- When the kubelet fails to assign CPUs to a Pod because there less available CPUs than the Pod requests, the error message changed from

- A new kubelet command line option, `--reserved-cpus`, is introduced to explicitly define the CPU list that will be reserved for system. For example, if `--reserved-cpus=0,1,2,3` is specified, then cpu 0,1,2,3 will be reserved for the system.  On a system with 24 CPUs, the user may specify `isolcpus=4-23` for the kernel option and use CPU 4-23 for the user containers. ([#83592](https://github.com/kubernetes/kubernetes/pull/83592), [@jianzzh...

- 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))...

- In the kubelet resource metrics endpoint at /metrics/resource, change the names of the following metrics:
  - node_cpu_usage_seconds --> node_cpu_usage_seconds_total
  - container_cpu_usage_seconds --> container_cpu_usage_seconds_total

* Fixed pod cleanup when /var/lib/kubelet is a symlink. ([#68741](https://github.com/kubernetes/kubernetes/pull/68741), [@jsafrane](https://github.com/jsafrane))
* Add "only_cpu_and_memory" GET parameter to /stats/summary http handler in kubelet. If parameter is true then only cpu and memory will be present in response. ([#67829](https://github.com/kubernetes/kubernetes/pull/67829), [@krzysztof-jastrzebski](https://github.com/krzysztof-jastrzebski))

- Fix a race in the timeout handler that could lead to kube-apiserver crashes ([#108455](https://github.com/kubernetes/kubernetes/pull/108455), [@Argh4k](https://github.com/Argh4k))
- Fix container creation errors for pods with cpu requests bigger than 256 cpus ([#106570](https://github.com/kubernetes/kubernetes/pull/106570), [@odinuge](https://github.com/odinuge))

- Fixed a bug whereby the allocation of reusable CPUs and devices was not being honored when the TopologyManager was enabled ([#93189](https://github.com/kubernetes/kubernetes/pull/93189), [@klueska](https://github.com/klueska)) [SIG Node]

The Resource Management Working Group graduated three features to beta in the 1.10 release.  First, [CPU Manager](https://kubernetes.io/docs/tasks/administer-cluster/cpu-management-policies/), which allows users to request exclusive CPU cores.  This helps performance in a variety of use-cases, including network latency sensitive applications, as well as applications that benefit from CPU cache residency.  Next, [Huge Pages](https://kubernetes.io/docs/tasks/manage-hugepages/scheduling-hugepages/),...

#### **GCP**

*   The service account made available on your nodes is now configurable. ([#52868](https://github.com/kubernetes/kubernetes/pull/52868),[ @ihmccreery](https://github.com/ihmccreery))
*   GCE nodes with NVIDIA GPUs attached now expose nvidia.com/gpu as a resource instead of alpha.kubernetes.io/nvidia-gpu. ([#54826](https://github.com/kubernetes/kubernetes/pull/54826),[ @mindprince](https://github.com/mindprince))

- The CPU Manager will now validate the state of the node,  enabling Kubernetes to maintain the CPU topology even if resources change. ([#66718](https://github.com/kubernetes/kubernetes/pull/66718), [@ipuustin](https://github.com/ipuustin))