perf(api): add multi-column GIN index on findings array fields (#11001)

This commit is contained in:
Josema Camacho
2026-05-12 11:45:16 +02:00
committed by GitHub
parent 80482da1cb
commit 6dfa135755
4 changed files with 109 additions and 1 deletions
+11
View File
@@ -4,6 +4,14 @@ All notable changes to the **Prowler API** are documented in this file.
## [1.27.1] (Prowler v5.26.1)
### 🚀 Added
- GIN index on `findings(categories, resource_services, resource_regions, resource_types)` to speed up `/api/v1/finding-groups` array filters [(#11001)](https://github.com/prowler-cloud/prowler/pull/11001)
### 🔄 Changed
- Remove orphaned `gin_resources_search_idx` declaration from `Resource.Meta.indexes` (DB index dropped in `0072_drop_unused_indexes`) [(#11001)](https://github.com/prowler-cloud/prowler/pull/11001)
### 🐞 Fixed
- `POST /api/v1/scans` was intermittently failing with `Scan matching query does not exist` in the `scan-perform` worker; the Celery task is now published via `transaction.on_commit` so the worker cannot read the Scan before the dispatch-wide transaction commits [(#11122)](https://github.com/prowler-cloud/prowler/pull/11122)
@@ -15,6 +23,9 @@ All notable changes to the **Prowler API** are documented in this file.
### 🚀 Added
- `scan-reset-ephemeral-resources` post-scan task zeroes `failed_findings_count` for resources missing from the latest full-scope scan, keeping ephemeral resources from polluting the Resources page sort [(#10929)](https://github.com/prowler-cloud/prowler/pull/10929)
### 🔄 Changed
- ASD Essential Eight (AWS) compliance framework support [(#10982)](https://github.com/prowler-cloud/prowler/pull/10982)
### 🔐 Security
@@ -0,0 +1,31 @@
from functools import partial
from django.db import migrations
from api.db_utils import create_index_on_partitions, drop_index_on_partitions
class Migration(migrations.Migration):
atomic = False
dependencies = [
("api", "0090_attack_paths_cleanup_priority"),
]
operations = [
migrations.RunPython(
partial(
create_index_on_partitions,
parent_table="findings",
index_name="gin_find_arrays_idx",
columns="categories, resource_services, resource_regions, resource_types",
method="GIN",
all_partitions=True,
),
reverse_code=partial(
drop_index_on_partitions,
parent_table="findings",
index_name="gin_find_arrays_idx",
),
)
]
@@ -0,0 +1,58 @@
import django.contrib.postgres.indexes
from django.db import migrations
INDEX_NAME = "gin_find_arrays_idx"
PARENT_TABLE = "findings"
def create_parent_and_attach(apps, schema_editor):
with schema_editor.connection.cursor() as cursor:
cursor.execute(
f"CREATE INDEX {INDEX_NAME} ON ONLY {PARENT_TABLE} "
f"USING gin (categories, resource_services, resource_regions, resource_types)"
)
cursor.execute(
"SELECT inhrelid::regclass::text "
"FROM pg_inherits "
"WHERE inhparent = %s::regclass",
[PARENT_TABLE],
)
for (partition,) in cursor.fetchall():
child_idx = f"{partition.replace('.', '_')}_{INDEX_NAME}"
cursor.execute(f"ALTER INDEX {INDEX_NAME} ATTACH PARTITION {child_idx}")
def drop_parent_index(apps, schema_editor):
with schema_editor.connection.cursor() as cursor:
cursor.execute(f"DROP INDEX IF EXISTS {INDEX_NAME}")
class Migration(migrations.Migration):
dependencies = [
("api", "0091_findings_arrays_gin_index_partitions"),
]
operations = [
migrations.SeparateDatabaseAndState(
state_operations=[
migrations.AddIndex(
model_name="finding",
index=django.contrib.postgres.indexes.GinIndex(
fields=[
"categories",
"resource_services",
"resource_regions",
"resource_types",
],
name=INDEX_NAME,
),
),
],
database_operations=[
migrations.RunPython(
create_parent_and_attach,
reverse_code=drop_parent_index,
),
],
),
]
+9 -1
View File
@@ -946,7 +946,6 @@ class Resource(RowLevelSecurityProtectedModel):
OpClass(Upper("name"), name="gin_trgm_ops"),
name="res_name_trgm_idx",
),
GinIndex(fields=["text_search"], name="gin_resources_search_idx"),
models.Index(fields=["tenant_id", "id"], name="resources_tenant_id_idx"),
models.Index(
fields=["tenant_id", "provider_id"],
@@ -1152,6 +1151,15 @@ class Finding(PostgresPartitionedModel, RowLevelSecurityProtectedModel):
fields=["tenant_id", "scan_id", "check_id"],
name="find_tenant_scan_check_idx",
),
GinIndex(
fields=[
"categories",
"resource_services",
"resource_regions",
"resource_types",
],
name="gin_find_arrays_idx",
),
]
class JSONAPIMeta: