data-plane-api/envoy/api/v2/cluster/outlier_detection.proto

syntax = "proto3";

package envoy.api.v2.cluster;

import "google/protobuf/duration.proto";
import "google/protobuf/wrappers.proto";

import "validate/validate.proto";
import "gogoproto/gogo.proto";

option (gogoproto.equal_all) = true;

// [#protodoc-title: Outlier detection]

// See the :ref:`architecture overview <arch_overview_outlier_detection>` for
// more information on outlier detection.
message OutlierDetection {
  // The number of consecutive 5xx responses before a consecutive 5xx ejection
  // occurs. Defaults to 5.
  google.protobuf.UInt32Value consecutive_5xx = 1;

  // The time interval between ejection analysis sweeps. This can result in
  // both new ejections as well as hosts being returned to service. Defaults
  // to 10000ms or 10s.
  google.protobuf.Duration interval = 2 [(validate.rules).duration.gt = {}];

  // The base time that a host is ejected for. The real time is equal to the
  // base time multiplied by the number of times the host has been ejected.
  // Defaults to 30000ms or 30s.
  google.protobuf.Duration base_ejection_time = 3 [(validate.rules).duration.gt = {}];

  // The maximum % of an upstream cluster that can be ejected due to outlier
  // detection. Defaults to 10% but will eject at least one host regardless of the value.
  google.protobuf.UInt32Value max_ejection_percent = 4 [(validate.rules).uint32.lte = 100];

  // The % chance that a host will be actually ejected when an outlier status
  // is detected through consecutive 5xx. This setting can be used to disable
  // ejection or to ramp it up slowly. Defaults to 100.
  google.protobuf.UInt32Value enforcing_consecutive_5xx = 5 [(validate.rules).uint32.lte = 100];

  // The % chance that a host will be actually ejected when an outlier status
  // is detected through success rate statistics. This setting can be used to
  // disable ejection or to ramp it up slowly. Defaults to 100.
  google.protobuf.UInt32Value enforcing_success_rate = 6 [(validate.rules).uint32.lte = 100];

  // The number of hosts in a cluster that must have enough request volume to
  // detect success rate outliers. If the number of hosts is less than this
  // setting, outlier detection via success rate statistics is not performed
  // for any host in the cluster. Defaults to 5.
  google.protobuf.UInt32Value success_rate_minimum_hosts = 7;

  // The minimum number of total requests that must be collected in one
  // interval (as defined by the interval duration above) to include this host
  // in success rate based outlier detection. If the volume is lower than this
  // setting, outlier detection via success rate statistics is not performed
  // for that host. Defaults to 100.
  google.protobuf.UInt32Value success_rate_request_volume = 8;

  // This factor is used to determine the ejection threshold for success rate
  // outlier ejection. The ejection threshold is the difference between the
  // mean success rate, and the product of this factor and the standard
  // deviation of the mean success rate: mean - (stdev *
  // success_rate_stdev_factor). This factor is divided by a thousand to get a
  // double. That is, if the desired factor is 1.9, the runtime value should
  // be 1900. Defaults to 1900.
  google.protobuf.UInt32Value success_rate_stdev_factor = 9;

  // The number of consecutive gateway failures (502, 503, 504 status or
  // connection errors that are mapped to one of those status codes) before a
  // consecutive gateway failure ejection occurs. Defaults to 5.
  google.protobuf.UInt32Value consecutive_gateway_failure = 10;

  // The % chance that a host will be actually ejected when an outlier status
  // is detected through consecutive gateway failures. This setting can be
  // used to disable ejection or to ramp it up slowly. Defaults to 0.
  google.protobuf.UInt32Value enforcing_consecutive_gateway_failure = 11
      [(validate.rules).uint32.lte = 100];
}