its ranges onto self and calling
read_multi_iter. Same signature and iterator contract, so all callers are
unchanged. Leaves iter_vectors as read_multi_iter's only remaining caller.
Co-Authored-By: Claude Opus 4.8 (1M context) <noreply@anthropic.com>
* Revert "Drive ReadPipeline directly in on-disk postings with_posting_views"
This reverts commit c02c41f17b.
* Add callback-based for_each_vector next to iter_vectors
for_each_vector drives the ReadPipeline directly across chunk files and
invokes a fallible callback per flattened multi-vector, returning
OperationResult, instead of returning an iterator built on read_multi_iter.
Callers will migrate onto it so iter_vectors (read_multi_iter's last caller)
can be removed.
Co-Authored-By: Claude Opus 4.8 (1M context) <noreply@anthropic.com>
* Make dense for_each_in_batch / for_each_in_dense_batch fallible
Thread OperationResult up the dense batch-read path so io_uring read
errors propagate instead of being .expect()ed deep inside the storage.
The for_each_in_dense_batch scorer path (custom/metric query scorers)
now carries the Result to the infallible score() boundary where it is
.expect()ed; read_vectors keeps its () signature and .expect()s locally.
Co-Authored-By: Claude Opus 4.8 (1M context) <noreply@anthropic.com>
* Convert dense read_vectors to for_each_vector
The read-only and appendable dense storage read_vectors impls drove
ChunkedVectors::iter_vectors directly; switch them to the callback-based
for_each_vector and .expect() the result at the (infallible) read_vectors
boundary. Removes the last dense-path iter_vectors callers.
Co-Authored-By: Claude Opus 4.8 (1M context) <noreply@anthropic.com>
* Convert quantized for_each_offset to for_each_vector + OperationResult
The two chunked MultivectorOffsetsStorage impls drove iter_vectors to read
the offset table; switch them to the callback-based for_each_vector.
for_each_vector returns OperationResult, so upgrade the for_each_offset
trait (and all four impls) from universal_io::Result to OperationResult
(the universal_io -> Operation direction, via ?). No error downgrade.
Co-Authored-By: Claude Opus 4.8 (1M context) <noreply@anthropic.com>
* Convert EncodedStorage/EncodedVectors iter_batch to callback for_each_batch
The two chunked-mmap EncodedStorage impls drove ChunkedVectors::iter_vectors
to back iter_batch. Replace the iterator-returning iter_batch on both the
EncodedStorage and EncodedVectors traits (quantization crate) with a callback
for_each_batch(FnMut(usize, &[u8])), and switch the chunked impls to
for_each_vector. The callback is infallible: the chunked impls .expect() the
read internally, matching iter_vectors' prior panic-on-read-error behavior,
so no OperationError is downgraded. Scorers and the multivector readers adopt
the callback; the accumulating multivector path owns (to_vec) only when it
must buffer across components.
Co-Authored-By: Claude Opus 4.8 (1M context) <noreply@anthropic.com>
* Convert multivector read paths to for_each_vector
The read_only multivector free fn chained two iter_vectors (offsets feeding
vectors) - the recursive iterator nesting behind the worst symbol bloat.
Replace it with a callback for_each_vector that resolves the per-point
offsets into a Vec first, then drives ChunkedVectors::for_each_vector over
the flattened vectors. Migrate both multivector storages' read_vectors and
for_each_in_batch_multi accordingly, .expect()ing at their infallible
boundaries.
Co-Authored-By: Claude Opus 4.8 (1M context) <noreply@anthropic.com>
* Remove read_multi_iter and ChunkedVectors::iter_vectors
With every caller migrated to callback-based for_each_vector/for_each_batch,
delete the last iterator-returning multi-read APIs: ChunkedVectors::iter_vectors
(segment) and the read_multi_iter trait method plus its mmap override, the
TypedStorage/ReadOnly wrapper forwarders, and the two io_uring unit tests.
These deeply-nested monomorphized iterator types (read_multi_iter feeding
read_multi_iter) produced >1 MiB mangled drop_in_place symbols that overflowed
the macOS ld symbol-name limit; the callback rewrite eliminates them.
Co-Authored-By: Claude Opus 4.8 (1M context) <noreply@anthropic.com>
* Pass owned Cow through for_each_vector/for_each_batch to avoid a copy
The callback-based readers handed the callback a borrowed `&[u8]`/`&[T]`,
forcing the quantized multivector batch read to `to_vec()` each sub-vector
into its per-point buffer. But io_uring-like backends already return a freshly
owned buffer per read (`ACow::Owned`), so that was a redundant second copy.
Change `ChunkedVectorsRead::for_each_vector` and the `EncodedStorage` /
`EncodedVectors` `for_each_batch` callbacks to receive `Cow<[..]>` by value.
The buffering path now `into_owned()`s it — a move when the backend returned
owned (the case this path targets), a copy only for a borrowed Cow (mmap),
which never reaches this path. Immediate-use callers (scorers,
score_point_max_similarity, the dense/multivector readers) just deref the Cow;
the dense readers drop their now-redundant `Cow::Borrowed` wraps.
Also clarifies the multivector reader: `SubVectorOwner`/`owners`/
`sub_vector_offsets` naming, docs, and a corrected comment noting the per-point
buffer is what makes regrouping order-independent under out-of-order completion.
Co-Authored-By: Claude Opus 4.8 (1M context) <noreply@anthropic.com>
* Drop the removed ReadMulti JWT access test; fix clippy unwrap_or_default
The ReadMulti StorageRead RPC was removed earlier in this branch, so the
consensus JWT-access test (and its registry entry) for it must go too. Also
switch the multivector buffer's `or_insert_with(SmallVec::new)` to
`or_default()` per clippy::unwrap_or_default.
Co-Authored-By: Claude Opus 4.8 (1M context) <noreply@anthropic.com>
* Add MmapFile::read_batch
---------
Co-authored-by: Claude Opus 4.8 (1M context) <noreply@anthropic.com>
Co-authored-by: xzfc <xzfcpw@gmail.com>
* feat(bm25): add explicit Disabled stemmer; deprecate language hack
Adds a `Disabled` variant to `StemmingAlgorithm` (`stemmer: {"type": "none"}`)
so stemming can be turned off explicitly in both the main engine and Edge,
instead of relying on the undocumented `language: "none"` footgun that
silently disabled both stemming and stopwords.
For language-neutral text processing the supported setup is now:
1. set the stemmer to disabled, and
2. configure an empty stopword set.
The main engine still tolerates unsupported languages (so existing
`language: "none"` configs keep working on upgrade) but now logs a
deprecation warning pointing users to the explicit setup. Edge continues
to reject unsupported languages, and now has a real way to disable stemming.
Refs: https://github.com/qdrant/qdrant/issues/9289
Co-authored-by: Cursor <cursoragent@cursor.com>
* fix(edge-py): handle Disabled stemmer in python bindings; fix openapi schema
- Handle the new StemmingAlgorithm::Disabled variant in the qdrant-edge-py
bindings (FromPyObject/IntoPyObject/Repr) and add a DisabledStemmer pyclass
plus its .pyi stub entry.
- Match generator output for the StemmingAlgorithm OpenAPI schema (plain $ref
in anyOf) so docs/redoc/master/openapi.json stays consistent.
Co-authored-by: Cursor <cursoragent@cursor.com>
* fix(openapi): regenerate StemmingAlgorithm schema with generator output
Ran tools/generate_openapi_models.sh so docs/redoc/master/openapi.json
exactly matches generator output: DisabledStemmerParams/NoStemmer are placed
after SnowballLanguage, and the StemmingAlgorithm anyOf entry is a plain $ref
(the schema2openapi step flattens the allOf+description wrapper).
Co-authored-by: Cursor <cursoragent@cursor.com>
* fix(test): avoid wildcard enum match arm in bm25 sparse_len helper
clippy --all-targets flags `other => panic!()` as wildcard_enum_match_arm;
match the Dense/MultiDense variants explicitly instead.
Co-authored-by: Cursor <cursoragent@cursor.com>
* fix: issues
* fix: log::warn as call once
---------
Co-authored-by: Cursor <cursoragent@cursor.com>
Co-authored-by: Daniel Boros <dancixx@gmail.com>
* Add routing token structure
* Implement routing token in read operation executor as per design doc
* Add TODO to glue routing token to user requests
* Implement routing header for REST API
* Source routing token from request, not from JWT token
* Implement routing token in gRPC API
* Add test
* Review remarks
Co-authored-by: coderabbitai[bot] <136622811+coderabbitai[bot]@users.noreply.github.com>
* Use lower case header name to prevent panic
* Rename header to X-Qdrant-Route-Affinity
* Assert routing consistency in test on all peers
---------
Co-authored-by: coderabbitai[bot] <136622811+coderabbitai[bot]@users.noreply.github.com>
`FieldCondition::validate` checked geo polygon *shape* (point count and
closure) but never the *coordinate ranges* of any geo sub-condition. A gRPC
filter with latitude outside [-90, 90] or longitude outside [-180, 180] (in
geo_bounding_box, geo_radius, or geo_polygon) passed validation, reached the
geo index, and panicked during geohash encoding, which expects pre-validated
input.
Reject out-of-range coordinates at the API boundary for all three geo
sub-conditions, mirroring `segment::types::GeoPoint::validate`. The bounds are
duplicated because the `api` crate does not depend on `segment`.
Includes a regression test covering geo_radius, geo_bounding_box, and a
well-formed (shape-valid) geo_polygon with out-of-range coordinates.
* Use assert_matches!
* Add trailing commas
* Use more assert_matches!
Also, drop now redundant `expected blah but got blah` messages because
`assert_matches!` will print these.
* Use debug_assert_matches!
---------
Co-authored-by: xzfc <xzfcpw@gmail.com>
`validate_multi_vector_len(N, &[])` with N > 0 previously returned Ok:
it passes the `vectors_count != 0` check, an empty `flatten_dense_vector`
clears the size check, and `0.is_multiple_of(N)` is true, so it falls into
the Ok branch. The unvalidated value then reaches
`convert_to_plain_multi_vector`, where `dim = data.len() / vectors_count = 0`,
the divisibility check `dim * vectors_count != data.len()` (0 == 0) passes,
and `data.into_iter().chunks(0)` panics (itertools asserts the chunk size is
non-zero). This is reachable from a single malformed gRPC Upsert via the
deprecated `vectors_count` field.
Add an `is_empty()` guard to `validate_multi_vector_len`, mirroring the
sibling `validate_multi_vector_by_length`, so empty flattened data is
rejected with a clear validation error before any conversion. Also add a
defensive `vectors_count == 0 || data.is_empty()` guard at the top of
`convert_to_plain_multi_vector`, which aligns it with the already-guarded
`MultiDenseVectorInternal::try_from_flatten` and closes the same panic on the
internal node-to-node `sync` path (where validation is log-only and
`SyncPoints.points` is not validated).
This completes the empty-vector hardening started in #9070, which covered the
REST side only and did not touch the gRPC flattened `vectors_count` form.
Includes a regression test covering both the rejected (empty) and accepted
(consistent multivector) cases.
`impl Validate for grpc::FieldCondition` only checked that at least one
condition field was set; it never validated the contents of a geo polygon.
A `FieldCondition` carrying a malformed `geo_polygon` (empty exterior, fewer
than 4 points, or an unclosed exterior/interior ring) therefore passed
validation, and the invalid shape later reached the geo index and panicked.
Recurse into the polygon's existing validator (`geo_polygon.validate()?`),
which already rejects these shapes (it is covered by `test_geo_polygon`), so
the request is rejected with a clean validation error instead.
Includes a regression test asserting a FieldCondition with an empty polygon
exterior is rejected while a well-formed polygon still passes.
* Strict mode: add `max_disk_usage_percent`
Mirrors `max_resident_memory_percent`: rejects disk-consuming update ops
(upsert, set/overwrite payload, update vectors) when the filesystem hosting
Qdrant storage is filled above the configured percentage. Delete-style ops
remain allowed so callers can free disk.
Disk usage is sampled via `statvfs` and TTL-cached for 5s (same cadence as
the resident-memory reader) so high-RPS request paths don't hammer the
syscall. Reader is keyed by path in `common::disk_usage` and returns `None`
on stat failure — callers (the strict-mode check) treat `None` as "skip",
matching the memory-check behaviour.
Plumbing follows the existing pattern: field on `StrictModeConfig` (+
output/diff/Hash), gRPC proto field `22`, validation 1..=100, REST/proto
conversions, and the hook into `check_strict_mode_toc_batch` alongside the
memory check (both guarded by `any_consumes_memory`).
Co-authored-by: Cursor <cursoragent@cursor.com>
* Fix CI: Windows disk_usage test + e2e WAL config
- `missing_path_returns_none` panicked on Windows because
`GetDiskFreeSpaceEx` succeeds for non-existent paths (it resolves up to
the containing drive). Relax the assertion to "must not panic; if a
value is returned it must be well-formed". The contract we care about
(None on failure) is platform-defined, not something we can portably
force.
- e2e test failed at batch 0 with "WAL buffer size exceeds available disk
space": Qdrant's existing per-shard `DiskUsageWatcher` enforces
`free >= 2 * wal_capacity_mb` and the default WAL didn't fit in the
50 MB tmpfs. Bump tmpfs to 200 MB and shrink `wal_capacity_mb` to 1 MB
(same pattern as `test_low_disk.py`) so our strict-mode gate is the
one that fires, not the WAL pre-check. Raise the gate threshold to
50% to match the larger headroom.
Co-authored-by: Cursor <cursoragent@cursor.com>
---------
Co-authored-by: Cursor <cursoragent@cursor.com>
* [ai] TQDT in the API
* [ai] unify new sparse error for TQDT
* Rename to `turbo4`
* Add `Turbo4` to comments and doc strings.
* Also validate named sparse vector creation
The previous description was outdated: it claimed that enabling this
option "blocks updates at the request level" until segments are
re-optimized. In practice the implementation uses "deferred points":
new points written to large unoptimized segments are persisted but
excluded from read/search results until the segments are optimized.
Updates are not blocked; only `wait=true` clients are made to wait for
the deferred points to become visible. Update this in the REST schema
(via `OptimizersConfig` / `OptimizersConfigDiff`), in the gRPC proto,
in the edge config docstrings, and regenerate the OpenAPI bundle via
`tools/generate_openapi_models.sh`.
Co-authored-by: Cursor Agent <agent@cursor.com>
Co-authored-by: Cursor <cursoragent@cursor.com>
Match the REST API by adding an optional `WriteOrdering` field to
`CreateVectorNameRequest` and `DeleteVectorNameRequest`, and propagate
it through the tonic handlers and remote-shard forwarding paths.
Co-authored-by: Claude Opus 4.7 (1M context) <noreply@anthropic.com>
* [AI] strict mode parameter for limiting update requests if ram usage is over threshold
* opanAPI update
* [AI] end-to-end test
* fmt
* Fix e2e test: memory rejection check broken by string truncation
UnexpectedResponse.__str__() truncates the raw response body, cutting
off the `max_resident_memory_percent` hint at the end of the error
message. Use `resident memory usage` instead, which appears early
enough to survive the truncation.
Made-with: Cursor
* add grpc validation
* test check_resident_memory
---------
Co-authored-by: Cursor Agent <agent@cursor.com>
Co-authored-by: Arnaud Gourlay <arnaud.gourlay@gmail.com>
* Add mincore-based memory stats to MmapFile
Add `resident_bytes()`, `disk_bytes()`, and `probe_memory_stats()` methods
to `MmapFile` for measuring page cache residency via `mincore(2)`. This is
the foundation for per-collection memory usage reporting.
Also extract `page_size()` as a public function in `mmap::advice`, replacing
the internal `PAGE_SIZE_MASK` with a direct page size cache.
Co-Authored-By: Claude Opus 4.6 (1M context) <noreply@anthropic.com>
* [AI] introduce trait for reporting memory usage per component
* [AI] memory reporter implementation for vector storage
* [AI] implement MemoryReporter for QuantizedVectors
* [AI] implement MemoryReporter for VectorIndexEnum
* Implement MemoryReporter for IdTrackerEnum with RAM estimation
Add ram_usage_bytes() to all ID tracker types and their data structures:
- PointMappings, CompressedPointMappings, CompressedVersions,
CompressedInternalToExternal, CompressedExternalToInternal
- MutableIdTracker, ImmutableIdTracker, InMemoryIdTracker
All ID trackers load their data into RAM (none use mmap for working data).
Files are reported as OnDisk (persistence only), actual RAM footprint
is reported via extra_ram_bytes. Uses struct destructuring to ensure
new fields trigger compile errors if not accounted for.
Co-Authored-By: Claude Opus 4.6 (1M context) <noreply@anthropic.com>
* [AI] implement MemoryReporter for PayloadStorageEnum and adjust FileStorageIntent
* [AI] implement MemoryReporter for PayloadStorageEnum and adjust FileStorageIntent
* [AI] implement MemoryReporter for payload indexes: in-ram structures memory consumtion computation + caching
* [AI] implement MemoryReporter for payload indexes: in-ram structures memory consumtion computation + caching
* [AI] segment-level memory usage report
* [AI] Block 3: Aggregation Layer and Data Model + internal api for remote shard
* [AI] REST API handler
* fmt
* [AI] clippy fixes
* [AI] macos fix + proxy segment fix
* [AI] make text index estimation a bit more correct
* fix is_on_disk reporting for dense_vector_storage
* fix after rebase
* [AI] deep account for quantized vectors RAM usage + unify chunk size + shring volatile storage after load
* remove debug log
* cache in test
* make manual test easier to run
* rollback chunk size diff, but keep it for test only
* review fixes
* Use exhaustive match
* Use div_ceil on bits everywhere
It does not seem to be strictly necessary because the number of bits
should already be a multiple of the used container size bytes. Still
it's good practice to be careful with this calculation.
* Improve heap size bytes for encoded product quantization vectors
* Include vector stats for binary quantized vectors
* In volatile chunked vectors, include heap allocated vector
* Include rest of heap allocated structures for mutable map index
* In mutable geo index, the hash map is also heap allocated
* Update tests/manual/test_memory_reporting.py
Co-authored-by: coderabbitai[bot] <136622811+coderabbitai[bot]@users.noreply.github.com>
---------
Co-authored-by: Claude Opus 4.6 (1M context) <noreply@anthropic.com>
Co-authored-by: timvisee <tim@visee.me>
Co-authored-by: Tim Visée <tim+github@visee.me>
Co-authored-by: coderabbitai[bot] <136622811+coderabbitai[bot]@users.noreply.github.com>
* Add empty placeholder vector storage types for named vector CRUD
Introduce EmptyDenseVectorStorage and EmptySparseVectorStorage as
placeholder storages for newly created named vectors on immutable
segments. These report all vectors as deleted, consume no disk space,
and are reconstructed from segment config on load via the new
VectorStorageType::Empty and SparseVectorStorageType::Empty variants.
Key design decisions:
- is_on_disk is derived from original user config, not hardcoded
- MultiVectorConfig is preserved for multi-vector support
- Config mismatch optimizer skips Empty storage to avoid false rebuilds
- Quantization delegates normally (handles 0 vectors gracefully)
- get_vector includes debug_assert to catch unexpected access
Co-Authored-By: Claude Opus 4.6 (1M context) <noreply@anthropic.com>
* [AI] segment-level operations for creating and deleting anmed vectors
* [AI] implement named vector creation and deleting in proxy segment
* [AI] Step 3: Proxy Segment Handling for Named Vector Operations
* [AI] implement for Edge
* [AI] implement consensus operations for named vector operations
* [AI] refactor VectorNameConfig, remove VectorNameConfigInternal
* [AI] handle vector schema inconsistency in raft snapshot recovery
* [AI] rest + grpc API
* [AI] clippy
* [AI] generate openAPI schema
* fmt
* ci fixes
* [AI] fix jwt access test
* [AI] nop operation for awaiting of consensus-commited update ops
* [AI] move vector name operations into points service
* [AI] implement internal api for vector name operations
* [AI] change collection-level config along with segment level operation
* [AI] vector schema reconceliation instead of error
* fmt
* missing compile-time option
* [AI] integration test
* [AI] fix missing JWT tests
* [AI] remove NOP
* [AI] openapi test
* [AI] fix initialization of mutable segment
* [AI] more simple integration tests
* fmt
* [AI] make cluster test a bit harder
* [AI] make test less flacky
* [AI] rabbit comments
* [AI] check params compatibility before writing vector config
* [AI] make sure to register vector storages in structure payload index
* [AI] vector name validation
* lower vector length validation to 200 chars to account for prefix in filename
* [AI] proxy segment: prevent stale data leak through optimization
* fmt
* [AI] filter out removed vectors from proxy response
* [AI] handle vector name in proxy
* fmt
* adjust proxy info based on dropped vectors
* [AI] proxy segment: update filters to correct has_vector condition
* fmt
* clippy
* Fix consensus snapshot applicaiton for vector schema
---------
Co-authored-by: Claude Opus 4.6 (1M context) <noreply@anthropic.com>
* [ai] Replace manual into mappings with Into::into
* Reformat
* [ai] Use implicit .iter
* Don't iterate over keys too
* [ai] Replace unwrap_or
* Reformat
* [ai] Use as_deref and then_some
* [ai] Use more to_string
* [ai] Use explicitly typed into conversions
* Reformat
* [ai] More explicit into conversions
* Reformat
* feat: add search_max_batchsize to strict mode config
* added test case for search_max_batchsize
* Changes for fixing CI issue dure openapi
* Modify check_strict_mode_batch
---------
Co-authored-by: Arnaud Gourlay <arnaud.gourlay@gmail.com>
* Add REST API for reading audit logs across the cluster
Introduces a new `GET /audit/logs` endpoint that retrieves audit log
entries from all peers in the cluster. The API supports filtering by
time range (time_from/time_to), dynamic key=value field filters, and
a built-in limit parameter to prevent reading too many logs at once.
- Add `audit_reader` module in storage crate for efficient file-based
log retrieval, selecting only files whose date range overlaps the
query window
- Add `GetAuditLog` internal gRPC RPC for cross-peer log retrieval
- Add `GET /audit/logs` REST endpoint restricted to management access
- Aggregate and sort results from all peers by timestamp (newest first)
Made-with: Cursor
* [AI] Update filter_files_by_time_range make it aware of the log rotation granulatity (either hourly or daily)
* [AI] For AuditLogParams, try to use DateTime types natively into serde, instead of manual parsing
* [AI] Refactor API into separate file, propagate timeout, use spawn-blocking
* [AI] introduce cancellation token
* [AI] move timestamp to constant
* small manual fixes
* review fixes part 1
* review: switch to POST instead of GET
* [AI] review: sorting update
* [AI] use strict typing
---------
Co-authored-by: Cursor Agent <agent@cursor.com>
Co-authored-by: Andrey Vasnetsov <andrey@vasnetsov.com>
