http fault: add response rate limit injection (#6267)

Part of envoyproxy/envoy#5942

Signed-off-by: Matt Klein <mklein@lyft.com>

Mirrored from https://github.com/envoyproxy/envoy @ 628d1668d7dc9244e3a8fa3d3fbabca23e92e23d

envoy/config/filter/fault/v2/fault.proto

@@ -42,6 +42,25 @@ message FaultDelay {
         [(validate.rules).duration.gt = {}, (gogoproto.stdduration) = true];
   }
 
-  // The percentage of operations/connection requests on which the delay will be injected.
-  envoy.type.FractionalPercent percentage = 4;
+  // The percentage of operations/connections/requests on which the delay will be injected.
+  type.FractionalPercent percentage = 4;
+}
+
+// Describes a rate limit to be applied.
+message FaultRateLimit {
+  // Describes a fixed/constant rate limit.
+  message FixedLimit {
+    // The limit supplied in KiB/s.
+    uint64 limit_kbps = 1 [(validate.rules).uint64.gte = 1];
+  }
+
+  oneof limit_type {
+    option (validate.required) = true;
+
+    // A fixed rate limit.
+    FixedLimit fixed_limit = 1;
+  }
+
+  // The percentage of operations/connections/requests on which the rate limit will be injected.
+  type.FractionalPercent percentage = 2;
 }

envoy/config/filter/http/fault/v2/fault.proto

@@ -30,13 +30,13 @@ message FaultAbort {
 
   // The percentage of requests/operations/connections that will be aborted with the error code
   // provided.
-  envoy.type.FractionalPercent percentage = 3;
+  type.FractionalPercent percentage = 3;
 }
 
 message HTTPFault {
   // If specified, the filter will inject delays based on the values in the
-  // object. At least *abort* or *delay* must be specified.
-  envoy.config.filter.fault.v2.FaultDelay delay = 1;
+  // object.
+  filter.fault.v2.FaultDelay delay = 1;
 
   // If specified, the filter will abort requests based on the values in
   // the object. At least *abort* or *delay* must be specified.
@@ -79,4 +79,11 @@ message HTTPFault {
   //   limit. It's possible for the number of active faults to rise slightly above the configured
   //   amount due to the implementation details.
   google.protobuf.UInt32Value max_active_faults = 6;
+
+  // The response rate limit to be applied to the response body of the stream.
+  //
+  // .. attention::
+  //  This is a per-stream limit versus a connection level limit. This means that concurrent streams
+  //  will each get an independent limit.
+  filter.fault.v2.FaultRateLimit response_rate_limit = 7;
 }