- Add a new `distribute-cpus-across-numa` option to the static `CPUManager` policy. When enabled, this will trigger the `CPUManager` to evenly distribute CPUs across NUMA nodes in cases where more than one NUMA node is required to satisfy the allocation. ([#105631](https://github.com/kubernetes/kubernetes/pull/105631), [@klueska](https://github.com/klueska))...

	}
	info := getLocalServerProperty(globalEndpoints, &r, metrics)
	return madminServerProperties.NewJSONWith(&info), nil
}

// GetCPUsHandler - returns CPU info.
func (s *peerRESTServer) GetCPUsHandler(_ *grid.MSS) (*grid.JSON[madmin.CPUs], *grid.RemoteErr) {
	info := madmin.GetCPUs(context.Background(), globalLocalNodeName)
	return madminCPUs.NewJSONWith(&info), nil
}

define_opts = {
  autostart: false
}.freeze

Vagrant.configure(2) do |config|

  config.vm.provider 'virtualbox' do |vbox|
    # Give the box more memory and cpu because our tests are beasts!
    vbox.memory = Integer(ENV['VAGRANT_MEMORY'] || 8192)
    vbox.cpus = Integer(ENV['VAGRANT_CPUS'] || 4)

    # see https://github.com/hashicorp/vagrant/issues/9524
    vbox.customize ["modifyvm", :id, "--audio", "none"]
  end

- Fixes regression in CPUManager that caused freeing of exclusive CPUs at incorrect times ([#90377](https://github.com/kubernetes/kubernetes/pull/90377), [@cbf123](https://github.com/cbf123)) [SIG Cloud Provider and Node]

Wie viele Systemressourcen möchten Sie verbrauchen/nutzen? Sie mögen „nicht viel“ denken, aber in Wirklichkeit möchten Sie tatsächlich **so viel wie möglich ohne Absturz** verwenden.

		if nErr.Err != nil {
			peersLogOnceIf(logger.SetReqInfo(ctx, reqInfo), nErr.Err, nErr.Host.String())
		}
	}
}

// GetCPUs - Get all CPU information.
func (sys *NotificationSys) GetCPUs(ctx context.Context) []madmin.CPUs {
	reply := make([]madmin.CPUs, len(sys.peerClients))

	g := errgroup.WithNErrs(len(sys.peerClients))
	for index, client := range sys.peerClients {
		if client == nil {
			continue
		}

Por otro lado, si tienes 2 servidores y estás usando **100% de su CPU y RAM**, en algún momento un proceso pedirá más memoria y el servidor tendrá que usar el disco como "memoria" (lo cual puede ser miles de veces más lento), o incluso **colapsar**. O un proceso podría necesitar hacer algún cálculo y tendría que esperar hasta que la CPU esté libre de nuevo.

- kubeadm: Implemented preflight check to ensure that number of CPUs ([#70048](https://github.com/kubernetes/kubernetes/pull/70048), [@bart0sh](https://github.com/bart0sh))

- User can choose a different static policy option `SpreadPhysicalCPUsPreferredOption` to spread cpus across physical cpus for some specific applications ([#123733](https://github.com/kubernetes/kubernetes/pull/123733), [@Jeffwan](https://github.com/Jeffwan)) [SIG Node]

- Fixes regression in CPUManager that caused freeing of exclusive CPUs at incorrect times ([#90377](https://github.com/kubernetes/kubernetes/pull/90377), [@cbf123](https://github.com/cbf123)) [SIG Cloud Provider and Node]