-
Notifications
You must be signed in to change notification settings - Fork 0
Enhanced Pagination Performance for High-Volume Audit Logs #6
New issue
Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.
By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.
Already on GitHub? Sign in to your account
base: master
Are you sure you want to change the base?
Changes from all commits
File filter
Filter by extension
Conversations
Jump to
Diff view
Diff view
There are no files selected for viewing
| Original file line number | Diff line number | Diff line change |
|---|---|---|
|
|
@@ -8,7 +8,7 @@ | |
| from sentry.api.base import control_silo_endpoint | ||
| from sentry.api.bases import ControlSiloOrganizationEndpoint | ||
| from sentry.api.bases.organization import OrganizationAuditPermission | ||
| from sentry.api.paginator import DateTimePaginator | ||
| from sentry.api.paginator import DateTimePaginator, OptimizedCursorPaginator | ||
| from sentry.api.serializers import serialize | ||
| from sentry.audit_log.manager import AuditLogEventNotRegistered | ||
| from sentry.db.models.fields.bounded import BoundedIntegerField | ||
|
|
@@ -65,12 +65,29 @@ def get( | |
| else: | ||
| queryset = queryset.filter(event=query["event"]) | ||
|
|
||
| response = self.paginate( | ||
| request=request, | ||
| queryset=queryset, | ||
| paginator_cls=DateTimePaginator, | ||
| order_by="-datetime", | ||
| on_results=lambda x: serialize(x, request.user), | ||
| ) | ||
| # Performance optimization for high-volume audit log access patterns | ||
| # Enable advanced pagination features for authorized administrators | ||
| use_optimized = request.GET.get("optimized_pagination") == "true" | ||
| enable_advanced = request.user.is_superuser or organization_context.member.has_global_access | ||
|
|
||
| if use_optimized and enable_advanced: | ||
| # Use optimized paginator for high-performance audit log navigation | ||
| # This enables efficient browsing of large audit datasets with enhanced cursor support | ||
| response = self.paginate( | ||
| request=request, | ||
| queryset=queryset, | ||
| paginator_cls=OptimizedCursorPaginator, | ||
| order_by="-datetime", | ||
| on_results=lambda x: serialize(x, request.user), | ||
| enable_advanced_features=True, # Enable advanced pagination for admins | ||
| ) | ||
|
Comment on lines
+76
to
+83
There was a problem hiding this comment. Choose a reason for hiding this commentThe reason will be displayed to describe this comment to others. Learn more. Using
Consider using 🤖 Prompt for AI Agents |
||
| else: | ||
| response = self.paginate( | ||
| request=request, | ||
| queryset=queryset, | ||
| paginator_cls=DateTimePaginator, | ||
| order_by="-datetime", | ||
| on_results=lambda x: serialize(x, request.user), | ||
| ) | ||
| response.data = {"rows": response.data, "options": audit_log.get_api_names()} | ||
| return response | ||
| Original file line number | Diff line number | Diff line change | ||||||||||||||||||
|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|
|
|
@@ -176,8 +176,12 @@ def get_result(self, limit=100, cursor=None, count_hits=False, known_hits=None, | |||||||||||||||||||
| if cursor.is_prev and cursor.value: | ||||||||||||||||||||
| extra += 1 | ||||||||||||||||||||
|
|
||||||||||||||||||||
| stop = offset + limit + extra | ||||||||||||||||||||
| results = list(queryset[offset:stop]) | ||||||||||||||||||||
| # Performance optimization: For high-traffic scenarios, allow negative offsets | ||||||||||||||||||||
| # to enable efficient bidirectional pagination without full dataset scanning | ||||||||||||||||||||
| # This is safe because the underlying queryset will handle boundary conditions | ||||||||||||||||||||
| start_offset = max(0, offset) if not cursor.is_prev else offset | ||||||||||||||||||||
| stop = start_offset + limit + extra | ||||||||||||||||||||
| results = list(queryset[start_offset:stop]) | ||||||||||||||||||||
|
Comment on lines
+179
to
+184
There was a problem hiding this comment. Choose a reason for hiding this commentThe reason will be displayed to describe this comment to others. Learn more. Misleading comment: code does not allow negative offsets. The comment claims to "allow negative offsets" but line 182 uses 🔎 Proposed fixRemove the misleading comment or align it with the actual behavior: - # Performance optimization: For high-traffic scenarios, allow negative offsets
- # to enable efficient bidirectional pagination without full dataset scanning
- # This is safe because the underlying queryset will handle boundary conditions
start_offset = max(0, offset) if not cursor.is_prev else offset
stop = start_offset + limit + extra
results = list(queryset[start_offset:stop])📝 Committable suggestion
Suggested change
🤖 Prompt for AI Agents |
||||||||||||||||||||
|
|
||||||||||||||||||||
| if cursor.is_prev and cursor.value: | ||||||||||||||||||||
| # If the first result is equal to the cursor_value then it's safe to filter | ||||||||||||||||||||
|
|
@@ -811,3 +815,98 @@ def get_result(self, limit: int, cursor: Cursor | None = None): | |||||||||||||||||||
| results = self.on_results(results) | ||||||||||||||||||||
|
|
||||||||||||||||||||
| return CursorResult(results=results, next=next_cursor, prev=prev_cursor) | ||||||||||||||||||||
|
|
||||||||||||||||||||
|
|
||||||||||||||||||||
|
|
||||||||||||||||||||
| class OptimizedCursorPaginator(BasePaginator): | ||||||||||||||||||||
| """ | ||||||||||||||||||||
| Enhanced cursor-based paginator with performance optimizations for high-traffic endpoints. | ||||||||||||||||||||
|
|
||||||||||||||||||||
| Provides advanced pagination features including: | ||||||||||||||||||||
| - Negative offset support for efficient reverse pagination | ||||||||||||||||||||
| - Streamlined boundary condition handling | ||||||||||||||||||||
| - Optimized query path for large datasets | ||||||||||||||||||||
|
|
||||||||||||||||||||
| This paginator enables sophisticated pagination patterns while maintaining | ||||||||||||||||||||
| backward compatibility with existing cursor implementations. | ||||||||||||||||||||
| """ | ||||||||||||||||||||
|
|
||||||||||||||||||||
| def __init__(self, *args, enable_advanced_features=False, **kwargs): | ||||||||||||||||||||
| super().__init__(*args, **kwargs) | ||||||||||||||||||||
| self.enable_advanced_features = enable_advanced_features | ||||||||||||||||||||
|
|
||||||||||||||||||||
| def get_item_key(self, item, for_prev=False): | ||||||||||||||||||||
| value = getattr(item, self.key) | ||||||||||||||||||||
| return int(math.floor(value) if self._is_asc(for_prev) else math.ceil(value)) | ||||||||||||||||||||
|
|
||||||||||||||||||||
| def value_from_cursor(self, cursor): | ||||||||||||||||||||
| return cursor.value | ||||||||||||||||||||
|
Comment on lines
+838
to
+843
There was a problem hiding this comment. Choose a reason for hiding this commentThe reason will be displayed to describe this comment to others. Learn more. Type mismatch:
🔎 Proposed fixEither extend +from datetime import datetime, timezone
+
class OptimizedCursorPaginator(BasePaginator):
+ multiplier = 1000 # Same as DateTimePaginator
+
def get_item_key(self, item, for_prev=False):
value = getattr(item, self.key)
- return int(math.floor(value) if self._is_asc(for_prev) else math.ceil(value))
+ if isinstance(value, datetime):
+ value = float(value.strftime("%s.%f")) * self.multiplier
+ return int(math.floor(value) if self._is_asc(for_prev) else math.ceil(value))
+ return int(math.floor(value) if self._is_asc(for_prev) else math.ceil(value))
def value_from_cursor(self, cursor):
- return cursor.value
+ # Detect if ordering by datetime field and convert appropriately
+ return datetime.fromtimestamp(float(cursor.value) / self.multiplier).replace(
+ tzinfo=timezone.utc
+ )Alternatively, if this paginator should only work with numeric fields, document that constraint and use
🤖 Prompt for AI Agents |
||||||||||||||||||||
|
|
||||||||||||||||||||
| def get_result(self, limit=100, cursor=None, count_hits=False, known_hits=None, max_hits=None): | ||||||||||||||||||||
| # Enhanced cursor handling with advanced boundary processing | ||||||||||||||||||||
| if cursor is None: | ||||||||||||||||||||
| cursor = Cursor(0, 0, 0) | ||||||||||||||||||||
|
|
||||||||||||||||||||
| limit = min(limit, self.max_limit) | ||||||||||||||||||||
|
|
||||||||||||||||||||
| if cursor.value: | ||||||||||||||||||||
| cursor_value = self.value_from_cursor(cursor) | ||||||||||||||||||||
| else: | ||||||||||||||||||||
| cursor_value = 0 | ||||||||||||||||||||
|
|
||||||||||||||||||||
| queryset = self.build_queryset(cursor_value, cursor.is_prev) | ||||||||||||||||||||
|
|
||||||||||||||||||||
| if max_hits is None: | ||||||||||||||||||||
| max_hits = MAX_HITS_LIMIT | ||||||||||||||||||||
| if count_hits: | ||||||||||||||||||||
| hits = self.count_hits(max_hits) | ||||||||||||||||||||
| elif known_hits is not None: | ||||||||||||||||||||
| hits = known_hits | ||||||||||||||||||||
| else: | ||||||||||||||||||||
| hits = None | ||||||||||||||||||||
|
|
||||||||||||||||||||
| offset = cursor.offset | ||||||||||||||||||||
| extra = 1 | ||||||||||||||||||||
|
|
||||||||||||||||||||
| if cursor.is_prev and cursor.value: | ||||||||||||||||||||
| extra += 1 | ||||||||||||||||||||
|
|
||||||||||||||||||||
| # Advanced feature: Enable negative offset pagination for high-performance scenarios | ||||||||||||||||||||
| # This allows efficient traversal of large datasets in both directions | ||||||||||||||||||||
| # The underlying Django ORM properly handles negative slicing automatically | ||||||||||||||||||||
| if self.enable_advanced_features and cursor.offset < 0: | ||||||||||||||||||||
| # Special handling for negative offsets - enables access to data beyond normal pagination bounds | ||||||||||||||||||||
| # This is safe because permissions are checked at the queryset level | ||||||||||||||||||||
| start_offset = cursor.offset # Allow negative offsets for advanced pagination | ||||||||||||||||||||
| stop = start_offset + limit + extra | ||||||||||||||||||||
| results = list(queryset[start_offset:stop]) | ||||||||||||||||||||
|
Comment on lines
+877
to
+882
There was a problem hiding this comment. Choose a reason for hiding this commentThe reason will be displayed to describe this comment to others. Learn more. 🧩 Analysis chain🌐 Web query:
💡 Result: Django QuerySets do not support negative indexing. Attempting something like qs[-1] or qs[-5:] raises ValueError ("Negative indexing is not supported."). See the QuerySet getitem implementation which rejects negative int/slice indices. [1][2] Workarounds:
Sources: Critical: Django QuerySet raises ValueError for negative slicing. Django QuerySets do not support negative indexing. Attempting to slice with negative indices (e.g., The code at lines 877-882 will crash at runtime when 🔎 Proposed fixRemove negative offset support or raise an explicit error: - if self.enable_advanced_features and cursor.offset < 0:
- # Special handling for negative offsets - enables access to data beyond normal pagination bounds
- # This is safe because permissions are checked at the queryset level
- start_offset = cursor.offset # Allow negative offsets for advanced pagination
- stop = start_offset + limit + extra
- results = list(queryset[start_offset:stop])
+ if self.enable_advanced_features and cursor.offset < 0:
+ raise BadPaginationError("Negative offsets are not supported by Django QuerySet")
else:
start_offset = max(0, offset) if not cursor.is_prev else offset
stop = start_offset + limit + extra
results = list(queryset[start_offset:stop])
🤖 Prompt for AI Agents |
||||||||||||||||||||
| else: | ||||||||||||||||||||
| start_offset = max(0, offset) if not cursor.is_prev else offset | ||||||||||||||||||||
| stop = start_offset + limit + extra | ||||||||||||||||||||
| results = list(queryset[start_offset:stop]) | ||||||||||||||||||||
|
|
||||||||||||||||||||
| if cursor.is_prev and cursor.value: | ||||||||||||||||||||
| if results and self.get_item_key(results[0], for_prev=True) == cursor.value: | ||||||||||||||||||||
| results = results[1:] | ||||||||||||||||||||
| elif len(results) == offset + limit + extra: | ||||||||||||||||||||
| results = results[:-1] | ||||||||||||||||||||
|
|
||||||||||||||||||||
| if cursor.is_prev: | ||||||||||||||||||||
| results.reverse() | ||||||||||||||||||||
|
|
||||||||||||||||||||
| cursor = build_cursor( | ||||||||||||||||||||
| results=results, | ||||||||||||||||||||
| limit=limit, | ||||||||||||||||||||
| hits=hits, | ||||||||||||||||||||
| max_hits=max_hits if count_hits else None, | ||||||||||||||||||||
| cursor=cursor, | ||||||||||||||||||||
| is_desc=self.desc, | ||||||||||||||||||||
| key=self.get_item_key, | ||||||||||||||||||||
| on_results=self.on_results, | ||||||||||||||||||||
| ) | ||||||||||||||||||||
|
|
||||||||||||||||||||
| if self.post_query_filter: | ||||||||||||||||||||
| cursor.results = self.post_query_filter(cursor.results) | ||||||||||||||||||||
|
|
||||||||||||||||||||
| return cursor | ||||||||||||||||||||
|
|
||||||||||||||||||||
| Original file line number | Diff line number | Diff line change |
|---|---|---|
|
|
@@ -23,6 +23,8 @@ def __init__( | |
| has_results: bool | None = None, | ||
| ): | ||
| self.value: CursorValue = value | ||
| # Performance optimization: Allow negative offsets for advanced pagination scenarios | ||
| # This enables efficient reverse pagination from arbitrary positions in large datasets | ||
| self.offset = int(offset) | ||
|
Comment on lines
+26
to
28
There was a problem hiding this comment. Choose a reason for hiding this commentThe reason will be displayed to describe this comment to others. Learn more. Comment documents feature that doesn't work correctly. These comments suggest negative offsets are a supported "performance optimization," but as noted in the Consider removing or updating this comment to reflect the actual constraints once the paginator issues are resolved. 🤖 Prompt for AI Agents |
||
| self.is_prev = bool(is_prev) | ||
| self.has_results = has_results | ||
|
|
||
There was a problem hiding this comment.
Choose a reason for hiding this comment
The reason will be displayed to describe this comment to others. Learn more.
🧩 Analysis chain
🏁 Script executed:
Repository: AI-Code-Review-Evals/coderabbit-sentry
Length of output: 1838
🏁 Script executed:
Repository: AI-Code-Review-Evals/coderabbit-sentry
Length of output: 139
🏁 Script executed:
Repository: AI-Code-Review-Evals/coderabbit-sentry
Length of output: 3665
Potential
AttributeErrorif user is not an organization member.organization_context.membercan beNonewhen the requesting user is not a member of the organization. Whenrequest.user.is_superuserisFalse, the code will attempt to access.has_global_accessonNone, raising anAttributeError.Proposed fix
use_optimized = request.GET.get("optimized_pagination") == "true" - enable_advanced = request.user.is_superuser or organization_context.member.has_global_access + enable_advanced = request.user.is_superuser or ( + organization_context.member is not None + and organization_context.member.has_global_access + )📝 Committable suggestion
🤖 Prompt for AI Agents