feat(vpa): add MemoryPerCPURatio alpha feature gate
This commit is contained in:
Jérémy Spriet
jeremy.spriet
parent
0a85516c69
commit
691cb27872
|
|
@ -7,6 +7,7 @@
|
|||
- [CPU Recommendation Rounding](#cpu-recommendation-rounding)
|
||||
- [Memory Recommendation Rounding](#memory-recommendation-rounding)
|
||||
- [In-Place Updates](#in-place-updates-inplaceorrecreate)
|
||||
- [MemoryPerCPU](#memorypercpu-memorypercpuratio)
|
||||
|
||||
## Limits control
|
||||
|
||||
|
|
@ -153,3 +154,52 @@ VPA provides metrics to track in-place update operations:
|
|||
* `vpa_vpas_with_in_place_updatable_pods_total`: Number of VPAs with pods eligible for in-place updates
|
||||
* `vpa_vpas_with_in_place_updated_pods_total`: Number of VPAs with successfully in-place updated pods
|
||||
* `vpa_updater_failed_in_place_update_attempts_total`: Number of failed attempts to update pods in-place.
|
||||
|
||||
## MemoryPerCPU (`MemoryPerCPURatio`)
|
||||
|
||||
> [!WARNING]
|
||||
> FEATURE STATE: VPA v1.5.0 [alpha]
|
||||
|
||||
VPA can enforce a fixed memory-per-CPU ratio in its recommendations.
|
||||
When enabled, the recommender adjusts CPU or memory so that:
|
||||
```
|
||||
memory_bytes = cpu_cores * memoryPerCPU
|
||||
```
|
||||
|
||||
This applies to Target, LowerBound, UpperBound, and UncappedTarget recommendations.
|
||||
|
||||
### Usage
|
||||
|
||||
Enable the feature on the recommender with:
|
||||
```bash
|
||||
--feature-gates=MemoryPerCPURatio=true
|
||||
```
|
||||
|
||||
Then configure the ratio in your VPA object using the memoryPerCPU field, for example:
|
||||
```yaml
|
||||
apiVersion: autoscaling.k8s.io/v1
|
||||
kind: VerticalPodAutoscaler
|
||||
metadata:
|
||||
name: my-app
|
||||
spec:
|
||||
resourcePolicy:
|
||||
containerPolicies:
|
||||
- containerName: app
|
||||
minAllowed:
|
||||
cpu: 1
|
||||
memory: 4Gi
|
||||
maxAllowed:
|
||||
cpu: 4
|
||||
memory: 16Gi
|
||||
controlledResources: ["cpu", "memory"]
|
||||
controlledValues: RequestsAndLimits
|
||||
memoryPerCPU: "4Gi"
|
||||
```
|
||||
|
||||
### Behavior
|
||||
|
||||
* If both CPU and Memory are controlled, VPA enforces the ratio.
|
||||
|
||||
### Limitations
|
||||
|
||||
* If `minAllowed` or `maxAllowed` constraints conflict with the ratio, the constraints take precedence and the ratio may not be respected.
|
||||
|
|
|
|||
|
|
@ -14,7 +14,7 @@ This document is auto-generated from the flag definitions in the VPA admission-c
|
|||
| `address` | string | ":8944" | The address to expose Prometheus metrics. |
|
||||
| `alsologtostderr` | | | log to standard error as well as files (no effect when -logtostderr=true) |
|
||||
| `client-ca-file` | string | "/etc/tls-certs/caCert.pem" | Path to CA PEM file. |
|
||||
| `feature-gates` | mapStringBool | | A set of key=value pairs that describe feature gates for alpha/experimental features. Options are:<br>AllAlpha=true\|false (ALPHA - default=false)<br>AllBeta=true\|false (BETA - default=false)<br>InPlaceOrRecreate=true\|false (BETA - default=true) |
|
||||
| `feature-gates` | mapStringBool | | A set of key=value pairs that describe feature gates for alpha/experimental features. Options are:<br>AllAlpha=true\|false (ALPHA - default=false)<br>AllBeta=true\|false (BETA - default=false)<br>InPlaceOrRecreate=true\|false (BETA - default=true)<br>MemoryPerCPURatio=true\|false (ALPHA - default=false) |
|
||||
| `ignored-vpa-object-namespaces` | string | | A comma-separated list of namespaces to ignore when searching for VPA objects. Leave empty to avoid ignoring any namespaces. These namespaces will not be cleaned by the garbage collector. |
|
||||
| `kube-api-burst` | float | 100 | QPS burst limit when making requests to Kubernetes apiserver |
|
||||
| `kube-api-qps` | float | 50 | QPS limit when making requests to Kubernetes apiserver |
|
||||
|
|
@ -68,7 +68,7 @@ This document is auto-generated from the flag definitions in the VPA recommender
|
|||
| `cpu-integer-post-processor-enabled` | | | Enable the cpu-integer recommendation post processor. The post processor will round up CPU recommendations to a whole CPU for pods which were opted in by setting an appropriate label on VPA object (experimental) |
|
||||
| `external-metrics-cpu-metric` | string | | ALPHA. Metric to use with external metrics provider for CPU usage. |
|
||||
| `external-metrics-memory-metric` | string | | ALPHA. Metric to use with external metrics provider for memory usage. |
|
||||
| `feature-gates` | mapStringBool | | A set of key=value pairs that describe feature gates for alpha/experimental features. Options are:<br>AllAlpha=true\|false (ALPHA - default=false)<br>AllBeta=true\|false (BETA - default=false)<br>InPlaceOrRecreate=true\|false (BETA - default=true) |
|
||||
| `feature-gates` | mapStringBool | | A set of key=value pairs that describe feature gates for alpha/experimental features. Options are:<br>AllAlpha=true\|false (ALPHA - default=false)<br>AllBeta=true\|false (BETA - default=false)<br>InPlaceOrRecreate=true\|false (BETA - default=true)<br>MemoryPerCPURatio=true\|false (ALPHA - default=false) |
|
||||
| `history-length` | string | "8d" | How much time back prometheus have to be queried to get historical metrics |
|
||||
| `history-resolution` | string | "1h" | Resolution at which Prometheus is queried for historical metrics |
|
||||
| `humanize-memory` | | | DEPRECATED: Convert memory values in recommendations to the highest appropriate SI unit with up to 2 decimal places for better readability. This flag is deprecated and will be removed in a future version. Use --round-memory-bytes instead. |
|
||||
|
|
@ -144,7 +144,7 @@ This document is auto-generated from the flag definitions in the VPA updater cod
|
|||
| `eviction-rate-burst` | int | 1 | Burst of pods that can be evicted. |
|
||||
| `eviction-rate-limit` | float | | Number of pods that can be evicted per seconds. A rate limit set to 0 or -1 will disable<br>the rate limiter. (default -1) |
|
||||
| `eviction-tolerance` | float | 0.5 | Fraction of replica count that can be evicted for update, if more than one pod can be evicted. |
|
||||
| `feature-gates` | mapStringBool | | A set of key=value pairs that describe feature gates for alpha/experimental features. Options are:<br>AllAlpha=true\|false (ALPHA - default=false)<br>AllBeta=true\|false (BETA - default=false)<br>InPlaceOrRecreate=true\|false (BETA - default=true) |
|
||||
| `feature-gates` | mapStringBool | | A set of key=value pairs that describe feature gates for alpha/experimental features. Options are:<br>AllAlpha=true\|false (ALPHA - default=false)<br>AllBeta=true\|false (BETA - default=false)<br>InPlaceOrRecreate=true\|false (BETA - default=true)<br>MemoryPerCPURatio=true\|false (ALPHA - default=false) |
|
||||
| `ignored-vpa-object-namespaces` | string | | A comma-separated list of namespaces to ignore when searching for VPA objects. Leave empty to avoid ignoring any namespaces. These namespaces will not be cleaned by the garbage collector. |
|
||||
| `in-recommendation-bounds-eviction-lifetime-threshold` | | 12h0m0s | duration Pods that live for at least that long can be evicted even if their request is within the [MinRecommended...MaxRecommended] range |
|
||||
| `kube-api-burst` | float | 100 | QPS burst limit when making requests to Kubernetes apiserver |
|
||||
|
|
|
|||
|
|
@ -40,6 +40,12 @@ const (
|
|||
// In each feature gate description, you must specify "components".
|
||||
// The feature must be enabled by the --feature-gates argument on each listed component.
|
||||
|
||||
// alpha: v1.5.0
|
||||
// components: recommender
|
||||
|
||||
// MemoryPerCPURatio enables enforcing a fixed memory-per-CPU ratio in recommendations.
|
||||
MemoryPerCPURatio featuregate.Feature = "MemoryPerCPURatio"
|
||||
|
||||
// alpha: v1.4.0
|
||||
// beta: v1.5.0
|
||||
|
||||
|
|
|
|||
|
|
@ -27,6 +27,9 @@ import (
|
|||
|
||||
// Entries are alphabetized.
|
||||
var defaultVersionedFeatureGates = map[featuregate.Feature]featuregate.VersionedSpecs{
|
||||
MemoryPerCPURatio: {
|
||||
{Version: version.MustParse("1.5"), Default: false, PreRelease: featuregate.Alpha},
|
||||
},
|
||||
InPlaceOrRecreate: {
|
||||
{Version: version.MustParse("1.4"), Default: false, PreRelease: featuregate.Alpha},
|
||||
{Version: version.MustParse("1.5"), Default: true, PreRelease: featuregate.Beta},
|
||||
|
|
|
|||
|
|
@ -268,7 +268,10 @@ func run(ctx context.Context, healthCheck *metrics.HealthCheck, commonFlag *comm
|
|||
postProcessors = append(postProcessors, &routines.IntegerCPUPostProcessor{})
|
||||
}
|
||||
|
||||
postProcessors = append(postProcessors, &routines.MemoryPerCPUPostProcessor{})
|
||||
if features.Enabled(features.MemoryPerCPURatio) {
|
||||
postProcessors = append(postProcessors, &routines.MemoryPerCPUPostProcessor{})
|
||||
}
|
||||
|
||||
globalMaxAllowed := initGlobalMaxAllowed()
|
||||
// CappingPostProcessor, should always come in the last position for post-processing
|
||||
postProcessors = append(postProcessors, routines.NewCappingRecommendationProcessor(globalMaxAllowed))
|
||||
|
|
|
|||
Loading…
Reference in New Issue