Merge branch 'main' into ksohi/add-mistral-guide

fluxninja · Jan 5, 2024 · 25fe3cd · 25fe3cd
2 parents e0f72a6 + 49006a3
commit 25fe3cd
Show file tree

Hide file tree

Showing 64 changed files with 607 additions and 126 deletions.
diff --git a/api/buf.lock b/api/buf.lock
@@ -9,8 +9,8 @@ deps:
   - remote: buf.build
     owner: envoyproxy
     repository: envoy
-    commit: 5b59168cb47246a3b40d27598b6d5909
-    digest: shake256:e219b11f3e40c9e2956286c5de5d2cb3ea6288228b5f6126be163dbe62b050e7accef81d13e5cf35b447e6903a3f21b82019e676ad8b858ca60c48ca8126e391
+    commit: 39f01805b8754956a78bc77bda4c3761
+    digest: shake256:a7e7c7675618056879597d6205e394e85b63b71fd1766818042e6fd9b5c4fd623bede2784a9c635dced61fb40a22610812f164ed40c7a0cecbe50c0ecc76952d
   - remote: buf.build
     owner: envoyproxy
     repository: protoc-gen-validate

diff --git a/blueprints/concurrency-limiting/base/config.libsonnet b/blueprints/concurrency-limiting/base/config.libsonnet
@@ -13,7 +13,6 @@ commonConfig {
       max_concurrency: '__REQUIRED_FIELD__',
       selectors: commonConfig.selectors_defaults,
       parameters: {
-        limit_by_label_key: 'limit_by_label_key',
         max_inflight_duration: '__REQUIRED_FIELD__',
       },
       request_parameters: {},

diff --git a/blueprints/concurrency-limiting/base/gen/definitions.json b/blueprints/concurrency-limiting/base/gen/definitions.json
@@ -67,7 +67,6 @@
             "parameters": {
               "description": "Parameters.",
               "default": {
-                "limit_by_label_key": "limit_by_label_key",
                 "max_inflight_duration": "__REQUIRED_FIELD__"
               },
               "type": "object",

diff --git a/blueprints/concurrency-limiting/base/gen/values.yaml b/blueprints/concurrency-limiting/base/gen/values.yaml
@@ -29,7 +29,6 @@ policy:
     # Type: aperture.spec.v1.ConcurrencyLimiterParameters
     # Required: True
     parameters:
-      limit_by_label_key: "limit_by_label_key"
       max_inflight_duration: __REQUIRED_FIELD__
     # Request Parameters.
     # Type: aperture.spec.v1.ConcurrencyLimiterRequestParameters

diff --git a/blueprints/concurrency-scheduling/base/config.libsonnet b/blueprints/concurrency-scheduling/base/config.libsonnet
@@ -13,14 +13,9 @@ commonConfig {
       max_concurrency: '__REQUIRED_FIELD__',
       selectors: commonConfig.selectors_defaults,
       concurrency_limiter: {
-        limit_by_label_key: 'limit_by_label_key',
         max_inflight_duration: '__REQUIRED_FIELD__',
       },
-      scheduler: {
-        tokens_label_key: 'tokens',
-        priority_label_key: 'priority',
-        workload_label_key: 'workload',
-      },
+      scheduler: {},
       alerter: {
         alert_name: 'Too many inflight requests',
       },

diff --git a/blueprints/concurrency-scheduling/base/gen/definitions.json b/blueprints/concurrency-scheduling/base/gen/definitions.json
@@ -61,7 +61,6 @@
             "concurrency_limiter": {
               "description": "Concurrency Limiter Parameters.",
               "default": {
-                "limit_by_label_key": "limit_by_label_key",
                 "max_inflight_duration": "__REQUIRED_FIELD__"
               },
               "type": "object",
@@ -75,11 +74,7 @@
             },
             "scheduler": {
               "description": "Scheduler configuration.",
-              "default": {
-                "priority_label_key": "priority",
-                "tokens_label_key": "tokens",
-                "workload_label_key": "workload"
-              },
+              "default": {},
               "type": "object",
               "$ref": "../../../gen/jsonschema/_definitions.json#/definitions/Scheduler"
             },

diff --git a/blueprints/concurrency-scheduling/base/gen/values.yaml b/blueprints/concurrency-scheduling/base/gen/values.yaml
@@ -25,18 +25,14 @@ policy:
     # Type: aperture.spec.v1.ConcurrencyLimiterParameters
     # Required: True
     concurrency_limiter:
-      limit_by_label_key: "limit_by_label_key"
       max_inflight_duration: __REQUIRED_FIELD__
     # Max concurrency.
     # Type: float64
     # Required: True
     max_concurrency: __REQUIRED_FIELD__
     # Scheduler configuration.
     # Type: aperture.spec.v1.Scheduler
-    scheduler:
-      priority_label_key: "priority"
-      tokens_label_key: "tokens"
-      workload_label_key: "workload"
+    scheduler: {}
     # Flow selectors to match requests against.
     # Type: []aperture.spec.v1.Selector
     # Required: True

diff --git a/blueprints/quota-scheduling/base/config.libsonnet b/blueprints/quota-scheduling/base/config.libsonnet
@@ -15,14 +15,9 @@ commonConfig {
       fill_amount: '__REQUIRED_FIELD__',
       selectors: commonConfig.selectors_defaults,
       rate_limiter: {
-        limit_by_label_key: 'limit_key',
         interval: '__REQUIRED_FIELD__',
       },
-      scheduler: {
-        tokens_label_key: 'tokens',
-        priority_label_key: 'priority',
-        workload_label_key: 'workload',
-      },
+      scheduler: {},
       alerter: {
         alert_name: 'More than 90% of requests are being rate limited',
       },

diff --git a/blueprints/quota-scheduling/base/gen/definitions.json b/blueprints/quota-scheduling/base/gen/definitions.json
@@ -78,19 +78,14 @@
             "rate_limiter": {
               "description": "Rate Limiter Parameters.",
               "default": {
-                "interval": "__REQUIRED_FIELD__",
-                "limit_by_label_key": "limit_key"
+                "interval": "__REQUIRED_FIELD__"
               },
               "type": "object",
               "$ref": "../../../gen/jsonschema/_definitions.json#/definitions/RateLimiterParameters"
             },
             "scheduler": {
               "description": "Scheduler configuration.",
-              "default": {
-                "priority_label_key": "priority",
-                "tokens_label_key": "tokens",
-                "workload_label_key": "workload"
-              },
+              "default": {},
               "type": "object",
               "$ref": "../../../gen/jsonschema/_definitions.json#/definitions/Scheduler"
             },

diff --git a/blueprints/quota-scheduling/base/gen/values.yaml b/blueprints/quota-scheduling/base/gen/values.yaml
@@ -34,13 +34,9 @@ policy:
     # Required: True
     rate_limiter:
       interval: __REQUIRED_FIELD__
-      limit_by_label_key: "limit_key"
     # Scheduler configuration.
     # Type: aperture.spec.v1.Scheduler
-    scheduler:
-      priority_label_key: "priority"
-      tokens_label_key: "tokens"
-      workload_label_key: "workload"
+    scheduler: {}
     # Flow selectors to match requests against.
     # Type: []aperture.spec.v1.Selector
     # Required: True

diff --git a/blueprints/rate-limiting/base/config.libsonnet b/blueprints/rate-limiting/base/config.libsonnet
@@ -15,7 +15,6 @@ commonConfig {
       fill_amount: '__REQUIRED_FIELD__',
       selectors: commonConfig.selectors_defaults,
       parameters: {
-        limit_by_label_key: 'limit_key',
         interval: '__REQUIRED_FIELD__',
       },
       request_parameters: {},

diff --git a/blueprints/rate-limiting/base/gen/definitions.json b/blueprints/rate-limiting/base/gen/definitions.json
@@ -78,8 +78,7 @@
             "parameters": {
               "description": "Parameters.",
               "default": {
-                "interval": "__REQUIRED_FIELD__",
-                "limit_by_label_key": "limit_key"
+                "interval": "__REQUIRED_FIELD__"
               },
               "type": "object",
               "$ref": "../../../gen/jsonschema/_definitions.json#/definitions/RateLimiterParameters"

diff --git a/blueprints/rate-limiting/base/gen/values.yaml b/blueprints/rate-limiting/base/gen/values.yaml
@@ -34,7 +34,6 @@ policy:
     # Required: True
     parameters:
       interval: __REQUIRED_FIELD__
-      limit_by_label_key: "limit_key"
     # Request Parameters.
     # Type: aperture.spec.v1.RateLimiterRequestParameters
     request_parameters: {}

diff --git a/...ture-for-infra/guides/api-quota-management/assets/inter-service-rate-limiting/policy.yaml b/...ture-for-infra/guides/api-quota-management/assets/inter-service-rate-limiting/policy.yaml
@@ -26,9 +26,6 @@ spec:
               num_sync: 4
             limit_by_label_key: api_key
           scheduler:
-            priority_label_key: priority
-            tokens_label_key: tokens
-            workload_label_key: workload
             workloads:
             - label_matcher:
                 match_labels:

diff --git a/...tent/guides/assets/concurrency-quota-management/concurrency-scheduling-test.png b/...tent/guides/assets/concurrency-quota-management/concurrency-scheduling-test.png
diff --git a/docs/content/guides/assets/managing-quotas/policy.yaml b/docs/content/guides/assets/managing-quotas/policy.yaml
@@ -24,7 +24,6 @@ spec:
             limit_by_label_key: user_id
           scheduler:
             priority_label_key: priority
-            tokens_label_key: tokens
             workload_label_key: workload
           selectors:
           - control_point: quota-scheduling-feature

diff --git a/docs/content/guides/assets/mistral/graph.mmd.svg b/docs/content/guides/assets/mistral/graph.mmd.svg
diff --git a/docs/content/guides/assets/mistral/policy.yaml b/docs/content/guides/assets/mistral/policy.yaml
@@ -10,7 +10,6 @@ spec:
     - flow_control:
         concurrency_scheduler:
           concurrency_limiter:
-            limit_by_label_key: limit_by_label_key
             max_inflight_duration: 60s
           in_ports:
             max_concurrency:

diff --git a/docs/content/guides/assets/openai/policy.yaml b/docs/content/guides/assets/openai/policy.yaml
@@ -24,8 +24,6 @@ spec:
             limit_by_label_key: api_key
           scheduler:
             priority_label_key: priority
-            tokens_label_key: tokens
-            workload_label_key: workload
           selectors:
           - control_point: openai
             label_matcher:

diff --git a/.../content/guides/assets/per-user-concurrency-limiting/concurrency-limit-test.png b/.../content/guides/assets/per-user-concurrency-limiting/concurrency-limit-test.png
diff --git a/docs/content/guides/assets/per-user-concurrency-limiting/graph.mmd b/docs/content/guides/assets/per-user-concurrency-limiting/graph.mmd
@@ -9,7 +9,7 @@ style root.0_outports fill:none,stroke:none
 root.0accept_percentage[accept_percentage]
 end
 end
-root.0_max_concurrency_FakeConstantout((10.00))
+root.0_max_concurrency_FakeConstantout((20.00))
 subgraph root.1[<center>Decider<br/>gte for 0s</center>]
 subgraph root.1_inports[ ]
 style root.1_inports fill:none,stroke:none

diff --git a/docs/content/guides/assets/per-user-concurrency-limiting/graph.mmd.md5sum b/docs/content/guides/assets/per-user-concurrency-limiting/graph.mmd.md5sum
@@ -1 +1 @@
-20c0f9a2d5725d98bf669184912349d9
+54eafc610acde98b66db3b35e651964a
Original file line number	Diff line number	Diff line change
		@@ -1 +1 @@
		20c0f9a2d5725d98bf669184912349d9
		54eafc610acde98b66db3b35e651964a