[Proxy] Litellm add DB metrics to prometheus (#13626)

* Fix - add safe divide by 0 for most places to prevent crash

* feat(prometheus): add new metrics for monitoring pod lock manager and spend update queues

* fix(prometheus): specify type for buffer monitoring metrics in PrometheusMetricLabels

* Revert "Fix - add safe divide by 0 for most places to prevent crash"

This reverts commit 265d40e390.
This commit is contained in:
Jugal D. Bhatt 2025-08-14 16:16:48 -07:00 • committed by GitHub
parent ab8bd70c5e
commit 40550e5b88
No known key found for this signature in database
GPG key ID: B5690EEEBB952194

View file

@ -176,6 +176,11 @@ DEFINED_PROMETHEUS_METRICS = Literal[
"litellm_deployment_failure_responses",
"litellm_deployment_total_requests",
"litellm_deployment_success_responses",
"litellm_pod_lock_manager_size",
"litellm_in_memory_daily_spend_update_queue_size",
"litellm_redis_daily_spend_update_queue_size",
"litellm_in_memory_spend_update_queue_size",
"litellm_redis_spend_update_queue_size",
]
@ -378,6 +383,17 @@ class PrometheusMetricLabels:
litellm_deployment_success_responses = litellm_deployment_total_requests
# Buffer monitoring metrics - these typically don't need additional labels
litellm_pod_lock_manager_size: List[str] = []
litellm_in_memory_daily_spend_update_queue_size: List[str] = []
litellm_redis_daily_spend_update_queue_size: List[str] = []
litellm_in_memory_spend_update_queue_size: List[str] = []
litellm_redis_spend_update_queue_size: List[str] = []
@staticmethod
def get_labels(label_name: DEFINED_PROMETHEUS_METRICS) -> List[str]:
default_labels = getattr(PrometheusMetricLabels, label_name)