Merge pull request #39 from kfswain/gateway-testing

Adding circuit breaker and timeout layers to avoid Gateway 5xx errors.

Author: k8s-ci-robot

pkg/README.md

@@ -1,5 +1,8 @@
 ## Quickstart
 
+### Requirements
+The current manifests rely on Envoy Gateway [v1.2.1](https://gateway.envoyproxy.io/docs/install/install-yaml/#install-with-yaml) or higher.
+
 ### Steps
 
 1. **Deploy Sample vLLM Application**

pkg/manifests/ext_proc.yaml

@@ -61,7 +61,17 @@ spec:
         request:
           body: Buffered
         response:
-      messageTimeout: 5s
+      # The timeouts are likely not needed here. We can experiment with removing/tuning them slowly.
+      # The connection limits are more important and will cause the opaque: ext_proc_gRPC_error_14 error in Envoy GW if not configured correctly. 
+      messageTimeout: 1000s
+      backendSettings:
+        circuitBreaker:
+          maxConnections: 40000
+          maxPendingRequests: 40000
+          maxParallelRequests: 40000 
+        timeout:
+          tcp:
+            connectTimeout: 24h
   targetRef:
     group: gateway.networking.k8s.io
     kind: HTTPRoute

pkg/manifests/gateway.yaml

@@ -44,4 +44,7 @@ spec:
   - backendRefs:
       - group: gateway.envoyproxy.io
         kind: Backend
-        name: backend-dummy
+        name: backend-dummy
+    timeouts:
+      request: "24h"
+      backendRequest: "24h"

pkg/manifests/patch_policy.yaml

@@ -26,9 +26,14 @@ spec:
           original_dst_lb_config:
             use_http_header: true
             http_header_name: "target-pod"
-          connect_timeout: 6s
+          connect_timeout: 1000s
           lb_policy: CLUSTER_PROVIDED
           dns_lookup_family: V4_ONLY
+          circuit_breakers:
+            thresholds:
+            - max_connections: 40000
+              max_pending_requests: 40000
+              max_requests: 40000
 
     - type: "type.googleapis.com/envoy.config.route.v3.RouteConfiguration"
       name: default/<GATEWAY-NAME>/llm-gw

pkg/manifests/traffic_policy.yaml

@@ -0,0 +1,16 @@
+apiVersion: gateway.envoyproxy.io/v1alpha1
+kind: BackendTrafficPolicy
+metadata:
+  name: high-connection-route-policy
+spec:
+  targetRefs:
+  - group: gateway.networking.k8s.io
+    kind: HTTPRoute
+    name: llm-route
+  circuitBreaker:
+    maxConnections: 40000
+    maxPendingRequests: 40000
+    maxParallelRequests: 40000 
+  timeout:
+    tcp:
+      connectTimeout: 24h