feat(loadbalancer): Add LoadBalancerType Client Side Weighted Round Robin #7407
There are no files selected for viewing
| Original file line number | Diff line number | Diff line change |
|---|---|---|
|
|
@@ -11,15 +11,17 @@ import gwapiv1 "sigs.k8s.io/gateway-api/apis/v1" | |
| // +union | ||
| // | ||
| // +kubebuilder:validation:XValidation:rule="self.type == 'ConsistentHash' ? has(self.consistentHash) : !has(self.consistentHash)",message="If LoadBalancer type is consistentHash, consistentHash field needs to be set." | ||
| // +kubebuilder:validation:XValidation:rule="self.type == 'BackendUtilization' ? has(self.backendUtilization) : !has(self.backendUtilization)",message="If LoadBalancer type is BackendUtilization, backendUtilization field needs to be set." | ||
| // +kubebuilder:validation:XValidation:rule="self.type in ['Random', 'ConsistentHash'] ? !has(self.slowStart) : true ",message="Currently SlowStart is only supported for RoundRobin, LeastRequest, and BackendUtilization load balancers." | ||
| // +kubebuilder:validation:XValidation:rule="self.type in ['ConsistentHash', 'BackendUtilization'] ? !has(self.zoneAware) : true ",message="Currently ZoneAware is only supported for LeastRequest, Random, and RoundRobin load balancers." | ||
| type LoadBalancer struct { | ||
| // Type decides the type of Load Balancer policy. | ||
| // Valid LoadBalancerType values are | ||
| // "ConsistentHash", | ||
| // "LeastRequest", | ||
| // "Random", | ||
| // "RoundRobin", | ||
| // "BackendUtilization". | ||
| // | ||
| // +unionDiscriminator | ||
| Type LoadBalancerType `json:"type"` | ||
|
|
@@ -29,6 +31,12 @@ type LoadBalancer struct { | |
| // +optional | ||
| ConsistentHash *ConsistentHash `json:"consistentHash,omitempty"` | ||
|
|
||
| // BackendUtilization defines the configuration when the load balancer type is | ||
| // set to BackendUtilization. | ||
| // | ||
| // +optional | ||
| BackendUtilization *BackendUtilization `json:"backendUtilization,omitempty"` | ||
|
|
||
| // EndpointOverride defines the configuration for endpoint override. | ||
| // When specified, the load balancer will attempt to route requests to endpoints | ||
| // based on the override information extracted from request headers or metadata. | ||
|
|
@@ -39,7 +47,7 @@ type LoadBalancer struct { | |
|
|
||
| // SlowStart defines the configuration related to the slow start load balancer policy. | ||
| // If set, during slow start window, traffic sent to the newly added hosts will gradually increase. | ||
| // Supported for RoundRobin, LeastRequest, and BackendUtilization load balancers. | ||
| // | ||
| // +optional | ||
| SlowStart *SlowStart `json:"slowStart,omitempty"` | ||
|
|
@@ -51,7 +59,7 @@ type LoadBalancer struct { | |
| } | ||
|
|
||
| // LoadBalancerType specifies the types of LoadBalancer. | ||
| // +kubebuilder:validation:Enum=ConsistentHash;LeastRequest;Random;RoundRobin;BackendUtilization | ||
| type LoadBalancerType string | ||
|
|
||
| const ( | ||
|
|
@@ -63,6 +71,8 @@ const ( | |
| RandomLoadBalancerType LoadBalancerType = "Random" | ||
| // RoundRobinLoadBalancerType load balancer policy. | ||
| RoundRobinLoadBalancerType LoadBalancerType = "RoundRobin" | ||
| // BackendUtilizationLoadBalancerType load balancer policy. | ||
| BackendUtilizationLoadBalancerType LoadBalancerType = "BackendUtilization" | ||
| ) | ||
|
|
||
| // ConsistentHash defines the configuration related to the consistent hash | ||
|
|
@@ -148,6 +158,63 @@ type Cookie struct { | |
| Attributes map[string]string `json:"attributes,omitempty"` | ||
| } | ||
|
|
||
| // BackendUtilization defines configuration for Envoy's Backend Utilization policy. | ||
| // It uses Open Resource Cost Application (ORCA) load metrics reported by endpoints to make load balancing decisions. | ||
| // These metrics are typically sent by the backend service in response headers or trailers. | ||
| // | ||
| // The backend should report these metrics in header/trailer as one of the following formats: | ||
| // - Binary: `endpoint-load-metrics-bin` with base64-encoded serialized `OrcaLoadReport` proto. | ||
| // - JSON: `endpoint-load-metrics` with JSON-encoded `OrcaLoadReport` proto, e.g., `JSON {"cpu_utilization": 0.3}`. | ||
| // - TEXT: `endpoint-load-metrics` with comma-separated key-value pairs, e.g., `TEXT cpu=0.3,mem=0.8`. | ||
| // | ||
| // By default, Envoy will forward these ORCA response headers/trailers from the upstream service to the downstream client. | ||
| // If the downstream client also uses this information for load balancing, it might lead to unexpected behavior. | ||
| // To avoid this, you can use the `HTTPRoute` or `BackendTrafficPolicy` to remove the load report headers before sending the response to the client. | ||
altaiezior marked this conversation as resolved.
Show resolved
Hide resolved
|
||
| // | ||
| // See Envoy proto: envoy.extensions.load_balancing_policies.client_side_weighted_round_robin.v3.ClientSideWeightedRoundRobin | ||
|
Contributor
There was a problem hiding this comment. tbh https://www.envoyproxy.io/docs/envoy/latest/api-v3/extensions/load_balancing_policies/client_side_weighted_round_robin/v3/client_side_weighted_round_robin.proto is not descriptive enough, and doesnt mention how this needs to be instrumented in the upstream, are there other links than can be used
Contributor
There was a problem hiding this comment. Yeah the docs aren't great... for example out-of-band reporting isn't supported at all yet reading the docs would indicate otherwise. We could contribute some docs changes upstream but agreed that including a reference to how
Author
There was a problem hiding this comment. @arkodg what changes would you suggest me to add here? This is a bit more elaborative document https://docs.cloud.google.com/load-balancing/docs/https/applb-custom-metrics although this can also be confusing and gcp specific.
Contributor
There was a problem hiding this comment. do any docs exist that explain how a backend / server should be enhanced to send the appropriate trailors in the response ?
Author
There was a problem hiding this comment. There is a google doc I will have to find it though but nothing stated officially as far I am aware of
Contributor
There was a problem hiding this comment. we should consider adding one if it doesnt exist There was a problem hiding this comment. Ack, this is good feedback on the docs gaps. I'll work with @efimki on this.
Contributor
There was a problem hiding this comment. thanks @AndresGuedez ! Happy to be the beta tester
Contributor
There was a problem hiding this comment. This is specific to google but some of their descriptions on ORCA/custom metrics may be helpful for the EG API fields - https://docs.cloud.google.com/load-balancing/docs/https/applb-custom-metrics#configure-custom-metrics That's not an explicit ask to make changes but give this a read. |
||
| // See ORCA Load Report proto: xds.data.orca.v3.orca_load_report.proto | ||
| type BackendUtilization struct { | ||
| // A given endpoint must report load metrics continuously for at least this long before the endpoint weight will be used. | ||
altaiezior marked this conversation as resolved.
Show resolved
Hide resolved
|
||
| // Default is 10s. | ||
| // +optional | ||
| BlackoutPeriod *gwapiv1.Duration `json:"blackoutPeriod,omitempty"` | ||
|
|
||
| // If a given endpoint has not reported load metrics in this long, stop using the reported weight. Defaults to 3m. | ||
| // +optional | ||
| WeightExpirationPeriod *gwapiv1.Duration `json:"weightExpirationPeriod,omitempty"` | ||
|
|
||
| // How often endpoint weights are recalculated. Values less than 100ms are capped at 100ms. Default 1s. | ||
| // +optional | ||
| WeightUpdatePeriod *gwapiv1.Duration `json:"weightUpdatePeriod,omitempty"` | ||
|
|
||
| // ErrorUtilizationPenaltyPercent adjusts endpoint weights based on the error rate (eps/qps). | ||
| // This is expressed as a percentage-based integer where 100 represents 1.0, 150 represents 1.5, etc. | ||
| // | ||
| // For example: | ||
| // - 100 => 1.0x | ||
| // - 120 => 1.2x | ||
| // - 200 => 2.0x | ||
| // | ||
| // Note: In the internal IR/XDS configuration this value is converted back to a | ||
| // floating point multiplier (value / 100.0). | ||
| // | ||
| // Must be non-negative. | ||
| // +kubebuilder:validation:Minimum=0 | ||
| // +optional | ||
| ErrorUtilizationPenaltyPercent *uint32 `json:"errorUtilizationPenaltyPercent,omitempty"` | ||
|
|
||
| // Metric names used to compute utilization if application_utilization is not set. | ||
| // For map fields in ORCA proto, use the form "<map_field>.<key>", e.g., "named_metrics.foo". | ||
| // +optional | ||
| MetricNamesForComputingUtilization []string `json:"metricNamesForComputingUtilization,omitempty"` | ||
|
|
||
| // RemoveResponseHeaders removes the ORCA load report headers/trailers before sending the response to the client. | ||
|
Contributor
There was a problem hiding this comment. if we are removing by default, should we change the field name to
Author
There was a problem hiding this comment. Sure let me know if I have to make the changes, I also forgot to reframe the documentation here
Contributor
There was a problem hiding this comment. yeah prefer |
||
| // Defaults to true. | ||
| // +optional | ||
| // +kubebuilder:default=true | ||
| RemoveResponseHeaders *bool `json:"removeResponseHeaders,omitempty"` | ||
| } | ||
|
|
||
| // ConsistentHashType defines the type of input to hash on. | ||
| // +kubebuilder:validation:Enum=SourceIP;Header;Headers;Cookie;QueryParams | ||
| type ConsistentHashType string | ||
|
|
||
Uh oh!
There was an error while loading. Please reload this page.