mirror of
https://github.com/qdrant/qdrant.git
synced 2026-08-01 15:40:53 -05:00
c2faf6c729
* On segment flush, read-lock all segments to prevent CoW between flushes For example, we have a point on an immutable segment. If we use a set-payload operation, we do copy-on-write. The point from immutable segment A is deleted, the updated point is stored on appendable segment B. Because of flush ordering segment B (appendable) is flushed before segment A (not-appendable). If the copy-on-write operation happens in between, the point is deleted from A but the new point in B is not persisted. We cannot recover this by replaying the WAL in case of a crash because the point in A does not exist anymore, making copy-on-write impossible. Locking all segments prevents copy-on-write operations from occurring in between flushes. * Return proper status on set payload operations in segment * Disable propagating point deletions to its vectors, it looses vectors * Update vector tests after disabling point delete propagation to vectors * Implement retry with exponential backoff for read-locking all segments * Use try_read_for rather than sleeping after lock attempts * Simplify locking many, just lock one by one Refs: <https://github.com/qdrant/qdrant/pull/2527> Co-authored-by: generall <andrey@vasnetsov.com> * Comment out now obsolete test * Error handling in method getting segment locks by ID --------- Co-authored-by: generall <andrey@vasnetsov.com>
64 lines
2.0 KiB
Python
64 lines
2.0 KiB
Python
import pytest
|
|
|
|
from .helpers.collection_setup import basic_collection_setup, drop_collection
|
|
from .helpers.fixtures import on_disk_vectors
|
|
from .helpers.helpers import request_with_validation
|
|
|
|
collection_name = 'test_collection_delete'
|
|
|
|
|
|
@pytest.fixture(autouse=True)
|
|
def setup(on_disk_vectors):
|
|
basic_collection_setup(collection_name=collection_name, on_disk_vectors=on_disk_vectors)
|
|
yield
|
|
drop_collection(collection_name=collection_name)
|
|
|
|
|
|
def test_delete_points():
|
|
# delete point by filter (has_id)
|
|
response = request_with_validation(
|
|
api='/collections/{collection_name}/points/delete',
|
|
method="POST",
|
|
path_params={'collection_name': collection_name},
|
|
query_params={'wait': 'true'},
|
|
body={
|
|
"filter": {
|
|
"must": [
|
|
{"has_id": [5]}
|
|
]
|
|
}
|
|
}
|
|
)
|
|
assert response.ok
|
|
|
|
# quantity check if the above point id was deleted
|
|
response = request_with_validation(
|
|
api='/collections/{collection_name}',
|
|
method="GET",
|
|
path_params={'collection_name': collection_name},
|
|
)
|
|
assert response.ok
|
|
assert response.json()['result']['points_count'] == 7
|
|
assert response.json()['result']['vectors_count'] == 8 # We don't propagate deletes to vectors at this time
|
|
|
|
response = request_with_validation(
|
|
api='/collections/{collection_name}/points/delete',
|
|
method="POST",
|
|
path_params={'collection_name': collection_name},
|
|
query_params={'wait': 'true'},
|
|
body={
|
|
"points": [1, 2, 3, 4]
|
|
}
|
|
)
|
|
assert response.ok
|
|
|
|
# quantity check if the above point id was deleted
|
|
response = request_with_validation(
|
|
api='/collections/{collection_name}',
|
|
method="GET",
|
|
path_params={'collection_name': collection_name},
|
|
)
|
|
assert response.ok
|
|
assert response.json()['result']['points_count'] == 3
|
|
assert response.json()['result']['vectors_count'] == 8
|