Merge branch 'dynamic-loading' of github.com:fastmachinelearning/SuperSONIC into dynamic-loading

Author: kondratyevd

docs/.values-table.md

@@ -34,9 +34,11 @@
 | envoy.rate_limiter.listener_level.max_tokens | int | `5` | Maximum number of simultaneous connections to the Envoy Proxy. Each new connection takes a "token" from the "bucket" which initially contains ``max_tokens`` tokens. |
 | envoy.rate_limiter.listener_level.tokens_per_fill | int | `1` | ``tokens_per_fill`` tokens are added to the "bucket" every ``fill_interval``, allowing new connections to be established. |
 | envoy.rate_limiter.listener_level.fill_interval | string | `"12s"` | For example, adding a new token every 12 seconds allows 5 new connections every minute. |
-| envoy.rate_limiter.prometheus_based | object | `{"enabled":false,"luaConfig":"cfg/envoy-filter.lua"}` | This rate limiter rejects new connections based on metric extracted from Prometheus (e.g. inference queue latency). The metric is taken from parameter ``prometheus.serverLoadMetric``, and the threshold is set by ``prometheus.serverLoadThreshold``. These parameters are the same as those used by the KEDA autoscaler. |
+| envoy.rate_limiter.prometheus_based | object | `{"enabled":false}` | This rate limiter rejects new connections based on metric extracted from Prometheus (e.g. inference queue latency). The metric is taken from parameter ``prometheus.serverLoadMetric``, and the threshold is set by ``prometheus.serverLoadThreshold``. These parameters are the same as those used by the KEDA autoscaler. |
 | envoy.rate_limiter.prometheus_based.enabled | bool | `false` | Enable rate limiter |
 | envoy.loadBalancerPolicy | string | `"LEAST_REQUEST"` | Envoy load balancer policy. Options: ROUND_ROBIN, LEAST_REQUEST, RING_HASH, RANDOM, MAGLEV |
+| envoy.lua_filter.enabled | bool | `false` |  |
+| envoy.lua_filter.lua_config | string | `"cfg/envoy-filter.lua"` |  |
 | envoy.dynamic_routing | object | `{"enabled":false}` | Enable dynamic routing in Envoy proxy. |
 | envoy.auth.enabled | bool | `false` | Enable authentication in Envoy proxy |
 | envoy.auth.jwt_issuer | string | `""` |  |

helm/supersonic/values.schema.json

@@ -370,14 +370,10 @@
               "properties": {
                 "enabled": {
                   "type": "boolean"
-                },
-                "luaConfig": {
-                  "type": "string"
                 }
               },
               "required": [
-                "enabled",
-                "luaConfig"
+                "enabled"
               ]
             }
           },
@@ -389,6 +385,21 @@
         "loadBalancerPolicy": {
           "type": "string"
         },
+        "lua_filter": {
+          "type": "object",
+          "properties": {
+            "enabled": {
+              "type": "boolean"
+            },
+            "lua_config": {
+              "type": "string"
+            }
+          },
+          "required": [
+            "enabled",
+            "lua_config"
+          ]
+        },
         "dynamic_routing": {
           "type": "object",
           "properties": {
@@ -441,6 +452,7 @@
         "image",
         "ingress",
         "loadBalancerPolicy",
+        "lua_filter",
         "rate_limiter",
         "replicas",
         "resources",