From 668dc57e7c06da9b29dd677648fdb198901332a1 Mon Sep 17 00:00:00 2001 From: Boovan Rajendran Date: Mon, 26 Feb 2024 04:40:48 -0500 Subject: [PATCH] kubeadm: create platform pods with zero CPU resources This specifies zero CPU resources when creating the manifests for the static platform pods, as a workaround for the lack of separate resource tracking for platform resources. This specifies zero CPU and Memory resources for the coredns deployment. manifests.go is the main source file for this, not sure if the coredns.yaml are used but they are updated to be consistent. This specifies CPU limit of 1 for kube-apiserver pod so that it is treated as a burstable QoS. This gives a boost of cgroup CPUShares since the burstable cgroup parent has significantly more CPUShares than best-effort on typical systems. This improves kube-apiserver API responsiveness. This increases kube-apiserver Readiness probe periodSeconds to 10 based on WRS/SS joint recommendation for minimum probe settings. This reduces likelihood of kube-apiserver probe failure and subsequent pod-restart under servere load. This also reduces CPU demand. Signed-off-by: Daniel Safta Signed-off-by: Saba Touheed Mujawar Signed-off-by: Boovan Rajendran Signed-off-by: Jim Gauld --- cluster/addons/dns/coredns/coredns.yaml.base | 4 ++-- cluster/addons/dns/coredns/coredns.yaml.in | 4 ++-- cluster/addons/dns/coredns/coredns.yaml.sed | 4 ++-- cmd/kubeadm/app/phases/addons/dns/manifests.go | 4 ++-- .../app/phases/controlplane/manifests.go | 8 +++++--- cmd/kubeadm/app/util/staticpod/utils.go | 17 ++++++++++++++++- 6 files changed, 29 insertions(+), 12 deletions(-) diff --git a/cluster/addons/dns/coredns/coredns.yaml.base b/cluster/addons/dns/coredns/coredns.yaml.base index dd4570adb65..3a0fd7adb72 100644 --- a/cluster/addons/dns/coredns/coredns.yaml.base +++ b/cluster/addons/dns/coredns/coredns.yaml.base @@ -139,8 +139,8 @@ spec: limits: memory: __DNS__MEMORY__LIMIT__ requests: - cpu: 100m - memory: 70Mi + cpu: 0 + memory: 0 args: [ "-conf", "/etc/coredns/Corefile" ] volumeMounts: - name: config-volume diff --git a/cluster/addons/dns/coredns/coredns.yaml.in b/cluster/addons/dns/coredns/coredns.yaml.in index 6939faec3f9..74b59584bc7 100644 --- a/cluster/addons/dns/coredns/coredns.yaml.in +++ b/cluster/addons/dns/coredns/coredns.yaml.in @@ -139,8 +139,8 @@ spec: limits: memory: 'dns_memory_limit' requests: - cpu: 100m - memory: 70Mi + cpu: 0 + memory: 0 args: [ "-conf", "/etc/coredns/Corefile" ] volumeMounts: - name: config-volume diff --git a/cluster/addons/dns/coredns/coredns.yaml.sed b/cluster/addons/dns/coredns/coredns.yaml.sed index a90f2b7674a..61afbecd9da 100644 --- a/cluster/addons/dns/coredns/coredns.yaml.sed +++ b/cluster/addons/dns/coredns/coredns.yaml.sed @@ -139,8 +139,8 @@ spec: limits: memory: $DNS_MEMORY_LIMIT requests: - cpu: 100m - memory: 70Mi + cpu: 0 + memory: 0 args: [ "-conf", "/etc/coredns/Corefile" ] volumeMounts: - name: config-volume diff --git a/cmd/kubeadm/app/phases/addons/dns/manifests.go b/cmd/kubeadm/app/phases/addons/dns/manifests.go index 905a2e050e6..2a2212d5d37 100644 --- a/cmd/kubeadm/app/phases/addons/dns/manifests.go +++ b/cmd/kubeadm/app/phases/addons/dns/manifests.go @@ -104,8 +104,8 @@ spec: limits: memory: 170Mi requests: - cpu: 100m - memory: 70Mi + cpu: 0 + memory: 0 args: [ "-conf", "/etc/coredns/Corefile" ] volumeMounts: - name: config-volume diff --git a/cmd/kubeadm/app/phases/controlplane/manifests.go b/cmd/kubeadm/app/phases/controlplane/manifests.go index 998ca2e3456..7988f1fe918 100644 --- a/cmd/kubeadm/app/phases/controlplane/manifests.go +++ b/cmd/kubeadm/app/phases/controlplane/manifests.go @@ -66,7 +66,9 @@ func GetStaticPodSpecs(cfg *kubeadmapi.ClusterConfiguration, endpoint *kubeadmap LivenessProbe: staticpodutil.LivenessProbe(staticpodutil.GetAPIServerProbeAddress(endpoint), "/livez", endpoint.BindPort, v1.URISchemeHTTPS), ReadinessProbe: staticpodutil.ReadinessProbe(staticpodutil.GetAPIServerProbeAddress(endpoint), "/readyz", endpoint.BindPort, v1.URISchemeHTTPS), StartupProbe: staticpodutil.StartupProbe(staticpodutil.GetAPIServerProbeAddress(endpoint), "/livez", endpoint.BindPort, v1.URISchemeHTTPS, cfg.APIServer.TimeoutForControlPlane), - Resources: staticpodutil.ComponentResources("250m"), + // WRS: Increase kube-apiserver cgroup CPUShares to improve API responsiveness; + // achieved by setting CPU Limits to make it burstable QoS. + Resources: staticpodutil.ComponentLimitResources("0", "1"), Env: kubeadmutil.MergeKubeadmEnvVars(proxyEnvs, cfg.APIServer.ExtraEnvs), }, mounts.GetVolumes(kubeadmconstants.KubeAPIServer), map[string]string{kubeadmconstants.KubeAPIServerAdvertiseAddressEndpointAnnotationKey: endpoint.String()}), @@ -78,7 +80,7 @@ func GetStaticPodSpecs(cfg *kubeadmapi.ClusterConfiguration, endpoint *kubeadmap VolumeMounts: staticpodutil.VolumeMountMapToSlice(mounts.GetVolumeMounts(kubeadmconstants.KubeControllerManager)), LivenessProbe: staticpodutil.LivenessProbe(staticpodutil.GetControllerManagerProbeAddress(cfg), "/healthz", kubeadmconstants.KubeControllerManagerPort, v1.URISchemeHTTPS), StartupProbe: staticpodutil.StartupProbe(staticpodutil.GetControllerManagerProbeAddress(cfg), "/healthz", kubeadmconstants.KubeControllerManagerPort, v1.URISchemeHTTPS, cfg.APIServer.TimeoutForControlPlane), - Resources: staticpodutil.ComponentResources("200m"), + Resources: staticpodutil.ComponentResources("0"), Env: kubeadmutil.MergeKubeadmEnvVars(proxyEnvs, cfg.ControllerManager.ExtraEnvs), }, mounts.GetVolumes(kubeadmconstants.KubeControllerManager), nil), kubeadmconstants.KubeScheduler: staticpodutil.ComponentPod(v1.Container{ @@ -89,7 +91,7 @@ func GetStaticPodSpecs(cfg *kubeadmapi.ClusterConfiguration, endpoint *kubeadmap VolumeMounts: staticpodutil.VolumeMountMapToSlice(mounts.GetVolumeMounts(kubeadmconstants.KubeScheduler)), LivenessProbe: staticpodutil.LivenessProbe(staticpodutil.GetSchedulerProbeAddress(cfg), "/healthz", kubeadmconstants.KubeSchedulerPort, v1.URISchemeHTTPS), StartupProbe: staticpodutil.StartupProbe(staticpodutil.GetSchedulerProbeAddress(cfg), "/healthz", kubeadmconstants.KubeSchedulerPort, v1.URISchemeHTTPS, cfg.APIServer.TimeoutForControlPlane), - Resources: staticpodutil.ComponentResources("100m"), + Resources: staticpodutil.ComponentResources("0"), Env: kubeadmutil.MergeKubeadmEnvVars(proxyEnvs, cfg.Scheduler.ExtraEnvs), }, mounts.GetVolumes(kubeadmconstants.KubeScheduler), nil), } diff --git a/cmd/kubeadm/app/util/staticpod/utils.go b/cmd/kubeadm/app/util/staticpod/utils.go index ea2b13f4b16..6f9afebf348 100644 --- a/cmd/kubeadm/app/util/staticpod/utils.go +++ b/cmd/kubeadm/app/util/staticpod/utils.go @@ -99,6 +99,18 @@ func ComponentResources(cpu string) v1.ResourceRequirements { } } +// ComponentLimitResources returns the v1.ResourceRequirements object needed for allocating a specified amount of the CPU with Limits +func ComponentLimitResources(cpu string, lcpu string) v1.ResourceRequirements { + return v1.ResourceRequirements{ + Requests: v1.ResourceList{ + v1.ResourceCPU: resource.MustParse(cpu), + }, + Limits: v1.ResourceList{ + v1.ResourceCPU: resource.MustParse(lcpu), + }, + } +} + // NewVolume creates a v1.Volume with a hostPath mount to the specified location func NewVolume(name, path string, pathType *v1.HostPathType) v1.Volume { return v1.Volume{ @@ -255,7 +267,10 @@ func LivenessProbe(host, path string, port int32, scheme v1.URIScheme) *v1.Probe func ReadinessProbe(host, path string, port int32, scheme v1.URIScheme) *v1.Probe { // sets initialDelaySeconds as '0' because we don't want to delay user infrastructure checks // looking for "ready" status on kubeadm static Pods - return createHTTPProbe(host, path, port, scheme, 0, 15, 3, 1) + // WRS/SS joint recommendation: All pods probes should have following minimum probe + // settings unless required by the service (initialDelaySecond 0, periodSeconds 10, + // timeoutSeconds 5, successThreshold 1, failureThreshold 3) + return createHTTPProbe(host, path, port, scheme, 0, 15, 3, 10) } // StartupProbe creates a Probe object with a HTTPGet handler -- 2.25.1